SANJIT KUMAR
Sardar Vallabhbhai National Institute of Technology Surat, Bennett University, Indian Institute of Technology Patna, National Institute of Technology Agartala, SRM Institute of Science and Technology
Research areas: Earth and Planetary Sciences · Earth-Surface Processes · Hydrology and Sediment Transport Processes · Hydrological Forecasting Using AI · Hydraulic flow and structures
0000-0001-6000-6365
About
I am Dr. Sanjit Kumar, an assistant professor in the Department of Computer Science and Engineering at Sardar Vallabhbhai National Institute of Technology (SVNIT) Surat, India. My current research interests are image processing, computer vision, machine learning, deep learning, and time series forecasting. Application of hybrid, ensemble, standalone machine learning and deep learning models and developed tools in inter-disciplinary areas like hydrology and sediment transport. Attention gate and Recurrent Residual Convolutional Neural Network-based UNet deep learning model are used in flood area segmentation. Image outpainting for extrapolation and image aesthetics to recommend lens among triplet lens cameras. Image inpainting model using GAN model with accurate text mask ROI generation and inpainting of the text ROIs for seamless overlay of the target text. In 2024, I received my Ph.D. from the Computer Science and Engineering Department at the Indian Institute of Technology Patna, India. In 2019, I received my M.Tech. in Computer Science and Engineering from the National Institute of Technology, Agartala. In 2017, I received my B.Tech. in Computer Science and Engineering from Motihari College of Engineering.
Employment
-
Sardar Vallabhbhai National Institute of Technology Surat Assistant Professor2026 - Present
-
Bennett University Assistant Professor2025 - 2026
-
SRM Institute of Science and Technology Assistant Professor2024 - 2025
Education
- 2020 - 2024
- 2017 - 2019
Projects & Funding
Projects & funding information is unavailable.
Publications (19)
- Hybrid Machine Learning for Predicting Particle Froude Number in Auto-washout Drainage Systems with Sedimented Beds Save
- Optimizing Intrusion Detection Systems Using Machine Learning for Enhanced Cybersecurity and Threat Prevention Save
- Standalone and novel hybrid ML models for estimating stream velocities in a river channel with vegetation Save
- Knowing When Not to Answer: Mitigating Social Bias in LLMs via Epistemic Abstention Save
- Standalone and Hybrid machine learning approaches to predict sediment load in an alluvial channel Save
- Anaphora Resolution through Salience in Magahi: A Syntactic and Semantic Analysis Save
- The Power of AI in Banking 4.0: Enhancing Customer Experience and Operational Efficiency Save
- AI-driven predictions of geophysical river flows with vegetation Save
- Efficient functioning of a sewer system: application of novel hybrid machine learning methods for the prediction of particle Froude number Save
- Estimation of Particle Froude Number in Deposited Bed Condition Using Hybrid Machine Learning Models Save
- Forecasting of time-dependent scour depth based on bagging and boosting machine learning approaches Save
- Forecasting particle Froude number in non-deposition scenarios within sewer pipes through hybrid machine learning approaches Save
- Predict Total Sediment Load Using Standalone and Ensemble Machine Learning Models Save
- Predicting flow velocity in a vegetative alluvial channel using standalone and hybrid machine learning techniques Save
- Estimation of time dependent scour depth around circular bridge piers: Application of ensemble machine learning methods Save
- Application of novel hybrid machine learning techniques for particle Froude number estimation in sewer pipes Save
- Estimation of Time-Dependent Pier Scour Depth Using Ensemble and Boosting-Based Data-Driven Approaches Save
- Radial Basis Function Regression (RBFR), ARRBFR models for Estimation of Particle Froude Number in Sewer Pipes Under Deposited Conditions Save
- Predicting the abrasion loss of open-graded friction course mixes with EAF steel slag aggregates using machine learning algorithms Save