• 18 Citations
  • 3 h-Index
If you made any changes in Pure, your changes will be visible here soon.

Personal profile

Research interests

Research Expertise: 
Data Mining and Statistical Learning | Robust Estimation | Bayesian Statistics

We are pursuing several lines of research to identify and validate the use of statistical learning/data mining methods with multidisciplinary data. 

Projects include:
Biomarker discovery for neurogenerative diseases

Peak detection with maximum entropy principal

Clustering mix attributes – network security

Spoof detection and Speaker identification/verification in biometrics

Assessing robust methods for analyzing multivariate data Telemedicine/Telehealth statistical learning

Member of:
American Statistical Association (www.asa.org)
Institute of Mathematical Statistics (www.imstat.org)
Institute of Applied Statistics Sri Lanka (www.iappstat.lk)
Data Science Association

Education/Academic qualification

Fingerprint Fingerprint is based on mining the text of the experts' scientific documents to create an index of weighted terms, which defines the key subjects of each individual researcher.

Data mining Engineering & Materials Science
Clustering algorithms Engineering & Materials Science
Robust Estimation Mathematics
Classifiers Engineering & Materials Science
Pulse amplitude modulation Engineering & Materials Science
Model Comparison Mathematics
Expectation Maximization Mathematics
Count Data Mathematics

Network Recent external collaboration on country level. Dive into details by clicking on the dots.

Research Output 2009 2019

  • 18 Citations
  • 3 h-Index
  • 6 Conference contribution
  • 3 Article
  • 1 Chapter
  • 1 Conference article

Accuracy of clustering prediction of PAM and K-modes algorithms

Dixon, M. G., Genov, S., Hnatyshin, V. & Thayasivam, U., Jan 1 2019, Advances in Information and Communication Networks - Proceedings of the 2018 Future of Information and Communication Conference FICC, Vol. 1. Bhatia, R., Arai, K. & Kapoor, S. (eds.). Springer Verlag, p. 330-345 16 p. (Advances in Intelligent Systems and Computing; vol. 886).

Rowan University

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Pulse amplitude modulation
Clustering algorithms

A pattern recognition approach to signal to noise ratio estimation of speech

Awolumate, P. A., Rudy, M., Ramachandran, R., Bouaynaya, N., Dahm, K., Nazari, R. & Thayasivam, U., Jun 24 2017, In : ASEE Annual Conference and Exposition, Conference Proceedings. 2017-June

Rowan University

Research output: Contribution to journalConference article

Pattern recognition
Signal to noise ratio
Additive noise
Identification (control systems)
3 Citations

Autoantibodies as diagnostic biomarkers for the detection and subtyping of multiple sclerosis

DeMarshall, C., Goldwaser, E. L., Sarkar, A., Godsey, G. A., Acharya, N. K., Thayasivam, U., Belinka, B. A. & Nagele, R., Aug 15 2017, In : Journal of Neuroimmunology. 309, p. 51-57 7 p.

Rowan University

Research output: Contribution to journalArticle

Multiple Sclerosis
Relapsing-Remitting Multiple Sclerosis
Protein Array Analysis
1 Citations

Robust speaker verification with a two classifier format and feature enhancement

Edwards, J. S., Ramachandran, R. & Thayasivam, U., Sep 25 2017, IEEE International Symposium on Circuits and Systems: From Dreams to Innovation, ISCAS 2017 - Conference Proceedings. Institute of Electrical and Electronics Engineers Inc., 8050775

Rowan University

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Fusion reactions
Additive noise
Analysis of variance (ANOVA)
2 Citations

Accuracy of class prediction using similarity functions in PAM

Thayasivam, U., Hnatyshin, V. & Muck, I. B., May 19 2016, Proceedings - 2016 IEEE International Conference on Industrial Technology, ICIT 2016. Institute of Electrical and Electronics Engineers Inc., Vol. 2016-May. p. 586-591 6 p. 7474815

Rowan University

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Clustering algorithms