PESU Research Foundation
PESURF
"Fostering Thought. Fueling Innovation. Interdisciplinary Minds. Transformative Outcomes."
About PESURF
PESU Research Foundation (PESURF) serves as a pivotal anchor for research within the university, committed to nurturing a vibrant research culture that drives scholarly excellence and interdisciplinary innovation. Fostering innovative, yet frugal solutions to address pressing real-world challenges is central to our engagement with the budding researchers.
Areas of Research
3Our Objectives
2Create an ecosystem that empower the students and faculty in high-impact research. Develop innovative, frugal solutions for societal challenges in multidisciplinary domains.
Bridge the academia - industry gaps through mutually beneficial collaborative research. We onboard organizations and research advisors to work along with our faculty and students in these projects.
Active & Completed Projects
2This is a collaborative project of PESU IMSR and Computer Science & Engineering, EC Campus funded by PES University.
Currently we have the following opportunities for collaboration.
1. Students - join us as Interns to work on an exciting healthtech project.
We welcome student interns from departments of CSE, CSE/AIML and Nursing to join our project.
2. Faculty - collaborate with us to expand the scope of the project
3. External Researchers - join us to bring impactful research outcomes
4. Entrepreneurs - commercialize some of our research findings
Contact for more details: sudeepar@pes.edu
Publications:
1. The AgeWell Index: An RF-Seeded Adaptive Genetic Algorithm for Explainable Aging Assessment in Mid-Life Adults – Doi: 10.1109/IITCEE67948.2026.11394091.
2. “Unsupervised Learning for Successful Ageing: Integrating PCA And Autoencoders in the Construction of a Multi-Domain Composite ageing index”, presented at the 10th International Conference on Information System Design and Intelligent Applications (ISDIA-2026) Organized by University of Wollongong in Dubai
Noncognitive skills define a person's attitudes and behaviors in general and they are distinct from cognitive skills or intellectual capabilities. Research in the recent past posited noncognitive skills such as self regulation, resilience, social skills etc. as foundational to educational success, often acting as better predictors of long-term academic and life outcomes than cognitive ability alone. This project explores the role of noncognitive skills specifically in higher education. Objectives of the study included identifying and measuring relevant noncognitive skills that affect academic performance, enabling right interventions and enhanced academic success.
Publications:
D. Suryaprasad, S. Jayadevappa and B. Shah, "Learnability Index – a Composite Measure for Non-Cognitive Skills Relevant in Academics," 2020 IEEE International Conference on Teaching, Assessment, and Learning for Engineering (TALE), Takamatsu, Japan, 2020, pp. 349-354, doi: 10.1109/TALE48869.2020.9368476.
Product:
Learnability Index Scale: An assessment tool based on self-reported Likert Scale based instrument for measuring non-cognitive skills relevant in the academic environment.
Our Researchers
6
Research Funding
1 funding source
1 funding source
Tools & Technologies
IBM SPSS Statistics is a comprehensive, user-friendly software platform for advanced statistical analysis, data management, and data visualization. "IBM SPSS Statistics is a comprehensive statistical analysis platform designed to help organizations and individuals extract reliable insights from data. It combines robust statistical testing, predictive modeling, regression, and forecasting with streamlined data preparation and automated analysis. With built-in extensibility for Python and R, scalable licensing, and deployment flexibility, it empowers its users across levels to move confidently from data to defensible, data-driven decisions." For more details: https://www.ibm.com/products/spss-statistics
Add-on module for IBM SPSS Statistics for regression models studies. "IBM® SPSS® Regression enables you to predict categorical outcomes, create regression models, analyze model summaries and apply various nonlinear regression procedures to datasets when studying consumer buying habits, treatment responses, efficacy of diagnostic measures, credit risk analysis and other situations where ordinary regression and data analysis techniques are limiting or inappropriate." More details available at https://www.ibm.com/products/spss-statistics/regression
