{"id":7616,"date":"2011-01-31T07:38:39","date_gmt":"2011-01-31T12:38:39","guid":{"rendered":"http:\/\/www.bu.edu\/systems\/?p=7616"},"modified":"2021-02-11T12:40:48","modified_gmt":"2021-02-11T17:40:48","slug":"detecting-explosives-eng-groups-quest-to-improve-airport-screening-systems","status":"publish","type":"post","link":"https:\/\/www.bu.edu\/cise\/detecting-explosives-eng-groups-quest-to-improve-airport-screening-systems\/","title":{"rendered":"Detecting Explosives: ENG group\u2019s quest to improve airport screening systems"},"content":{"rendered":"

By Mark Dwortzan<\/p>\n

\"Using
Using advanced modeling and algorithms, the ALERT team at BU aims to enable airport screening machines to provide three-dimensional cross sections of a bag so that individual items can be clearly separated. Images show top and back views of a boom box and other objects. Images courtesy of W. Clem Karl<\/figcaption><\/figure>\n

Airport luggage inspection machines scan one bag every six seconds, but the conventional medical imaging technology they use can easily overlook potential threats. In the vitally important quest to make airline travel safer since 9\/11, David Casta\u00f1\u00f3n is working to equip these machines with a wider range of sensors and pattern recognition tools and more sophisticated signal processing algorithms to analyze the data in real time.<\/p>\n

\u201cWe need to design a system that\u2019s partially automated and where human intelligence gets used as needed to resolve ambiguities and produce highly reliable decisions,\u201d says Casta\u00f1\u00f3n, a College of Engineering professor and chair ad interim of electrical and computer engineering. \u201cThis involves several systems engineering trade-offs: how much do you automate? What\u2019s the algorithm you put in for making that decision? How do you generate alerts? What sensors do you bring to bear?\u201d<\/p>\n

Since 2008, Casta\u00f1\u00f3n, Clem Karl, a professor of electrical and computer engineering, Venkatesh Saligrama, an associate professor of electrical and computer engineering, and five PhD students have addressed these questions for potential applications ranging from whole-body imaging to video surveillance in a Department of Homeland Security initiative called Project ALERT: Awareness and Localization of Explosive Related Threats. Focusing on systems engineering solutions, Casta\u00f1\u00f3n is associate director and the University\u2019s principal investigator of the project, which draws on experts from 15 academic institutions to improve the nation\u2019s explosives detection capability.<\/p>\n

The BU team\u2019s effort centers on mathematical problems in machine learning, optimization, and image processing. \u201cWe model the capabilities of different sensors,\u201d says Casta\u00f1\u00f3n, \u201cdevelop algorithms to combine the information they gather to form decisions concerning the presence of a potential risk, and intelligently sequence sensor data to ensure that the system as a whole performs well.\u201d<\/p>\n

One promising solution emerging from the team\u2019s work is an \u201cadaptive training\u201d system that uses video cameras to monitor pedestrian and traffic behavior, and that \u201clearns\u201d on the job to detect abandoned packages and vehicles by tracking changes in image pixels of sidewalks and streets. The team is also designing an intelligent sensor network system to monitor moving crowds with infrared cameras, chemical sniffers, and other devices. The system tracks individuals\u2019 locations and detects unusual behaviors and explosives nonintrusively yet reliably.<\/p>\n

\u201cIn explosives detection applications, most researchers focus on improving the performance of individual components, such as sharper imaging quality,\u201d says Casta\u00f1\u00f3n. \u201cWe\u2019re exploring ways of combining components and examining trade-offs to see how different data streams can complement each other to get a more accurate system.\u201d<\/p>\n

One important trade-off is between throughput and sensitivity. \u201cThe question of how to improve both throughput and sensitivity is at the heart of some of the novel pattern recognition and statistical learning techniques being developed at Boston University,\u201d says Saligrama.<\/p>\n

Mark Dwortzan can be reached at dwortzan@bu.edu.
\nThis story originally appeared in BU Today and the fall 2010 issue of Engineer.<\/p>\n","protected":false},"excerpt":{"rendered":"

By Mark Dwortzan Airport luggage inspection machines scan one bag every six seconds, but the conventional medical imaging technology they use can easily overlook potential threats. In the vitally important quest to make airline travel safer since 9\/11, David Casta\u00f1\u00f3n is working to equip these machines with a wider range of sensors and pattern recognition […]<\/p>\n","protected":false},"author":1500,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":[],"categories":[26],"tags":[],"_links":{"self":[{"href":"https:\/\/www.bu.edu\/cise\/wp-json\/wp\/v2\/posts\/7616"}],"collection":[{"href":"https:\/\/www.bu.edu\/cise\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.bu.edu\/cise\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.bu.edu\/cise\/wp-json\/wp\/v2\/users\/1500"}],"replies":[{"embeddable":true,"href":"https:\/\/www.bu.edu\/cise\/wp-json\/wp\/v2\/comments?post=7616"}],"version-history":[{"count":3,"href":"https:\/\/www.bu.edu\/cise\/wp-json\/wp\/v2\/posts\/7616\/revisions"}],"predecessor-version":[{"id":30757,"href":"https:\/\/www.bu.edu\/cise\/wp-json\/wp\/v2\/posts\/7616\/revisions\/30757"}],"wp:attachment":[{"href":"https:\/\/www.bu.edu\/cise\/wp-json\/wp\/v2\/media?parent=7616"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.bu.edu\/cise\/wp-json\/wp\/v2\/categories?post=7616"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.bu.edu\/cise\/wp-json\/wp\/v2\/tags?post=7616"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}