Pub Date : 2006-07-10DOI: 10.1109/ICIF.2006.301632
Bin Yu, K. Sycara
The problem of decision fusion has been studied for distributed sensor systems in the past two decades. Various techniques have been developed for either binary or multiple hypotheses decision fusion. However, most of them do not address the challenges that come with the changing quality of sensor data. In this paper we investigate adaptive decision fusion rules for multiple hypotheses within the framework of Dempster-Shafer theory. We provide a novel learning algorithm for determining the quality of sensor data in the fusion process. In our approach each sensor actively learns the quality of information from different sensors and updates their reliabilities using the weighted majority technique. Several examples are provided to show the effectiveness of our approach
{"title":"Learning the Quality of Sensor Data in Distributed Decision Fusion","authors":"Bin Yu, K. Sycara","doi":"10.1109/ICIF.2006.301632","DOIUrl":"https://doi.org/10.1109/ICIF.2006.301632","url":null,"abstract":"The problem of decision fusion has been studied for distributed sensor systems in the past two decades. Various techniques have been developed for either binary or multiple hypotheses decision fusion. However, most of them do not address the challenges that come with the changing quality of sensor data. In this paper we investigate adaptive decision fusion rules for multiple hypotheses within the framework of Dempster-Shafer theory. We provide a novel learning algorithm for determining the quality of sensor data in the fusion process. In our approach each sensor actively learns the quality of information from different sensors and updates their reliabilities using the weighted majority technique. Several examples are provided to show the effectiveness of our approach","PeriodicalId":248061,"journal":{"name":"2006 9th International Conference on Information Fusion","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130475887","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 : 2006-07-10DOI: 10.1109/ICIF.2006.301741
Hugues Demers, G. Michaud, Daniel Turgeon
The development of an algorithm for fusing an ESM track to multiple radar tracks is presented. This work is motivated by the difficulty of associating ESM sensor data with large measurement errors to closely-spaced radar tracks. The algorithm presents a novel approach to fusing identity information. It assigns to multiple radar tracks the identity information content of an ESM track. The identity fusion is performed using the Dempster-Shafer rule of combination. A weight based on the positional likelihood of association is included in the fusion process. Simulations of a group of targets for which angular distances are similar to the measurement errors of the ESM sensor are presented. Results show that it is possible to correctly identify a target within the group in a reasonable time interval without having to wait for the group to completely separate
{"title":"Identity multiassignment in ESM to radar fusion","authors":"Hugues Demers, G. Michaud, Daniel Turgeon","doi":"10.1109/ICIF.2006.301741","DOIUrl":"https://doi.org/10.1109/ICIF.2006.301741","url":null,"abstract":"The development of an algorithm for fusing an ESM track to multiple radar tracks is presented. This work is motivated by the difficulty of associating ESM sensor data with large measurement errors to closely-spaced radar tracks. The algorithm presents a novel approach to fusing identity information. It assigns to multiple radar tracks the identity information content of an ESM track. The identity fusion is performed using the Dempster-Shafer rule of combination. A weight based on the positional likelihood of association is included in the fusion process. Simulations of a group of targets for which angular distances are similar to the measurement errors of the ESM sensor are presented. Results show that it is possible to correctly identify a target within the group in a reasonable time interval without having to wait for the group to completely separate","PeriodicalId":248061,"journal":{"name":"2006 9th International Conference on Information Fusion","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127921910","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 : 2006-07-10DOI: 10.1109/ICIF.2006.301679
B. Cour, Christopher Collins, J. Landry
This paper describes the multi-everything sonar simulator (MESS), a system for performing general active or passive undersea sonar simulations. It is designed to provide element or beam-level data, in the time or frequency domain, in either a real or basebanded format. It is capable of handling any number and variety of sources, receivers, and targets with arbitrary, rigid-body trajectories in three dimensions. In general, simulated data will contain contributions from all sound sources: ambient noise, reverberation, source direct blasts, target echoes, target radiated noise and receiver self noise. The underlying signal generation, acoustic propagation, and physical interactions are performed using the sonar simulation toolset (SST), which in turn uses the comprehensive acoustic sonar system (CASS) and Gaussian ray bundle (GRAB) algorithm for eigenray generation. Acoustic propagation is ray-based only but is range dependent. The system may be used for generating active, passive or combined active/passive scenarios. It may also be used to inject active or passive targets into existing, real-world data sets
{"title":"Multi-everything Sonar Simulator (MESS)","authors":"B. Cour, Christopher Collins, J. Landry","doi":"10.1109/ICIF.2006.301679","DOIUrl":"https://doi.org/10.1109/ICIF.2006.301679","url":null,"abstract":"This paper describes the multi-everything sonar simulator (MESS), a system for performing general active or passive undersea sonar simulations. It is designed to provide element or beam-level data, in the time or frequency domain, in either a real or basebanded format. It is capable of handling any number and variety of sources, receivers, and targets with arbitrary, rigid-body trajectories in three dimensions. In general, simulated data will contain contributions from all sound sources: ambient noise, reverberation, source direct blasts, target echoes, target radiated noise and receiver self noise. The underlying signal generation, acoustic propagation, and physical interactions are performed using the sonar simulation toolset (SST), which in turn uses the comprehensive acoustic sonar system (CASS) and Gaussian ray bundle (GRAB) algorithm for eigenray generation. Acoustic propagation is ray-based only but is range dependent. The system may be used for generating active, passive or combined active/passive scenarios. It may also be used to inject active or passive targets into existing, real-world data sets","PeriodicalId":248061,"journal":{"name":"2006 9th International Conference on Information Fusion","volume":"R-30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126629517","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 : 2006-07-10DOI: 10.1109/ICIF.2006.301622
T. Bieker
Classification of high-range-resolution profiles is a viable method of non-cooperative target identification. In order to increase the reliability and robustness of the classification result, methods of decision-level identity fusion can be applied. Different approaches have been used for a cumulative fusion of declarations of successively recorded radar range profiles. Besides probabilistic techniques such as the Bayesian fusion, non-probabilistic methods based on Dempster-Shafer or voting algorithms have come into focus. In this paper these different approaches are compared for typical situations which can arise in aircraft identification scenarios
{"title":"Comparison of Fusion Methods for Successive Declarations of Radar Range Pro les","authors":"T. Bieker","doi":"10.1109/ICIF.2006.301622","DOIUrl":"https://doi.org/10.1109/ICIF.2006.301622","url":null,"abstract":"Classification of high-range-resolution profiles is a viable method of non-cooperative target identification. In order to increase the reliability and robustness of the classification result, methods of decision-level identity fusion can be applied. Different approaches have been used for a cumulative fusion of declarations of successively recorded radar range profiles. Besides probabilistic techniques such as the Bayesian fusion, non-probabilistic methods based on Dempster-Shafer or voting algorithms have come into focus. In this paper these different approaches are compared for typical situations which can arise in aircraft identification scenarios","PeriodicalId":248061,"journal":{"name":"2006 9th International Conference on Information Fusion","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126839231","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 : 2006-07-10DOI: 10.1109/ICIF.2006.301554
P. Svenson
Complex networks have recently emerged as an independent area of study. It has connections to random graph theory from mathematics as well as to social network analysis and recent work by physicists interested in understanding the behaviour of large, interacting networks. Network models are important for information fusion in two manners. First, the command and control networks of distributed information fusion systems must be designed in such a way that they are both robust against failures and attacks and so that information spreads quickly in them. Second, network models and social network analysis is an important tool to use when analyzing the opponents facing us in international operations. In this paper, we describe the basics of complex network models and point out how they can be used for both these purposes. By simulating several different network architectures, it will be possible to choose the best
{"title":"Complex networks and social network analysis in information fusion","authors":"P. Svenson","doi":"10.1109/ICIF.2006.301554","DOIUrl":"https://doi.org/10.1109/ICIF.2006.301554","url":null,"abstract":"Complex networks have recently emerged as an independent area of study. It has connections to random graph theory from mathematics as well as to social network analysis and recent work by physicists interested in understanding the behaviour of large, interacting networks. Network models are important for information fusion in two manners. First, the command and control networks of distributed information fusion systems must be designed in such a way that they are both robust against failures and attacks and so that information spreads quickly in them. Second, network models and social network analysis is an important tool to use when analyzing the opponents facing us in international operations. In this paper, we describe the basics of complex network models and point out how they can be used for both these purposes. By simulating several different network architectures, it will be possible to choose the best","PeriodicalId":248061,"journal":{"name":"2006 9th International Conference on Information Fusion","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126855569","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 : 2006-07-10DOI: 10.1109/ICIF.2006.301641
Federico Perea, H. D. Waard
The multidimensional assignment problem (MAP) is a combinatorial optimization problem arising in many applications, for instance in multi-target multi-sensor tracking problems. It is well-known that the MAP is NP-hard. The objective of a MAP is to match d-tuples of objects in such a way that the solution with the optimum total cost is found. In this paper a new class of approximation algorithms to solve the MAP is presented, named K-SGTS, and its effectiveness in multi-target multi-sensor tracking situations is shown. Its computational complexity is proven to be polynomial. Experimental results on the accuracy and speed of K-SGTS are provided in the last section of the paper
{"title":"A new class of Heuristic Polynomial Time Algorithms to solve the Multidimensional Assignment Problem","authors":"Federico Perea, H. D. Waard","doi":"10.1109/ICIF.2006.301641","DOIUrl":"https://doi.org/10.1109/ICIF.2006.301641","url":null,"abstract":"The multidimensional assignment problem (MAP) is a combinatorial optimization problem arising in many applications, for instance in multi-target multi-sensor tracking problems. It is well-known that the MAP is NP-hard. The objective of a MAP is to match d-tuples of objects in such a way that the solution with the optimum total cost is found. In this paper a new class of approximation algorithms to solve the MAP is presented, named K-SGTS, and its effectiveness in multi-target multi-sensor tracking situations is shown. Its computational complexity is proven to be polynomial. Experimental results on the accuracy and speed of K-SGTS are provided in the last section of the paper","PeriodicalId":248061,"journal":{"name":"2006 9th International Conference on Information Fusion","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122964700","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 : 2006-07-10DOI: 10.1109/ICIF.2006.301666
E. Dura, B. Gawrońska, B. Olsson, Björn Erlendsson
The long-term goal of the research presented in this paper is to incorporate linguistic text analysis into a system for evaluation of biological pathways. In this system, relations extracted from biomedical texts will be compared with pathways encoded in existing specialized databases. In this way, the biologist's conclusions regarding the plausibility and/or novelty of a certain relation between genes, proteins, etc., can be supported by fused information from biological databases and biological literature. We aim at overcoming the shortcomings of existing systems for information retrieval by proposing a method based on thorough linguistic analysis of a large text corpus. In this paper, we present a comparative analysis of two corpora: one consisting of biomedical texts from PubMed, the other one of general English prose. The results stress the importance of taking multiword entries into account when constructing a system for extracting biological relations from texts
{"title":"Towards Information Fusion in Pathway Evaluation: Encoding Relations in Biomedical Texts","authors":"E. Dura, B. Gawrońska, B. Olsson, Björn Erlendsson","doi":"10.1109/ICIF.2006.301666","DOIUrl":"https://doi.org/10.1109/ICIF.2006.301666","url":null,"abstract":"The long-term goal of the research presented in this paper is to incorporate linguistic text analysis into a system for evaluation of biological pathways. In this system, relations extracted from biomedical texts will be compared with pathways encoded in existing specialized databases. In this way, the biologist's conclusions regarding the plausibility and/or novelty of a certain relation between genes, proteins, etc., can be supported by fused information from biological databases and biological literature. We aim at overcoming the shortcomings of existing systems for information retrieval by proposing a method based on thorough linguistic analysis of a large text corpus. In this paper, we present a comparative analysis of two corpora: one consisting of biomedical texts from PubMed, the other one of general English prose. The results stress the importance of taking multiword entries into account when constructing a system for extracting biological relations from texts","PeriodicalId":248061,"journal":{"name":"2006 9th International Conference on Information Fusion","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122271611","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 : 2006-07-10DOI: 10.1109/ICIF.2006.301566
Arnaud Martin
We present in this article a new evaluation method for classification and segmentation of textured images in uncertain environments. In uncertain environments, real classes and boundaries are known with only a partial certainty given by the experts. Most of the time, in many presented papers, only classification or only segmentation are considered and evaluated. Here, we propose to take into account both the classification and segmentation results according to the certainty given by the experts. We present the results of this method on a fusion of classifiers of sonar images for a seabed characterization
{"title":"Fusion for Evaluation of Image Classication in Uncertain Environments","authors":"Arnaud Martin","doi":"10.1109/ICIF.2006.301566","DOIUrl":"https://doi.org/10.1109/ICIF.2006.301566","url":null,"abstract":"We present in this article a new evaluation method for classification and segmentation of textured images in uncertain environments. In uncertain environments, real classes and boundaries are known with only a partial certainty given by the experts. Most of the time, in many presented papers, only classification or only segmentation are considered and evaluated. Here, we propose to take into account both the classification and segmentation results according to the certainty given by the experts. We present the results of this method on a fusion of classifiers of sonar images for a seabed characterization","PeriodicalId":248061,"journal":{"name":"2006 9th International Conference on Information Fusion","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121805357","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 : 2006-07-10DOI: 10.1109/ICIF.2006.301661
N. Bomberger, B. Rhodes, M. Seibert, A. Waxman
Neurobiologically inspired algorithms have been developed to continuously learn behavioral patterns at a variety of conceptual, spatial, and temporal levels. In this paper, we outline our use of these algorithms for situation awareness in the maritime domain. Our algorithms take real-time tracking information and learn motion pattern models on-the-fly, enabling the models to adapt well to evolving situations while maintaining high levels of performance. The constantly refined models, resulting from concurrent incremental learning, are used to evaluate the behavior patterns of vessels based on their present motion states. At the event level, learning provides the capability to detect (and alert) upon anomalous behavior. At a higher (inter-event) level, learning enables predictions, over pre-defined time horizons, to be made about future vessel location. Predictions can also be used to alert on anomalous behavior. Learning is context-specific and occurs at multiple levels: for example, for individual vessels as well as classes of vessels. Features and performance of our learning system using recorded data are described
{"title":"Associative Learning of Vessel Motion Patterns for Maritime Situation Awareness","authors":"N. Bomberger, B. Rhodes, M. Seibert, A. Waxman","doi":"10.1109/ICIF.2006.301661","DOIUrl":"https://doi.org/10.1109/ICIF.2006.301661","url":null,"abstract":"Neurobiologically inspired algorithms have been developed to continuously learn behavioral patterns at a variety of conceptual, spatial, and temporal levels. In this paper, we outline our use of these algorithms for situation awareness in the maritime domain. Our algorithms take real-time tracking information and learn motion pattern models on-the-fly, enabling the models to adapt well to evolving situations while maintaining high levels of performance. The constantly refined models, resulting from concurrent incremental learning, are used to evaluate the behavior patterns of vessels based on their present motion states. At the event level, learning provides the capability to detect (and alert) upon anomalous behavior. At a higher (inter-event) level, learning enables predictions, over pre-defined time horizons, to be made about future vessel location. Predictions can also be used to alert on anomalous behavior. Learning is context-specific and occurs at multiple levels: for example, for individual vessels as well as classes of vessels. Features and performance of our learning system using recorded data are described","PeriodicalId":248061,"journal":{"name":"2006 9th International Conference on Information Fusion","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121515379","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 : 2006-07-10DOI: 10.1109/ICIF.2006.301803
P. Svensson
The paper summarizes the result of a literature study of robust uncertainty management methodologies, carried out to indicate options available in the design and construction of trustworthy decision support systems based on high-level information fusion methods. Among the candidate methodologies briefly discussed for creating trustworthy decision support are robust Bayesian statistics, imprecise probabilities and sensitivity analysis of simulation models. However, few reports of the application of such techniques in information fusion software systems were found
{"title":"On reliability and trustworthiness of high-level fusion-based decision support systems: basic concepts and possible formal methodologies","authors":"P. Svensson","doi":"10.1109/ICIF.2006.301803","DOIUrl":"https://doi.org/10.1109/ICIF.2006.301803","url":null,"abstract":"The paper summarizes the result of a literature study of robust uncertainty management methodologies, carried out to indicate options available in the design and construction of trustworthy decision support systems based on high-level information fusion methods. Among the candidate methodologies briefly discussed for creating trustworthy decision support are robust Bayesian statistics, imprecise probabilities and sensitivity analysis of simulation models. However, few reports of the application of such techniques in information fusion software systems were found","PeriodicalId":248061,"journal":{"name":"2006 9th International Conference on Information Fusion","volume":"90 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125134258","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：