INTRODUCTION

Recent years have witnessed the significant development of urban Internet-of-Things (IoT) for smart cities. Urban IoT is built on the top of complex Cyber-Physical Systems (CPSs) that consist of spatially distributed entities that interact with each other over time, leading to an inherently spatio-temporal and interconnected composition. In this setting, urban IoT generates ubiquitously available data for demonstrating real-time and fine-granular status of the complicated urban systems. Mining such urban IoT data can reveal holistic human and system structures, dynamics, and semantics of the underlying urban systems, and further provides intelligent decision support for urban public administration in boosting commercial activities, enhancing public security, fostering social interaction, and thus yielding livable, sustainable, and viable environments.

Our workshop is a half-day workshop at ICDM 2022. The workshop aims to bring together academia researchers and industry practitioners to (1) discuss the principles, limitations and applications of urban IoT intelligence, and (2) foster research on innovative algorithms, novel techniques, and new applications of urban IoT intelligence in smart cities.

PROGRAM

Key West D, Hilton Orlando, Orlando, FL

9:00-11:50 a.m., New York Time

• Opening Remarks (9:00-9:05)

Dr. Yanjie Fu (University of Central Florida)

• Keynote Speech I: Vehicle Computing: Vision and Challenges (9:05-9:50)

Dr. Weisong Shi (University of Delaware)

Abstract:

Vehicles have been majorly used for transportation in the last century. With the proliferation of onboard computing and communication capabilities, we envision that future connected vehicle (CVs) will be serving as a mobile computing platform in addition to their conventional transportation role for the next century. In this article, we present the vision of Vehicle Computing, i.e., CVs are the perfect computation platforms, and connected devices/things with limited computation capacities can rely on surrounding CVs to perform complex computational tasks. We also discuss Vehicle Computing from several aspects, including several key and enabling technologies, case studies, open challenges, and the potential business model.

Bio:

Weisong Shi is a Professor and Chair of the Department of Computer and Information Sciences at the University of Delaware (UD), where he leads the Connected and Autonomous Research (CAR) Laboratory. Dr. Shi is an internationally renowned expert in edge computing, autonomous driving and connected health. His pioneer paper entitled “Edge Computing: Vision and Challenges” has been cited more than 5400 times. Dr. Shi is the chair of IEEE Computer Society Special Technology Community on Autonomous Driving Technologies (ADT), the Strategic Planning Committee member of the Autoware Foundation. He is an IEEE Fellow and an ACM Distinguished Scientist. More information can be found at http://weisongshi.org

• Keynote Speech II: Spatiotemporal Event Forecasting in Social Media (9:50-10:35)

Dr. Chang-Tien Lu (Virginia Tech)

Abstract:

Social media has become a popular data source as a surrogate for monitoring and detecting events. Analyzing social media (e.g., tweets) to reveal event information requires sophisticated techniques. Tweets are written in unstructured language and often contain typos, non-standard acronyms, and spam. In addition to the textual content, Twitter data form a heterogeneous information network where users, tweets, and hashtags have mutual relationships. These features pose technical challenges for designing event detection and forecasting methods. In this talk, I will present the design and implementation a fully automated forecasting system for significant societal events using open source data including tweets, blog posts, and news articles. I will describe the system architecture, individual models that leverage specific data sources, and a fusion engine that supports trading off specific evaluation criteria. I will also demonstrate its superiority and capability to forecast significant societal happenings.

Bio:

Chang-Tien Lu is a Professor and National Capital Region Program Director in the Department of Computer Science and Associate Director of the Sanghani Center for AI and Data Analytics at Virginia Tech. He received his Ph.D. from the University of Minnesota at Twin Cities in 2001. Dr. Lu currently serves as Associate Editor of ACM Trans. on Spatial Algorithms and Systems, Data & Knowledge Engineering, IEEE Trans. on Big Data, and GeoInformatica. He has regularly served on the organizing and program committees of conferences, including as Program Chair of the 18th IEEE Intl. Conference on Tools with Artificial Intelligence in 2006, and General Chair of the 17th ACM SIGSPATIAL Intl. Conference on Advances in Geographic Information Systems in 2009, 2020, and 2021, and the Intl. Symposium on Spatial and Temporal Databases in 2017. He also served as Secretary (2008-2011) and Vice Chair (2011-2014) of the ACM Special Interest Group on Spatial Information (ACM SIGSPATIAL). His research interests include spatial databases, data mining, urban computing, and intelligent transportation systems. He has published over 190 articles in top rated journals and conference proceedings. His research has been supported by NSF, NIH, DoD, IARPA, VDOT, and DCDOT. He is an ACM Distinguished Scientist and Virginia Tech College of Engineering faculty fellow.

• Tea Break (10:35-10:45)

• Paper Presentation I: Streaming Traffic Flow Prediction Based on Continuous Reinforcement Learning (10:45-11:05)

Yanan Xiao (Northeast Normal University)

• Paper Presentation II: A Multi-Source Information Learning Model Framework for Airbnb Price Prediction (11:05-11:25)

Lu Jiang (Northeast Normal University)

• Paper Presentation III: A Comparison of Ambulance Redeployment Systems on Real-World Data (11:25-11:45)

Niklas Strauß (LMU Munich)

• Closing Remarks (11:45-11:50)

Dr. Yanjie Fu (University of Central Florida)

CALL FOR PAPERS

We encourage submissions on a broad range of data mining for urban IoT intelligence. Topics of interest include but are not limited to theories, algorithms, applications, systems, and tools, such as:

• Building Sensing Infrastructures for Developing Urban or IoT Intelligence

- Mobile sensing

- Communication and networking for AI and machine learning

- Unmanned aerial vehicle (UAV)-based sensing/communications/networking

- Cellular communications and data networks, e.g. 5G, 6G, and beyond

- Cloud, Edge, and Fog computing for sensing and inference

- Sensing and Networking for Smart & Connected Communities

- Sensing and networking of social systems

• Novel Machine Learning Models or Systems for Analytics and Prediction in Urban or IoTs Setting

- Deep learning, Representation Learning

- Transfer learning

- Meta learning

- Multi-modality learning

- Multi-view learning

- Domain shift & generalization

• Solving the Urban and IoT Data Challenges for Urban or IoT Analytics

- Data sparsity, noises, outliers, unbalanced, outlier non-IID issues

- Data spatial autocorrelation, temporal dependencies, heterogeneity

- Graph structure mining and learning issues

- Image, video, audio, multi-media data mining issues

- Data fusion and knowledge transferring

• Computation

- Efficiency and scalability, e.g., model compression/pruning for IoT devices

- Trustworthiness, e.g., federated learning for IoT devices

- Robustness, e.g., attacks and defenses for IoT devices

• Decision-Making & Operation & Management

- Decision and control, e.g., reinforcement learning for urban IoT

- Applications, e.g., intelligent transportation, public health/administration/policy, smart energy, power grids, smart homes, vehicle to vehicle networks, etc

IMPORTANT DATES & SUBMISSIONS

All deadlines will be adjusted accordingly based on the ICDM 2022 main conference.

• April 5, 2022: Workshop call for papers

• September 17, 2022: Workshop paper submission

• October 8, 2022: Notification of workshop papers acceptance to authors

• October 15, 2022: Camera-ready deadline and copyright form

• November 28, 2022: Workshops date

All dates are 11:59pm Pacific Daylight Time.

All submissions should be in English, double-column pdfs in IEEE conference format, and be limited to a maximum of 8 pages. The paper should be submitted using the website [LINK]. For details about the latex templates and other information, please refer to the main conference website of ICDM 2022. [LINK]

All accepted papers will be included in the ICDM'22 Workshop Proceedings published by the IEEE Computer Society Press. The submitted paper should not be published or under review by any other venues (i.e., conferences, workshops, journals). The reviews are triple-blind.

Any enquiries regarding the submissions should be emailed to pywang [at] um.edu.mo.

ORGANIZERS