Qualification: 
MS, BSc
jayasreen@am.amrita.edu

Jayasree Narayanan currently serves as the Assistant Professor at the Department of Computer Science Engineering at Amrita School of Engineering, Amritapuri. She pursued her M. S. in System Software. Prior to joining Amrita, she worked at Defence Research and Development Organization (DRDO). Jayasree she has 21 years of industry experience and 9 years of academic experience.

Publications

Publication Type: Conference Paper

Year of Publication Title

2019

A. Vijayan, Kumar, A. S., and Jayasree Narayanan, “Fuzzy Logic: Adding Personal Attributes to Estimate Effect of Accident Frequencies”, in 4th International Conference on Artificial Intelligence and Evolutionary Computations in Engineering Systems ICAIECES 19, 2019.

2015

R. Krithika and Jayasree Narayanan, “Learning to Grade Short Answers Using Machine Learning Techniques”, in Proceedings of the Third International Symposium on Women in Computing and Informatics, New York, NY, USA, 2015.[Abstract]


In this work, we are attempting to grade short answer automatically which can be efficient and helpful to both students and teachers. It uses a combination of many semantic and graph alignment features and is implemented in the Microsoft Azure Machine Learning using Two-class Averaged Perceptron, Linear and Isotonic Regression. We also provide first attempt to use graph alignment features at sentence level. We compare the results of two machine learning algorithms like Two-class Averaged Perceptron and Two-class Support Vector Machine in the results of grading short answers. We have devised novel techniques to apply the concept of Random Projection for grading 150 algorithmic answers on a coding question using our own domain specific corpus which gives precise classification of right and wrong answers.

More »»

Publication Type: Conference Proceedings

Year of Publication Title

2018

J. V. Anand Sukumar, Pranav, I., Neetish, M., and Jayasree Narayanan, “Network Intrusion Detection Using Improved Genetic k-means Algorithm”, 2018 International Conference on Advances in Computing, Communications and Informatics (ICACCI). IEEE, Bangalore, India, pp. 2441-2446, 2018.[Abstract]


Internet is a widely used platform nowadays by people across the globe. This has led to the advancement in science and technology. Many surveys show that network intrusion has registered a consistent increase and lead to personal privacy theft and has become a major platform for attack in the recent years. Network intrusion is any unauthorized activity on a computer network. Hence there is a need to develop an effective intrusion detection system. In this paper we acquaint an intrusion detection system that uses improved genetic k-means algorithm(IGKM) to detect the type of intrusion. This paper also shows a comparison between an intrusion detection system that uses the k-means++ algorithm and an intrusion detection system that uses IGKM algorithm while using smaller subset of kdd-99 dataset with thousand instances and the KDD-99 dataset. The experiment shows that the intrusion detection that uses IGKM algorithm is more accurate when compared to k-means++ algorithm.

More »»

2018

K. K. Samhitha, Dr. Sajeev G. P., and Jayasree Narayanan, “A Novel Community Detection Method for Collaborative Networks”, 2018 International Conference on Advances in Computing, Communications and Informatics (ICACCI). IEEE, Bangalore, India, India, pp. pp. 866-872., 2018.[Abstract]


Community structure prevails in network graphs like social networks, web graphs and collaborative networks. Clique percolation is one popular method used for unfolding the community structure in networks. However, clique percolation method is inefficient as the computational time is high for merging the identified cliques. This paper proposes a novel technique for detecting overlapping community structure by addressing the problem of clique merging. We reduce the overall time for community detection by applying edge streaming technique. The proposed method is validated through experiments using real and synthetic data in comparison with conventional clique percolation algorithm. The performance parameters such as execution time and goodness of the cluster are used for comparison and the results are promising. This model is suitable for community detection in collaborative network.

More »»

Publication Type: Journal Article

Year of Publication Title

2012

P. G. Pillai and Jayasree Narayanan, “Question categorization using SVM based on different term weighting methods”, International Journal on Computer Science and Engineering, vol. 4, p. 938, 2012.[Abstract]


This paper deals with the performance of Question Categorization based on four different term weighting methods. Term weighting methods such as tf*idf, qf*icf, iqf*qf*icf and vrf together with SVM classifier were used for categorization. From the experiments conducted using both linear and nonlinear SVM, term weighting method iqf*qf*icf showed better performance in question categorization than other methods.

More »»