dynamic Bayesian network

Many approaches to facial expression recognition focus on assessing the six basic emotions (anger, disgust, happiness, fear, sadness, and surprise). Real-life situations proved to produce many more subtle facial expressions. A reliable way of analyzing the facial behavior is the Facial Action Coding System (FACS) developed by Ekman and Friesen, which decomposes the face into 46 action units (AU) and is usually performed by a human observer. Each AU is related to the contraction of one or more specific facial muscles. In this study we present an approach towards automatic AU recognition enabling recognition of an extensive palette of facial expressions. As distinctive features we used motion flow estimators between every two consecutive frames, calculated in special regions of interest (ROI). Even though a lot has been published on the facial expression recognition theme, it is still difficult to draw a conclusion regarding the best methodology as there is no common basis for compari...

Abstract. We present a data mining approach to model the cooling infrastructure in data centers, particularly the chiller ensemble. These infrastructures are poorly understood due to the lack of “first principles ” models of chiller systems. At the same time, they abound in data due to instrumentation by modern sensor networks. We present a multi-level framework to transduce sensor streams into an actionable dynamic Bayesian network model of the system. This network is then used to explain observed system transitions and aid in diagnostics and prediction. We showcase experimental results using a HP data center in Bangalore, India. 1

This paper presents a system for inferring complex mental states from video of facial expressions and head gestures in real-time. The system is based on a multi-level dynamic Bayesian network classifier which models complex mental states as a number of interacting facial and head displays, identified from component-based facial features. Experimental results for 6 mental states groups- agreement, concentrating, disagreement, interested, thinking and unsure are reported. Real-time performance, unobtrusiveness and lack of preprocessing make our system particularly suitable for user-independent human computer interaction.

RÉSUMÉ. La modélisation des dynamiques des procédés de transformation dans l'industrie agro-alimentaire est un enjeu important pour mieux maîtriser la qualité des produits. L'utilisation de réseaux bayésiens dynamiques est alors une approche candidate pertinente. Malgré ...

Plan Recognition Using Multimodal Integration Olga Vybornova (vybornova@gmail.com) Kosta Gaitanis (gaitanis@tele.ucl.ac.be) Benoit Macq (Benoit.Macq@UCLouvain.be) UCL-TELE, Universite Catholique de Louvain, Batiment Stevin, Place du Levant, 2, B-1348, Louvain-la-Neuve, Belgium Keywords: multimodal interfaces; semantics; ontology; online probabilistic plan recognition; Dynamic Bayesian Networks. General Overview and Method We describe an ongoing research aimed at development of an anthropomorphic multimodal interface (meaning an interface for which the goal is not to precisely achieve a measurable task, like in instrumental interfaces, but more to provide a natural interaction) for recognition of a general intention, as well as of particular goals and plan fragments. To recognize the communicative and overall practical intentions and goals of a person we use information arriving from natural language and gestures (actions). The result of the multimodal integration is a joint semantic...

Mining temporal network models from discrete event streams is an important problem with applications in computational neuroscience, physical plant diagnostics, and human-computer interaction modeling. We focus in this paper on temporal models representable as excitatory networks where all connections are stimulative, rather than inhibitive. Through this emphasis on excitatory networks, we show how they can be learned by creating bridges to frequent episode mining. Specifically, we show that frequent episodes help identify nodes with high mutual information relationships and which can be summarized into a dynamic Bayesian network (DBN). To demonstrate the practical feasibility of our approach, we show how excitatory networks can be inferred from both mathematical models of spiking neurons as well as real neuroscience datasets.

Detection of individuals intentions and actions from a stream of human behaviour is an open problem. Yet for robotic agents to be truly perceived as human-friendly entities they need to respond naturally to the physical interactions with the surrounding environment, most notably with the user. This paper proposes a generative probabilistic approach in the form of Dynamic Bayesian Networks (DBN) to seamlessly account for users attitudes. A model is presented which can learn to recognize a subset of possible actions by the user of a gait stability support power rollator walker, such as standing up, sitting down or assistive strolling, and adapt the behaviour of the device accordingly. The communication between the user and the device is implicit, without any explicit intention such as a keypad or voice.The end result is a decision making mechanism that best matches the users cognitive attitude towards a set of assistive tasks, effectively incorporating the evolving activity model of the user in the process. The proposed framework is evaluated in real-life condition.

This paper presents a Dynamic Bayesian Network (DBN)-based distributed diagnosis scheme, where each distributed diagnoser generates globally correct diagnosis results without a centralized coordinator by communicating a minimal number of measurements so that each diagnoser satises local observability properties, and the overall diagnoser is globally observable. We present a procedure for designing the distributed diagnosers by factoring a system DBN

We introduce a novel approach for noise-robust feature extraction in speech recognition, based on non-negative matrix factorization (NMF). While NMF has previously been used for speech denoising and speaker separation, we directly extract time-varying features from the NMF output. To this end we extend basic unsupervised NMF to a hybrid supervised/unsupervised algorithm. We present a Dynamic Bayesian Network (DBN) architecture that can exploit these features in a Tandem manner together with the ...

The growing complexity of IP networks in terms of hardware components, operating system, communication and application software and the huge amount of dependencies among them have caused an increase in demand for network management systems, particularly in fault management An efficient fault detection system needs to work effectively even in face of incomplete management information, uncertain situations and dynamic changes. In this paper, dynamic Bayesian networks are proposed to model static and dynamic dependencies between managed objects in IP networks. Prediction strategies and a backward inference approach are provided for the proactive management in fault detection based on the dynamic changes of IP networks.