Research / Programming 
Experiences 

In my pioneering research, "Phoenix: IoT Trust Evaluation Using Game Theory with Second Chance Protocol," I developed a novel trust evaluation framework that significantly enhances IoT security and reliability. Leveraging game theory and Bayesian inference, the framework introduces a "Second Chance Protocol" to accurately identify and reintegrate temporarily malfunctioning devices, thereby optimizing network resource utilization and trustworthiness. My work not only demonstrates a detection rate of 97.99% for low noise levels but also sets new benchmarks in IoT security research, showcasing my deep analytical abilities, innovative problem-solving skills, and my commitment to advancing cybersecurity in smart environments.

​

My Role and Contributions:

As a lead researcher, I spearheaded the development of a hierarchical trust evaluation framework for IoT devices, incorporating innovative strategies such as the "Second Chance Protocol." This protocol uniquely identifies and rehabilitates temporarily malfunctioning nodes, optimizing resource utilization and trustworthiness across the network. Through meticulous experimentation and synthetic data analysis, my team and I demonstrated significant improvements in trust evaluation accuracy and device utilization, setting new benchmarks in IoT security research.

In this groundbreaking study, we explore the impact of soil properties on Ground Penetrating Radar (GPR) signals to enhance subsurface imaging for various applications. As the lead researcher, I spearheaded the integration of gprMax simulations with descriptive statistical analysis and machine learning techniques, notably employing a Random Forest model to distill and evaluate the essential features of GPR signals. This innovative approach not only streamlined the complex GPR data into actionable insights but also markedly improved soil characterization and subsurface analysis accuracy. Our findings, supported by the USDA and conducted at Worcester Polytechnic Institute, underscore my pivotal role in bridging advanced computational methods with geophysical research, thereby offering novel solutions for agriculture, civil engineering, and beyond.

In the transformative study titled "Phantom Tumor Tracking in Dual-Energy Fluoroscopy using a Kalman Filter," we tackle the critical challenge of accurately tracking lung tumors in real-time for radiation therapy (RT), overcoming obstacles posed by tumor motion due to breathing. As a key researcher in this project, I devised and implemented a hybrid approach that integrates template matching with Kalman Filter algorithms, utilizing three distinct physics-based models for motion prediction. This innovative method demonstrated superior performance in tracking tumors obscured by bones, significantly enhancing the precision of RT. Our findings indicate that the Kalman Filter with Spring Motion physics model notably outperformed others, with an average Root Mean Square Error (RMSE) improvement from 1.81 cm to just 0.44 mm. This study, part of the 2020 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), not only showcases the potential of existing fluoroscopic hardware for improved lung radiotherapy but also sets the stage for my continued contributions to the field of bioinformatics and medical imaging technology.

This paper presents a novel Ground Penetrating Radar (GPR)-based framework for precisely estimating root-zone soil moisture, a key parameter in precision agriculture. The approach is structured as follows: First, we generate a synthetic dataset using gprMax, carefully calibrated against real-world data to reflect actual soil conditions. Feature engineering techniques are then employed to extract meaningful features from the GPR signals, followed by a rigorous selection process to identify the most effective machine learning (ML) model for soil moisture prediction. The proposed framework is crucial for optimizing irrigation practices and water resource management, directly contributing to more sustainable agriculture. Finally, we validate our model by integrating synthetic data with real GPR data collected at the SoilX Lab at Worcester Polytechnic Institute (WPI), enhancing prediction accuracy and generalization capability. We aim to support efficient farming practices that lead to better crop yields and food security by ensuring our model's applicability to diverse agricultural environments.