Boosted learning in dynamic bayesian networks for multimodal speaker detection

A New Approach to Learning in Dynamic Bayesian Networks (DBNs)

We propose a dynamic differential Bayesian networks (DDBNs) and nonparametric regression model. This model is an extended model of traditional dynamic Bayesian networks (DBNs), which can incorporate temporal information in a natural way and directly handle real-valued data obtained from microarrays without any transformation. In addition, it can cope with differential information between gene expression levels, without any loss to the traditional advantage, i.e., the capability of estimating non-linear relationships between genes. We apply DDBNs to analyze simulated data and real data, i.e., Saccharomyces cerevisiae cell cycle gene expression data. We have confirmed the effectiveness of our approach in the sense that some edges have been successfully detected only by DDBNs, not by DBNs.

In order to find out the problems of students' learning in the online learning process in time and ensure that students can successfully complete the online learning course, the dynamic Bayesian network is used to predict students' online learning scores. First, the online course Bayesian network is established, and then the dynamic Bayesian network is established by combining the Bayesian network and hidden Markov according to the time slice. The maximum expectation algorithm is used for Bayesian parameter learning, and the scores are predicted according to video learning, chapter test and other influencing factors. The results show that the dynamic Bayesian network can effectively predict the online learning results, the prediction results provide teachers with decision-making, and students can carry out targeted reinforcement learning according to the prediction results in the learning process.

Bayesian networks are a concise graphical formalism for describing probabilistic models. We have provided a brief tutorial of methods for learning and inference in dynamic Bayesian networks. In many of the interesting models, beyond the simple linear dynamical system or hidden Markov model, the calculations required for inference are intractable. Two different approaches for handling this intractability are Monte Carlo methods such as Gibbs sampling, and variational methods. An especially promising variational approach is based on exploiting tractable substructures in the Bayesian network.

To take full advantage of the historical information, we adopt dynamic Bayesian networks and discrete-time Bayesian networks to describe the event trees or dynamic fault trees. On this basis of the regulation, corresponding dynamic Bayesian networks and discrete-time Bayesian networks models are established for safety assessment in timing system. When the discrete-time time Bayesian network of dynamic fault trees is acquired, the Bayesian network is used to study the consequences probability, key degree and computation method. A simulated banking transaction system is analyzed and assessed by above models. The results show that the safety assessment scheme can provide model without subjectivity, which raises the credibility of model. In addition, it can obtain general assessment results and acquire more extensive diagnostics and information.

Nowadays, several components and systems are designed and produced based on reliability. Since the reliability criterion has an important role in purchasing and implementation of these systems. In the design of a reliable system, fault and failure analysis must be carried out in order to reduce fault probability of the system. When dependency and the relation between components of a complex system are important and should be mentioned, determination of system reliability is very difficult. In this paper, dynamic fault tree is used to evaluate the systems reliability that their behavior is varied with time. Dynamic fault tree is constructed and then it converted to dynamic bayesian network. In this paper, the principle of dynamic fault tree gates and their mapping into dynamic bayesian are explained and some new relations between events and gates for this mapping are proposed. GeNIe package is used to determine dynamic bayesian network based on stochastic sampling algorithms. Four systems (cardiac assist system, hypothetical cascaded priority-and system, inertial navigation system/ global positioning system integrated, and emergency detection system) are investigated; reliability and fault probability of these systems are calculated. Comparison of the results with those obtained by other researches shows the proposed method effectiveness for systems reliability modeling and assessment via dynamic bayesian network.

Bayesian network based dynamic operational risk assessment

Bayesian Network is a stochastic model, which shows the qualitative dependence between two or more random variables by the graph structure, and indicates the quantitative relations between individual variables by the conditional probability. This paper deals with the production and inventory control using the dynamic Bayesian network. The probabilistic values of the amount of delivered goods and the production quantities are changed in the real environment, and then the total stock is also changed randomly. The probabilistic distribution of the total stock is calculated through the propagation of the probability on the Bayesian network. Moreover, an adjusting rule of the production quantities to maintain the probability of the lower bound and the upper bound of the total stock to certain values is shown.

Telemedicine is a mean of facilitating the distribution of human resources and professional competences. It can speed up diagnosis and therapeutic care delivery and allow peripheral healthcare providers to receive continuous assistance from specialized centers. The need of specialized human resources becomes critical with the aging of the population. The treatment of renal failure is an example where telemedicine can help to increase care quality. Over the last decades Bayesian networks has become a popular representation for encoding uncertain expert knowledge. Dynamic Bayesian networks are an extension of Bayesian networks for modeling dynamic processes. We developed a dynamic Bayesian network adapted to the monitoring of the dry weight of patients suffering from chronic renal failure treated by hemodialysis. An experimentation conducted at dialysis units indicated that the system is reliable and gets the approbation of its users

A multisensor fusion system that is used for estimating the location of a robot and the state of the objects around it is presented. The whole fusion system has been implemented as a dynamic Bayesian network (DBN) with the purpose of having a homogenous and formalized way of capturing the dependencies that exist between robot location, the state of the environment, and all sensorial data. At this stage of research it consists of two independent DBNs, one for estimating robot location and another for building an occupancy probabilistic map of the environment, which are the basis of a unified fusion system. The dependencies of the variables and information in the two DBNs are captured by a unique DBN constructed by adding arcs (and nodes if necessary) between the two DBNs. The DBN implemented so far can be used in robots with different sets of sensors.

A new method based on Dynamic Bayesian Network (DBN) is proposed to assess the car engine reliability because of the limitation that the existing reliability analysis methods can only be used in static system reliability assessment. Firstly, define the failure mode and effect analysis table (FMEA) and the failure rates of the main components of the car engine and construct Bayesian network (BN) model. Secondly, combine the original BN model with time information and assess the reliability of the systems by using the advantages of BN in terms of the multi-state variables and uncertainly relations. The method is able not only to compute the reliability indices of car engine but also to carry out the fault detection easily to recognize the weakness of the system. This research is meaningful for reliability design and prediction of car engine.

Coordinately embedding machine learning and optimization in the Monte Carlo simulation is proposed as a new framework for reliability evaluation, which is becoming more challenging due to the joining of variability and intermittency of the renewable generation and components’ ageing. As a machine learning method, the dynamic Bayesian belief network predicts the renewable outputs by generating their probability distributions through historical data to overcome the defect of rarely grasping the low-probability events in the traditional methods, which either predict a single-point value or presume a parametric probability distribution. As the internal operation module of the framework, the rolling-horizon unit commitment maintains the complexity of the operation model and meantime punctually updates the predicted renewable generation and the components’ ageing. The dynamic Bayesian belief network and the rolling-horizon unit commitment traverse time step after time step throughout the horizon, and thus form one bid of the Monte Carlo simulation. In each time step, the dynamic Bayesian belief network extracts the probability distributions of the renewable generation, from which the boundary of the commitment is sampled, and the impact of scheduling the generators on their ageing is then accumulated from the commitment. The proposed framework has its effectiveness proved on a microgrid.

Police patrols are used ubiquitously to deter crimes in urban areas. A distinctive feature of urban crimes is that criminals react opportunistically to patrol officers assignments. Compared to strategic attackers (such as terrorists) with a well-laid out plan, opportunistic criminals are less strategic in planning attacks and more flexible in executing them. In this paper, our goal is to recommend optimal police patrolling strategy against such opportunistic criminals. We first build a game-theoretic model that captures the interaction between officers and opportunistic criminals. However, while different models of adversary behavior have been proposed, their exact form remains uncertain. Rather than simply hypothesizing a model as done in previous work, one key contribution of this paper is to learn the model from real-world criminal activity data. To that end, we represent the criminal behavior and the interaction with the patrol officers as parameters of a Dynamic Bayesian Network (DBN), enabling application of standard algorithms such as EM to learn the parameters. Our second contribution is a sequence of modifications to the DBN representation, that allows for a compact representation of the model resulting in better learning accuracy and increased speed of learning of the EM algorithm when used for the modified DBN. These modifications use marginalization approaches and exploit the structure of this problem. Finally, our third contribution is an iterative learning and planning mechanism that keeps updating the adversary model periodically. We demonstrate the efficiency of our learning algorithm by applying it to a real data set of criminal activity obtained from the police department of University of Southern California (USC) situated in Los Angeles, USA. We project a significant reduction in crime rate using our planning strategy as opposed to the actual strategy deployed by the police department. We also demonstrate the improvement in crime prevention in simulations when we use our iterative planning and learning mechanism compared to just learning once and planing. This work was done in collaboration with the police department of USC.

Unmanned Combat Aerial Vehicle (UCAV) is an inevitable trend of the future intelligent and unmanned flight platform. Situation assessment is an effective method to solve the battlefield autonomous decision-making problem. The process of situation assessment and the concept and inference of static Bayesian networks are introduced. Then a Bayesian blackboard method with knowledge sources modify Bayesian networks is analyzed. Structure-variable dynamic Bayesian networks is put forward to deal with situation changes. Finally, the hybrid Bayesian blackboard and structure-variable dynamic Bayesian network is proposed for the highly dynamic air combat situation assessment and the model is proposed. The simulation results show that the inference results are preferable and consistent with the analysis.

In order to reduce the risks caused by congestion to scenic spot management and tourist safety, a dynamic Bayesian network model based on K-means++ clustering is proposed to realize the prediction of tourist transfer volume between scenic spots. Firstly, the K-means++ method is used to cluster the tourist transfer volume between scenic spots, we select the best number of clustering by the elbow rule, and the grade interval is determined by clustering results. Secondly, we consider the passenger transfer volume and tourist flow as the nodes of the dynamic Bayesian network, which can estimate the probability of tourist transfer from the upstream scenic spots to the target scenic spot, and the tourist volume of the target scenic spot is predicted. Finally, the confusion matrix is used to verify the validity of the proposed model. The case study shows: 1.) The prediction accuracy of the model can reach about 96%, which indicates that the model is suitable for tourist flow prediction. 2.) Compared to ARIMA, SVR, K-means + BN, and K-means + DBN, the proposed model has better prediction accuracy. 3.) The Bayesian network model outperforms deep learning models in interpretability.