Electroencephalography (EEG) is a non-invasive technique used to record the brain’s evoked and induced electrical activity from the scalp. Artificial intelligence, particularly machine learning (ML) and deep learning (DL) algorithms, are increasingly being applied to EEG data for pattern analysis, group membership classification, and brain-computer interface purposes. This study aimed to systematically review recent advances in ML and DL supervised models for decoding and classifying EEG signals. Moreover, this article provides a comprehensive review of the state-of-the-art techniques used for EEG signal preprocessing and feature extraction. To this end, several academic databases were searched to explore relevant studies from the year 2000 to the present. Our results showed that the application of ML and DL in both mental workload and motor imagery tasks has received substantial attention in recent years. A total of 75% of DL studies applied convolutional neural networks with various learning algorithms, and 36% of ML studies achieved competitive accuracy by using a support vector machine algorithm. Wavelet transform was found to be the most common feature extraction method used for all types of tasks. We further examined the specific feature extraction methods and end classifier recommendations discovered in this systematic review.

This study intends to examine different dynamics of the chaotic incommensurate fractional‐order Hopfield neural network model. The stability of the proposed incommensurate‐order model is analyzed numerically by continuously varying the values of the fractional‐order derivative and the values of the system parameters. It turned out that the formulated system using the Caputo differential operator exhibits many rich complex dynamics, including symmetry, bistability, and coexisting chaotic attractors. On the other hand, it has been detected that by adapting the corresponding controlled constants, such systems possess the so‐called offset boosting of three variables. Besides, the resultant periodic and chaotic attractors can be scattered in several forms, including 1D line, 2D lattice, and 3D grid, and even in an arbitrary location of the phase space. Several numerical simulations are implemented, and the obtained findings are illustrated through constructing bifurcation diagrams, computing Lyapunov exponents, calculating Lyapunov dimensions, and sketching the phase portraits in 2D and 3D projections.

Groundwater (GW) studies have been conducted worldwide with regard to several pressures, including climate change, seawater intrusion, and water overexploitation. GW quality is a very important sector for several countries in the world, in particular for Tunisia. The shallow coastal aquifer of Sfax (located in Tunisia) was found to be under the combined conditions of continuous drop in GW and further deterioration of the groundwater quality (GWQ). This study was conducted to identify the processes that control GWQ mainly in relation to mineralization sources in the shallow Sfax coastal aquifer. To perform this task, 37 wells are considered. Data include 10 physico-chemical properties of groundwater analyzed in water samples: pH, EC, calcium (Ca), sodium (Na), magnesium (Mg), potassium (K), chloride (Cl), sulfate (SO₄), bicarbonate (HCO₃), and nitrate (NO₃), i.e., investigation was based on a database of 370 observations. Principal component analysis (PCA) and hydrochemical facies evolution (HFE) were conducted to extract the main factors affecting GW chemistry. The results obtained using the PCA model show that GWQ is mainly controlled by either natural factors (rock–water interactions) or anthropogenic ones (agricultural and domestic activities). Indeed, the GW overexploitation generated not only the GWQ degradation but also the SWI. The inverse distance weighted (IDW) method, integrated in a geographic information system (GIS), is employed to achieve spatial mapping of seawater intrusion locations. Hydrochemical facies evolution (HFE) results corroborate the seawater intrusion and its spatial distribution. Furthermore, the mixing ratio showed that Jebeniana and Chaffar–Mahares localities are characterized by high SWI hazard. This research should be done to better manage GW resources and help to develop a suitable plan for the exploitation and protection of water resources.

Companies attempt to improve the performance of their supply chain (SC) by distinguishing and presenting feasible sustainable development practices (SDP). Considering SDP without focusing on sustainability risks may disturb the company’s future. Very few studies in the extant literature have dealt with the impact of (SDP) on the supply chain risk management (SCRM). In fact, the aim of this paper is to classify and prioritize SDPs according to their priority for better risk management and effective SC performance. The proposed approach comprises two phases. First, 14 SDPs are identified and selected from the literature. Second, MICMAC (Matrice d’impacts croisés multiplication appliquée à un classement) method as a structural analysis method applies to identify and assess sustainable supply chain risk management (SSCRM) practices which reduce risk in the SC. The input data for each phase are based on Delphi technique, which is a process group used to collect the opinions of experts in the field. The aim of the proposed approach is to prioritize SSCRM practices and classify them into influential, non-influential, independent and dependent practices and their mutual relationships. The six key findings SSCRM practices from direct and indirect classification include the following elements: (1) Delayed differentiation, (2) Information sharing with upstream and/or downstream partners, (3) Simplification of product dismantling/anticipation of product end of life, (4) Supplier/subcontractor’s performance assessment, (5) establishing shared supply management and (6) establishment of contracts with transporters.

The COVID-19 pandemic has had unprecedented social and economic consequences in the United States. Therefore, accurately predicting the dynamics of the pandemic can be very beneficial. Two main elements required for developing reliable predictions include: (1) a predictive model and (2) an indicator of the current condition and status of the pandemic. As a pandemic indicator, we used the effective reproduction number (Rt), which is defined as the number of new infections transmitted by a single contagious individual in a population that may no longer be fully susceptible. To bring the pandemic under control, Rt must be less than one. To eliminate the pandemic, Rt should be close to zero. Therefore, this value may serve as a strong indicator of the current status of the pandemic. For a predictive model, we used graph neural networks (GNNs), a method that combines graphical analysis with the structure of neural networks. We developed two types of GNN models, including: (1) graph-theory-based neural networks (GTNN) and (2) neighborhood-based neural networks (NGNN). The nodes in both graphs indicated individual states in the United States. While the GTNN model’s edges document functional connectivity between states, those in the NGNN model link neighboring states to one another. We trained both models with R_t numbers collected over the previous four days and asked them to predict the following day for all states in the United States. The performance of these models was evaluated with the datasets that included R_t values reflecting conditions from 22 January through 26 November 2020 (before the start of COVID-19 vaccination in the United States). To determine the efficiency, we compared the results of two models with each other and with those generated by a baseline Long short-term memory (LSTM) model. The results indicated that the GTNN model outperformed both the NGNN and LSTM models for predicting Rt.

The performance of text classification methods has improved greatly over the last decade for text instances of less than 512 tokens. This limit has been adopted by most state-of-the-research transformer models due to the high computational cost of analyzing longer text instances. To mitigate this problem and to improve classification for longer texts, researchers have sought to resolve the underlying causes of the computational cost and have proposed optimizations for the attention mechanism, which is the key element of every transformer model. In our study, we are not pursuing the ultimate goal of long text classification, i.e., the ability to analyze entire text instances at one time while preserving high performance at a reasonable computational cost. Instead, we propose a text truncation method called Text Guide, in which the original text length is reduced to a predefined limit in a manner that improves performance over naive and semi-naive approaches while preserving low computational costs. Text Guide benefits from the concept of feature importance, a notion from the explainable artificial intelligence domain. We demonstrate that Text Guide can be used to improve the performance of recent language models specifically designed for long text classification, such as Longformer. Moreover, we discovered that parameter optimization is the key to Text Guide performance and must be conducted before the method is deployed. Future experiments may reveal additional benefits provided by this new method.