Pub Date : 2006-07-10DOI: 10.1109/ICIF.2006.301636
A. Lauberts, D. Lindgren
Audio recordings of vehicles passing a microphone network are studied with respect to the classification ability under different weather and local conditions. The audio data base includes recordings in different seasons, recordings at various sensor locations and also recordings using different microphones. A support vector machine (SVM) is used to classify vehicles from normalized, low-frequency spectral features of short time chunks of the audio signals. The classification performance using individual time chunks is estimated, as well as the accuracy of fusing data from the different microphones in the network. The study shows that, combining temporal and spatial data, a vehicle traversing a microphone network can be correctly classified in up to 90 percent of all runs. A more demanding test, classifying data from a totally independent measurement equipment, yields 70 percent correct classifications
{"title":"Generalization Ability of a Support Vector Classifier Applied to Vehicle Data in a Microphone Network","authors":"A. Lauberts, D. Lindgren","doi":"10.1109/ICIF.2006.301636","DOIUrl":"https://doi.org/10.1109/ICIF.2006.301636","url":null,"abstract":"Audio recordings of vehicles passing a microphone network are studied with respect to the classification ability under different weather and local conditions. The audio data base includes recordings in different seasons, recordings at various sensor locations and also recordings using different microphones. A support vector machine (SVM) is used to classify vehicles from normalized, low-frequency spectral features of short time chunks of the audio signals. The classification performance using individual time chunks is estimated, as well as the accuracy of fusing data from the different microphones in the network. The study shows that, combining temporal and spatial data, a vehicle traversing a microphone network can be correctly classified in up to 90 percent of all runs. A more demanding test, classifying data from a totally independent measurement equipment, yields 70 percent correct classifications","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":"131331565","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.2006.301816
G. Chemello, C. Sossai
Using suitable topoi of presheaves, a categorical definition of measure is given. When the general definition is specialized to particular categories made of sets of possibility, probability or imprecise probability measures, the internal language of the corresponding topos gives a valid and complete proof system for the corresponding semantics. An application of this method to data fusion in mobile robotics is presented
{"title":"A Categorical Approach to Data Fusion","authors":"G. Chemello, C. Sossai","doi":"10.1109/ICIF.2006.301816","DOIUrl":"https://doi.org/10.1109/ICIF.2006.301816","url":null,"abstract":"Using suitable topoi of presheaves, a categorical definition of measure is given. When the general definition is specialized to particular categories made of sets of possibility, probability or imprecise probability measures, the internal language of the corresponding topos gives a valid and complete proof system for the corresponding semantics. An application of this method to data fusion in mobile robotics is presented","PeriodicalId":248061,"journal":{"name":"2006 9th International Conference on Information Fusion","volume":"211 1-2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131829521","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.2006.301645
H. Blom, E. A. Bloem, D. Musicki
Joint PDA has proven to be effective in tracking multiple targets from measurements amidst clutter and missed detections. Joint IPDA has built upon this by including the probability of target existence as a track quality measure to enable automatic tracking and track maintenance. Both JPDA and JIPDA suffer from the problem of track coalescence of near target tracks. JPDA* is an extension of JPDA which avoids coalescence by pruning specific permutation hypotheses prior to hypothesis merging. Following JPDA*'s descriptor system derivation, this paper developes JIPDA*, an extension of JIPDA which avoids track coalescence. JIPDA* updates the probability of target existence as the track quality measure. An initial simulation study corroborates the effectiveness of this approach for tracking crossing targets in heavy clutter
{"title":"Joint Integrated PDA Avoiding Track Coalescence under Non-Homogeneous Clutter Density","authors":"H. Blom, E. A. Bloem, D. Musicki","doi":"10.1109/ICIF.2006.301645","DOIUrl":"https://doi.org/10.1109/ICIF.2006.301645","url":null,"abstract":"Joint PDA has proven to be effective in tracking multiple targets from measurements amidst clutter and missed detections. Joint IPDA has built upon this by including the probability of target existence as a track quality measure to enable automatic tracking and track maintenance. Both JPDA and JIPDA suffer from the problem of track coalescence of near target tracks. JPDA* is an extension of JPDA which avoids coalescence by pruning specific permutation hypotheses prior to hypothesis merging. Following JPDA*'s descriptor system derivation, this paper developes JIPDA*, an extension of JIPDA which avoids track coalescence. JIPDA* updates the probability of target existence as the track quality measure. An initial simulation study corroborates the effectiveness of this approach for tracking crossing targets in heavy clutter","PeriodicalId":248061,"journal":{"name":"2006 9th International Conference on Information Fusion","volume":"80 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":"131833607","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.2006.301611
A. Debiolles, L. Oukhellou, T. Denoeux, P. Aknin
This paper addresses the problem of fault detection in a complex system made up of several spatially dependent subsystems. The diagnosis method consists of both detecting and localizing a defect on the system by combining the outputs scores of subclassifiers within the framework of belief function theory. This paper is focused on the coding and the combination of classifier outputs that can reflect the spatial relationship between the subsystems. In the particular case of upstream/downstream dependency, two strategies of output coding are detailed. The proposed methodology is illustrated on a railway device diagnosis application. It will be shown that the choice of an appropriate coding scheme improves the classification results
{"title":"Output coding of spatially dependent subclassifiers in evidential framework. Application to the diagnosis of railway track/vehicle transmission system","authors":"A. Debiolles, L. Oukhellou, T. Denoeux, P. Aknin","doi":"10.1109/ICIF.2006.301611","DOIUrl":"https://doi.org/10.1109/ICIF.2006.301611","url":null,"abstract":"This paper addresses the problem of fault detection in a complex system made up of several spatially dependent subsystems. The diagnosis method consists of both detecting and localizing a defect on the system by combining the outputs scores of subclassifiers within the framework of belief function theory. This paper is focused on the coding and the combination of classifier outputs that can reflect the spatial relationship between the subsystems. In the particular case of upstream/downstream dependency, two strategies of output coding are detailed. The proposed methodology is illustrated on a railway device diagnosis application. It will be shown that the choice of an appropriate coding scheme improves the classification results","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":"128239974","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.2006.301593
S. A. Pasha, B. Vo, H. Tuan, Wing-Kin Ma
In recent years there has been much interest in the probability hypothesis density (PHD) filtering approach, an attractive alternative to tracking unknown numbers of targets and their states in the presence of data association uncertainty, clutter, noise, and miss-detection. In particular, it has been discovered that the PHD filter has a closed form solution under linear Gaussian assumptions on the target dynamics and birth. This finding opens up a new direction where the PHD filter can be practically implemented in an effective and reliable fashion. However, the previous work is not general enough to handle jump Markov systems (JMS), a popular approach to modeling maneuvering targets. In this paper, a closed form solution for the PHD filter with linear JMS is derived. Our simulations demonstrate that the proposed PHD filtering algorithm provides promising performance. In particular, the algorithm is capable of tracking multiple maneuvering targets that cross each other
{"title":"Closed Form PHD Filtering for Linear Jump Markov Models","authors":"S. A. Pasha, B. Vo, H. Tuan, Wing-Kin Ma","doi":"10.1109/ICIF.2006.301593","DOIUrl":"https://doi.org/10.1109/ICIF.2006.301593","url":null,"abstract":"In recent years there has been much interest in the probability hypothesis density (PHD) filtering approach, an attractive alternative to tracking unknown numbers of targets and their states in the presence of data association uncertainty, clutter, noise, and miss-detection. In particular, it has been discovered that the PHD filter has a closed form solution under linear Gaussian assumptions on the target dynamics and birth. This finding opens up a new direction where the PHD filter can be practically implemented in an effective and reliable fashion. However, the previous work is not general enough to handle jump Markov systems (JMS), a popular approach to modeling maneuvering targets. In this paper, a closed form solution for the PHD filter with linear JMS is derived. Our simulations demonstrate that the proposed PHD filtering algorithm provides promising performance. In particular, the algorithm is capable of tracking multiple maneuvering targets that cross each other","PeriodicalId":248061,"journal":{"name":"2006 9th International Conference on Information Fusion","volume":"39 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":"128332215","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.2006.301727
M. Xiao, Chongzhao Han, Xin Kang
Based on assumption that background would not be the parts which appear in the sequence for a short time, a background reconstruction algorithm based on online clustering was proposed in this paper. Firstly, pixels intensities are classified based on online clustering. Secondly, cluster centers and appearance probabilities of each cluster are calculated. Finally, a single or multi intensities clusters with the appearance probability greater than threshold are selected as the background pixel intensity value. Simulation results show that the algorithm can represent situation where the background contains bi-model or multi-model distribution, and motion segmentation can be performed correctly. The algorithm with inexpensive computation and low memory can accommodate the real-time need
{"title":"A Background Reconstruction for Dynamic Scenes","authors":"M. Xiao, Chongzhao Han, Xin Kang","doi":"10.1109/ICIF.2006.301727","DOIUrl":"https://doi.org/10.1109/ICIF.2006.301727","url":null,"abstract":"Based on assumption that background would not be the parts which appear in the sequence for a short time, a background reconstruction algorithm based on online clustering was proposed in this paper. Firstly, pixels intensities are classified based on online clustering. Secondly, cluster centers and appearance probabilities of each cluster are calculated. Finally, a single or multi intensities clusters with the appearance probability greater than threshold are selected as the background pixel intensity value. Simulation results show that the algorithm can represent situation where the background contains bi-model or multi-model distribution, and motion segmentation can be performed correctly. The algorithm with inexpensive computation and low memory can accommodate the real-time need","PeriodicalId":248061,"journal":{"name":"2006 9th International Conference on Information Fusion","volume":"12 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":"130377429","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.2006.301794
R. Streit
Probabilistic multi-hypothesis tracking (PMHT) is an algorithm for tracking multiple targets when measurement-to-target assignments are unknown and must be estimated jointly with the target tracks. PMHT is linear in the number of targets and the number of measurements; moreover, it is guaranteed to converge to locally optimal state estimates. However, it violates the rule that no target can be assigned more than one measurement. This hereby leads to a plethora of local maxima that cause performance problems. These problems are greatly reduced by applying the PMHT method to multi-frame data sequences, that is, to the set of all possible measurement sequences in the last L scans. The blend of PMHT and limited enumeration reduces the mismatch induced by violating the "at most one measurement per target" rule. Two new PMHT algorithms are presented. Both are linear in the number of targets and the number of enumerated sequences
{"title":"PMHT Algorithms for Multi-Frame Assignment","authors":"R. Streit","doi":"10.1109/ICIF.2006.301794","DOIUrl":"https://doi.org/10.1109/ICIF.2006.301794","url":null,"abstract":"Probabilistic multi-hypothesis tracking (PMHT) is an algorithm for tracking multiple targets when measurement-to-target assignments are unknown and must be estimated jointly with the target tracks. PMHT is linear in the number of targets and the number of measurements; moreover, it is guaranteed to converge to locally optimal state estimates. However, it violates the rule that no target can be assigned more than one measurement. This hereby leads to a plethora of local maxima that cause performance problems. These problems are greatly reduced by applying the PMHT method to multi-frame data sequences, that is, to the set of all possible measurement sequences in the last L scans. The blend of PMHT and limited enumeration reduces the mismatch induced by violating the \"at most one measurement per target\" rule. Two new PMHT algorithms are presented. Both are linear in the number of targets and the number of enumerated sequences","PeriodicalId":248061,"journal":{"name":"2006 9th International Conference on Information Fusion","volume":"45 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":"129673921","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.2006.301608
J. T. Rickard
This paper presents a novel approach to data fusion knowledge representation using conceptual spaces. Conceptual spaces represent knowledge geometrically in multiple domains, each domain consisting of multiple dimensions with an associated distance metric and corresponding similarity measure. Complex concepts such as those required for level 2/3 fusion are described by multiple property regions within these domains, along with the property correlations and salience weights. These concepts are mapped into points in the unit hypercube that capture all of their essential elements. Observations are also mapped into points in the same unit hypercube. The relative similarity of observations to concepts can then be calculated using the fuzzy subsethood measure
{"title":"Level 2/3 fusion in conceptual spaces","authors":"J. T. Rickard","doi":"10.1109/ICIF.2006.301608","DOIUrl":"https://doi.org/10.1109/ICIF.2006.301608","url":null,"abstract":"This paper presents a novel approach to data fusion knowledge representation using conceptual spaces. Conceptual spaces represent knowledge geometrically in multiple domains, each domain consisting of multiple dimensions with an associated distance metric and corresponding similarity measure. Complex concepts such as those required for level 2/3 fusion are described by multiple property regions within these domains, along with the property correlations and salience weights. These concepts are mapped into points in the unit hypercube that capture all of their essential elements. Observations are also mapped into points in the same unit hypercube. The relative similarity of observations to concepts can then be calculated using the fuzzy subsethood measure","PeriodicalId":248061,"journal":{"name":"2006 9th International Conference on Information Fusion","volume":"267 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":"134021374","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.2006.301600
N. Cvejic, J. Lewis, D. Bull, C. N. Canagarajah
In this paper, we present a novel multimodal image fusion algorithm in ICA domain. It uses segmentation to determine the most important regions in the input images and consequently fuses the ICA coefficients from given regions using the Piella fusion metric to maximise the quality of the fused image. The proposed method exhibits significantly higher performance than the basic ICA algorithm and improvement over other state-of-the-art algorithms
{"title":"Adaptive Region-Based Multimodal Image Fusion Using ICA Bases","authors":"N. Cvejic, J. Lewis, D. Bull, C. N. Canagarajah","doi":"10.1109/ICIF.2006.301600","DOIUrl":"https://doi.org/10.1109/ICIF.2006.301600","url":null,"abstract":"In this paper, we present a novel multimodal image fusion algorithm in ICA domain. It uses segmentation to determine the most important regions in the input images and consequently fuses the ICA coefficients from given regions using the Piella fusion metric to maximise the quality of the fused image. The proposed method exhibits significantly higher performance than the basic ICA algorithm and improvement over other state-of-the-art algorithms","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":"132998903","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.2006.301614
L. Kuncheva, S. Hadjitodorov, L. Todorova
Cluster ensembles are deemed to be a robust and accurate alternative to single clustering runs. 24 methods for designing cluster ensembles are compared here using 24 data sets, both artificial and real. Adjusted rand index and classification accuracy are used as accuracy criteria with respect to a known partition assumed to be the "true" one. The data sets are randomly chosen to represent medium-size problems arising within a variety of biomedical domains. Ensemble size of 10 was considered. It was found that there is a significant difference among the compared methods (Friedman's two way ANOVA). The best ensembles were based on k-means individual clusterers. Consensus functions interpreting the consensus matrix of the ensemble as data, rather than similarity, were found to be significantly better than the traditional alternatives, including CSPA and HGPA
集群集成被认为是单一集群运行的鲁棒性和准确性替代方案。本文使用24个人工和真实数据集，对24种设计聚类集成的方法进行了比较。对于假设为“真实”的已知分区，使用调整后的rand指数和分类精度作为精度标准。数据集是随机选择的，以表示在各种生物医学领域中出现的中等规模的问题。考虑整体规模为10。结果发现，比较方法之间存在显著差异(Friedman’s two way ANOVA)。最佳的集合是基于k-均值单个聚类的。共识函数将集合的共识矩阵解释为数据，而不是相似性，被发现明显优于传统的替代方案，包括CSPA和HGPA
{"title":"Experimental Comparison of Cluster Ensemble Methods","authors":"L. Kuncheva, S. Hadjitodorov, L. Todorova","doi":"10.1109/ICIF.2006.301614","DOIUrl":"https://doi.org/10.1109/ICIF.2006.301614","url":null,"abstract":"Cluster ensembles are deemed to be a robust and accurate alternative to single clustering runs. 24 methods for designing cluster ensembles are compared here using 24 data sets, both artificial and real. Adjusted rand index and classification accuracy are used as accuracy criteria with respect to a known partition assumed to be the \"true\" one. The data sets are randomly chosen to represent medium-size problems arising within a variety of biomedical domains. Ensemble size of 10 was considered. It was found that there is a significant difference among the compared methods (Friedman's two way ANOVA). The best ensembles were based on k-means individual clusterers. Consensus functions interpreting the consensus matrix of the ensemble as data, rather than similarity, were found to be significantly better than the traditional alternatives, including CSPA and HGPA","PeriodicalId":248061,"journal":{"name":"2006 9th International Conference on Information Fusion","volume":"87 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":"132161398","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：