ACS 2013 - ACS 2013 : Analytics for Cyber-Physical Systems

A cyber-physical system (CPS) is a system that exhibits a co-ordination between the system's computational and physical elements. Such systems are becoming increasingly ubiquitous with applications in diverse domains such as transportation, health care, emergency response, physical infrastructure, etc. Typically, such systems are often configured as a system of sub-systems that are functionally independent but operationally dependent on each other. Analyzing data collected from such CPS requires a system of systems approach, which is not often seen in traditional data analytic solutions. The CPS domain possesses unique sets of challenges, in terms of modeling the relationship between different sub-systems to effectively extract knowledge from underlying data, while operating under real time contraints and handling massive and often streaming data.
Building on the success of first workshop at SDM 2012, the 2nd workshop on Analytics for Cyber-Physical Systems aims to bring together researchers from academia, government and industrial research labs who are working in the area of Cyber-Physical Systems with an eye towards real world deployments. Large scale physical systems are increasingly being instrumented with various types of sensors (including human sensors). To convert this data into actionable insights, analytics is needed at each step: From signal processing of distributed sensor data, to business intelligence techniques to integrate data from various sources, and to techniques from data mining to machine learning to give us insights over this data.
Topics of Interest
The workshop welcomes contributions in any area of analytics for Cyber-Physical systems. The topics include:
Sensor Data Mining
Time series mining
Outlier detection for identifying faults and anomalies in CPS
Data mining/machine learning for massive sensor data
Signal processing of real world sensor data
Event Mining
Analyzing Logs for Event Detection
Complex Event Processing
Online failure prediction
Big Data Challenges in CPS
Distributed analytics over big data
Scaling standard analytic algorithms to big data
Near real time analytics for streaming data
Mining Heterogeneous Data
Transfer learning from one CPS domain to another
Applications and Case Studies
Challenges in using analytics to close the control loop in CPS.
Success stories deployment of CPS.
Challenges in deployment of CPS.
New application domains for CPS.
The main motivation for this workshop stems from the increasing need for a forum to exchange ideas and recent research results, and to facilitate collaboration and dialog between academia, government, and industrial stakeholders.
We solicit high quality papers and extended abstracts in the general areas of data analytics for large cyber-physical systems. We also encourage submissions describing work in progress in relevant areas.
All submitted papers will be peer reviewed. We have identified a set of researchers who are currently active in the related research areas as potential reviewers (Click here for the preliminary list). If accepted, at least one of the authors must attend the workshop to present the work. Selected accepted papers will be recommended for submission to special issues of journals.
Paper Submission
All full papers should have a maximum length of 8 pages (single-spaced, 2 column, 10 point font, and at least 1 inch margin on each side). We also invite 4 page extended abstracts. Authors should use US Letter (8.5 in x 11 in) paper size. Papers must have an abstract with a maximum of 300 words and a keyword list with no more than 6 keywords. Authors are required to submit their papers electronically in PDF format (postscript files can be converted using standard converters) to https://www.easychair.org/conferences/?conf=acs201.... We would like to encourage you to prepare your paper in LaTeX2e. Papers should be formatted using the SIAM SODA macro, which is available through the SIAM website. You can access it at http://www.siam.org/proceedings/macros.php. The filename is soda2e.all. Make sure you use the macros for SODA and Data Mining Proceedings; papers prepared using other proceedings macros will not be accepted. For Microsoft Word users, please convert your document to the PDF format. All submissions should clearly present the author information including the names of the authors, the affiliations and the emails. The papers should be submitted using the workshop submission system.