Applied Artificial Intelligence

At the Applied Artificial Intelligence group, we develop multidisciplinary AI-driven technologies for smart cities, transportation, agriculture, and healthcare. Our research integrates sensing, communication, computation, and autonomous decision-making to address practical real-world challenges. We leverage advanced AI technologies, including machine learning, computer vision, and large language models, as key enablers for our solutions. In smart health, we are developing LiDAR-based platforms for human activity recognition and rehabilitation, enabling accurate, remote, and privacy-preserving monitoring. In smart agriculture, our research combines drones, multimodal sensing, and AI analytics for precision farming and advanced plant health assessment. In intelligent transportation, we integrate multi-modal perception and design AI-enabled frameworks for traffic monitoring, abnormal driving behavior detection, and enhanced mobility. We are also leading research on scalable crowd management systems for safer and smarter urban environments through AI-driven analytics and edge computing. Through interdisciplinary AI research activities, our mission is to develop intelligent technologies that support safer, healthier, and more sustainable societies.

Watch Intro to CCSL Applied Artificial Intelligence Group on YouTube.

EdgeCIM: A Hardware-Software Co-Design for CIM-Based Acceleration of Small Language Models

The deployment of language models is rapidly shifting from datacenters to edge devices such as laptops, smartphones, and embedded platforms, driven by the demand for interactive, low-latency, and privacy-preserving applications. In this context, Small Language Models (SLMs) have emerged as practical candidates, yet their inference reveals inefficiencies in conventional accelerators. While GPUs and NPUs process the GEMM-heavy prefill stage efficiently, they remain underutilized during the GEMV-dominated decoding phase, resulting in limited throughput and excessive energy consumption at the edge

Efficient AI Across Edge, Near-Edge, and Cloud

Modern applications — smart cameras, self-driving cars, AR/VR headsets, on-device assistants — depend on increasingly large AI models. The catch is that the appetite of these models is growing far faster than the hardware meant to run them, especially at the edge. Closing that gap is not just a matter of building bigger chips; it requires rethinking where each part of a model executes across the devices a user actually has access to. Our work develops two complementary frameworks that address this directly. DONNA decides how to split a model across heterogeneous devices — CPUs, GPUs, and

Meet the Team

Ahmed Eltawil
Hakim Ghazzai
Hakim Ghazzai
Mojtaba Alshams
Jinane Bazzi

more

Discover More Research Areas in the CCSL Group

Wireless Communication

Wireless Communication The CCSL advances next-generation wireless communication through a synergistic combination of theory, system design, and artificial intelligence. Our research explores digital twin frameworks for both indoor and outdoor wireless scenarios, enabling real-time system monitoring, optimization, and predictive analysis. We leverage multimodal sensing to enhance situational awareness and resilience, while reconfigurable intelligent surface (RIS)-aided localization pushes the boundaries of positioning accuracy. In integrated sensing and communication (ISAC), the lab
Overview of wearable sensing technologies for comprehensive human health monitoring.

Body Area Network

Body Area Network Our work explores new frontiers where the human body and nature itself become powerful channels for communication. We are driven by the vision that signals can be harnessed and transformed into reliable pathways for exchanging information. By combining innovative circuit design, ultra-low-power integrated systems, and bio-inspired networking, we seek to enable technologies that go far beyond traditional wireless communication. Our research spans from the Internet of Body, where multiple biosensors can communicate seamlessly through the human body, to the Internet of Plants