Reem Awad

EngineeRing is a wearable smart ring designed to enable intuitive cursor navigation and gesture-based input through mid-air hand movements. The system integrates IMU motion sensing with Bluetooth Low Energy communication to translate gestures into real-time computer interactions. In addition to general computer interaction, the system was designed with rehabilitation applications in mind, allowing motion tracking and gesture-based exercises that can support motor recovery and physical therapy.

As the Software Lead, I developed the Python-based control software responsible for gesture interpretation and system responsiveness. I implemented sensor fusion techniques to process IMU data and designed algorithms to smooth motion input, reduce jitter, and improve interaction precision. The system supports multiple interaction modes, allowing users to switch dynamically between pointer navigation, gesture typing, presentation control, and rehabilitation-focused motion tracking to illustrate the ring's potential across assistive technology, productivity, and everyday human–computer interaction scenarios.

This project involved building a simulation environment to analyze communication performance in unmanned aerial vehicle (UAV) networks. The simulator models the physical, MAC, and routing layers of wireless communication to study how drone networks behave under varying mobility and interference conditions.

I contributed to the development of the physical-layer communication model, implementing log-distance path loss calculations, RSSI/SNR estimation, interference modeling, and distance-based packet loss. These models allowed the simulator to replicate realistic wireless communication behavior between drones.

The simulator supports experiments with up to 100 UAVs, enabling analysis of network scalability, packet delivery ratio, latency, and energy–throughput tradeoffs. The project was used to evaluate how routing protocols and channel conditions affect network reliability.

To showcase the system, we also developed a web-based interface that visualizes the simulated drone network in real time, allowing users to observe node movement, communication links, and network performance metrics during simulations. The interface provides an interactive way to explore how network behavior changes under different mobility patterns, interference levels, and routing configurations.

This project focused on developing a machine learning system to predict individual medical insurance costs based on demographic and health-related features.

I built an end-to-end regression pipeline that included data preprocessing, feature engineering, cross-validation, and model evaluation. To determine the most effective predictive approach, I implemented and tested three different regression models, comparing their performance using standard evaluation metrics. Through this experimentation process, ensemble methods such as XGBoost produced the best results, achieving an R² score of approximately 0.86.

After identifying the most accurate model, I deployed the solution using Streamlit, a Python framework for building web-based interactive applications. The Streamlit interface allows users to input personal health and demographic information and receive real-time insurance cost predictions, providing an accessible way to demonstrate the model's functionality and performance.

This project involved building a full-stack web application designed to simulate an AI-driven medical consultation platform.

Working collaboratively with a development team, I contributed to both the frontend and backend development, helping build a React-based user interface and supporting backend functionality using FastAPI. My work focused on implementing core application features, integrating front-end components with backend services, and supporting user authentication and session-based interactions.

I also assisted with designing structured data models and organizing backend components to support secure data handling and scalable system architecture. More advanced API architecture and integration were developed by other members of the team, while I focused on ensuring smooth interaction between the user interface and backend services.

The platform demonstrates how conversational AI and modern web technologies can be integrated into digital healthcare tools.