The Experts below are selected from a list of 10776 Experts worldwide ranked by ideXlab platform
Wenyuan Wang - One of the best experts on this subject based on the ideXlab platform.
-
ICNC (1) - On-Line signature verification based on Dynamic Bayesian Network
Lecture Notes in Computer Science, 2006Co-Authors: Hairong Lv, Wenyuan WangAbstract:In this paper, we present a novel approach to automatic on-line signature verification using Dynamic Bayesian Network (DBN). On-line signatures can be viewed as time-series data. For modeling time-series data, it's natural to use directed graphical models, which can capture the fact that time flows forward. The model is called Dynamic Bayesian Network and it hasn't been used in online signature verification. Experimental evaluation on a database containing a total of 3500 signatures of 100 individuals shows promising results compared to other classical methods.
-
ICNC (1) - On-Line signature verification based on Dynamic Bayesian Network
Lecture Notes in Computer Science, 2006Co-Authors: Wenyuan WangAbstract:In this paper, we present a novel approach to automatic on-line signature verification using Dynamic Bayesian Network (DBN). On-line signatures can be viewed as time-series data. For modeling time-series data, it's natural to use directed graphical models, which can capture the fact that time flows forward. The model is called Dynamic Bayesian Network and it hasn't been used in online signature verification. Experimental evaluation on a database containing a total of 3500 signatures of 100 individuals shows promising results compared to other classical methods.
Junji Yamato - One of the best experts on this subject based on the ideXlab platform.
-
real time estimation of human visual attention with Dynamic Bayesian Network and mcmc based particle filter
International Conference on Multimedia and Expo, 2009Co-Authors: Kouji Miyazato, Akisato Kimura, Shigeru Takagi, Junji YamatoAbstract:Recent studies in signal detection theory suggest that the human responses to the stimuli on a visual display are nondeterministic. People may attend to different locations on the same visual input at the same time. Constructing a stochastic model of human visual attention would be promising to tackle the above problem. This paper proposes a new method to achieve a quick and precise estimation of human visual attention based on our previous stochastic model with a Dynamic Bayesian Network. A particle filter with Markov chain Monte-Carlo (MCMC) sampling make it possible to achieve a quick and precise estimation through stream processing. Experimental results indicate that the proposed method can estimate human visual attention in real time and more precisely than previous methods.
-
a stochastic model of selective visual attention with a Dynamic Bayesian Network
International Conference on Multimedia and Expo, 2008Co-Authors: Derek Pang, Akisato Kimura, Tatsuto Takeuchi, Junji Yamato, Kunio KashinoAbstract:Recent studies in signal detection theory suggest that the human responses to the stimuli on a visual display are nondeterministic. People may attend to different locations on the same visual input at the same time. To predict the likelihood of where humans typically focus on a video scene, we propose a new stochastic model of visual attention by introducing a Dynamic Bayesian Network. Our model simulates and combines the visual saliency response and the cognitive state of a person to estimate the most probable attended regions. Experimental results have demonstrated that our model performs significantly better in predicting human visual attention compared to the previous deterministic model.
-
conversation scene analysis with Dynamic Bayesian Network basedon visual head tracking
International Conference on Multimedia and Expo, 2006Co-Authors: Kazuhiro Otsuka, Junji Yamato, Yoshinao Takemae, Hiroshi MuraseAbstract:A novel method based on a probabilistic model for conversation scene analysis is proposed that can infer conversation structure from video sequences of face-to-face communication. Conversation structure represents the type of conversation such as monologue or dialogue, and can indicate who is talking / listening to whom. This study assumes that the gaze directions of participants provide cues for discerning the conversation structure, and can be identified from head directions. For measuring head directions, the proposed method newly employs a visual head tracker based on Sparse-Template Condensation. The conversation model is built on a Dynamic Bayesian Network and is used to estimate the conversation structure and gaze directions from observed head directions and utterances. Visual tracking is conventionally thought to be less reliable than contact sensors, but experiments confirm that the proposed method achieves almost comparable performance in estimating gaze directions and conversation structure to a conventional sensor-based method.
Baoping Cai - One of the best experts on this subject based on the ideXlab platform.
-
Operation-Oriented Reliability and Availability Evaluation for Onboard High-Speed Train Control System with Dynamic Bayesian Network
Bayesian Networks for Reliability Engineering, 2020Co-Authors: Baoping Cai, Yuanjiang Chang, Zengkai Liu, Yonghong Liu, Lei JiangAbstract:The reliability and availability of the onboard high-speed train control system are important to guarantee operational efficiency and railway safety. Failures occurring in the onboard system may result in serious accidents. In the analysis of the effects of failure, it is significant to consider the operation of an onboard system. This paper presents a systemic approach to evaluate the reliability and availability for the onboard system based on Dynamic Bayesian Network, with taking into account Dynamic failure behaviors, imperfect coverage factors, and temporal effects in operational phase. The case studies are presented and compared for onboard systems with different redundant strategies, i.e., the triple modular redundancy, hot spare double dual, and cold spare double dual. Dynamic fault trees of the three kinds of onboard system are constructed and mapped into Dynamic Bayesian Network. The forward and backward inferences are conducted not only to evaluate the reliability and availability, but also recognize the vulnerabilities of the onboard systems. A sensitivity analysis is carried out for evaluating the effects of failure rates subject to uncertainties. To improve the reliability and availability, the recovery mechanism should be paid more attention. Finally, the proposed approach is validated with the field data from one railway bureau in China and some industrial impacts are provided.
-
Dynamic Bayesian Network Modeling of Reliability of Subsea Blowout Preventer Stack in the Presence of Common Cause Failures
Bayesian Networks for Reliability Engineering, 2020Co-Authors: Baoping Cai, Yuanjiang Chang, Zengkai Liu, Yonghong Liu, Lei JiangAbstract:A subsea blowout preventer (BOP) stack is used to seal, control, and monitor oil and gas wells. It can be regarded as a series–parallel system consisting of several subsystems. This paper develops the Dynamic Bayesian Network (DBN) of a parallel system with n components, taking account of common cause failures and imperfect coverage. Multiple-error shock model is used to model common cause failures. Based on the proposed generic model, DBNs of the two commonly used stack types, namely the conventional BOP and modern BOP, are developed. In order to evaluate the effects of the failure rates and coverage factor on the reliability and availability of the stacks, sensitivity analysis is performed.
-
a Dynamic Bayesian Network based fault diagnosis methodology considering transient and intermittent faults
IEEE Transactions on Automation Science and Engineering, 2017Co-Authors: Baoping Cai, Yu Liu, Min XieAbstract:Transient fault (TF) and intermittent fault (IF) of complex electronic systems are difficult to diagnose. As the performance of electronic products degrades over time, the results of fault diagnosis could be different at different times for the given identical fault symptoms. A Dynamic Bayesian Network (DBN)-based fault diagnosis methodology in the presence of TF and IF for electronic systems is proposed. DBNs are used to model the Dynamic degradation process of electronic products, and Markov chains are used to model the transition relationships of four states, i.e., no fault, TF, IF, and permanent fault. Our fault diagnosis methodology can identify the faulty components and distinguish the fault types. Four fault diagnosis cases of the Genius modular redundancy control system are investigated to demonstrate the application of this methodology.
-
IEEM - A reliability analysis framework based on time-varying Dynamic Bayesian Network
2015 IEEE International Conference on Industrial Engineering and Engineering Management (IEEM), 2015Co-Authors: Y. Liu, Baoping CaiAbstract:In the last decade, Bayesian Networks have become more and more popular in solving statistical problems. This method also attracts a lot of attention in reliability analysis community. In this paper, a time-varying Dynamic Bayesian Network modeling framework which is extended from basic Dynamic Bayesian Network model is proposed to analyze the non-stationary failure process. And the model is illustrated with the availability analysis of PV power system.
Qiang Yang - One of the best experts on this subject based on the ideXlab platform.
-
deriving a stationary Dynamic Bayesian Network from a logic program with recursive loops
Inductive Logic Programming, 2005Co-Authors: Yidong Shen, Qiang YangAbstract:Recursive loops in a logic program present a challenging problem to the PLP framework. On the one hand, they loop forever so that the PLP backward-chaining inferences would never stop. On the other hand, they generate cyclic influences, which are disallowed in Bayesian Networks. Therefore, in existing PLP approaches logic programs with recursive loops are considered to be problematic and thus are excluded. In this paper, we propose an approach that makes use of recursive loops to build a stationary Dynamic Bayesian Network. Our work stems from an observation that recursive loops in a logic program imply a time sequence and thus can be used to model a stationary Dynamic Bayesian Network without using explicit time parameters. We introduce a Bayesian knowledge base with logic clauses of the form A ← A1,...,Al, true, Context, Types, which naturally represents the knowledge that the Ais have direct influences on A in the context Context under the type constraints Types. We then use the well-founded model of a logic program to define the direct influence relation and apply SLG-resolution to compute the space of random variables together with their parental connections. We introduce a novel notion of influence clauses, based on which a declarative semantics for a Bayesian knowledge base is established and algorithms for building a two-slice Dynamic Bayesian Network from a logic program are developed.
-
deriving a stationary Dynamic Bayesian Network from a logic program with recursive loops
arXiv: Artificial Intelligence, 2005Co-Authors: Yidong Shen, Qiang Yang, Liyan YuanAbstract:Recursive loops in a logic program present a challenging problem to the PLP framework. On the one hand, they loop forever so that the PLP backward-chaining inferences would never stop. On the other hand, they generate cyclic influences, which are disallowed in Bayesian Networks. Therefore, in existing PLP approaches logic programs with recursive loops are considered to be problematic and thus are excluded. In this paper, we propose an approach that makes use of recursive loops to build a stationary Dynamic Bayesian Network. Our work stems from an observation that recursive loops in a logic program imply a time sequence and thus can be used to model a stationary Dynamic Bayesian Network without using explicit time parameters. We introduce a Bayesian knowledge base with logic clauses of the form $A \leftarrow A_1,...,A_l, true, Context, Types$, which naturally represents the knowledge that the $A_i$s have direct influences on $A$ in the context $Context$ under the type constraints $Types$. We then use the well-founded model of a logic program to define the direct influence relation and apply SLG-resolution to compute the space of random variables together with their parental connections. We introduce a novel notion of influence clauses, based on which a declarative semantics for a Bayesian knowledge base is established and algorithms for building a two-slice Dynamic Bayesian Network from a logic program are developed.
Hairong Lv - One of the best experts on this subject based on the ideXlab platform.
-
ICNC (1) - On-Line signature verification based on Dynamic Bayesian Network
Lecture Notes in Computer Science, 2006Co-Authors: Hairong Lv, Wenyuan WangAbstract:In this paper, we present a novel approach to automatic on-line signature verification using Dynamic Bayesian Network (DBN). On-line signatures can be viewed as time-series data. For modeling time-series data, it's natural to use directed graphical models, which can capture the fact that time flows forward. The model is called Dynamic Bayesian Network and it hasn't been used in online signature verification. Experimental evaluation on a database containing a total of 3500 signatures of 100 individuals shows promising results compared to other classical methods.
