Bayesian Network Modeling of Transcription Factor Binding Sites

A predicament that engineers who wish to employ Bayesian networks to solve practical problems often face is the depth of study required in order to obtain a workable understanding of this tool. This chapter is intended as a tutorial material to assist the reader in efficiently understanding the fundamental concepts involved in Bayesian network applications. It presents a complete step by step solution of a bioinformatics problem using Bayesian network models, with detailed illustration of modeling, parameter estimation, and inference mechanisms. Considerations in determining an appropriate Bayesian network model representation of a physical problem are also discussed.

Retrieval of Bio-Geophysical Parameters from Remotely Sensing Data by Using Bayesian Methodology

This chapter introduces the use of Bayesian methodology for inversion purposes: the extraction of bio-geophysical parameters from remotely sensed data. Multisources information, such as different polarizations, frequencies, and sensors are fundamental to the development of operationally useful inversion systems. In this context, Bayesian methodologies offer a convenient tool of combining two or more disparate sources of information, models, and data. The chapter describes the development of a general model starting from a theoretical model, including the sensor noise and the model errors, by using a Bayesian approach. Furthermore, the developed procedure is applied to some experimental data sets. The author hopes that considering theoretical models and experimental data in many different configurations can give an idea of the versatility and robustness of the Bayesian framework.

Multimodal Human Localization Using Bayesian Network Sensor Fusion

In applications where the locations of human subjects are needed, for example, human-computer interface, video conferencing, and security surveillance applications, localizations are often performed using single sensing modalities. These mono localization modalities, such as beamforming microphone array and video-graphical localization techniques, are often prone to errors. In this chapter, a modular multimodal localization framework was constructed by combining multiple mono localization modalities using a Bayesian network. As a case study, a joint audio-video talker localization system for the video conferencing application was presented. Based on the results, the proposed multimodal localization method outperforms localization methods, in terms of accuracy and robustness, when compare with mono modal modalities that rely only on audio or video.

DBN Models for Visual Tracking and Prediction

In a visual tracking task, the object may exhibit rich dynamic behavior in complex environments that can corrupt target observations via background clutter and occlusion. Such dynamics and background induce nonlinear, nonGaussian and multimodal observation densities. These densities are difficult to model with traditional methods such as Kalman filter models (KFMs) due to their Gaussian assumptions. Dynamic Bayesian networks (DBNs) provide a more general framework in which to solve these problems. DBNs generalize KFMs by allowing arbitrary probability distributions, not just (unimodal) linear-Gaussian. Under the DBN umbrella, a broad class of learning and inference algorithms for time-series models can be used in visual tracking. Furthermore, DBNs provide a natural way to combine multiple vision cues. In this chapter, we describe some DBN models for tracking in nonlinear, nonGaussian and multimodal situations, and present a prediction method to assist feature extraction part by making a hypothesis for the new observations.

Bayesian Networks for Image Understanding

Image understanding deals with extracting and interpreting scene content for use in various applications. In this chapter, we illustrate that Bayesian networks are particularly well-suited for image understanding problems, and present case studies in indoor-outdoor scene classification and parts-based object detection. First, improved scene classification is accomplished using both low-level features, such as color and texture, and semantic features, such as the presence of sky and grass. Integration of low-level and semantic features is achieved using a Bayesian network framework. The network structure can be determined by expert opinion or by automated structure learning methods. Second, object detection at multiple views relies on a parts-based approach, where specialized detectors locate object parts and a Bayesian network acts as the arbitrator in order to determine the object presence. In general, Bayesian networks are found to be powerful integrators of different features and help improve the performance of image understanding systems.

Application of Bayesian Network in Learning Gene Network

Exact determination of a gene network is required to discover the higher-order structures of an organism and to interpret its behavior. Currently, learning gene network is one of the central themes of the post genome era. A lot of mathematical models are applied to learn gene networks. Among them, Bayesian network has shown its advantages over other methods because of its abilities to handle stochastic events, control noise, and handle dataset with a few replicates. In this chapter, we will introduce how Bayesian network has been applied to learn gene networks and how we integrated the important biological factors into the framework of Bayesian network to improve the learning performance.

Application of Bayesian Network in Drug Discovery and Development Process

The end of the 20th century and the advent of the new millennium have brought in a true merger of sciences for the benefit of mankind. The biggest promise it holds is that of improving the quality of human life by the discovery of newer medicines and better cures for diseases such as cancer and heart disease. Pharmaceutical companies and academic institutions alike have not failed to deliver on part of the promise by bringing out technologies and products that have significantly decreased mortality and morbidity associated with these diseases. An increase in the scale and complexity of the technologies has made it increasingly important to develop intelligent tools to analyze their output, and numerous mathematical and statistical techniques have been explored and exploited to do exactly this. Bayesian networks (BN) and similar graphical models for multivariate analysis are being used for analyzing these data with great success. They have made possible a high resolution insight into disease mechanisms like never before. These insights into the biological processes of health and disease have helped identify the appropriate targets for drug discovery and aided in the process of bringing better drugs faster to the market for patients in need. This chapter briefly explains the application and contribution of Bayesian networks to the drug discovery and development process.

Long Term Tracking of Pedestrians with Groups and Occlusions

This chapter describes an algorithm for tracking groups of pedestrians in video sequences. The main difficulties addressed in this work concern total occlusions of the objects to be tracked, as well as group merging and splitting. Because there is ambiguity, the algorithm should be able to provide the most probable interpretation of the data. A two layer solution is proposed. The first layer produces a set of spatiotemporal trajectories based on low level operations which manage to track the pedestrians most of the time. The second layer performs a consistent labeling of the detected segments using a statistical model based on Bayesian networks. The Bayesian network is recursively computed during the tracking operation and allows the update of the tracker results every time new information is available. Interpretation/recognition errors can thus be detected after receiving enough information about the group of interacting objects. Experimental tests are included to show the performance of the algorithm in complex situations. This work was supported by FEDER and FCT under project LT (POSI 37844/01).

NetCube

We present a novel method for answering count queries from a large database approximately and quickly. Our method implements an approximate DataCube of the application domain, which can be used to answer any conjunctive count query that can be formed by the user. The DataCube is a conceptual device that in principle stores the number of matching records for all possible such queries. However, because its size and generation time are inherently exponential, our approach uses one or more Bayesian networks to implement it approximately. Bayesian networks are statistical graphical models that can succinctly represent the underlying joint probability distribution of the domain, and can therefore be used to calculate approximate counts for any conjunctive query combination of attribute values and “don’t cares.” The structure and parameters of these networks are learned from the database in a preprocessing stage. By means of such a network, the proposed method, called NetCube, exploits correlations and independencies among attributes to answer a count query quickly without accessing the database. Our preprocessing algorithm scales linearly on the size of the database, and is thus scalable; it is also parallelizable with a straightforward parallel implementation. We give an algorithm for estimating the count result of arbitrary queries that is fast (constant) on the database size. Our experimental results show that NetCubes have fast generation and use, achieve excellent compression and have low reconstruction error. Moreover, they naturally allow for visualization and data mining, at no extra cost.

A Novel Discriminative Naive Bayesian Network for Classification

Naive Bayesian network (NB) is a simple yet powerful Bayesian network. Even with a strong independency assumption among the features, it demonstrates competitive performance against other state-of-the-art classifiers, such as support vector machines (SVM). In this chapter, we propose a novel discriminative training approach originated from SVM for deriving the parameters of NB. This new model, called discriminative naive Bayesian network (DNB), combines both merits of discriminative methods (e.g., SVM) and Bayesian networks. We provide theoretic justifications, outline the algorithm, and perform a series of experiments on benchmark real-world datasets to demonstrate our model’s advantages. Its performance outperforms NB in classification tasks and outperforms SVM in handling missing information tasks.