Data: Acquisition to Analysis
Welcome + Panel Discussion!
Full Paper Presentation
Accepted Dataset Papers:
Data Acquisition, Analysis and Reuse for AI + IoT Applications
Assistant Professor, University of California Merced
Dr. Shijia Pan is an assistant professor in the Computer Science and Engineering Department at the University of California Merced. She received her bachelor’s degree in Computer Science and Technology from the University of Science and Technology of China (USTC) and her Ph.D. degree in Electrical and Computer Engineering at Carnegie Mellon University (CMU). Her research interests include cyber-physical systems, Internet-of-Things (IoT), and ubiquitous computing. She worked in multiple disciplines and focused on self-assessing and self-adaptive heterogeneous cyber-physical systems for accurate indoor occupant information inference with limited resources.
Principal Scientist at GE Research
Dr. Radislav A. Potyrailo is a Principal Scientist at GE Research. He received PhD in Analytical Chemistry from Indiana University, Bloomington, IN in 1998. Dr. Potyrailo directs programs on innovative multi-response gas and biological sensors for diverse applications. His passion is to bring innovative sensing systems from laboratory feasibility to field validations and to commercialization. Dr. Potyrailo has been serving as a technical lead on GE R&D programs transitioned to GE businesses or GE partners for commercialization. Examples include optical multi-parameter chemical sensor for GE Water, wireless gas sensors for GE Oil & Gas, multi-parameter oil sensor for GE Renewable Energy, and GE Ventures start-up company on radio-frequency sensors. Dr. Potyrailo has been serving as a Principal Investigator on US Government programs funded by AFRL, DARPA, DHS, DOE, DTRA, NIH, NIOSH, and other agencies. Dr. Potyrailo has summarized some of his results in 140+ granted US Patents and numerous technical publications on transducers, sensing materials, and data analytics; his Google Scholar h-index is 50 and his i10-index is 215. Dr. Potyrailo is the initiator and a co-organizer of the First Gordon Research Conference on Combinatorial and High Throughput Materials Science. He serves as an editor of the Springer-Nature book series Integrated Analytical Systems. Dr. Potyrailo is the North America Regional Chair of International Society for Olfaction and Chemical Sensing, and is the Chair of the Device Working Group of the MEMS and Sensors Industry Group. His recognitions include Prism Award by Photonics Media, Innovation Award by the Association for Sensor and Measurement Technology, and SPIE Fellow.
Assistant Professor, University of California Los Angeles
Dr. Gao explores the visual roots of human social perception and cognition. He builds models of artificial social intelligence with human-like visual commonsense which — just by sharing the same visual environment — can cooperate, and communicate with humans in intuitive, effective, and trustworthy ways. He obtained his Ph.D. in cognitive psychology from Yale in 2011. He was a post-doctoral fellow in the Center of Brain, Mind and Machine at MIT between 2011-2015. He then worked at GE research as a computer vision scientist between 2015-2017. He has been jointly appointed to the departments of Statistics, Communication and Psychology at UCLA since 2017.
Founder and Chief Scientist at XYZ10
Qiang is the founder and the chief scientist of XYZ10, which is a startup company offering a reliable indoor-outdoor positioning service. Qiang received his Ph.D from the University of Michigan in 2013. Before founding XYZ10, Qiang has been working at NEC Labs Amercia, Boeing Labs, Microsoft Research, AT&T Labs Research. Along this career path, Qiang has been collected diverse hands-on experience regarding systems, networking, AIoT, machine learning, etc.
Check Call for Papers for information on submission!
ABOUT THE WORKSHOP
As the enthusiasm for and success of the Internet of Things (IoT), Cyber-Physical Systems (CPS), and Smart Buildings grows, so too does the volume and variety of data collected by these systems. How do we ensure that this data is of high quality, and how do we maximize the utility of collected data such that many projects can benefit from the time, cost, and effort of deployments?
The Data: Acquisition To Analysis (DATA) workshop aims to look broadly at interesting data from interesting sensing systems. The workshop considers problems, solutions, and results from all across the real-world data pipeline. We solicit submissions on unexpected challenges and solutions in the collection of datasets, on new and novel datasets of interest to the community, and on experiences and results—explicitly including negative results—in using prior datasets to develop new insights.
The workshop aims to bring together a community of application researchers and algorithm researchers in the sensing systems and building domains to promote breakthroughs from integration of the generators and users of datasets. The workshop will foster cross-domain understanding by enabling both the understanding of application needs and data collection limitations.
CALL FOR PAPERS
The workshop seeks contributions across two major thrusts, but is open to a broad view of interesting questions around the collection, dissemination, and use of data as well as interesting datasets:
The collection and use of data
- - Challenges and solutions in data collection, especially around security and privacy
- - Expectations and norms for data collection from sensor networks, especially those that involve human factors
- - Novel insights from existing datasets
- - Metadata management for complex datasets
- - Synthetic data, including its generation, application, and utility
- - Success stories—key properties of useful datasets and how to generalize these
- - Preprocessing, cleaning, and fusing datasets
- - analysis and visualization of the data
- - Shortcomings of prior datasets—and how to address these in the future
- - Position papers on policies and norms from experimental design through data management and use are explicitly welcomed
New and interesting datasets, including but not limited to:
- - Shopping related sensing data
- - Animal related data or sensed data
- - Anonymized health, or synthetic health related data
- - Indoor localization, especially unprocessed/unfiltered physical layer measurements
- - Smart building, occupancy, motion data, energy, human comfort, vibration, BIM
- - Vehicular, GPS, cellular, or wifi traces and remote sensing
- - Reproductions of prior work that validate, refute, or enhance results
- - Anonymized contact tracing, interaction and exposure notification data
To enable the longevity of submitted datasets, we plan on providing a central location where a repository for the data, and information about the data can be archived for at least 5 years.
Submissions may range from 1-5 pages in PDF format, excluding references, using the standard ACM conference template. DATA 2021 follows the single-blind review policy. The names and affiliations of all the authors must be present in the submitted manuscript. Submissions are strongly encouraged to use only as much space as needed to clearly convey the significance of the work—we fully expect many submissions, especially datasets, to use only 1-2 pages, but wish to allow those interested in fully elucidating positions on data collection and use or insights from reproducibility efforts ample space to do so. Submissions should use only as much space as necessary to clearly convey their ideas and contributions.
Dataset submissions should prefix paper titles with “Dataset: “ and must include a description of the dataset as well as a reasonable accompanying data sample. Once accepted, a full described dataset must be shared to a public repository by the camera ready deadline. Issues on licenses will be resolved by generally following the procedure similar to CRAWDAD (https://crawdad.org) and special treatments, if needed, will be discussed separately with the TPC chairs. The dataset submission must submit a link to the dataset at the time of submission.
Datasets will be reviewed by an artifact evaluation committee. To support this, dataset submissions must include:
- - A link to the full dataset (not just a single sample) at the time of submission
- - An example analysis or result from the dataset (what kind of insights might folks glean?)
- - Steps to run an analysis on the dataset, e.g.
- - A graph and the steps (sample code) to generate the graph
- - A video demonstrating access and manipulation of the data or execution of queries and results on the data
- - Other evidence or demonstration of how the dataset can be accessed and used
The evaluation committee will work with sumbitters to ask clarifying questions, etc. The goal is not to be a barrier to submission, but instead to help make sure datasets are usable and useful for folks in the future.
Each accepted submission is required to have at least one author attend the workshop and present to the workshop attendees.
Submission site: link
Abstract Registration: September 24th, 2021, AOE , HotCRP
Submission Deadline: September 24th, 2021, AOE
Notifications: October 11th, 2021?
Workshop: November 17th, 2021