E. Kodhai
@citchennai.edu.in
Professor/CSE
Chennai Institute of Technology
Dr. E. Kodhai is currently working as Professor in the Department of Computer Science and Engineering at Chennai Institute of Technology affiliated to Anna University, Chennai, India. She has completed her M.C.A from Cauvery College for women, Trichy affiliated to Bharathidasan University, Trichy and M.E. in Computer Science and Engineering from Vinayaka Mission’s Kirupananda Variyar Engineering College, Salem. She has completed her Ph.D from Pondicherry Engineering College affiliated to Pondicherry University, Puducherry, India. She has more than 23 years of experience in teaching in various engineering colleges. Her Research interests include Software Clones, Software Engineering, and Artificial Intelligence. She has published more than 100 papers in international conference and journals. She is a member of ISTE, India.
EDUCATION
AUG 2015
PH.D (CSE), Pondicherry Engineering College, Puducherry, India.
• Awarded Ph.D
• Thesis title : Development of a Light-Weight Hybrid (LWH) Approach for Method-level Code Clone Detection and Maintenance
JUL 2006
M.TECH (CSE), Vinayaka Mission’s Kirupananda Variyar Engineering College, Salem, India.
APR 1999
MCA, Cauvery College for Women, Trichy, India.
APR 1996
B.SC (MATHS), Seethalakshmi Ramasamy College, Trichy, India.
MAY 1993
12TH STANDARD, Sacred Heart Convent Higher Secondary School, Villupuram, India.
JUN 1991
10TH STANDARD, Sacred Heart Convent Higher Secondary School, Villupuram, India.
RESEARCH, TEACHING, or OTHER INTERESTS
Computer Engineering, Software, Artificial Intelligence, Computer Science
Scopus Publications
Scholar Citations
Scholar h-index
Scholar i10-index
Scopus Publications
Anand Mohan, E. Kodhai, Makarand Upadhyaya, K. Thilagam, Ashim Bora, P. Vijayakumar, and Pravin R. Kshirsagar
AIP Publishing
The goal to promote human limits is for Artificial Intelligence (AI). It takes a posture on public administrations, represents the increasing availability of regaining clinical data and the rapid creation of intelligent strategies. The need to stress the need to use AI in the fight against the COVID-19 crisis. The paper outlines the main role played by Ai technologies in this unprecedented war and introduces a survey of AI methods used for multiple purposes in the fight against the outbreak of COVID-19. This paper also explains how the body temperature and coughing of the incoming person are assessed and whether the incoming person has not a protective facial mask. Should either of the above tests disqualify the participant, an alarming device invokes the local officials;the entrant may otherwise enter the premises after his/her hand has been sanitized. © 2022 Author(s).
B. Parvathi Sangeetha, E. Kodhai, M. Belsam Jeba Ananth, R. Revathi, Akkaraju Sailesh Chandra, and P. Vijayakumar
AIP Publishing
E. Kodhai, Manga Haneesha Gowri, Susmitha S., and Muthamizh R.
IEEE
Personal Health Records are used in hospitals to maintain data and details of the patients. These records are really important and contain the health history of the patients. In case of any malpractice, the health records of the patients might be mishandled. Here we have surveyed projects and papers that are related to Personal Health Records. These records of the patients were first in hand-written documents later they were converted to electronic records. These electronic records also have less security and they are stored in the local server they are then made a little secured and can be stored in the cloud. This survey explores us about the technologies and techniques that are used in the literature to keep the documents of the patients. These patient documents holds the personal health records in a more secure manner.
E. Kodhai, A. Pooveswari, P. Sharmila, and N. Ramiya
IEEE
Emotion plays a significant role in human beings daily lives. Humans can easily sense a person's emotions. But in some cases devices need to sense people's emotions. Machine learning is a sub-part of artificial intelligence that produces robots handling tasks like us. Emotion recognition is a small module that can be easily achieved by machines using machine learning algorithms. This paper describes the various algorithms used to recognize the facial expressions of a person such as happy, angry, sad, disgust, neutral, fear. Gabor filters and Local Binary Pattern Operators (LBP) are discussed for the process of feature extraction. Different types of classification algorithms such as Support Vector Machines, K-Nearest Neighbors are discussed. The training of the image data is carried by comparing various neural networks including Attentional Neural Network, Convolutional neural network, shallow neural network etc.
Dipali A. Sable and S. Ganorkar
Blue Eyes Intelligence Engineering and Sciences Engineering and Sciences Publication - BEIESP
Breast cancer, a major public health contention and currently causes an increased rate of cancer death in women. The preeminent intent of this project in medical diagnostics is by using mammography, that is a unique imaging technique in medicine for examining the breasts. A higher quality mammographic images (for example electronic pictures) are stored, mammography method (i.e exam) is performed, which is a prior stage for detection and diagnosis of bosom’s malignant growth. In order to detect the tumor FCM algorithm for segmentation is used and the features are extracted by using multi-level wavelet transformation technique with PCA and then some features are added with GLCM features. Further, those segmented region features are extracted and the dataset is trained and tested completely. The images are classified by using SVM, KNN, Tree classifier, Neural Networks or Naive Bayes classifier. Finally, the images from Kaggle dataset are compared and categorized as normal, benign or malignant tumors.
E. Kodhai and S. Kanmani
Inderscience Publishers
E. Kodhai and P. Bharathi
IEEE
In a low time to live based wireless network, the node drops all its energy before actually transferring the data given to it. This serves as a drawback where the data is not transferred completely resulting in bandwidth wastage and improper message delivery. To address this problem we formulate new routing techniques by which the data from one part is scheduled to reach the destination based on the computed time to live and available bandwidth. Other than forming a routing tree which may fail when overhearing occurs, split the data and place them into appropriate bandwidths where the bandwidth wastage is minimal. Therefore the process is divided into two steps: Identifying the throughput and the mean bandwidth, initiate the data such that a least amount of bandwidth is wasted. In this method, the routing must be updated every six sees, with respect to the time to live (computed) of the node. The node energy is the tedious process which can be further enhanced by controlling the node between active and sleep state. The problems of link failure, denial of service can be rectified in this process.
E. Kodhai and B. Dhivya
IEEE
Software developers often need to examine program differences between two versions and reason about the changes. Analyzing the changes is the task. To facilitate the programmers to represent the high level source code changes, this proposed system introduces the rule-based program differencing approach to represent the changes as logical rules. This approach is instantiated with three levels: first level describes the changes in method header names and signature; second level captures change in the code level and structural dependences; and third level identifies the same set of function with different name. This approach concisely represents the systematic changes and helps the software engineers to recognize the program differences. This approach can be applied in open source project to examine the difference among program version.
E. Kodhai and S. Kanmani
Springer International Publishing
A Perumal, S Kanmani, and E Kodhai
IEEE
Copying a code fragment and reusing it by pasting with or without minor modifications is a common practice in software development environments. Various techniques have been proposed to find duplicated redundant code. Previous work was simple and practical methods for detecting exact and near miss clones over arbitrary program fragments in program source code by using abstract syntax trees. Our proposal is a new technique for finding similar code blocks and for quantifying their similarity. Our techniques can be used to find clone clusters, sets of code blocks all within a user-supplied similarity. It detects similar clones using metrics for type 1, type 2 of clones.
E. Kodhai, S. Kanmani, A. Kamatchi, R. Radhika, and B. Vijaya Saranya
IEEE
Clone Detection has considerably evolved over the last decade, leading to approaches with better results but with increasing complexity. Most of the existing approaches are limited to finding program fragments similar in their syntax or semantics, while the fraction of candidates that are actually clones and fraction of actual clones identified as candidates on the average remain similar. In this paper, a metric-based approach combined with the textual comparison of the source code for the detection of functional Clones in C source code has been proposed. Various metrics had been formulated and their values were utilized during the detection process. Compared to the other approaches, this method is considered to be the least complex and is to provide a more accurate and efficient way of Clone Detection. The results obtained had been compared with the two other existing tools for the open source project Weltab.
E. Kodhai, S. Kanmani, A. Kamatchi, R. Radhika, and B. Vijaya Saranya
Springer Berlin Heidelberg