Skip to main content

Applied Systems & Prototypes

Projects

A collection of research implementations, experimental sequence modeling architectures, and verified software engineering applications.

Research Projects

Algorithm design, model implementations, and benchmark evaluations in trajectory representation and machine learning

Trajectory Representation LearningUnder Review

DeltaPath: Gated Delta-Rule Encoding for Efficient Vehicle Trajectory Representation Learning

A gated delta-rule encoding framework designed for efficient, long-sequence trajectory representation learning in intelligent transportation systems.

Challenge: Traditional recurrent models struggle with long-range dependencies, while full-attention Transformers incur quadratic computational complexity when processing dense vehicle trajectory sequences.
Methodology: Formulates a gated delta-rule sequence encoder that dynamically updates memory representations while maintaining linear computational efficiency with respect to trajectory sequence length.
Impact / Findings: Achieved superior representation quality on trajectory similarity and downstream routing tasks while substantially cutting training and inference overhead.
PythonPyTorchSequence ModellingSpatiotemporal Data Mining
Trajectory Prediction & Attention ModelsAccepted

TSCA-Net: Temporal-Spatial Clique Attention for Multimodal Pedestrian Trajectory Prediction

Temporal-spatial clique attention network modeling multi-agent interactions and environmental contexts for robust multimodal trajectory forecasting.

Challenge: Accurate trajectory forecasting in crowded environments requires joint modeling of subtle individual intentions, complex social conventions, and multi-agent spatial cliques.
Methodology: Introduces a temporal-spatial clique attention mechanism that groups interacting pedestrians into topological cliques and extracts coordinated motion features over time.
Impact / Findings: Demonstrated competitive displacement error reductions across benchmark pedestrian trajectory datasets (accepted at MSN 2026).
PythonPyTorchClique AttentionPedestrian Dynamics
Medical Computer VisionPublished

Transfer Learning-Based COVID-19 Detection Using Chest X-Ray Images

A deep transfer learning pipeline utilizing pretrained convolutional representations coupled with a tailored classifier for diagnostic radiography screening.

Challenge: Limited labeled medical imaging datasets during critical health events impede training deep neural networks from scratch without severe overfitting.
Methodology: Leveraged pretrained convolutional feature extractors fine-tuned with customized classification layers and rigorous data augmentation on chest X-ray scans.
Impact / Findings: Achieved robust diagnostic classification performance on multi-class radiography benchmarks (published in IEEE QPAIN 2025).
PythonPyTorchTransfer LearningComputer Vision

Software Engineering Projects

Full-stack web applications demonstrating scalable architecture, database modeling, and interactive frontend development

DevSkill — Learning Management System (LMS)

DevSkill — Learning Management System (LMS)

2023 – 2024

A complete Learning Management System featuring interactive course catalogs, student enrollment workflows, lesson progress tracking, and administrative controls.

Approach: Architected a responsive frontend with React and Tailwind CSS, coupled with modular Express.js REST APIs and MongoDB for high-throughput course and user data handling.

Outcome: Delivered a production-ready, accessible web application with smooth client-side routing, modular components, and reliable backend services.

ReactNode.jsExpress.jsMongoDBTailwind CSSREST API
Sales & Inventory Management System (Windows App)

Sales & Inventory Management System (Windows App)

2021

A Windows-based sales and inventory management application featuring role-based access, product and stock management, sales processing, and business performance analysis.

Approach: Developed a Windows Forms application using C# with a layered architecture, separating business logic and data access into dedicated modules. Integrated Microsoft SQL Server for data management and implemented role-based access control for administrative and user operations.

Outcome: Delivered a functional desktop management system with user authentication, dedicated dashboards, product and inventory management, sales tracking, profit analysis, and profile management.

C#.NET FrameworkWindows Forms (WinForms)Microsoft SQL ServerSQLLayered Architecture
ChronoDial — Watch E-Commerce Platform

ChronoDial — Watch E-Commerce Platform

2023

A responsive e-commerce web application with product catalog navigation, item filtering, user authentication, and shopping cart management.

Approach: Built interactive product discovery components using React and responsive design principles, integrated with backend data stores and authentication.

Outcome: Implemented a clean, reliable storefront with client-side state persistence and responsive layouts across desktop and mobile screens.

ReactNode.jsExpress.jsMongoDBResponsive Web DesignREST API