Bayesian Network Classifiers Research Articles

The combination of four molecular markers improves thyroid cancer cytologic diagnosis and patient management.

BackgroundPapillary thyroid cancer is the most common endocrine malignancy. The most sensitive and specific diagnostic tool for thyroid nodule diagnosis is fine-needle aspiration (FNA) biopsy with cytological evaluation. Nevertheless, FNA biopsy is not always decisive leading to “indeterminate” or “suspicious” diagnoses in 10 %–30 % of cases. BRAF V600E detection is currently used as molecular test to improve the diagnosis of thyroid nodules, yet it lacks sensitivity. The aim of the present study was to identify novel molecular markers/computational models to improve the discrimination between benign and malignant thyroid lesions.MethodsWe collected 118 pre-operative thyroid FNA samples. All 118 FNA samples were characterized for the presence of the BRAF V600E mutation (exon15) by pyrosequencing and further assessed for mRNA expression of four genes (KIT, TC1, miR-222, miR-146b) by quantitative polymerase chain reaction. Computational models (Bayesian Neural Network Classifier, discriminant analysis) were built, and their ability to discriminate benign and malignant tumors were tested. Receiver operating characteristic (ROC) analysis was performed and principal component analysis was used for visualization purposes.ResultsIn total, 36/70 malignant samples carried the V600E mutation, while all 48 benign samples were wild type for BRAF exon15. The Bayesian neural network (BNN) and discriminant analysis, including the mRNA expression of the four genes (KIT, TC1, miR-222, miR-146b) showed a very strong predictive value (94.12 % and 92.16 %, respectively) in discriminating malignant from benign patients. The discriminant analysis showed a correct classification of 100 % of the samples in the malignant group, and 95 % by BNN. KIT and miR-146b showed the highest diagnostic accuracy of the ROC curve, with area under the curve values of 0.973 for KIT and 0.931 for miR-146b.ConclusionsThe four genes model proposed in this study proved to be highly discriminative of the malignant status compared with BRAF assessment alone. Its implementation in clinical practice can help in identifying malignant/benign nodules that would otherwise remain suspicious.Electronic supplementary materialThe online version of this article (doi:10.1186/s12885-015-1917-2) contains supplementary material, which is available to authorized users.

Design of one-way acoustic energy flow devices using Bayesian network classifiers

Linear acoustic metamaterials (AMM) displaying dynamic negative stiffness or density have been the subject of current research to design exotic devices such as acoustic super-lenses and cloaks. More recently, nonlinear AMM have been of interest as one means of creating non-reciprocal acoustic devices [Liang et al., Nat. Mater. 9 (2010)]. The efficiency of those types of non-reciprocal acoustic devices strongly depends on the material nonlinearity of one of its components and is therefore limited by existing fluids containing contrast agents. This work addresses this limitation by exploring the top-down design of a nonlinear AMM with non-resonant subwavelength structures that display non-monotonic pressure-volume strain response to generate an AMM with large parameters of nonlinearity. A simple one-way device consisting of a frequency-selective acoustic mirror and a nonlinear medium is described using a nonlinear multiscale model and a nonlinear propagation model that includes quadratic and cubic nonlinearity. Bayesian network classifiers (BNC) map regions of high performance at the device scale to each design level and intersect the high performance space across levels to identify multilevel solutions. Three design levels are considered: one-way performance, nonlinear acoustic propagation in the effective medium, and effective properties of the AMM based on subwavelength structure.

Toward an Effective Combination of multiple Visual Features for Semantic Image Annotation

In this paper we study the problem of combining low-level visual features for semantic image annotation. The problem is tackled with a two different approaches that combines texture, color and shape features via a Bayesian network classifier. In first approach, vector concatenation has been applied to combine the three low-level visual features. All three descriptors are normalized and merged into a unique vector used with single classifier. In the second approach, the three types of visual features are combined in parallel scheme via three classifiers. Each type of descriptors is used separately with single classifier. The experimental results show that the semantic image annotation accuracy is higher when the second approach is used.

Toward an Effective Combination of multiple Visual Features for Semantic Image Annotation

In this paper we study the problem of combining low-level visual features for semantic image annotation. The problem is tackled with a two different approaches that combines texture, color and shape features via a Bayesian network classifier. In first approach, vector concatenation has been applied to combine the three low-level visual features. All three descriptors are normalized and merged into a unique vector used with single classifier. In the second approach, the three types of visual features are combined in parallel scheme via three classifiers. Each type of descriptors is used separately with single classifier. The experimental results show that the semantic image annotation accuracy is higher when the second approach is used.

Exploring the effect of a user’s personality traits on tactile communication with a robot using Bayesian networks

Because robots are physically embodied agents, touch is one of the important modalities through which robots communicate with humans. Among the several factors that affect human-robot interaction, this research focuses on the effect of a user’s personality traits on tactile interactions with a robot. Participants interacted freely with a robot and their tactile interaction patterns were analyzed. Several classifiers were used to examine the effect of a participant’s degree of extroversion on tactile communication patterns with the robot and our results showed that a user’s personality traits affected the way in which they interacted with the robot. Specifically, important features of Bayesian networks, such as the Markov blanket and what-if/goal-seeking power were tested and showed the effect of personality on tactile interaction with respect to where and how participants touched the robot. We also found that, by using Bayesian network classifiers, a user’s personality traits can be inferred based on tactile communication patterns.

Interactive Naive Bayesian network: A new approach of constructing gene-gene interaction network for cancer classification.

Naive Bayesian (NB) network classifier is a simple and well-known type of classifier, which can be easily induced from a DNA microarray data set. However, a strong conditional independence assumption of NB network sometimes can lead to weak classification performance. In this paper, we propose a new approach of interactive naive Bayesian (INB) network to weaken the conditional independence of NB network and classify cancers using DNA microarray data set. We selected the differently expressed genes (DEGs) to reduce the dimension of the microarray data set. Then, an interactive parent which has the biggest influence among all DEGs is searched for each DEG. And then we calculate a weight to represent the interactive relationship between a DEG and its parent. Finally, the gene-gene interaction network is constructed. We experimentally test the INB network in terms of classification accuracy using leukemia and colon DNA microarray data sets, then we compare it with the NB network. The INB network can get higher classification accuracies than NB network. And INB network can show the gene-gene interactions visually.

Activity Recognition Using Fusion of Low-Cost Sensors on a Smartphone for Mobile Navigation Application

Low-cost inertial and motion sensors embedded on smartphones have provided a new platform for dynamic activity pattern inference. In this research, a comparison has been conducted on different sensor data, feature spaces and feature selection methods to increase the efficiency and reduce the computation cost of activity recognition on the smartphones. We evaluated a variety of feature spaces and a number of classification algorithms from the area of Machine Learning, including Naive Bayes, Decision Trees, Artificial Neural Networks and Support Vector Machine classifiers. A smartphone app that performs activity recognition is being developed to collect data and send them to a server for activity recognition. Using extensive experiments, the performance of various feature spaces has been evaluated. The results showed that the Bayesian Network classifier yields recognition accuracy of 96.21% using four features while requiring fewer computations.

A hybrid method for learning multi-dimensional Bayesian network classifiers based on an optimization model

Bayesian networks, which have a solid mathematical basis as classifiers, take the prior information of samples into consideration. They have gained considerable popularity for solving classification problems. However, many real-world applications can be viewed as classification problems in which instances have to be assigned to a set of different classes at the same time. To address this problem, multi-dimensional Bayesian network classifiers (MBCs), which organize class and feature variables as three subgraphs, have recently been proposed. Because each subgraph has different structural restrictions, three different learning algorithms are needed. In this paper, we present for the first time an MBC learning algorithm based on an optimization model (MBC-OM) that is inspired by the constraint-based Bayesian network structure learning method. MBC-OM uses the chi-squared statistic and mutual information to estimate the dependence coefficients among variables, and these are used to construct an objective function as an overall measure of the dependence for a classifier structure. Therefore, the problem of searching for an optimal classifier becomes one of finding the maximum value of the objective function in feasible fields. We prove the existence and uniqueness of the numerical solution. Moreover, we validate our method on five benchmark data sets. Experimental results are competitive, and outperform state-of-the-art algorithms for multi-dimensional classification.

Discriminative Learning of Bayesian Networks via Factorized Conditional Log-Likelihood

We propose an efficient and parameter-free scoring criterion, the factorized conditional log-likelihood (fCLL), for learning Bayesian network classifiers. The proposed score is an approximation of the conditional log-likelihood criterion. The approximation is devised in order to guarantee decomposability over the network structure, as well as efficient estimation of the optimal parameters, achieving the same time and space complexity as the traditional log-likelihood scoring criterion. The resulting criterion has an information-theoretic interpretation based on interaction information, which exhibits its discriminative nature. To evaluate the performance of the proposed criterion, we present an empirical comparison with state-of-the-art classifiers. Results on a large suite of benchmark data sets from the UCI repository show that fCLL-trained classifiers achieve at least as good accuracy as the best compared classifiers, using significantly less computational resources.

Analysis of the socioecological structure and dynamics of the territory using a hybrid Bayesian network classifier

Territorial planning and management requires that the spatial structure of the socioecological sectors is adequately understood. Several classification techniques exist that have been applied to detect ecological, or socioeconomic sectors, but not simultaneously in the same model; and also, with a limited number of variables. We have developed and applied a new probabilistic methodology – based on hierarchical hybrid Bayesian network classifiers – to identify the different socioecological sectors in Andalusia, a region in southern Spain, and incorporate a scenario of change. Results show that a priori, the socioecological structure is highly heterogeneous, with an altitude gradient from the river basin to the mountain peaks. However, under a scenario of global environmental change this heterogeneity is lost, making the territory more vulnerable to any alteration or disturbance. The methodology applied allows dealing with complex problems, containing a large number of variables, by splitting them into several sub-problems that can be easily solved. In the case of territorial planning, each component of the territory is modelled independently before combining them into a general classifier model. Furthermore, it can be applied to any complex unsupervised classification problem with no modification to the methodology.

On Bayesian Network Classifiers with Reduced Precision Parameters.

Bayesian network classifier (BNCs) are typically implemented on nowadays desktop computers. However, many real world applications require classifier implementation on embedded or low power systems. Aspects for this purpose have not been studied rigorously. We partly close this gap by analyzing reduced precision implementations of BNCs. In detail, we investigate the quantization of the parameters of BNCs with discrete valued nodes including the implications on the classification rate (CR). We derive worst-case and probabilistic bounds on the CR for different bit-widths. These bounds are evaluated on several benchmark datasets. Furthermore, we compare the classification performance and the robustness of BNCs with generatively and discriminatively optimized parameters, i.e. parameters optimized for high data likelihood and parameters optimized for classification, with respect to parameter quantization. Generatively optimized parameters are more robust for very low bit-widths, i.e. less classifications change because of quantization. However, classification performance is better for discriminatively optimized parameters for all but very low bit-widths. Additionally, we perform analysis for margin-optimized tree augmented network (TAN) structures which outperform generatively optimized TAN structures in terms of CR and robustness.

Diagnosis of Cardiovascular Diseases with Bayesian Classifiers

Cardiovascular disease or atherosclerosis is any disease affecting the cardiovascular system. They include coronary heart disease, raised blood pressure, cerebrovascular disease, peripheral artery disease, rheumatic heart disease, congenital heart disease and heart failure. They are treated by cardiologists, thoracic surgeons, vascular surgeons, neurologists and interventional radiologists. The diagnosis is an important yet complicated task that needs to be done accurately and efficiently. The automation of this system is very much needed to help the physicians to do better diagnosis and treatment. Computer aided diagnosis systems are widely discussed as classification problems. The objective is to reduce the number of false decisions and increase the true ones. In this study, we evaluate the performance of Bayesian classifier (BN) in predicting the risk of cardiovascular disease. Bayesian networks are selected as they are able to produce probability estimates rather than predictions. These estimates allow predictions to be ranked and their expected costs to be minimized. The major advantage of BN is the ability to represent and hence understand knowledge. The cardiovascular dataset is provided by University of California, Irvine (UCI) machine learning repository. It consists of 303 instances of heart disease data each having 76 variables including the predicted class one. This study evaluates two Bayesian network classifiers; Tree Augmented Naive Bayes and the Markov Blanket Estimation and their prediction accuracies are benchmarked against the Support Vector Machine. The experimental results show that Bayesian networks with Markov blanket estimation has a superior performance on the diagnosis of cardiovascular diseases with classification accuracy of MBE model is 97.92% of test samples, while TAN and SVM models have 88.54 and 70.83% respectively.

Bayesian predictive modeling based on multidimensional connectivity profiling.

Dysfunction of brain structural and functional connectivity is increasingly being recognized as playing an important role in many brain disorders. Diffusion tensor imaging (DTI) and functional magnetic resonance (fMR) imaging are widely used to infer structural and functional connectivity, respectively. How to combine structural and functional connectivity patterns for predictive modeling is an important, yet open, problem. We propose a new method, called Bayesian prediction based on multidimensional connectivity profiling (BMCP), to distinguish subjects at the individual level based on structural and functional connectivity patterns. BMCP combines finite mixture modeling and Bayesian network classification. We demonstrate its use in distinguishing young and elderly adults based on DTI and resting-state fMR data.

Multidimensional Learning from Crowds: Usefulness and Application of Expertise Detection

Learning from crowds is a classification problem where the provided training instances are labeled by multiple (usually conflicting) annotators. In different scenarios of this problem, straightforward strategies show an astonishing performance. In this paper, we characterize the crowd scenarios where these basic strategies show a good behavior. As a consequence, this study allows to identify those scenarios where non-basic methods for combining the multiple labels are expected to obtain better results. In this context, we extend the learning from crowds paradigm to the multidimensional (MD) classification domain. Measuring the quality of the annotators, the presented EM-based method overcomes the lack of a fully reliable labeling for learning MD Bayesian network classifiers: As the expertise is identified and the contribution of the relevant annotators promoted, the model parameters are optimized. The good performance of our proposal is demonstrated throughout different sets of experiments.

Locally Weighted Learning: How and When Does it Work in Bayesian Networks?

AbstractBayesian network (BN), a simple graphical notation for conditional independence assertions, is promised to represent the probabilistic relationships between diseases and symptoms. Learning the structure of a Bayesian network classifier (BNC) encodes conditional independence assumption between attributes, which may deteriorate the classification performance. One major approach to mitigate the BNC's primary weakness (the attributes independence assumption) is the locally weighted approach. And this type of approach has been proved to achieve good performance for naive Bayes, a BNC with simple structure. However, we do not know whether or how effective it works for improving the performance of the complex BNC. In this paper, we first do a survey on the complex structure models for BNCs and their improvements, then carry out a systematically experimental analysis to investigate the effectiveness of locally weighted method for complex BNCs, e.g., tree-augmented naive Bayes (TAN), averaged one-dependenc...

Decision boundary for discrete Bayesian network classifiers

Bayesian network classifiers are a powerful machine learning tool. In order to evaluate the expressive power of these models, we compute families of polynomials that sign-represent decision functio...

Fault Detection and Diagnosis in a Bayesian Network classifier incorporating probabilistic boundary1

The purpose of this article is to present a method for Fault Detection and Diagnosis (FDD) with Bayesian network, and more particularly with Conditional Gaussian Network (CGN). A classical problem of FDD with supervised classification is when Normal Operating Conditions class is integrated, the false alarm rate is not guarantee by the classifier. The interest of the proposed method is to introduce a probabilistic limit on the Normal Operating Conditions class, allowing to respect a given false alarm rate. Performances of this method are evaluated on data of a benchmark example: the Tennessee Eastman Process. Three kinds of faults are taken into account on this complex process.

The Optimisation of Bayesian Classifier in Predictive Spatial Modelling for Secondary Mineral Deposits

This paper discusses the general concept of Bayesian Network classifier and the optimisation of a predictive spatial model using Naive Bayes (NB) on secondary mineral deposit data. A different NB modelling approaches to mineral distribution data was used to predict the occurrence of a particular mineral deposit in a given area, which include; predictive attributes sub-selection, normalised attributes selection, NB dependent attributes and the strictness to NB model assumptions of attributes independence selection. The performance of the model was determined by selecting a model with the best predictive accuracy. The NB classifier that violates assumptions of attributes independence was used to compare with other forms of NB. The aim is to improve the general performance of the model through the best selection of predictive attribute data. The paper elaborates the workings of a Bayesian Network learning model, the concept of NB and its application to predicting mineral deposit potentials. The result of the optimised NB model based on predictive accuracies and the Receivr Operating Characteristics (ROC) value is also determined.

Spam filtering by using Genetic based Feature Selection

Spam is defined as redundant and unwanted electronical letters, and nowadays, it has created many problems in business life such as occupying networks bandwidth and the space of user’s mailbox. Due to these problems, much research has been carried out in this regard by using classification technique. The resent research show that feature selection can have positive effect on the efficiency of machine learning algorithm. Most algorithms try to present a data model depending on certain detection of small set of features. Unrelated features in the process of making model result in weak estimation and more computations. In this research it has been tried to evaluate spam detection in legal electronica letters, and their effect on several Machin learning algorithms through presenting a feature selection method based on genetic algorithm. Bayesian network and KNN classifiers have been taken into account in classification phase and spam base dataset is used.

Bayesian network classifiers for categorizing cortical GABAergic interneurons.

An accepted classification of GABAergic interneurons of the cerebral cortex is a major goal in neuroscience. A recently proposed taxonomy based on patterns of axonal arborization promises to be a pragmatic method for achieving this goal. It involves characterizing interneurons according to five axonal arborization features, called F1-F5, and classifying them into a set of predefined types, most of which are established in the literature. Unfortunately, there is little consensus among expert neuroscientists regarding the morphological definitions of some of the proposed types. While supervised classifiers were able to categorize the interneurons in accordance with experts' assignments, their accuracy was limited because they were trained with disputed labels. Thus, here we automatically classify interneuron subsets with different label reliability thresholds (i.e., such that every cell's label is backed by at least a certain (threshold) number of experts). We quantify the cells with parameters of axonal and dendritic morphologies and, in order to predict the type, also with axonal features F1-F4 provided by the experts. Using Bayesian network classifiers, we accurately characterize and classify the interneurons and identify useful predictor variables. In particular, we discriminate among reliable examples of common basket, horse-tail, large basket, and Martinotti cells with up to 89.52% accuracy, and single out the number of branches at 180 μm from the soma, the convex hull 2D area, and the axonal features F1-F4 as especially useful predictors for distinguishing among these types. These results open up new possibilities for an objective and pragmatic classification of interneurons.