Search

Internet of Things (IoTs) has been playing an important role in many sectors, such as smart cities, smart agriculture, smart healthcare, and smart manufacturing. However, IoT devices are highly vulnerable to cyber-attacks, which may result in security breaches and data leakages. To effectively prevent these attacks, a variety of machine learning-based network intrusion detection methods for IoT networks have been developed, which often rely on either feature extraction or feature selection techniques for reducing the dimension of input data before being fed into machine learning models. This aims to make the detection complexity low enough for real-time operations, which is particularly vital in any intrusion detection systems. This paper provides a comprehensive comparison between these two feature reduction methods of intrusion detection in terms of various performance metrics, namely, precision rate, recall rate, detection accuracy, as well as runtime complexity, in the presence of the modern UNSW-NB15 dataset as well as both binary and multiclass classification. For example, in general, the feature selection method not only provides better detection performance but also lower training and inference time compared to its feature extraction counterpart, especially when the number of reduced features K increases. However, the feature extraction method is much more reliable than its selection counterpart, particularly when K is very small, such as K = 4 . Additionally, feature extraction is less sensitive to changing the number of reduced features K than feature selection, and this holds true for both binary and multiclass classifications. Based on this comparison, we provide a useful guideline for selecting a suitable intrusion detection type for each specific scenario, as detailed in Table 14 at the end of Sect. 4. Note that such the comparison between feature selection and feature extraction over UNSW-NB15 as well as theoretical guideline have been overlooked in the literature. [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]

Considering that serious hand function damage will greatly affect the daily life of patients, its recovery mainly depends on the regular inspection and manual training of medical staff, and medical monitoring based on bioelectric signals can largely replace manual re-examination as autonomous rehabilitation technology. So, for the rationality of feature selection and the diversity of classifier design in the gesture recognition process based on electromyography (EMG) signals, this paper proposes a hand medical monitoring system based on feature selection method of feature subset average recognition rate and optimal machine learning algorithm selection, which mainly depends on the prediction of hand movement. At the same time, since most experiments are conducted in different non-public proprietary databases, the comparison between various gesture recognition methods can only be analyzed to a certain extent. Therefore, this paper uses the DB1 dataset in the large publicly available NinaPro database and combines with presently well-known 11 time-domain (TD) features and 5 frequency domain (FD) features, then uses the support vector machine (SVM) classifier to comparative analysis total 136 feature combinations under various feature numbers. Under the premise of ensuring the overall recognition rate of electromyography gesture, this method will be able to reduce the number of features in feature set, according to the change of the average remove redundant features, and construct an optimal reduced EMG feature set. Finally, through the four common hand motion classifiers based on machine learning: SVM, back propagation neural network, linear discriminant analysis, and K-nearest neighbor, this paper tests and verifies the separability of the optimal reduced EMG feature set, and based on this, selects the optimal hand motion classifier to build the optimal hand motion recognition system, improve the hand medical monitoring system, and provide technical reference for the construction of real-time medical monitoring system. [ABSTRACT FROM AUTHOR]

Feature selection is an important component of the machine learning domain, which selects the ideal subset of characteristics relative to the target data by omitting irrelevant data. For a given number of features, there are 2n possible feature subsets, making it challenging to select the optimal set of features from a dataset via conventional feature selection approaches. We opted to investigate glaucoma infection since the number of individuals with this disease is rising quickly around the world. The goal of this study is to use the feature set (features derived from fundus images of benchmark datasets) to classify images into two classes (infected and normal) and to select the fewest features (feature selection) to achieve the best performance on various efficiency measuring metrics. In light of this, the paper implements and recommends a metaheuristics-based technique for feature selection based on emperor penguin optimization, bacterial foraging optimization, and proposes their hybrid algorithm. From the retinal fundus benchmark images, a total of 36 features were extracted. The proposed technique for selecting features minimizes the number of features while improving classification accuracy. Six machine learning classifiers classify on the basis of a smaller subset of features provided by these three optimization techniques. In addition to the execution time, eight statistically based performance metrics are calculated. The hybrid optimization technique combined with random forest achieves the highest accuracy, up to 0.95410. Because the proposed medical decision support system is effective and ensures trustworthy decision-making for glaucoma screening, it might be utilized by medical practitioners as a second opinion tool, as well as assist overworked expert ophthalmologists and prevent individuals from losing their eyesight. [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]

Human activity recognition (HAR) using inertial motion data has gained a lot of momentum in recent years both in research and industrial applications. From the abstract perspective, this has been driven by the rapid dynamics for building intelligent, smart environments, and ubiquitous systems that cover all aspects of human life including healthcare, sports, manufacturing, commerce, etc., which necessitate and subsume activity recognition aiming at recognizing the actions, characteristics, and goals of one or more agent(s) from a temporal series of observations streamed from one or more sensors. From a more concrete and seemingly orthogonal perspective, such momentum has been driven by the ubiquity of inertial motion sensors on-board mobile and wearable devices including smartphones, smartwatches, etc. In this paper we give an introductory and a comprehensive survey to the subject from a given perspective. We focus on a subset of topics, that we think are major, that will have significant and influential impacts on the future research and industrial-scale deployment of HAR systems. These include: (1) a comprehensive and detailed description of the inertial motion benchmark datasets that are publicly available and/or accessible, (2) feature selection and extraction techniques and the corresponding learning methods used to build workable HAR systems; we survey classical handcrafted datasets as well as data-oriented automatic representation learning approach to the subject, (3) transfer learning as a way to overcome many hurdles in actual deployments of HAR systems on a large scale, (4) embedded implementations of HAR systems on mobile and/or wearable devices, and finally (5) we touch on adversarial attacks, a topic that is essentially related to the security and privacy of HAR systems. As the field is very huge and diverse, this article is by no means comprehensive; it is though meant to provide a logically and conceptually rather complete picture to advanced practitioners, as well as to present a readable guided introduction to newcomers. Our logical and conceptual perspectives mimic the typical data science pipeline for state-of-the-art AI-based systems. [ABSTRACT FROM AUTHOR]

The recent trend in network intrusion detection leverages key features of machine learning (ML) algorithms to detect network traffic anomalies. Network traffic flows contain high dimensional features which significantly affect data-driven approaches. Therefore, the performance of ML-based approaches mainly depends on the appropriate set of features of network data. Different feature selection and extraction methods are extensively employed to attain the informative and compact set of features. Existing methods often suffer from achieving the expected performance due to the lacking of effectively removing redundant features as well as incorporating features with complementary information. In this paper, we present a cluster-based feature extraction method using Mahalanobis distance (cFEM) that clusters the correlated features and extracts new feature representations based on a distance metric. The extracted features on the transformed dimensions are employed to train different machine learning classifiers. We conducted extensive experiments using three renowned datasets. The results show that cFEM outperforms the state-of-the-art intrusion detection methods in several performance metrics such as detection rate (99.61%) and false alarm rate (0.26%). Further experiments on extracted features show that our extracted features are discriminative, free of redundancy, and able to capture complementary information. [ABSTRACT FROM AUTHOR]

Industry 4.0 brings about a convergence between traditional industrial practices and modern computational techniques. The manufacturing sector is expected to make a greater number of decisions and actions based on the advanced computational analysis of the measurable machinery data. Predictive maintenance of the CNC lathe spindle unit helps the machine avoid unexpected downtimes and meet closer machining tolerances. In this paper, the vibration signals acquired from an experimental run-to-failure test rig are first processed to extract health degradation features, which are then subjected to a neighborhood component analysis-based regression feature selection criteria. Finally, the selected spindle health degradation features are used to train a support-vector machine (SVM) algorithm to evolve a remaining useful life (RUL) estimation model. The SVM hyperparameters that strongly affect the prediction performance are tuned using the Bayesian optimization approach. The evolved predictive model is tested using an independent lathe spindle health degradation data set to obtain the root-mean-square error for predicted and actual RUL. The overall predicted RUL is having an acceptable agreement with the actual RUL. An RMSE equal to 206.23 is obtained as a quantitative measure of prediction accuracy for the Bayesian optimized SVM model for the given dataset. In industrial practice, the evolved SVM predictive model can be employed for the real-time RUL estimation of a similar mechanical system. The proposed predictive model with the integrated feature extraction, selection, and prognosis algorithm can be employed on a real-time spindle health monitoring and predictive maintenance platform for maintenance decision-making. [ABSTRACT FROM AUTHOR]

Feature extraction, feature clustering, feature selection are suitable to enhance learning performance, reduce computational complexity, create better generalizable models, and reduce required storage. Although there are several feature reduction techniques, still it remains one of the research hot spots in the field of data mining and machine learning groups. Owl search algorithm (OSA) is one of the recent metaheuristic optimization algorithms that mimic the hunting mechanism of owls in dark. However, OSA suffers from the same problem faced by many other optimization algorithms and tends to fall in local optima and premature convergence. To overcome these problems, two improvements for OSA algorithm are proposed in this paper. The first improvement uses a fuzzy system which is responsible to tune a control parameter in the updating phase of OSA. The second improvement includes the fuzzy system along with modifying the updating equation of OSA to enhance the exploration activity. In addition, this paper presents a new feature extraction technique for regression problems based on the improved OSA, called Fuzzy Owl Clustering Dimension Reduction (FOCDR). We apply a method that uses three weighting methods (i.e., soft, hard, and mixed) to extract new features based on the generated clusters. The experiment is divided into two parts. In the first part, the performance of the OSA algorithm and two improvement versions are analyzed with ten benchmark functions. The results show that the proposed versions on average can improve the convergence rate by 6.75% and 14.2% compared to OSA in solving complex problems. The second part is conducted to show FOCDR's ability for feature selection problems. The effectiveness of FOCDR has been evaluated using four benchmark datasets and a real-world case study. [ABSTRACT FROM AUTHOR]

In past few decades, there was a tremendous enhancement in natural disaster and their effects on economy and population. An adverse events like floods, wildfires, cyclones, earthquakes, tsunamis, etc., are regarded as a natural disaster once it strikes the vulnerable population areas. An early tracking of susceptibility areas and immediate tracking of affected areas might help in facilitating rescue and early warnings to the public. To achieve autonomous natural disaster prediction, this paper makes use of current developments in remote sensing, which speed up the availability of aerial/satellite data and are reinforced by progress in the computing sector. The aerial/satellite imageries are employed for acquiring the data from areas of Queensland-Australia that are more prone to natural disaster in an eagle-eye perspective. Since there were several techniques employed so far for the automatic prediction of natural disaster susceptibilities, there were some limitations like reduced rate of accuracy and so on. So as to overcome these limitations, deep learning based automated process is employed for predicting the natural disaster areas and probability of event occurrences. The main intention of the work is to detect the natural disaster occurrence from the sensed data which aids in providing warning to public and to safeguard them by taking necessary actions. Initially, remote sensing data is pre-processed and the features are extracted using Adaptive linear Internal embedding algorithm-based feature extraction (ALIE-FE). The extracted features are selected using Recursive Wrapper-based feature subset selection. To estimate best fitness function and to enhance the prediction accuracy, the optimization process is carried using Bio-Inspired Squirrel Search Optimization algorithm (BI-SSOA). Finally, the classification is carried by means of Deep learning based Multi-layer Alex Net classifier (DBMLA) approach. The simulation is carried and the outcomes attained are estimated for predicting flood susceptibility and wildfire susceptibility. The proposed BISSOA-DBMLA offers sensitivity of 98%, specificity of 99%, and TSS of 97%. The proposed system offers 98.99% classification accuracy. Accuracy, sensitivity, specificity, TSS, and area under the curve (AUC) are used to evaluate the efficacy of the suggested system in light of the achieved results from other approaches. To demonstrate the efficacy of the suggested mechanism, the achieved results are compared with those of current approaches. [ABSTRACT FROM AUTHOR]

Predicting students' performance during their years of academic study has been investigated tremendously. It offers important insights that can help and guide institutions to make timely decisions and changes leading to better student outcome achievements. In the post-COVID-19 pandemic era, the adoption of e-learning has gained momentum and has increased the availability of online related learning data. This has encouraged researchers to develop machine learning (ML)-based models to predict students' performance during online classes. The study presented in this paper, focuses on predicting student performance during a series of online interactive sessions by considering a dataset collected using digital electronics education and design suite. The dataset tracks the interaction of students during online lab work in terms of text editing, a number of keystrokes, time spent in each activity, etc., along with the exam score achieved per session. Our proposed prediction model consists of extracting a total of 86 novel statistical features, which were semantically categorized in three broad categories based on different criteria: (1) activity type, (2) timing statistics, and (3) peripheral activity count. This set of features were further reduced during the feature selection phase and only influential features were retained for training purposes. Our proposed ML model aims to predict whether a student's performance will be low or high. Five popular classifiers were used in our study, namely: random forest (RF), support vector machine, Naïve Bayes, logistic regression, and multilayer perceptron. We evaluated our model under three different scenarios: (1) 80:20 random data split for training and testing, (2) fivefold cross-validation, and (3) train the model on all sessions but one which will be used for testing. Results showed that our model achieved the best classification accuracy performance of 97.4% with the RF classifier. We demonstrated that, under similar experimental setup, our model outperformed other existing studies. [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]

Nowadays, the economy of countries highly depends on the agriculture productivity which has a great effect on the development of human civilization. Sometimes, plant diseases cause a major reduction in agricultural products. This paper proposes a new approach for the automatic detection and classification of plant leaf diseases based on using the ELM deep learning algorithm on a real dataset of plant leaf images. The proposed approach uses the k-means clustering algorithm for image segmentation and applies the GLCM for feature extraction. The BDA optimization algorithm is employed for feature selection, and lastly the ELM algorithm is used for plant leaf diseases classification. The presented approach optimizes the input weights and hidden biases for ELM. The dataset used in this study includes 73 plant leaf images, such that we tested our approach on four diseases that usually affect plants, including: Alternaria alternata, Anthracnose, Bacterial blight, and Cercospora leaf spot. The experimental results show that the proposed approach has achieved encouraging results in terms of these classification measures: accuracy, error rate, recall, F score, and AUC which are 94%, 6%, 92%, 95%, and 96% respectively. Babu [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]

Spike trains (STs) induced by external stimuli are complex and challenging to decode the embedded spatiotemporal information. Although various methods have been developed to characterize STs, few applications have been reported in tactile discrimination applications. In this paper, a neurocomputing method based on reference spike train (RST) is proposed to establish a neural computation scheme, on which existing ST metrics could be fed into various traditional models directly. Moreover, existing metrics in the field of statistics and vector measurement are introduced together to extract more discriminative features. With the binning technique and feature selection algorithm applied, the neural computation scheme is aimed at taking advantage of as maximal as possible information contained in tactile signals. Based on our designed artificial fingertip, the effect is validated by improving the recognition accuracy from 77.6% to 83.4% when it is applied to the discrimination of eight roughness surfaces. Furthermore, properties of RST, such as spike intervals and distributions, are evaluated and it is found that RSTs with uniform distribution perform the best for tactile discrimination. [ABSTRACT FROM AUTHOR]