Specialization

Statistical and machine learning based solutions for the problems which involves recognition, classification, clustering, modeling, estimation and information retrieval

Email

saurabh.bhardwaj@thapar.edu

Specialization : Machine Learning

Email and Phone : saurabh.bhardwaj@thapar.edu , +91-7528981415

Biography :  Professor and Research Scientist with 23+ years of academic and research experience, specializing in statistical and machine learning methodologies with a focus on computational biology. Currently serving as Professor and Associate Dean of Faculty Affairs at Thapar Institute of Engineering and Technology, India, and Research Scientist at Virginia Tech, USA.

Actively involved in the development of innovative analytic tools for molecular feature identification, expression analysis, and unsupervised deconvolution. Demonstrated expertise in higher education teaching, research leadership, and cross- institutional collaborations.

Notable contributions include publications in Bioinformatics, IEEE Transactions on Cybernetics, and Scientific Reports. Passionate about advancing data-driven biological discovery through robust algorithmic frameworks and committed to mentoring the next generation of researchers.

Previous research applications span speaker identification, brain fingerprinting, clustering, and solar radiation prediction. Holds a Postdoctoral Fellowship from Virginia Tech University, USA, and a Ph.D. in Instrumentation & Control Engineering from Delhi University (NSIT), India.

Education

Experience

Research Guidance

Ph.D. Thesis completed     -               05

Ph.D. Thesis ongoing           -               01

US Govt. Projects as Research Scientist, Virginia Tech University, USA

Project – 1 :  Genomic & Proteomic Architecture of Atherosclerosis          

Project – 2 :  Metabolomics analysis of Coronary Artery Disease (CAD)   

Project – 3 :  Cell communication in antiestrogen resistance                      

Research Project Completed

Brain Fingerprinting: Detection of physiological based concealed information in the brain of suspect using Machine Learning Techniques

Responsibilities

• Associate Dean Faculty Affairs (ECED and EIED)
• Member Institute Ranking Team
• UG Coordinator, Electronics Instrumentation and Control Engineering
• D. Coordinator, Electrical and Instrumentation Engineering Department
• Deputy Superintendent (End Semester Examination).
• National Board of Accreditation (NBA) Coordinator.
• Member of the ABET Committee.

Teaching

Courses Taught                                                                               

• Machine learning Techniques                              
• Soft Computing Techniques
• Measurement Science and Techniques
• Intelligent Techniques and Applications
• Industrial Instrumentation
• Analog and Digital Electronics

Lab Setup

• Industrial Instrumentation Lab
• Lab In-charge up to Dec 2022

Course Developed

• Computational Techniques for Research course for Ph.D. Students

Editor

1. Associate Editor: Springer Nature, Scientific Reports

Keynote Speaker

1. Keynote Speaker at the IEEE International Conference on Modelling, Simulation, and Intelligent Computing (MoSICom 2023) Dubai
   • Topic: Robust and Insightful Tools for Bioinformatics and Intelligent Systems Date: 09-11 December, 2024
   • Organiser and venue: BITS Pilani, Dubai Campus.
2. Keynote Speaker at the 3^rd International Conference on recent advances in computational techniques from 26-27 June, 2025.
   • Organiser and venue: Amity University, Mumbai, India

Award/Fellowship

1. TIET-VT Fellowship: One year
2. Teaching Cum Research Fellow: Three years (2009-2012)
3. Best Paper Award: 3rd International Conference on Information Systems Design and Intelligent Applications, Date: January 9, 2016
4. Best Presentation Award: Workshop: Computational Intelligence: Theories, Applications and Future Directions, Date: July 14, 2013, Venue: IIT Kanpur, India
5. Student Research Convention Achievement: ANVESHAN-08, Date: February 13-15, 2008, Ranked 1st Position in the poster presentation in parallel session. Ranked 2nd Position in the final presentation
6. Best Presentation Award: Symposium: NASET-2008, Date: March 7-8, 2008, 1st Prize in final presentation
7. Best Presentation Award: 2nd Chandigarh Science Congress (CHASCON-2008), Date: March 14-15, 2008
8. Outstanding Performance Award: Hotline-Switchgear & Controls, Delhi

PROJECTS

1. Unsupervised Deconvolution of Different Datasets using Improved Convex Analysis of Mixtures (CAM): To detect latent sources, their respective source signature genes/metabolites, and their relevant concentration patterns between healthy control and patients for the following datasets: CAD GWAS metabolomic datasets ('Mesa' and 'Rotterdam'), GPAA proteomics, and GPAA RNAseq.

2. Missing Data Imputation of Different Datasets: To impute the missing values for the Fresh frozen LAD45, AA paired Trizol data, and the LAD Trizol data. Further, to conduct a comparative analysis of different missing data imputation methods.

3. Application of Cosine-based One-Sample Test (COT) to Detect Marker Genes Among Many Subtypes: To enhance COT for downregulated signature genes (DSGs) along with upregulated expressed genes (SGs). COT-based detection of both condition-specific SGs and DSGs for the following datasets: GPAA RNAseq, GPAA proteomics, Edinburgh.

4. Integrating Information Set Theory with Deep Learning Principles to Improve Noisy Pattern Classification: To address the critical problem of the absence of robust deep learning models, we propose Information-Set Deep Learning (ISDL) architectures with four variants by integrating information set theory and deep learning principles.
5. Text Independent Speaker Identification: The aim of this project is to develop robust speaker recognition models. Three distinct approaches were developed for this purpose.

6. Pattern Similarity Based Clustering: Two pattern similarity-based techniques were developed for data clustering. The project demonstrates that distance functions are not always sufficient for data clustering, as strong correlations may exist among data vectors even if they are physically distant from each other.

7. Time Series Prediction: To predict chaotic time series data.

8. Solar Radiation Estimation: To estimate solar radiation using machine learning techniques and meteorological data.
9. Brain Fingerprinting: Detection of Physiological Based Concealed Information in the Brain of Culprit using Machine Learning Techniques : The project aimed to use electroencephalogram (EEG) data for the forensic application of identifying concealed information in the human brain.