Indulekha T. S. currently serves as an Assistant Professor at the Department of Computer Science Applications at Amrita School of Engineering, Amritapuri.


Publication Type: Conference Paper

Year of Publication Publication Type Title


Conference Paper

Indulekha T.S., S, A. G., and Sudhakaran, P., “A Graph Based Algorithm for Clustering and Ranking Proteins for Identifying Disease Causing Genes”, in International Conference on Advances in Computing, Communications and Informatics (ICACCI), 2018.[Abstract]

Identification of genes which cause a particular disease in humans is a main objective of hereditary genetics. Such genes are said to be disease genes. Several natural techniques are accessible to recognize disease genes. The candidate genes should be additionally explored to distinguish the disease causing genes. Scholars must organize the genes from most to minimum promising while carrying out the validation procedure. This is essential for reducing the cost required for experimental testing. The idea here is to prioritize candidate genes in a protein-protein interaction network based on community detection. We implement a method to prioritize the candidate genes in PPI network. We tested the efficiency of our algorithm over the existing algorithms.

More »»


Conference Paper

Dr. Bhadrachalam Chitturi, Thomas, J., and Indulekha T.S., “New approaches for discovering unsupervised human activities by mining sensor data”, in 2015 International Conference on Computing and Network Communications, CoCoNet 2015, 2015, pp. 118-123.[Abstract]

Discovering human activities facilitates computerization and the consequent monitoring of the smart home environment. The existing unsupervised human activity discovery systems perform segmentation clustering followed by the labeling of the sensor data. Segmentation clustering consists of forming segments from similar consecutive frames and then clustering similar segments. A cluster is labeled by the action associated with its most frequent sensor(s). In these methods, even if similar segments denote distinct activities they often occur in the same cluster. We propose three alternate methods to address this issue. The first method is a minor variant of the segmentation clustering where subsequences of the segments are clustered instead of the segments. We employ the concept of cover where (a, b, c) subsumes (a, c) if they have identical frequency. The second method employs a new algorithm, i.e. LRS, instead of segmentation. The third method is a hybrid method that extracts subsequences from the output of LRS. We compared the proposed systems with the existing system on CASAS dataset, a real world human activity dataset. The third method that employs LRS followed by subsequence extraction yielded the best Dunn's index and the best correctness in clusters as per confusion matrix. © 2015 IEEE.

More »»

Publication Type: Conference Proceedings

Year of Publication Publication Type Title


Conference Proceedings

Indulekha T.S., Nair, A. G., and Harikesh, P., “Graphical representation of prolog traces”, Second International Conference Computer Paradigms(ICCP 2016), International Journal of Control Theory and Applications, vol. 9. pp. 4563-4574, 2016.[Abstract]

While designing programming environments, one should consider a very easily understandable way to explain it to the user how their program works. For a programmer who migrates from a procedure oriented language to a logic programming language like Prolog, it is difficult to understand the search strategy used while it derives new information from the existing knowledge base. But for a Prolog programmer it is essential to understand how the unification and searching process are done in order to write and debug programs. Here, a tool which can graphically show the order in which Prolog searches and backtracks for the answer of a particular query is presented. To understand the program execution, a model of the programming language is essential. For that, the model should include some information about the search space, the flow of control through the search space and the Prolog clauses. The proposed system will be helpful for the teaching purpose. The graphical representation of these Prolog trace is very much helpful for the learner to understand how the query has been traced from the whole knowledge base. Instead of showing only the correct path, the system could show failed paths also. It is mainly intended to make the students understand, how the Prolog trace works. © International Science Press.

More »»
Faculty Research Interest: