Webinars

Upcoming:

Smart Roads for Resiliance in Intelligent Transportation Systems

Speaker: Dr. Mona Jaber, Queen Mary University of London, UK 

Date and Time: February 5, 2025 at 11:00am CST

Abstract

Surface intelligent transportation systems (ITS) are enabled by a wide range of connected sensors that inform on continuously changing situations and conditions on the roads. In this talk, I will first discuss different types of such sensors and how each contributes to the resilience or lack of resilience in ITS. Next, I will present the emerging optical fibre-based distributed acoustic sensor (DAS) systems and how these can be deployed to inform on ITS problems and complement existing sensors to improve the resilience and precision. The talk will examine how deep learning models are trained to analyse the DAS signature of vehicles to determine their location, speed, direction of movement, and also the type of vehicle and its occupancy. I will then present new findings in which DAS is used to analyse and monitor active travel: can the system enable tracking the location and speed of unmotorised traffic? Can the DAS signature inform if the person is walking, cycling, or riding an e-scooter? The talk will discuss the role of DAS in informing ITS in different road conditions and will explore how it can be used jointly with existing systems, such as GNSS, to track surface traffic when the satellite signal is obstructed.

Biography

Mona Jaber is a Senior Lecturer in IoT with the School of Electronic Engineering and Computer Science, Queen Mary University of London. Her research interests include zero-touch networks, the intersection of ML and IoT in the context of sustainable development goals, and IoT-driven digital twins. In this regard, she has published in the areas of sustainable energy, smart mobility, and privacy-preserving e-health. As part of her industry research collaboration efforts, Mona has established a ground-breaking project that uses optical fibre systems for the detection and classification of active travel – a robust, scalable, and privacy-preserving method that informs smart city and safety in transportation planning. She is the director of the ‘Digital Twins for Sustainable Development Goals’ research lab at QMUL, where she attracted the first multidisciplinary core team to further the studies in this area. Mona was awarded the title of N2Women Rising Star in Computer Networking and Communications in 2022. She is a committee member of the IEEE-PST-Transportation group and an executive committee member of the IEEE UK and Ireland Women in Engineering affinity group.

---

Presented:   

Exploring Auditory Perception for Autopiloting with CARLA Simulator

Speaker: Dr. Jian Tao, Texas A&M University

Date and Time: September 11, 2024 at 11:00am CST

Abstract

In this talk, we will present our project aimed at enhancing the CARLA simulator by integrating auditory information to improve the perception capabilities of autonomous vehicles. The primary objective is to incorporate sound-based data to augment the decision-making processes of autopiloting systems, enabling them to respond more effectively to their environment. We will discuss the development and integration of virtual microphones and other auditory sensors within the CARLA environment, specifically designed to detect sirens. The talk will cover the implementation of the sound processing algorithm for sound source localization, classification, and event detection. A sample autopilot system is demonstrated to automatically pull over the car when approaching sirens are detected and resume driving once the sirens fade away. This project aims to push the boundaries of autonomous vehicle technology, making it more perceptive, responsive, and safer for real-world deployment, while also advancing the simulation capabilities of the CARLA platform.

Biography

Dr. Jian Tao is an Assistant Professor from the Section of Visual Computing & Computational Media in the School of Performance, Visualization & Fine Arts at Texas A&M University. He is also the Director of the Digital Twin Lab and the Assistant Director for Project Development at the Texas A&M Institute of Data Science. Tao received his Ph.D. in Computational Astrophysics from Washington University in St. Louis in 2008 and worked on computational frameworks for numerical relativity, computational fluid dynamics, coastal modeling, and other applications at Louisiana State University before he joined Texas A&M in 2016. In 2018, Tao led the Texas A&M team to the final of both the ASC18 and SC18 student cluster competitions. He is a faculty advisor of the Texas A&M 12th Unmanned Team for the SAE/GM AutoDrive Challenge Competition. Supported by a grant from the Department of Commerce, Tao is leading an effort to build a digital twin for the Disaster City managed by the Texas A&M Engineering Extension Service. Tao is an NVIDIA DLI University Ambassador and a contributor to the SPEC CPU 2017 benchmark suite. He currently serves as the Testbed Committee Co-Chair of the IEEE Public Safety Technology Initiative. His research interests include digital twin, numerical modeling, machine learning, data analytics, distributed computing, visualization, and workflow management.

This webinar has passed. To listen to a recording of the session please click on the video above.

---

Enhancing AI/ML-Based Attack Detection in Connected and Autonomous Vehicles through Generative AI and Combinatorial Fusion Analysis

Speaker: Dr. Mohamed Rahouti, Fordham University 

Date and Time: October 9, 2024 at 11:00am CST

Abstract

Ensuring the security and reliability of Connected and Autonomous Vehicles (CAVs) necessitates robust intrusion and attack detection mechanisms. While AI and ML methods have shown promise in this area, there is a pressing need for strategies that enhance their generalizability and
robustness. This talk will explore the synergy of Generative AI (GAI) and Combinatorial Fusion Analysis (CFA) in improving attack detection systems for CAVs. CFA integrates multiple pre- trained AI/ML models using sophisticated fusion algorithms, enhancing overall performance and
reliability. Simultaneously, GAI models, such as GANs, VAEs, and GPTs, can augment and balance datasets, generating new features to enrich data representation. The combination of GAI and CFA offers a powerful and sustainable platform for detecting and mitigating a wide range of cyber threats in CAV environments. This presentation will delve into recent advances in intrusion detection, highlighting the effectiveness of the GAI/CFA approach specifically tailored for CAVs.

Biography

Mohamed Rahouti received an M.S. degree in Mathematics (Statistics Concentration) and a Ph.D. degree in Electrical and Computer Engineering, both from the University of South Florida (Tampa, FL). He is currently an Assistant Professor in the Department of Computer and Information Science at Fordham University in New York City. His research interest focuses on blockchain technology, computer networking, machine learning, and network security with applications to smart cities. Dr. Rahouti has authored/co-authored over 50 peer-reviewed journals/conference papers and is a member of the IEEE Computer and Communications Societies.