Pub Date : 2011-12-19DOI: 10.1109/THS.2011.6107901
Bryan K. Olsen, John R. Johnson, T. Critchlow
Cyber analysts are tasked with the identification and mitigation of network exploits and threats. These compromises are difficult to identify due to the characteristics of cyber communication, the volume of traffic, and the duration of possible attack. In this paper, we describe a prototype implementation designed to provide cyber analysts an environment where they can interactively explore a month's worth of cyber security data. This prototype utilized On-Line Analytical Processing (OLAP) techniques to present a data cube to the analysts. The cube provides a summary of the data, allowing trends to be easily identified as well as the ability to easily pull up the original records comprising an event of interest. The cube was built using SQL Server Analysis Services (SSAS), with the interface to the cube provided by Tableau. This software infrastructure was supported by a novel hardware architecture comprising a Netezza TwinFin for the underlying data warehouse and a cube server with a FusionIO drive hosting the data cube. We evaluated this environment on a month's worth of artificial, but realistic, data using multiple queries provided by our cyber analysts. As our results indicate, OLAP technology has progressed to the point where it is in a unique position to provide novel insights to cyber analysts, as long as it is supported by an appropriate data intensive architecture.
{"title":"Data intensive architecture for scalable cyber analytics","authors":"Bryan K. Olsen, John R. Johnson, T. Critchlow","doi":"10.1109/THS.2011.6107901","DOIUrl":"https://doi.org/10.1109/THS.2011.6107901","url":null,"abstract":"Cyber analysts are tasked with the identification and mitigation of network exploits and threats. These compromises are difficult to identify due to the characteristics of cyber communication, the volume of traffic, and the duration of possible attack. In this paper, we describe a prototype implementation designed to provide cyber analysts an environment where they can interactively explore a month's worth of cyber security data. This prototype utilized On-Line Analytical Processing (OLAP) techniques to present a data cube to the analysts. The cube provides a summary of the data, allowing trends to be easily identified as well as the ability to easily pull up the original records comprising an event of interest. The cube was built using SQL Server Analysis Services (SSAS), with the interface to the cube provided by Tableau. This software infrastructure was supported by a novel hardware architecture comprising a Netezza TwinFin for the underlying data warehouse and a cube server with a FusionIO drive hosting the data cube. We evaluated this environment on a month's worth of artificial, but realistic, data using multiple queries provided by our cyber analysts. As our results indicate, OLAP technology has progressed to the point where it is in a unique position to provide novel insights to cyber analysts, as long as it is supported by an appropriate data intensive architecture.","PeriodicalId":228322,"journal":{"name":"2011 IEEE International Conference on Technologies for Homeland Security (HST)","volume":"99 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116651382","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2011-12-19DOI: 10.1109/THS.2011.6107877
Harriet Goldman, R. McQuaid, J. Picciotto
Our national security and critical infrastructure sectors have become increasingly dependent on commercial information systems and technologies whose pedigree is uncertain given the globalization of the supply chain. Furthermore, these system architectures are brittle and fail or are compromised when subjected to ever-increasingly advanced and adaptive cyber attacks, resulting in failed, disrupted or compromised mission operations. While we must continue to raise the bar to protect mission critical systems from these threats by implementing best security practices, the current philosophy of trying to keep the adversaries out, or the assumption that they will be detected if they get through the first line of defense, is no longer valid. Given the sophistication, adaptiveness, and persistence of cyber threats, we can no longer assume that we can completely defend against intruders and must change our mindset to assume some degree of adversary success and be prepared to “fight through” cyber attacks to ensure mission success even in a degraded or contested environment. This paper will focus on actionable architectural and operational recommendations to address the advanced cyber threat and to enable mission assurance for critical operations. These recommendations can create transformational improvements by helping to reverse adversary advantage, minimize exploit impact to essential operations, increase adversary cost and uncertainty, and act as a deterrent. These approaches go well beyond traditional information assurance, disaster recovery and survivability techniques. The approaches and strategies to be discussed include creative applications of trust technologies and advanced detection capabilities in conjunction with combination of techniques using diversity, redundancy, isolation and containment, least privilege, moving target defense, randomization and unpredictability, deception, and adaptive management and response.
{"title":"Cyber resilience for mission assurance","authors":"Harriet Goldman, R. McQuaid, J. Picciotto","doi":"10.1109/THS.2011.6107877","DOIUrl":"https://doi.org/10.1109/THS.2011.6107877","url":null,"abstract":"Our national security and critical infrastructure sectors have become increasingly dependent on commercial information systems and technologies whose pedigree is uncertain given the globalization of the supply chain. Furthermore, these system architectures are brittle and fail or are compromised when subjected to ever-increasingly advanced and adaptive cyber attacks, resulting in failed, disrupted or compromised mission operations. While we must continue to raise the bar to protect mission critical systems from these threats by implementing best security practices, the current philosophy of trying to keep the adversaries out, or the assumption that they will be detected if they get through the first line of defense, is no longer valid. Given the sophistication, adaptiveness, and persistence of cyber threats, we can no longer assume that we can completely defend against intruders and must change our mindset to assume some degree of adversary success and be prepared to “fight through” cyber attacks to ensure mission success even in a degraded or contested environment. This paper will focus on actionable architectural and operational recommendations to address the advanced cyber threat and to enable mission assurance for critical operations. These recommendations can create transformational improvements by helping to reverse adversary advantage, minimize exploit impact to essential operations, increase adversary cost and uncertainty, and act as a deterrent. These approaches go well beyond traditional information assurance, disaster recovery and survivability techniques. The approaches and strategies to be discussed include creative applications of trust technologies and advanced detection capabilities in conjunction with combination of techniques using diversity, redundancy, isolation and containment, least privilege, moving target defense, randomization and unpredictability, deception, and adaptive management and response.","PeriodicalId":228322,"journal":{"name":"2011 IEEE International Conference on Technologies for Homeland Security (HST)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121352105","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2011-12-19DOI: 10.1109/THS.2011.6107920
J. McClintock, M. Saxon, J. Forsythe, James Rascoe, J. Risser
Battelle developed the Adaptable, Geographic Information System (GIS) based, Multi-threat, Detection System (AGMDS) to provide a portable, exterior, full threat spectrum detection system for special events, operations that require a quickly deployable area surveillance system, and mobile applications such as convoys, patrols, or covert operations. The AGMDS increases the user's situational awareness by detecting potential threats and attacks and communicating wirelessly through a mesh network with a central control station that consolidates the data on a unified map display. Development of the AGMDS was part of Project Ancile that Battelle performed for the Defense Threat Reduction Agency (DTRA). The goal of the project was to develop cost-effective, integrated solutions for protection against the full range of terrorist threats — i.e. physical; cyber; and chemical biological, radiological, nuclear, and explosive (CBRNE) threats. This document describes the AGMDS development process, beginning with the technology gap assessment which identified the need for the system development; continuing through requirements analysis, system design and trade studies, integration and test; and culminating in a demonstration at the U.S. Naval Academy. The first phase of Project Ancile was to define technology gaps in active military facilities. Battelle visited three active installations and assessed their current security systems against the full threat spectrum. The gaps identified during the assessment were documented as needs for a potential system. Battelle developed conceptual systems to fill these needs and performed a trade study to determine which system should be developed and demonstrated. The AGMDS was selected as it addresses the majority of the technology gaps identified and had the lowest relative cost and risk associated with development. The AGMDS is modular and portable, consisting of five subsystems: detector subsystem, vehicle subsystem, personnel subsystem, relay subsystem, and a control subsystem. The current configuration includes: • High resolution video surveillance with 180° field of view • Personnel physiology monitoring of heart and breathing rates and position • Concealed object detection using thermal imaging • Chemical detection, biological detection and identification and radiation detection. The detector and vehicle subsystems house the CBRE sensors as well as video and communications equipment. The personnel subsystem provides blue force tracking and physiological monitoring, and the relay subsystems allow expanded network coverage. Together, the subsystems create a network of networks. Each detector and vehicle station houses a local network of sensors. The stations communicate with the control station via an ad-hoc, self-organizing, wireless mesh network; enabling display of sensor locations and alarms on a site map; as well as monitoring of video surveillance data.
{"title":"Development of the adaptable, GIS-based, multi-threat detection system","authors":"J. McClintock, M. Saxon, J. Forsythe, James Rascoe, J. Risser","doi":"10.1109/THS.2011.6107920","DOIUrl":"https://doi.org/10.1109/THS.2011.6107920","url":null,"abstract":"Battelle developed the Adaptable, Geographic Information System (GIS) based, Multi-threat, Detection System (AGMDS) to provide a portable, exterior, full threat spectrum detection system for special events, operations that require a quickly deployable area surveillance system, and mobile applications such as convoys, patrols, or covert operations. The AGMDS increases the user's situational awareness by detecting potential threats and attacks and communicating wirelessly through a mesh network with a central control station that consolidates the data on a unified map display. Development of the AGMDS was part of Project Ancile that Battelle performed for the Defense Threat Reduction Agency (DTRA). The goal of the project was to develop cost-effective, integrated solutions for protection against the full range of terrorist threats — i.e. physical; cyber; and chemical biological, radiological, nuclear, and explosive (CBRNE) threats. This document describes the AGMDS development process, beginning with the technology gap assessment which identified the need for the system development; continuing through requirements analysis, system design and trade studies, integration and test; and culminating in a demonstration at the U.S. Naval Academy. The first phase of Project Ancile was to define technology gaps in active military facilities. Battelle visited three active installations and assessed their current security systems against the full threat spectrum. The gaps identified during the assessment were documented as needs for a potential system. Battelle developed conceptual systems to fill these needs and performed a trade study to determine which system should be developed and demonstrated. The AGMDS was selected as it addresses the majority of the technology gaps identified and had the lowest relative cost and risk associated with development. The AGMDS is modular and portable, consisting of five subsystems: detector subsystem, vehicle subsystem, personnel subsystem, relay subsystem, and a control subsystem. The current configuration includes: • High resolution video surveillance with 180° field of view • Personnel physiology monitoring of heart and breathing rates and position • Concealed object detection using thermal imaging • Chemical detection, biological detection and identification and radiation detection. The detector and vehicle subsystems house the CBRE sensors as well as video and communications equipment. The personnel subsystem provides blue force tracking and physiological monitoring, and the relay subsystems allow expanded network coverage. Together, the subsystems create a network of networks. Each detector and vehicle station houses a local network of sensors. The stations communicate with the control station via an ad-hoc, self-organizing, wireless mesh network; enabling display of sensor locations and alarms on a site map; as well as monitoring of video surveillance data.","PeriodicalId":228322,"journal":{"name":"2011 IEEE International Conference on Technologies for Homeland Security (HST)","volume":"344 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133210601","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2011-12-19DOI: 10.1109/THS.2011.6107857
Bryan Lemon, V. Kulathumani
We present a distributed camera control algorithm that can be used for the monitoring of large regions using a network of PTZ (pan/tilt/zoom) cameras. The proposed strategy would allow for continuous target tracking at a high resolution, while still maintaining coverage over the entire monitored region at the highest possible resolution. Our algorithm requires only a local exchange of information, is quick to converge and ensures longer periods of stability between successive reconfiguration steps. We evaluate the performance of our algorithm in simulation and demonstrate that local reconfiguration is sufficient for maintaining an acceptable coverage of target and non-target points.
{"title":"Local reconfiguration for simultaneous coverage and tracking in a large scale camera network","authors":"Bryan Lemon, V. Kulathumani","doi":"10.1109/THS.2011.6107857","DOIUrl":"https://doi.org/10.1109/THS.2011.6107857","url":null,"abstract":"We present a distributed camera control algorithm that can be used for the monitoring of large regions using a network of PTZ (pan/tilt/zoom) cameras. The proposed strategy would allow for continuous target tracking at a high resolution, while still maintaining coverage over the entire monitored region at the highest possible resolution. Our algorithm requires only a local exchange of information, is quick to converge and ensures longer periods of stability between successive reconfiguration steps. We evaluate the performance of our algorithm in simulation and demonstrate that local reconfiguration is sufficient for maintaining an acceptable coverage of target and non-target points.","PeriodicalId":228322,"journal":{"name":"2011 IEEE International Conference on Technologies for Homeland Security (HST)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115861653","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2011-12-19DOI: 10.1109/THS.2011.6107842
S. Subik, C. Wietfeld
In this paper, the authors present a novel solution for the integration of TETRA-based PMR and IP based wireless broadband networks through a novel inter-system interface. This solution enables secure group communications based on PMR standards using heterogeneous devices ranging from a traditional PMR device to smart phones such as the iPhone. Thereby a Smart-phone user will be enabled to leverage on one hand the multimedia data capabilities of 3G and 4G wireless networks (UMTS, LTE) while at the same time be part of a PMR group communication. In other words, any authorized Smart-phone can become part of a PMR communication group by simply downloading the appropriate, dedicated Application. As a key benefit, homeland security personnel can be included in the disaster response actions instantaneously, without necessarily carrying around a PMR device and without the need for PMR coverage. In contrast to existing solutions, the proposed interface solution prevents the reduction of the voice quality when bridging system boundaries by tandem encoding with a TETRA-over-IP (ToIP) interconnection. The presented solutions include different interconnection setups including Trunked Mode (TMO) and Direct Mode (DMO) capabilities. To enable the group communications services as known in PMR systems, a dedicated protocol, the Push-to-X protocol developed by CNI, is leveraged. The results of performance evaluations show that the speech quality is still acceptable even under harsh conditions. The proposed system therefore paves the way towards a future, high performance PMR based on LTE, while preserving backwards compatibility with existing PMR systems.
{"title":"Integrated PMR-broadband-IP network for secure realtime multimedia information sharing","authors":"S. Subik, C. Wietfeld","doi":"10.1109/THS.2011.6107842","DOIUrl":"https://doi.org/10.1109/THS.2011.6107842","url":null,"abstract":"In this paper, the authors present a novel solution for the integration of TETRA-based PMR and IP based wireless broadband networks through a novel inter-system interface. This solution enables secure group communications based on PMR standards using heterogeneous devices ranging from a traditional PMR device to smart phones such as the iPhone. Thereby a Smart-phone user will be enabled to leverage on one hand the multimedia data capabilities of 3G and 4G wireless networks (UMTS, LTE) while at the same time be part of a PMR group communication. In other words, any authorized Smart-phone can become part of a PMR communication group by simply downloading the appropriate, dedicated Application. As a key benefit, homeland security personnel can be included in the disaster response actions instantaneously, without necessarily carrying around a PMR device and without the need for PMR coverage. In contrast to existing solutions, the proposed interface solution prevents the reduction of the voice quality when bridging system boundaries by tandem encoding with a TETRA-over-IP (ToIP) interconnection. The presented solutions include different interconnection setups including Trunked Mode (TMO) and Direct Mode (DMO) capabilities. To enable the group communications services as known in PMR systems, a dedicated protocol, the Push-to-X protocol developed by CNI, is leveraged. The results of performance evaluations show that the speech quality is still acceptable even under harsh conditions. The proposed system therefore paves the way towards a future, high performance PMR based on LTE, while preserving backwards compatibility with existing PMR systems.","PeriodicalId":228322,"journal":{"name":"2011 IEEE International Conference on Technologies for Homeland Security (HST)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116280645","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2011-12-19DOI: 10.1109/THS.2011.6107878
Xunyi Yu, A. Ganz
We introduce a calibration free hybrid RF and video surveillance system for reliable tracking, identification in Mass Casualty Incidents (MCI). The system fuses RF measurements along with information harvested from the video such as target temporal, kinematic, and appearance information. Our hybrid RF and video surveillance system can be deployed rapidly without manual calibration of either the camera or the RF devices, and can work in complex RF environments. This is made possible by the simultaneous identification and mapping algorithm that iteratively refines the mapping of the radio beacon signal strength signature to target positions in video frames. The system is the basis of identity aware video surveillance, i.e. enabling unique identification of targets in the video and applying identity specific analytics roles to individual targets.
{"title":"A calibration free hybrid RF and video surveillance system for reliable tracking and identification","authors":"Xunyi Yu, A. Ganz","doi":"10.1109/THS.2011.6107878","DOIUrl":"https://doi.org/10.1109/THS.2011.6107878","url":null,"abstract":"We introduce a calibration free hybrid RF and video surveillance system for reliable tracking, identification in Mass Casualty Incidents (MCI). The system fuses RF measurements along with information harvested from the video such as target temporal, kinematic, and appearance information. Our hybrid RF and video surveillance system can be deployed rapidly without manual calibration of either the camera or the RF devices, and can work in complex RF environments. This is made possible by the simultaneous identification and mapping algorithm that iteratively refines the mapping of the radio beacon signal strength signature to target positions in video frames. The system is the basis of identity aware video surveillance, i.e. enabling unique identification of targets in the video and applying identity specific analytics roles to individual targets.","PeriodicalId":228322,"journal":{"name":"2011 IEEE International Conference on Technologies for Homeland Security (HST)","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115140119","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2011-12-19DOI: 10.1109/THS.2011.6107906
S. Ambroziak, R. Katulski, J. Sadowski, W. Siwicki, J. Stefanski
Since first travels by land or sea, it was necessary to determine position in an unknown environment. At the beginning methods were simple. They were based on the observation of characteristic points, in the case of shipping additional observations of the coastline. Then came a navigation based on astronomical methods (astronavigation). At the beginning of the XX-century a new way of determining the current location was developed. It uses radiowave signals. First came the radio-beacons, which at fixed intervals, transmitted well-defined sequence of radio signals. Then came ground-based systems. Pulse signals are received from at least three stations operating synchronously. Electronically measured the delay of one signal relative to the other, allows to determine the difference in distance separating the object from the localized sources. According to the principles of geometry allows the plot (or find) on the map hyperbole, which is the object. The newest way to determine your position are satellite systems. They are based on the measurement of arrival time of radio signals from satellites to the receiver. Currently, the most popular system is GPS (Global Positioning System). This system is fully controlled by the Department of Defense, and only the U.S. forces and their closest allies have guaranteed accuracy offered by the system. Armies of other countries can only use the civilian version. Due to the popularity of this system and its worldwide range, terrorist can build bombs with simple GPS receivers to detonate in a specific place. To prevent this, deliberate errors to the civilian version of the system can be introduced. Those deliberate errors will also prevent the use of GPS by the secret services or the armies of other countries than the U.S. This situation has spawned the need for an independent radiolocation system. This article describes the construction and operation of such a technology demonstrator that was developed at the Technical University of Gdansk. It was named AEGIR (according to Norse mythology: god of the seas and oceans). The main advantage of the system is to dispense with the chain organization of the reference station, which work with each other asynchronously. This paper presents results and analysis of its effectiveness.
{"title":"Asynchronous and self-organizing radiolocation system — AEGIR","authors":"S. Ambroziak, R. Katulski, J. Sadowski, W. Siwicki, J. Stefanski","doi":"10.1109/THS.2011.6107906","DOIUrl":"https://doi.org/10.1109/THS.2011.6107906","url":null,"abstract":"Since first travels by land or sea, it was necessary to determine position in an unknown environment. At the beginning methods were simple. They were based on the observation of characteristic points, in the case of shipping additional observations of the coastline. Then came a navigation based on astronomical methods (astronavigation). At the beginning of the XX-century a new way of determining the current location was developed. It uses radiowave signals. First came the radio-beacons, which at fixed intervals, transmitted well-defined sequence of radio signals. Then came ground-based systems. Pulse signals are received from at least three stations operating synchronously. Electronically measured the delay of one signal relative to the other, allows to determine the difference in distance separating the object from the localized sources. According to the principles of geometry allows the plot (or find) on the map hyperbole, which is the object. The newest way to determine your position are satellite systems. They are based on the measurement of arrival time of radio signals from satellites to the receiver. Currently, the most popular system is GPS (Global Positioning System). This system is fully controlled by the Department of Defense, and only the U.S. forces and their closest allies have guaranteed accuracy offered by the system. Armies of other countries can only use the civilian version. Due to the popularity of this system and its worldwide range, terrorist can build bombs with simple GPS receivers to detonate in a specific place. To prevent this, deliberate errors to the civilian version of the system can be introduced. Those deliberate errors will also prevent the use of GPS by the secret services or the armies of other countries than the U.S. This situation has spawned the need for an independent radiolocation system. This article describes the construction and operation of such a technology demonstrator that was developed at the Technical University of Gdansk. It was named AEGIR (according to Norse mythology: god of the seas and oceans). The main advantage of the system is to dispense with the chain organization of the reference station, which work with each other asynchronously. This paper presents results and analysis of its effectiveness.","PeriodicalId":228322,"journal":{"name":"2011 IEEE International Conference on Technologies for Homeland Security (HST)","volume":"132 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126287710","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2011-12-19DOI: 10.1109/THS.2011.6107890
C. Nelson, W. Pottenger
The detection of potentially threatening nuclear materials is a challenging homeland security problem. This research reports on the application of a novel statistical relational learning algorithm, Higher Order Naïve Bayes (HONB), to improve the detection and identification of nuclear isotopes. When classifying nuclear detection data, distinguishing potentially threatening from harmless radioisotopes is critical. These also must be distinguished from the naturally occurring radioactive background. This research applied Higher Order Learning to nuclear detection data to improve the detection and identification of four isotopes: Ga67, I131, In111, and Tc99m. In the research traditional IID machine learning methods are applied to the area of nuclear detection, and the results compared with the performance of leveraging higher-order dependencies between feature values using HONB. The findings give insight about the performance of higher-order classifiers (described in [2]) on datasets with small numbers of positive instances. In the initial study, Naïve Bayes was compared with its higher-order counterpart, Higher Order Naïve Bayes. HONB was found to perform statistically significantly better for isotope Ga67 when using a preprocessing methodology of discretizing then binarizing the input sensor data. Similar results were seen for different amounts of training data for I131, In111, and Tc99m. HONB was also found to perform statistically significantly better for isotopes I131 and Tc99m when the preprocessing involved normalization, discretization then binarization. This study shows that Higher Order Learning techniques can be very useful in the arena of nuclear detection.
{"title":"Nuclear detection using higher order learning","authors":"C. Nelson, W. Pottenger","doi":"10.1109/THS.2011.6107890","DOIUrl":"https://doi.org/10.1109/THS.2011.6107890","url":null,"abstract":"The detection of potentially threatening nuclear materials is a challenging homeland security problem. This research reports on the application of a novel statistical relational learning algorithm, Higher Order Naïve Bayes (HONB), to improve the detection and identification of nuclear isotopes. When classifying nuclear detection data, distinguishing potentially threatening from harmless radioisotopes is critical. These also must be distinguished from the naturally occurring radioactive background. This research applied Higher Order Learning to nuclear detection data to improve the detection and identification of four isotopes: Ga67, I131, In111, and Tc99m. In the research traditional IID machine learning methods are applied to the area of nuclear detection, and the results compared with the performance of leveraging higher-order dependencies between feature values using HONB. The findings give insight about the performance of higher-order classifiers (described in [2]) on datasets with small numbers of positive instances. In the initial study, Naïve Bayes was compared with its higher-order counterpart, Higher Order Naïve Bayes. HONB was found to perform statistically significantly better for isotope Ga67 when using a preprocessing methodology of discretizing then binarizing the input sensor data. Similar results were seen for different amounts of training data for I131, In111, and Tc99m. HONB was also found to perform statistically significantly better for isotopes I131 and Tc99m when the preprocessing involved normalization, discretization then binarization. This study shows that Higher Order Learning techniques can be very useful in the arena of nuclear detection.","PeriodicalId":228322,"journal":{"name":"2011 IEEE International Conference on Technologies for Homeland Security (HST)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129995478","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2011-12-19DOI: 10.1109/THS.2011.6107846
V. Lavigne, D. Gouin, Michael Davenport
Maintaining situation awareness in the maritime domain is a challenging mandate. Task analysis activities were conducted to identify where visual analytics science and technology could improve maritime domain awareness and reduce information overload. Three promising opportunities were identified: the visualization of normal maritime behaviour, anomaly detection, and the collaborative analysis of a vessel of interest. In this paper, we describe the result of our user studies along with potential visual analytics solutions and features considered for a maritime analytics prototype.
{"title":"Visual analytics for maritime domain awareness","authors":"V. Lavigne, D. Gouin, Michael Davenport","doi":"10.1109/THS.2011.6107846","DOIUrl":"https://doi.org/10.1109/THS.2011.6107846","url":null,"abstract":"Maintaining situation awareness in the maritime domain is a challenging mandate. Task analysis activities were conducted to identify where visual analytics science and technology could improve maritime domain awareness and reduce information overload. Three promising opportunities were identified: the visualization of normal maritime behaviour, anomaly detection, and the collaborative analysis of a vessel of interest. In this paper, we describe the result of our user studies along with potential visual analytics solutions and features considered for a maritime analytics prototype.","PeriodicalId":228322,"journal":{"name":"2011 IEEE International Conference on Technologies for Homeland Security (HST)","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131481887","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2011-12-19DOI: 10.1109/THS.2011.6107884
M. Staymates, G. Gillen, J. Grandner, Stefan R Lukow
In collaboration with the Transportation Security Laboratory, the National Institute of Standards and Technology has been developing a prototype shoe sampling system that relies on aerodynamic sampling for liberating, transporting, and collecting explosive contamination. Here, we focus on the measurement science of aerodynamic sampling with the goal of uncovering the underlying physics of the flow fields within these sampling systems. This paper will cover the results of a series of experiments that were used to help with the design of our prototype shoe sampling system. Laser light-sheet flow visualization revealed the bulk fluid motion inside and around the sampling system. Polymer microsphere particle standards were used to quantify the particle release efficiency of the shoe sampling system. Patches containing a known mass of explosives were also used to determine the effectiveness of particle release in the shoe sampler. Results from these experiments indicate that particle removal efficiency at a specific location is strongly influenced by its distance from an air jet and the type of explosive or material on the surface. The successful application of these flow visualization techniques and other metrology tools has helped us construct the sampling portion of a shoe screening prototype. The hope is that these tools will be useful to others who are developing next-generation aerodynamic sampling technologies.
{"title":"The development of an aerodynamic shoe sampling system","authors":"M. Staymates, G. Gillen, J. Grandner, Stefan R Lukow","doi":"10.1109/THS.2011.6107884","DOIUrl":"https://doi.org/10.1109/THS.2011.6107884","url":null,"abstract":"In collaboration with the Transportation Security Laboratory, the National Institute of Standards and Technology has been developing a prototype shoe sampling system that relies on aerodynamic sampling for liberating, transporting, and collecting explosive contamination. Here, we focus on the measurement science of aerodynamic sampling with the goal of uncovering the underlying physics of the flow fields within these sampling systems. This paper will cover the results of a series of experiments that were used to help with the design of our prototype shoe sampling system. Laser light-sheet flow visualization revealed the bulk fluid motion inside and around the sampling system. Polymer microsphere particle standards were used to quantify the particle release efficiency of the shoe sampling system. Patches containing a known mass of explosives were also used to determine the effectiveness of particle release in the shoe sampler. Results from these experiments indicate that particle removal efficiency at a specific location is strongly influenced by its distance from an air jet and the type of explosive or material on the surface. The successful application of these flow visualization techniques and other metrology tools has helped us construct the sampling portion of a shoe screening prototype. The hope is that these tools will be useful to others who are developing next-generation aerodynamic sampling technologies.","PeriodicalId":228322,"journal":{"name":"2011 IEEE International Conference on Technologies for Homeland Security (HST)","volume":"45 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121014864","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：