Index
AI for Inflammatory Skin Pathology: Psoriasis and Eczema Classification in Whole-Slide Images
Exploring foundation models for high-resolution whole-slide image classification, with a focus on interpretable predictions through attention maps that align with medically relevant regions.
Evaluating Time-Frequency Representations for Intelligent Fault Analysis in Power System Protection
This project investigates how different time-frequency representations, including spectrograms, wavelets, scalograms, and Gramian Angular Fields, affect deep learning performance in fault analysis tasks. Using high-resolution current and voltage signals, it benchmarks various representation strategies across multiple neural network architectures. The goal is to determine which transformations capture fault dynamics most effectively and enable robust model generalization. The findings will guide the design of future machine learning based protection systems for resilient and data-driven power grids.
Multi-Task Learning for Integrated Fault Analysis in Power System Protection
Modern electric power systems require rapid and reliable fault analysis to ensure grid stability amid increasing renewable integration. This project explores multi-task learning as a unified framework for simultaneously detecting, classifying, and localizing faults in transmission networks. By sharing representations across tasks, the model aims to reduce redundancy and enhance generalization compared to traditional single-task approaches. The results will contribute to the development of scalable, data-driven protection schemes for future intelligent power grids.
A Resource-Efficient AC Power Flow Prediction Framework using Physics-Informed GNNs and RL-Based Model Compression
1. Motivation
Modern power grids require accurate, real-time AC power flow prediction to ensure secure and efficient operation. Graph Neural Networks (GNNs) are promising due to their ability to model the grid’s topological and nonlinear properties. However, standard GNNs are often too large for edge deployment, and naïve compression can lead to physically infeasible predictions. There is a pressing need for compression techniques that preserve physical accuracy.
2. Objective
This project aims to develop a two-phase framework:
1. Physics-Informed GNN: Predict voltage magnitudes and phase angles from power grid snapshots using AC power flow laws.
2. RL-Guided Compression: Learn to prune and quantize the model efficiently while preserving physical feasibility.
3D detection of Abdominal Trauma in CT images using cross-attention
Interpretable Vision Transformers with Attention Maps for Phonological Precision Assessment from MRI
Reinforcement Learning for Centralized Fault Coordination in Power Systems
In this project, we develop a hybrid reinforcement learning framework for adaptive protection in power grids with high DER penetration. A centralized model is first trained using system-wide current, voltage, and impedance data to coordinate both primary and backup relays, followed by decentralized fine-tuning using only local measurements to ensure autonomous operation in case of communication loss. The approach aims to improve relay coordination, robustness, and decision-making by exploring different recurrent network architectures such as RNN and LSTM.
Transformer-Based Forecasting Model for Fault Detection in Power System Protection
This project explores transformer-based forecasting models for intelligent fault detection in electrical power systems. The approach reframes fault detection as a prediction problem, where the model learns the normal temporal dynamics of high-frequency voltage and current waveforms and identifies deviations as anomalies. By doing so, it avoids the heavy reliance on labeled data that limits many existing machine learning approaches in protection systems.
The study evaluates several transformer architectures on a large set of physics-based simulations that represent realistic grid conditions, fault types, and operating scenarios. The results demonstrate that prediction-based attention models can achieve high detection accuracy and robustness, even under scarce data and varying grid configurations. This work provides a promising foundation for more adaptive, data-efficient, and resilient protection schemes in future power networks.
Report Generation in pathology using WSIs
This project focuses on developing methods for processing large-scale digital pathology datasets and extracting meaningful features from whole slide images to support automated report generation. Emphasis is placed on efficient handling of gigapixel image data and preparing it for use in vision-language models for clinical applications.