SM Shaqib

Developed an automated medical image segmentation platform using a modified U-Net architecture with attention mechanisms. This system assists in diagnosing nasal sinus diseases with high precision and is deployed for clinical research exploration.

Built an end-to-end NLP application that automates document analysis and summarization using HuggingFace API and Streamlit. The tool processes large PDFs, extracts key insights, and enables semantic search with interactive Q&A capabilities, showcasing practical applications of retrieval-augmented generation and LLM-based information extraction.

Developed a comprehensive sentiment analysis system for Bangla text using LSTM and Bi-LSTM architectures. Implemented multiple optimization strategies and conducted extensive performance analysis. The system demonstrates state-of-the-art accuracy in low-resource language processing.

Created an AI-powered safety monitoring system that detects vehicle speeds and recognizes safety equipment in construction environments. Uses real-time object detection and tracking to ensure compliance with safety regulations and prevent accidents.

Implemented an explainable deep learning model for insect species classification. The system not only classifies insects with high accuracy but also visualizes the features that contribute to classification decisions, making the model interpretable for ecological researchers.

Developed an efficient real-time system for evaluating strawberry freshness using transfer learning. The lightweight model can run on edge devices and provides instant quality assessments, helping reduce food waste in agricultural supply chains.

Collection of optimized solutions to complex algorithmic problems from platforms like Codeforces. Demonstrates strong problem-solving skills and mastery of data structures, algorithms, and computational thinking essential for AI research.