Search

Identifying discriminative patterns, known as shapelets, within time series is a critical step in many time series classification tasks. A major limitation of shapelet learning is that often hindered by their unsupervised methods, treating shapelet learning as an unsupervised subsequence clustering process and discovery based on pre-defined metric, which performed sequentially. This sequential procedure presents challenges, as it fails to establish a direct connection between shapelets and samples, and lacks the capacity to explicitly incorporate label information. In this paper, we proposed a novel shapelet learning algorithm called Discriminative Shapelet Learning via Temporal Clustering and Matrix Factorization (DSLMF). DSLMF introduced a joint framework that combines matrix factorization and coherent temporal clustering to discovery salient and coherent feature subsets. To further enhance discriminability and prevent arbitrary shapelet shapes, DSLMF integrates a label-specific shapelet regularization as a guiding mechanism enabling the learning of shapelets optimized for higher classification performance. The proposed algorithm has shown to be effective for capturing the temporal cluster structure and interpretability of shapelet-based method. The results of experiments showcased in this paper highlight DSLMF's effectiveness in capturing temporal cluster structures and learning meaningful shapelets, ultimately leading to promising performance on benchmark datasets. [ABSTRACT FROM AUTHOR]

In this paper we propose a new algorithm, named NICE, to generate counterfactual explanations for tabular data that specifically takes into account algorithmic requirements that often emerge in real-life deployments: (1) the ability to provide an explanation for all predictions, (2) being able to handle any classification model (also non-differentiable ones), (3) being efficient in run time, and (4) providing multiple counterfactual explanations with different characteristics. More specifically, our approach exploits information from a nearest unlike neighbor to speed up the search process, by iteratively introducing feature values from this neighbor in the instance to be explained. We propose four versions of NICE, one without optimization and, three which optimize the explanations for one of the following properties: sparsity, proximity or plausibility. An extensive empirical comparison on 40 datasets shows that our algorithm outperforms the current state-of-the-art in terms of these criteria. Our analyses show a trade-off between on the one hand plausibility and on the other hand proximity or sparsity, with our different optimization methods offering users the choice to select the types of counterfactuals that they prefer. An open-source implementation of NICE can be found at https://github.com/ADMAntwerp/NICE. [ABSTRACT FROM AUTHOR]

Machine learning techniques aim to mimic the human ability to automatically learn how to perform tasks through training examples. They have proven capable of tasks such as prediction, learning and adaptation based on experience and can be used in virtually any scientific application, ranging from biomedical, robotic, to business decision applications, and others. However, the lack of domain knowledge for a particular application can make feature extraction ineffective or even unattainable. Furthermore, even in the presence of pre-processed datasets, the iterative process of optimizing Machine Learning parameters, which do not translate from one domain to another, maybe difficult for inexperienced practitioners. To address these issues, we present in this paper a Vectorized Automated ML Pre-processIng and post-pRocEssing framework, approximately named (VAMPIRE), which implements feature extraction algorithms capable of converting large time-series recordings into datasets. Also, it introduces a new concept, the Activation Engine, which is attached to the output of a Multi Layer Perceptron and extracts the optimal threshold to apply binary classification. Moreover, a tree-based algorithm is used to achieve multi-class classification using the Activation Engine. Furthermore, the internet of things gives rise to new applications such as remote sensing and communications, so consequently applying Machine Learning to improve operation accuracy, latency, and reliability is beneficial in such systems. Therefore, all classifications in this paper were performed on the edge in order to reach high accuracy with limited resources. Moreover, forecasts were applied on three unrelated biomedical datasets, and on two other pre-processed urban and activity detection datasets. Features were extracted when required, and training and testing were performed on the Raspberry Pi remotely, where high accuracy and inference speed were achieved in every experiment. Additionally, the board remained competitive in terms of power consumption when compared with a laptop which was optimized using a Graphical Processing Unit. [ABSTRACT FROM AUTHOR]

In the era of big data, the demand for multivariate time series prediction has surged, drawing increased attention to feature selection and neural networks in machine learning. However, certain feature selection methods neglect the alignment between actual data sample differences and clustering results, while neural networks lack automatic parameter adjustment in response to changing target features. This paper presents the MBSSA-Bi-AESN model, a Bi-directional Adaptive Echo State Network that utilizes the modified salp swarm algorithm (MBSSA) and feature selection to address the limitations of manually set parameters. Initial feature subset selection involves assigning weights based on the consistency of clustering results with differences. Subsequently, the four critical parameters in the Bi-AESN model are optimized using MBSSA. The optimized Bi-AESN model and selected feature subset are then integrated for simultaneous model learning and optimal feature subset selection. Experimental analysis on eight datasets demonstrates the superior prediction accuracy of the MBSSA-Bi-AESN model compared to benchmark models, underscoring its feasibility, validity, and universality. [ABSTRACT FROM AUTHOR]

In Machine Learning (ML), Feature Selection (FS) plays a crucial part in reducing data's dimensionality and enhancing any proposed framework's performance. However, in real-world applications, FS work suffers from high dimensionality, computational and storage complexity, noisy or ambiguous nature, high performance, etc. The area of FS is very vast and challenging in its nature. There are lots of work that have been reported on FS over the various area of applications. This paper has discussed FS's framework and the multiple models of FS with detailed descriptions. We have also classified the various FS algorithms with respect to the data, i.e., structured or labeled data and unstructured data for the different applications of ML. We have also discussed what essential features are, the commonly used FS methods, the widely used datasets, and the widely used work done in the various ML fields for the FS task. Here we try to view the multiple comparison experimental results of FS work in different result discussions. This paper draws a descriptive survey on FS with the associated area of real-world problem domains. This paper's main objective is to understand the main idea of FS work and identify the core idea of how FS will be applicable in various problem domains. [ABSTRACT FROM AUTHOR]

The aim of this paper is to introduce a new two-step inertial method for approximating a solution to a generalized split common fixed point problem, which is a unique solution to a variational inequality problem. We establish a strong convergence theorem for the sequence generated by the algorithm. We explore various special cases related to fundamental problems, including the split feasibility problem, the split common null point problem, and the constrained convex minimization problem. To demonstrate the efficacy and performance of our proposed algorithm, we apply it to a practical scenario involving support vector machines for binary classification. The algorithm is employed on diverse datasets sourced from the UC Irvine Machine Learning Repository, serving as the training set. [ABSTRACT FROM AUTHOR]

It has been shown that unsupervised outlier detection methods can be adapted to the one-class classification problem (Janssens and Postma, in: Proceedings of the 18th annual Belgian-Dutch on machine learning, pp 56–64, 2009; Janssens et al. in: Proceedings of the 2009 ICMLA international conference on machine learning and applications, IEEE Computer Society, pp 147–153, 2009. https://doi.org/10.1109/ICMLA.2009.16). In this paper, we focus on the comparison of one-class classification algorithms with such adapted unsupervised outlier detection methods, improving on previous comparison studies in several important aspects. We study a number of one-class classification and unsupervised outlier detection methods in a rigorous experimental setup, comparing them on a large number of datasets with different characteristics, using different performance measures. In contrast to previous comparison studies, where the models (algorithms, parameters) are selected by using examples from both classes (outlier and inlier), here we also study and compare different approaches for model selection in the absence of examples from the outlier class, which is more realistic for practical applications since labeled outliers are rarely available. Our results showed that, overall, SVDD and GMM are top-performers, regardless of whether the ground truth is used for parameter selection or not. However, in specific application scenarios, other methods exhibited better performance. Combining one-class classifiers into ensembles showed better performance than individual methods in terms of accuracy, as long as the ensemble members are properly selected. [ABSTRACT FROM AUTHOR]

Machine learning algorithms often contain many hyperparameters whose values affect the predictive performance of the induced models in intricate ways. Due to the high number of possibilities for these hyperparameter configurations and their complex interactions, it is common to use optimization techniques to find settings that lead to high predictive performance. However, insights into efficiently exploring this vast space of configurations and dealing with the trade-off between predictive and runtime performance remain challenging. Furthermore, there are cases where the default hyperparameters fit the suitable configuration. Additionally, for many reasons, including model validation and attendance to new legislation, there is an increasing interest in interpretable models, such as those created by the decision tree (DT) induction algorithms. This paper provides a comprehensive approach for investigating the effects of hyperparameter tuning for the two DT induction algorithms most often used, CART and C4.5. DT induction algorithms present high predictive performance and interpretable classification models, though many hyperparameters need to be adjusted. Experiments were carried out with different tuning strategies to induce models and to evaluate hyperparameters' relevance using 94 classification datasets from OpenML. The experimental results point out that different hyperparameter profiles for the tuning of each algorithm provide statistically significant improvements in most of the datasets for CART, but only in one-third for C4.5. Although different algorithms may present different tuning scenarios, the tuning techniques generally required few evaluations to find accurate solutions. Furthermore, the best technique for all the algorithms was the Irace. Finally, we found out that tuning a specific small subset of hyperparameters is a good alternative for achieving optimal predictive performance. [ABSTRACT FROM AUTHOR]

Clustering and classification-based pattern recognition techniques are widely used in various domains. While many approaches exist to perform these tasks, it remains a difficult process to perform clustering and classification simultaneously for particular datasets. In this paper, a method based on k-nearest neighbor (KNN) is presented to classify the dataset with PSO optimized k-medoids clustering. Initial clustering with k-medoids algorithm divides the dataset into smaller and disjoint clusters featuring similarity within clusters and dissimilarity with members of other clusters. Particle swarm optimization (PSO) is an evolutionary algorithm mainly used to optimize the issues in several research areas including data analytics. The fitness function of the PSO approach mentioned in this paper is based on inertia weights that identify the particles with the best positions and velocities for optimization. Additionally, PSO uses a novel elitism concept that allows massive searching capability between the swarm of particles to achieve a better convergence rate. Because of this property, it can be applied throughout different machine learning fields. Moreover, the KNN classifier outperforms the classification task in terms of classifying the optimized particles with high accuracy. The performance of the proposed technique is evaluated by experimenting with datasets taken from open sources. The simulation results revealed that the performance of the proposed method is better than the existing methods in terms of effective clustering as well as accurate classification. [ABSTRACT FROM AUTHOR]

In the research area of time series classification, the ensemble shapelet transform algorithm is one of the state-of-the-art algorithms for classification. However, its high time complexity is an issue to hinder its application since its base classifier shapelet transform includes a high time complexity of a distance calculation and shapelet selection. Therefore, in this paper we introduce a novel algorithm, i.e., short isometric shapelet transform (SIST), which contains two strategies to reduce the time complexity. The first strategy of SIST fixes the length of shapelet based on a simplified distance calculation, which largely reduces the number of shapelet candidates as well as speeds up the distance calculation in the ensemble shapelet transform algorithm. The second strategy is to train a single linear classifier in the feature space instead of an ensemble classifier. The theoretical evidence of these two strategies is presented to guarantee a near-lossless accuracy under some preconditions while reducing the time complexity. Furthermore, empirical experiments demonstrate the superior performance of the proposed algorithm. [ABSTRACT FROM AUTHOR]

The paper is devoted to the application of the plausible reasoning principles to symbolic machine learning. It seems for us that the applications are essential and necessary to improve the efficiency of ML algorithms. Many such algorithms produce and use rules in the form of implication. The generation of these rules with respect to the object classes is discussed. Our classification rules are specific. Their premise part, called good closed tests (GCTs), should cover as many objects as possible. One of the algorithms of GCTs generation called NIAGARA is presented. The algorithm is revisited and new procedures based on plausible reasoning are proposed. Their correctness is proved in propositions. We use the following rules: implication, interdiction, inductive rules of extending current sets of goal-oriented objects, rules of pruning the domain of searching solution. They allow to rise the effectiveness of algorithms. [ABSTRACT FROM AUTHOR]

Classification is a widely used supervised learning technique that enables models to discover the relationship between a set of features and a specified label using available data. Its applications span various fields such as engineering, telecommunication, astronomy, and medicine. In this paper, we propose a novel rule-based classifier called RUCIB (RUle-based Classifier Inspired by BRADO), which draws inspiration from the socio-inspired swarm intelligence algorithm known as BRADO. RUCIB introduces two key aspects: the ability to accommodate multiple values for features within a rule and the capability to explore all data features simultaneously. To evaluate the performance of RUCIB, we conducted experiments using ten databases sourced from the UCI machine learning database repository. In terms of classification accuracy, we compared RUCIB to ten well-known classifiers. Our results demonstrate that, on average, RUCIB outperforms Naive Bayes, SVM, PART, Hoeffding Tree, C4.5, ID3, Random Forest, CORER, CN2, and RACER by 9.32%, 8.97%, 7.58%, 7.4%, 7.34%, 7.34%, 7.22%, 5.06%, 5.01%, and 1.92%, respectively. [ABSTRACT FROM AUTHOR]

This paper addresses the question of maximizing classifier accuracy for classifying task-related mental activity from Magnetoencelophalography (MEG) data. We propose the use of different sources of information and introduce an automatic channel selection procedure. To determine an informative set of channels, our approach combines a variety of machine learning algorithms: feature subset selection methods, classifiers based on regularized logistic regression, information fusion, and multiobjective optimization based on probabilistic modeling of the search space. The experimental results show that our proposal is able to improve classification accuracy compared to approaches whose classifiers use only one type of MEG information or for which the set of channels is fixed a priori. [ABSTRACT FROM AUTHOR]

The qualities of new data used in the sequential learning phase of the online sequential extreme learning machine algorithm (OS-ELM) have a significant impact on the performance of OS-ELM. This paper proposes a novel data filter mechanism for OS-ELM from the perspective of fuzziness and a fuzziness-based online sequential extreme learning machine algorithm (FOS-ELM). In FOS-ELM, when new data arrive, a fuzzy classifier first picks out the meaningful data according to the fuzziness of each sample. Specifically, the new samples with high-output fuzziness are selected and then used in sequential learning. The experimental results on eight binary classification problems and three multiclass classification problems have shown that FOS-ELM updated by the new samples with high-output fuzziness has better generalization performance than OS-ELM. Since the unimportant data are discarded before sequential learning, FOS-ELM can save more memory and have higher computational efficiency. In addition, FOS-ELM can handle data one-by-one or chunk-by-chunk with fixed or varying sizes. The relationship between the fuzziness of new samples and the model performance is also studied in this paper, which is expected to provide some useful guidelines for improving the generalization ability of online sequential learning algorithms. [ABSTRACT FROM AUTHOR]

Multi-label learning has attracted many attentions. However, the continuous data generated in the fields of sensors, network access, etc., that is data streams, the scenario brings challenges such as real-time, limited memory, once pass. Several learning algorithms have been proposed for offline multi-label classification, but few researches develop it for dynamic multi-label incremental learning models based on cascading schemes. Deep forest can perform representation learning layer by layer, and does not rely on backpropagation, using this cascading scheme, this paper proposes a multi-label data stream deep forest (VDSDF) learning algorithm based on cascaded Very Fast Decision Tree (VFDT) forest, which can receive examples successively, perform incremental learning, and adapt to concept drift. Experimental results show that the proposed VDSDF algorithm, as an incremental classification algorithm, is more competitive than batch classification algorithms on multiple indicators. Moreover, in dynamic flow scenarios, the adaptability of VDSDF to concept drift is better than that of the contrast algorithm. [ABSTRACT FROM AUTHOR]

In this paper, some significant efforts on fuzzy oblique decision tree (FODT) have been done to improve classification accuracy and decrease tree size. Firstly, to eliminate data redundancy and improve classification efficiency, a forward greedy fast feature selection algorithm based on neighborhood rough set (NRS_FS_FAST) is introduced. Then, a new fuzzy rule generation algorithm (FRGA) is proposed to generate fuzzy rules. These fuzzy rules are used to construct leaf nodes for each class in each layer of the FODT. Different from the traditional axis-parallel decision trees and oblique decision trees, the FODT takes dynamic mining fuzzy rules as decision functions. Moreover, the parameter δ, which can control the size of the tree, is optimized by genetic algorithm. Finally, a series of comparative experiments are carried out with five traditional decision trees (C4.5, Best First Tree (BFT), amulti-class alternating decision tree (LAD), Simple Cart (SC), Naive Bayes Tree (NBT)), and recently proposed decision trees (FRDT, HHCART, and FMMDT-HB) on UCI machine learning datasets. The experimental results demonstrate that the FODT exhibits better performance on classification accuracy and tree size than the chosen benchmarks. [ABSTRACT FROM AUTHOR]

Feature selection becomes prominent, especially in the data sets with many variables and features. It will eliminate unimportant variables and improve the accuracy as well as the performance of classification. Random Forest has emerged as a quite useful algorithm that can handle the feature selection issue even with a higher number of variables. In this paper, we use three popular datasets with a higher number of variables (Bank Marketing, Car Evaluation Database, Human Activity Recognition Using Smartphones) to conduct the experiment. There are four main reasons why feature selection is essential. First, to simplify the model by reducing the number of parameters, next to decrease the training time, to reduce overfilling by enhancing generalization, and to avoid the curse of dimensionality. Besides, we evaluate and compare each accuracy and performance of the classification model, such as Random Forest (RF), Support Vector Machines (SVM), K-Nearest Neighbors (KNN), and Linear Discriminant Analysis (LDA). The highest accuracy of the model is the best classifier. Practically, this paper adopts Random Forest to select the important feature in classification. Our experiments clearly show the comparative study of the RF algorithm from different perspectives. Furthermore, we compare the result of the dataset with and without essential features selection by RF methods varImp(), Boruta, and Recursive Feature Elimination (RFE) to get the best percentage accuracy and kappa. Experimental results demonstrate that Random Forest achieves a better performance in all experiment groups. [ABSTRACT FROM AUTHOR]

Machine learning-based predictive modeling is to develop machine learning-based or data-driven models to predict failures before they occur and estimate the remaining useful life or time to failure (TTF) accurately. Accurate TTF estimation plays a vital role in predictive maintenance or PHM (Prognostic and Health Management). Despite the availability of large amounts of data and a variety of powerful data analysis methods, predictive models developed for PHM still fail to provide accurate and precise TTF estimations. This paper addresses this problem by integrating machine learning algorithms such as classification, regression and clustering. A classification system is used to determine the likelihood of component failures such that rough indications of TTF are provided. Clustering and SVM-based local regression are then introduced to refine the time to failure estimations provided by the classification system. The paper illustrates the applicability of the proposed approach through a real world aerospace application with details on data pre-processing requirements. The results demonstrate that the proposed method can reduce uncertainty in estimating time to failure, which in turn helps augment the usefulness of predictive maintenance. [ABSTRACT FROM AUTHOR]

Real-world classification domains, such as medicine, health and safety, and finance, often exhibit imbalanced class priors and have asynchronous misclassification costs. In such cases, the classification model must achieve a high recall without significantly impacting precision. Resampling the training data is the standard approach to improving classification performance on imbalanced binary data. However, the state-of-the-art methods ignore the local joint distribution of the data or correct it as a post-processing step. This can causes sub-optimal shifts in the training distribution, particularly when the target data distribution is complex. In this paper, we propose Radial-Based Combined Cleaning and Resampling (RB-CCR). RB-CCR utilizes the concept of class potential to refine the energy-based resampling approach of CCR. In particular, RB-CCR exploits the class potential to accurately locate sub-regions of the data-space for synthetic oversampling. The category sub-region for oversampling can be specified as an input parameter to meet domain-specific needs or be automatically selected via cross-validation. Our 5 × 2 cross-validated results on 57 benchmark binary datasets with 9 classifiers show that RB-CCR achieves a better precision-recall trade-off than CCR and generally out-performs the state-of-the-art resampling methods in terms of AUC and G-mean. [ABSTRACT FROM AUTHOR]

Knowledge in the source domain can be used in transfer learning to help train and classification tasks within the target domain with fewer available data sets. Therefore, given the situation where the target domain contains only a small number of available unlabeled data sets and multi-source domains contain a large number of labeled data sets, a new Multi-source Fast Transfer Learning algorithm based on support vector machine(MultiFTLSVM) is proposed in this paper. Given the idea of multi-source transfer learning, more source domain knowledge is taken to train the target domain learning task to improve classification effect. At the same time, the representative data set of the source domain is taken to speed up the algorithm training process to improve the efficiency of the algorithm. Experimental results on several real data sets show the effectiveness of MultiFTLSVM, and it also has certain advantages compared with the benchmark algorithm. [ABSTRACT FROM AUTHOR]

Adaptive boosting (Adaboost) is a typical ensemble learning algorithm, which has been studied and widely used in classification tasks. Traditional Adaboost algorithms ignore the sample weights while selecting the most useful features, and most of them ignore the fact that the performances of weak classifiers on each category are always different. On this basis, a weighted feature selection and category classification confidence based Adaboost algorithm is proposed in this paper. The first contribution, is that we propose a weighted feature selection to select the most useful features, which can both distinguish the majority of all samples and the previous misclassified samples. The second contribution, is that we improve the traditional error rate calculation method and propose a category based error rate calculation method to combine the classification abilities of Adaboost on different categories. A detailed performances comparison of various Adaboost algorithms are carried out on eight typical datasets. The experimental results show that the proposed algorithm obtains significant improvement on classification accuracy compared to typical Adaboost algorithms when different datasets especially the unbalanced datasets are used. [ABSTRACT FROM AUTHOR]

The unique properties of terahertz (THz) spectroscopy show a great potential for security and defense applications such as safe screening of persons and objects. However, a successful implementation of THz screening systems requires a development of reliable and efficient identification algorithms. Dimensionality reduction (DR) methods aim to reduce the dimensionality of the multivariate data and are therefore commonly used as a preprocessing step for classification algorithms and as an analytical tool allowing data visualization. In this paper, we compare the use of unsupervised and supervised DR methods for analysis and classification of THz reflection spectra based on their most widespread linear representatives, namely principal component analysis and linear discriminant analysis, respectively. To this end, both methods were applied to more than 5000 THz reflection spectra acquired from six active materials mixed at three different concentrations with polyethylene and measured at various humidity conditions. While considering scenarios with different levels of complexity, we found that the supervised approach provides better results because it enables efficient grouping despite intra-class variability. Furthermore, we showed that manipulating labels introduced into the supervised DR algorithm allows conditioning the data for a desired classification task such as security screening. Presented classification results show that simple machine learning algorithms are sufficient for highly accurate classification (>98.6%) of THz spectra, which will be suitable for many real-life applications of THz spectroscopy based on material identification. [ABSTRACT FROM AUTHOR]

Feature selection is one of the main steps in preprocessing data in machine learning, and its goal is to reduce features by removing additional and noisy features. Feature selection methods and feature reduction in a dataset must consider the accuracy of the classifying algorithms. Meta-heuristic algorithms serve as the most successful and promising methods to solve this problem. Symbiotic Organisms Search (SOS) is one of the most successful meta-heuristic algorithms inspired by organisms' interaction in nature called mutualism, commensalism, and parasitism. In this paper, three SOS-based binary approaches are offered to solve the feature selection problem. In the first and second approaches, several S-shaped transfer functions and several Chaotic Tent Function-based V-shaped transfer functions called BSOSST and BSOSVT are used to make the binary SOS (BSOS). In the third approach, an advanced BSOS based on changing SOS and the chaotic Tent function operators called EBCSOS is provided. The EBCSOS algorithm uses the chaotic Tent function and the Gaussian mutation to increase usefulness and exploration. Moreover, two new operators, i.e., BMPT and BCPT, are suggested to make the commensalism and mutualism stage binary based on a chaotic function to solve the feature selection problem. Finally, the proposed BSOSST and BSOSVT methods and the advanced version of EBCSOS were implemented on 25 datasets than the basic algorithm's binary meta-heuristic algorithms. Various experiments demonstrated that the proposed EBCSOS algorithm outperformed other methods in terms of several features and accuracy. To further confirm the proposed EBCSOS algorithm, the problem of detecting spam E-mails was applied, with the results of this experiment indicating that the proposed EBCSOS algorithm significantly improved the accuracy and speed of all categories in detecting spam E-mails. [ABSTRACT FROM AUTHOR]

Classification is one of the foremost machine learning tasks in this modern era. Neural Network (NN) is one of the powerful classification techniques. NN can achieve high classification accuracy on highly imbalanced and complex datasets, but lacks in explanation of its reasoning process which limits its applicability in various domains which require transparent decision along with good accuracy. There are some techniques which extract rules from NN and make it transparent; however, attribute pruning, rule pruning and class overlap algorithms are not sufficiently effective. Therefore, this paper proposes a rule extraction algorithm, called Transparent Rule Extraction using Neural Network (TRENN) to convert NN into white box with greater emphasis on attribute pruning and rule pruning. The proposed TRENN is a pedagogical approach and an extension of one of the existing algorithms named Rule Extraction from Neural Network using Classified and Misclassified data (RxNCM). The proposed TRENN extends the RxNCM with sequential floating backward search for feature and rule selection to improve the comprehensibility of the generated rules. Besides, the proposed TRENN uses probabilistic approach for the treatment of class overlapping problem in the rule updating phase instead of reclassification used in RxNCM where the overlap may persist. Experiments are conducted with eight real datasets collected from the UCI repository. Performance of the TRENN is measured with Precision, Recall, FP-Rate, F-measure, and local and global comprehensibility. It is observed from the experimental results that TRENN performs better than Re-RX, RxNCM and RxREN. [ABSTRACT FROM AUTHOR]

The extreme learning machine (ELM), a typical machine learning algorithm based on feedforward neural network, has been widely used in classification, clustering, regression and feature learning. However, the traditional ELM learns all samples at once, and sample weights of traditional methods are defined before the learning process and they will not change during the learning process. So, its performance is vulnerable to noisy data and outliers, finding a way to solve this problem is meaningful. In this work, we propose a model of self-paced ELM named SP-ELM for binary classification and multi-classification originated from the self-paced learning paradigm. Concretely, the algorithm takes the importance of samples into account according to the loss of predicted value and real value, and it establishes the model from the simple samples to complex samples. By setting certain restrictions, the influence of complex data on the model is reduced. Four different self-paced regularization terms are adopted in the paper to select the instances. Experimental results demonstrate the effectiveness and of the proposed method by comparing it with other improved ELMs. [ABSTRACT FROM AUTHOR]

In recent years, classifier ensemble techniques have drawn the attention of many researchers in the machine learning research community. The ultimate goal of these researches is to improve the accuracy of the ensemble compared to the individual classifiers. In this paper, a novel algorithm for building ensembles called dynamic programming-based ensemble design algorithm (DPED) is introduced and studied in detail. The underlying theory behind DPED is based on cooperative game theory in the first phase and applying a dynamic programming approach in the second phase. The main objective of DPED is to reduce the size of the ensemble while encouraging extra diversity in order to improve the accuracy. The performance of the DPED algorithm is compared empirically with the classical ensemble model and with a well-known algorithm called "the most diverse." The experiments were carried out with 13 datasets from UCI and three ensemble models. Each ensemble model is constructed from 15 different base classifiers. The experimental results demonstrate that DPED outperforms the classical ensembles on all datasets in terms of both accuracy and size of the ensemble. Regarding the comparison with the most diverse algorithm, the number of selected classifiers by DPED across all datasets and all domains is less than or equal to the number selected by the most diverse algorithm. Experiment on blog spam dataset, for instance, shows that DPED provides an accuracy of 96.47 compared to 93.87 obtained by the most diverse using 40% training size. Finally, the experimental results verify the reliability, stability, and effectiveness of the proposed DPED algorithm. [ABSTRACT FROM AUTHOR]

In recent years, considerable resources have been invested to exploit vast amounts of data that get collected during exploration, drilling and production of oil and gas. Data-related digital technologies potentially become a game changer for the industry in terms of reduced costs through increasing operational efficiency and avoiding accidents, improved health, safety and environment through strengthening situational awareness and so on. Machine learning, an application of artificial intelligence to offer systems/processes self-learning and self-driving ability, has been around for recent decades. In the last five to ten years, the increased computational powers along with heavily digitized control and monitoring systems have made machine learning algorithms more available, powerful and accurate. Considering the state-of-art technologies that exist today and the significant resources that are being invested into the technologies of tomorrow, the idea of intelligent and automated drilling systems to select best decisions or provide good recommendations based on the information available becomes closer to a reality. This study shows the results of our research activity carried out on the topic of drilling automation and digitalization. The main objective is to test the developed machine learning algorithms of formation classification and drilling operations identification on a laboratory drilling system. In this paper, an algorithm to develop data-driven models based on the laboratory data collocated in many scenarios (for instance, drilling different formation samples with varying drilling operational parameters and running different operations) is presented. Moreover, a testing algorithm based on data-driven models for new formation detection and confirmation is proposed. In the case study, results on multiple experiments conducted to test and validate the developed machine learning methods have been illustrated and discussed. [ABSTRACT FROM AUTHOR]

As a competitive machine learning algorithm, extreme learning machine (ELM), with its simple theory and easy implementation, has been widely used in the field of pattern accuracy. Recently, researchers have proposed related research algorithms to accommodate noise and outlier data. With a proper fuzzy membership function, a fuzzy ELM can effectively reduce the effects of outliers when solving the classification problem. However, how to apply ELM for learning and accuracy in the presence of noise is still an important research topic. A novel fuzzy ELM (ANFELM) technique is proposed in this paper. In the algorithm, the membership degree of the sample is calculated in a feature mapping space instead of the data input space. The algorithm provides good performance in reducing the effects of outliers and significantly improves classification accuracy and generalization. Experiments on UCI datasets and textual datasets show that the proposed algorithm significantly improves the classification capability of ELM and is superior to other algorithms. [ABSTRACT FROM AUTHOR]

In this paper, an optimal weight semi-supervised learning machine for a single-hidden layer feedforward network (SLFN) with time delay is developed. Both input weights and output weights of the SLFN are globally optimized with manifold regularization. By feature mapping, input vectors can be placed at the prescribed positions in the feature space in the sense that the separability of all nonlinearly separable patterns can be maximized, unlabeled data can be leveraged to improve the classification accuracy when labeled data are scarce, and a high degree of recognition accuracy can be achieved with a small number of hidden nodes in the SLFN. Some simulation examples are presented to show the excellent performance of the proposed algorithm. [ABSTRACT FROM AUTHOR]

Text classification reduces the time complexity and space complexity by dividing the complete task into the different classes. The main problem with text classification is a vast number of features extracted from the textual data. Pre-processed dataset have many features, some of which are not desirable and act only like noise. In this paper, a novel approach for optimal text classification based on nature-inspired algorithm and ensemble classifier is proposed. In the proposed model, feature selection was performed with Biogeography Based Optimization (BBO) algorithm along with ensemble classifiers (Bagging). The use of ensemble classifiers for classification delivers better performance for optimal text classification as compared to an individual classifier, and hence, improving the accuracy. Ensemble classifiers combines the weakness of individual classifiers. The individual classifiers are unable to improve the classification results when compared to ensemble classifier. The selected features, after feature selection using BBO algorithm, are classified into various classes using six machine learning classifier. The experimental results are computed on ten text classification datasets taken from UCI repository and one real-time dataset of an airlines. The four different measures namely; Accuracy, Precision, Recall and F- measure are used to validate performance of our model with ten-fold cross-validation. For feature selection process, a comparison is performed among state-of-the-art algorithms available in the literature. Results shows that BBO for feature selection outperforms the other similar nature-based optimization techniques. Our proposed approach of BBO with ensemble classifier is also compared with techniques proposed by other researchers and we analyzed the results quantitatively and qualitatively. [ABSTRACT FROM AUTHOR]

Due to the lack of experience and prior knowledge, the selection of the most informative features has become one of the challenging problems in many applications. Recently, many metaheuristic algorithms have widely used to solve the feature selection problem for classification tasks. In this paper, the chaotic atom search optimization (CASO) that integrates the chaotic maps into atom search optimization (ASO) is applied for wrapper feature selection. Twelve different chaotic maps are used to adjust the parameter of CASO through the optimization process, which is beneficial for enhancing the convergence rate and improving the efficiency of ASO algorithm. In this study, twenty benchmark datasets acquired from the UCI machine learning repository are used to validate the performance of CASO in feature selection. Several state-of-the-art metaheuristic algorithms are adopted to examine the efficacy and effectiveness of the proposed approach. Our results indicated that the Logistic-Tent map was the most suitable chaotic map to boost the performance of CASO. The experimental result shows the capability of CASO not only in finding the optimal solution but also in significantly improving the prediction accuracy and reducing the number of features. [ABSTRACT FROM AUTHOR]

Feature selection is one of the hottest machine learning topics in recent years. The main purposes of it are to simplify the original model, improve the readability of the model, and prevent over-fitting by searching for a suitable subset of features. There are many methods for this problem, including evolutionary algorithms and particle swarm optimization. Among them, the competitive swarm optimizer is a new optimization algorithm proposed in recent years, which is based on particle swarm optimization algorithm, and has achieved good results in high-dimensional feature selection problems, but it also has the problems of high computation time cost and easily being premature. Aiming at these problems, this paper proposes to add the crossover operator and mutation operator in the genetic algorithm to the competitive swarm optimization, so as to improve the generation speed of new individuals in the algorithm and prevent premature population. After testing on UC Irvine Machine Learning Repository, the new algorithm not only improves the computational efficiency, but also avoids the problem that the competitive swarm optimization algorithm is easy to fall into the local optimum, which greatly improves the calculation effect. [ABSTRACT FROM AUTHOR]

A set of classification rules can be considered as a disjunction of rules, where each rule is a disjunct. A small disjunct is a rule covering a small number of examples. Small disjuncts are a serious problem for effective classification, because the small number of examples satisfying these rules makes their prediction unreliable and error-prone. This paper offers two main contributions to the research on small disjuncts. First, it investigates six candidate solutions (algorithms) for the problem of small disjuncts. Second, it reports the results of a meta-learning experiment, which produced meta-rules predicting which algorithm will tend to perform best for a given data set. The algorithms investigated in this paper belong to different machine learning, paradigms and their hybrid combinations, as follows: two versions of a decision-tree (DT) induction algorithm; two versions of a hybrid DT/genetic algorithm (GA) method; one GA; one hybrid DT/instance-based learning (IBL) algorithm. Experiments with 22 data sets evaluated both the predictive accuracy and the simplicity of the discovered rule sets, with the following conclusions. If one wants to maximize predictive accuracy only, then the hybrid DT/IBL seems to be the best choice. On the other hand, if one wants to maximize both predictive accuracy and rule set simplicity — which is important in the context of data mining — then a hybrid DT/GA seems to be the best choice. [ABSTRACT FROM AUTHOR]

Label propagation is an essential graph-based semi-supervised learning algorithm. However, the algorithm has two problems: how to effectively measure sample similarity and handle label imbalanced sets. Recent advances in the semi-supervised field have shown that self-supervised pre-training can help to model more explicit class boundaries and significantly improve classification accuracy. Inspired by the problems and progress, we propose an integrated self-supervised label propagation algorithm (ISSLP). Our algorithm's framework introduces self-supervised information in the iterative label propagation process to establish more explicit inter-class boundaries and control the label propagation scope. In addition, considering that different self-supervised models can capture different feature views of the data, we propose an entropy approach to measure the quality of feature views and generate weights for integrating multiple propagation results. The experimental results on synthetic and real-world datasets show that the proposed method can effectively solve the label imbalance problem and is insensitive to the parameters in the graph construction stage. [ABSTRACT FROM AUTHOR]

Copyright of Arabian Journal for Science & Engineering (Springer Science & Business Media B.V. ) is the property of Springer Nature and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

K-nearest neighbors (KNN) algorithm is a common algorithm used for classification, and also a sub-routine in various complicated machine learning tasks. In this paper, we presented a quantum algorithm (QKNN) for implementing this algorithm based on the metric of Hamming distance. We put forward a quantum circuit for computing Hamming distance between testing sample and each feature vector in the training set. Taking advantage of this method, we realized a good analog for classical KNN algorithm by setting a distance threshold value t to select k − n e a r e s t neighbors. As a result, QKNN achieves O( n ) performance which is only relevant to the dimension of feature vectors and high classification accuracy, outperforms Llyod's algorithm (Lloyd et al. 2013) and Wiebe's algorithm (Wiebe et al. 2014). [ABSTRACT FROM AUTHOR]

Multi-instance learning was first proposed by Dietterich et al. (Artificial Intelligence 89(1–2):31–71, 1997 ) when they were investigating the problem of drug activity prediction. Here, the training set is composed of labeled bags, each of which consists of many unlabeled instances. And the goal of this learning framework is to learn some classifier from the training set for correctly labeling unseen bags. After Dietterich et al., many studies about this new learning framework have been started and many new algorithms have been proposed, for example, DD, EM-DD, Citation- kNN and so on. All of these algorithms are working on the full data set. But as in single-instance learning, different feature in training set has different effect on the training about classifier. In this paper, we will study the problem about feature selection in multi-instance learning. We will extend the data reliability measure and make it select the key feature in multi-instance scenario. [ABSTRACT FROM AUTHOR]

Regularized multiple criteria linear programming (RMCLP) model is a new powerful method for classification and has been used in various real-life data mining problems. In this paper, a new Multi-instance Classification method based on RMCLP was proposed (called MI-RMCLP), which includes two algorithms for linearly separable case and nonlinearly case separately. The key point of this method, instead of a mixed integer quadratic programming in MI-SVM, is that it is able to deal with multi-instance learning problem by an iterative strategy solving sequential quadratic programming problems. All experiment results have shown that MI-RMCLP method can converge to the optimal value in limited iterative steps and be a competitive method in multi-instance learning classification. [ABSTRACT FROM AUTHOR]

Recently, the following Discrimination-Aware Classification Problem was introduced: Suppose we are given training data that exhibit unlawful discrimination; e.g., toward sensitive attributes such as gender or ethnicity. The task is to learn a classifier that optimizes accuracy, but does not have this discrimination in its predictions on test data. This problem is relevant in many settings, such as when the data are generated by a biased decision process or when the sensitive attribute serves as a proxy for unobserved features. In this paper, we concentrate on the case with only one binary sensitive attribute and a two-class classification problem. We first study the theoretically optimal trade-off between accuracy and non-discrimination for pure classifiers. Then, we look at algorithmic solutions that preprocess the data to remove discrimination before a classifier is learned. We survey and extend our existing data preprocessing techniques, being suppression of the sensitive attribute, massaging the dataset by changing class labels, and reweighing or resampling the data to remove discrimination without relabeling instances. These preprocessing techniques have been implemented in a modified version of Weka and we present the results of experiments on real-life data. [ABSTRACT FROM AUTHOR]

Incremental learning has been used extensively for data stream classification. Most attention on the data stream classification paid on non-evolutionary methods. In this paper, we introduce new incremental learning algorithms based on harmony search. We first propose a new classification algorithm for the classification of batch data called harmony-based classifier and then give its incremental version for classification of data streams called incremental harmony-based classifier. Finally, we improve it to reduce its computational overhead in absence of drifts and increase its robustness in presence of noise. This improved version is called improved incremental harmony-based classifier. The proposed methods are evaluated on some real world and synthetic data sets. Experimental results show that the proposed batch classifier outperforms some batch classifiers and also the proposed incremental methods can effectively address the issues usually encountered in the data stream environments. Improved incremental harmony-based classifier has significantly better speed and accuracy on capturing concept drifts than the non-incremental harmony based method and its accuracy is comparable to non-evolutionary algorithms. The experimental results also show the robustness of improved incremental harmony-based classifier. [ABSTRACT FROM AUTHOR]

In multi-instance learning, the training set is composed of labeled bags each consists of many unlabeled instances, that is, an object is represented by a set of feature vectors instead of only one feature vector. Most current multi-instance learning algorithms work through adapting single-instance learning algorithms to the multi-instance representation, while this paper proposes a new solution which goes at an opposite way, that is, adapting the multi-instance representation to single-instance learning algorithms. In detail, the instances of all the bags are collected together and clustered into d groups first. Each bag is then re-represented by d binary features, where the value of the ith feature is set to one if the concerned bag has instances falling into the ith group and zero otherwise. Thus, each bag is represented by one feature vector so that single-instance classifiers can be used to distinguish different classes of bags. Through repeating the above process with different values of d, many classifiers can be generated and then they can be combined into an ensemble for prediction. Experiments show that the proposed method works well on standard as well as generalized multi-instance problems. [ABSTRACT FROM AUTHOR]

In this paper, the classification of the two binary bioinformatics datasets, leukemia and colon tumor, is further studied by using the recently developed neural network-based finite impulse response extreme learning machine (FIR-ELM). It is seen that a time series analysis of the microarray samples is first performed to determine the filtering properties of the hidden layer of the neural classifier with FIR-ELM for feature identification. The linear separability of the data patterns in the microarray datasets is then studied. For improving the robustness of the neural classifier against noise and errors, a frequency domain gene feature selection algorithm is also proposed. It is shown in the simulation results that the FIR-ELM algorithm has an excellent performance for the classification of bioinformatics data in comparison with many existing classification algorithms. [ABSTRACT FROM AUTHOR]

This paper presents a new classification method utilizing distance-based decision surface with nearest neighbor projection approach, called DDC. Kernel type of DDC has been extended to take into account the effective nonlinear structure of the data. DDC has some properties: (1) does not need conventional learning procedure (as k-NN algorithm), (2) does not need searching time to locate the k-nearest neighbors, and (3) does not need optimization process unlike some classification methods such as Support Vector Machine (SVM). In DDC, we compute the weighted average of distances to all the training samples. Unclassified sample will be classified as belonging to a class that has the minimum obtained distance. As a result, by such a rule we can derive a formula that can be used as the decision surface. DDC is tested on both synthetic and real-world data sets from the UCI repository, and the results were compared with k-NN, RBF Network, and SVM. The experimental results indicate DDC outperforms k-NN in the most experiments and the results are comparable to or better than SVM with some data sets. [ABSTRACT FROM AUTHOR]

This paper aims to assist the administration departments of medical organisations in making the right decision on selecting a suitable multiclass classification model for acute leukaemia. In this paper, we proposed a framework that will aid these departments in evaluating, benchmarking and ranking available multiclass classification models for the selection of the best one. Medical organisations have continuously faced evaluation and benchmarking challenges in such endeavour, especially when no single model is superior. Moreover, the improper selection of multiclass classification for acute leukaemia model may be costly for medical organisations. For example, when a patient dies, one such organisation will be legally or financially sued for incidents in which the model fails to fulfil its desired outcome. With regard to evaluation and benchmarking, multiclass classification models are challenging processes due to multiple evaluation and conflicting criteria. This study structured a decision matrix (DM) based on the crossover of 2 groups of multi-evaluation criteria and 22 multiclass classification models. The matrix was then evaluated with datasets comprising 72 samples of acute leukaemia, which include 5327 gens. Subsequently, multi-criteria decision-making (MCDM) techniques are used in the benchmarking and ranking of multiclass classification models. The MCDM used techniques that include the integrated BWM and VIKOR. BWM has been applied for the weight calculations of evaluation criteria, whereas VIKOR has been used to benchmark and rank classification models. VIKOR has also been employed in two decision-making contexts: individual and group decision making and internal and external group aggregation. Results showed the following: (1) the integration of BWM and VIKOR is effective at solving the benchmarking/selection problems of multiclass classification models. (2) The ranks of classification models obtained from internal and external VIKOR group decision making were almost the same, and the best multiclass classification model based on the two was 'Bayes. Naive Byes Updateable' and the worst one was 'Trees.LMT'. (3) Among the scores of groups in the objective validation, significant differences were identified, which indicated that the ranking results of internal and external VIKOR group decision making were valid. [ABSTRACT FROM AUTHOR]

Ensemble learning has gained considerable attention in different learning tasks including regression, classification, and clustering problems. One of the drawbacks of the ensemble is the high computational cost of training stages. Resampling local negative correlation (RLNC) is a technique that combines two well-known methods to generate ensemble diversity-resampling and error negative correlation-and a fine-grain parallel approach that allows us to achieve a satisfactory balance between accuracy and efficiency. In this paper, we introduce a structure of the virtual machine aimed to test diverse selection strategies of parameters in neural ensemble designs, such as RLNC. We assess the parallel performance of this approach on a virtual machine cluster based on the full virtualization paradigm, using speedup and efficiency as performance metrics, for different numbers of processors and training data sizes. [ABSTRACT FROM AUTHOR]

This paper introduces a new outlier detection approach and discusses and extends a new concept, class separation through variance. We show that even for balanced and concentric classes differing only in variance, accumulating information about the outlierness of points in multiple subspaces leads to a ranking in which the classes naturally tend to separate. Exploiting this leads to a highly effective and efficient unsupervised class separation approach. Unlike typical outlier detection algorithms, this method can be applied beyond the 'rare classes' case with great success. The new algorithm FASTOUT introduces a number of novel features. It employs sampling of subspaces points and is highly efficient. It handles arbitrarily sized subspaces and converges to an optimal subspace size through the use of an objective function. In addition, two approaches are presented for automatically deriving the class of the data points from the ranking. Experiments show that FASTOUT typically outperforms other state-of-the-art outlier detection methods on high-dimensional data such as Feature Bagging, SOE1, LOF, ORCA and Robust Mahalanobis Distance, and competes even with the leading supervised classification methods for separating classes. [ABSTRACT FROM AUTHOR]

In the classification framework there are problems in which the number of examples per class is not equitably distributed, formerly known as imbalanced data sets. This situation is a handicap when trying to identify the minority classes, as the learning algorithms are not usually adapted to such characteristics. An usual approach to deal with the problem of imbalanced data sets is the use of a preprocessing step. In this paper we analyze the usefulness of the data complexity measures in order to evaluate the behavior of undersampling and oversampling methods. Two classical learning methods, C4.5 and PART, are considered over a wide range of imbalanced data sets built from real data. Specifically, oversampling techniques and an evolutionary undersampling one have been selected for the study. We extract behavior patterns from the results in the data complexity space defined by the measures, coding them as intervals. Then, we derive rules from the intervals that describe both good or bad behaviors of C4.5 and PART for the different preprocessing approaches, thus obtaining a complete characterization of the data sets and the differences between the oversampling and undersampling results. [ABSTRACT FROM AUTHOR]

This paper presents a novel classification approach that integrates fuzzy class association rules and support vector machines. A fuzzy discretization technique based on fuzzy c-means clustering algorithm is employed to transform the training set, particularly quantitative attributes, to a format appropriate for association rule mining. A hill-climbing procedure is adapted for automatic thresholds adjustment and fuzzy class association rules are mined accordingly. The compatibility between the generated rules and fuzzy patterns is considered to construct a set of feature vectors, which are used to generate a classifier. The reported test results show that compatibility rule-based feature vectors present a highly- qualified source of discrimination knowledge that can substantially impact the prediction power of the final classifier. In order to evaluate the applicability of the proposed method to a variety of domains, it is also utilized for the popular task of gene expression classification. Further, we show how this method provide biologists with an accurate and more understandable classifier model compared to other machine learning techniques. [ABSTRACT FROM AUTHOR]

Abstract  Aiming at the common support vector machine’s biased disadvantage and computational complexity, an unbiased least squares support vector machine (LSSVM) model is proposed in this paper. The model eliminates the bias item of LSSVM by improving the form of structure risk, then the unbiased least squares support vector classifier and the unbiased least squares support vector regression are deduced. Based on this model, we design a new learning algorithm using Cholesky factorization according to the characteristic of kernel function matrix, in this way the calculation of Lagrangian multipliers is greatly simplified. Several experiments on diffenert datasets are carried out, including the common datasets classification, synthetic aperture radar image automatic target recognition and chaotic time series prediction. The experimental results of correct recognition rate and the fitting precision testify that the unbiased LSSVM model has good universal ability and fitting accuracy, better generalization capability and stability, and have a great improvement in learning speed. [ABSTRACT FROM AUTHOR]

Automatic text classification is one of the most important tools in Information Retrieval. This paper presents a novel text classifier using positive and unlabeled examples. The primary challenge of this problem as compared with the classical text classification problem is that no labeled negative documents are available in the training example set. Firstly, we identify many more reliable negative documents by an improved 1-DNF algorithm with a very low error rate. Secondly, we build a set of classifiers by iteratively applying the SVM algorithm on a training data set, which is augmented during iteration. Thirdly, different from previous PU-oriented text classification works, we adopt the weighted vote of all classifiers generated in the iteration steps to construct the final classifier instead of choosing one of the classifiers as the final classifier. Finally, we discuss an approach to evaluate the weighted vote of all classifiers generated in the iteration steps to construct the final classifier based on PSO (Particle Swarm Optimization), which can discover the best combination of the weights. In addition, we built a focused crawler based on link-contexts guided by different classifiers to evaluate our method. Several comprehensive experiments have been conducted using the Reuters data set and thousands of web pages. Experimental results show that our method increases the performance (F1-measure) compared with PEBL, and a focused web crawler guided by our PSO-based classifier outperforms other several classifiers both in harvest rate and target recall. [ABSTRACT FROM AUTHOR]