Photometric clustering of regenerated plants of gladiolus by neural networks and its biological validation

Author(s): Gupta, S.D. | Prasad, V.S.S. |

Year: 2008

Citation: COMPUTERS AND ELECTRONICS IN AGRICULTURE Volume: 60 Issue: 1 Pages: 8-17

Abstract: Photometric clustering of regenerated plants of gladiolus was described using fuzzy adaptive resonance theory (ART) and the resultant grouping pattern was compared with ART 2, and self-organizing map (SOM) neural network modules. Classical clustering techniques such as hierarchical (HC) and k-means clustering (KM) were also applied to analyze the same data set to evaluate the performance of the artificial neural network (ANN)-based clustering. Regenerated plants were clustered into two groups in varying numbers by ART 2, SOM, HC and KM. With ART 2, 19 of 55 plants were sorted into group 0 and the remaining 36 plants were placed in group 1 , whereas; SOM distributed the regenerated plants in the ratio of 28:27. The clustering ratios of HC and KM were 34:21 and 26:29, respectively. However, a refined clustering of regenerated plants into seven groups was observed with Fuzzy ART. There was a similarity in the number of generated clusters between the training and validation data sets indicating the network efficiency. Biological validation of photometric clustering of regenerated plants was also assessed by indexing the corm induction potential of the sorted groups. A significant difference in corm induction potential between the groups was noted only with ART 2. Fuzzy ART- assisted grouping patterns are not conducive to segregate the potential corm producing shoots. ART 2-aided clustering of the regenerated plants appeared to be more promising for selecting group of plants capable of corm development than did other clustering approaches.

Topics: Machine Learning, Applications: Biological Classification, Models: ART 2 / Fuzzy ART, Self Organizing Maps,

PDF download

Cross References

  1. 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

  2. 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

  3. 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

  4. 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

  5. Inference of common genetic network using fuzzy adaptive resonance theory associated matrix methods
    Inferring genetic networks from gene expression data is the most challenging work in the postgenomic era. However, most studies tend to show their genetic network inference ability by using artificial data. Here, we ... Article Details

  6. Analysis of expression profile using fuzzy adaptive resonance theory
    Motivation: It is well understood that the successful clustering of expression profiles give beneficial ideas to understand the functions of uncharacterized genes. In order to realize such a successful clustering, we ... Article Details