LLM Personalized Music Assistant for Cognitive Tasks
Built an LLM-powered web prototype and designed a study of personalized background music, attention, memory, and planning.
Read the storyResearch
Studies, models, and experimental systems
My projects connect AI and human–AI interaction with software development, sensing, and electronics. They span cognitive-task study design, language-model adaptation, data pipelines, image classification, web applications, interactive environments, and hardware design.
The collection begins with my LLM Personalized Music Assistant, a web prototype and study prepared for future participant data collection. The remaining projects are grouped by technical area so you can explore both detailed case studies and shorter implementation projects.
Main project
Read the case studies
AI, data pipelines and model comparisons
Visual Emotion Recognition on MELD: EmotionCLIP vs. CLIP
Built a video-preprocessing and annotation pipeline and collaborated on comparing EmotionCLIP and CLIP for seven-class emotion recognition.
USGS Earthquake Magnitude Classification Pipeline
Built a Spark pipeline for USGS earthquake data and compared models for multiclass magnitude classification.
Read the storyRecipe Recommendation LLM Fine Tuning with LoRA + RAG
Fine-tuned TinyLlama for recipe recommendations, integrated retrieval, and compared fine-tuned and RAG outputs.
Read the storyMulti Label Retinal Disease Detection via Transfer Learning
Built a multi-label retinal imaging pipeline and fine-tuned CNNs for DR, Glaucoma, and AMD.
Read the storyAge Estimation from Facial Images (Neural Network from Scratch)
Built a feedforward neural network with manual backpropagation and evaluated its generalization on UTKFace.
Real-Time Detection of Traffic Signs and Animals Using OpenCV
A real-time traffic-sign and animal-detection project using OpenCV.
Infant Health Diagnosis Using K-Nearest Neighbors
An infant-health diagnosis project using K-Nearest Neighbors.
Temperature Range Classification with Multilayer Perceptron Neural Networks in PySpark
A temperature-range classification project using multilayer perceptron neural networks in PySpark.
Software and interactive systems
Learnia – Learning Platform
Developed a microservices learning platform that processes study files into summaries, key concepts, and flashcards.
Full-Stack Reputation & Leaderboard System (Mini Social)
Designed and implemented reputation scoring and a dynamic leaderboard for a Flask-based platform.
Multiplayer VR Tyre Changing Simulator (Unity + Photon)
Developed a shared VR tyre-changing environment with real-time and physics-based interaction.
Aura Program AI-Based Video-Call System
Participated in a team project on an AI-based video-call system using multimodal signal analysis; the team won first place in the Aura Program.
Edge computing and sensing
5G-Based IoT Gateway with Edge ML
Developed a distributed edge-cloud IoT gateway for real-time sensor processing and anomaly detection.
Edge Activity Recognition & Fall Detection
Built an activity-recognition and fall-detection pipeline with on-device TinyML inference and cloud monitoring.
Electronics and hardware design
8-bit CPU Design & Simulation in Verilog
Designed and simulated an 8-bit CPU at RTL level using Verilog.
PIC Microcontroller LED Control with Timer Interrupts
Implemented timer-interrupt LED control on a PIC microcontroller and tested it in simulation.
Audio Amplifier Design for Microphone Signal Enhancement
Designed an analog amplifier circuit for microphone signal enhancement.
Precision Spin Coater Design & Construction
A precision spin-coater design and construction project associated with a microfabrication lab.
Discuss the work
To discuss these projects or related research, get in touch.