The widespread deployment of wireless communication systems creates unprecedented opportunities to impact our daily lives. Regardless of whether wireless infrastructures are used just for communication or as the basis for actual responses, large-scale wireless data provide increasing opportunities for detecting environmental changes caused by moving objects. Indeed, it is expected to develop the ability to make use of existing wireless infrastructure and sensing data to track moving objects which do not carry radio devices and may not even being aware of being tracked. However, these wireless data are dynamic and have complex data characteristics, such as multi-scale, multi-source and multi-modal. As these data become large and more detailed, new challenges are emerging for intrusion learning.

This project aims to develop effective and scalable multi-modal passive intrusion learning techniques that have the capability to detect and track device-free moving objects in pervasive wireless environments through adaptive learning in a collaborative way. In contrast to traditional techniques, which require pre-deployment of specialized hardware, and thus not easily deployed for unscheduled tasks and may not be scalable, this project leads to new insights into intrusion learning by mining on wireless environmental data, as well as leading to new approaches to device-free wireless localization, which can be used to assist a broad array of applications (e.g., identification of people trapped in a fire building during emergency evacuation). Project results are expected to open a new venue for integrating learning capabilities into emerging pervasive wireless fields. The educational component seeks to equip students with the necessary background and practical skills needed to contribute to information technology and have a practical impact on a large set of cross-section domains.

Project Report

This project aims to develop effective and scalable multi-modal passive intrusion learning techniques that have the capability to detect and track device-free moving objects in pervasive wireless environments through adaptive learning in a collaborative way. A set of device-free passive localization techniques are developed to identify moving objects in various scenarios. This project results in multiple publications centered around four main areas: (1) developing adaptive device-free passive localization techniques to localize intruders when they move with dynamic speeds; (2) designing accurate peer assisted WiFi device indoor localization systems; (3) achieving robust wireless localization resilient to signal strength attacks; and (4) developing human queue monitoring techniques leveraging unique patterns of WiFi signals from smartphones that are used in queues. (1) Intruders may move at different speeds when approaching different sections of the area of interest. Assuming a constant moving speed when locating such targets may result in significant impact on the localization accuracy. We found significant performance degradation on existing received signal strength (RSS) based device-free localization algorithms due to the unawareness of the speed change of the moving target. To cope with dynamic moving speeds, we proposed an adaptive speed change detection framework to improve localization performance over existing device-free localization systems. (2) The feasibility of leveraging the most prevalent WiFi infrastructure for high accuracy localization on smartphones is still an open question. We observed that smartphones are gradually woven into our social life and usually a high density of them exist in public spaces. The relative positions of nearby peer devices could be used as physical constraints on the possible location of a smartphone. Inspired by this observation, We proposed a peer-phone assisted localization approach that leverages the acoustic ranging between peers, without requiring special hardware yet producing highly accurate location estimates. (3) RSS-based localization algorithms are sensitive to a set of non-cryptographic attacks, where the physical measurement process itself can be corrupted by adversaries. We focused on addressing all-around signal strength attacks, where similar attacks are launched towards all landmarks. We proposed a principle that advises the usage of a new ratio-based signal strength metric (RSM) instead of RSS in designing localization algorithms. (4) We explore whether signal power readings of WiFi traffic generated by mobile devices are sufficient to monitor a fine-scale, yet common, process: human queues. Real-time quantification of queue parameters could provide rich information of a queue and enable many applications. We explored the approach of utilizing low infrastructure and low cost sensing technology that can infer important queuing times from WiFi traffic generated by mobile devices in queues. In particular, we seek to develop a mechanism that can effectively track waiting and service times of persons in queues, which enables further queue optimization. Broader impacts of this project include the collaboration with industry, ECE department weekly seminar, an embedded systems course module, training for 2 PhD students with both completed dissertation so far, and outreach to the general public by featuring into various news outlets. In particular, my group has established collaboration with AT&T Labs, AT&T Chief Security Office, and IBM T. J. Watson Research Center. Our industrial collaborators are informed of the latest development of the new techniques, and they can utilize their expertise to help validating the practical needs of our work and explore the possibility of technology transfer of the project. Students in the course of CPE/EE556 "Computing Principles for Embedded Systems" have the opportunity to conduct course projects which are related to the research tasks in this project. Moreover, through the management of the regular ECE departmental seminars, I coordinate and help to invite researchers from both academia and industry to give talks about cutting-edge research topics once every week. Our speakers are prime candidates to exchange new research ideas, explore the collaboration, and validate my current work. Further, I expect that these seminars will provide a vehicle to present project results to students, faculty and experts from local industry.

Project Start
Project End
Budget Start
2010-09-01
Budget End
2014-08-31
Support Year
Fiscal Year
2010
Total Cost
$264,015
Indirect Cost
Name
Stevens Institute of Technology
Department
Type
DUNS #
City
Hoboken
State
NJ
Country
United States
Zip Code
07030