T
T. Devi
Researcher at Saveetha University
Publications - 58
Citations - 420
T. Devi is an academic researcher from Saveetha University. The author has contributed to research in topics: Computer science & Support vector machine. The author has an hindex of 8, co-authored 37 publications receiving 212 citations. Previous affiliations of T. Devi include VIT University & Bharathiar University.
Papers
More filters
Book ChapterDOI
Client-Controlled HECC-as-a-Service (HaaS)
T. Devi,N. Deepa,K. Jaisharma +2 more
TL;DR: Data security model (DSM) with safe data retrieval framework has been proposed which employs hyperelliptic curve cryptography for data encryption in order to avoid huge computation costs for keys involved and is much faster than any other model employing HECC in cloud.
Proceedings ArticleDOI
Prediction based on social media dataset using CNN-LSTM to classify the accurate Aggression level
Rahul Sai Ganesh,T. Devi +1 more
TL;DR: In this article, an ensemble method based on voting is used to detect the issue of aggression in social media using CNN and Long Short Term Memory (LSTM) classifiers.
Journal ArticleDOI
Development of a Data Clustering Algorithm for Predicting Heart
Bala Sundar,T. Devi,N Saravanan +2 more
TL;DR: The research result shows that the integration of clustering gives promising results with highest accuracy rate and robustness in prediction of heart disease diagnosis with real and artificial datasets.
Journal ArticleDOI
Software metrics validation methodologies in software engineering
K.P. Srinivasan,T. Devi +1 more
TL;DR: The validation methodology, techniques and different properties of measures that are used for software metrics validation are discussed, which are a critical task in any engineering project.
Proceedings ArticleDOI
E-TLCNN Classification using DenseNet on Various Features of Hypertensive Retinopathy (HR) for Predicting the Accuracy
TL;DR: In this article, an enhanced transfer learning-convolutional neural network (E-TLCNN) model is proposed for diagnosing hypertension using high quality images from fundus images.