Search

Around a third of the total population of Europe suffers from mental disorders. The use of electroencephalography (EEG) together with Machine Learning (ML) algorithms to diagnose mental disorders has recently been shown to be a prominent research area, as exposed by several reviews focused on the field. Nevertheless, previous to the application of ML algorithms, EEG data should be correctly preprocessed and prepared via Feature Engineering (FE). In fact, the choice of FE techniques can make the difference between an unusable ML model and a simple, effective model. In other words, it can be said that FE is crucial, especially when using complex, non-stationary data such as EEG. To this aim, in this paper we present a Systematic Mapping Study (SMS) focused on FE from EEG data used to identify mental disorders. Our SMS covers more than 900 papers, making it one of the most comprehensive to date, to the best of our knowledge. We gathered the mental disorder addressed, all the FE techniques used, and the Artificial Intelligence (AI) algorithm applied for classification from each paper. Our main contributions are: (i) we offer a starting point for new researchers on these topics, (ii) we extract the most used FE techniques to classify mental disorders, (iii) we show several graphical distributions of all used techniques, and (iv) we provide critical conclusions for detecting mental disorders. To provide a better overview of existing techniques, the FE process is divided into three parts: (i) signal transformation, (ii) feature extraction, and (iii) feature selection. Moreover, we classify and analyze the distribution of existing papers according to the mental disorder they treat, the FE processes used, and the ML techniques applied. As a result, we provide a valuable reference for the scientific community to identify which techniques have been proven and tested and where the gaps are located in the current state of the art. [ABSTRACT FROM AUTHOR]

Effective management of dementia requires the timely detection of mild cognitive impairment (MCI). This paper introduces a multi-objective optimization approach for selecting EEG channels (and features) for the purpose of detecting MCI. Firstly, each EEG signal from each channel is decomposed into subbands using either variational mode decomposition (VMD) or discrete wavelet transform (DWT). A feature is then extracted from each subband using one of the following measures: standard deviation, interquartile range, band power, Teager energy, Katz's and Higuchi's fractal dimensions, Shannon entropy, sure entropy, or threshold entropy. Different machine learning techniques are used to classify the features of MCI cases from those of healthy controls. The classifier's performance is validated using leave-one-subject-out (LOSO) cross-validation (CV). The non-dominated sorting genetic algorithm (NSGA)-II is designed with the aim of minimizing the number of EEG channels (or features) and maximizing classification accuracy. The performance is evaluated using a publicly available online dataset containing EEGs from 19 channels recorded from 24 participants. The results demonstrate a significant improvement in performance when utilizing the NSGA-II algorithm. By selecting only a few appropriate EEG channels, the LOSO CV-based results show a significant improvement compared to using all 19 channels. Additionally, the outcomes indicate that accuracy can be further improved by selecting suitable features from different channels. For instance, by combining VMD and Teager energy, the SVM accuracy obtained using all channels is 74.24%. Interestingly, when only five channels are selected using NSGA-II, the accuracy increases to 91.56%. The accuracy is further improved to 95.28% when using only 8 features selected from 7 channels. This demonstrates that by choosing informative features or channels while excluding noisy or irrelevant information, the impact of noise is reduced, resulting in improved accuracy. These promising findings indicate that, with a limited number of channels and features, accurate diagnosis of MCI is achievable, which opens the door for its application in clinical practice. [ABSTRACT FROM AUTHOR]

Internet of Things (IoT) devices are widely used but also vulnerable to cyberattacks that can cause security issues. To protect against this, machine learning approaches have been developed for network intrusion detection in IoT. These often use feature reduction techniques like feature selection or extraction before feeding data to models. This helps make detection efficient for real-time needs. This paper thoroughly compares feature extraction and selection for IoT network intrusion detection in machine learning-based attack classification framework. It looks at performance metrics like accuracy, f1-score, and runtime, etc. on the heterogenous IoT dataset named Network TON-IoT using binary and multiclass classification. Overall, feature extraction gives better detection performance than feature selection as the number of features is small. Moreover, extraction shows less feature reduction compared with that of selection, and is less sensitive to changes in the number of features. However, feature selection achieves less model training and inference time compared with its counterpart. Also, more space to improve the accuracy for selection than extraction when the number of features changes. This holds for both binary and multiclass classification. The study provides guidelines for selecting appropriate intrusion detection methods for particular scenarios. Before, the TON-IoT heterogeneous IoT dataset comparison and recommendations were overlooked. Overall, the research presents a thorough comparison of feature reduction techniques for machine learning-driven intrusion detection in IoT networks. [ABSTRACT FROM AUTHOR]

Features of data are much critical to the classification. However, when only small data are available, suitable features can not be easily obtained, easily leading to the bad classification performance. This paper propose a novel approach to automatically learns features from the irrelevant domain with much discriminative features for the given classification task. It first computes as the learning objectives the central vectors of each class in the irrelevant domain, and then uses machine learning method to automatically learn features for each sample in the target domain from these objectives. The merits of our method lie in that unlike the transfer learning, our method does not require the similarity between two domains. It can learn features from much discriminative domains. Its learned features are not limited to its original ones, unlike feature selection and feature extraction methods, so that the classification performance with the learned features can be better. Finally, our method is much general, simple, and efficient. Lots of experimental results validated the proposed method. [ABSTRACT FROM AUTHOR]

Diabetes retinopathy (DR) is one of the leading causes of blindness globally. Early detection of this condition is essential for preventing patients' loss of eyesight caused by diabetes mellitus being untreated for an extended period. This paper proposes the design of an augmented bioinspired multidomain feature extraction and selection model for diabetic retinopathy severity estimation using an ensemble learning process. The proposed approach initiates by identifying DR severity levels from retinal images that segment the optical disc, macula, blood vessels, exudates, and hemorrhages using an adaptive thresholding process. Once the images are segmented, multidomain features are extracted from the retinal images, including frequency, entropy, cosine, gabor, and wavelet components. These data were fed into a novel Modified Moth Flame Optimization-based feature selection method that assisted in optimal feature selection. Finally, an ensemble model using various ML (machine learning) algorithms, which included Naive Bayes, K-Nearest Neighbours, Support Vector Machine, Multilayer Perceptron, Random Forests, and Logistic Regression were used to identify the various severity complications of DR. The experiments on different openly accessible data sources have shown that the proposed method outperformed conventional methods and achieved an Accuracy of 96.5% in identifying DR severity levels. [ABSTRACT FROM AUTHOR]

Ultrasonic testing (UT) is increasingly combined with machine learning (ML) techniques for intelligently identifying damage. Extracting significant features from UT data is essential for efficient defect characterization. Moreover, the hidden physics behind ML is unexplained, reducing the generalization capability and versatility of ML methods in UT. In this paper, a generally applicable ML framework based on the model interpretation strategy is proposed to improve the detection accuracy and computational efficiency of UT. Firstly, multi-domain features are extracted from the UT signals with signal processing techniques to construct an initial feature space. Subsequently, a feature selection method based on model interpretable strategy (FS-MIS) is innovatively developed by integrating Shapley additive explanation (SHAP), filter method, embedded method and wrapper method. The most effective ML model and the optimal feature subset with better correlation to the target defects are determined self-adaptively. The proposed framework is validated by identifying and locating side-drilled holes (SDHs) with 0.5λ central distance and different depths. An ultrasonic array probe is adopted to acquire FMC datasets from several aluminum alloy specimens containing two SDHs by experiments. The optimal feature subset selected by FS-MIS is set as the input of the chosen ML model to train and predict the times of arrival (ToAs) of the scattered waves emitted by adjacent SDHs. The experimental results demonstrate that the relative errors of the predicted ToAs are all below 3.67% with an average error of 0.25%, significantly improving the time resolution of UT signals. On this basis, the predicted ToAs are assigned to the corresponding original signals for decoupling overlapped pulse-echoes and reconstructing high-resolution FMC datasets. The imaging resolution is enhanced to 0.5λ by implementing the total focusing method (TFM). The relative errors of hole depths and central distance are no more than 0.51% and 3.57%, respectively. Finally, the superior performance of the proposed FS-MIS is validated by comparing it with initial feature space and conventional dimensionality reduction techniques. [ABSTRACT FROM AUTHOR]

In stock market forecasting, the identification of critical features that affect the performance of machine learning (ML) models is crucial to achieve accurate stock price predictions. Several review papers in the literature have focused on various ML, statistical, and deep learning-based methods used in stock market forecasting. However, no survey study has explored feature selection and extraction techniques for stock market forecasting. This survey presents a detailed analysis of 32 research works that use a combination of feature study and ML approaches in various stock market applications. We conduct a systematic search for articles in the Scopus and Web of Science databases for the years 2011–2022. We review a variety of feature selection and feature extraction approaches that have been successfully applied in the stock market analyses presented in the articles. We also describe the combination of feature analysis techniques and ML methods and evaluate their performance. Moreover, we present other survey articles, stock market input and output data, and analyses based on various factors. We find that correlation criteria, random forest, principal component analysis, and autoencoder are the most widely used feature selection and extraction techniques with the best prediction accuracy for various stock market applications. [ABSTRACT FROM AUTHOR]

As basic research, it has also received increasing attention from people that the "curse of dimensionality" will lead to increase the cost of data storage and computing; it also influences the efficiency and accuracy of dealing with problems. Feature dimensionality reduction as a key link in the process of pattern recognition has become one hot and difficulty spot in the field of pattern recognition, machine learning and data mining. It is one of the most challenging research fields, which has been favored by most of the scholars' attention. How to implement "low loss" in the process of feature dimension reduction, keep the nature of the original data, find out the best mapping and get the optimal low dimensional data are the keys aims of the research. In this paper, two-dimensionality reduction methods, feature selection and feature extraction, are introduced; the current mainstream dimensionality reduction algorithms are analyzed, including the method for small sample and method based on deep learning. For each algorithm, examples of their application are given and the advantages and disadvantages of these methods are evaluated. [ABSTRACT FROM AUTHOR]

Recently, with the advance in information technology, pure data-driven approaches such as machine learnings have been widely applied in status diagnosis. However, the accuracy of those predictions strongly relies on the original data, which largely depends on the selected sensors and signal features. Furthermore, for unsupervised machine learning schemes, although it could avoid the concern of labeling in training, it lacks a quantified evaluation of the prediction results. These concerns significantly limit the effectiveness of modern machine learning and thus should be investigated. Meanwhile, ball bearings are fundamental key machine elements in rotating machinery and their condition monitoring should be critical for both quality control and longevity assessment. In this paper, by utilizing ball bearing failure diagnosis as the main theme, the flow of feature selection and evaluation, as well as the evaluation flow for multiple failure diagnosis, is developed for accessing the status of bearings in their imbalance, lubrication, and grease contamination levels based on unsupervised machine learning. The experimental results indicated that with proper feature selection, the failure identification could be more definite. Finally, a novel model based on the second norm to quantify the classification level of each cluster in hyperspace is proposed as the measure for unsupervised machine learning as the basis for performance evaluation and optimization of unsupervised machine learning schemes and should benefit related machine reliability evaluation studies and applications. [ABSTRACT FROM AUTHOR]

Dimension reduction is a preprocessing step in machine learning for eliminating undesirable features and increasing learning accuracy. In order to reduce the redundant features, there are data representation methods, each of which has its own advantages. On the other hand, big data with imbalanced classes is one of the most important issues in pattern recognition and machine learning. In this paper, a method is proposed in the form of a cost-sensitive optimization problem which implements the process of selecting and extracting the features simultaneously. The feature extraction phase is based on reducing error and maintaining geometric relationships between data by solving a manifold learning optimization problem. In the feature selection phase, the cost-sensitive optimization problem is adopted based on minimizing the upper limit of the generalization error. Finally, the optimization problem which is constituted from the above two problems is solved by adding a cost-sensitive term to create a balance between classes without manipulating the data. To evaluate the results of the feature reduction, the multi-class linear SVM classifier is used on the reduced data. The proposed method is compared with some other approaches on 21 datasets from the UCI learning repository, microarrays and high-dimensional datasets, as well as imbalanced datasets from the KEEL repository. The results indicate the significant efficiency of the proposed method compared to some similar approaches. [ABSTRACT FROM AUTHOR]

Microstructure determines the most important factors that influence all aspects of the physical properties of the metal. Machine learning based systems allow us to look at the images to find the features of microstructure images which will be useful for classifying such images. These classification outcomes are the fundamental data for many material scientists. However, handcrafted feature vectors extracted by some means may involve a significant amount of irrelevant and redundant features, which may lead to misclassification of the microstructural images. In this paper, at first, a modified version of texture-based feature descriptor, Local Tetra Pattern (LTrP), which is named as Uniform variant of LTrP (ULTrP) is used to extract the features from the microstructural images. Then a feature selection algorithm based on Genetic Algorithm (GA), named as Diversification of Population (DP) in GA (DPGA), is proposed which is applied on ULTrP to remove the possible redundant features present therein. To assess fitness of the candidate solutions, instead of applying a learning algorithm, which is a common trend, the proposed DPGA uses an ensemble of three filter ranking methods. Impressive outcomes obtained by evaluating the proposed classification framework on a standard 7-class microstructural image dataset confirm its superiority over some state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Speech enhancement has substantial interest in the utilization of speaker identification, video-conference, speech transmission through communication channels, speech-based biometric system, mobile phones, hearing aids, microphones, voice conversion etc. Pattern mining methods have a vital step in the growth of speech enhancement schemes. To design a successful speech enhancement system consideration to the background noise processing is needed. A substantial number of methods from traditional techniques and machine learning have been utilized to process and remove the additive noise from a speech signal. With the advancement of machine learning and deep learning, classification of speech has become more significant. Methods of speech enhancement consist of different stages, such as feature extraction of the input speech signal, feature selection, feature selection followed by classification. Deep learning techniques are also an emerging field in the classification domain, which is discussed in this review. The intention of this paper is to provide a state-of-the-art summary and present approaches for using the widely used machine learning and deep learning methods to detect the challenges along with future research directions of speech enhancement systems. [ABSTRACT FROM AUTHOR]

Recognizing an individual's preference state for potential romantic partners based on electroencephalogram (EEG) signals holds significant practical value in enhancing matchmaking success rates and preventing romance fraud. Despite some progress has been made in this field, challenges such as high-dimensional feature space and channel redundancy limited the technology's practical application. The aim of this study is to explore the most discriminative EEG features and channels, in order to enhance the recognition performance of the system, while maximizing the portable and practical value of EEG-based systems for recognizing romantic attraction. To achieve this goal, we first conducted an interesting simulated dating experiment to collect the necessary data. Next, EEG features were extracted from various dimensions, including band power and asymmetry index features. Then, we introduced a novel method for EEG feature and channel selection that combines the sequential forward selection (SFS) algorithm with the frequency-based feature subset integration (FFSI) algorithm. Finally, we used the random forest classifier (RFC) to determine a person's preference state for potential romantic partners. Experimental results indicate that the optimal feature subset, selected using the SFS-FFSI method, attained an average classification accuracy of 88.42%. Notably, these features were predominantly sourced from asymmetry index features of electrodes situated in the frontal, parietal, and occipital lobes. [ABSTRACT FROM AUTHOR]

Autism Spectrum Disorder (ASD) is characterized as a neurodevelopmental disorder with a heterogeneous nature, influenced by genetics and exhibiting diverse clinical presentations. In this study, we dissect Autism Spectrum Disorder (ASD) into its behavioral components, mirroring the diagnostic process used in clinical settings. Morphological features are extracted from magnetic resonance imaging (MRI) scans, found in the publicly available dataset ABIDE II, identifying the most discriminative features that differentiate ASD within various behavioral domains. Then, each subject is categorized as having severe, moderate, or mild ASD, or typical neurodevelopment (TD), based on the behavioral domains of the Social Responsiveness Scale (SRS). Through this study, multiple artificial intelligence (AI) models are utilized for feature selection and classifying each ASD severity and behavioural group. A multivariate feature selection algorithm, investigating four different classifiers with linear and non-linear hypotheses, is applied iteratively while shuffling the training-validation subjects to find the set of cortical regions with statistically significant association with ASD. A set of six classifiers are optimized and trained on the selected set of features using 5-fold cross-validation for the purpose of severity classification for each behavioural group. Our AI-based model achieved an average accuracy of 96%, computed as the mean accuracy across the top-performing AI models for feature selection and severity classification across the different behavioral groups. The proposed AI model has the ability to accurately differentiate between the functionalities of specific brain regions, such as the left and right caudal middle frontal regions. We propose an AI-based model that dissects ASD into behavioral components. For each behavioral component, the AI-based model is capable of identifying the brain regions which are associated with ASD as well as utilizing those regions for diagnosis. The proposed system can increase the speed and accuracy of the diagnostic process and result in improved outcomes for individuals with ASD, highlighting the potential of AI in this area. [ABSTRACT FROM AUTHOR]

Over the past few years, the processing of motor imagery (MI) electroencephalography (EEG) signals has been attracted for developing brain-computer interface (BCI) applications, since feature extraction and classification of these signals are extremely difficult due to the inherent complexity and tendency to artifact properties of them. The BCI systems can provide a direct interaction pathway/channel between the brain and a peripheral device, hence the MI EEG-based BCI systems seem crucial to control external devices for patients suffering from motor disabilities. The current study presents a semi-supervised model based on three-stage feature extraction and machine learning algorithms for MI EEG signal classification in order to improve the classification accuracy with smaller number of deep features for distinguishing right- and left-hand MI tasks. Stockwell transform is employed at the first phase of the proposed feature extraction method to generate two-dimensional time–frequency maps (TFMs) from one-dimensional EEG signals. Next, the convolutional neural network (CNN) is applied to find deep feature sets from TFMs. Then, the semi-supervised discriminant analysis (SDA) is utilized to minimize the number of descriptors. Finally, the performance of five classifiers, including support vector machine, discriminant analysis, k-nearest neighbor, decision tree, random forest, and the fusion of them are compared. The hyperparameters of SDA and mentioned classifiers are optimized by Bayesian optimization to maximize the accuracy. The presented model is validated using BCI competition II dataset III and BCI competition IV dataset 2b. The performance metrics of the proposed method indicate its efficiency for classifying MI EEG signals. [ABSTRACT FROM AUTHOR]

Radiomics-based machine learning classifiers have shown potential for detecting bone metastases (BM) and for evaluating BM response to radiotherapy (RT). However, current radiomics models require large datasets of images with expert-segmented 3D regions of interest (ROIs). Full ROI segmentation is time consuming and oncologists often outline just RT treatment fields in clinical practice. This presents a challenge for real-world radiomics research. As such, a method that simplifies BM identification but does not compromise the power of radiomics is needed. The objective of this study was to investigate the feasibility of radiomics models for BM detection using lesion-center-based geometric ROIs. The planning-CT images of 170 patients with non-metastatic lung cancer and 189 patients with spinal BM were used. The point locations of 631 BM and 674 healthy bone (HB) regions were identified by experts. ROIs with various geometric shapes were centered and automatically delineated on the identified locations, and 107 radiomics features were extracted. Various feature selection methods and machine learning classifiers were evaluated. Our point-based radiomics pipeline was successful in differentiating BM from HB. Lesion-center-based segmentation approach greatly simplifies the process of preparing images for use in radiomics studies and avoids the bottleneck of full ROI segmentation. [ABSTRACT FROM AUTHOR]

Complete pathological response (pCR) to neoadjuvant chemotherapy (NAC) is a prognostic factor for breast cancer (BC) patients and is correlated with improved survival. However, pCR rates are variable to standard NAC, depending on BC subtype. This study investigates quantitative digital histopathology coupled with machine learning (ML) to predict NAC response a priori. Clinicopathologic data and digitized slides of BC core needle biopsies were collected from 149 patients treated with NAC. The nuclei within the tumor regions were segmented on the histology images of biopsy samples using a weighted U-Net model. Five pathomic feature subsets were extracted from segmented digitized samples, including the morphological, intensity-based, texture, graph-based and wavelet features. Seven ML experiments were conducted with different feature sets to develop a prediction model of therapy response using a gradient boosting machine with decision trees. The models were trained and optimized using a five-fold cross validation on the training data and evaluated using an unseen independent test set. The prediction model developed with the best clinical features (tumor size, tumor grade, age, and ER, PR, HER2 status) demonstrated an area under the ROC curve (AUC) of 0.73. Various pathomic feature subsets resulted in models with AUCs in the range of 0.67 and 0.87, with the best results associated with the graph-based and wavelet features. The selected features among all subsets of the pathomic and clinicopathologic features included four wavelet and three graph-based features and no clinical features. The predictive model developed with these features outperformed the other models, with an AUC of 0.90, a sensitivity of 85% and a specificity of 82% on the independent test set. The results demonstrated the potential of quantitative digital histopathology features integrated with ML methods in predicting BC response to NAC. This study is a step forward towards precision oncology for BC patients to potentially guide future therapies. [ABSTRACT FROM AUTHOR]