A Tri-Objective Method for Bi-Objective Feature Selection in Classification.

<p>Classification aims to identify a class label of an instance according to the information from its characteristics or features. Unfortunately, many classification problems have a large feature set containing irrelevant and redundant features, which reduce the classification performance. In order to address the above problem, feature selection is proposed to select a small subset of relevant features. There are three main types of feature selection methods, i.e. wrapper, embedded and filter approaches. Wrappers use a classification algorithm to evaluate candidate feature subsets. In embedded approaches, the selection process is embedded in the training process of a classification algorithm. Different from the other two approaches, filters do not involve any classification algorithm during the selection process. Feature selection is an important process but it is not an easy task due to its large search space and complex feature interactions. Because of the potential global search ability, Evolutionary Computation (EC), especially Particle Swarm Optimization (PSO), has been widely and successfully applied to feature selection. However, there is potential to improve the effectiveness and efficiency of EC-based feature selection. The overall goal of this thesis is to investigate and improve the capability of EC for feature selection to select small feature subsets while maintaining or even improving the classification performance compared to using all features. Different aspects of feature selection are considered in this thesis such as the number of objectives (single-objective/multi-objective), the fitness function (filter/wrapper), and the searching mechanism. This thesis introduces a new fitness function based on mutual information which is calculated by an estimation approach instead of the traditional counting approach. Results show that the estimation approach works well on both continuous and discrete data. More importantly, mutual information calculated by the estimation approach can capture feature interactions better than the traditional counting approach. This thesis develops a novel binary PSO algorithm, which is the first work to redefine some core concepts of PSO such as velocity and momentum to suit the characteristics of binary search spaces. Experimental results show that the proposed binary PSO algorithm evolve better solutions than other binary EC algorithms when the search spaces are large and complex. Specifically, on feature selection, the proposed binary PSO algorithm can select smaller feature subsets with similar or better classification accuracies, especially when there are a large number of features. This thesis proposes surrogate models for wrapper-based feature selection. The surrogate models use surrogate training sets which are subsets of informative instances selected from the training set. Experimental results show that the proposed surrogate models assist PSO to reduce the computational cost while maintaining or even improving the classification performance compared to using only the original training set. The thesis develops the first wrapper-based multi-objective feature selection algorithm using MOEA/D. A new decomposition strategy using multiple reference points for MOEA/D is designed, which can deal with different characteristics of multi-objective feature selection such as highly discontinuous Pareto fronts and complex relationships between objectives. The experimental results show that the proposed algorithm can evolve more diverse non-dominated sets than other multi-objective algorithms. This thesis introduces the first PSO-based feature selection algorithm for transfer learning. In the proposed algorithm, the fitness function uses classification performance to reduce the differences between domains while maintaining the discriminative ability on the target domain. The experimental results show that the proposed algorithm can select feature subsets which achieve better classification performance than four state-of-the-art feature-based transfer learning algorithms.</p>

<p>Classification problems often have a large number of features, but not all of them are useful for classification. Irrelevant and redundant features may even reduce the classification accuracy. Feature selection is a process of selecting a subset of relevant features, which can decrease the dimensionality, shorten the running time, and/or improve the classification accuracy. There are two types of feature selection approaches, i.e. wrapper and filter approaches. Their main difference is that wrappers use a classification algorithm to evaluate the goodness of the features during the feature selection process while filters are independent of any classification algorithm. Feature selection is a difficult task because of feature interactions and the large search space. Existing feature selection methods suffer from different problems, such as stagnation in local optima and high computational cost. Evolutionary computation (EC) techniques are well-known global search algorithms. Particle swarm optimisation (PSO) is an EC technique that is computationally less expensive and can converge faster than other methods. PSO has been successfully applied to many areas, but its potential for feature selection has not been fully investigated. The overall goal of this thesis is to investigate and improve the capability of PSO for feature selection to select a smaller number of features and achieve similar or better classification performance than using all features. This thesis investigates the use of PSO for both wrapper and filter, and for both single objective and multi-objective feature selection, and also investigates the differences between wrappers and filters. This thesis proposes a new PSO based wrapper, single objective feature selection approach by developing new initialisation and updating mechanisms. The results show that by considering the number of features in the initialisation and updating procedures, the new algorithm can improve the classification performance, reduce the number of features and decrease computational time. This thesis develops the first PSO based wrapper multi-objective feature selection approach, which aims to maximise the classification accuracy and simultaneously minimise the number of features. The results show that the proposed multi-objective algorithm can obtain more and better feature subsets than single objective algorithms, and outperform other well-known EC based multi-objective feature selection algorithms. This thesis develops a filter, single objective feature selection approach based on PSO and information theory. Two measures are proposed to evaluate the relevance of the selected features based on each pair of features and a group of features, respectively. The results show that PSO and information based algorithms can successfully address feature selection tasks. The group based method achieves higher classification accuracies, but the pair based method is faster and selects smaller feature subsets. This thesis proposes the first PSO based multi-objective filter feature selection approach using information based measures. This work is also the first work using other two well-known multi-objective EC algorithms in filter feature selection, which are also used to compare the performance of the PSO based approach. The results show that the PSO based multiobjective filter approach can successfully address feature selection problems, outperform single objective filter algorithms and achieve better classification performance than other multi-objective algorithms. This thesis investigates the difference between wrapper and filter approaches in terms of the classification performance and computational time, and also examines the generality of wrappers. The results show that wrappers generally achieve better or similar classification performance than filters, but do not always need longer computational time than filters. The results also show that wrappers built with simple classification algorithms can be general to other classification algorithms.</p>

A new hybrid filter/wrapper algorithm for feature selection in classification

Classification has been widely studied due to its practical applications. Feature selection aims to improve the classification accuracy by selecting a small feature subset from the original full feature set. However, identification of relevant features is not trivial due to the large search space. Particle swarm optimisation (PSO) is an efficient meta-heuristic algorithm which has shown to be promising in feature selection. However, traditional PSO uses its personal best experience and its historical best experience to determine its search direction, but this learning strategy may limit its performance for feature selection due to the premature convergence. Therefore, the potential of PSO needs to be further explored. In this paper, a new evolutionary learning algorithm termed hybridising PSO with differential evolution (HPSO-DE) is proposed to develop new feature selection methods. In HPSO-DE, differential evolution is applied to breed promising and efficient exemplars for PSO to guide its search, which is expected to not only preserve the diversity of the population but also guide particles to fly to promising areas. HPSO-DE is compared with three classic PSO variants and five traditional feature selection methods on 15 classification problems. The results show that the proposed algorithm can effectively achieve a higher classification accuracy with a smaller feature subset than the compared methods.

A discrete bacterial algorithm for feature selection in classification of microarray gene expression cancer data

Computer-aided diagnosis has the potential of increasing diagnostic accuracy by providing a second reading to radiologists. In many computerized schemes, numerous features can be extracted to describe suspect image regions. A subset of these features is then employed in a data classifier to determine whether the suspect region is abnormal or normal. Different subsets of features will, in general, result in different classification performances. A feature selection method is often used to determine an "optimal" subset of features to use with a particular classifier. A classifier performance measure (such as the area under the receiver operating characteristic curve) must be incorporated into this feature selection process. With limited datasets, however, there is a distribution in the classifier performance measure for a given classifier and subset of features. In this paper, we investigate the variation in the selected subset of "optimal" features as compared with the true optimal subset of features caused by this distribution of classifier performance. We consider examples in which the probability that the optimal subset of features is selected can be analytically computed. We show the dependence of this probability on the dataset sample size, the total number of features from which to select, the number of features selected, and the performance of the true optimal subset. Once a subset of features has been selected, the parameters of the data classifier must be determined. We show that, with limited datasets and/or a large number of features from which to choose, bias is introduced if the classifier parameters are determined using the same data that were employed to select the "optimal" subset of features.

With the rapid development of artificial intelligence in recent years, the research on image processing, text mining, and genome informatics has gradually deepened, and the mining of large-scale databases has begun to receive more and more attention. The objects of data mining have also become more complex, and the data dimensions of mining objects have become higher and higher. Compared with the ultra-high data dimensions, the number of samples available for analysis is too small, resulting in the production of high-dimensional small sample data. High-dimensional small sample data will bring serious dimensional disasters to the mining process. Through feature selection, redundancy and noise features in high-dimensional small sample data can be effectively eliminated, avoiding dimensional disasters and improving the actual efficiency of mining algorithms. However, the existing feature selection methods emphasize the classification or clustering performance of the feature selection results and ignore the stability of the feature selection results, which will lead to unstable feature selection results, and it is difficult to obtain real and understandable features. Based on the traditional feature selection method, this paper proposes an ensemble feature selection method, Random Bits Forest Recursive Clustering Eliminate (RBF-RCE) feature selection method, combined with multiple sets of basic classifiers to carry out parallel learning and screen out the best feature classification results, optimizes the classification performance of traditional feature selection methods, and can also improve the stability of feature selection. Then, this paper analyzes the reasons for the instability of feature selection and introduces a feature selection stability measurement method, the Intersection Measurement (IM), to evaluate whether the feature selection process is stable. The effectiveness of the proposed method is verified by experiments on several groups of high-dimensional small sample data sets.

Feature selection aims to select a subset of relevant features from typically a large number of original features, which is a difficult task due to the large search space. Particle swarm optimisation (PSO) is a powerful search technique, but there are some limitations on using the standard PSO for feature selection. This paper proposes a new PSO based feature selection approach, which introduces an external archive to store promising solutions obtained during the search process. The solutions in the archive serve as potential leaders (i.e. global best, gbest) to guide the swarm to search for an optimal feature subset with the lowest classification error rate and a smaller number of features. The proposed approach has two specific methods, PSOArR and PSOArRWS, where PSOArR randomly selects gbest from the archive and PSOArRWS uses the roulette wheel selection to select gbest considering both the classification error rate and also considering the number of selected features. Experiments on twelve benchmark datasets show that both PSOArR and PSOArRWS can successfully select a smaller number of features and achieve similar or better classification performance than using all features. PSOArR and PSOArRWS outperform a PSO based algorithm without using an archive and two traditional feature selection methods. The performance of PSOArR and PSOArRWS are similar to each other.

Fault diagnosis methods based on machine learning have made great progress for rotating machinery. The main steps of the machine learning process involve feature extraction, selection, and classification. Feature selection improves classification accuracy and reduces diagnosis time by selecting the better features. Due to the difficulty of traditional feature selection methods to rank the feature importance of each class, the best subset of features could hardly be obtained. Therefore, this article proposes a new feature selection method to address the shortcomings of the above traditional methods, called Feature Ranking based on Optimal Class Distance Ratio (FROCDR), which can choose the optimal features between every two classes of samples to obtain feature ranking that is conducive to classification. In order to comprehensively extract the fault information in the signal, the multiscale analysis and the variational mode decomposition (VMD) method are applied to process the vibration signals under different scales and frequency bands, and the processed signals are visualized by symmetrized dot pattern (SDP). In addition, features are extracted from the obtained SDP images, and the proposed FROCDR method is used to select the best subset of features. The final diagnosis task is accomplished by a random forest (RF) classifier. Experimental cases of bearing and gear data show that the proposed method has higher diagnostic accuracy and stability.

In classification, feature selection is an important, but difficult problem. Particle swarm optimisation (PSO) is an efficient evolutionary computation technique. However, the traditional personal best and global best updating mechanism in PSO limits its performance for feature selection and the potential of PSO for feature selection has not been fully investigated. This paper proposes a new initialisation strategy and a new personal best and global best updating mechanism in PSO to develop a novel feature selection algorithm with the goals of minimising the number of features, maximising the classification performance and simultaneously reducing the computational time. The proposed algorithm is compared with two traditional feature selection methods, a PSO based method with the goal of only maximising the classification performance, and a PSO based two-stage algorithm considering both the number of features and the classification performance. Experiments on eight benchmark datasets show that the proposed algorithm can automatically evolve a feature subset with a smaller number of features and higher classification performance than using all features. The proposed algorithm achieves significantly better classification performance than the two traditional methods. The proposed algorithm also outperforms the two PSO based feature selection algorithms in terms of the classification performance, the number of features and the computational cost.

Feature selection is one of the most significant procedures in machine learning algorithms. It is particularly to improve the performance and prediction accuracy for complex data classification. This paper discusses a hybrid feature selection technique with the decision tree-based classification algorithm. The feature selected using information gain (IG) is combined with the features selected from ReliefF which generates the resultant feature subset. Then the resultant feature subset is in turn combined with a correlation-based feature selection (CFS) method to generate the aggregated feature subset. To perform classification accuracy on the aggregated feature subset, different decision trees-based classification algorithm such as C4.5, decision stumps, naive Bayes tree, and random forest with ten-fold cross-validation have been deployed. To check the prediction accuracy of the proposed work eight different multilevel University of California, Irvine (UCI) machine learning datasets have been used with minimum to maximum numbers of features. The main objective of the hybrid feature selection is to improve the classification accuracy, prediction and to reduce the execution time using standard datasets.

• Neural Network feature selection methodology for both numerical and categorical data. • Embedded feature selection provides model and feature subset in a single training. • Novel feature embedding for dealing with high-cardinality categorical features. • Validation of the methodology on several open and real industry dataset. • Comparison with several state-of-the-art feature selection methodologie. In an era of effortless data collection, the impact of machine learning — especially neural networks (NNs) — is undeniable. As datasets grow in size and complexity, efficiently handling mixed data types, including categorical and numerical features, becomes critical. Feature encoding and selection play a key role in improving NN performance, efficiency, interpretability, and generalisation. This paper presents GLEm-Net (Grouped Lasso with Embeddings Network), a novel NN-based approach that seamlessly integrates feature encoding and selection directly into the training process. GLEm-Net uses embedding layers to process categorical features with high cardinality, simplifying the model and improving generalisation. By extending the grouped Lasso regularisation to explicitly consider categorical features, GLEm-Net automatically identifies the most relevant features during training and returns them to the analyst. We evaluate GLEm-Net on open and proprietary industry datasets and compare it to state-of-the-art feature selection methodologies. Results show that GLEm-Net adapts to each dataset by allowing the NN to directly select subsets of most important features, offering on par performance with the best state-of-the-art feature selection methods, while eliminating the need for the external feature encoding and selection steps that are now incorporated in the NN training stage.

© 2015 IEEE. Feature selection often involves two conflicting objectives of minimizing the feature subset size and the maximizing the classification accuracy. In this paper, a multi-objective artificial bee colony (MOABC) framework is developed for feature selection in classification, and a new fuzzy mutual information based criterion is proposed to evaluate the relevance of feature subsets. Three new multi-objective feature selection approaches are proposed by integrating MOABC with three filter fitness evaluation criteria, which are mutual information, fuzzy mutual information and the proposed fuzzy mutual information. The proposed multi-objective feature selection approaches are examined by comparing them with three single-objective ABC-based feature selection approaches on six commonly used datasets. The results show that the proposed approaches are able to achieve better performance than the original feature set in terms of the classification accuracy and the number of features. By using the same evaluation criterion, the proposed multi-objective algorithms generally perform better than the single-objective methods, especially in terms of reducing the number of features. Furthermore, the proposed fuzzy mutual information criterion outperforms mutual information and the original fuzzy mutual information in both single-objective and multi-objective manners. This work is the first study on multi-objective ABC for filter feature selection in classification, which shows that multi-objective ABC can be effectively used to address feature selection problems.<div><br></div><div><div><table><tr><td>© 2015 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.</td></tr></table></div></div>

QSAR analysis of diaryl COX-2 inhibitors: Comparison of feature selection and train-test data selection methods

Proposes a node saliency measure and a backpropagation type of algorithm to compute the node saliencies. A node-pruning procedure is then presented to remove insalient nodes in the network to create a parsimonious network. The optimal/suboptimal subset of features are simultaneously selected by the network. The performance of the proposed approach for feature selection is compared with Whitney's feature selection method. One advantage of the node-pruning procedure over classical feature selection methods is that the node-pruning procedure can simultaneously "optimize" both the feature set and the classifier, while classical feature selection methods select the "best" subset of features with respect to a fixed classifier.