Email Scholar GitHub LinkedIn

AI/ML Projects & Applications

Here's a selection of my practical projects demonstrating the application of AI and Machine Learning in diverse fields.

Patient Risk Stratification
Patient Risk Stratification Model (Heart Disease)

Healthcare | Classification

This project applies machine learning to predict the risk of heart disease based on patient health data. By combining efficient preprocessing techniques with advanced classification models, the system delivers accurate and reliable predictions that can support early medical intervention.

Brain CT Analysis
AI-Powered Brain CT Image Analysis for Anomaly Detection

Healthcare | Image Processing

This project implements a deep learning approach to classify brain CT scans as Healthy or Tumor. It combines a custom-built CNN with powerful pre-trained models like VGG16, ResNet50, and DenseNet121 to enhance accuracy and efficiency. Key features include automatic dataset splitting, performance evaluation with metrics and visualizations, and a comparative analysis to determine the best-performing model.

Spatial Interpolation
Geostatistical Spatial Interpolation Enhanced with AI Regression Models

Engineering | Spatial Interpolation Modeling

This project delivers an end-to-end spatial interpolation system that integrates advanced AI regression models with geostatistics to accurately predict geothermal resource potential. The hybrid approach significantly improves spatial prediction accuracy for informed decision-making in energy exploration.

Weather AI
Predictive Weather Modeling using Time-Series AI

Environmental Science | Time-Series Forecasting

This project applies machine learning to predict daily precipitation using key weather parameters like specific humidity, relative humidity, and temperature. Multiple models are trained, evaluated, and compared to identify the most accurate forecasting approach.

Anomaly Detection
Seismic Soil Liquefaction Analysis Tool

Soil Dynamics | Geotechnical Engineering

This desktop application simplifies the evaluation of soil liquefaction risk by computing the Liquefaction Potential Index (LPI) and Liquefaction Severity Number (LSN) from geotechnical inputs like SPT, CPT, and site-specific data. It’s a practical tool for geotechnical engineers, researchers, and students working in earthquake-prone areas.

UHPC Design
AI-Driven Design of Ultra-High Performance Concrete (UHPC)

Civil Engineering | Advanced Materials

Leveraged advanced AI algorithms to explore and optimize complex mix designs for Ultra-High Performance Concrete (UHPC), facilitating the development of materials with superior strength and durability properties.

Soil Compaction
AI-Optimized Soil Compaction and Compression Parameters

Civil Engineering | Geotechnical Engineering

This application predicts Optimum Moisture Content (OMC) and Maximum Dry Density (MDD) using pre-trained Gradient Boosting models based on soil properties like Gravel, Sand, Silt, Liquid Limit, Plastic Limit, and Compaction Energy. It also dynamically computes Clay content and Plasticity Index from user inputs for accurate and efficient soil compaction analysis.

Concrete Strength
Machine Learning for Soil Compression Prediction (Consolidation)

Civil Engineering | Material Science

This project uses artificial intelligence to predict the Compression Index (Cc) and Swelling Index (Cs) from key soil properties such as soil type, moisture content, and void ratio. By reducing reliance on time-consuming lab tests, it supports faster, data-driven decisions in geotechnical and civil engineering projects.

XAI Project
Explainable AI (XAI) for Engineering Systems: Parametric Studies

Engineering | Model Interpretability

Gain a deeper understanding of your model’s behavior with this XAI package — a Python toolkit for exploring how input features shape predictions. Whether you are comparing models or uncovering hidden patterns, this XAI brings clarity to complex AI systems through intuitive parametric analysis.

XAI Package Demo
Interactive XAI Package

Tool Development | AI Interpretability

This Python module enhances model interpretability by analyzing how input features influence predictions. Designed for explainable AI (XAI), it supports sensitivity analysis, and visual comparisons across multiple machine learning models and datasets.

Civil Engineering AI Suite
Civil Engineering AI Suite (Ongoing Development)

Civil Engineering | Full Stack AI

Developing a comprehensive AI suite for civil engineering applications, encompassing modules for structural analysis, material optimization, and construction planning using advanced machine learning techniques.

Fitness and Wellness App
AI-Powered Fitness and Wellness App (Ongoing Development)

Wellness | Fitness

Building an intelligent mobile application that uses AI to provide personalized fitness plans, track user progress, and offer nutritional advice, aiming to enhance overall health and wellness.