Page 95. 63 4 Mechanical Detection of Deception: A Short Review Kristin E. Heckman, D. Sc. Mark D... more Page 95. 63 4 Mechanical Detection of Deception: A Short Review Kristin E. Heckman, D. Sc. Mark D. Happel, D. Sc. with the assistance of Janice R. Ballo, Research Librarian The MITRE Corporation November 2005 Abstract ...
Proceedings Mexico-USA Collaboration in Intelligent Systems Technologies., 1996
The Adaptive Learning Image and Signal Analysis (ALISA) system was used to extract geometric info... more The Adaptive Learning Image and Signal Analysis (ALISA) system was used to extract geometric information from images of printed text (alphabetic characters) for optical character recognition. Each pixel in a character image was classified by the ALISA Geometry Module as a constituent of a small universal (canonical) set of primitive geometry classes, creating a geometric class map that was spatially isomorphic with the original image. The canonical class maps were then mode filtered to reduce the sparseness of the original images and to improve the separability and robustness of the classification process. Each of - the pixels in the canonical class maps was then classified again as a constituent of a printed character by training ALISA to recognize the secular geometries of the canonical geometric classes for each character. It was hypothesized that a combination of several of these secular class maps, each captured at a different spatial resolution, could be scanned in parallel to...
While specialized hardware description languages allow for maximum capability and efficiency in a... more While specialized hardware description languages allow for maximum capability and efficiency in a design automation system, the use of a general purpose language in the same role can make the system more available or more pr act i ca 1 for a larger set of users. This project demonstrates the use of ADA* for the description and simulation of small digital signal processing systems. Building on conventions and primitives proposed by Denyer and Renshaw, a simple subsystem was described in ADA and then tested with a small simulator also written in ADA. * ADA is a trademark of the United States Department of Defense ADA Joint Program Office (AJPO).
This article examines the current technology-based capabilities of national security and law enfo... more This article examines the current technology-based capabilities of national security and law enforcement officials to assess the credibility of individuals who are being evaluated as a potential source of information or to determine whether they can be trusted with sensitive information. At present, these officials, both domestically and internationally, rely most heavily on the polygraph for a wide variety of credibility assessment applications. However, its accuracy and reliability vary greatly across the different investigative problems to which it is applied. Major improvements in credibility assessment will likely require considerable investments in basic research, but more modest improvements appear within reach by using existing instruments and methods. Perhaps the most promising is the electroencephalogram (EEG), which may be able to detect when an individual is attempting to conceal information. The applicable EEG-based credibility assessment research is reviewed, showing l...
The design of an optimal Bayesian classifier for multiple features is dependent on the estimation... more The design of an optimal Bayesian classifier for multiple features is dependent on the estimation of multidimensional joint probability density functions and therefore requires a design sample size that increases exponentially with the number of dimensions. A method was developed that combines classifications from marginal density functions using an additional classifier. Unlike voting methods, this method can select a more appropriate class than the ones selected by the marginal classifiers, thus "overriding" their decisions. For two classes and two features, this method always demonstrates a probability of error no worse than the probability of error of the best marginal classifier.
Optics and Photonics in Global Homeland Security, 2005
The National Geospatial-Intelligence Agency (NGA) is faced with the difficult task of extracting ... more The National Geospatial-Intelligence Agency (NGA) is faced with the difficult task of extracting geospatial intelligence information on complex, time-sensitive targets from a growing volume of images. Neuroscience promises to provide basic research findings that could translate into tools, training, and procedures capable of enhancing the current analysts' performance and productivity, as well as leading toward tools for automated image analysis.
The use of multiple features by a classifier often leads to a reduced probability of error, but t... more The use of multiple features by a classifier often leads to a reduced probability of error, but the design of an optimal Bayesian classifier for multiple features is dependent on the estimation of multidimensional joint probability density functions and therefore requires a design sample size that, in general, increases exponentially with the number of dimensions. The classification method described in this paper makes decisions by combining the decisions made by multiple Bayesian classifiers using an additional classifier that estimates the joint probability densities of the decision space rather than the joint probability densities of the feature space. A proof is presented for the restricted case of two classes and two features; showing that the method always demonstrates a probability of error that is less than or equal to the probability of error of the marginal classifier with the lowest probability of error.
The Adaptive Learning Image and Signal Analysis (ALISA) system was used to extract geometric info... more The Adaptive Learning Image and Signal Analysis (ALISA) system was used to extract geometric information from images of printed text (alphabetic characters) for optical character recognition. Each pixel in a character image was classified by the ALISA Geometry Module as a constituent of a small universal (canonical) set of primitive geometry classes, creating a geometric class map that was spatially
The detection of deception is among the most important and pressing requirements faced by federal... more The detection of deception is among the most important and pressing requirements faced by federal agencies with national security responsibilities. The polygraph is insufficient in its present state of development for meeting the needs of national security. While some neuroscience-based alternatives to the polygraph have been proposed (e.g., EEG and fMRI), there are significant problems with these techniques and consideration of their operational use is premature. The development of a more effective means for detecting deception will require substantial conceptual advances in the science of deception, in particular the establishment of a sound theoretical basis on which to design such a system. Neuroscience and related fields can make significant contributions toward the development of a theory of deception, given sufficient government support and commitment to such an effort. However, even a sound theory of deception cannot guarantee success; it is vital that the associated policy, legal, and ethical implications of such a system be taken into account.
International Journal on Artificial Intelligence Tools, 2001
The design of an optimal Bayesian classifier for multiple features is dependent on the estimation... more The design of an optimal Bayesian classifier for multiple features is dependent on the estimation of multidimensional joint probability density functions and therefore requires a design sample size that increases exponentially with the number of dimensions. A method was developed that combines classification decisions from marginal density functions using an additional classifier. Unlike voting methods, this method can select a more appropriate class than the ones selected by the marginal classifiers, thus…
Proceedings of the 13th International FLAIRS …, 2000
The design of an optimal Bayesian classifier for multiple features is dependent on the estimation... more The design of an optimal Bayesian classifier for multiple features is dependent on the estimation of multidimensional joint probability density functions and therefore requires a design sample size that increases exponentially with the number of dimensions. A method was developed that combines classifications from marginal density functions using an additional classifier. Unlike voting methods, this method can select a more appropriate class than the ones selected by the marginal classifiers, thus "overriding" their decisions. For two classes and two features, this method always demonstrates a probability of error no worse than the probability of error of the best marginal classifier.
The papers included in this volume were part of the technical conference cited on the cover and t... more The papers included in this volume were part of the technical conference cited on the cover and title page. Papers were selected and subject to review by the editors and conference program committee. Some conference presentations may not be available for publication. The papers published in these proceedings reflect the work and thoughts of the authors and are published herein as submitted. The publisher is not responsible for the validity of the information or for any outcomes resulting from reliance thereon. ... Please use the following format to cite ...
Page 95. 63 4 Mechanical Detection of Deception: A Short Review Kristin E. Heckman, D. Sc. Mark D... more Page 95. 63 4 Mechanical Detection of Deception: A Short Review Kristin E. Heckman, D. Sc. Mark D. Happel, D. Sc. with the assistance of Janice R. Ballo, Research Librarian The MITRE Corporation November 2005 Abstract ...
Proceedings Mexico-USA Collaboration in Intelligent Systems Technologies., 1996
The Adaptive Learning Image and Signal Analysis (ALISA) system was used to extract geometric info... more The Adaptive Learning Image and Signal Analysis (ALISA) system was used to extract geometric information from images of printed text (alphabetic characters) for optical character recognition. Each pixel in a character image was classified by the ALISA Geometry Module as a constituent of a small universal (canonical) set of primitive geometry classes, creating a geometric class map that was spatially isomorphic with the original image. The canonical class maps were then mode filtered to reduce the sparseness of the original images and to improve the separability and robustness of the classification process. Each of - the pixels in the canonical class maps was then classified again as a constituent of a printed character by training ALISA to recognize the secular geometries of the canonical geometric classes for each character. It was hypothesized that a combination of several of these secular class maps, each captured at a different spatial resolution, could be scanned in parallel to...
While specialized hardware description languages allow for maximum capability and efficiency in a... more While specialized hardware description languages allow for maximum capability and efficiency in a design automation system, the use of a general purpose language in the same role can make the system more available or more pr act i ca 1 for a larger set of users. This project demonstrates the use of ADA* for the description and simulation of small digital signal processing systems. Building on conventions and primitives proposed by Denyer and Renshaw, a simple subsystem was described in ADA and then tested with a small simulator also written in ADA. * ADA is a trademark of the United States Department of Defense ADA Joint Program Office (AJPO).
This article examines the current technology-based capabilities of national security and law enfo... more This article examines the current technology-based capabilities of national security and law enforcement officials to assess the credibility of individuals who are being evaluated as a potential source of information or to determine whether they can be trusted with sensitive information. At present, these officials, both domestically and internationally, rely most heavily on the polygraph for a wide variety of credibility assessment applications. However, its accuracy and reliability vary greatly across the different investigative problems to which it is applied. Major improvements in credibility assessment will likely require considerable investments in basic research, but more modest improvements appear within reach by using existing instruments and methods. Perhaps the most promising is the electroencephalogram (EEG), which may be able to detect when an individual is attempting to conceal information. The applicable EEG-based credibility assessment research is reviewed, showing l...
The design of an optimal Bayesian classifier for multiple features is dependent on the estimation... more The design of an optimal Bayesian classifier for multiple features is dependent on the estimation of multidimensional joint probability density functions and therefore requires a design sample size that increases exponentially with the number of dimensions. A method was developed that combines classifications from marginal density functions using an additional classifier. Unlike voting methods, this method can select a more appropriate class than the ones selected by the marginal classifiers, thus "overriding" their decisions. For two classes and two features, this method always demonstrates a probability of error no worse than the probability of error of the best marginal classifier.
Optics and Photonics in Global Homeland Security, 2005
The National Geospatial-Intelligence Agency (NGA) is faced with the difficult task of extracting ... more The National Geospatial-Intelligence Agency (NGA) is faced with the difficult task of extracting geospatial intelligence information on complex, time-sensitive targets from a growing volume of images. Neuroscience promises to provide basic research findings that could translate into tools, training, and procedures capable of enhancing the current analysts' performance and productivity, as well as leading toward tools for automated image analysis.
The use of multiple features by a classifier often leads to a reduced probability of error, but t... more The use of multiple features by a classifier often leads to a reduced probability of error, but the design of an optimal Bayesian classifier for multiple features is dependent on the estimation of multidimensional joint probability density functions and therefore requires a design sample size that, in general, increases exponentially with the number of dimensions. The classification method described in this paper makes decisions by combining the decisions made by multiple Bayesian classifiers using an additional classifier that estimates the joint probability densities of the decision space rather than the joint probability densities of the feature space. A proof is presented for the restricted case of two classes and two features; showing that the method always demonstrates a probability of error that is less than or equal to the probability of error of the marginal classifier with the lowest probability of error.
The Adaptive Learning Image and Signal Analysis (ALISA) system was used to extract geometric info... more The Adaptive Learning Image and Signal Analysis (ALISA) system was used to extract geometric information from images of printed text (alphabetic characters) for optical character recognition. Each pixel in a character image was classified by the ALISA Geometry Module as a constituent of a small universal (canonical) set of primitive geometry classes, creating a geometric class map that was spatially
The detection of deception is among the most important and pressing requirements faced by federal... more The detection of deception is among the most important and pressing requirements faced by federal agencies with national security responsibilities. The polygraph is insufficient in its present state of development for meeting the needs of national security. While some neuroscience-based alternatives to the polygraph have been proposed (e.g., EEG and fMRI), there are significant problems with these techniques and consideration of their operational use is premature. The development of a more effective means for detecting deception will require substantial conceptual advances in the science of deception, in particular the establishment of a sound theoretical basis on which to design such a system. Neuroscience and related fields can make significant contributions toward the development of a theory of deception, given sufficient government support and commitment to such an effort. However, even a sound theory of deception cannot guarantee success; it is vital that the associated policy, legal, and ethical implications of such a system be taken into account.
International Journal on Artificial Intelligence Tools, 2001
The design of an optimal Bayesian classifier for multiple features is dependent on the estimation... more The design of an optimal Bayesian classifier for multiple features is dependent on the estimation of multidimensional joint probability density functions and therefore requires a design sample size that increases exponentially with the number of dimensions. A method was developed that combines classification decisions from marginal density functions using an additional classifier. Unlike voting methods, this method can select a more appropriate class than the ones selected by the marginal classifiers, thus…
Proceedings of the 13th International FLAIRS …, 2000
The design of an optimal Bayesian classifier for multiple features is dependent on the estimation... more The design of an optimal Bayesian classifier for multiple features is dependent on the estimation of multidimensional joint probability density functions and therefore requires a design sample size that increases exponentially with the number of dimensions. A method was developed that combines classifications from marginal density functions using an additional classifier. Unlike voting methods, this method can select a more appropriate class than the ones selected by the marginal classifiers, thus "overriding" their decisions. For two classes and two features, this method always demonstrates a probability of error no worse than the probability of error of the best marginal classifier.
The papers included in this volume were part of the technical conference cited on the cover and t... more The papers included in this volume were part of the technical conference cited on the cover and title page. Papers were selected and subject to review by the editors and conference program committee. Some conference presentations may not be available for publication. The papers published in these proceedings reflect the work and thoughts of the authors and are published herein as submitted. The publisher is not responsible for the validity of the information or for any outcomes resulting from reliance thereon. ... Please use the following format to cite ...
Uploads
Papers by Mark Happel