Pub Date : 2007-07-09DOI: 10.1109/ICIF.2007.4408169
D. Gains
We describe data fusion technology relevant to two applications of potential benefit to the Canadian army. The first application is a local situational awareness system (LSAS) while the second is a versatile surveillance platform. The LSAS improves an armored vehicle crew's ability to recognize and locate threats and hazards without leaving the relative safety of their vehicle. It is designed primarily to protect the soldiers involved. The surveillance application augments an operator's ability to detect and track objects of interest. This is desirable in modern environments where there are large numbers of closely spaced potential targets.
{"title":"Data fusion for Canadian army applications","authors":"D. Gains","doi":"10.1109/ICIF.2007.4408169","DOIUrl":"https://doi.org/10.1109/ICIF.2007.4408169","url":null,"abstract":"We describe data fusion technology relevant to two applications of potential benefit to the Canadian army. The first application is a local situational awareness system (LSAS) while the second is a versatile surveillance platform. The LSAS improves an armored vehicle crew's ability to recognize and locate threats and hazards without leaving the relative safety of their vehicle. It is designed primarily to protect the soldiers involved. The surveillance application augments an operator's ability to detect and track objects of interest. This is desirable in modern environments where there are large numbers of closely spaced potential targets.","PeriodicalId":298941,"journal":{"name":"2007 10th International Conference on Information Fusion","volume":"111 10","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120824228","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 : 2007-07-09DOI: 10.1109/ICIF.2007.4408113
A. Stotz, M. Sudit
Information fusion engine for real-time decision- making (INFERD) is a perceptual information fusion engine designed and developed for the purpose of cyber attack tracking and network situational awareness. While the original application was cyber orientated, the engine itself is designed to generalize and has been ported to other application environments such as maritime domain awareness and medical syndromic surveillance. Comparisons and contrasts are drawn to the traditional Kalman ground target tracking science, motivating high level architectural modules and presenting the cyber environment complexities and assumptions. Performance results are presented showing success in both detection accuracy and temporal expedience, an important design goal.
{"title":"INformation fusion engine for real-time decision-making (INFERD): A perceptual system for cyber attack tracking","authors":"A. Stotz, M. Sudit","doi":"10.1109/ICIF.2007.4408113","DOIUrl":"https://doi.org/10.1109/ICIF.2007.4408113","url":null,"abstract":"Information fusion engine for real-time decision- making (INFERD) is a perceptual information fusion engine designed and developed for the purpose of cyber attack tracking and network situational awareness. While the original application was cyber orientated, the engine itself is designed to generalize and has been ported to other application environments such as maritime domain awareness and medical syndromic surveillance. Comparisons and contrasts are drawn to the traditional Kalman ground target tracking science, motivating high level architectural modules and presenting the cyber environment complexities and assumptions. Performance results are presented showing success in both detection accuracy and temporal expedience, an important design goal.","PeriodicalId":298941,"journal":{"name":"2007 10th International Conference on Information Fusion","volume":"56 12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124396749","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 : 2007-07-09DOI: 10.1109/ICIF.2007.4408031
O. Bilenne
This work is concerned with the design of sensor fusion methods using the fault-tolerant interval functions proposed by K. Marzullo and U. Schmid. A trade-off exists between the precision of the interval functions and their tolerance to invalid input intervals. The study shows how the performances of the interval functions in terms of expected length and variance can be estimated from their asymptotic properties for large data samples. Under certain conditions, the limits of the fault- tolerant interval functions are proven to belong to the class of M-estimators, and to be asymptotically normal when the number of input intervals grows to infinity. The precision of the interval functions is predicted by the approximation of the actual functions by linear functionals that are easier to handle. The relevance of the asymptotic properties of the interval functions for finite input sets is tested on a simulated example.
{"title":"Design of fault-tolerant interval functions based on their large-sample properties","authors":"O. Bilenne","doi":"10.1109/ICIF.2007.4408031","DOIUrl":"https://doi.org/10.1109/ICIF.2007.4408031","url":null,"abstract":"This work is concerned with the design of sensor fusion methods using the fault-tolerant interval functions proposed by K. Marzullo and U. Schmid. A trade-off exists between the precision of the interval functions and their tolerance to invalid input intervals. The study shows how the performances of the interval functions in terms of expected length and variance can be estimated from their asymptotic properties for large data samples. Under certain conditions, the limits of the fault- tolerant interval functions are proven to belong to the class of M-estimators, and to be asymptotically normal when the number of input intervals grows to infinity. The precision of the interval functions is predicted by the approximation of the actual functions by linear functionals that are easier to handle. The relevance of the asymptotic properties of the interval functions for finite input sets is tested on a simulated example.","PeriodicalId":298941,"journal":{"name":"2007 10th International Conference on Information Fusion","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128698886","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 : 2007-07-09DOI: 10.1109/ICIF.2007.4408217
J. Llinas
The international defense and security community is moving ahead at flank speed to realize the vision of network centric warfare (NCW; aka network-enabled capability (NEC) and etc). Extensive efforts are being put forth to define, design, and develop many of the technical components of such a capability, to include varieties of networked communications systems, various highly-capable military platforms, and "service-oriented architectures" for a broad-based enterprise service middleware capability. To varying degrees, the human factors/human engineering community has also engaged in broad studies of "sensemaking" and "shared awareness" toward understanding some of the information-sharing and information- understanding paradigms put forward in the NCW literature.
{"title":"Intelligent agents as one framework for defining fusion requirements for complex adaptive systems","authors":"J. Llinas","doi":"10.1109/ICIF.2007.4408217","DOIUrl":"https://doi.org/10.1109/ICIF.2007.4408217","url":null,"abstract":"The international defense and security community is moving ahead at flank speed to realize the vision of network centric warfare (NCW; aka network-enabled capability (NEC) and etc). Extensive efforts are being put forth to define, design, and develop many of the technical components of such a capability, to include varieties of networked communications systems, various highly-capable military platforms, and \"service-oriented architectures\" for a broad-based enterprise service middleware capability. To varying degrees, the human factors/human engineering community has also engaged in broad studies of \"sensemaking\" and \"shared awareness\" toward understanding some of the information-sharing and information- understanding paradigms put forward in the NCW literature.","PeriodicalId":298941,"journal":{"name":"2007 10th International Conference on Information Fusion","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131249901","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 : 2007-07-09DOI: 10.1109/ICIF.2007.4408123
E. Santos, R. Sabourin, P. Maupin
Dynamic classifier selection has traditionally focused on selecting the most accurate classifier to predict the class of a particular test pattern. In this paper we propose a new dynamic selection method to select, from a population of ensembles, the most confident ensemble of classifiers to label the test sample. Such a level of confidence is measured by calculating the ambiguity of the ensemble on each test sample. We show theoretically and experimentally that choosing the ensemble of classifiers, from a population of high accurate ensembles, with lowest ambiguity among its members leads to increase the level of confidence of classification, consequently, increasing the generalization performance. Experimental results conducted to compare the proposed method to static selection and DCS-LA, demonstrate that our method outperforms both DCS-LA and static selection strategies when a population of high accurate ensembles is available.
{"title":"Ambiguity-guided dynamic selection of ensemble of classifiers","authors":"E. Santos, R. Sabourin, P. Maupin","doi":"10.1109/ICIF.2007.4408123","DOIUrl":"https://doi.org/10.1109/ICIF.2007.4408123","url":null,"abstract":"Dynamic classifier selection has traditionally focused on selecting the most accurate classifier to predict the class of a particular test pattern. In this paper we propose a new dynamic selection method to select, from a population of ensembles, the most confident ensemble of classifiers to label the test sample. Such a level of confidence is measured by calculating the ambiguity of the ensemble on each test sample. We show theoretically and experimentally that choosing the ensemble of classifiers, from a population of high accurate ensembles, with lowest ambiguity among its members leads to increase the level of confidence of classification, consequently, increasing the generalization performance. Experimental results conducted to compare the proposed method to static selection and DCS-LA, demonstrate that our method outperforms both DCS-LA and static selection strategies when a population of high accurate ensembles is available.","PeriodicalId":298941,"journal":{"name":"2007 10th International Conference on Information Fusion","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132585265","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 : 2007-07-09DOI: 10.1109/ICIF.2007.4408152
M. Oxley, S. Thorsen, Christine M. Schubert-Kabban
A reasonable starting place for developing decision fusion rules of families of classification systems is using the logical AND and OR rules. These two rules, along with the unary rule NOT, can lead to a Boolean algebra when a number of properties are shown to exist. This paper examines how these rules for classification system families comprise a Boolean algebra of systems. This Boolean algebra of families is then shown under assumptions of independence to be isomorphic to a Boolean algebra of receiver operating characteristic (ROC) curves. These decision fusion rules produce ROC curves which become the bounds by which to test non-Boolean, possibly non-decision fusion rules for performance increases. We give an example to demonstrate the usefulness of this Boolean algebra of ROC curves.
{"title":"A Boolean Algebra of receiver operating characteristic curves","authors":"M. Oxley, S. Thorsen, Christine M. Schubert-Kabban","doi":"10.1109/ICIF.2007.4408152","DOIUrl":"https://doi.org/10.1109/ICIF.2007.4408152","url":null,"abstract":"A reasonable starting place for developing decision fusion rules of families of classification systems is using the logical AND and OR rules. These two rules, along with the unary rule NOT, can lead to a Boolean algebra when a number of properties are shown to exist. This paper examines how these rules for classification system families comprise a Boolean algebra of systems. This Boolean algebra of families is then shown under assumptions of independence to be isomorphic to a Boolean algebra of receiver operating characteristic (ROC) curves. These decision fusion rules produce ROC curves which become the bounds by which to test non-Boolean, possibly non-decision fusion rules for performance increases. We give an example to demonstrate the usefulness of this Boolean algebra of ROC curves.","PeriodicalId":298941,"journal":{"name":"2007 10th International Conference on Information Fusion","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128148978","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 : 2007-07-09DOI: 10.1109/ICIF.2007.4408074
Jesús García, J. M. Molina, J. Besada, G. D. Miguel
This work addresses off-line accurate trajectory reconstruction for air traffic control. We propose the use of specific dynamic models after identification of regular motion patterns. Datasets recorded from opportunity traffic are first segmented in motion segments, based on the mode probabilities of an IMM filter. Then, reconstruction is applied with an optimal smoothing filter operating forward and backward. The parameters describing the specific modes are estimated and then used as external input for smoothing filters. The performance of this approach is compared with a method based on interpolation B-splines. Comparative results on simulated and real data are discussed at the end.
{"title":"Model-based trajectory reconstruction using IMM smoothing and motion pattern identification","authors":"Jesús García, J. M. Molina, J. Besada, G. D. Miguel","doi":"10.1109/ICIF.2007.4408074","DOIUrl":"https://doi.org/10.1109/ICIF.2007.4408074","url":null,"abstract":"This work addresses off-line accurate trajectory reconstruction for air traffic control. We propose the use of specific dynamic models after identification of regular motion patterns. Datasets recorded from opportunity traffic are first segmented in motion segments, based on the mode probabilities of an IMM filter. Then, reconstruction is applied with an optimal smoothing filter operating forward and backward. The parameters describing the specific modes are estimated and then used as external input for smoothing filters. The performance of this approach is compared with a method based on interpolation B-splines. Comparative results on simulated and real data are discussed at the end.","PeriodicalId":298941,"journal":{"name":"2007 10th International Conference on Information Fusion","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132021992","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 : 2007-07-09DOI: 10.1109/ICIF.2007.4408057
S. Boutoille, S. Reboul, M. Benjelloun
This paper presents a Bayesian off-line fusion segmentation method, applied to the code tracking in a multi-carrier GPS receiver. The tracking is realized with discriminator values obtained on the different carrier frequencies. We suppose that the evolution of the pseudo-ranges satellites-receiver is piecewise linear. We propose a Bayesian method for the fusion of change detection models in the discriminators evolution. In this context, we construct a penalized contrast function to estimate the model parameters. The contrast function is deduced from log-likelihood of the parametric distribution that models the discriminators statistic evolution. We deduced the penalty term from the prior law of change instants. It is composed of parameters that guide the number of changes and of parameters that will bring prior information on the ionospheric delays between the GPS signals on the different carrier frequencies. We show on synthetic and real data the feasibility and the contribution of our method.
{"title":"Bayesian off-line segmentation applied to multi-carrier GPS signals fusion","authors":"S. Boutoille, S. Reboul, M. Benjelloun","doi":"10.1109/ICIF.2007.4408057","DOIUrl":"https://doi.org/10.1109/ICIF.2007.4408057","url":null,"abstract":"This paper presents a Bayesian off-line fusion segmentation method, applied to the code tracking in a multi-carrier GPS receiver. The tracking is realized with discriminator values obtained on the different carrier frequencies. We suppose that the evolution of the pseudo-ranges satellites-receiver is piecewise linear. We propose a Bayesian method for the fusion of change detection models in the discriminators evolution. In this context, we construct a penalized contrast function to estimate the model parameters. The contrast function is deduced from log-likelihood of the parametric distribution that models the discriminators statistic evolution. We deduced the penalty term from the prior law of change instants. It is composed of parameters that guide the number of changes and of parameters that will bring prior information on the ionospheric delays between the GPS signals on the different carrier frequencies. We show on synthetic and real data the feasibility and the contribution of our method.","PeriodicalId":298941,"journal":{"name":"2007 10th International Conference on Information Fusion","volume":"83 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134092403","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 : 2007-07-09DOI: 10.1109/ICIF.2007.4408040
R. Streit
An alternating directions method is presented for joint maximum a posteriori estimation of target track and sensor field using bistatic range data. The algorithm cycles over two sub-algorithms: one improves the target state estimate conditioned on sensor field state, and the other improves the sensor field state estimate conditioned on target state. Nonlinearities in the sub-algorithms are mitigated by decomposing their likelihood functions using integral representations. The kernels of these integrals are linear-Gaussian densities in the states to be estimated, a fact that facilitates the use of missing data methods. The resulting sub-algorithms are equivalent to linear-Gaussian Kalman smoothers. The alternating directions algorithm is guaranteed to converge to (at least) a local maximum of the joint target-field likelihood function.
{"title":"Likelihood function decomposition for multistatic tracking and field stabilization","authors":"R. Streit","doi":"10.1109/ICIF.2007.4408040","DOIUrl":"https://doi.org/10.1109/ICIF.2007.4408040","url":null,"abstract":"An alternating directions method is presented for joint maximum a posteriori estimation of target track and sensor field using bistatic range data. The algorithm cycles over two sub-algorithms: one improves the target state estimate conditioned on sensor field state, and the other improves the sensor field state estimate conditioned on target state. Nonlinearities in the sub-algorithms are mitigated by decomposing their likelihood functions using integral representations. The kernels of these integrals are linear-Gaussian densities in the states to be estimated, a fact that facilitates the use of missing data methods. The resulting sub-algorithms are equivalent to linear-Gaussian Kalman smoothers. The alternating directions algorithm is guaranteed to converge to (at least) a local maximum of the joint target-field likelihood function.","PeriodicalId":298941,"journal":{"name":"2007 10th International Conference on Information Fusion","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132934475","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 : 2007-07-09DOI: 10.1109/ICIF.2007.4407974
P. H. Foo, G. Ng
The interacting multiple model (IMM) algorithm is a widely accepted state estimation scheme for solving maneuvering target tracking problems, which are generally nonlinear. During the IMM filtering process, serious errors can arise when a Gaussian mixture of posterior probability density functions is approximated by a single Gaussian. Particle filters (PFs) are effective in dealing with nonlinearity and non-Gaussianity. This work considers an IMM algorithm that includes a constant velocity model, a constant acceleration model and a 3D turning rate (3DTR) model for tracking three-dimensional (3D) target motion, using various combinations of nonlinear filters. In existing literature on combining IMM and particle filtering techniques to tackle difficult target maneuvers, a PF is usually used in every model In comparison, simulation results show that by using a computationally economical PF in the 3DTR model and Kalman filters in the remaining models, superior performance can be achieved with significant reduction in computational costs.
{"title":"Combining IMM Method with Particle filters for 3D maneuvering target tracking","authors":"P. H. Foo, G. Ng","doi":"10.1109/ICIF.2007.4407974","DOIUrl":"https://doi.org/10.1109/ICIF.2007.4407974","url":null,"abstract":"The interacting multiple model (IMM) algorithm is a widely accepted state estimation scheme for solving maneuvering target tracking problems, which are generally nonlinear. During the IMM filtering process, serious errors can arise when a Gaussian mixture of posterior probability density functions is approximated by a single Gaussian. Particle filters (PFs) are effective in dealing with nonlinearity and non-Gaussianity. This work considers an IMM algorithm that includes a constant velocity model, a constant acceleration model and a 3D turning rate (3DTR) model for tracking three-dimensional (3D) target motion, using various combinations of nonlinear filters. In existing literature on combining IMM and particle filtering techniques to tackle difficult target maneuvers, a PF is usually used in every model In comparison, simulation results show that by using a computationally economical PF in the 3DTR model and Kalman filters in the remaining models, superior performance can be achieved with significant reduction in computational costs.","PeriodicalId":298941,"journal":{"name":"2007 10th International Conference on Information Fusion","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133281995","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：