Citizen Science for the Sea with Information Technologies: An Open Platform for Gathering Marine Data and Marine Litter Detection from Leisure Boat Instruments

Our IEEE eScience 2023 paper introduces the C4Sea-IT framework, an open platform for collecting marine data from leisure vessel instruments. It leverages the Internet of Things and Cloud Computing to enhance coastal data sharing, with a use case demonstrating marine litter tracking. The ultimate objective is to improve weather and ocean forecasts using AI.

AnB: Application-In-A-Box To Rapidly Deploy and Self-Optimize 5G Apps

Our Application in a Box (AnB) project, presented at SMARTCOMP 2023, simplifies the deployment of remote 5G applications. AnB includes pre-configured hardware and software, allowing quick setup without extensive technical knowledge. It features automated resource management for optimized performance, demonstrating real-world applications and significantly reducing deployment time from months to minutes.

Elixir: A System To Enhance Data Quality For Multiple Analytics On A Video Stream

Our Elixir is a system that enhances video analytics performance from multiple IoT cameras by adjusting camera settings through Multi-Objective Reinforcement Learning (MORL). In tests, Elixir significantly outperformed default settings and time-sharing methods, improving detection rates for cars, faces, persons, and license plates, addressing challenges in multi-analytical unit settings.

Content-aware auto-scaling of stream processing applications on container orchestration platforms

At the PDP 2023 conference, we presented a study on application scaling in microservices deployed via Kubernetes. It critiques the Horizontal Pod Autoscaler (HPA) for inefficient scaling due to neglecting microservice interactions. The proposed DataX AutoScaler improves performance by accounting for these interactions, achieving up to 43% better performance in video analytics applications.

DataX Allocator: Dynamic resource management for stream analytics at the Edge

At the 9th International Conference on IOTSMS 2022, we presented a reinforcement-learning technique to enhance serverless edge computing by optimizing resource allocation for microservices. This innovative approach achieved remarkable improvements in processing rate in real-world applications, demonstrating versatility and efficiency that promise to revolutionize AI and machine learning.

APT: Adaptive Perceptual quality based camera Tuning using reinforcement learning

At the 9th International Conference on Internet of Things: Systems, Management and Security (IOTSMS 2022), we presented a novel reinforcement-learning system called APT, which dynamically adjusts camera parameters remotely via 5G networks. Experiments showed a significant accuracy improvement in video analytics, particularly a 42% enhancement in object detection, demonstrating APT's applicability across various tasks.