Research
My focus is on enhancing UAV operations through cutting-edge parallel processing techniques and pioneering the integration of edge computing architectures into the fabric of autonomous aerial systems. By uncovering novel insights and contributing to the evolution of UAV technologies, my work aims to redefine the benchmarks of computational capabilities in the skies, propelling advancements across industries and shaping the future of autonomous airborne systems.
If you are interested in becoming a collaboratior with me to better understand my research or increase productivity, feel free to email and we can schedule a meeting to discuss further.
Edge AI framework for Precision Agriculture and Insect Pest Monitoring
Developing WASP, an edge-AI framework that combines robust insect classification with adaptive LoRaWAN communication for reliable pest monitoring in real-world agricultural environments. WASP uses curriculum-based training to make lightweight vision models resilient to weather and lighting degradation and location-aware data-rate adaptation to improve wireless reliability in dense vegetation. The system bridges machine learning, edge computing, and low-power networking for scalable precision agriculture.
Automatic Deployment Right-Sizing Through Hyperparameter Optimization
Internet of Things (IoT) and Edge deployments are diverse, complex, and highly constrained. These properties make correctness difficult or impossible to verify a priori. We present early work on an automatic deployment right-sizing tool for edge and IoT deployments. Our tool uses the PROWESS testbed to accurately emulate candidate deployment form-factors, and optimizes deployment parameters to minimize costs. We show that our early work finds optimal deployment configurations 6.3X faster than Bayesian optimization, a state of the art hyperparameter optimization technique.
