Browse Bar: Browse by Author | Browse by Category | Browse by Citation | Advanced Search
Author(s):
Year:
Citation:
Abstract:
Models:
Distributed ART,
Self Organizing Maps,
Author(s):
Year:
Citation:
Abstract:
Topics:
Biological Vision,
Author(s): Carpenter, G.A. | Ravindran, A. |
Year: 2009
Citation: Submitted to Neural Networks
Abstract: CONFIGR-STARS, a new methodology based on a model of the human visual system, is developed for registration of star images. The algorithm first applies CONFIGR, a neural model that connects sparse and noisy image components. CONFIGR produces a web of connections between stars in a reference starmap or in a test patch of unknown location. CONFIGR-STARS splits the resulting, typically highly connected, web into clusters, or “constellations.” Cluster geometry is encoded as a signature vector that records edge lengths and angles relative to the cluster’s baseline edge. The location of a test patch cluster is identified by comparing its signature to signatures in the codebook of a reference starmap, where cluster locations are known. Simulations demonstrate robust performance in spite of image perturbations and omissions, and across starmaps from different sources and seasons. Further studies would test CONFIGR-STARS and algorithm variations applied to very large starmaps.
CONFIGR: A vision-based model for long-range figure completion
CONFIGR (CONtour FIgure GRound) is a computational model based on principles of biological vision that completes sparse and noisy image figures. Within an integrated vision/recognition system, CONFIGR posits an initial ... Article Details
Author(s):
Year:
Citation:
Abstract:
Topics:
Image Analysis,
Author(s): Keskin, G.A. | Ozkan, C. |
Year: 2009
Citation: QUALITY AND RELIABILITY ENGINEERING INTERNATIONAL Volume: 25 Issue: 6 Pages: 647-661
Abstract: Failure Mode and Effects Analysis (F MEA) is a technique used in the manufacturing industry to improve production quality and productivity. It is a method that evaluates possible failures in the system, design, process or service. It aims to continuously improve and decrease these kinds of failure modes. Adaptive Resonance Theory (ART) is one of the learning algorithms without consultants, which are developed for clustering problems in artificial neural networks. In the FMEA method, every failure mode in the system is analyzed according to severity, occurrence and detection. Then, risk priority number (RPN) is acquired by multiplication of these three factors and the necessary failures are improved with respect to the determined threshold value. In addition, there exist many shortcomings of the traditional FMEA method, which affect its efficiency and thus limit its realization. To respond to these difficulties, this study introduces the method named Fuzzy Adaptive Resonance Theory (Fuzzy ART), one of the ART networks, to evaluate RPN in FMEA.
Topics:
Machine Learning,
Applications:
Industrial Control,
Models:
ART 2 / Fuzzy ART,
Author(s): Xu, Z. | Shi, X.J. | Wang, L.Y. | Luo, J. | Zhong, C.J. |
Year: 2009
Citation: SENSORS AND ACTUATORS B-CHEMICAL Volume: 141 Issue: 2 Pages: 458-464
Abstract: A Fuzzy ARTMAP classifier for pattern recognition in chemical sensor array was developed based on Fuzzy Set Theory and Adaptive Resonance Theory. In contrast to most current classifiers with difficulty in detecting new analytes, the Fuzzy ARTMAP system can identify untrained analytes with comparatively high probability. And to detect presence of new analyte, the Fuzzy ARTMAP classifier does not need retraining process that is necessary for most traditional neural network classifiers. In this study, principal component analysis (PCA) was first implemented for feature extraction purpose, followed by pattern recognition using Fuzzy ARTMAP classifiers. To construct the classifier with high recognition rate, parameter sensitive analysis was applied to find critical factors and Pareto optimization was used to locate the optimum parameter setting for the classifier. The test result shows that the proposed method can not only maintain satisfactory correct classification rate for trained analytes, but also be able to detect untrained analytes at a high recognition rate. Also the Pareto optimal values of the most important parameter have been identified, which could help constructing Fuzzy ARTMAP classifiers with good classification performance in future application.
Topics:
Machine Learning,
Applications:
Chemical Analysis,
Models:
Fuzzy ARTMAP,
Author(s): Anton | Rodriguez, M. | Diaz | Pernas, F.J. | Diez | Higuera, J.F. | Martinez | Zarzuela, M. | Gonzalez | Ortega, D. |
Year: 2009
Citation: NEUROCOMPUTING Volume: 72 Issue: 16-18 Special Issue: Sp. Iss. SI Pages: 3713-3725
Abstract: The aim of this paper is to outline a multiple scale neural model to recognise colour images of textured scenes. This model combines colour and textural information in order to recognise colour texture images through the operation of two main components: a segmentation component composed of the colour opponent system (COS) and the chromatic segmentation system (CSS): and a recognition component formed by an ARTMAP-based neural network with scale and orientation-invariance properties. Segmentation is achieved by perceptual contour extraction and diffusion processes on the colour opponent channels based on the human psychophysical theory of colour perception. This colour regions enhancement along with their local textural features constitutes the recognition pattern to be sent to the supervised neural classifier. The CSS accomplishes the colour region enhancement through a multiple scale loop of oriented filters and competition-cooperation mechanisms. Afterwards, the neural architecture performs an attentive recognition of the scene using those oriented filters responses and the chromatic diffusions. Some comparative tests with other models are included in order to prove the recognition capabilities of this neural architecture and how the use of colour information encourages the texture classification and the accuracy of the boundary detection.
Topics:
Image Analysis,
Models:
ARTMAP,
Author(s): Tansel, I.N. | Demetgul, M. | Taskin, S. |
Year: 2009
Citation: EXPERT SYSTEMS WITH APPLICATIONS Volume: 36 Issue: 7 Pages: 10512-10519
Abstract: Pneumatic systems repeat the identical programmed sequence during their operation. The data was collected when the pneumatic system worked perfectly and had some faults including empty magazine, zero vacuum, inappropriate material, no pressure, closed manual pressure valve, missing drilling stroke, poorly located material, not vacuuming the material and low air pressure. The signals of eight sensors were collected during the entire sequence and the 24 most descriptive features of the data were encoded to present to the ANNs. A synthetic data generation process was proposed to train and test the ANNs better when signals are extremely repetitive from one sequence to other. Two artificial neural networks (ANN) were used for interpretation of the encoded signals. The tested ANNs were Adaptive Resonance Theory 2 (ART2), and Back propagation (Bp). ART2 correctly distinguished the perfect and faulty operations at all the tested vigilance values. It classified 11 faulty and 1 normal modes in seven or eight categories at the best vigilance values. Bp also distinguished perfect and faulty operations without even the slightest uncertainty. In less than 10 cases, it had difficulty identifying the 11 types of possible faults. The average estimation error of the Bp was better than 2.1% of the output range on the test data which was created by deviating the encoded values. The ART2 and Bp performance was found excellent with the proposed encoding and synthetic data generation procedures for extremely repetitive sequential data.
Topics:
Machine Learning,
Applications:
Industrial Control,
Models:
ART 2 / Fuzzy ART,
Author(s): Almonacid, M. | Cano-Izquierdo, J.M. | Ibarrola, J. | Pinzolas, M. |
Year: 2009
Citation: NEURAL NETWORKS Volume: 22 Issue: 4 Pages: 479-487
Abstract: The temporal character of the input is, generally, not taken into account in the neural models. This paper presents an extension of the FasArt model focused on the treatment of temporal signals. FasArt model is proposed as an integration of the characteristic elements of the Fuzzy System Theory in an ART architecture. A duality between the activation concept and membership function is established. FasArt maintains the structure of the Fuzzy ARTMAP architecture, implying a static character since the dynamic response of the input is not considered. The proposed novel model, dynamic FasArt (dFasArt), uses dynamic equations for the processing stages of FasArt: activation, matching and learning. The new formulation of dFasArt includes time as another characteristic of the input. This allows the activation of the units to have a history-dependent character instead of being only a function of the last input value. Therefore, dFasArt model is robust to spurious values and noisy inputs. As experimental work, some cases have been used to check the robustness of dFasArt. A possible application has been proposed for the detection of variations in the system dynamics.
Topics:
Machine Learning,
Models:
ART 2 / Fuzzy ART,
Modified ART,
Author(s): Li, H. | Liu, J.F. | Wang, A. | Yu, Z.G. | Yuan, W.J. |
Year: 2009
Citation: COMPUTERS & MATHEMATICS WITH APPLICATIONS Volume: 57 Issue: 11-12 Pages: 1908-1914
Abstract: Based on the principle of one-against-one support vector machines (SVMs) multi-class classification algorithm, this paper proposes an extended SVMs method which couples adaptive resonance theory (ART) network to reconstruct a multi-class classifier. Different coupling strategies to reconstruct a multi-class classifier from binary SVM classifiers are compared with application to fault diagnosis of transmission line. Majority voting, a mixture matrix and self-organizing map (SOM) network are compared in reconstructing the global classification decision. In order to evaluate the method's efficiency, one-against-all, decision directed acyclic graph (DDAG) and decision-tree (DT) algorithm based SVM are compared too. The comparison is done with Simulations and the best method is validated with experimental data.
Topics:
Machine Learning,
Models:
ART 1,
Modified ART,
Self Organizing Maps,
Author(s): Anagnostopoulos, G.C. | Georgiopoulos, M. | Kaylani, A. | Mollaghasemi, M. |
Year: 2009
Citation: NEUROCOMPUTING Volume: 72 Issue: 10-12 Special Issue: Sp. Iss. SI Pages: 2079-2092
Abstract: This paper focuses on classification problems, and in particular on the evolution of ARTMAP architectures using genetic algorithms, with the objective of improving generalization performance and alleviating the adaptive resonance theory (ART) category proliferation problem. In a previous effort, we introduced evolutionary fuzzy ARTMAP (FAM), referred to as genetic Fuzzy ARTMAP (GFAM). In this paper we apply an improved genetic algorithm to FAM and extend these ideas to two other ART architectures; ellipsoidal ARTMAP (EAM) and Gaussian ARTMAP (CAM). One of the major advantages of the proposed improved genetic algorithm is that it adapts the CA parameters automatically, and in a way that takes into consideration the intricacies of the classification problem under consideration. The resulting genetically engineered ART architectures are justifiably referred to as AG-FAM, AG-EAM and AG-GAM or collectively as AG-ART (adaptive genetically engineered ART). We compare the performance (in terms of accuracy, size, and computational cost) of the AG-ART architectures with GFAM, and other ART architectures that have appeared in the literature and attempted to solve the category proliferation problem. Our results demonstrate that AG-ART architectures exhibit better performance than their other ART counterparts (semi-supervised ART) and better performance than GFAM. We also compare AG-ART's performance to other related results published in the classification literature, and demonstrate that AG-ART architectures exhibit competitive generalization performance and, quite often, produce smaller size classifiers in solving the same classification problems. We also show that AG-ART's performance gains are achieved within a reasonable computational budget.
Topics:
Machine Learning,
Models:
ARTMAP,
Fuzzy ARTMAP,
Modified ART,
Genetic Algorithms,
Author(s): Mahapatra, S.S. | Pandian, R.S. |
Year: 2009
Citation: COMPUTERS & INDUSTRIAL ENGINEERING Volume: 56 Issue: 4 Pages: 1340-1347
Abstract: Batch type production strategies need adoption of cellular manufacturing (CM) in order to improve operational effectiveness by reducing manufacturing lead time and costs related to inventory and material handling. CM necessitates that parts are to be grouped into part families based on their similarities in manufacturing and design attributes. Then, machines are allocated into machine cells to produce the identified part families so that productivity and flexibility of the system can be improved. Zero-one part-machine incidence matrix (PMIM) generated from route sheet information is commonly presented as input for clustering of parts and machines. An entry of '1' in PMIM indicates that the part is visiting the machine and zero otherwise. The output is generated in the form of block diagonal structure where each block represents a machine cell having more than one machines and a part family. The major limitations of this approach lies in the fact that important production factors like operation time, sequence of operations, and lot size of the parts are not accounted for. In this paper, an attempt has been made to propose a clustering methodology based on adaptive resonance theory (ART) for addressing these issues. Initially, a methodology considering only the operation sequence of the parts has been proposed. Then, the methodology is suitably modified to deal with combination of operation sequence and operation time of the parts to address generalized cell formation (CF) problem. A new performance measure is proposed to quantify the performance of the proposed methodology. The performance of the proposed algorithm is tested with benchmark problems from open literature and the results are compared with the existing methods. The results clearly indicate that the proposed methodology outperforms the existing methods in most cases.
Topics:
Machine Learning,
Applications:
Industrial Control,
Models:
ART 1,
Author(s): Brannon, N.G. | Draelos, T.J. | Seiffertt, J.E. | Wunsch, D.C. |
Year: 2009
Citation: Neural Networks Volume: 22 Issue: 3, Sp. Iss. SI Pages: 316-325
Abstract: Domains such as force protection require an effective decision maker to maintain a high level of situation awareness. A system that combines humans with neural networks is a desirable approach. Furthermore, it is advantageous for the calculation engine to operate in three learning modes: supervised for initial training and known updating, reinforcement for online operational improvement, and unsupervised in the absence of all external signaling. An Adaptive Resonance Theory based architecture capable of seamlessly switching among the three types of learning is discussed that can be used to help optimize the decision making of a human operator in such a scenario. This is followed by a situation assessment module.
Topics:
Machine Learning,
Applications:
Industrial Control,
Information Fusion,
Models:
ARTMAP,
Modified ART,
Author(s): Chen, S.W. | Fang, C.Y. | Cherng, S. |
Year: 2009
Citation: IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS Volume: 10 Issue: 1 Pages: 70-82
Abstract: Driving always involves risk. Various means have been proposed to reduce the risk. Critical motion detection of nearby moving vehicles is one of the important means of preventing accidents. In this paper, a computational model, which is referred to as the dynamic visual model (DVM), is proposed to detect critical motions of nearby vehicles while driving on a highway. The DVM is motivated by the human visual system and consists of three analyzers: 1) sensory analyzers, 2) perceptual analyzers, and 3) conceptual analyzers. In addition, a memory, which is called the episodic memory, is incorporated, through which a number of features of the system, including hierarchical processing, configurability, adaptive response, and selective attention, are realized. A series of experimental results with both single and multiple critical motions are demonstrated and show the feasibility of the proposed system.
Topics:
Biological Vision,
Image Analysis,
Applications:
Industrial Control,
Models:
ART 2 / Fuzzy ART,
Author(s): Massey, L. |
Year: 2009
Citation: NEURAL COMPUTING & APPLICATIONS Volume: 18 Issue: 3 Pages: 261-273
Abstract: This paper investigates the abilities of adaptive resonance theory (ART) neural networks as miners of hierarchical thematic structure in text collections. We present experimental results with binary ART1 on the benchmark Reuter-21578 corpus. Using both quantitative evaluation with the standard F (1) measure and qualitative visualization of the hierarchy obtained with ART, we discuss how useful ART built hierarchies would be to a user intending to use it as a means to find and access textual information. Our F (1) results show that ART1 produces hierarchical clustering that exhibit a quality exceeding k-means and a hierarchical clustering algorithm. However, we identify several critical problem areas that would make it rather impractical to actually use such a hierarchy in a real-life environment. These predicaments point to the importance of semantic feature selection. Our main contribution is to test in details the applicability of ART to the important domain of hierarchical document clustering, an application of Adaptive Resonance that had received little attention until now.
Topics:
Machine Learning,
Applications:
Information Fusion,
Models:
ART 1,
Author(s): Liu, L. | Huang, L.H. | Lai, M.Y. | Ma, C.Q. |
Year: 2009
Citation: NEUROCOMPUTING Volume: 72 Issue: 4-6 Special Issue: Sp. Iss. SI Pages: 1283-1295
Abstract: Unlike to traditional hierarchical and partitional clustering algorithms which always fail to deal with very large databases, a neural network architecture, projective adaptive resonance theory (PART), is developed for the high dimensional space clustering. However, the success of the PART algorithm depends on both accurate parameters and satisfied orders of input data sets. These disadvantages prevent PART from being applied to realtime databases. In this paper, we propose an improved method, PART with buffer management, to overcome these disadvantages. The major contributions of our method are introducing a buffer management and a new similar degree function and buffer checkout process. The buffer management mechanism allows data sets not to be immediately clustered to one cluster. The purpose of the average similar degree is to successfully work with high similar noise data sets and partly achieve an order-independent objective without correct parameters. And the average similar degree has a good attribute, the parameter-tolerance. Namely, the clustering result does not depend on the precise choice of input parameters, and different parameter values have close clustering results including dimensions associated with clusters. The buffer checkout process call handle a huge amount of input data sets by a small buffer space. Also, simulations and comparisons in high dimensional spaces are reported, and an application by using our algorithm to find stock concurrence association rules is given finally.
Topics:
Machine Learning,
Applications:
Financial Time Series Predictions,
Models:
Modified ART,
Author(s): Grossberg, S. | Mingolla, E. | Fazl, A. |
Year: 2009
Citation: COGNITIVE PSYCHOLOGY Volume: 58 Issue: 1 Pages: 1-48
Abstract: How does the brain learn to recognize an object from multiple viewpoints while scanning a scene with eye movements? How does the brain avoid the problem of erroneously classifying parts of different objects together? How are attention and eye movements intelligently coordinated to facilitate object learning? A neutral model provides- a Unified mechanistic explanation of how spatial and object attention work together to search a scene and learn what is in it. The ARTSCAN model predicts how an object's Surface representation generates a form-fitting distribution of spatial attention, or "attentional shroud". All Surface representations dynamically compete for spatial attention to form a shroud, The winning shroud persists during active scanning of the object. The shroud maintains sustained activity of an emerging view-invariant category representation while multiple view-specific category representations are learned and are linked through associative learning to the view-invariant object category. The shroud also helps to restrict scanning eye movements to salient features on the attended object. Object attention plays a role in controlling and stabilizing the learning of view-specific object categories. Spatial attention hereby coordinates the deployment of object attention during object category learning. Shroud collapse releases a reset signal that inhibits the active view-invariant category in the What cortical processing stream. Then a new shroud, corresponding to a different object, forms in the Where cortical processing stream, and search using attention shifts and eye movements continues to learn new objects throughout a scene. The model mechanistically clarifies basic properties of attention shifts (engage, move, disengage) and inhibition of return. it simulates human reaction time data about object-based spatial attention shifts, and learns with 98.1% accuracy and a compression of 430 on a letter database whose letters vary in size, position, and orientation. The model provides a powerful framework for unifying many data about spatial and object attention, and their interactions during perception, cognition, and action. (C) 2008 Elsevier Inc. All rights reserved.
Topics:
Biological Learning,
Models:
Modified ART,
Author(s): Meuth, R.J. | Robinette, P. |
Year: 2008
Citation: IEEE International Joint Conference on Neural Networks (IJCNN) Vols:1-8 Pages: 686-691
Abstract: The NetFlix Prize is a research contest that will award $1 Million to the first group to improve NetFlix's movie recommendation system by 10%. Contestants are given a dataset containing the movie rating histories of customers for movies. From this data, a processing scheme must be developed that can predict how a customer will rate a given movie on a scale of 1 to 5. An architecture is presented that utilizes the Fuzzy-Adaptive Resonance Theory clustering method to create an interesting set of data attributes that are input to a neural network for mapping to a classification.
Topics:
Machine Learning,
Applications:
Information Fusion,
Models:
ART 2 / Fuzzy ART,
Author(s): Lim, C.P. | Lai, W.K. | Loy, C.C. | Tan, C.P. |
Year: 2008
Citation: International Joint Conference on Neural Networks (IJCNN) Pages: 2405-2412
Abstract: This paper presents a Fuzzy ARTMAP (FAM) based modular architecture for multi-class pattern recognition known as Modular Adaptive Resonance Theory Map (MARTMAP). The prediction of class membership is made collectively by combining outputs from multiple novelty detectors. Distance-based familiarity discrimination is introduced to improve the robustness of MARTMAP in the presence of noise. The effectiveness of the proposed architecture is analyzed and compared with ARTMAP-FD network, FAM network, and One-Against-One Support Vector Machine (OAO-SVM). Experimental results show that MARTMAP is able to retain effective familiarity discrimination in noisy environment, and yet less sensitive to class imbalance problem as compared to its counterparts.
Topics:
Machine Learning,
Models:
Fuzzy ARTMAP,
Modified ART,
Author(s): Aguilar, J. | AlDaraiseh, A. | Altamiranda, J. | Hernandez, L. |
Year: 2008
Citation: IEEE International Joint Conference on Neural Networks (IJCNN), VOLS 1-8 Pages: 3407-3411
Abstract: We develop a Data Mining system to assist with the elucidation by graphical means of the biochemical changes in the brains of rodents. Manual analysis of such experiments is increasingly impractical because of the voluminous nature of the data that is generated, and the tedious nature of the analysis means that important information can be missed. For this purpose we are constructing an increasingly sophisticated Data Mining system which contains a number of pre-processing stages and classification via two steps of an Adaptive Resonance Theory Artificial Neural Network. In this paper we describe the system. The focus of our activity Is the study of neurotransmitters: Glutamate and Aspartate and we present an example of how to utilize our Data Mining system for the automated classification of samples that are extracted from the brains of rodents. This methodology should prove equally valuable to other biochemical analysis problems in experimental Physiology.
Topics:
Image Analysis,
Applications:
Biological Classification,
Models:
ART 2 / Fuzzy ART,
Author(s): Abidin, I. Z. | Afifi, A. | Ayatollahi, A. | Raissi, F. |
Year: 2009
Citation: IEICE Electronics Express Vol. 6 , No. 3 pp.148-153
Abstract: Implementation of a correlation-based learning rule, Spike-Timing-Dependent-Plasticity (STDP), for asynchronous neuromorphic networks is demonstrated using `memristive' nanodevice. STDP is performed using locally available information at the specific moment of time, for which mapping to crossbar-based CMOS-Nano architectures, such as CMOS-MOLecular (CMOL), is done rather easily. The learning method is dynamic and online in which the synaptic weights are modified based on neural activity. The performance of the proposed method is analyzed for specifically shaped spikes and simulation results are provided for a synapse with STDP properties.
Topics:
Neural Hardware,
KInNeSS: A modular framework for computational neuroscience
Making use of very detailed neurophysiological, anatomical, and behavioral data to build biologically-realistic computational models of animal behavior is often a difficult task. Until recently, many software packages have ... Article Details
Spikes, synchrony, and attentive learning by laminar thalamocortical circuits
This article develops the Synchronous Matching Adaptive Resonance Theory (SMART) neural model to explain how the brain may coordinate multiple levels of thalamocortical and corticocortical processing to rapidly learn, and ... Article Details
A model of STDP based on spatially and temporally local information: Derivation and combination with gated decay
Temporal relationships between neuronal firing and plasticity have received significant attention in recent decades. Neurophysiological studies have shown the phenomenon of spike-timing-dependent plasticity (STDP). Various ... Article Details
KInNeSS - the KDE Integrated NeuroSimulation Software
KInNeSS is an open source neural simulation software package that allows to design, simulate and analyze the behavior of networks of hundreds to thousands of branched multi-compartmental neurons with biophysical properties ... Software Details
Author(s):
Year:
Citation:
Abstract:
Topics:
Biological Vision,
Image Analysis,
Author(s):
Year:
Citation:
Abstract:
Topics:
Biological Vision,
Image Analysis,
Author(s):
Year:
Citation:
Abstract:
Applications:
Biological Classification,
Character Recognition,
Information Fusion,
Models:
ART 2 / Fuzzy ART,
Author(s):
Year:
Citation:
Abstract:
Topics:
Biological Learning,
Author(s):
Year:
Citation:
Abstract:
Topics:
Other,
Author(s):
Year:
Citation:
Abstract:
Applications:
Utilities,
Author(s):
Year: 2009
Citation: User Guide, SyNAPSE Software Repository, CNS Technology Lab
Abstract: Frequently, a computer program requires input parameters to define a specific application prior to running it. For codes that require few input parameters, the usual method to define these parameters is to store them in a file or through commandline arguments. Upon reading these parameters, the computer code then proceed to perform computations or other types of operations. For codes that require more input parameters -- especially under less straightforward conditions -- a Graphical User Interface (GUI) may be preferable to query the code runner for input parameters at runtime. However, writing a GUI can often be time-consuming and the code developer may not be readily familiar with the knowledge necessary to develop a GUI. With this in mind, the GUI4GUI package (GUI4GUI.zip) is developed to build GUIs automatically based on users providing data that describe the details of the GUI components, such as menus, and their associated actions. The programmer needs no knowledge of MATLAB GUI development fundamentals or usages of GUIDE, the MATLAB GUI development environment. The GUI4GUI package consists of two tiers of GUIs: the main GUI and an optional secondary GUI. We will discuss the main GUI first and defer the discussion of the secondary GUI until later.
Topics:
Other,
Applications:
Other,
Models:
Other,
An Automated Graphical User Interface builder
An Automated Matlab Graphical User Interface builder. For a quick overview on how to use the builder see the tutorial GUI4GUI_for_Dummies.pdf. For more advanced descriptions, and more features see the official GUI4GUI Users ... Software Details
Author(s):
Year:
Citation:
Abstract:
Applications:
Remote Sensing,
Models:
Boundary Contour System,
Author(s):
Year:
Citation:
Abstract:
Models:
Feature filling-in,
Author(s):
Year:
Citation:
Abstract:
Topics:
Machine Learning,
Models:
ARTMAP,
Modified ART,
Author(s):
Year:
Citation:
Abstract:
Topics:
Biological Vision,
Image Analysis,
Models:
Boundary Contour System,
Author(s):
Year:
Citation:
Abstract:
Topics:
Machine Learning,
Applications:
Remote Sensing,
Models:
ARTMAP,
Fuzzy ARTMAP,
Author(s):
Year:
Citation:
Abstract:
Topics:
Biological Learning,
Author(s):
Year:
Citation:
Abstract:
Topics:
Biological Learning,
Author(s): Carpenter, G.A. | Gaddam, C.S. |
Year: 2009
Citation: Technical Report CAS/CNS TR-2009-003
Abstract: Memories in Adaptive Resonance Theory (ART) networks are based on matched patterns that focus attention on those portions of bottom-up inputs that match active top-down expectations. While this learning strategy has proved successful for both brain models and applications, computational examples show that attention to early critical features may later distort memory representations during online fast learning. For supervised learning, biased ARTMAP (bARTMAP) solves the problem of over-emphasis on early critical features by directing attention away from previously attended features after the system makes a predictive error. Small-scale, hand-computed analog and binary examples illustrate key model dynamics. Two-dimensional simulation examples demonstrate the evolution of bARTMAP memories as they are learned online. Benchmark simulations show that featural biasing also improves performance on large-scale examples. One example, which predicts movie genres and is based, in part, on the Netflix Prize database, was developed for this project. Both first principles and consistent performance improvements on all simulation studies suggest that featural biasing should be incorporated by default in all ARTMAP systems. Benchmark datasets and bARTMAP code are available from the CNS Technology Lab Website: http://cns.bu.edu/techlab/.
Topics:
Machine Learning,
Models:
ARTMAP,
Author(s): Amis, G.P. | Carpenter, G.A. |
Year: 2009
Citation: Techical Report CAS/CNS TR-2009-006
Abstract: Computational models of learning typically train on labeled input patterns (supervised learning), unlabeled input patterns (unsupervised learning), or a combination of the two (semi-supervised learning). In each case input patterns have a fixed number of features throughout training and testing. Human and machine learning contexts present additional opportunities for expanding incomplete knowledge from formal training, via self-directed learning that incorporates features not previously experienced. This article defines a new self-supervised learning paradigm to address these richer learning contexts, introducing a new neural network called self-supervised ARTMAP. Self-supervised learning integrates knowledge from a teacher (labeled patterns with some features), knowledge from the environment (unlabeled patterns with more features), and knowledge from internal model activation (self-labeled patterns). Self-supervised ARTMAP learns about novel features from unlabeled patterns without destroying partial knowledge previously acquired from labeled patterns. A category selection function bases system predictions on known features, and distributed network activation scales unlabeled learning to prediction confidence. Slow distributed learning on unlabeled patterns focuses on novel features and confident predictions, defining classification boundaries that were ambiguous in the labeled patterns. Self-supervised ARTMAP improves test accuracy on illustrative low-dimensional problems and on high-dimensional benchmarks. Model code and benchmark data are available from: http://cns.bu.edu/techlab/SSART/.
Topics:
Machine Learning,
Models:
ARTMAP,
Author(s):
Year:
Citation:
Abstract:
Topics:
Biological Vision,
Author(s):
Year:
Citation:
Abstract:
Models:
ART 2 / Fuzzy ART,
Fuzzy ARTMAP,
Author(s): Grossberg, S. | Todorovic, D. |
Year: 1988
Citation: Perception and Psychophysics, 43, 241-277
Abstract: Computer simulations of a neural network model of I-D and 2-D brightness phenomena are presented. The simulations indicate how configural image properties trigger interactions among spatially organized contrastive, boundary segmentation, and filling-in processes to generate emergent percepts. They provide the first unified mechanistic explanation of this set of phenomena, a number of which have received no previous mechanistic explanation. Network interactions between a Boundary Contour (BC) System and a Feature Contour (FC) System comprise the model. The BC System consists of a hierarchy of contrast-sensitive and orientationally tuned interactions, leading to a boundary segmentation. On and off geniculate cells and simple and complex cortical cells are modeled. Output signals from the BC System segmentation generate compartmental boundaries within the FC System. Contrast-sensitive inputs to the FC System generate a lateral filling-in of activation within FC System compartments. The filling-in process is defined by a nonlinear diffusion mechanism. Simulated phenomena include network responses to stimulus distributions that involve combinations of luminance steps, gradients, cusps, and corners of various sizes. These images include impossible staircases, bull s-eyes, nested combinations of luminance profiles, and images viewed under nonuniform illumination conditions. Simulated phenomena include variants of brightness constancy, brightness contrast, brightness assimilation, the Craik-O Brien-Cornsweet effect, the Kofika-Benussi ring, the Kanizsa-Minguzzi anomalous brightness differentiation, the Hermann grid, and a Land Mondrian viewed under constant and gradient illumination that cannot be explained by retinex theory.
Topics:
Biological Vision,
Models:
Boundary Contour System,
Author(s): Ames, H. | Grossberg, S. |
Year: 2008
Citation: The Journal of the Acoustical Society of America 2008;124(6):3918-36.
Abstract: Auditory signals of speech are speaker dependent, but representations of language meaning are speaker independent. The transformation from speaker-dependent to speaker-independent language representations enables speech to be learned and understood from different speakers. A neural model is presented that performs speaker normalization to generate a pitch-independent representation of speech sounds, while also preserving information about speaker identity. This speaker-invariant representation is categorized into unitized speech items, which input to sequential working memories whose distributed patterns can be categorized, or chunked, into syllable and word representations. The proposed model fits into an emerging model of auditory streaming and speech categorization. The auditory streaming and speaker normalization parts of the model both use multiple strip representations and asymmetric competitive circuits, thereby suggesting that these two circuits arose from similar neural designs. The normalized speech items are rapidly categorized and stably remembered by adaptive resonance theory circuits. Simulations use synthesized steady-state vowels from the Peterson and Barney [Peterson, G. E., and Barney, H.L., J. Acoust. Soc. Am. 24, 175-184 (1952).] vowel database and achieve accuracy rates similar to those achieved by human listeners. These results are compared to behavioral data and other speaker normalization models.
Topics:
Speech and Hearing,
Applications:
Human-Machine Interface,
Models:
Fuzzy ARTMAP,
Author(s):
Year:
Citation:
Abstract:
Topics:
Biological Learning,
Biological Vision,
Machine Learning,
Mathematical Foundations of Neural Networks,
Applications:
Biological Classification,
Author(s):
Year:
Citation:
Abstract:
Topics:
Neural Hardware,
Models:
Other,
Author(s): Ames, H. | Gorchetchnikov, A. | Versace, M. |
Year: 2007
Citation: Application Number 11860254: Graphic Processor Based Accelerator System and Method
Abstract:
Application Number 11860254: Graphic Processor Based Accelerator System and Method (U.S. Utility Patent filed on September 24, 2007)
Author(s): Grossberg, S. | Mingolla, E. |
Year: 1989
Citation: U.S. Patent #4,803,736: Neural networks for machine vision
Abstract: U.S. Patent #4,803,736: Neural networks for machine vision. (Filed: July 23, 1987. Issued: February 7, 1989.) Based on Grossberg, S. & Mingolla, E. (1985). Neural dynamics of form perception: Boundary completion, illusory figures, and neon color spreading. Psychological Review, 92, 173-211.
Neural dynamics of form perception: Boundary completion, illusory figures, and neon color spreading
A real-time visual processing theory is used to analyze real and illusory contour formation, contour and brightness interactions, neon color spreading, complementary color induction, and filling-in of discounted illuminants ... Article Details
Author(s): Carpenter, G.A. | Grossberg, S. | Reynolds, J.H. |
Year: 1993
Citation: U.S. Patent No. 5,214,715: Predictive self-organizing neural network
Abstract: U.S. Patent No. 5,214,715: Predictive self-organizing neural network (Filed: January 31, 1991. Issued: May 25, 1993). Based on Carpenter, G.A., Grossberg, S., & Reynolds, J.H. (1991). ARTMAP: Supervised real-time learning and classification of nonstationary data by a self-organizing neural network. Neural Networks, 4, 565-588.
ARTMAP: Supervised real-time learning and classification of nonstationary data by a self-organizing neural network
This article introduces a new neural network architecture, called ARTMAP, that autonomously learns to classify arbitrarily many, arbitrarily ordered vectors into recognition categories based on predictive success. This ... Article Details
Author(s): Carpenter, G.A. | Grossberg, S. |
Year: 1994
Citation: U.S. Patent No. 5,311,601: Pattern recognition system with variable selection weights
Abstract: U.S. Patent No. 5,311,601: Pattern recognition system with variable selection weights (Filed: January 12, 1990. Issued: May 10, 1994). Based on Carpenter, G.A. & Grossberg, S. and Rosen, D.B. (1987). ART 2-A: An adaptive resonance algorithm for rapid category learning and recognition. Neural Networks, 4, 493-504.
ART 2-A: An adaptive resonance algorithm for rapid category learning and recognition
This article introduces Adaptive Resonance Theory 2-A (ART 2-A), an efficient algorithm that emulates the self-organizing pattern recognition and hypothesis testing properties of the ART 2 neural network architecture, but at ... Article Details
Author(s): Carpenter, G.A. | Grossberg, S. | Rosen, D.B. |
Year: 1992
Citation: U.S. Patent No. 5,157,738: Rapid category learning and recognition system
Abstract: U.S. Patent No. 5,157,738: Rapid category learning and recognition system (Filed: December 18, 1990. Issued: October 20, 1992). Based on Carpenter, G.A. & Grossberg, S. (1987). ART 2-A: An adaptive resonance algorithm for rapid category learning and recognition. Neural Networks, 4, 493-504.
ART 2-A: An adaptive resonance algorithm for rapid category learning and recognition
This article introduces Adaptive Resonance Theory 2-A (ART 2-A), an efficient algorithm that emulates the self-organizing pattern recognition and hypothesis testing properties of the ART 2 neural network architecture, but at ... Article Details
Author(s): Carpenter, G.A. | Grossberg, S. |
Year: 1992
Citation: U.S. Patent Nos. 4,914,708 and 5,133,021: System for self-organization of stable category recognition codes for analog patterns
Abstract: U.S. Patent Nos. 4,914,708 and 5,133,021: System for self-organization of stable category recognition codes for analog patterns (Filed: June 19, 1987. Issued: April 3, 1990 and July 21, 1992). Based on Carpenter, G.A. & Grossberg, S. (1987). ART 2: Self-organization of stable category recognition codes for analog input patterns. Applied Optics : Special Issue on Neural Networks, 26, 4919-4930.
ART 2: Self organization of stable category recognition codes for analog input patterns
Adaptive resonance architectures are neural networks that self-organize stable pattern recognition codes in real-time in response to arbitrary sequences of input patterns. This article introduces ART 2, a class of adaptive ... Article Details
Author(s): Carpenter, G.A. | Grossberg, S. |
Year: 1992
Citation: U.S. Patent No. 5,142,590: Pattern recognition system
Abstract: U.S. Patent No. 5,142,590: Pattern recognition system (Filed: November 27, 1985. Issued: August 25, 1992. European Patent No. 0244483, issued July 15, 1992). Based on Carpenter, G.A. & Grossberg, S. (1987). A massively parallel architecture for a self-organizing neural pattern recognition machine. Computer Vision, Graphics, and Image Processing, 37, 54-115.
A massively parallel architecture for a self organizing neural pattern recognition machine
A neural network architecture for the learning of recognition categories is derived. Real-time network dynamics are completely characterized through mathematical analysis and computer simulations. The architecture ... Article Details
Author(s): Grossberg, S. |
Year: 1982
Citation: Journal of Theoretical Neurobiology, 1, 286-369
Abstract: NA
Topics:
Biological Learning,
Models:
Other,
Author(s): Liu, D.R. | Lloyd, S.R. | Pang, Z.Y. |
Year: 2008
Citation: IEEE TRANSACTIONS ON NEURAL NETWORKS Volume: 19 Issue: 2 Pages: 308-318
Abstract: Electroencephalogram (EEG) is able to indicate states of mental activity ranging from concentrated cognitive efforts to sleepiness. Such mental activity can be reflected by EEG energy. In particular, intrusion of EEG theta wave activity into the beta activity of active wakefulness has been interpreted as ensuing sleepiness. Pupil behavior can also provide information regarding alertness. This paper develops an innovative signal classification method that is capable of differentiating subjects with sleep disorders which cause excessive daytime sleepiness (EDS) from normal control subjects who do not have a sleep disorder based on EEG and pupil size. Subjects with sleep disorders include persons with untreated obstructive sleep apnea (OSA) and narcolepsy. The Yoss pupil staging rule is used to scale levels of wakefulness and at the same time theta energy ratios are calculated from the same 2-s sliding windows by Fourier or wavelet transforms. Then, an artificial neural network (NN) of modified adaptive resonance theory (ART2) is utilized to identify the two groups within a combined group of subjects including those with OSA and healthy controls. This grouping from the NN is then compared with the actual diagnostic classification of subjects as OSA or controls and is found to be 91% accurate in differentiating between the two groups. The same algorithm results in 90% correct differentiation between narcoleptic and control subjects.
Topics:
Machine Learning,
Applications:
Medical Diagnosis,
Models:
ART 2 / Fuzzy ART,
ART 2: Self organization of stable category recognition codes for analog input patterns
Adaptive resonance architectures are neural networks that self-organize stable pattern recognition codes in real-time in response to arbitrary sequences of input patterns. This article introduces ART 2, a class of adaptive ... Article Details
Adaptive pattern classification and universal recoding: II Feedback, expectation, olfaction, illusions
Part I of this paper describes a model for the parallel development and adult coding of neural feature detectors. It shows how any set of arbitrary spatial patterns can be recoded, or transformed, into any other spatial ... Article Details
Author(s): Akhbardeh, A. | Junnila, S. | Koivistoinen, T. | Varri, A. |
Year: 2007
Citation: JOURNAL OF MEDICAL SYSTEMS Volume: 31 Issue: 1 Pages: 69-77
Abstract: This paper presents a comparative analysis of novel supervised fuzzy adaptive resonance theory (SF-ART), multilayer perceptron (MLP) and Multi Layer Perceptrons (MLP) neural networks over Ballistocardiogram (BCG) signal recognition. To extract essential features of the BCG signal, we applied Biorthogonal wavelets. SF-ART performs classification on two levels. At first level, pre-classifier which is self-organized fuzzy ART tuned for fast learning classifies the input data roughly to arbitrary (M) classes. At the second level, post-classification level, a special array called Affine Look- up Table (ALT) with M elements stores the labels of corresponding input samples in the address equal to the index of fuzzy ART winner. However, in running (testing) mode, the content of an ALT cell with address equal to the index of fuzzy ART winner output will be read. The read value declares the final class that input data belongs to. In this paper, we used two well-known patterns (IRIS and Vowel data) and a medical application (Ballistocardiogram data) to evaluate and check SF-ART stability, reliability, learning speed and computational load. Initial tests with BCG from six subjects (both healthy and unhealthy people) indicate that the SF-ART is capable to perform with a high classification performance, high learning speed (elapsed time for learning around half second), and very low computational load compared to the well-known neural networks such as MLP which needs minutes to learn the training material. Moreover, to extract essential features of the BCG signal, we applied Biorthogonal wavelets. The applied wavelet transform requires no prior knowledge of the statistical distribution of data samples.
Topics:
Machine Learning,
Applications:
Medical Diagnosis,
Models:
ART 2 / Fuzzy ART,
Fuzzy ARTMAP,
Author(s): Massey, L. |
Year: 2008
Citation: SOFT COMPUTING Volume: 12 Issue: 7 Pages: 657-665
Abstract: Stability and plasticity in learning systems are both equally essential, but achieving stability and plasticity simultaneously is difficult. Adaptive resonance theory (ART) neural networks are known for their plastic and stable learning of categories, hence providing an answer to the so called stability-plasticity dilemma. However, it has been demonstrated recently that contrary to general belief, ART stability is not possible with infinite streaming data. In this paper, we present an improved stabilization strategy for ART neural networks that does not suffer from this problem and that produces a soft-clustering solution as a positive side effect. Experimental results in a task of text clustering demonstrate that the new stabilization strategy works well, but with a slight loss in clustering quality compared to the traditional approach. For real-life intelligent applications in which infinite streaming data is generated, the stable and soft-clustering solution obtained with our approach more than outweighs the small loss in quality.
Topics:
Machine Learning,
Applications:
Other,
Models:
ART 1,
ART 2 / Fuzzy ART,
ART 2-A,
ARTMAP,
Fuzzy ARTMAP,
ARTMAP-FTR: A neural network for fusion target recognition, with application to sonar classification
ART (Adaptive Resonance Theory) neural networks for fast, stable learning and prediction have been applied in a variety of areas. Applications include automatic mapping from satellite remote sensing data, machine tool ... Article Details
Adaptive pattern classification and universal recoding: I Parallel development and coding of neural feature detectors
This paper analyses a model for the parallel development and adult coding of neural feature detectors. The model was introduced in Grossberg (1976). We show how experience can retune feature detectors to respond to a ... Article Details
A Modified Fuzzy ART for Soft Document Clustering
Document clustering is a very useful application in recent days especially with the advent of the World Wide Web. Most of the existing document clustering algorithms either produce clusters of poor quality or are highly ... Article Details
Author(s): Chen, R.C. | Chuang, C.H. |
Year: 2008
Citation: EXPERT SYSTEMS Volume: 25 Issue: 4 Pages: 414-430
Abstract: Research on semantic webs has become increasingly widespread in the computer science community. The core technology of a semantic web is an artefact called an ontology. The major problem in constructing an ontology is the long period of time required. Another problem is the large number of possible meanings for the knowledge in the ontology. In this paper, we present a novel ontology construction based on artificial neural networks and a Bayesian network. First, we collected web pages related to the problem domain using search engines. The system then used the labels of the HTML tags to select keywords, and used WordNet to determine the meaningful keywords, called terms. Next, it calculated the entropy value to determine the weight of the terms. After the above steps, the projective adaptive resonance theory neural network clustered the collected web pages and found the representative term of each cluster of web pages using the entropy value. The system then used a Bayesian network to insert the terms and complete the hierarchy of the ontology. Finally, the system used a resource description framework to store and express the ontology results.
Topics:
Machine Learning,
Applications:
Network Analysis,
Models:
ART 1,
Projective ART for clustering data sets in high dimensional spaces
A new neural network architecture (PART) and the resulting algorithm are proposed to find projected clusters for data sets in high dimensional spaces. The architecture is based on the well known ART developed by Carpenter ... Article Details
ART 2: Self organization of stable category recognition codes for analog input patterns
Adaptive resonance architectures are neural networks that self-organize stable pattern recognition codes in real-time in response to arbitrary sequences of input patterns. This article introduces ART 2, a class of adaptive ... Article Details
The ART of adaptive pattern recognition by a self organizing neural network
The adaptive resonance theory (ART) suggests a solution to the stability-plasticity dilemma facing designers of learning systems, namely how to design a learning system that will remain plastic, or adaptive, in response to ... Article Details
Competitive learning: From interactive activation to adaptive resonance
Functional and mechanistic comparisons are made between several network models of cognitive processing: competitive learning, interactive activation, adaptive resonance, and back propagation. The starting point of this ... Article Details
Author(s): Hsu, C.C. | Huang, Y.P. |
Year: 2008
Citation: EXPERT SYSTEMS WITH APPLICATIONS Volume: 35 Issue: 3 Pages: 1177-1185
Abstract: Clustering is an important function in data mining. Its typical application includes the analysis of consumer s materials. Adaptive resonance theory network (ART) is very popular in the unsupervised neural network. Type I adaptive resonance theory network (ART1) deals with the binary numerical data, whereas type II adaptive resonance theory network (ART2) deals with the general numerical data. Several information systems collect the mixing type attitudes, which included numeric attributes and categorical attributes. However, ART1 and ART2 do not deal with mixed data. If the categorical data attributes are transferred to the binary data format, the binary data do not reflect the similar degree. It influences the Clustering quality. Therefore, this paper proposes a modified adaptive resonance theory network (M-ART) and the conceptual hierarchy tree to solve similar degrees of mixed data. This paper Utilizes artificial simulation materials and collects a piece of actual data about the family income to do experiments. The results show that the M-ART algorithm can process the mixed data and has a great effect on clustering.
Topics:
Machine Learning,
Applications:
Information Fusion,
Models:
ART 1,
ART 2 / Fuzzy ART,
Distributed learning, recognition, and prediction by ART and ARTMAP neural networks
A class of adaptive resonance theory (ART) models for learning, recognition, and prediction with arbitrarily distributed code representations is introduced. Distributed ART neural networks combine the stable fast learning ... Article Details
Normal and amnesic learning, recognition, and memory by a neural model of cortico hippocampal interactions
The processes by which humans and other primates learn to recognize objects have been the subject of many models. Processes such as learning, categorization, attention, memory search, expectation and novelty detection work ... Article Details
ART 2: Self organization of stable category recognition codes for analog input patterns
Adaptive resonance architectures are neural networks that self-organize stable pattern recognition codes in real-time in response to arbitrary sequences of input patterns. This article introduces ART 2, a class of adaptive ... Article Details
Fuzzy ART: Fast stable learning and categorization of analog patterns by an adaptive resonance system
A Fuzzy Adaptive Resonance Theory (ART) model capable of rapid stable learning of recognition categories in response to arbitrary sequences of analog or binary input patterns is described. Fuzzy ART incorporates computations ... Article Details
The link between brain learning, attention, and consciousness
The processes whereby our brains continue to learn about a changing world in a stable fashion throughout life are proposed to lead to conscious experiences. These processes include the learning of top-down expectations, the ... Article Details
How does the cerebral cortex work? Learning, attention and grouping by the laminar circuits of visual cortex
The organization of neocortex into layers is one of its most salient anatomical features. These layers include circuits that form functional columns in cortical maps. A major unsolved problem concerns how bottom-up, ... Article Details
Author(s): Lim, C.P. | Rao, M.V.C. | Tan, S.C. |
Year: 2008
Citation: SOFT COMPUTING Volume: 12 Issue: 8 Pages: 765-775
Abstract: This paper presents a novel conflict-resolving neural network classifier that combines the ordering algorithm, fuzzy ARTMAP (FAM), and the dynamic decay adjustment (DDA) algorithm, into a unified framework. The hybrid classifier, known as Ordered FAMDDA, applies the DDA algorithm to overcome the limitations of FAM and ordered FAM in achieving a good generalization/performance. Prior to network learning, the ordering algorithm is first used to identify a fixed order of training patterns. The main aim is to reduce and/or avoid the formation of overlapping prototypes of different classes in FAM during learning. However, the effectiveness of the ordering algorithm in resolving overlapping prototypes of different classes is compromised when dealing with complex datasets. Ordered FAMDDA not only is able to determine a fixed order of training patterns for yielding good generalization, but also is able to reduce/resolve overlapping regions of different classes in the feature space for minimizing misclassification during the network learning phase. To illustrate the effectiveness of Ordered FAMDDA, a total of ten benchmark datasets are experimented. The results are analyzed and compared with those from FAM and Ordered FAM. The outcomes demonstrate that Ordered FAMDDA, in general, outperforms FAM and Ordered FAM in tackling pattern classification problems.
Topics:
Machine Learning,
Models:
Fuzzy ARTMAP,
ART-EMAP: A neural network architecture for object recognition by evidence accumulation
A new neural network architecture is introduced for the recognition of pattern classes after supervised and unsupervised learning. Applications include spatio-temporal image understanding and prediction and ... Article Details
Distributed ARTMAP: a neural network for fast distributed supervised learning
Distributed coding at the hidden layer of a multi-layer perceptron (MLP) endows the network with memory compression and noise tolerance capabilities. However, an MLP typically requires slow off-line learning to avoid ... Article Details
Fuzzy ARTMAP: A neural network architecture for incremental supervised learning of analog multidimensional maps
A new neural network architecture is introduced for incremental supervised learning of recognition categories and multidimensional maps in response to arbitrary sequences of analog or binary input vectors, which may ... Article Details
An Ordering Algorithm for Pattern Presentation in Fuzzy ARTMAP That Tends to Improve Generalization Performance
In this paper we introduce a procedure, based on the max?min clustering method, that identifies a fixed order of training pattern presentation for fuzzy adaptive resonance theory mapping (ARTMAP). This procedure is referred ... Article Details
A modified fuzzy ARTMAP architecture for the approximation of noisy mappings
A neural architecture, fuzzy ARTMAP, is considered here as an alternative to standard feedforward networks for noisy mapping tasks. It is one of a series of architectures based upon adaptive resonance theory or ART. Like ... Article Details
Author(s): Ng, G.S. | Quek, C. | Razvi, K. | Tan, T.Z. |
Year: 2008
Citation: ARTIFICIAL INTELLIGENCE IN MEDICINE Volume: 43 Issue: 3 Pages: 207-222
Abstract: Early detection is paramount to reduce the high death rate of ovarian cancer. Unfortunately, current detection toot is not sensitive. New techniques such as deoxyribonucleic acid (DNA) micro-array and proteomics data are difficult to analyze due to high dimensionality, whereas conventional methods such as blood test are neither sensitive nor specific. Methods: Thus, a functional model of human pattern recognition known as compte-mentary learning fuzzy neural network (CLFNN) is proposed to aid existing diagnosis methods. In contrast to conventional computational intelligence methods, CLFNN exploits the Lateral inhibition between positive and negative samples. Moreover, it is equipped with autonomous rule generation facility. An example named fuzzy adaptive learning control network with another adaptive resonance theory (FALCON-AART) is used to illustrate the performance of CLFNN. Results: The confluence of CLFNN-micro-array, CLFNN-blood test, and CLFNN-proteo-mics demonstrate good sensitivity and specificity in the experiments. The diagnosis decision is accurate and consistent. CLFNN also outperforms most of the conventional methods. Conclusions: This research work demonstrates that the confluence of CLFNN-DNA micro-array, CLFNN-blood tests, and CLFNN-proteomic test improves the diagnosis accuracy with higher consistency. CLFNN exhibits good performance in ovarian cancer diagnosis in general. Thus, CLFNN is a promising toot for clinical decision support.
Topics:
Machine Learning,
Applications:
Medical Diagnosis,
Models:
Fuzzy ARTMAP,
A novel approach to the derivation of fuzzy membership functions using the Falcon-MART architecture
A fuzzy neural network, Falcon-MART, is proposed in this paper. This is a modification of the original Falcon-ART architecture. Both Falcon-ART and Falcon-MART are fuzzy neural networks that can be used as fuzzy controllers ... Article Details
Author(s): Caudell, T.P. | Wunsch, D.C. | McGann, R.K. | Morris, D.J. |
Year: 1993
Citation: Applied Optics, Vol. 32, Special Issue on Neural Networks
Abstract: We describe a novel adaptive resonance theory (ART) device that is fully optical in the input-output processing path. This device is based on holographic information processing in a photorefractive crystal. This sets up an associative pattern retrieval in a resonating loop that uses angle-multiplexed reference beams for pattern classification. A reset mechanism is used to reject any given beam, permitting an ART search strategy. The design is similar to an existing nonlearning optical associative memory, but ours permits learning and makes use of information that the other device discards. It is a suitable response to the challenges of connectivity, learning, and reset presented by ART architectures. Furthermore, the design includes an efficient mechanism for area normalization of templates. It also permits the user to capitalize on the ability of ART networks to process large patterns. This new device is expected to offer higher information storage density than alternative ART implementations.
Topics:
Neural Hardware,
Models:
Modified ART,
Author(s): Georgiopoulos, M. | Liou, J.J. | Wuerz, D. |
Year: 1994
Citation: INTERNATIONAL JOURNAL OF ELECTRONICS Volume: 74 Issue: 1 Pages: 101-110
Abstract: This paper outlines the design and simulation of an analogue integrated circuit for the adaptive resonanace theory (ART1) neural network. The circuit is designed based on a set of coupled differential equations which describe the behaviour of the neural network and on analogue electronic components such as operational amplifiers. It performs the same functionality as the one-node neural network in the F2 layer of ART1. We have implemented and verified the circuit using a circuit simulator called Pspice run on a SPARC II Sun workstation. Results obtained from circuit simulation compare favourably with those calculated directly from the coupled differential equations. The one-node circuit developed here can be used as a subcircuit for a larger ART1 neural network with an arbitrary number of nodes.
Topics:
Neural Hardware,
Models:
ART 1,
Author(s): Fung, W.K. | Liu, Y.H. |
Year: 2003
Citation: NEURAL NETWORKS Volume: 16 Issue: 10 Pages: 1403-1420
Abstract: Adaptive Resonance Theory (ART) networks are employed in robot behavior learning. Two of the difficulties in online robot behavior learning, namely, (1) exponential memory increases with time, (2) difficulty for operators to specify learning tasks accuracy and control learning attention before learning. In order to remedy the aforementioned difficulties, an adaptive categorization mechanism is introduced in ART networks for perceptual and action patterns categorization in this paper. A game-theoretic formulation of adaptive categorization for ART networks is proposed for vigilance parameter adaptation for category size control on the categories formed. The proposed vigilance parameter update rule can help improving categorization performance in the aspect of category number stability and solve the problem of selecting initial vigilance parameter prior to pattern categorization in traditional ART networks. Behavior learning using physical robot is conducted to demonstrate the effectiveness of the proposed adaptive categorization mechanism in ART networks.
Topics:
Robotics,
Applications:
Other,
Models:
ART 2 / Fuzzy ART,
Author(s): Georgiopoulos, M. | Heileman, G.L. | Ho, C.S. | Liou, J.J. | Christodoulou, C. |
Year: 1994
Citation: INTERNATIONAL JOURNAL OF ELECTRONICS Volume: 76 Issue: 2 Pages: 271-291
Abstract: An analogue circuit implementation is presented for an adaptive resonance theory neural network architecture, called the augmented ART-1 neural network (AARTI-NN). The AARTI-NN is a modification of the popular ARTI-NN, developed by Carpenter and Grossberg, and it exhibits the same behaviour as the ART1-NN. The AART1-NN is a real-time model, and has the ability to classify an arbitrary set of binary input patterns into different clusters. The design of the AARTI-NN circuit is based on a set of coupled nonlinear differential equations that constitute the AARTI-NN model. The circuit is implemented by utilizing analogue electronic components such as operational amplifiers, transistors, capacitors, and resistors. The implemented circuit is verified using the PSpice circuit simulator, running on Sun workstations. Results obtained from the PSpice circuit simulation compare favourably with simulation results produced by solving the differential equations numerically. The prototype system developed here can be used as a building block for larger AARTI-NN architectures, as well as for other types of ART architectures that involve the AARTI-NN model.
Topics:
Neural Hardware,
Models:
ART 1,
Modified ART,
Author(s): Srinivasan, N. | Jouaneh, M. |
Year: 1993
Citation: IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS Volume: 23 Issue: 5 Pages: 1432-1437
Abstract: A novel invariant pattern recognition machine is proposed based on a modified ART architecture. Invariance is achieved by adding a new layer called F23, beyond the F2 layer in the ART architecture. The design of the weight connections between the nodes of the F2 layer and the cells of the F3 layer are similar to the invariance net. Computer simulations show that the model is not only invariant to translations and rotations of 2-D binary images but also noise-tolerant to these transformed images.
Topics:
Machine Learning,
Applications:
Character Recognition,
Models:
ART 1,
Modified ART,
Author(s): Chen, S.J. | Cheng, C.S. |
Year: 1995
Citation: INTERNATIONAL JOURNAL OF PRODUCTION RESEARCH Volume: 33 Issue: 2 Pages: 293-318
Abstract: The Adaptive Resonance Theory (ART) neural network is a novel method for the cell formation problem in group technology (GT). The advantages of using an ART network over other conventional methods are its fast computation and the outstanding ability to handle large scale industrial problems. One weakness of this approach is that the quality of a grouping solution is highly dependent on the initial disposition of the machine-part incidence matrix especially in the presence of bottleneck machines and/or bottleneck parts. The effort of this paper has been aimed at alleviating the above mentioned problem by the introduction of a set of supplementary procedures. The advantages of the supplementary procedures are demonstrated by 40 examples from the literature. The results clearly demonstrate that our algorithm is more reliable and efficient in cases of ill-structured data.
Topics:
Machine Learning,
Applications:
Industrial Control,
Models:
ART 1,
Author(s): Dagli, C.H. | Bahrami, A. | Lynch, M. |
Year: 1995
Citation: INTERNATIONAL JOURNAL OF PRODUCTION RESEARCH Volume: 33 Issue: 2 Pages: 405-426
Abstract: We describe a hybrid intelligent design retrieval and packaging system by utilizing techniques such as fuzzy associative memory, backpropagation neural networks, and adaptive resonance theory. As an illustrative example, a prototype of the proposed system has been developed to intelligently retrieve a design from a standard set of chair designs that can satisfy the required needs. The system then automatically passes the design to an intelligent packaging system which locates the parts needed from a designated area and packages the parts in the packaging area. This novel application of neural networks could establish the basic foundation of a true intelligent manufacturing system.
Topics:
Machine Learning,
Applications:
Industrial Control,
Models:
ART 1,
Author(s): Dagli, C.H. |
Year: 1995
Citation: INTERNATIONAL JOURNAL OF PRODUCTION RESEARCH Volume: 33 Issue: 4 Pages: 893-913
Abstract: The ART1 neural network paradigm employs a heuristic where new vectors are compared with group representative vectors for classification. ART1 is adapted for the cell formation problem by reordering input vectors and by using a better representative vector. This is validated with both test cases studied in literature as well as synthetic matrices. Algorithms for effective use of ART1 are proposed. This approach is observed to produce sufficiently accurate results and is therefore promising in both speed and functionality. For the automatic generation of an optimal family formation solution a decision support system can be integrated with ART1.
Topics:
Machine Learning,
Models:
ART 1,
Author(s): Dimitriadis, Y.A. | Coronado, J.L. |
Year: 1995
Citation: PATTERN RECOGNITION Volume: 28 Issue: 6 Pages: 807-822
Abstract: A new mathematical editor, based on the recognition of run-on discrete handwritten symbols, is proposed. The tested laboratory prototype of the system, modular and adaptable to the user habits and site requirements, uses a natural handwriting interface as well as human gestures. Two methods were used for symbol recognition, namely the state-of-the-art elastic matching algorithm and an Adaptive Resonance Theory neural architecture. The neural solution is proved to be better adapted to the cognitive nature of the problem and faster in both learning and test phases. Finally a novel attribute grammar permits the detection and subsequent correction of errors in the mathematical expressions.
Topics:
Image Analysis,
Applications:
Character Recognition,
Human-Machine Interface,
Models:
ART 2 / Fuzzy ART,
Author(s): Ho, C.S. | Liou, J.J. |
Year: 1995
Citation: INTERNATIONAL JOURNAL OF ELECTRONICS Volume: 79 Issue: 2 Pages: 151-162
Abstract: A digital VLSI circuit design for an adaptive resonance theory (ART) neural network architecture, called the augmented ART-1 neural network (AART1-NN) is presented. An axon-synapse-tree structure is used to realize the activities of the short-term memories and reset subsystem. The long-term memory traces are implemented using NMOS transmission gates. PSpice circuit simulation was carried out to verify the design of a prototype, seven-node AART1-NN. A clock-controlled delay element is included in the simulation to illustrate the functionality of the AART1-NN. It is shown that the AART1-NN node selection activities simulated from the circuit designed are identical to those described by the coupled differential equations governing the AART1-NN.
Topics:
Neural Hardware,
Models:
ART 1,
Modified ART,
Author(s): Chong, C.W. | Hwarng, H.B. |
Year: 1995
Citation: INTERNATIONAL JOURNAL OF PRODUCTION RESEARCH Volume: 33 Issue: 7 Pages: 1817-1833
Abstract: An adaptive resonance theory (ART) based, general-purpose control chart pattern recognizer (CCPR) which is capable of fast and cumulative learning is presented. The implementation of this ART-based CCPR was made possible by introducing two key alternatives, that is, incorporating a synthesis layer in addition to the existing two-layer architecture and adopting a quasi-supervised training strategy. IA detailed algorithm with the training and the testing modes was presented. Extensive simulations and performance evaluations were conducted and proved that this ART-based CCPR indeed possesses the capability of fast and cumulative learning. When compared with a back-propagation pattern recognizer (BPPR), the ART-based CCPR is superior on cyclic patterns, inferior on mixture patterns, and comparable on other patterns. Furthermore, an ART-based CCPR is easier to develop since it needs fewer training templates and takes less time to learn. This study not only provides a basis for understanding the capabilities of ART-based neural networks on control chart pattern recognition but re-confirms the applicability of the neural network approach.
Topics:
Machine Learning,
Models:
ART 1,
Modified ART,
Author(s): McLaughlin, C. | Tansel, I.N. | Mekdeci, C. |
Year: 1995
Citation: INTERNATIONAL JOURNAL OF MACHINE TOOLS & MANUFACTURE Volume: 35 Issue: 8 Pages: 1137-1147
Abstract: Detection of tool failure is very important in automated manufacturing. In this study, tool failure detection was conducted in two steps by using Wavelet Transformations and Neural Networks (WT-NN). In the first step, data were compressed by using wavelet transformations and unnecessary details were eliminated. In the second step, the estimated parameters of the wavelet transformations were classified by using Adaptive Resonance Theory (ART2)-type self-learning neural networks. Wavelet transformations represent transitionary data and complex patterns in a more compact form than time-series methods (frequency and time-domain) by using a family of the most suitable wave forms. Wavelet transformations can also be implemented on parallel processors and require less computations than Fast Fourier Transformation (FFT). The training of ART2-type neural networks is faster than backpropagation-type neural networks and ART2 is capable of updating its experience with the help of an operator while it is monitoring the sensory signals. The proposed approach was tested in over 171 cases and all the presented cases were accurately classified. The proposed system can be easily trained to inspect data during transition and/or any complex cutting conditions. The system will indicate failure instantaneously by creating a new category, thus alerting the operator.
Topics:
Machine Learning,
Applications:
Industrial Control,
Models:
ART 2 / Fuzzy ART,
Author(s): Harrison, R.F. | Marriott, S. |
Year: 1995
Citation: NEURAL NETWORKS Volume: 8 Issue: 4 Pages: 619-641
Abstract: A neural architecture, fuzzy ARTMAP, is considered here as an alternative to standard feedforward networks for noisy mapping tasks. It is one of a series of architectures based upon adaptive resonance theory or ART. Like other ART-based systems, fuzzy ARTMAP has advantages over feedforward networks and is especially suited to classification-type problems. Here it is used to approximate a noisy continuous mapping. Results show that properties that confer useful advantages for classification problems do not necessarily confer similar advantages for noisy mapping problems. One particular feature, match tracking, is found to cause overlearning of the data. A modified variant is proposed, without match tracking, that stores probability information in the map field This information is subsequently used to compute output estimates. The proposed fuzzy ARTMAP variant is found to outperform fuzzy ARTMAP in a mapping task.
Topics:
Machine Learning,
Models:
Fuzzy ARTMAP,
Modified ART,
Author(s): Bartfai, G. |
Year: 1996
Citation: NEURAL NETWORKS Volume: 9 Issue: 2 Pages: 295-308
Abstract: This article analyses the match tracking anomaly (MTA) of the ARTMAP neural network. The anomaly arises when an input pattern exactly matches its category prototype that the network has previously learned, and the network generates a prediction (through a previously learned associative link) that contradicts the output category that was selected upon presentation of the corresponding target output. Carpenter et al. claimed that such an anomalous situation will never arise if the (binary) input vectors have the same number of 1s (Carpenter et al., 1991, Neural Networks, 4, 565-588).
This paper shows that such situations can in fact occur. The timing according to which inputs are presented to the network in each learning trial is crucial. if the target output is presented to the network before the corresponding input pattern, certain pattern sequences will lead the network to the MTA. Two kinds of MTA are distinguished: one that is independent of the choice parameter (beta) of the ART(b) module, and another that is nor. Results of experiments that were carried out on a machine learning database demonstrate the existence of the match tracking anomaly as well as support the analytical results presented here.
Topics:
Machine Learning,
Applications:
Biological Classification,
Models:
ARTMAP,
Author(s): Buydens, L. | Wienke, D. |
Year: 1996
Citation: CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS Volume: 32 Issue: 2 Pages: 151-164
Abstract: The FuzzyARTMAP algorithm is studied with respect to its usefulness for supervised chemical pattern recognition. The theory of this relatively complex artificial neural classifier is presented in detail for chemists. An instructive data set of moderate size, describing male and female participants in courses of chemometrics by their body measures, is used to demonstrate how FuzzyARTMAP works and what its basic properties are.
Topics:
Machine Learning,
Applications:
Chemical Analysis,
Models:
Fuzzy ARTMAP,
Author(s): Buydens, L. | Cammann, K. | Feldhoff, R. | Huth-Fehre, T. | Kantimm, T. | Wienke, D. | van den Broek, W. |
Year: 1996
Citation: CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS Volume: 32 Issue: 2 Pages: 165-176
Abstract: The supervised working FuzzyARTMAP pattern recognition algorithm has been applied to automated identification of post-consumer plastics by near-infrared spectroscopy (NIRS). Experimentally, a remote operating parallel multisensor device, based on a rapid InGaAs diode array detector combined with new collimation optics, has been used. The laboratory setup allows on-line identification of more than 100 spectra per second. Internal parameter settings of FuzzyARTMAP were varied to explore their influence on the classifier s behavior. Discrimination results obtained were better than those from an optimized multilayer feedforward backpropagation artificial neural network (MLF-BP) and significantly better than those provided by the partial least squares method (PLS2). Additional advantages of FuzzyARTMAP compared to these two classifiers are a significantly higher speed of calibration, the chemical interpretability of network weight coefficients and a built-in detector against extrapolations.
Topics:
Machine Learning,
Applications:
Chemical Analysis,
Industrial Control,
Models:
Fuzzy ARTMAP,
Author(s): Ganapathy, C. | Idichandy, V.G. | Mangal, L. |
Year: 1996
Citation: APPLIED OCEAN RESEARCH Volume: 18 Issue: 2-3 Pages: 137-143
Abstract: A novel scheme using artificial neural networks to automate the vibration monitoring method of detecting the occurrence and location of damage in offshore jacket platforms is presented. A multiple neural network system is adopted which enables the problem to be decomposed into smaller ones, facilitating easier solution. An adaptive resonance theory (ART) neural network is used for damage diagnosis and its advantages and limitations are investigated. A comparison between a back-propagation network and an ART network is presented. The adaptability of ART for on-line monitoring is explored for possible adaptation to monitor offshore platforms in service. The system developed is tested using data from a finite-element analysis of a scale model of a jacket platform.
Topics:
Machine Learning,
Applications:
Industrial Control,
Remote Sensing,
Models:
ART 2 / Fuzzy ART,
Author(s): Kim, H.J. | Kim, J.W. | Kim, S.K. |
Year: 1996
Citation: NEUROCOMPUTING Volume: 10 Issue: 3 Pages: 291-305
Abstract: This paper proposes an efficient method for on-line recognition of cursive Korean characters. Since Korean characters are composed of two or three graphemes in two dimensions, strokes, primitive components of the characters, are usually warped into a cursive form. To classify automatically such cursive strokes, an Adaptive Resonance Theory (ART) neural network is used. Fuzzy membership functions are used to adjust the system according to the writing habits of individual users. The positional relation between two consecutive strokes is also computed with fuzzy functions. With a sequence of strokes classified by the ART neural network and their positional relations computed by fuzzy functions, a character is recognized on a multilayer perceptron for character construction. The proposed method works well with the variation of different writing styles. A test with 17,500 hand-written characters shows a recognition rate of 96.5 per cent and a speed of 0.3 second per character.
Topics:
Image Analysis,
Applications:
Character Recognition,
Models:
ART 1,
Author(s): Williamson, J.R. |
Year: 1996
Citation: NEURAL NETWORKS Volume: 9 Issue: 5 Pages: 881-897
Abstract: A new neural network architecture for incremental supervised learning of analog multidimensional maps is introduced. The architecture, called Gaussian ARTMAP, is a synthesis of a Gaussian classifier and an adaptive resonance theory (ART) neural network, achieved by defining the ART choice function as the discriminant function of a Gaussian classifier with separable distributions, and the ART match function as the same, but with the distributions normalized to a unit height. While Gaussian ARTMAP retains the attractive parallel computing and fast learning properties of fuzzy ARTMAP, it learns a more efficient internal representation of a mapping while being more resistant to noise than fuzzy ARTMAP on a number of benchmark databases. Several simulations are presented which demonstrate that Gaussian ARTMAP consistently obtains a better trade-off of classification rate to number of categories than fuzzy ARTMAP. Results on a vowel classification problem are also presented which demonstrate that Gaussian ARTMAP outperforms many other classifiers.
Topics:
Machine Learning,
Models:
Fuzzy ARTMAP,
Modified ART,
Author(s): Bartfai, G. |
Year: 1996
Citation: NEUROCOMPUTING Volume: 13 Issue: 1 Pages: 31-45
Abstract: This paper introduces a neural architecture (HART for Hierarchical ART ) that is capable of learning hierarchical clusterings of arbitrary input sequences, The network is built up of layers of Adaptive Resonance Theory (ART) network modules where each layer learns to cluster the prototypes developed at the layer directly below it. The notion of effective vigilance is introduced to refer to the vigilance level of multiple ART modules in a HART network. An upper bound is derived for the number of HART layers needed in the case when all ART modules have the same vigilance. Experiments were carried out on a machine learning benchmark database to demonstrate the developed internal representation as well as some learning properties of two- and three-layer binary HART networks.
Topics:
Machine Learning,
Models:
ART 1,
Modified ART,
Author(s): LinaresBarranco, B. | SerranoGotarredona, T. |
Year: 1996
Citation: NEURAL NETWORKS Volume: 9 Issue: 6 Pages: 1025-1043
Abstract: This paper presents a modification to the original ART 1 algorithm (Carpenter & Grossberg, 1987a, A massively parallel architecture for a self-organizing neural pattern recognition machine, Computer Vision, Graphics, and Image Processing, 37, 54-115) that is conceptually similar, can be implemented in hardware with less sophisticated building blocks, and maintains the computational capabilities of the originally proposed algorithm. This modified ART 1 algorithm (which we will call here ART 1(m)) is the result of hardware motivated simplifications investigated during the design of an actual ART 1 chip [Serrano-Gotarredona et al., 1994, Proc. 1994 IEEE Int. Conf. Neural Networks (Vol. 3, pp. 1912-1916); Serrano-Gotarredona & Linares-Barranco, 1996, IEEE Trans. VLSI Systems, (in press)]. The purpose of this paper is simply to justify theoretically that the modified algorithm preserves the computational properties of the original one and to study the difference in behavior between the two approaches.
Topics:
Neural Hardware,
Applications:
Other,
Models:
ART 1,
Author(s): Naghdy, G. | Ogunbona, P. | Wang, J. |
Year: 1996
Citation: ELECTRONICS LETTERS Volume: 32 Issue: 23 Pages: 2154-2154
Abstract: A modified fuzzy adaptive resonance theory neural network (ART) is used as a classifier for a texture recognition system. The system consists of a wavelet based low level feature detector and a high level ART classifier. The performance improvement is measured in terms of identification accuracy and computational burden.
Topics:
Image Analysis,
Models:
ART 2 / Fuzzy ART,
Author(s): Kim, H.J. | Jung, J.W. | Kim, S.Y. |
Year: 1996
Citation: PATTERN RECOGNITION LETTERS Volume: 17 Issue: 12 Pages: 1311-1322
Abstract: This paper proposes an on-line Chinese character recognition method using Adaptive Resonance Theory (ART) based stroke classification. Strokes, primitive components of Chinese characters, are usually warped into a cursive form and classifying them is very difficult, To deal with such cursive strokes, we consider them as a recognition unit and automatically classify them using an ART-2 neural network. The neural network has the advantage of assembling similar patterns together to form classes in a self-organized manner. This stroke classifier contributes to high stroke recognition rate and less recognition time. A database for character recognition also dynamically constructed with generalized character lists, and a new character can be included simply by adding a new sequence to the list. Character recognition is achieved by traversing the Chinese character database with a sequence of recognized strokes and positional relations between the strokes. To verify the performance of the system, we tested it on 1800 basic Chinese characters used daily in Korea, and obtained a good recognition rate of 93.13%. These results suggest that the proposed system is pertinent to be put into practical use.
Topics:
Image Analysis,
Applications:
Character Recognition,
Models:
ART 2 / Fuzzy ART,
Author(s): Ishihara, K. | Ishihara, S. | Matsubara, Y. | Nagamachi, M. |
Year: 1997
Citation: INTERNATIONAL JOURNAL OF INDUSTRIAL ERGONOMICS Volume: 19 Issue: 2 Pages: 93-104
Abstract: Kansei engineering is a technology for translating human feelings into product design. Several multivariate analyses are used for analyzing human feelings and building rules. Although these methods are reliable, they require large computing resources. It is difficult for general users to deal with many variables because of small personal computers, and the need for the user to be an expert on statistics. This paper presents an automatic semantic structure analyzer and Kansei expert systems builder using self-organizing neural networks, ART1.5-SSS and PCAnet. ART1.5-SSS is our modified version of ART1.5, a variant of the Adaptive Resonance Theory neural network. It is used as a stable non-hierarchical classifier and a feature extractor, in a small sample size condition. PCAnet performs principal component analysis based on generalized Hebbian algorithm by Sanger (1989). These networks enable quick and automatic rule building in Kansei engineering expert systems. AKSYONN4 system is the automatic builder for Kansei engineering expert systems because it uses self-organizing neural networks. The system enables real-world applications of Kansei engineering in product development.
Topics:
Machine Learning,
Applications:
Human-Machine Interface,
Models:
ART 1,
Modified ART,
Author(s): AshforthFrost, S. | Fontama, V.N. | Hartle, S.L. | Jambunathan, K. |
Year: 1997
Citation: ARTIFICIAL INTELLIGENCE IN ENGINEERING Volume: 11 Issue: 2 Pages: 135-141
Abstract: A novel algorithm for obtaining flow velocity vectors using ART2 networks (based on adaptive resonance theory) is presented. The method involves tracking the movement of groups of seeding particles in a fluid space through the analysis of two successive images. Simulated flows, created artificially by shifting the particles through known distances or rotating through known angles, were used to establish the accuracy of the technique in predicting displacements. Accuracies were quantified by comparison with known displacements and were found to improve with increasing displacement, angle of rotation and size of the sampling window. In addition, the technique has been extended to derive qualitative and quantitative information for a practical case of natural convective flow.
Topics:
Image Analysis,
Models:
ART 2 / Fuzzy ART,
Author(s): Caudell, T.P. | Healy, M.J. |
Year: 1997
Citation: IEEE TRANSACTIONS ON NEURAL NETWORKS Volume: 8 Issue: 3 Pages: 461-474
Abstract: Envisioning neural networks as systems that learn rules calls forth the verification issues already being studied in knowledge-based systems engineering, and complicates these with neural-network concepts such as nonlinear dynamics and distributed memories, We show that the issues can be clarified and the learned rules visualized symbolically by formalizing the semantics of rule-learning in the mathematical language of two-valued predicate logic, We further show that this can, at least in some cases, be done with a fairly simple logical model, We illustrate this,vith a combination of two example neural-network architectures, LAPART, designed to learn rules as logical inferences from binary data patterns, and the stack interval network, which converts real-valued data into binary patterns that preserve the semantics of the ordering of real values, We discuss the significance of the formal model in facilitating the analysis of the underlying logic of rule-learning and numerical data representation, We provide examples to illustrate the formal model, with the combined stack interval/LAPART networks extracting rules from numerical data.
Topics:
Machine Learning,
Models:
ART 1,
Modified ART,
Author(s): Caudell, T.P. | Anderson, M. | Escobedo, R. | Smith, S.D.G. |
Year: 1997
Citation: IEEE TRANSACTIONS ON NEURAL NETWORKS Volume: 8 Issue: 4 Pages: 847-851
Abstract: We describe a neural information retrieval system (NIRS), now in production within the Boeing Company, which has been developed for the identification and retrieval of engineering designs. Two-dimensional and three-dimensional representations of engineering designs are input to adaptive resonance theory (ART-1) neural networks to produce clusters of similar parts. The trained networks are then used to recall an appropriate cluster when queried with a new part design. This application is of great practical value to industry because it aids in the identification, retrieval, and reuse of engineering designs, potentially saving large amounts of nonrecurring costs. In this paper, we review the application, the neural architectures and algorithms, and then give the current status and the lessons learned in developing a neural-network system for production use in industry.
Topics:
Image Analysis,
Machine Learning,
Applications:
Industrial Control,
Models:
ART 1,
Author(s): Molenaar, P. | Raijmakers, M. |
Year: 1997
Citation: NEURAL NETWORKS Volume: 10 Issue: 4 Pages: 649-669
Abstract: In this article we introduce a continuous time implementation of adaptive resonance theory (ART). ART designed by Grossberg concerns neural networks that self-organize stable pattern recognition categories of arbitrary sequences of input patterns. In contrast to the current implementations of ART we introduce a complete implementation of an ART network, including all regulatory and logical functions, as a system of ordinary differential equations capable of stand-alone running in real time. This means that transient behavior is kept in tact. This implementation of ART is based on ART 2 and is called Exact ART. Exact ART includes an implementation of a gated dipole field and an implementation of the orienting sub-system. The most important features of Exact ART, which are the design principles of ART 2, are proven mathematically. Also simulation studies show that Exact ART self-organizes stable recognition codes that agree with the classification behavior of ART 2.
Topics:
Machine Learning,
Models:
ART 2 / Fuzzy ART,
Modified ART,
Author(s): Durg, A. | Keyvan, S. | Nagaraj, J. |
Year: 1997
Citation: EXPERT SYSTEMS Volume: 14 Issue: 2 Pages: 69-79
Abstract: A prototype of a Signal Monitoring System (SMS) utilizing artificial neural networks is developed in this work. The prototype system is unique in: 1) its utilization of state-of-the-art technology in pattern recognition such as the Adaptive Resonance Theory family of neural networks, and 2) the Integration of neural network results of pattern recognition and fault identification databases. The system is developed in an X-windows environment that offers an excellent Graphical User Interface (GUI). Motif software is used to build the GUI. The system is user-friendly, menu-driven, and allows the user to select signals and paradigms of interest. The system provides the status or condition of the signals tested as either normal or faulty. In the case of faulty status, SMS, through an integrated database, identifies the fault and indicates the progress of the fault relative to the normal condition as well as relative to the previous tests. Nuclear reactor signals from an Experimental Breeder Reactor are analyzed to closely represent actual reactor operational data. The signals are both measured signals collected by a Data Acquisition System as well as simulated signals.
Topics:
Machine Learning,
Applications:
Industrial Control,
Models:
ART 2 / Fuzzy ART,
ART 2-A,
Author(s): Chang, T.C. | Chatterjee, S. | Lankalapalli, K. |
Year: 1997
Citation: JOURNAL OF INTELLIGENT MANUFACTURING Volume: 8 Issue: 3 Pages: 203-214
Abstract: A self-organizing neural network, ART2, based on adaptive resonance theory (ART), is applied to the problem of feature recognition from a boundary representation (B-rep) solid model. A modified face score vector calculation scheme is adopted to represent the features by continuous-valued vectors, suitable to be input to the network. The face score is a measure of the face complexity based upon the convexity or concavity of the surrounding region. The face score vector depicts the topological relations between a face and its neighbouring faces. The ART2 network clusters similar features together. The similarity of the features within a cluster is controlled by a vigilance parameter. A new feature presented to the net is associated with one of the existing clusters, if the feature is similar to the members of the cluster. Otherwise, the net creates a new cluster. An algorithm of the ART2 network is implemented and tested with nine different features. The results obtained indicate that the network has significant potential for application to the problem of feature recognition.
Topics:
Image Analysis,
Models:
ART 2 / Fuzzy ART,
Author(s): Cha, J.W. | Kim, E.S. | Ryu, C.S. |
Year: 1997
Citation: ELECTRONICS LETTERS Volume: 33 Issue: 16 Pages: 1396-1398
Abstract: A modified adaptive resonance theory (mART) neural network of modular structure is proposed. The similarity function and weight resolution of the ART neural networks are modified, and the cluster merging algorithm and modular training method are both introduced. The results from 3D target recognition experiments are compared with those of a self-organising map (SOM) and single mART.
Topics:
Image Analysis,
Machine Learning,
Applications:
Remote Sensing,
Models:
Modified ART,
Self Organizing Maps,
Author(s): Naghdy, G. | Ogunbona, P. | Wang, J. |
Year: 1997
Citation: JOURNAL OF ELECTRONIC IMAGING Volume: 6 Issue: 3 Pages: 329-336
Abstract: A new method of texture classification comprising two processing stages, namely a low-level evolutionary feature extraction based on Gabor wavelets and a high-level neural network based pattern recognition, is proposed. The design of these stages is motivated by the processes involved in the human visual system: low-level receptors responsible for early vision processing and the high-level cognition. Gabor wavelets are used as extractors of "low-level" features that feed the feature-adaptive adaptive resonance theory (ART) neural network acting as a high-level "cognitive system." The novelty of the model developed in this paper lies in the use of a self-organizing input layer to the fuzzy ART. Evaluation of the model is performed by using natural textures, and results obtained show that the developed model is capable of performing the texture recognition task effectively. Applications of the developed model include the study of artificial vision systems motivated by the human visual system model.
Topics:
Image Analysis,
Models:
ART 2 / Fuzzy ART,
Author(s): Subrahmanyam, M. | Sujatha, C. |
Year: 1997
Citation: TRIBOLOGY INTERNATIONAL Volume: 30 Issue: 10 Pages: 739-752
Abstract: Two neural network based approaches, a multilayered feed forward neural network trained with supervised Error Back Propagation technique and an unsupervised Adaptive Resonance Theory-2 (ART2) based neural network were used for automatic detection/diagnosis of localized defects in ball bearings. Vibration acceleration signals were collected from a normal bearing and two different defective bearings under various load and speed conditions. The signals were processed to obtain various statistical parameters, which are good indicators of bearing condition, and these inputs were used to train the neural network and the output represented the ball bearing states, The trained neural networks were used for the recognition of ball bearing states. The results showed that the trained neural networks were able to distinguish a normal bearing from defective bearings with 100% reliability. Moreover, the networks were able to classify the ball bearings into different states with success rates better than those achieved with the best among the state-of-the-art techniques.
Topics:
Machine Learning,
Applications:
Industrial Control,
Models:
ART 2 / Fuzzy ART,
Modified ART,
Author(s): Williamson, J.R. |
Year: 1997
Citation: NEURAL COMPUTATION Volume: 9 Issue: 7 Pages: 1517-1543
Abstract: Gaussian ARTMAP (GAM) is a supervised-learning adaptive resonance theory (ART) network that uses gaussian-defined receptive fields. Like other ART networks, GAM incrementally learns and constructs a representation of sufficient complexity to solve a problem it is trained on. GAM s representation is a gaussian mixture model of the input space, with learned mappings from the mixture components to output classes. We show a close relationship between GAM and the well-known expectation-maximization (EM) approach to mixture modeling. GAM outperforms an EM classification algorithm on three classification benchmarks, thereby demonstrating the advantage of the ART match criterion for regulating learning and the ARTMAP match tracking operation for incorporating environmental feedback in supervised learning situations.
Topics:
Machine Learning,
Models:
ARTMAP,
Author(s): Chen, J.J.G. | Song, I.R. | Yang, T.Y. |
Year: 1997
Citation: COMPUTERS & INDUSTRIAL ENGINEERING Volume: 33 Issue: 3-4 Pages: 469-472
Abstract: The Exchange Heuristic (EH) has demonstrated superior results compared with other RCS methods in solving Resource Constrained Scheduling (RCS) problems. Selecting the most promising target constitutes the success of EH. The current version of EH highly depends an experts intuition in selecting a target. Expert systems and Fuzzy rulebase as well as Neural Network (NN) have been considered as alternatives for human experts. Expert systems are brittle in nature, and the Fuzzy rulebase needs membership functions defined for each linguistic variable. However, these membership functions can not be justified and can be very subjective. Therefore, Neural Network is employed because of its capability of learning as well as dealing with fuzzy data. Known examples are used to train the NN. Back propagation algorithm is used first, then an Adaptive Resonance Theory (ART) network is employed to reduce training time since new rules come up often. Even at the end of the training the NN, we may end up with local optima or the NN which is too general to specific problems. Utilizing the Genetic Algorithm (GA) will help to further refine or adapt the weights of the NN which optimizes target selection strategy for a specific problem.
Topics:
Machine Learning,
Applications:
Industrial Control,
Models:
ARTMAP,
Genetic Algorithms,
Author(s): Mannan, B. | Ray, A.K. | Roy, J. |
Year: 1998
Citation: INTERNATIONAL JOURNAL OF REMOTE SENSING Volume: 19 Issue: 4 Pages: 767-774
Abstract: The fuzzy ARTMAP has been applied to the supervised classification of multi-spectral remotely-sensed images. This method is found to be more efficient, in terms of classification accuracy, compared to the conventional maximum likelihood classifier and also multi-layer perceptron with back propagation learning. The results have been discussed.
Topics:
Image Analysis,
Applications:
Remote Sensing,
Models:
Fuzzy ARTMAP,
Author(s): Frank, T. | Kraiss, K.F. | Kuhlen, T. |
Year: 1998
Citation: IEEE TRANSACTIONS ON NEURAL NETWORKS Volume: 9 Issue: 3 Pages: 544-559
Abstract: Adaptive resonance theory (ART) describes a family of self-organizing neural networks, capable of clustering arbitrary sequences of input patterns into stable recognition codes. Many different types of ART-networks have been developed to improve clustering capabilities. In this paper we compare clustering performance of different types of ART-networks: Fuzzy ART, ART 2A with and without complement encoded input patterns, and an Euclidean ART 2A-variation. All types are tested with two-and high-dimensional input patterns in order to illustrate general capabilities and characteristics in different system environments. Based on our simulation results, Fuzzy ART seems to be less appropriate whenever input signals are corrupted by addititional noise, while ART 2A-type networks keep stable in all inspected environments. Together with other examined features, ART-architectures suited for particular applications can be selected.
Topics:
Machine Learning,
Models:
ART 2 / Fuzzy ART,
ART 2-A,
Author(s): Chen, B.H. | McGreavy, C. | Wang, X.Z. | Yang, S.H. |
Year: 1999
Citation: COMPUTERS & CHEMICAL ENGINEERING Volume: 23 Issue: 7 Pages: 899-906
Abstract: An integrated framework for process monitoring and diagnosis is presented which combines wavelets for feature extraction from dynamic transient signals and an unsupervised neural network for identification of operational states. Multiscale wavelet analysis is used to determine the singularities of transient signals which represent the features characterising the transients. This simultaneously reduces the dimensionality of the data and removes noise components. A modified version of the adaptive resonance theory is developed, which is designated ARTnet and uses wavelet feature extraction as the substitute of the data pre-processing unit. ARTnet is proved to be more effective in dealing with noise contained in the transient signals while retains being an unsupervised and recursive clustering approach. The work is reported in two parts. The first part is focused on feature extraction using wavelets. The second part describes ARTnet and its application to a case study of a refinery fluid catalytic cracking process.
Topics:
Machine Learning,
Applications:
Industrial Control,
Models:
ART 2 / Fuzzy ART,
Modified ART,
Author(s): Fergenson, D.P. | Hopke, P. | Prather, K.A. | Song, X.H. |
Year: 1999
Citation: ANALYTICAL CHEMISTRY Volume: 71 Issue: 4 Pages: 860-865
Abstract: Aerosol particles have received significant public and scientific attention in recent years due to studies linking them to global climatic changes and human health effects. In 1994, Prather et al, (Prather, K. A.; Nordmeyer, T,; Salt, K, Anal. Chem. 1994, 66, 1403-1407) developed aerosol time-of-night mass spectrometry (ATOFMS), the first technique capable of simultaneously determining both size and chemical composition of polydisperse single particles in real time. ATOFMS can typically analyze between 50 and 100 particles/min under typical atmospheric conditions. This significant volume of data requires automated data analysis for efficient processing. This paper reports the successful analysis of ATOFMS data acquired during a 1996 field study in Southern California using an adaptive resonance theory-based neural network, ART-2a. The ART-2a network revealed particle categories consistent with those obtained previously by manual analysis. The classification was accomplished in less time than the acquisition, rendering it possible to develop a data acquisition system using an on-line ART-2a that classifies particles as they are acquired.
Topics:
Machine Learning,
Applications:
Chemical Analysis,
Models:
ART 2-A,
Author(s): Bebis, G. | Dagher, I. | Georgiopoulos, M. | Heileman, G.L. |
Year: 1999
Citation: NEURAL NETWORKS Volume: 12 Issue: 6 Pages: 837-850
Abstract: This paper discusses a variation of the Fuzzy ART algorithm referred to as the Fuzzy ART Variant. The Fuzzy ART Variant is a Fuzzy ART algorithm that uses a very large choice parameter value. Based on the geometrical interpretation of the weights in Fuzzy ART, useful properties of learning associated with the Fuzzy ART Variant are presented and proven. One of these properties establishes an upper bound on the number uf list presentations required by the Fuzzy ART Variant to learn an arbitrary list of input patterns. This bound is small and demonstrates the short-training time property of the Fuzzy ART Variant. Through simulation, it is shown that the Fuzzy ART Variant is as good a clustering algorithm as a Fuzzy ART algorithm that uses typical (i.e. small) values for the choice parameter.
Topics:
Machine Learning,
Models:
ART 2 / Fuzzy ART,
Modified ART,
Author(s): Lavoie, P. | Crespo, J.F. | Savaria, Y. |
Year: 1999
Citation: IEEE TRANSACTIONS ON NEURAL NETWORKS Volume: 10 Issue: 4 Pages: 757-767
Abstract: The internal competition between categories in the adaptive resonance theory (ART) neural model can be biased by replacing the original choice function by one that contains an attentional tuning parameter under external control. For the same input but different values of the attentional tuning parameter, the network can learn and recall different categories with different degrees of generality, thus permitting the coexistence of both general and specific categorizations of the same set of data. Any number of these categorizations can be learned within one and the same network by virtue of generalization and discrimination properties. A simple model in which the attentional tuning parameter and the vigilance parameter of ART are linked together is described. The self-stabilization property is shown to be preserved for an arbitrary sequence of analog inputs, and for arbitrary orderings of arbitrarily chosen vigilance levels.
Topics:
Machine Learning,
Models:
ART 2 / Fuzzy ART,
Author(s): Li, X.Q. | Nee, A.Y.C. | Wong, Y.S. |
Year: 1999
Citation: PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART B-JOURNAL OF ENGINEERING MANUFACTURE Volume: 213 Issue: 2 Pages: 191-196
Abstract: Tool wear monitoring is crucial for an automated machining system to maintain consistent quality of machined parts and prevent damage to the parts during the machining operation. A vision-based approach is presented for tool wear identification in finish turning using an adaptive resonance theory (ART2) neural network embedded with fuzzy classifiers. The proposed approach is established upon the fact that the optical scattering image of a turned surface is related to the wear of the cutting tool. By applying the technique of the ART2 neural network embedded with fuzzy classifiers, the state of wear of the turning tool is determined from captured images obtained by laser scattering from the machined surfaces of the workpiece. This approach is not unlike the visual inspection of the surface of a machined workpiece to determine the state of wear of a cutting tool by an expert machinist. However, experimental results indicate that the conventional technique of measuring surface finish does not give values that correlate well with tool wear. On the other hand, the laser scattering image provides a good indication of the tool wear as it is not readily affected by buildup edge or cold-welded material, scratches and other disruptive defects on the turned surface as the tool wears. In this paper, the theory on the laser scattering image and the principle of tool wear identification are described. Based on the scattering images, the proposed approach can correctly identify the condition of significant wear prior to the rapid tool wear stage for the cutting tool.
Topics:
Image Analysis,
Applications:
Industrial Control,
Models:
ART 2 / Fuzzy ART,