Sitemap

A list of all the posts and pages found on the site. For you robots out there, there is an XML version available for digesting as well.

Posts

Future Blog Post

less than 1 minute read

Published: January 01, 2199

This post will show up by default. To disable scheduling of future posts, edit config.yml and set future: false. Read more

Blog Post number 4

less than 1 minute read

Published: August 14, 2015

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool. Read more

Blog Post number 3

less than 1 minute read

Published: August 14, 2014

Blog Post number 2

less than 1 minute read

Published: August 14, 2013

Blog Post number 1

less than 1 minute read

Published: August 14, 2012

portfolio

Energy Consumption Disaggregation and Forecasting

Published: April 01, 2023

Time-series forecasting application achieving 95% accuracy for 3-day predictions using LSTM and Graph Signal Processing. Selected for college-level Demo-Day with 90%+ appliance-level energy disaggregation accuracy. Read more

Tweeshirt – AI-Powered E-commerce Platform

Published: February 01, 2024

GenAI-powered e-commerce platform enabling personalized merchandise creation from social media content using Stable Diffusion. Processes 300+ daily requests with sub-2-second latency using Next.js, Node.js, and Printrove API integration. Read more

TCE Hostel Admin Management System

Published: September 01, 2024

Full-stack MERN application managing 1000+ student records, currently in active production. Reduces manual record-keeping time by 85% and eliminates 95% of data-entry errors using MongoDB Atlas with 99.99% uptime. Read more

Locallu – Freelancer-Employer Marketplace

Published: November 01, 2024

Dual-sided platform connecting freelancers and employers with separate dashboards, MVC architecture, and real-time notifications. Built with React.js, Node.js, MongoDB, and Firebase for instant messaging and job management. Read more

LegalAppa – AI-Driven Legal Document Platform

Published: December 01, 2024

Full-stack platform serving 15+ lawyers with AI-powered document automation and LaTeX compilation. Reduced manual document preparation time by 97% using React.js, Node.js, Firebase, and LLM integration. Read more

Emotion Recognition Research using XAI and Fair AI

Published: May 01, 2025

GRU-based emotion classification system achieving 95% accuracy using physiological biosignals (ECG, EMG, GSR, respiration, BVP). Implemented SHAP/LIME explainability and fairness-aware techniques reducing demographic bias by 30%. Read more

HamAI – AI-Powered Budget Tracking Application

Published: January 01, 2026

Production-ready budgeting application with AI-powered transaction parsing using Google Gemini. Full-stack solution with React.js frontend, Node.js/Express backend, Firebase authentication, and comprehensive analytics dashboard. Read more

Multi-Agent Research Assistant

Published: March 01, 2026

Self-correcting multi-agent RAG system for querying academic research papers through natural language. Built with LangGraph, FAISS, and MCP — featuring a critic-refine loop, intelligent query routing, and Claude Desktop integration. Read more

publications

Performance Analysis of Regression Models in Solar PV Forecasting

IEEE Conference, March 18-20, 2023 Google Scholar

Published on June 1, 2023. This work aims to produce reliable short-term forecasting using machine learning methods such as Linear Regression, Random Forest Regression, and Decision Tree Regression. Results show 99% accuracy for the proposed models. Read more

Recommended citation: A.R. Kaushik, S. Padmavathi, K.S. Gurucharan, and S.Charles Raja, "Performance Analysis of Regression Models in Solar PV Forecasting," IEEE Conference, March 18-20, 2023.

Enhancing Human Activity Recognition: An Exploration of Machine Learning Models and Explainable AI Approaches for Feature Contribution Analysis

2023 International Conference on Energy, Materials and Communication Engineering (ICEMCE), December 14-15, 2023 Google Scholar

Published on February 21, 2024. This study utilizes an Activity of Daily Living (ADL) dataset collected from 30 participants who performed six distinct activities while wearing smartphones equipped with sensors. Explainable AI (XAI) techniques like LIME and SHAP are used to understand the attributes significantly influencing model predictions. Read more

Recommended citation: A. R. Kaushik, K. S. Gurucharan and S. Padmavathi, "Enhancing Human Activity Recognition: An Exploration of Machine Learning Models and Explainable AI Approaches for Feature Contribution Analysis," 2023 International Conference on Energy, Materials and Communication Engineering (ICEMCE), Madurai, India, 2023, pp. 1-6, doi: 10.1109/ICEMCE57940.2023.10434184.

Enhanced Drone Classification using Transfer Learning and Optimized RF-Spectrogram

Presented at Conference on July 6, 2025 GitHub

Presented on July 6, 2025. This paper presents important contributions toward state-of-the-art drone classification systems that are deployable in challenging environments. Building on the groundwork laid by existing drone categorization methods, we provide two major contributions: (i) a new processing pipeline that converts RF signals into optimized spectrogram images for computer vision applications, and (ii) an extensive analysis of nine state-of-the-art CNN models. Read more

Recommended citation: Kaushik A R, Annaamalai U, and Padmavathi S, "Enhanced Drone Classification using Transfer Learning and Optimized RF-Spectrogram," Presented at Conference, July 6, 2025.