Project archive · 2023–2026
Nine projects show the range: identity from CCTV, grounded legal retrieval, market forecasting, UAV systems, and full-stack products. Metrics appear where the work produced a defensible evaluation.
Document-grounded legal research with hybrid retrieval
A document-grounded legal assistant for Indonesian TNI law revisions, combining fine-tuned language models with hybrid retrieval and reranking.
Delivered a Streamlit prototype that returns document-grounded answers with supporting knowledge-base references.
Individual identification from real-world CCTV footage
A computer-vision system that distinguishes individual swiftlets in noisy CCTV footage through detection, embeddings, and identity classification.
Market forecasting informed by news sentiment
A market-forecasting application that connects five years of price history with news sentiment and LSTM time-series modeling.
Autonomous fire detection for low-connectivity missions
A funded TEKNOFEST concept for autonomous forest-fire detection and mapping, designed to keep image capture useful when connectivity is limited.
The project received TEKNOFEST Turkey 2025 funding; Thariq contributed as a team member.
Calibrated image measurement with 0.01–0.05 cm reported error
A calibrated vision system that turns images into physical measurements with ChArUco, ArUco markers, and automated scale conversion.
Attention-guided detection over a ConvNeXt backbone
A deepfake classifier that combines local attention, global context, and texture evidence while exposing where the network looks.
A unified workspace for planning, focus, and learning
A full-stack learning workspace that brings courses, notes, weekly planning, focus sessions, analytics, and progress into one product.
Delivered the core full-stack planning and study-management workflows.
A funded Transformer concept for two-way communication
A funded Program Kreativitas Mahasiswa concept for two-way communication between BISINDO users and text through Transformer-based NLP.
Selected for Liga Program Kreativitas Mahasiswa ITS.
Aerial fire detection within a UAV development program
A YOLO and OpenCV fire-detection concept developed as part of a broader UAV monitoring and flight-testing program.
Integrated the computer-vision concept into ongoing UAV development activities.