Prof. Athman Bouguettaya
The University of Sydney, Australia
Abstract: We propose a novel service framework to effectively provision drone-based delivery services in a skyway network. This service framework provides a high-level service-oriented architecture and an abstraction to model the drone service from both functional and non-functional perspectives. We focus on spatio-temporal aspects as key parameters to query the drone services under a range of requirements, including drone capabilities, flight duration, and payloads. We propose to reformulate the problem of drone package delivery as finding an optimal composition of drone delivery services from a designated take-off station (e.g., a warehouse rooftop) to a landing station (e.g., a recipient’s landing pad). We select and compose those drone services that provide the best quality of delivery service in terms of payload, time, and cost under a range of intrinsic and extrinsic environmental (i.e., context-aware) factors, such as battery life, range, wind conditions, drone formation, etc. This talk will overview the key challenges and propose solutions in the context of single drones and swarms of drones for service delivery.
Biography:
Athman Bouguettaya is Professor and previous Head of School of Computer Science, at the University of Sydney, Australia. He was also previously Professor and Head of School of Computer Science and IT at RMIT University, Melbourne, Australia. He received his PhD in Computer Science from the University of Colorado at Boulder (USA) in 1992. He was previously Science Leader in Service Computing at the CSIRO ICT Centre (now DATA61), Canberra. Australia. Before that, he was a tenured faculty member and Program Director in the Computer Science department at Virginia Polytechnic Institute and State University (commonly known as Virginia Tech) (USA). He is a founding member and past President of the Service Science Society, a non-profit organization that aims at forming a community of service scientists for the advancement of service science. He is or has been on the editorial boards of several journals including, the IEEE Transactions on Services Computing, IEEE Transactions on Knowledge and Data Engineering, ACM Transactions on Internet Technology, The ACM Computing Surveys, the International Journal on Next Generation Computing, VLDB Journal, Distributed and Parallel Databases Journal, and the International Journal of Cooperative Information Systems. He is also the Editor-in-Chief of the Springer-Verlag book series on Services Science. He served as a guest editor of a number of special issues including the special issue of the ACM Transactions on Internet Technology on Semantic Web services, a special issue of the IEEE Transactions on Services Computing on Service Query Models, and a special issue of IEEE Internet Computing on Database Technology on the Web. He was the General Chair of the WISE International Conference for 2023. He was the General Chair of the IEEE ICWS for 2021 and 2022. He was also General Chair of ICSOC for 2020. He served as a Program Chair of the 2012 and 2017 International Conference on Web and Information System Engineering, the 2009 and 2010 Australasian Database Conference, 2008 International Conference on Service Oriented Computing (ICSOC) and the IEEE RIDE Workshop on Web Services for E-Commerce and E-Government (RIDE-WS-ECEG'04). He also served on the IEEE Fellow Selection Committee as a Vice-Chair for 2022 and 2023. He has published more than 300 books, book chapters, and articles in journals and conferences in the area of databases and service computing (e.g., the IEEE Transactions on Knowledge and Data Engineering, the ACM Transactions on the Web, WWW Journal, VLDB Journal, SIGMOD, ICDE, VLDB, and EDBT). Bouguettaya's work in Web services and more generally in service computing, greatly contributed to the formation of a whole community around the idea of service computing. The impact of his foundational work in Web services has led to numerous highly cited papers. The total Google Scholar citation is more than 10,350. He is also listed by Google Scholar as one of the top 10 cited researchers in the world using the keyword "Service Computing" or “Service-Oriented Computing” or “Web Services”. He was the recipient of several federally competitive grants in Australia (e.g., ARC), the US (e.g., NSF, NIH), Qatar (NPRP). EU (FP7), and China (NSFC). He also won major industry grants from companies like HP and Sun Microsystems (now Oracle). He has been an invited speaker at many international conferences and universities around the world. Because of his pioneering work, he was invited to a keynote and speaker at a number of conferences and universities in Australia, UK, France, Morocco, Malaysia, Netherlands, Tunisia, New Zealand, Algeria, China, Qatar, the UAE, etc. Bouguettaya has trained many PhD students who went on to be professors at Purdue University (USA), University of Michigan, Rochester Institute of Technology, Deakin University, Sajib Mistry, and Texas A&M. He also trained a number of postdocs who are now researchers at Alibaba, Sun Yat-Sen University (China), University of Adelaide, Data61, and UNSW. Bouguettaya is a Fellow of the IEEE, Member of the Academia Europaea (Honoris Causa) (MAE) (HON), WISE Fellow, AAIA Fellow, and Distinguished Scientist of the ACM. He is also a Distinguished Speaker of the ACM and IEEE.
Dr. Jules Ferdinand P. Disso
BNP Paribas, UK
Abstract: The integration of Artificial Intelligence (AI) with the Internet of Things (IoT) has given rise to autonomous systems that are increasingly prevalent in various sectors, including, healthcare, smart cities, and industrial automation. However, the opaque nature of many AI models, often referred to as "black boxes," poses significant challenges in understanding and trusting the decision-making processes of these systems. This talk will explore the imperative need for Explainable AI (XAI) in order to build trust and transparency in IoT systems. It will look into current advancements in AI, highlighting the evolution of machine learning models and their applications in IoT systems. It also sets the stage for a deep dive into Explainable AI techniques such as LIME (Local Interpretable Model-agnostic Explanations), SHAP (SHapley Additive exPlanations), and attention mechanisms and examine their suitability and effectiveness in elucidating AI-driven decisions within IoT systems. Key discussion points will include maintaining balance between model explainability and performance as well as addressing the trade-offs and strategies for optimizing both. The ethical implications of deploying XAI in scenarios where user trust is paramount will also be scrutinized, considering the potential consequences of opaque decision-making in critical applications. Real-world case studies will illustrate successful implementations of XAI in IoT systems, showcasing how transparency can enhance reliability and user trust. Furthermore, the talk will explore the challenges faced and lessons learned from these implementations. Finally, it will highlight emerging trends and open research questions in XAI, which aim to encourage academic and industrial community to further investigate this crucial research area.
Biography:
Dr. Jules Ferdinand Pagna Disso is the Director and Group Head of Cyber Risk Intelligence & Insider Technology Risk at BNP Paribas and Head of Digital Asset Risk. He has obtained PhD in Intrusion Detection Systems from the University of Bradford. He possesses extensive experience in cyber threat intelligence, IT risk management, vulnerability management, IT governance and Artificial Intelligence. He overseas the external surface attack management for a large number of websites across nearly 50 business units, ensuring the identification and resolution of cyber threats. He has developed innovative techniques for integrating AI into cybersecurity processes, enhancing the field's capabilities to mitigate risks effectively. At the Paris HUB AI, Dr. Disso collaborates with legal experts in order to navigate and influence AI regulations. He has also delivered numerous talks at international conferences on AI and its implications on cybersecurity. He has significant expertise in developing world-class offensive tools, managing complex deception networks, and conducting high-profile incident responses.