M. V. Judy

Bio: M. V. Judy is an academic researcher from Cochin University of Science and Technology. The author has contributed to research in topics: Computer science & Genetic algorithm. The author has an hindex of 7, co-authored 27 publications receiving 156 citations. Previous affiliations of M. V. Judy include Shanmugha Arts, Science, Technology & Research Academy & Amrita Vishwa Vidyapeetham.

Autism spectrum disorders: Integration of the genome, transcriptome and the environment

Abstract: Autism spectrum disorders denote a series of lifelong neurodevelopmental conditions characterized by an impaired social communication profile and often repetitive, stereotyped behavior. Recent years have seen the complex genetic architecture of the disease being progressively unraveled with advancements in gene finding technology and next generation sequencing methods. However, a complete elucidation of the molecular mechanisms behind autism is necessary for potential diagnostic and therapeutic applications. A multidisciplinary approach should be adopted where the focus is not only on the 'genetics' of autism but also on the combinational roles of epigenetics, transcriptomics, immune system disruption and environmental factors that could all influence the etiopathogenesis of the disease. ASD is a clinically heterogeneous disorder with great genetic complexity; only through an integrated multidimensional effort can modern autism research progress further.

Constructing a personalized e-learning system for students with autism based on soft semantic web technologies

Abstract: Computer use offers a flexible, high status means of providing opportunities for people with autism in education, communication, creativity, leisure and employment. It may offer a range of very useful tools for a person with autism, but this must be embedded in a wider care for educational system to be effective. People with autism have a psychoeducational profile that is different from normally developing individuals. Planning the instructional program for students with autism is complex, because these students have significant differences from most other students in learning style, communication, and social skill development, and often have challenging behaviours. There is considerable individual variability in how these characteristics affect a particular person. Programs must be individualized based on the unique needs and abilities of each student. Context aware e-learning system provides the learning contents based on the individual characteristics of the learner. An adaptive e-learning system based on soft semantic web technologies can be developed to teach the students with autism.

A multi-objective evolutionary algorithm for protein structure prediction with immune operators.

Abstract: Genetic algorithms (GA) are often well suited for optimisation problems involving several conflicting objectives. It is more suitable to model the protein structure prediction problem as a multi-objective optimisation problem since the potential energy functions used in the literature to evaluate the conformation of a protein are based on the calculations of two different interaction energies: local (bond atoms) and non-local (non-bond atoms) and experiments have shown that those types of interactions are in conflict, by using the potential energy function, Chemistry at Harvard Macromolecular Mechanics. In this paper, we have modified the immune inspired Pareto archived evolutionary strategy (I-PAES) algorithm and denoted it as MI-PAES. It can effectively exploit some prior knowledge about the hydrophobic interactions, which is one of the most important driving forces in protein folding to make vaccines. The proposed MI-PAES is comparable with other evolutionary algorithms proposed in literature, both in ...

Analytical Study of Selected Classification Algorithms for Clinical Dataset

Abstract: The objective of this paper is to analyze and identify the best classification solution for clinical decision making. Several classification algorithms Like Discriminant Analysis (LDA), Support Vector Machine (SVM), Artificial Neural Network (ANN), Naive Bayes (NB), and Decision Trees are compared to find the optimum diagnostic accuracy. The performance of classification algorithms are compared using benchmark dataset, breast cancer. The effects of normalization using z-score and min-max approaches are also investigated. The results are compared based on different performance parameters like accuracy, sensitivity, specificity and root node error value. Accuracy has been improved for all classifications methods after normalizing the data set. Z-score normalization performs better for all the measures when compared to min-max normalization. The proposed approach shows higher accuracy rate for Naive Bayes algorithm when compared with the other algorithms.

A secure framework for remote diagnosis in health care: A high capacity reversible data hiding technique for medical images

Abstract: The health care industry involves the processing of large-scale images for various applications. Remote diagnosis is one such significant area where medical images are sent across vulnerable communication media. Hence, a secure and robust framework is necessary to hide and retrieve patient information in medical images. Here, we propose a high capacity reversible data hiding technique that can be used to embed patient data using a new weighted interpolation technique. In this approach, to improve the payload capacity, interpolated pixels are effectively utilized for the data embedding process using modular arithmetic. The original cover pixels are also employed to embed data using the difference expansion method. The framework developed is tested with standard benchmark images and medical images. The experimental results prove that the proposed method proffers a better output in comparison with the other contemporary methods in this domain.

Incorporation of Solvent Effect into Multi-Objective Evolutionary Algorithm for Improved Protein Structure Prediction

Abstract: The problem of predicting the three-dimensional (3-D) structure of a protein from its one-dimensional sequence has been called the “holy grail of molecular biology”, and it has become an important part of structural genomics projects. Despite the rapid developments in computer technology and computational intelligence, it remains challenging and fascinating. In this paper, to solve it we propose a multi-objective evolutionary algorithm. We decompose the protein energy function Chemistry at HARvard Macromolecular Mechanics force fields into bond and non-bond energies as the first and second objectives. Considering the effect of solvent, we innovatively adopt a solvent-accessible surface area as the third objective. We use 66 benchmark proteins to verify the proposed method and obtain better or competitive results in comparison with the existing methods. The results suggest the necessity to incorporate the effect of solvent into a multi-objective evolutionary algorithm to improve protein structure prediction in terms of accuracy and efficiency.

The Effect of the Normalization Method Used in Different Sample Sizes on the Success of Artificial Neural Network Model

Abstract: In this study, it was aimed to compare different normalization methods employed in model developing process via artificial neural networks with different sample sizes. As part of comparison of normalization methods, input variables were set as: work discipline, environmental awareness, instrumental motivation, science self-efficacy, and weekly science learning time that have been covered in PISA 2015, whereas students' Science Literacy level was defined as the output variable. The amount of explained variance and the statistics about the correct classification ratios were used in the comparison of the normalization methods discussed in the study. The data was analyzed in Matlab2017b software and both prediction and classification algorithms were used in the study. According to the findings of the study, adjusted min-max normalization method yielded better results in terms of the amount of explained variance in different sample sizes compared to other normalization methods; no significant difference was found in correct classification rates according to the normalization method of the data, which lacked normal distribution and the possibility of overfitting should be taken into consideration when working with small samples in the modelling process of artificial neural network. In addition, it was also found that sample size had a significant effect on both classification and prediction analyzes performed with artificial neural network methods. As a result of the study, it was concluded that with a sample size over 1000, more consistent results can be obtained in the studies performed with artificial neural networks in the field of education.

Dendritic spine actin cytoskeleton in autism spectrum disorder.

Abstract: Dendritic spines are small actin-rich protrusions from neuronal dendrites that form the postsynaptic part of most excitatory synapses. Changes in the shape and size of dendritic spines correlate with the functional changes in excitatory synapses and are heavily dependent on the remodeling of the underlying actin cytoskeleton. Recent evidence implicates synapses at dendritic spines as important substrates of pathogenesis in neuropsychiatric disorders, including autism spectrum disorder (ASD). Although synaptic perturbations are not the only alterations relevant for these diseases, understanding the molecular underpinnings of the spine and synapse pathology may provide insight into their etiologies and could reveal new drug targets. In this review, we will discuss recent findings of defective actin regulation in dendritic spines associated with ASD.