Search

This paper addresses the problem classification of instances/questions based on the opinions (classes) provided by anonymous agents. The solution aggregates the agents' classifications, aiming to obtain as close as possible to an unknown correct classification. However, the agents' fields or domains of competence and their levels of expertise are unknown and can vary extensively. Many popular classification algorithms address such a problem by following a "wisdom-of-the-crowd" approach while using different voting methods and expectation–maximization techniques. These algorithms lead to correct classifications when the majority of the agents are experts, thus classifying the instances correctly. However, they often result in erroneous classification when only a small subset of the agents are indeed correct. Moreover, these algorithms often assume a fixed set of classes for all instances. This study presents a fast (one-pass) classification algorithm that can estimate the unknown agents' expertise level and aggregates their classifications accordingly, even when these are obtained from different questionnaires; thus, when the instances are not necessarily classified to a fixed set of classes. The proposed algorithm finds the experts and the nonexpert agents for each question by analyzing the distance between them. The algorithm identifies the expert agents for each instance and then classifies them accordingly. The suggested algorithm is validated and compared against known methods by using both simulated datasets and real-world datasets collected from various sources. The obtained results clearly demonstrate the effectiveness and advantages of the proposed method. [ABSTRACT FROM AUTHOR]

Abstract: In this paper, a method for telecommunications fraud detection is proposed. The method is based on the user profiling utilizing the Latent Dirichlet Allocation (LDA). Fraudulent behavior is detected with use of a threshold-type classification algorithm, allocating the telecommunication accounts into one of two classes: fraudulent account and non-fraudulent account. The paper provides also a method for automatic threshold computation. The accounts are classified with use of the Kullback–Leibler divergence (KL-divergence). Therefore, we also introduce three methods for approximating the KL-divergence between two LDAs. Finally, the results of experimental study on KL-divergence approximation and fraud detection in telecommunications are reported. [Copyright &y& Elsevier]

Feature weighting has been an important topic in classification learning algorithms. In this paper, we propose a new paradigm of assigning weights in classification learning, called value weighting method. While the current weighting methods assign a weight to each feature, we assign a different weight to the values of each feature. The proposed method is implemented in the context of naive Bayesian learning, and optimal weights of feature values are calculated using a gradient approach. The performance of naive Bayes learning with value weighting method is compared with that of other state-of-the-art methods for a number of datasets. The experimental results show that the value weighting method could improve the performance of naive Bayes significantly. [ABSTRACT FROM AUTHOR]

Abstract: Side information, like must-link (ML) and cannot-link (CL), has been widely used in single-view classification tasks. However, so far such information has never been applied in multi-view classification tasks. In many real world situations, data with multiple representations or views are frequently encountered, and most proposed algorithms for such learning situations require that all the multi-view data should be paired. Yet this requirement is difficult to satisfy in some settings and the multi-view data could be totally unpaired. In this paper, we propose an learning framework to design the multi-view classifiers by only employing the weak side information of cross-view must-links (CvML) and cross-view cannot-links (CvCL). The CvML and the CvCL generalize the traditional single-view must-link (SvML) and single-view cannot-link (SvCL), and to the best of our knowledge, are first definitely introduced and applied into the multi-view classification situations. Finally, we demonstrate the effectiveness of our method in our experiments. [Copyright &y& Elsevier]

Recently, many evolutionary computation methods have been developed to solve the feature selection problem. However, the studies focused mainly on small-scale issues, resulting in stagnation issues in local optima and numerical instability when dealing with large-scale feature selection dilemmas. To address these challenges, this paper proposes a novel weighted differential evolution algorithm based on self-adaptive mechanism, named SaWDE, to solve large-scale feature selection. First, a multi-population mechanism is adopted to enhance the diversity of the population. Then, we propose a new self-adaptive mechanism that selects several strategies from a strategy pool to capture the diverse characteristics of the datasets from the historical information. Finally, a weighted model is designed to identify the important features, which enables our model to generate the most suitable feature-selection solution. We demonstrate the effectiveness of our algorithm on twelve large-scale datasets. The performance of SaWDE is superior compared to six non-EC algorithms and six other EC algorithms, on both training and test datasets and on subset size, indicating that our algorithm is a favorable tool to solve the large-scale feature selection problem. Moreover, we have experimented SaWDE with six EC algorithms on twelve higher-dimensional data, which demonstrates that SaWDE is more robust and efficient compared to those state-of-the-art methods. SaWDE source code is available on Github at https://github.com/wangxb96/SaWDE. [ABSTRACT FROM AUTHOR]

Abstract: Support vector machine (SVM) has shown prominent performance for binary classification. How to effectively apply it to massive datasets with large number of classes and instances is still a serious challenge. Instance selection methods have been proposed and shown significant efficacy for reducing the training complexity of SVM, but more or less trade off the generalization performance. This paper presents an instance selection method especially for multi-class problems. With cluster centers of positive class as reference points instances are selected for each one-versus-rest SVM model. The purpose of clustering here is to improve the efficiency of instance selection, other than to select instances directly from clusters as previous methods did. Experiments on a wide variety of datasets demonstrate that the proposed method selects fewer instances than most competitive algorithms and keeps the highest classification accuracy on most datasets. Additionally, experimental results show that this method also performs superiorly for binary problems. [Copyright &y& Elsevier]

Abstract: Decision rule mining is an important technique in many applications. In this paper, we propose a new rough set approach for rule induction based on a significance measure, called classification consistency rate. The approach implements the rule induction from the viewpoint of attribute rather than descriptor. The proposed algorithm is tested and compared with LEM2 algorithm on several real-life data sets added with different levels of inconsistent data. The results show that the proposed algorithm is effective in rule induction for inconsistent data. [Copyright &y& Elsevier]

Abstract: Identity disclosure is one of the most serious privacy concerns in many data mining applications. A well-known privacy model for protecting identity disclosure is k-anonymity. The main goal of anonymizing classification data is to protect individual privacy while maintaining the utility of the data in building classification models. In this paper, we present an approach based on rough sets for measuring the data quality and guiding the process of anonymization operations. First, we make use of the attribute reduction theory of rough sets and introduce the conditional entropy to measure the classification data quality of anonymized datasets. Then, we extend conditional entropy under single-level granulation to hierarchical conditional entropy under multi-level granulation, and study its properties by dynamically coarsening and refining attribute values. Guided by these properties, we develop an efficient search metric and present a novel algorithm for achieving k-anonymity, Hierarchical Conditional Entropy-based Top-Down Refinement (HCE-TDR), which combines rough set theory and attribute value taxonomies. Theoretical analysis and experiments on real world datasets show that our algorithm is efficient and improves data utility. [Copyright &y& Elsevier]

Abstract: It has been shown that the structural information of data may contain useful prior domain knowledge for training a classifier. How to apply the structural information of data to build a good classifier is a new research focus recently. As we all know, the all existing structural large margin methods are the common in considering all structural information within classes into one model. In fact, these methods do not balance all structural information’s relationships both infra-class and inter-class, which directly results in these prior information not being exploited sufficiently. In this paper, we design a new Structural Twin Support Vector Machine (called -TWSVM). Unlike existing methods based on structural information, -TWSVM uses two hyperplanes to decide the category of new data, of which each model only considers one class’s structural information and closer to the class at the same time far away from the other class. This makes -TWSVM fully exploit these prior knowledge to directly improve the algorithm’s the capacity of generalization. All experiments show that our proposed method is rigidly superior to the state-of-the-art algorithms based on structural information of data in both computation time and classification accuracy. [Copyright &y& Elsevier]

Abstract: This paper presents a Crotch Ensemble classification model for high dimensional data. A Crotch Ensemble is obtained from a decision cluster tree built by calling a clustering algorithm recursively. A crotch is an inner node of the tree together with its direct children. If the children of a crotch have more than one dominant class, the crotch is defined as a crotch predictor. Each crotch predictor constructs a classifier by itself. A Crotch Ensemble consists of a set of crotch predictors. When classifying a new object, a subset of crotch predictors is selected according to the distances between the object and the crotch predictors. A classification is made on the object as the class predicted by the crotch predictors with the maximum accumulative weights. The experimental results on both synthetic and real data have shown that the Crotch Ensemble model can get better classification results on high dimensional data than other classification methods. [Copyright &y& Elsevier]

Abstract: Feature selection aims at finding a feature subset that has the most discriminative information from the original feature set. In this paper, we firstly present a new scheme for feature relevance, interdependence and redundancy analysis using information theoretic criteria. Then, a dynamic weighting-based feature selection algorithm is proposed, which not only selects the most relevant features and eliminates redundant features, but also tries to retain useful intrinsic groups of interdependent features. The primary characteristic of the method is that the feature is weighted according to its interaction with the selected features. And the weight of features will be dynamically updated after each candidate feature has been selected. To verify the effectiveness of our method, experimental comparisons on six UCI data sets and four gene microarray datasets are carried out using three typical classifiers. The results indicate that our proposed method achieves promising improvement on feature selection and classification accuracy. [Copyright &y& Elsevier]

Abstract: The vast subjective texts spreading all over the Internet promoted the demand for text sentiment classification technology. A well-known fact that often weakens the performance of classifiers is the distribution imbalance of review texts on the positive–negative classes. In this paper, we pay attention to the sentiment classification problem of imbalanced text sets. With regards to this problem, the algorithm BRC for clarifying the disorder boundary is proposed by cutting the majority class samples in the dense boundary region. The classifier is constructed based on Support Vector Machine. In order to find the better feature weight scheme, combination strategy of sample cutting, and parameters in BRC, three groups of experiments are designed on six text sets about five domains. The experimental results show that the feature weight scheme Presence has the best performance. And the combination strategy BRC+RS can give a tradeoff between the evaluation measures, Precision and Recall on two categories and make the synthetical evaluation measure Accuracy obtain a larger increase. It should be noted that the method of determining the parameters α and β in BRC is empirical. Although the boundary region cutting algorithm BRC is aimed to text sentiment classification we believe that it is also suitable to any two-category classification problem with imbalanced sample data. [Copyright &y& Elsevier]

Abstract: Numerous algorithms have been proposed to improve Naive Bayes (NB) by weakening its conditional attribute independence assumption, among which Tree Augmented Naive Bayes (TAN) has demonstrated remarkable classification performance in terms of classification accuracy or error rate, while maintaining efficiency and simplicity. In many real-world applications, however, classification accuracy or error rate is not enough. For example, in direct marketing, we often need to deploy different promotion strategies to customers with different likelihood (class probability) of buying some products. Thus, accurate class probability estimation is often required to make optimal decisions. In this paper, we investigate the class probability estimation performance of TAN in terms of conditional log likelihood (CLL) and present a new algorithm to improve its class probability estimation performance by the spanning TAN classifiers. We call our improved algorithm Averaged Tree Augmented Naive Bayes (ATAN). The experimental results on a large number of UCI datasets published on the main web site of Weka platform show that ATAN significantly outperforms TAN and all the other algorithms used to compare in terms of CLL. [Copyright &y& Elsevier]

Abstract: Translation initiation site (TIS) recognition is one of the first steps in gene structure prediction, and one of the common components in any gene recognition system. Many methods have been described in the literature to identify TIS in transcribed sequences such as mRNA, EST and cDNA sequences. However, the recognition of TIS in DNA sequences is a far more challenging task, and the methods described so far for transcripts achieve poor results in DNA sequences. Most methods approach this problem taking into account its biological characteristics. In this work we try a different view, considering this classification problem from a purely machine learning perspective. From the point of view of machine learning, TIS recognition is a class imbalance problem. Thus, in this paper we approach TIS recognition from this angle, and apply the different methods that have been developed to deal with imbalanced datasets. The proposed approach has two advantages. Firstly, it improves the results using standard classification methods. Secondly, it broadens the set of classification algorithms that can be used, as some of the class-imbalance methods, such as undersampling, are also useful as methods for scaling up data mining algorithms as they reduce the size of the dataset. In this way, classifiers that cannot be applied to the whole dataset, due to long training time or large memory requirements, can be used when undersampling method is applied. Results show an advantage of class imbalance methods with respect to the same methods applied without considering the class imbalance nature of the problem. The applied methods are also able to improve the results obtained with the best method in the literature, which is based on looking for the next in-frame stop codon from the putative TIS that must be predicted. [Copyright &y& Elsevier]

Abstract: The present paper investigates the influence of both the imbalance ratio and the classifier on the performance of several resampling strategies to deal with imbalanced data sets. The study focuses on evaluating how learning is affected when different resampling algorithms transform the originally imbalanced data into artificially balanced class distributions. Experiments over 17 real data sets using eight different classifiers, four resampling algorithms and four performance evaluation measures show that over-sampling the minority class consistently outperforms under-sampling the majority class when data sets are strongly imbalanced, whereas there are not significant differences for databases with a low imbalance. Results also indicate that the classifier has a very poor influence on the effectiveness of the resampling strategies. [Copyright &y& Elsevier]

Abstract: Data uncertainty can be caused by numerous factors such as measurement precision limitations, network latency, data staleness and sampling errors. When mining knowledge from emerging applications such as sensor networks or location based services, data uncertainty should be handled cautiously to avoid erroneous results. In this paper, we apply probabilistic and statistical theory on uncertain data and develop a novel method to calculate conditional probabilities of Bayes theorem. Based on that, we propose a novel Bayesian classification algorithm for uncertain data. The experimental results show that the proposed method classifies uncertain data with potentially higher accuracies than the Naive Bayesian approach. It also has a more stable performance than the existing extended Naive Bayesian method. [Copyright &y& Elsevier]

Abstract: A novel algorithm named NB+ which is an extended version of the traditional Naïve Bayesian algorithm has been presented in this paper. An exception occurs when there is an equal probability for the class label value in the Naïve Bayesian algorithm. The approach aims to suggest a solution with the help of a partial matching method. Consequently, the classification accuracy has drastically improved. Experimental evaluation has been done on various databases to show that NB+ algorithm outperforms the traditional Naïve Bayesian algorithm. [Copyright &y& Elsevier]

Abstract: Semi-supervised dimensional reduction methods play an important role in pattern recognition, which are likely to be more suitable for plant leaf and palmprint classification, since labeling plant leaf and palmprint often requires expensive human labor, whereas unlabeled plant leaf and palmprint is far easier to obtain at very low cost. In this paper, we attempt to utilize the unlabeled data to aid plant leaf and palmprint classification task with the limited number of the labeled plant leaf or palmprint data, and propose a semi-supervised locally discriminant projection (SSLDP) algorithm for plant leaf and palmprint classification. By making use of both labeled and unlabeled data in learning a transformation for dimensionality reduction, the proposed method can overcome the small-sample-size (SSS) problem under the situation where labeled data are scant. In SSLDP, the labeled data points, combined with the unlabeled data ones, are used to construct the within-class and between-class weight matrices incorporating the neighborhood information of the data set. The experiments on plant leaf and palmprint databases demonstrate that SSLDP is effective and feasible for plant leaf and palmprint classification. [ABSTRACT FROM AUTHOR]

Abstract: This paper introduces a new learning technique for the multicriteria classification method PROAFTN. This new technique, called DEPRO, utilizes a Differential Evolution (DE) algorithm for learning and optimizing the output of the classification method PROAFTN. The limitation of the PROAFTN method is largely due to the set of parameters (e.g., intervals and weights) required to be obtained to perform the classification procedure. Therefore, a learning method is needed to induce and extract these parameters from data. DE is an efficient metaheuristic optimization algorithm based on a simple mathematical structure to mimic a complex process of evolution. Some of the advantages of DE over other global optimization methods are that it often converges faster and with more certainty than many other methods and it uses fewer control parameters. In this work, the DE algorithm is proposed to inductively obtain PROAFTN’s parameters from data to achieve a high classification accuracy. Based on results generated from 12 public datasets, DEPRO provides excellent results, outperforming the most common classification algorithms. [Copyright &y& Elsevier]

Abstract: Extant multiple-cost-sensitive learning algorithms are usually designed for dealing with misclassification cost (MC) and test cost (TC) together. This paper outlines a new learning algorithm, called cost-time sensitive classification, designed for minimizing tangible costs (which includes TC and waiting cost (WC)) as well as maximizing the decrease of the intangible costs (also called MC). The proposed algorithm induces decision trees from training datasets with missing data, in which the costs are measured in different units. Firstly, a split criterion is proposed for building cost-time sensitive decision trees, aiming at possibly reducing the intangible cost. Then a hybrid test strategy, which can handle missing values in test datasets, is designed for combining the sequential test with the batch test strategy. To evaluate the efficiency of the proposed method, extensive experiments were conducted on the UCI datasets at different missing rates. The experimental results show that the proposed algorithm achieves better than the existing ones in terms of reducing the intangible costs when taking into account waiting costs. [Copyright &y& Elsevier]

Abstract: This paper presents Feature Interval Learning algorithms (FIL) which represent multi-concept descriptions in the form of disjoint feature intervals. The FIL algorithms are batch supervised inductive learning algorithms and use feature projections of the training instances to represent induced classification knowledge. The concept description is learned separately for each feature and is in the form of a set of disjoint intervals. The class of an unseen instance is determined by the weighted-majority voting of the feature predictions. The basic FIL algorithm is enhanced with adaptive interval and feature weight schemes in order to handle noisy and irrelevant features. The algorithms are empirically evaluated on twelve data sets from the UCI repository and are compared with k-NN, k-NNFP, and NBC classification algorithms. The experiments demonstrate that the FIL algorithms are robust to irrelevant features and missing feature values, achieve accuracy comparable to the best of the existing algorithms with significantly less average running times. [Copyright &y& Elsevier]

Abstract: This paper introduces a new algorithm called locality discriminating projection (LDP) for subspace learning, which provides a new scheme for discriminant analysis by considering both the manifold structure and the prior class information. In the LDP algorithm, the overlap among the class-specific manifolds is approximated by an invader graph, and a locality discriminant criterion is proposed to find the projections that best preserve the within-class local structures while decrease the between-class overlap. The feasibility of the LDP algorithm has been successfully tested in text data and visual recognition experiments. Experiment results show it is an effective technique for data modeling and classification comparing to linear discriminant analysis, locality preserving projection, and marginal Fisher analysis. [Copyright &y& Elsevier]

Abstract: In a typical application of association rule learning from market basket data, a set of transactions for a fixed period of time is used as input to rule learning algorithms. For example, the well-known Apriori algorithm can be applied to learn a set of association rules from such a transaction set. However, learning association rules from a set of transactions is not a one time only process. For example, a market manager may perform the association rule learning process once every month over the set of transactions collected through the last month. For this reason, we will consider the problem where transaction sets are input to the system as a stream of packages. The sets of transactions may come in varying sizes and in varying periods. Once a set of transactions arrive, the association rule learning algorithm is executed on the last set of transactions, resulting in new association rules. Therefore, the set of association rules learned will accumulate and increase in number over time, making the mining of interesting ones out of this enlarging set of association rules impractical for human experts. We refer to this sequence of rules as “association rule set stream” or “streaming association rules” and the main motivation behind this research is to develop a technique to overcome the interesting rule selection problem. A successful association rule mining system should select and present only the interesting rules to the domain experts. However, definition of interestingness of association rules on a given domain usually differs from one expert to another and also over time for a given expert. This paper proposes a post-processing method to learn a subjective model for the interestingness concept description of the streaming association rules. The uniqueness of the proposed method is its ability to formulate the interestingness issue of association rules as a benefit-maximizing classification problem and obtain a different interestingness model for each user. In this new classification scheme, the determining features are the selective objective interestingness factors related to the interestingness of the association rules, and the target feature is the interestingness label of those rules. The proposed method works incrementally and employs user interactivity at a certain level. It is evaluated on a real market dataset. The results show that the model can successfully select the interesting ones. [Copyright &y& Elsevier]

Abstract: This paper presents a novel algorithm named ID6NB for extending decision tree induced by Quinlan’s non-incremental ID3 algorithm. The presented approach is aimed at suggesting the solutions for few unhandled exceptions of the Decision tree induction algorithms such as (i) the situation in which the majority voting makes incorrect decision (generating two different types of rules for same data), and (ii) in case of dimensionality reduction by decision tree induction algorithms, the determination of appropriate attribute at a node where two or more attributes have equal highest information gain. Exception due to majority voting is handled with the help of Naive Bayes algorithm and also novel solutions are given for dimensionality reduction. As a result, the classification accuracy has drastically improved. An extensive experimental evaluation on a number of real and synthetic databases shows that ID6NB is a state-of-the-art classification algorithm that outperforms well than other methods of decision tree learning. [Copyright &y& Elsevier]

Support vector machines (SVMs) have been exploited in a plethora of real-life classification and regression tasks, and are one of the most researched supervised learners. However, their generalization abilities strongly depend on the pivotal hyperparameters of the classifier, alongside its training dataset. Also, the training process is computationally and memory expensive, hence learning multiple SVMs to grid-search the hyperparameter space is infeasible in practice. In this paper, we address the problem of optimizing SVMs for binary classification of difficult datasets, including very large and extremely imbalanced cases. We propose an evolutionary technique that simultaneously optimizes the critical SVM aspects, including the training sample, kernel functions, and features. Also, we introduce a co-evolutionary scheme that allows us to guide the search in a competitive way to the highest-quality solutions. Our extensive experimental study performed over more than 120 benchmarks showed that the proposed algorithm outperforms popular supervised learners, as well as other techniques for optimizing SVMs reported in the literature. [ABSTRACT FROM AUTHOR]

Feature selection is a key pre-processing technique for classification which aims at removing irrelevant or redundant features from a given dataset. Generally speaking, feature selection can be considered as a multi-objective optimization problem, i.e, removing number of features and improving the classification accuracy. Genetic algorithms (GAs) have been widely used for feature selection problems. The crossover operator, as an important technique to search for new solutions in GAs, has a strong impact on the final optimization results. However, many crossover operators are problem-dependent and have different search abilities. Thus, it is a challenge to select the most efficient one to solve different feature selection problems, especially when the nature of feature selection problems is unknown in advance. In order to overcome this challenge, in this paper, a multi-objective binary genetic algorithm integrating an adaptive operator selection mechanism (MOBGA-AOS) is proposed. In MOBGA-AOS, five crossover operators with different search characteristics are used. Each of them is assigned a probability based on the performance in the evolution process. In different phases of evolution, the proper crossover operator is selected by roulette wheel selection according to the probabilities to produce new solutions for the next generation. The proposed algorithm is compared with five well-known evolutionary multi-objective algorithms on ten datasets. The experimental results reveal that MOBGA-AOS is capable of removing a large amount of features while ensuring a small classification error. Moreover, it obtains prominent advantages on large-scale datasets, which demonstrates that MOBGA-AOS is competent to solve high-dimensional feature selection problems. [ABSTRACT FROM AUTHOR]

Many classification algorithms require that training examples contain only discrete values. In order to use these algorithms when some attributes have continuous numeric values, the numeric attributes must be converted into discrete ones. This paper describes a new way of discretizing numeric values using information theory. Our method is context-sensitive in the sense that it takes into account the value of the target attribute. The amount of information each interval gives to the target attribute is measured using Hellinger divergence, and the interval boundaries are decided so that each interval contains as equal amount of information as possible. In order to compare our discretization method with some current discretization methods, several popular classification data sets are selected for discretization. We use naive Bayesian classifier and C4.5 as classification tools to compare the accuracy of our discretization method with that of other methods. [Copyright &y& Elsevier]

Abstract: Whether a word (or a feature) should be included or excluded during the process of text classification could depend on a number of factors, such as the amount of information it represents, its appearance frequency and its meaning. The application context is another important factor that needs to be considered. A word may be able to represent the characteristic of a document in one application context but may not reflect its nature in another. This paper reports on an investigation into the selection of features for classification with the consideration of the application context of the documents to be processed. A new feature selection algorithm for text classification to be known as the PBMCD algorithm is proposed. This algorithm has been implemented and tested using three different data sets. The experiment results have shown that this algorithm cannot only filter out irrelevant features before the classification process but also can increase the classification accuracy. As a comparison, experiment results with other methods have also been presented. [Copyright &y& Elsevier]

In this paper, we propose a novel distance metric based on correntropy and kernel learning. Some properties of the proposed metric are demonstrated such as nonnegativity, non-convexity, boundedness and approximation behaviors. The proposed metric includes and extends classical metrics such as L 0 -norm and L 1 -norm metrics. Moreover, we develop a fraction loss function satisfying the Bayes rule, and demonstrate its robustness from the perspective of M-estimation. With the proposed robust metric and loss function, a new robust twin extreme learning machines framework (called LCFTELM) is presented to reduce the negative effect of noises and outliers. The proposed LCFTELM retains the advantages of twin extreme machines (TELM) and promotes the robustness. However, the non-convexity of the proposed model makes it difficult to optimize. Furthermore, an effective iterative algorithm for LCFTELM is designed, we present theoretical analysis on the convergence of the proposed algorithm. Following that, we evaluate the proposed algorithm on real-world datasets and artificial dataset under different noise settings. Experimental results show that the proposed method achieves better generalization than the state-of-the-art methods in most cases, which demonstrates the feasibility and robustness of the proposed LCFTELM. • Based on correntropy and Laplacian kernel, a robust distance metric is proposed. A new non-convex fraction loss function is developed. Applying to TELM, a robust classification framework is proposed. • The proposed metric includes and extends the traditional metrics and fractional loss function is a powerful adaptive cost in the presence of noise. • An efficient optimization method is proposed to solve the model. • Numerical experiments show that the proposed LCFTELM is effective and more robust to outliers. [ABSTRACT FROM AUTHOR]

Despite more than two decades of progress, learning from imbalanced data is still considered as one of the contemporary challenges in machine learning. This has been further complicated by the advent of the big data era, where popular algorithms dedicated to alleviating the class skew impact are no longer feasible due to the volume of datasets. Additionally, most of existing algorithms focus on binary imbalanced problems, where majority and minority classes are well-defined. Multi-class imbalanced data poses further challenges as the relationship between classes is much more complex and simple decomposition into a number of binary problems leads to a significant loss of information. In this paper, we propose the first compound framework for dealing with multi-class big data problems, addressing at the same time the existence of multiple classes and high volumes of data. We propose to analyze the instance-level difficulties in each class, leading to understanding what causes learning difficulties. We embed this information in popular resampling algorithms which allows for informative balancing of multiple classes. We propose an efficient implementation of the discussed algorithm on Apache Spark, including a novel version of SMOTE that overcomes spatial limitations in distributed environments of its predecessor. Extensive experimental study shows that using instance-level information significantly improves learning from multi-class imbalanced big data. Our framework can be downloaded from https://github.com/fsleeman/minority-type-imbalanced. • First complete framework for learning from multi-class imbalanced big data. • Informative multi-class sampling methods that use instance-level characteristics. • Novel oversampling modification dedicated to MapReduce environments. • Code and data repository for reproducibility and applications of proposed methods. [ABSTRACT FROM AUTHOR]

A central problem in machine learning and pattern recognition is the process of recognizing the most important features. In this paper, we provide a new feature selection method (DRPT) that consists of first removing the irrelevant features and then detecting correlations between the remaining features. Let D = A ∣ b be a dataset, where b is the class label and A is a matrix whose columns are the features. We solve A x = b using the least squares method and the pseudo-inverse of A. Each component of x can be viewed as an assigned weight to the corresponding column (feature). We define a threshold based on the local maxima of x and remove those features whose weights are smaller than the threshold. To detect the correlations in the reduced matrix, which we still call A , we consider a perturbation A ̃ of A. We prove that correlations are encoded in Δ x = ∣ x − x ̃ ∣ , where x ̃ is the least squares solution of A ̃ x ̃ = b. We cluster features first based on Δ x and then using the entropy of features. Finally, a feature is selected from each sub-cluster based on its weight and entropy. The effectiveness of DRPT has been verified by performing a series of comparisons with seven state-of-the-art feature selection methods over ten genetic datasets ranging up from 9,117 to 267,604 features. The results show that, over all, the performance of DRPT is favorable in several aspects compared to each feature selection algorithm. [ABSTRACT FROM AUTHOR]

In this paper, MCFS (Min-Cut-based feature-selection) is presented, which is a feature-selection algorithm based on the representation of the features in a dataset by means of a directed graph. The main contribution of our work is to show the usefulness of a general graph-processing technique in the feature-selection problem for classification datasets. The vertices of the graphs used herein are the features together with two special-purpose vertices (one of which denotes high correlation to the feature class of the dataset, and the other denotes a low correlation to the feature class). The edges are functions of the correlations among the features and also between the features and the classes. A classic max-flow min-cut algorithm is applied to this graph. The cut returned by this algorithm provides the selected features. We have compared the results of our proposal with well-known feature-selection techniques. Our algorithm obtains results statistically similar to those achieved by the other techniques in terms of number of features selected, while additionally significantly improving the accuracy. [ABSTRACT FROM AUTHOR]

Deep neural network needs large amount of data for training, to obtain more data, many simple data augmentation algorithms have been proposed. In this paper, we propose a LDA-based data augmentation algorithm to extend the training set. The proposed LDA-based data augmentation algorithm uses the topic model LDA to detect the key audio words in the recordings, and further to detect the key audio events and non-key audio events for each recording; with the detected key-audio-event segments, for each acoustic scene class, the probability distribution of key-audio-event's occurrence numbers, the probability distribution of key-audio-event's locations under each occurrence number and the probability distribution of key-audio-event's durations under each occurrence number is counted, and then the new recordings are generated according to these probability distributions. Experiments are done on the public TUT acoustic scenes 2016 dataset, and the experimental results show that compared with the other simple data augmentation algorithms, the proposed LDA-based data augmentation algorithm is more stable and effective, it can get better generalization ability for different kinds of neural network on different datasets. [ABSTRACT FROM AUTHOR]

Possible world has become one of the most effective tools to deal with various types of data uncertainty in uncertain data management. However, few uncertain data classification algorithms are proposed based on possible world. Most existing uncertain data classification algorithms are simply extended from traditional classification algorithms for certain data. They deal with data uncertainty based on relatively ideal probability distribution and data type assumptions, thus are difficult to be applied for various application scenarios. In this paper, we propose a novel possible world based AdaBoost algorithm for classifying uncertain data, called PwAdaBoost. In the training procedure, PwAdaBoost uses the possible world set generated from the uncertain training set sampled in each iteration to train the sub-basic classifiers, and employs the possible world set generated from the whole uncertain training set to adjust the weights of the sub-basic classifiers and detect the quality of the basic classifiers. In the prediction procedure, PwAdaBoost utilizes the possible world set generated from the predicted object to get the results of the basic classifiers via majority voting and weighted voting. Furthermore, we analyze the stability and give the parallelization strategies for its training procedure and prediction procedure respectively. The proposed PwAdaBoost can deal with various types of data uncertainty, and use any existing classification algorithms for certain data to serve for uncertain data. As far as we know, it is the first ensemble classification algorithm for uncertain data. Extensive experiment results demonstrate the superiority of our proposed algorithm in terms of effectiveness and efficiency. [ABSTRACT FROM AUTHOR]