2019 22th International Conference on Information Fusion (FUSION)最新文献_第10页

Radio Source Localization Using Received Signal Strength in a Multipath Environment 在多径环境中使用接收信号强度进行无线电源定位

2019 22th International Conference on Information Fusion (FUSION) Pub Date : 2019-07-01 DOI: 10.23919/fusion43075.2019.9011233

Shuai Sun, Xuezhi Wang, B. Moran, A. Al-Hourani, Wayne S. T. Rowe

引用次数: 5

Entropy-Based Metrics for URREF Criteria to Assess Uncertainty in Bayesian Networks for Cyber Threat Detection 基于熵的URREF准则在贝叶斯网络不确定性评估中的应用

2019 22th International Conference on Information Fusion (FUSION) Pub Date : 2019-07-01 DOI: 10.23919/fusion43075.2019.9011276

V. Dragos, Jürgen Ziegler, J. D. Villiers, A. D. Waal, A. Jousselme, E. Blasch

{"title":"Entropy-Based Metrics for URREF Criteria to Assess Uncertainty in Bayesian Networks for Cyber Threat Detection","authors":"V. Dragos, Jürgen Ziegler, J. D. Villiers, A. D. Waal, A. Jousselme, E. Blasch","doi":"10.23919/fusion43075.2019.9011276","DOIUrl":"https://doi.org/10.23919/fusion43075.2019.9011276","url":null,"abstract":"Bayesian Networks are widely accepted as efficient tools to represent causal models for decision making under uncertainty. In some applications, networks are built where the conditional probability tables are not derived from scientific laws but rely on expert knowledge. Such applications require assessment as to whether the knowledge representation is precise enough to infer reliable results. The uncertainty representation and reasoning evaluation framework (URREF) ontology offers a unified framework for the objective assessment of uncertainty representation and reasoning. This paper addresses the analysis of uncertainty in Bayesian networks (BNs) and develops metrics for URREF criteria based on the principle of entropy. BNs uncertainty includes variable transformation (accuracy), model structure (precision), and reasoning (probability distribution interpretations). The set of metrics are used to investigate a practical use case for probabilistic modeling of cyber threat analysis, and are correlated to a set of complementary metrics already described in a former contribution. The goal of the paper is to provide a new set of metrics able to assess, for a specific model and given input sources, the quality of results of BN-based inferences, in terms of accuracy, precision and end-user interpretation.","PeriodicalId":348881,"journal":{"name":"2019 22th International Conference on Information Fusion (FUSION)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130557116","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}

引用次数: 7

End-to-End Multi-Modal Behavioral Context Recognition in a Real-Life Setting 端到端多模态行为上下文识别在现实生活中的应用

2019 22th International Conference on Information Fusion (FUSION) Pub Date : 2019-07-01 DOI: 10.23919/fusion43075.2019.9011194

Aaqib Saeed, T. Ozcelebi, S. Trajanovski, J. Lukkien

{"title":"End-to-End Multi-Modal Behavioral Context Recognition in a Real-Life Setting","authors":"Aaqib Saeed, T. Ozcelebi, S. Trajanovski, J. Lukkien","doi":"10.23919/fusion43075.2019.9011194","DOIUrl":"https://doi.org/10.23919/fusion43075.2019.9011194","url":null,"abstract":"Smart devices of everyday use (such as smartphones and wearables) are increasingly integrated with sensors that provide immense amounts of information about a person's daily life. The automatic and unobtrusive sensing of human behavioral context can help develop solutions for assisted living, fitness tracking, sleep monitoring, and several other fields. Towards addressing this issue, we raise the question: can a machine learn to recognize a diverse set of contexts and activities in a real-life through jointly learning from raw multi-modal signals (e.g., accelerometer, gyroscope and audio)? In this paper, we propose a multi-stream network comprising of temporal convolution and fully-connected layers to address the problem of multi-label behavioral context recognition. A four-stream network architecture handles learning from each modality with a contextualization module which incorporates extracted representations to infer a user's context. Our empirical evaluation suggests that a deep convolutional network trained end-to-end achieves comparable performance to manual feature engineering with minimal effort. Furthermore, the presented architecture can be extended to include similar sensors for performance improvements and handles missing modalities through multi-task learning on a highly imbalanced and sparsely labeled dataset.","PeriodicalId":348881,"journal":{"name":"2019 22th International Conference on Information Fusion (FUSION)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124648571","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}

引用次数: 1

Pedestrian Tracking by Probabilistic Data Association and Correspondence Embeddings 基于概率数据关联和对应嵌入的行人跟踪

2019 22th International Conference on Information Fusion (FUSION) Pub Date : 2019-07-01 DOI: 10.23919/fusion43075.2019.9011317

Borna Bićanić, Marin Orsic, Ivan Marković, Sinisa Segvic, I. Petrović

{"title":"Pedestrian Tracking by Probabilistic Data Association and Correspondence Embeddings","authors":"Borna Bićanić, Marin Orsic, Ivan Marković, Sinisa Segvic, I. Petrović","doi":"10.23919/fusion43075.2019.9011317","DOIUrl":"https://doi.org/10.23919/fusion43075.2019.9011317","url":null,"abstract":"This paper studies the interplay between kinematics (position and velocity) and appearance cues for establishing correspondences in multi-target pedestrian tracking. We investigate tracking-by-detection approaches based on a deep learning detector, joint integrated probabilistic data association (JIPDA), and appearance-based tracking of deep correspondence embeddings. We first addressed the fixed-camera setup by fine-tuning a convolutional detector for accurate pedestrian detection and combining it with kinematic-only JIPDA. The resulting submission ranked first on the 3DMOT2015 benchmark. However, in sequences with a moving camera and unknown ego-motion, we achieved the best results by replacing kinematic cues with global nearest neighbor tracking of deep correspondence embeddings. We trained the embeddings by fine-tuning features from the second block of ResNet-18 using angular loss extended by a margin term. We note that integrating deep correspondence embeddings directly in JIPDA did not bring significant improvement. It appears that geometry of deep correspondence embeddings for soft data association needs further investigation in order to obtain the best from both worlds.","PeriodicalId":348881,"journal":{"name":"2019 22th International Conference on Information Fusion (FUSION)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124725439","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}

引用次数: 4

Schmidt-Kalman Filter with Polynomial Chaos Expansion for State Estimation 基于多项式混沌展开的状态估计Schmidt-Kalman滤波器

2019 22th International Conference on Information Fusion (FUSION) Pub Date : 2019-07-01 DOI: 10.23919/fusion43075.2019.9011327

Yang Yang, Han Cai, Baichun Gong, R. Norman

{"title":"Schmidt-Kalman Filter with Polynomial Chaos Expansion for State Estimation","authors":"Yang Yang, Han Cai, Baichun Gong, R. Norman","doi":"10.23919/fusion43075.2019.9011327","DOIUrl":"https://doi.org/10.23919/fusion43075.2019.9011327","url":null,"abstract":"Errors due to uncertain parameters of dynamical systems can result in deterioration of state estimation performance or even filter divergence sometimes using a conventional Kalman filter algorithm. Even worse, these parameters cannot be measured accurately or are unobservable for many applications. Hence, estimating parameters along with state variables would not achieve satisfactory performance. To handle this problem, the Schmidt-Kalman filter (SKF) was introduced to compensate for these errors by considering parameters' covariance, with an assumption of only Gaussian distributions. This paper introduces a new SKF algorithm with polynomial chaos expansion (PCE-SKF). Within the framework of PCE, the dynamical system is predicted forward with an ability to quantify non-Gaussian parametric uncertainties as well. More specifically, the a priori covariance of both the state and parameters can be propagated using PCE, followed by the update step of SKF formulation. Two examples are given to validate the efficacy of the PCE-SKF. The state estimation performance by PCE-SKF is compared with the extended Kalman filter, SKF, unscented Kalman filter and unscented Schmidt-Kalman filter. It is implied that the covariance propagation using PCE leads to more accurate state estimation solutions in comparison with those based on linear propagation or unscented transformation.","PeriodicalId":348881,"journal":{"name":"2019 22th International Conference on Information Fusion (FUSION)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122206385","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}

引用次数: 3

Time-Offset Estimation in Multisensor Tracking Systems 多传感器跟踪系统中的时间偏移估计

2019 22th International Conference on Information Fusion (FUSION) Pub Date : 2019-07-01 DOI: 10.23919/fusion43075.2019.9011300

Song Li, Yong-mei Cheng, Daly Brown, R. Tharmarasa, Gongjian Zhou, T. Kirubarajan

引用次数: 1

Track-to-Track fusion with cross-covariances from radar and IR/EO sensor 基于雷达和红外/光电传感器交叉协方差的航迹融合

2019 22th International Conference on Information Fusion (FUSION) Pub Date : 2019-07-01 DOI: 10.23919/fusion43075.2019.9011439

Kaipei Yang, Y. Bar-Shalom, P. Willett

{"title":"Track-to-Track fusion with cross-covariances from radar and IR/EO sensor","authors":"Kaipei Yang, Y. Bar-Shalom, P. Willett","doi":"10.23919/fusion43075.2019.9011439","DOIUrl":"https://doi.org/10.23919/fusion43075.2019.9011439","url":null,"abstract":"The Track-to-track fusion (T2TF) problem for estimates from radar and infrared/electro-optical (IR/EO) sensor is studied in this work. For such a problem, the heterogeneous estimates from local trackers (LT) are in different state spaces with various dimensions and are related by a nonlinear relationship with no inverse transformation. For the homogeneous T2TF problem, where the common state model is shared by both LTs in the same state space, the cross-covariance between the local estimation errors, which has been known for some time, needs to be considered in the T2TF. However, such a cross-covariance for heterogeneous T2TF was not available in previous works. In the present work, the derivation of the cross-covariance for heterogeneous LTs of different dimension states is provided, yielding a recursion, by taking into account the relationship between the local state model process noises. A linear minimum mean square (LMMSE) estimator is used for the T2TF. With the cross-covariance involved, the fusion will generate the covariance of the fused estimation error which makes the system consistent as shown in the simulation through Monte-Carlo runs.","PeriodicalId":348881,"journal":{"name":"2019 22th International Conference on Information Fusion (FUSION)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123324220","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}

引用次数: 3

Graph-Based Tracking with Uncertain ID Measurement Associations 不确定ID测量关联的基于图的跟踪

2019 22th International Conference on Information Fusion (FUSION) Pub Date : 2019-07-01 DOI: 10.23919/fusion43075.2019.9011377

S. Coraluppi, C. Carthel, A. Willsky

引用次数: 0

A Framework for Using Radar Measurements of Unknown Targets in Hierarchical Classification 一种基于雷达测量的未知目标分层分类框架

2019 22th International Conference on Information Fusion (FUSION) Pub Date : 2019-07-01 DOI: 10.23919/fusion43075.2019.9011387

M. Ruotsalainen, Henna Perälä, Minna Väilä, Juha Jylhä, Mikko Kauhanen

{"title":"A Framework for Using Radar Measurements of Unknown Targets in Hierarchical Classification","authors":"M. Ruotsalainen, Henna Perälä, Minna Väilä, Juha Jylhä, Mikko Kauhanen","doi":"10.23919/fusion43075.2019.9011387","DOIUrl":"https://doi.org/10.23919/fusion43075.2019.9011387","url":null,"abstract":"Real-life target recognition often requires appropriate processing of unknown targets. Such targets are the ones that the automatic target recognition system has not been trained to identify. These targets may, however, be interesting whereupon they should be further analyzed. In this paper, we propose a novel framework for analyzing radar measurements of unknown targets in order to incorporate them into a hierarchical target class taxonomy for the target recognition. Besides the preliminary information, a vital part in the analysis of the radar measurement is the comparison between the measured signature and the signatures of the known target types and categories. We use the results of such analysis to indicate potential spots in the class taxonomy where to add the unknown target. The framework allows identification of unknown target types that have been previously observed, when they are encountered again. We demonstrate the proposed framework through an experiment using the real data of a multi-radar system. In the experiments, we show the feasibility of our approach by examining target recognition in two cases: using our framework and without it. We find that the proposed framework enables enhanced processing of unknown targets in radar target recognition.","PeriodicalId":348881,"journal":{"name":"2019 22th International Conference on Information Fusion (FUSION)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130786484","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}

引用次数: 0

Houses Bombing in Ravixe: a Bench for High Level Fusion Evaluation 拉维克斯房屋爆炸:高水平融合评估的基础

2019 22th International Conference on Information Fusion (FUSION) Pub Date : 2019-07-01 DOI: 10.23919/fusion43075.2019.9011250

N. Museux, C. Laudy, M. Florea

{"title":"Houses Bombing in Ravixe: a Bench for High Level Fusion Evaluation","authors":"N. Museux, C. Laudy, M. Florea","doi":"10.23919/fusion43075.2019.9011250","DOIUrl":"https://doi.org/10.23919/fusion43075.2019.9011250","url":null,"abstract":"Many benchmarks exist for the evaluation of algorithms in fields such as numerical optimization, automatic planning, SAT solving, Natural Language Processing, automatic code parallelization, signal processing, machine learning and low level fusion. To the best of our knowledge, however, there is no such bench existing for the evaluation of high level information fusion. In this paper, we describe a benchmark that we developed with the aim of evaluating high level fusion algorithms. The bench is related to a house bombing scenario in a fictive world. The scenario is fictional and takes place in a city, within a context of instability in the population between the members of two different communities. We describe the scenario itself, as well as the different sources of information and the kind of information they provide. The whole set of information available in the bench is described. Starting from a complete version of the bench that contains all the information items exchanged during the scenario, we derived several other benches that contain less or altered information items. This will enable evaluating the robustness of the high level information fusion systems, according to the quality of the information they are provided with and without the imperfection of information extractors exhibiting pieces of information from raw data.","PeriodicalId":348881,"journal":{"name":"2019 22th International Conference on Information Fusion (FUSION)","volume":"141 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130819425","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}

引用次数: 2