Abstract: Component faults, bugs, and malicious attacks can all degrade in, or even prevent semi-autonomous systems (SASs) from, correctly capturing their operation context, which is essential to support critical safety features like emergency braking in an autonomous car. While safety features in modern SASs usually rely on static assignment of control priority, such a design may lead to catastrophic accidents when accompanied with erroneous/compromised control and context estimation. To mitigate the grave danger of SASs' use of incorrect data for making control decisions and learn from the incidents/crashes of Boeing 737 MAX, we propose CADCA, a novel control decision-maker for SASs, that is designed to operate under sensor/data errors or falsifications as well as malicious/erroneous control inputs with the ultimate goal of resolving conflicting control inputs to ensure safety. Our extensive evaluation (of more than 15,700 test-cases) has shown CADCA to achieve a 98% success rate in preventing the execution of incorrect control decisions caused by component failures and/or malicious attacks in the most common scenarios. This talk will detail the motivation, design and evaluation of CADCA with semi-autonomous vehicles as a representative SAS.

Bio: KANG G. SHIN is the Kevin & Nancy O'Connor Professor of Computer Science in the Department of Electrical Engineering and Computer Science, The University of Michigan, Ann Arbor. His current research focuses on safe and secure embedded real-time and cyber-physical systems as well as QoS-sensitive computing and networking. He has supervised the completion of 91 PhDs, and authored/coauthored about 1,000 technical articles, a textbook and about 60 patents or invention disclosures, and received numerous awards, including 2023 IEEE TCCPS Technical Achievement Award, 2023 SIGMOBILE Test-of-Time Award, 2019 Caspar Bowden Award for Outstanding Research in Privacy Enhancing Technologies, and the Best Paper Awards from 2023 VehicleSec, 2011 ACM International Conference on Mobile Computing and Networking (MobiCom'11), the 2011 IEEE International Conference on Autonomic Computing, 2010 and 2000 USENIX Annual Technical Conferences, as well as the 2003 IEEE Communications Society William R. Bennett Prize Paper Award and the 1987 Outstanding IEEE Transactions of Automatic Control Paper Award. He has also received several institutional awards, including the Research Excellence Award in 1989, Outstanding Achievement Award in 1999, Distinguished Faculty Achievement Award in 2001, and Stephen Attwood Award in 2004 from The University of Michigan (the highest honor bestowed to Michigan Engineering faculty); a Distinguished Alumni Award of the College of Engineering, Seoul National University in 2002; 2003 IEEE RTC Technical Achievement Award; and 2006 Ho-Am Prize in Engineering (the highest honor bestowed to Korean-origin engineers). He has chaired Michigan Computer Science and Engineering Division for 4 years starting 1991, and also several major conferences, including 2009 ACM MobiCom, and 2005 ACM/USENIX MobiSys. He was a co-founder of a couple of startups, licensed some of his technologies to industry, and served as an Executive Advisor for Samsung Research.

Abstract: Wireless technology has become an integral part of our daily lives, enabling remote education, supporting remote work, and connecting people worldwide. As we transition into the era of AI, wireless will play an even more important role by bringing AI to edge devices and equipping AI with a sixth sense. In this presentation, I will begin by offering an overview of the current state of wireless technologies. Then I will outline our vision and present our recent progress on the development of innovative intelligent environments.

Bio: Lili Qiu is an Assistant Managing Director of Microsoft Research Asia, primarily responsible for the research work at Microsoft Research Asia (Shanghai) and collaborating with the industry, universities, and research institutions. She received her Ph.D. in Computer Science from Cornell University in 2001 and began her career as a researcher at Microsoft Research Redmond lab the same year, working in the Systems and Networking group from 2001 to 2004. In 2005, she joined the Department of Computer Science at the University of Texas at Austin as an Assistant Professor and later was promoted to Professor. She has won numerous honors, including National Academy of Inventors (NAI) Fellow, ACM Fellow, IEEE Fellow, ACM Distinguished Scientist, NSF CAREER Award. She also chairs ACM SIGMOBILE.

Yuanqing Zheng: Enhancing LoRa for Scalable IoT and Beyond
Abstract: The Internet of Things (IoT), with its promise to connect an unprecedented scale of IoT devices, is widely expected to deepen our comprehension of the physical realm and play a pivotal role in the construction of smart cities and the development of industry 4.0 applications. Unlike conventional wireless technologies, e.g. 5G/Next-G, Wi-Fi, BLE, the recent advancements in Low Power Wide Area Network (LPWAN) technologies, exemplified by LoRa, have demonstrated transformative ability in offering extensive connectivity that spans kilometers and supports vast networking capable of accommodating over 10,000 IoT devices per gateway. Such unparalleled scalability and reach make LPWAN a most promising technology to shape the future of IoT landscape. This talk discusses a few potential approaches to further enhancing LoRa for scalable IoT connectivity and beyond.
Bio: Yuanqing Zheng is currently an associate professor in the department of computing, HK PolyU. His research interests include IoT, wireless networking, mobile computing, and AI and its applications. He serves as associate editors of ACM ToSN, ACM IMWUT, IEEE TWC, Computer Networks, and TPC members of INFOCOM, SenSys, IoTDI, and others.

Zhenjiang Li: Intelligent Computing in Edge-driven Roadside Systems
Abstract: Vehicle-to-everything (V2X) is a promising technology that can enable and advance autonomous driving in building future smart cities. V2X consists of edge-driven roadside systems deployed as infrastructure for smart sensing, execution of deep learning tasks, communication with on-board units on vehicles to enable smart connectivity and information exchange. In this talk, I will share our recent research on building new edge-driven roadside systems with intelligent computing, focusing on solving memory and power management issues at the mobile edge.
Bio: Zhenjiang Li is an associate professor in the Department of Computer Science at City University of Hong Kong. He received the B.E. degree from Xi'an Jiaotong University, and the M.Phil and Ph.D. degrees from Hong Kong University of Science and Technology. His research interests include Artificial Internet of Things (AIoT), edge AI systems and smart sensing. He has received the test of time award at ACM SenSys 2022 and the best paper award at IEEE INFOCOM 2019. He served as the TPC members of many international conferences, such as IEEE INFOCOM, IEEE ICDCS, IPSN, IoTDI, and he is currently an associate editor of IEEE Transactions on Mobile Computing.

Chenshu Wu: Signal Processing-Deep Learning Co-Design for Wireless Sensing AI
Abstract: The next big wireless movement is not about communication and networking, but sensing. Wireless sensing technology has turned Wi-Fi devices from a pure communication platform into ubiquitous, all-in-one sensors. In this talk, we start with a retrospective of our solutions based on signal processing techniques that have been successfully commercialized and deployed on massive IoT devices. We then investigate a signal processing-deep learning co-design and present our recent progress along three distinct aspects (physical data augmentation, RF data generation, and RF neural network design) towards practical wireless sensing AI.
Bio: Dr. Chenshu Wu is an Assistant Professor in the Department of Computer Science, The University of Hong Kong, where he leads the HKU AIoT Lab. He received his B.E. and Ph.D. degrees both from Tsinghua University. His research focuses on AIoT systems at the intersection of wireless sensing, ubiquitous computing, smart healthcare, and the Internet of Things. He has published 3 books and 100+ papers in prestigious conferences and journals like SIGCOMM, NSDI, MobiCom, MobiSys, UbiComp, with several best paper awards. He holds 90+ filed/granted US and international patents. His research on WiFi sensing has been deployed as award-winning products worldwide. He is a recipient of NSFC Excellent Young Scientists Fund (HK & Macau), NAM Healthy Longevity Catalyst Award, and CCF Outstanding Doctoral Dissertation Award. He is currently an associate editor of ACM IMWUT. More information at https://cswu.me

Lei Yang: Understanding Localization by Large AI Models
Abstract: Conventional deep learning approaches for indoor localization often suffer from their reliance on high-quality training samples and display limited adaptability across varied scenarios. To address these challenges, we repurpose the Transformer model, celebrated for its profound contextual insights, to explore the underlying principles of indoor localization. We developed a specialized Generative Pre-training Transformer (GPT) variant, termed LocGPT, configured with 36 million parameters that are tailored to facilitate transfer learning. By fine-tuning this pre-trained model, we achieve near-par accuracy using merely half the conventional dataset, thereby heralding a pioneering stride in transfer learning within the indoor localization domain.
Bio: Dr. YANG Lei is currently an Associate Professor in the Department of Computing, The Hong Kong Polytechnic University. Previously, he was a postdoc fellow at Tsinghua University. He received his B.S. and Ph.D. degrees from Xi’an Jiaotong University in 2004 and 2014 respectively. His research interests include Battery-free Internet of Things, AI-enabled wireless sensing, Indoor localization, mobile computing, wireless and backscatter communication. He is the recipient of the “Best Paper Awards” of ACM MobiCom 2014, ACM MobiHoc 2014, and IEEE SECON 2020, 2023. He also received the “ACM China Doctoral Dissertation Award” and the NSFC Excellent Young Scientists Fund (Hong Kong and Macau). He published more than 60 papers at leading conferences and journals including ACM MobiCom, ACM SIGCOMM, USENIX NSDI and IEEE S&P.

Zhenyu Yan: Towards General Intelligence Industrial Sensing Technologies
Abstract: Enhanced by the advancements in AI and embedded computing technologies, we now witness a new generation of wearable systems that harness multi-modal data for the creation of general intelligent applications in industrial environments. This talk will delve into a series of novel sensing systems and edge computing technologies for intelligent industrial application.
Bio: Dr. Zhenyu Yan is a Research Assistant Professor at The Chinese University of Hong Kong. Dr. Yan has extensive experience in sensing systems, signal and information processing, cyber-physical systems, and machine learning in IoT systems. His works have been published in top international conferences and journals, such as MobiCom, SenSys, IPSN, IEEE Transactions on Mobile Computing, and ACM Transactions on Sensor Networks. He is the recipient of the Kan Tong Po International Fellowship from the Royal Society in the UK and the Rising Star Award (Early Career Award) from ACM SIGBED China. His papers also received the Best Community Contributions Award at ACM MobiCom 2023, the Best Paper Award Runner-up at ACM MobiCom 2022, and the Best Artifact Award Runner-up at ACM/IEEE IPSN 2021.

Rob SCHARFF: Bioinspired Soft Robots for Dexterous Manipulation
Abstract: Soft robots offer safety and adaptability, making them ideal for deployment near humans and in highly unstructured and delicate environments, such as for human-robot collaboration in industrial settings, active debris removal in outer space, and underwater collection of biological specimens. In this talk, I will introduce our research on the design and manufacturing of pneumatic and tendon-driven soft actuators with integrated proprioceptive and tactile sensors. Moreover, I will demonstrate how robust closed loop control of these soft robots can be realized through the adoption of remarkably simple strategies observed in biological role models such as the elephant trunk, the octopus arm, and the searcher stems of climbing plants.
Bio: Rob Scharff is Assistant Professor in the Division of Integrative Systems and Design of The Hong Kong University of Science and Technology (HKUST). Prior to that, he was a postdoctoral researcher in the Bioinspired Soft Robotics group at the Italian Institute of Technology (IIT). Dr. Scharff obtained his Ph.D. degree at the department of Design Engineering from Delft University of Technology (TU Delft) in 2021 and received his M.Sc. degree in Integrated Product Design from the same institute. His research focuses on soft robotics, with an emphasis on the design and manufacturing of bioinspired soft robots with integrated proprioceptive and tactile sensors.

Chun Zhang: ASTRI sensor: from intelligent machine vision (IMV) to non destructive testing (NDT)
Abstract: The IoT Sensing and AI Technologies (IOTSAI)​ Department at ASTRI is committed to develop market-oriented & leading intelligent IoT sensing & integration solutions for intelligent manufacture, smart city and digital health related applications. ​For the last ten years, we have developed our strength in two folds, namely, intelligent machine vision (IMV) for surface inspection and non destructive testing (NDT) for interior inspection. In this presentation, some of our recent developments will be covered to demonstrate the power of such advanced sensing technologies.
Bio: Dr Chun ZHANG obtained PhD in physics from HKUST in 1999. He then worked in UC Berkeley for four years, in NAMI for eight years, and in ASTRI for thirteen years, continuing his pursuit of optical & acoustic sensing. He is now the Director of Sensing Devices and Integration of ASTRI, supervising the developments of leading technologies in digital jewellery inspection, portable environmental sensor, and smartphone spectrometer.

Abstract: Artificial intelligence (AI) has emerged as a powerful tool for solving complex health problems using data-driven approaches. AI for health is fueled by both the advancement in AI methods and the availability of data provided by electronic health records (EHR) and wearables. This talk will explore the potential to support precision medicine using wearables that enable unobtrusive monitoring of patients in their daily lives. To harness the full potential of wearables, it is crucial to develop machine learning (ML) models to extract reliable clinical information from noisy and incomplete sensor data. Moreover, these ML approaches need to scale effectively across a wide range of sample sizes, providing robust predictions even with limited data, while enhancing predictive power with large datasets. We will highlight three clinical studies that use Fitbit wristbands as wearable instruments. First, we have established a robust feature engineering and ML pipeline specifically tailored for wearable studies with limited sample sizes. This pipeline demonstrated its effectiveness in predicting postoperative complications in a prospective clinical trial of patients undergoing pancreatic surgery. Second, we have developed WearNet, an end-to- end deep learning model designed to detect mental health disorders using wearable data. WearNet has been trained and validated on a large public dataset comprising 8,996 participants, including 1,247 diagnosed with mental disorders. Finally, we have explored multi-task ML approaches to predict individualized responses to depression therapy based on wearable data collected in a randomized controlled trial (RCT). By the end of the talk, we will discuss the opportunities and directions in the interdisciplinary field of AI and wearables for health, showcasing the transformative impact they can have on healthcare outcomes.

Bio: Chenyang Lu is the Fullgraf Professor of Computer Science & Engineering and holds joint appointments as Professor of Anesthesiology and in Medicine at Washington University in St. Louis. He is the founding director of the AI for Health Institute (AIHealth), a multidisciplinary institute dedicated to driving AI innovation in health research. His research interests include AI for health, Internet of Things, real-time systems, and cyber-physical systems. In 2022, he was honored with the Outstanding Technical Achievement and Leadership Award from the IEEE Technical Community on Real-Time Systems (TCRTS). He has also been recognized with a Test of Time Award from the ACM Conference on Embedded Networked Sensor Systems (SenSys), an Influential Paper Award from the IEEE Real-Time and Embedded Technology and Applications Symposium (RTAS), and nine Best or Outstanding Paper Awards. He is the Editor-in-Chief of ACM Transactions on Cyber-Physical Systems. He also served as the Editor-in-Chief of ACM Transactions on Sensor Networks, Chair of TCRTS, and chaired leading conferences on IoT, real-time systems, and cyber-physical systems. He is a Fellow of ACM and IEEE.

Abstract: The conventional wisdom of wireless networking tells us that concurrent transmissions from multiple senders colliding at a receiver result in packet loss. However, this is not always true: under the proper signal timing and power conditions, one of the colliding transmissions is almost always received due to the capture effect. In this talk, we focus on ultra-wideband (UWB) radios. On one hand, concurrent transmissions can be exploited for multi-hop communication, enabling novel network primitives and protocol designs with unprecedented performance and reliability. On the other hand, they can be exploited in conjunction with the distinctive features of UWB: distance estimation and localization. Indeed, UWB transmissions rely on very short pulses; their individual times of arrival can be discriminated in the channel impulse (CIR) at the receiver. Based on this observation, we design unconventional schemes where a device can simultaneously estimate its distance from several others, or a set of devices can localize countless targets in an area, yielding accuracy comparable to conventional schemes but significantly faster and more energy-efficient operation.

Bio: Gian Pietro Picco is a professor in the Department of Information Engineering and Computer Science (DISI) at the University of Trento, Italy. His research has spanned software engineering, middleware, and distributed systems, and is currently focused on low-power wireless networking and localization for the Internet of Things and cyber-physical systems. The research performed in his group emphasizes the validation of novel approaches and protocols via system prototypes and their evaluation in real-world testbeds and applications. He is the recipient of several awards, including a "Most Influential Paper" at ICSE'07 (for a paper published a decade earlier) and Best Paper Awards at IPSN (2009, 2011, 2015), PerCom (2012), EWSN (2018), and IPIN (2019). He has served as General Chair and Program Chair for several flagship conferences (e.g., SenSys, CPS-Iot Week, SECON, EWSN, IoTDI, DCOSS, Middleware). He is an associate editor for ACM Trans. on Sensor Networks (TOSN) and has served in the same role for IEEE Trans. on Software Engineering (TSE) and the J. of Pervasive and Mobile Computing. He is also the founding Editor-in-Chief of the ACM Trans. on the Internet of Things (TIOT).

Abstract: Quantifying the chemical process of milk spoilage is challenging due to the need for bulky, expensive equipment that is not user-friendly for milk producers or customers. This lack of a convenient and accurate milk spoilage detection system can cause two significant issues. First, people who consume spoiled milk may experience serious health problems. Secondly, milk manufacturers typically provide a “best before” date to indicate freshness, but this date only shows the highest quality of the milk, not the last day it can be safely consumed, leading to significant milk waste. Thirdly, milk producers themselves are in-need of efficient ways to measure the quality of the milk in-situ for Quality Control purposes. We will discuss practical and efficient solutions to this problem in this talk.

Bio: Wen Hu is a professor at School of Computer Science and Engineering, the University of New South Wales (UNSW). Much of his research career has focused on novel applications, low-power communications, security, signal processing and machine learning Cyber Physical Systems (CPS) and Internet of Things (IoT). Hu published regularly in the top rated sensor network and mobile computing venues such as ACM/IEEE IPSN, ACM SenSys, ACM MobiCOM, ACM UbiCOMP, IEEE PerCOM, ACM TOSN, IEEE TMC, IEEE TIFS and IEEE TDSC. Hu was a principal research scientist and research project leader at CSIRO Digital Productivity Flagship, and received his Ph.D from the UNSW. He is a recipient of prestigious CSIRO Office of Chief Executive (OCE) Julius Career Award (2012 - 2015) and multiple research grants from Australian Research Council, CSIRO and industries. Hu is the editor in chief (EiC) of ACM TOSN, the general chair of CPS-IoT Week 2020, co-chair the program committee of ACM/IEEE IPSN 2023 and ACM Web Conference (WWW 2023, Systems and Infrastructure for Web, Mobile Web, and Web of Things track), as well as serves on the organising and program committees of networking conferences including ACM/IEEE IPSN, ACM SenSys, ACM SigCOMM, ACM MobiCOM and ACM MobiSys. Hu is a senior member of ACM and IEEE. Hu actively commercialises his research results in smart buildings and IoT, and his endeavours include working as the Chief Technical Officer (part time) and the Chief Scientist (part time) in Parking Spotz (2021 - 2022) and WBS Tech (2016-2020) respectively.