Special Issue on Data Mining in Pervasive Environments

The explosion of sensors and mobile phones and their interaction with human life funnel a phenomenal amount of data through pervasive computing environments. The data from these sensors (environmental sensors such as motion sensors; smart phone sensors such as accelerometers and GPS; and object sensors such as RFID tags) have to be carefully analyzed to extract interesting and relevant information. The sheer volume of sensor data, as well as its streaming and distributed nature, poses many challenges to the data mining, mobile sensing and knowledge discovery community. Analyzing these data trails can support different applications in a novel way. The applications may vary from personal and community healthcare (smart home independent living, fitness and exercising), green computing (building energy management, environment monitoring), urban sensing (intelligent transportation system, natural resource management), marketing industry (advertisement, consumer shopping habits) and after all social networking.

We solicit high quality and original unpublished papersfrom researchers working on data mining in pervasive environments to highlight current challenges, and to showcase the latest results. The results will demonstrate how current data mining, mobile sensing and knowledge discovery methods can be extended to mining solutions for dealing with challenging real world problems. The unique nature of sensor data in pervasive environments demands for novel data mining, mobile sensing and knowledge discovery methods that can handle large, multi-modal, heterogeneous and distributed streams of data. We hope that the results of this special issue not only can be beneficial for the pervasive computing community, but the resulting algorithms and solutions will also be adapted by researchers in various other application fields.

The major topics of the special issue include, but not limited to:

1.     Unsupervised methods for discovering interesting patterns such as human activity and behavior based on:

       Novel data mining methods

       Relational and graph mining methods

       Real time analysis of dynamic sensor data

       Models for sensor fusion

       Multimodal context recognition

2.     Supervised machine learning methods for analyzing data in pervasive environments

       Generative and Discriminative models

       Relational models

       Graphical models

3.     Mobile sensing

       Mobile data collection models

       Mining large scale sensor data

       Sensing and machine learning techniques

       Participatory, opportunistic and collaborative sensing

       Activity recognition and personal health monitoring using mobile phones

4.     Case studies based on success stories of data mining techniques for real-world pervasive computing applications

       Low level sensor data (accelerometers, GPS, RFID, Motion sensors, etc), Physiological sensors, smart phone based sensing, video and audio, other mediums

       Data fusion and uncertainty reasoning for situation awareness

       Novel proposals on architecture and middleware design for smart environments services

       Services and applications in pervasive healthcare, green building energy management and intelligent transportation, etc.

       Test-beds and real world deployments

Some of the fundamental questions that will be addressed in this special issue (but not limited to) are: What data mining or mobile sensing techniques support real-time recognition of human activities?, What are the solutions for improving the generalization of these pervasive data mining systems to support wide scale deployment and use?, What are the challenges and potential solutions for collecting pervasive data for modeling and analysis?, What are the strategies for benchmarking the results of various sensorial approaches in pervasive environments?


Submission process:

All submissions have to be prepared according to the Guide for Authors as published in the Journal website at www.ees.elsevier.com/pmc/. Authors should select SI: Data Mining, from the “Choose Article Type” pull-down menu during the submission process. All contributions must not have been previously published or be under consideration for publication elsewhere. A submission based on one or more papers that appeared elsewhere has to comprise major value-added extensions over what appeared previously (at least 30% new material). Authors are requested to attach to the submitted paper their relevant, previously published articles and a summary document explaining the enhancements made in the journal version.


Important Dates:

Paper submission deadline: September 15, 2013
First Notification: December 15, 2013
Final Notification: February 15, 2014


Guest Editors of the Special Issue:

Nirmalya Roy, University of Maryland at Baltimore County, nirmalya.roy@gmail.com

Parisa Rashidi, Northwestern University, parisa.rashidi@northwestern.edu

Liming Chen, University of Ulster, l.chen@ulster.ac.uk

Larry Holder, Washington State University, holder@eecs.wsu.edu