Learning semi-lazy Bayesian network classifier under the c.i.i.d assumption

From undirected dependence to directed causality: A novel Bayesian learning approach

Bayesian network (BN) is one of the most powerful probabilistic models in the field of uncertain knowledge representation and reasoning. During the past decade, numerous approaches have been proposed to build directed acyclic graph (DAG) as the structural specification of BN. However, for most Bayesian network classifiers (BNCs) the directed edges in DAG substantially represent assertions of conditional independence rather than causal relationships although the learned joint probability distributions may fit data well, thus they cannot be applied to causal reasoning. In this paper, conditional entropy is introduced to measure causal uncertainty due to its asymmetry characteristic, and heuristic search strategy is applied to build Bayesian causal tree (BCT) by identifying significant causalities. The resulting highly scalable topology can represent causal relationship in terms of causal science, and corresponding joint probability can fit training data in terms of data science. Then ensemble learning strategy is applied to build Bayesian causal forest (BCF) with a set of BCTs, each taking different attribute as the root node to represent root cause for causality analysis. Extensive experiments performed on 32 public datasets from the UCI machine learning repository show that BCF achieves outstanding classification performance compared to state-of-the-art single-model BNCs (e.g., CFWNB), ensemble BNCs (e.g., WATAN, IWAODE, WAODE-MI and TAODE) and non-Bayesian learners (e.g., SVM, k-NN, LR).

An Improved Dictionary-Based Method for Gas Identification with Electronic Nose

The dictionary learning algorithm has been successfully applied to electronic noses because of its high recognition rate. However, most dictionary learning algorithms use l0-norm or l1-norm to regularize the sparse coefficients, which means that the electronic nose takes a long time to test samples and results in the inefficiency of the system. Aiming at accelerating the recognition speed of the electronic nose system, an efficient dictionary learning algorithm is proposed in this paper where the algorithm performs a multi-column atomic update. Meanwhile, to solve the problem that the singular value decomposition of the k-means (K-SVD) dictionary has little discriminative power, a novel classification model is proposed, a coefficient matrix is achieved by a linear projection to the training sample, and a constraint is imposed where the coefficients in the same category should keep a large coefficient and be closer to their class centers while coefficients in the different categories should keep sparsity. The algorithm was evaluated and analyzed based on the comparisons of several traditional classification algorithms. When the dimension of the sample was larger than 10, the average recognition rate of the algorithm was maintained above 92%, and the average training time was controlled within 4 s. The experimental results show that the improved algorithm is an effective method for the development of an electronic nose.

Alleviating the independence assumptions of averaged one-dependence estimators by model weighting

Of numerous proposals to refine naive Bayes by weakening its attribute independence assumption, averaged one-dependence estimators (AODE) has been shown to be able to achieve significantly higher classification accuracy at a moderate cost in classification efficiency. However, all one-dependence estimators (ODEs) in AODE have the same weights and are treated equally. To address this issue, model weighting, which assigns discriminate weights to ODEs and then linearly combine their probability estimates, has been proved to be an efficient and effective approach. Most information-theoretic weighting metrics, including mutual information, Kullback-Leibler measure and the information gain, place more emphasis on the correlation between root attribute (value) and class variable. We argue that the topology of each ODE can be divided into a set of local directed acyclic graphs (DAGs) based on the independence assumption, and multivariate mutual information is introduced to measure the extent to which the DAGs fit data. Based on this premise, in this study we propose a novel weighted AODE algorithm, called AWODE, that adaptively selects weights to alleviate the independence assumption and make the learned probability distribution fit the instance. The proposed approach is validated on 40 benchmark datasets from UCI machine learning repository. The experimental results reveal that, AWODE achieves bias-variance trade-off and is a competitive alternative to single-model Bayesian learners (such as TAN and KDB) and other weighted AODEs (such as WAODE).

A novel dissolved oxygen prediction model based on enhanced semi-naive Bayes for ocean ranches in northeast China

A challenge of achieving intelligent marine ranching is the prediction of dissolved oxygen (DO). DO directly reflects marine ranching environmental conditions. Through accurate DO predictions, timely human intervention can be made in marine pasture water environments to avoid problems such as reduced yields or marine crop death due to low oxygen concentrations in the water. We use an enhanced semi-naive Bayes model for prediction based on an analysis of DO data from marine pastures in northeastern China from the past three years. Based on the semi-naive Bayes model, this paper takes the possible values of a DO difference series as categories, counts the possible values of the first-order difference series and the difference series of the interval before each possible value, and selects the most probable difference series value at the next moment. The prediction accuracy is optimized by adjusting the attribute length and frequency threshold of the difference sequence. The enhanced semi-naive Bayes model is compared with LSTM, RBF, SVR and other models, and the error function and Willmott's index of agreement are used to evaluate the prediction accuracy. The experimental results show that the proposed model has high prediction accuracy for DO attributes in marine pastures.

Predicting and Interpreting Students’ Grades in Distance Higher Education through a Semi-Regression Method

Multi-view learning is a machine learning app0roach aiming to exploit the knowledge retrieved from data, represented by multiple feature subsets known as views. Co-training is considered the most representative form of multi-view learning, a very effective semi-supervised classification algorithm for building highly accurate and robust predictive models. Even though it has been implemented in various scientific fields, it has not adequately used in educational data mining and learning analytics, since the hypothesis about the existence of two feature views cannot be easily implemented. Some notable studies have emerged recently dealing with semi-supervised classification tasks, such as student performance or student dropout prediction, while semi-supervised regression is uncharted territory. Therefore, the present study attempts to implement a semi-regression algorithm for predicting the grades of undergraduate students in the final exams of a one-year online course, which exploits three independent and naturally formed feature views, since they are derived from different sources. Moreover, we examine a well-established framework for interpreting the acquired results regarding their contribution to the final outcome per student/instance. To this purpose, a plethora of experiments is conducted based on data offered by the Hellenic Open University and representative machine learning algorithms. The experimental results demonstrate that the early prognosis of students at risk of failure can be accurately achieved compared to supervised models, even for a small amount of initially collected data from the first two semesters. The robustness of the applying semi-supervised regression scheme along with supervised learners and the investigation of features’ reasoning could highly benefit the educational domain.