Ramya G. R. currently serves as an Assistant Professor (Senior Grade) at the Department of Computer Science and Engineering, School of Engineering, Amrita Vishwa Vidyapeetham, Coimbatore. She joined the department in June 2008. She received her M.E. in Computer Science in the year 2008 and B.E. in Information Technology in the year 2004. She is currently a Ph. D. student at the School of Engineering, Amrita Vishwa Vidyapeetham, Coimbatore. Her areas of research include Social Influence Maximization, Predictive Analytics, Machine Learning, Deep Learning and Pattern Recognition. She has guided many student projects at the undergraduate level.
Year of Publication | Title |
---|---|
2017 |
M. R. Nair, G. R. Ramya, and Sivakumar, P. B., “Usage and Analysis of Twitter During 2015 Chennai Flood towards Disaster Management”, Procedia Computer Science, vol. 115. Elsevier B.V., pp. 350-358, 2017.[Abstract] Social media plays a major role in the propagation of information during disasters. This paper mainly contains a study regarding how people of Chennai used social media especially twitter, in response to the country's worst flood that had occurred recently. The tweets collected were analysed using machine learning algorithms such as Random Forests, Naive Bayes and Decision Tree. By comparing the performances of all the three it was found that Random Forests is the best algorithm that can be relied on, during a disaster. This paper also targeted the sources of the Twitter messages to explore the most influential users of Chennai flood. More »» |
Year of Publication | Title |
---|---|
2016 |
G. R. Ramya and Dr. Bhagavathi Sivakumar P., “Advocacy Monitoring of Women and Children Health through Social Data”, vol. 9, no. 6, 2016.[Abstract] Background/Objective:To classify the extracted women and children health data from the social media and to utilize it for advocacy monitoring.;Methods/Statistical Analysis:Advocacy monitoring can be performed by extracting the social data related to women and children health. A keyword based search technique is used for this purpose. The children health details like the nutrition deficiencies, lack of vaccination, diseases like pneumonia, diarrhea and malaria that affect new born children and the women health data like maternal weight loss, maternal mortality rate, sanitation and antenatal care during maternity can be gathered from the social media using keyword based search technique. The extracted data are needed to be analyzed and classified into related data groups using Decision tree C4.5 and Support Vector Machine (SVM).Findings:Decision tree C4.5 algorithm classifies the data based on the concept of information entropy. The data are classified at each node of the tree after analyzing the attribute of the data. SVM analyzes the extracted data and uses the health parameters listed to group the related data. The approach is of two stages: training and testing. The training dataset is build using the health data representing the listed search words. This training set is used to classify the test data. The data are tested with the training set and only women and child health data are stored in classes that help in advocacy monitoring in an efficient way.;Applications/Improvements:Advocacy monitoring is required to define the socio-economic status of a region. The proposed approach efficiently classifies the extracted social data of women and children health and aids in effective advocacy monitoring. More »» |