LLM Personalized Music Assistant for Cognitive Tasks
Built a web prototype and designed a study to investigate personalized music and cognitive performance.
Read the storyResearch
Studies, models, and experimental systems
These projects cover cognitive-task study design, language-model adaptation, image classification, and edge computing. They show my work on prototypes, data pipelines, and model comparisons.
Project collection
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 story5G-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.
Age Estimation from Facial Images (Neural Network from Scratch)
Built a feedforward neural network with manual backpropagation and evaluated its generalization on UTKFace.
Discuss the work
To discuss these projects or related research, get in touch.