Explore the vast range of titles available.

Analyzing electroencephalography (EEG) signals with machine learning approaches has become an attractive research domain for linking the brain to the outside world to establish communication in the name of the Brain-Computer Interface (BCI). Many researchers have been working on developing successful motor imagery (MI)-based BCI systems. However, they still face challenges in producing better performance with them because of the irrelevant features and high computational complexity. Selecting discriminative and relevant features to overcome the existing issues is crucial. In our proposed work, different feature selection algorithms have been studied to reduce the dimension of multiband feature space to improve MI task classification performance. In the procedure, we first decomposed the MI-based EEG signal into four sets of the narrowband signal. Then a common spatial pattern (CSP) approach was employed for each narrowband to extract and combine effective features, producing a high-dimensional feature vector. Three feature selection approaches, named correlation-based feature selection (CFS), minimum redundancy and maximum relevance (mRMR), and multi-subspace randomization and collaboration-based unsupervised feature selection (SRCFS), were used in this study to select the relevant and effective features for improving classification accuracy. Among them, the SRCFS feature selection approach demonstrated outstanding performance for MI classification compared to other schemes. The SRCFS is based on the multiple k-nearest neighbour graphs method for learning feature weight based on the Laplacian score and then discarding the irrelevant features based on the weight value, reducing the feature dimension. Finally, the selected features are fed into the support vector machines (SVM), linear discriminative analysis (LDA), and multi-layer perceptron (MLP) for classification. The proposed model is evaluated with two benchmark datasets, namely BCI Competition III dataset IVA and dataset IIIB, which are publicly available and mainly used to recognize the MI tasks. The LDA classifier with the SRCFS feature selection algorithm exhibits better performance. It proves the superiority of our proposed study compared to the other state-of-the-art BCI-based MI task classification systems.

Data-driven models were developed for monitoring the power consumption and wood quality during the lumber manufacturing process. The study proposes hybrid models using vibration signals combined with self-organizing maps (SOMs) for cutting power and waviness prediction in the circular sawing process of Douglas-fir wood under very high feed speed conditions. The acquired vibration signals were fed into SOMs with different topologies for data mapping and automatic sensory feature selection, which were fed into the adaptive neuro-fuzzy inference system (ANFIS) or multilayer perceptron (MLP) neural network (NN) for cutting power and waviness prediction. The monitoring performance of the hybrid SOM-MLP NN and SOM-ANFIS models was compared. The frequency response of vibration signals and its correlation with the cutting parameters as well as the cutting power and waviness were discussed. The study shows that the developed SOM models to select the optimal features from the vibration signals could accurately predict cutting power and waviness when combined with a machine learning model. The prediction performance is highly dependent on the optimal choice of SOM topology. Having a poor choice of SOM topology, fine-tuning the architecture of ANFIS and MLP NN is crucial and greatly impacts the monitoring performance. Based on the obtained results, SOM is recommended for the automatic feature in the machining or tool condition monitoring, where due to process high variability, manual feature selection is a challenging task. SOM combined with an ANN or ANFIS makes a powerful intelligent model for monitoring complex processes such as wood circular sawing.

The mass of redundant and irrelevant data in network traffic brings serious challenges to intrusion detection, and feature selection can effectively remove meaningless information from the data. Most current filtered and embedded feature selection methods use a fixed threshold or ratio to determine the number of features in a subset, which requires a priori knowledge. In contrast, wrapped feature selection methods are computationally complex and time-consuming; meanwhile, individual feature selection methods have a bias in evaluating features. This work designs an ensemble-based automatic feature selection method called EAFS. Firstly, we calculate the feature importance or ranks based on individual methods, then add features to subsets sequentially by importance and evaluate subset performance comprehensively by designing an NSOM to obtain the subset with the largest NSOM value. When searching for a subset, the subset with higher accuracy is retained to lower the computational complexity by calculating the accuracy when the full set of features is used. Finally, the obtained subsets are ensembled, and by comparing the experimental results on three large-scale public datasets, the method described in this study can help in the classification, and also compared with other methods, we discover that our method outperforms other recent methods in terms of performance.

Despite its efficacy, machine learning in health sciences faces limitations with regard to addiction prediction due to integrating diverse data sources, addressing biases, and interpreting complex models. This may reduce the effectiveness of predictive models in identifying at-risk individuals and informing intervention strategies. The current challenge lies in identifying the optimal number of features for model training and determining the influential factors for alcohol addiction. Therefore, this paper explores and proposes an enhanced feature engineering algorithm which not only ranks the feature importance, but also automatically extracts the optimal features for the prediction model, which in return improves the predictive power of kernel-based models. By using a feature aggregation approach, the features identified by different Relief-based algorithms (such as Relief, ReliefF and RReliefF) were merged into a unified set as a ranked feature list, and the Relief-based algorithms were integrated with the XGBoost boosting algorithm for the implementation of an automated feature selection process. The proposed method provided 11 influential features to be included as n_features in the predictive model. Three different families of classifiers, namely the Linear, Ensemble-based and Kernel-based classifiers were analysed in combination with the enhanced Relief-based algorithm to evaluate the response of the proposed model to the respective algorithms. In this context, the enhanced RReliefF algorithm improved the Kernel-based model by 7.47% in terms of the discriminative power and by 12.69% with regard to the predictive power, in comparison with the baseline model. These findings aided in resolving the limitations related to the manual optimal feature selection typical of the current feature engineering methods, thereby opening a new research avenue for automatic feature engineering in a low-code context. Overall, the proposed enhanced algorithm ensures technical correctness by leveraging ReliefF algorithm’s feature rankings effectively for an improved performance in the context of kernel-based models like Support Vector Machine (SVM), making them more accessible and actionable for clinicians and healthcare professionals working in alcohol addiction-related prevention and intervention.

Background Brain-machine interfaces (BMI) have recently been integrated within motor rehabilitation therapies by actively involving the central nervous system (CNS) within the exercises. For instance, the online decoding of intention of motion of a limb from pre-movement EEG correlates is being used to convert passive rehabilitation strategies into active ones mediated by robotics. As early stages of upper limb motor rehabilitation usually focus on analytic single-joint mobilizations, this paper investigates the feasibility of building BMI decoders for these specific types of movements. Methods Two different experiments were performed within this study. For the first one, six healthy subjects performed seven self-initiated upper-limb analytic movements, involving from proximal to distal articulations. For the second experiment, three spinal cord injury patients performed two of the previously studied movements with their healthy elbow and paralyzed wrist. In both cases EEG neural correlates such as the event-related desynchronization (ERD) and movement related cortical potentials (MRCP) were analyzed, as well as the accuracies of continuous decoders built using the pre-movement features of these correlates (i.e., the intention of motion was decoded before movement onset). Results The studied movements could be decoded in both healthy subjects and patients. For healthy subjects there were significant differences in the EEG correlates and decoding accuracies, dependent on the moving joint. Percentages of correctly anticipated trials ranged from 75 % to 40 % (with chance level being around 20 % ), with better performances for proximal than for distal movements. For the movements studied for the SCI patients the accuracies were similar to the ones of the healthy subjects. Conclusions This paper shows how it is possible to build continuous decoders to detect movement intention from EEG correlates for seven different upper-limb analytic movements. Furthermore we report differences in accuracies among movements, which might have an impact on the design of the rehabilitation technologies that will integrate this new type of information. The applicability of the decoders was shown in a clinical population, with similar performances between healthy subjects and patients.

Biomedical systems produce biosignals that arise from interaction mechanisms. In a general form, those mechanisms occur across multiple scales, both spatial and temporal, and contain linear and non-linear information. In this framework, entropy measures are good candidates in order provide useful evidence about disorder in the system, lack of information in time-series and/or irregularity of the signals. The most common movement disorder is essential tremor (ET), which occurs 20 times more than Parkinson’s disease. Interestingly, about 50%–70% of the cases of ET have a genetic origin. One of the most used standard tests for clinical diagnosis of ET is Archimedes’ spiral drawing. This work focuses on the selection of non-linear biomarkers from such drawings and handwriting, and it is part of a wider cross study on the diagnosis of essential tremor, where our piece of research presents the selection of entropy features for early ET diagnosis. Classic entropy features are compared with features based on permutation entropy. Automatic analysis system settled on several Machine Learning paradigms is performed, while automatic features selection is implemented by means of ANOVA (analysis of variance) test. The obtained results for early detection are promising and appear applicable to real environments.

The problem of hardware Trojan is certainly serious, complex and tricky. Therefore, hardware Trojan (HT) detection is difficult, time and effort consuming and challenging due to non-trivial threats that compromise the security of integrated circuits (IC). The problem becomes more serious with the extensive outsourcing of ICs design and fabrication by untrusted foundries. Recently, hardware Trojan detection has gained insight and interest from different researches and industries in order to detect Trojan horses in the fabrication phase of an IC. In that phase HT detection requires expensive testing techniques. Hardware Trojans in the fabrication phase show that the detection process may be either side-channel based (non-destructive) or reverse engineering based (destructive). The destructive approach consists mainly of three steps: (1) decapsulation, (2) delayering and (3) imaging for layout identification. This paper presents a new approach for automating the third step, namely, the layout identification of the underlying circuit. The proposed approach automatically extracts and describes the features of circuit layout by making use of histogram of oriented gradient. Features descriptors obtained from such histogram of oriented gradient are then fed to a machine learning classifier represented by a decision tree that aims at learning the pattern of malicious ICs in order to differentiate them from benign ones. In addition, the classification result is enhanced by utilizing AdaBoost learning algorithm to produce a strong meta-classifier in a chain of cascaded stages. Based on that scheme, a composite classification model is built up to provide an Automatic Hardware Trojan Detection and description Tool (AHTDT). The proposed model has been tested (on noisy and clean data) and evaluated using ISCAS89 benchmark dataset. Such benchmark is emphasized deliberately to show different Trojan examples –namely, Trojan insertion, Trojan deletion and Trojan parametric- inside hardware circuits. Model simulation and evaluation results have shown a remarkable enhancement in HT detection compared to other reverse engineering detection techniques. Moreover, the proposed approach has the advantages of being automatic, systematic and capable of detecting and diagnosing hardware Trojans accurately with high detection rate, while keeping low false positive rate.

Among neural disorders related to movement, essential tremor has the highest prevalence; in fact, it is twenty times more common than Parkinson’s disease. The drawing of the Archimedes’ spiral is the gold standard test to distinguish between both pathologies. The aim of this paper is to select non-linear biomarkers based on the analysis of digital drawings. It belongs to a larger cross study for early diagnosis of essential tremor that also includes genetic information. The proposed automatic analysis system consists in a hybrid solution: Machine Learning paradigms and automatic selection of features based on statistical tests using medical criteria. Moreover, the selected biomarkers comprise not only commonly used linear features (static and dynamic), but also other non-linear ones: Shannon entropy and Fractal Dimension. The results are hopeful, and the developed tool can easily be adapted to users; and taking into account social and economic points of view, it could be very helpful in real complex environments.

The concept of smart manufacturing has become an important issue in the manufacturing industry since the start of the twenty-first century in terms of time and production cost. In addition to high production quality, a quick response could determine the success or failure of many companies and factories. One the most effective concepts for achieving a smart manufacturing industry is the use of computer-aided process planning (CAPP) techniques. Computer-aided process planning refers to key technology that connects the computer-aided design (CAD) and the computer-aided manufacturing (CAM) processes. Researchers have used many approaches as an interface between CAD and CAPP systems. In this field of research, a lot of effort has been spent to take CAPP systems to the next level in the form of automatic computer-aided process planning (ACAPP). This is to provide complete information about the product, in a way that is automated, fast, and accurate. Moreover, automatic feature recognition (AFR) techniques are considered one of the most important tasks to create an ACAPP system. This article presents a comprehensive survey about two main aspects: the degree of automation in each required input and expected output of computer-aided process planning systems as well as the benefits and the limitations of the different automatic feature recognition techniques. The aim is to demonstrate the missing aspects in smart ACAPP generation, the limitations of current systems in recognising new features, and justifying the process of selection.

In the present study, a new algorithm for automatic target detection (ATR) in synthetic aperture radar (SAR) images has been proposed. First, moving and stationary target acquisition and recognition image chips have been segmented and then passed to a number of preprocessing stages such as histogram equalisation, position and size normalisation. Second, the feature extraction based on Zernike moments (ZMs) having linear transformation invariance properties and robustness in the presence of the noise has been introduced for the first time. Third, a genetic algorithm-based feature selection and a support vector machine classifier have been presented to select the optimal feature subset of ZMs for decreasing the computational complexity. Experimental results demonstrate the efficiency of the proposed approach in target recognition of SAR imagery. The authors obtained results show that just a small amount of ZMs features is sufficient to achieve the recognition rates that rival other established methods, and so ZMs features can be regarded as a powerful discriminatory feature for automatic target recognition applications relevant to SAR imagery. Furthermore, it can be observed that the classifier performs fairly well until the signal-to-noise ratio falls beneath 5 dB for noisy images.