Talks and presentations

Traditional cloud-based IoT architectures suffer from many issues, including scalability, communication and computational efficiency, in addition to privacy. This motivated the need for new emerging trends such as Edge, Fog, and Pervasive Computing, where we merge hierarchical computing with efficient communication, and leveraging learning-based distributed optimization, in order to resolve many of the issues highlighted above.

In this talk, I will highlight the motivation behind pervasive AI models for Internet of Things (IoT), and cyber-physical systems (CPS), in light of traditional cloud-based architectures. Then, I will discuss some contributions we have recently published regarding distributed inference/classifications in IoT, and multi-drone systems, taking into considerations privacy and mobility of network users. I will also cover recent contributions regarding distributed learning scenarios using multi-agents and federated learning architectures that address heterogeneous user data to improve the learning performance, and outcomes in distributed networks.

The seminar discusses the following related areas:

1. AI for multi-drone surveillance

• Vision-based detection and localization, mobile cameras

• Smart coverage and tracking using multi-drone systems

• Directional coverage and tracking using drones

• Trajectory planning for efficient energy consumption.

• Distributed machine learning for smart surveillance.

2. AI for anti-drone systems

• RF-based detection and identification

• Drone video-based detection and tracking

• Smart drone jamming

While healthcare is a top national interest worldwide, the scalability of the healthcare systems that rely on one-to-one relation between patients and doctors remain a daunting issue. Also, the proliferation of the Internet of Medical Things (IoMT), accounting for over 30% of the world’s IoT devices, poses new security attacks that may be life-threatening. On the other hands, the emergence of next generation 5G mobile networking and machine learning technologies has motivated a paradigm shift in the development of viable smart-health applications leveraging edge computing for effectively detecting, and securing the patient context to provide scalable and secure vital signs acquisition and delivery to the cloud.

In this talk, I address the challenges of scalable and secure healthcare and present some proposed solutions, leveraging edge computing for scalable smart health systems. In the first part of the talk, I cover vital signs data reduction using deep learning for real-time data acquisition. Then, I highlight scalable delivery of health data through energy-efficient network selection and resource allocation in heterogeneous wireless networks. Finally, I illustrate how machine learning can be leveraged for intrusion detection to provide efficient and secure communication in wireless medical systems.