Call for Papers

Mobile and ubiquitous computing has emerged as today's most prevalent computing paradigm, thanks to the tremendous advances in a broad range of technologies and applications, including wireless networking, Internet of things, mobile and sensor systems, RFID technology, and various location-based services. The workshop is intended to solicit technical papers pertaining to the broadly-conceived mobile and ubiquitous systems. The papers must be original, previously unpublished research, and not currently under review by another conference or journal. We encourage submissions of all types -- theory, algorithm, experiment, and experience papers, with preference to system and real-world deployment. Topics of interests include (but are not limited to) the following subject categories:

Novel applications and Devices Supporting Mobility

Mobile Location-based Services and Recommendation Systems

Mobile Cloud Computing and Data Management in the Mobile Cloud

Theoretical Foundations of Data-intensive Mobile Computing

Data Stream Processing in Mobile/Sensor Network

Wearable computing, Internet of Things, Sensing, and Context-awareness

Routing, Personalized Routing, Eco-Routing, Routing for Electrical Vehicles

Security and Privacy in Mobile Ubiquitous Systems

Submission

All submissions need to follow the IEEE Computer Society Proceedings Manuscript Formatting Guidelines. See templates below: https://www.ieee.org/conferences/publishing/templates.html

The length of a regular workshop papers is limited to 6 pages (including references). Note that a paper exceeding the page limit may be rejected without review. Please use the URL link below for submissions of Workshop Papers: https://easychair.org/conferences/?conf=must2023

Publication

All accepted workshop papers will be published in the proceedings of the 2023 International Conference on Mobile Data Management and included in the IEEE Xplore® digital library.

Program

July 3rd, 9:00AM - 4:30PM - Room SR3E (Registration at Level 4)
more info on the venue can be found at https://mdmconferences.org/mdm2023/venue_travel.html

SCHEDULE:

9:00AM - 10:00AM Keynote: “RL4SpatialDB: On Leveraging Reinforcement Learning for Spatial Data Management” by Prof. Cheng Long

10:10AM - 10:40AM Tea Break

10:40AM - 12:00PM Workshop Papers Presentations - Part 1 (15 min + 5 min Q&A):

• “Performance Comparison of Audio Tampering Detection Using Different Datasets”, Hsiang-Ping Hsu, Sheng-Chain Chang, Chao-Hsiang Hung, Syu-Siang Wang, and Shih-Hau Fang
• “Experimental Comparison of Graph Edit Distance Computation Methods”, Gaoming Zhang, Sen Lin, Xianmin Wang, Teng Huang, Xuan Hu, and Lingyun Zou
• “Smart Contract Service Optimization in Blockchain-Cloud Collaborative Computing”, Ji Wan, Kai Hu, Jie Li, Hao Su, Qingshun Wu, Mingyuan Li, Libo Feng, and Yan Pan
• “Interactive Multiobjective Optimization of Airport Baggage Trolley Scheduling Based on NSGA2”, Wanru Gao, Jiahao Li, and Mingliang Xu

12.30PM - 2.00PM Lunch

2:00PM - 3:00PM Workshop Papers Presentations - Part 2 (15 min + 5 min Q&A):

• “Cooperative Carrier Aircraft Support Operation Scheduling Based on Multi-Agent Reinforcement Learning”, Hongjie Hao, Xueqin Zhang, Yuan Chi, Mingliang Xu, and Rongxin Gao
• “The Specification of Blockchain Oracle System”, Jie Li, Kai Hu, Ji Wan, Wenhao Zhan, Yidan Zou, Yuan Ai, Liping Gao, and Yujun Yin
• “Secure Crowdsourced Blockchain Computation lntelligence for loT Systems”, Xiaoting Zhang, Xiangyu Feng, Huaiyuan Zhang, Bing Mi, and Kongyang Chen

3:00PM - 3:30PM Tea Break

3:30PM - 4:30PM Workshop Papers Presentations - Part 3 (15 min + 5 min Q&A):

• “Visual Analysis on Failure Mitigation in Multi-agent Systems”, Shun Liu, Jingyi Xue, Yingkang Zhang, Yibo Guo, and Mingling Xu
• “Context Query Generation using Scene Graph approach”, Ravindi De Silva, Arkady Zaslavsky, Seng W Loke, and Prem Prakash Jayaraman
• “Tackling Network Challenges in Context Aware Environments: Lightweight Context Management Architecture”, Shaine Christmas, Rob Davidson, Arkady Zaslavsky, and Kevin Lee

4:30 PM Closing Remarks

KEYNOTE "RL4SpatialDB: On Leveraging Reinforcement Learning for Spatial Data Management" by Prof. Cheng Long

Abstract: Spatial data plays a crucial role in various applications, encompassing geospatial information such as trajectory data, urban mobility data, spatial networks, and satellite images. Efficient management of spatial data heavily relies on spatial indexing, enabling rapid retrieval of spatial objects based on their location information. Traditional spatial indices, like the R-tree and space filling curve, have been widely employed in spatial data systems like PostGIS for several decades. However, the emergence of machine learning techniques has introduced a new approach known as learned spatial indices, which aim to replace the classic ones. While learned spatial indices have shown promising results by achieving enhanced efficiency for specific datasets, they possess several limitations. For instance, they are primarily designed for point objects and lack support for data updates. Additionally, the query processing algorithms developed for classic spatial indices cannot be readily applied to learned spatial indices. We propose an alternative approach to address these challenges by leveraging reinforcement learning (RL) to augment existing classic spatial indices rather than replacing them with learned models. By integrating reinforcement learning techniques into classic spatial indices, we can construct data-driven spatial indices that inherit the advantages of their traditional counterparts while addressing the limitations faced by learned spatial indices. In this presentation, I will introduce our RL-based techniques for building an R-Tree, which is a widely used spatial index structure. I will also discuss our RL-based methods for computing space-filling curves, another type of spatial index. These techniques leverage the power of RL to optimize the index construction process and improve query performance. Furthermore, I will briefly outline our RL-based techniques for simplifying trajectory data and performing similarity searches on sub-trajectories. These additional applications demonstrate the versatility and potential of reinforcement learning in enhancing various aspects of spatial data management.

Organizing Committee

Program Chairs

Yafei Li (Zhengzhou University)
Yun Peng (Guangzhou University)
Shangwei Guo (Chongqing University)

Program Members

Qian Chen (Google Inc.)
Lei Chen (Huawei Noah's Ark Lab)
Peipei Yi (Lenovo Machine Intelligence Center)
Cheng Xu (Simon Fraser University)
Jian Lou (Xidian University)
Chengcheng Dai (Grab Inc.)
Xiaoyi Fu (Hong Kong Baptist University)
Guozhong Li (Hong Kong Baptist University)
Ji Wan (Beihang University)
Hao Su (Beihang University)
Guanglei Zhu (Zhengzhou University)