Search

The sixth generation (6G) represents the next evolution in wireless communication technology and is currently under research and development. It is expected to deliver faster speeds, reduced latency, and greater capacity compared to the current 5G wireless technology. 6G is envisioned as a technology capable of establishing a fully data‐driven network, proficient in analyzing and optimizing end‐to‐end behavior and handling massive volumes of real‐time data at rates of up to terabits per second (Tb/s). Moreover, 6G is designed to accommodate an average of 1000+ substantial connections per person over the course of a decade. The concept of a data‐driven network introduces a new service paradigm, which offers fresh opportunities for applications within 6G wireless communication and network design in the future. This paper aims to provide a survey of existing applications of 6G that are based on deep learning techniques. It also explores the potential, essential technologies, scenarios, challenges, and related topics associated with 6G. These aspects are crucial for meeting the requirements for the development of future intelligent networks. Furthermore, this work delves into various research gaps between deep learning and 6G that remain unexplored. Different potential deep learning applications for 6G networks, including privacy, security, environmentally friendly communication, sustainability, and various wireless applications, are discussed. Additionally, we shed light on the challenges and future trends in this field. This article is categorized under:Technologies > Computational IntelligenceFundamental Concepts of Data and Knowledge > Explainable AITechnologies > Machine Learning [ABSTRACT FROM AUTHOR]

In this study, Mg-Ti-SiC composite powders with varied micron and nano silicon carbide (SiC) particle sizes were fabricated utilizing the ball milling technology at various milling times. The effect of reinforcement particles sizes and milling time on the morphology and microstructure of the magnesium composite powders was characterized. Then, we developed a machine-learning model based on Adaptive Neuro-fuzzy Inference System (ANFIS) modified with termite life cycle optimizer to predict the crystallite size of the produced composites. The average particles size in all composites including micron SiC (µSiC) and nano SiC (nSiC) always decreased with increasing milling time and SiC content, and the most optimal reduction in particle size was achieved after 16 h of milling for both configurations, which were 5.12 µm and 1.96 µm, respectively. Changing reinforcement particle size from micron to nano caused the peak intensities of Mg and Ti more decreased and phases Ti 5 Si 3 and TiC were observed after milling for 16 h in ND composite powder. With increasing milling time in Mg-25 wt% Ti-5 wt% µSiC, the crystallite size decreased from 31 nm to 13.62 nm after 1 h and 32 h milled, respectively. The most optimum reduction in crystallite size occurred in the composite powders including nSiC, in which crystallite size decreased to 13.35 nm. The developed Machine learning model was able to predict the evolution of the crystallite size of the produce d composites with very good accuracy. [ABSTRACT FROM AUTHOR]

Intrusion detection systems (IDS) play a crucial role in securing networks and identifying malicious activity. This is a critical problem in cyber security. In recent years, metaheuristic optimization algorithms and deep learning techniques have been applied to IDS to improve their accuracy and efficiency. Generally, optimization algorithms can be used to boost the performance of IDS models. Deep learning methods, such as convolutional neural networks, have also been used to improve the ability of IDS to detect and classify intrusions. In this paper, we propose a new IDS model based on the combination of deep learning and optimization methods. First, a feature extraction method based on CNNs is developed. Then, a new feature selection method is used based on a modified version of Growth Optimizer (GO), called MGO. We use the Whale Optimization Algorithm (WOA) to boost the search process of the GO. Extensive evaluation and comparisons have been conducted to assess the quality of the suggested method using public datasets of cloud and Internet of Things (IoT) environments. The applied techniques have shown promising results in identifying previously unknown attacks with high accuracy rates. The MGO performed better than several previous methods in all experimental comparisons. [ABSTRACT FROM AUTHOR]

The integration of metaheuristics with machine learning methodologies presents significant advantages, particularly in optimization and computational intelligence. This amalgamation leverages the global search capabilities of metaheuristics alongside the pattern recognition and predictive prowess of machine learning, facilitating enhanced convergence rates and solution quality in complex problem spaces. The Quantum Long Short-Term Memory (QLSTM) emerges as a highly efficient deep learning model tailored to tackle such intricate engineering problems. The QLSTM's architecture, comprising data encoding, variational, and quantum measurement layers, facilitates the effective encoding and processing of civil engineering data, leading to heightened prediction accuracy. However, the task of determining optimal values for QLSTM parameters presents challenges due to its NP-problem nature and time-consuming characteristics. To address this, we propose an alternative technique to optimize the QLSTM based on a modified Electric Eel Foraging Optimization (MEEFO). The MEEFO is a modified version of the original EEFO that applies triangular mutation operators to boost the search capability of the traditional EEFO. Thus, the MEEFO optimizes the QLSTM and boosts its prediction performance. To validate the efficacy of our proposed method, we conduct comprehensive experiments utilizing five real-world engineering datasets related to construction and structure engineering. The evaluation outcomes unequivocally demonstrate that the MMEFO significantly enhances the performance of the QLSTM. [ABSTRACT FROM AUTHOR]

In the context of the escalating use of social media in Arabic-speaking countries, driven by improved internet access, affordable smartphones, and a growing digital connectivity trend, this study addresses a significant challenge: the widespread dissemination of fake news. The ease and rapidity of spreading information on social media, coupled with a lack of stringent fact-checking measures, exacerbate the issue of misinformation. Our study examines how language features, especially Named Entity Recognition (NER) features, play a role in detecting fake news. We built two models: an AraBERT Multi-task Learning (MTL) based one for classifying Arabic fake news, and a token classification model that focuses on fake news NER features. The study combines embedding vectors from these models using an embedding fusion technique and applies machine learning algorithms for fake news detection in Arabic. We also introduced a feature selection algorithm named RLTTAO based on improving the Triangulation Topology Aggregation Optimizer (TTAO) performance using Reinforcement Learning and random opposition-based learning to enhance the performance by selecting relevant features, thereby improving the fusion process. Our results show that incorporating NER features enhances the accuracy of fake news detection in 5 out of 7 datasets, with an average improvement of 1.62%. [ABSTRACT FROM AUTHOR]

To meet the needs of Egypt's rising population, more land must be cultivated. Land evaluation is vital to achieving sustainable agricultural production. To determine the soil capability in the northeast Nile Delta region of Egypt, the present study introduces a new form of integration between the Agriculture Land Evaluation System (ALES Arid) model and the machine learning (ML) approach. The soil capability indicators required for the ALES Arid model were determined for the 47 collected soil profiles covering the study area. These indicators include soil pH, soil salinity, the sodium adsorption ratio (SAR), the exchangeable sodium percentage (ESP), the organic matter (OM) content, the calcium carbonate (CaCO3) content, the gypsum content, the clay percentage, and the slope. The ALES Arid model was run using these indicators, and soil capability indexes were obtained. Using GIS, these indexes helped to classify the study area into four capability classes, ranging from good to very poor soils. To predict the soil capability, three machine learning algorithms named traditional RVFL, sine cosine algorithm (SCA), and AFO were also applied to the same soil criteria. The developed ML method aims to enhance the prediction of soil capability. This method depends on improving the performance of Random Vector Functional Link (RVFL) using an optimization technique named Aptenodytes Forsteri Optimization (AFO). The operators of AFO were used to determine the best parameters of RVFL since traditional RVFL is sensitive to parameters. To assess the performance of the developed AFO-RVFL method, a set of real collected data was used. The experimental results illustrate the high efficacy of AFO-RVFL in the spatial prediction of soil capability. The correlations found in this study are critical for understanding the overall techniques for predicting soil capability. [ABSTRACT FROM AUTHOR]

Feature Selection (FS) is a major preprocessing stage which aims to improve Machine Learning (ML) models' performance by choosing salient features, while reducing the computational cost. Several approaches are presented to select the most Optimal Features Subset (OFS) in a given dataset. In this paper, we introduce an FS-based approach named Reptile Search Algorithm–Snake Optimizer (RSA-SO) that employs both RSA and SO methods in a parallel mechanism to determine OFS. This mechanism decreases the chance of the two methods to stuck in local optima and it boosts the capability of both of them to balance exploration and explication. Numerous experiments are performed on ten datasets taken from the UCI repository and two real-world engineering problems to evaluate RSA-SO. The obtained results from the RSA-SO are also compared with seven popular Meta-Heuristic (MH) methods for FS to prove its superiority. The results show that the developed RSA-SO approach has a comparative performance to the tested MH methods and it can provide practical and accurate solutions for engineering optimization problems. [ABSTRACT FROM AUTHOR]

[Display omitted] • Developed 12 novel methanol/diesel blends, achieving up to 9.3% increase in BP. • Lowest BSFC of 0.27 kg/kWh in methanol/diesel blends, outperforming pure diesel. • Machine learning model has a prediction accuracy of R2 ≈ 93% and RMSE ≈ 1.13. • BTE increased by 31.5% with C2 blend, showing enhanced combustion efficiency. • Methanol/diesel blends showed stable VE between 71.96% and 76.65% across loads. The pursuit of reducing diesel consumption while progressing towards a sustainable energy future necessitates critical decisions regarding fuel modifications or engine adaptations to ensure smooth transitions in transportation. This study explores the potential of methanol/diesel blends as a sustainable fuel solution for the transport sector. We address a significant gap by examining the impact of six different surfactants on blend stability and engine performance. Ternary phase diagrams were constructed to analyse blend stability, and engine testing on a 3.5 kW single-cylinder diesel engine evaluated the effects on brake power (BP), brake specific fuel consumption (BSFC), brake thermal efficiency (BTE), brake mean effective pressure (BMEP), and volumetric efficiency (VE) across various load conditions (2.5 %, 25 %, 50 %, 75 %, and 100 % load). Additionally, a novel predictive model was developed using the Partial Reinforcement Optimiser (PRO) algorithm integrated with Random Vector Functional Link (RVFL) to enhance engine performance estimation. Comparative analysis with established optimisation algorithms (GWO, WOA, AOA, HHO, and traditional RVFL) demonstrated the superior accuracy of the PRO-RVFL model. The model consistently achieved the highest R2 and lowest RMSE scores for all evaluated parameters (BP: R2 ≈ 93 %, RMSE ≈ 1.13; BSFC: R2 ≈ 91 %, RMSE ≈ 1.45; BTE: R2 ≈ 89 %; BMEP: R2 ≈ 81 %, RMSE ≈ 2.80; VE: R2 ≈ 71 %, RMSE ≈ 3.13). The findings support the viability of methanol/diesel blends in enhancing engine performance while promoting sustainability in transportation. This study, with its precise experimentation and advanced modelling techniques, paves the way for the development of cleaner and more efficient transportation systems. [ABSTRACT FROM AUTHOR]

The telecommunications industry is greatly concerned about customer churn due to dissatisfaction with service. This industry has started investing in the development of machine learning (ML) models for churn prediction to extract, examine and visualize their customers' historical information from a vast amount of big data which will assist to further understand customer needs and take appropriate actions to control customer churn. However, the high-dimensionality of the data has a large influence on the performance of the ML model, so feature selection (FS) has been applied since it is a primary preprocessing step. It improves the ML model's performance by selecting salient features while reducing the computational time, which can assist this sector in building effective prediction models. This paper proposes a new FS approach ACO-RSA, that combines two metaheuristic algorithms (MAs), namely, ant colony optimization (ACO) and reptile search algorithm (RSA). In the developed ACO-RSA approach, an ACO and RSA are integrated to choose an important subset of features for churn prediction. The ACO-RSA approach is evaluated on seven open-source customer churn prediction datasets, ten CEC 2019 test functions, and its performance is compared to particle swarm optimization (PSO), multi verse optimizer (MVO) and grey wolf optimizer (GWO), standard ACO and standard RSA. According to the results along with statistical analysis, ACO-RSA is an effective and superior approach compared to other competitor algorithms on most datasets. [ABSTRACT FROM AUTHOR]

According to the World Health Organization (WHO), patient Length of Stay (LOS) in hospitals is an important performance measurement and monitoring indicator. Prolonged LOS in the Intensive Care Unit (ICU) may lead to consuming hospital resources, manpower, and equipment. Therefore, accurate prediction of patient LOS may aid the healthcare specialists to take medical decisions and allocate medical team and resources. As well, the patient and insurance companies may use this prediction to manage their budget. In this paper, a framework for predicting patient LOS in the ICU using different machine learning (ML) techniques is proposed. Unlike most of the previous studies, this study relies on general medical features collected on patient admission regardless of the patient diagnosis. This provide a broad scope and cover all patients making this approach general and easy to use. The prediction accuracy of the proposed approach was recorded to be very high and different for each ML technique. For example, the best prediction accuracy was achieved by fuzzy with accuracy reach 92%, while classification tree managed to achieve a prediction accuracy of 90% coming in the second place. [ABSTRACT FROM AUTHOR]

Deep neural networks (DNNs) have evolved as a beneficial machine learning method that has been successfully used in various applications. Currently, DNN is a superior technique of extracting information from massive sets of data in a self-organized method. DNNs have different structures and parameters, which are usually produced for particular applications. Nevertheless, the training procedures of DNNs can be protracted depending on the given application and the size of the training set. Further, determining the most precise and practical structure of a deep learning method in a reasonable time is a possible problem related to this procedure. Meta-heuristics techniques, such as swarm intelligence (SI) and evolutionary computing (EC), represent optimization frames with specific theories and objective functions. These methods are adjustable and have been demonstrated their effectiveness in various applications; hence, they can optimize the DNNs models. This paper presents a comprehensive survey of the recent optimization methods (i.e., SI and EC) employed to enhance DNNs performance on various tasks. This paper also analyzes the importance of optimization methods in generating the optimal hyper-parameters and structures of DNNs in taking into consideration massive-scale data. Finally, several potential directions that still need improvements and open problems in evolutionary DNNs are identified. [ABSTRACT FROM AUTHOR]

• Developing a new paradigm for the feature selection problem based on the hyperheuristic methodology. • Configuring the combination of the components in to automatically find the most pertinent features for each dataset. • Evaluating the performance of the proposed technique using a comprehensive set of eighteen datasets. • Comparing the results of the best FS combination with the other well-known FS methods. Feature selection (FS) is a crucial step for effective data mining since it has largest effect on improving the performance of classifiers. This is achieved by removing the irrelevant features and using only the relevant features. Many metaheuristic approaches exist in the literature in attempt to address this problem. The performance of these approaches differ based on the settings of a number of factors including the use of chaotic maps, opposition-based learning (OBL) and the percentage of the population that OBL will be applied to, the metaheuristic (MH) algorithm adopted, the classifier utilized, and the threshold value used to convert real solutions to binary ones. However, it is not an easy task to identify the best settings for these different components in order to determine the relevant features for a specific dataset. Moreover, running extensive experiments to fine tune these settings for each and every dataset will consume considerable time. In order to mitigate this important issue, a hyper-heuristic based FS paradigm is proposed. In the proposed model, a two-stage approach is adopted to identify the best combination of these components. In the first stage, referred to as the training stage , the Differential Evolution (DE) algorithm is used as a controller for selecting the best combination of components to be used by the second stage. In the second stage, referred to as the testing stage , the received combination will be evaluated using a testing set. Empirical evaluation of the proposed framework is based on numerous experiments performed on the most popular 18 datasets from the UCI machine learning repository. Experimental results illustrates that the generated generic configuration provides a better performance than eight other metaheuristic algorithms over all performance measures when applied to the UCI dataset. Moreover, The overall paradigm ranks at number one when compared against state-of-the-art algorithms. Finally, the generic configuration provides a very competitive performance for high dimensional datasets. [ABSTRACT FROM AUTHOR]

Features Selection (FS) approaches have more attention since they have been applied to several fields primarily to deal with high dimensional data. An increase in the dimension of data can lead to degradation of the accuracy of the machine learning method. Therefore, there are several FS methods based on meta-heuristic (MH) techniques that have been developed to tackle the FS problem and avoid the limitations of traditional FS approaches. However, those MH methods still need improvements that suffer from some drawbacks that affect the quality of the final output. So, this paper proposed a modified Henry Gas Solubility Optimization (HGSO) using enhanced Harris hawks optimization (HHO) based on Heavy-tailed distributions (HTDs). In this study, a dynamical exchange between five HTDs is used to boost the HHO that modifies, in turn, the exploitation phase in HGSO. As a result, we proposed a dynamic modified HGSO based on enhanced HHO (DHGHHD). To assess the efficiency of the proposed DHGHHD, a set of eighteen UCI datasets are used. Furthermore, it applied to improve the prediction of two real-world datasets in the drug design and discovery field. The DHGHHD is compared with eight well-known MH methods. Comparison results illustrate the high quality of DHGHHD according to the values of accuracy, fitness value, and the number of selected features. [ABSTRACT FROM AUTHOR]

Recently, significant attention has been devoted to vaccine-derived poliovirus (VDPV) surveillance due to its severe consequences. Prediction of the outbreak incidence of VDPF requires an accurate analysis of the alarming data. The overarching aim to this study is to develop a novel hybrid machine learning approach to identify the key parameters that dominate the outbreak incidence of VDPV. The proposed method is based on the integration of random vector functional link (RVFL) networks with a robust optimization algorithm called whale optimization algorithm (WOA). WOA is applied to improve the accuracy of the RVFL network by finding the suitable parameter configurations for the algorithm. The classification performance of the WOA-RVFL method is successfully validated using a number of datasets from the UCI machine learning repository. Thereafter, the method is implemented to track the VDPV outbreak incidences recently occurred in several provinces in Lao People's Democratic Republic. The results demonstrate the accuracy and efficiency of the WOA-RVFL algorithm in detecting the VDPV outbreak incidences, as well as its superior performance to the traditional RVFL method. [ABSTRACT FROM AUTHOR]

This paper proposes an improved version of the grasshopper optimization algorithm (GOA) based on the opposition-based learning (OBL) strategy called OBLGOA for solving benchmark optimization functions and engineering problems. The proposed OBLGOA algorithm consists of two stages: the first stage generates an initial population and its opposite using the OBL strategy; and the second stage uses the OBL as an additional phase to update the GOA population in each iteration. However, the OBL is applied to only half of the solutions to reduce the time complexity. To investigate the performance of the proposed OBLGOA, six sets of experiment series are performed, and they include twenty-three benchmark functions and four engineering problems. The experiments revealed that the results of the proposed algorithm were superior to those of ten well-known algorithms in this domain. Eventually, the obtained results proved that the OBLGOA algorithm can provide competitive results for optimization engineering problems compared with state-of-the-art algorithms. [ABSTRACT FROM AUTHOR]

Breast cancer is defined as the growth of breast tissue in abnormal way that performing tumors. Breast cancer is one of the most spreading cancer between women and may considered as the first cause of their death. Not all tumors in breast are classified as breast cancer. However, they must be examined by physicians even if it may be normal tumors. Therefore, Detecting breast cancer in an early stage could increases the percent of surviving and may be saves more lives. In this paper, we propose a complete comparative study between different classifications techniques used to predict breast cancer. A set of popular supervised machine learning and data mining techniques will be used to predict breast cancer (benign or malignant). Three different techniques are proposed namely: Classification without feature selection (CWFS), Feature Selection Classification (FSC) and Normalization and Feature Selection Classification (NFSC). The results of accuracy, specificity, precision and sensitivity are calculated and recorded for each system. Hence, our results when compared with the up to date techniques show higher accuracy. [ABSTRACT FROM AUTHOR]

Real life optimization problems require techniques that properly explore the search spaces to obtain the best solutions. In this sense, it is common that traditional optimization algorithms fail in local optimal values. The Sine Cosine Algorithms (SCA) has been recently proposed; it is a global optimization approach based on two trigonometric functions. SCA uses the sine and cosine functions to modify a set of candidate solutions; such operators create a balance between exploration and exploitation of the search space. However, like other similar approaches, SCA tends to be stuck into sub-optimal regions that it is reflected in the computational effort required to find the best values. This situation occurs due that the operators used for exploration do not work well to analyze the search space. This paper presents an improved version of SCA that considers the opposition based learning (OBL) as a mechanism for a better exploration of the search space generating more accurate solutions. OBL is a machine learning strategy commonly used to increase the performance of metaheuristic algorithms. OBL considers the opposite position of a solution in the search space. Based on the objective function value, the OBL selects the best element between the original solution and its opposite position; this task increases the accuracy of the optimization process. The hybridization of concepts from different fields is crucial in intelligent and expert systems; it helps to combine the advantages of algorithms to generate more efficient approaches. The proposed method is an example of this combination; it has been tested over several benchmark functions and engineering problems. Such results support the efficacy of the proposed approach to find the optimal solutions in complex search spaces. [ABSTRACT FROM AUTHOR]

Nowadays, learning-based modeling methods are utilized to build a precise forecast model for renewable power sources. Computational Intelligence (CI) techniques have been recognized as effective methods in generating and optimizing renewable tools. The complexity of this variety of energy depends on its coverage of large sizes of data and parameters, which have to be investigated thoroughly. This paper covered the most resent and important researchers in the domain of renewable problems using the learning-based methods. Various types of Deep Learning (DL) and Machine Learning (ML) algorithms employed in Solar and Wind energy supplies are given. The performance of the given methods in the literature is assessed by a new taxonomy. This paper focus on conducting comprehensive state-of-the-art methods heading to performance evaluation of the given techniques and discusses vital difficulties and possibilities for extensive research. Based on the results, variations in efficiency, robustness, accuracy values, and generalization capability are the most obvious difficulties for using the learning techniques. In the case of the big dataset, the effectiveness of the learning techniques is significantly better than the other computational methods. However, applying and producing hybrid learning techniques with other optimization methods to develop and optimize the construction of the techniques is optionally indicated. In all cases, hybrid learning methods have better achievement than a single method due to the fact that hybrid methods gain the benefit of two or more techniques for providing an accurate forecast. Therefore, it is suggested to utilize hybrid learning techniques in the future to deal with energy generation problems. [ABSTRACT FROM AUTHOR]

Feature selection is a well-known prepossessing procedure, and it is considered a challenging problem in many domains, such as data mining, text mining, medicine, biology, public health, image processing, data clustering, and others. This paper proposes a novel feature selection method, called AOAGA, using an improved metaheuristic optimization method that combines the conventional Arithmetic Optimization Algorithm (AOA) with the Genetic Algorithm (GA) operators. The AOA is a recently proposed optimizer; it has been employed to solve several benchmark and engineering problems and has shown a promising performance. The main aim behind the modification of the AOA is to enhance its search strategies. The conventional version suffers from weaknesses, the local search strategy, and the trade-off between the search strategies. Therefore, the operators of the GA can overcome the shortcomings of the conventional AOA. The proposed AOAGA was evaluated with several well-known benchmark datasets, using several standard evaluation criteria, namely accuracy, number of selected features, and fitness function. Finally, the results were compared with the state-of-the-art techniques to prove the performance of the proposed AOAGA method. Moreover, to further assess the performance of the proposed AOAGA method, two real-world problems containing gene datasets were used. The findings of this paper illustrated that the proposed AOAGA method finds new best solutions for several test cases, and it got promising results compared to other comparative methods published in the literature. [ABSTRACT FROM AUTHOR]

• A new multi-objective optimization method used OBL strategy, WOA and DE algorithms • It combines DE and the OBL to improve the performance of the WOA • The MWDEO results outperformed all other algorithms in most of the test problems • 32 multi-objective test problems are used in the experiments and CEC2017 problems The optimization problems are divided into a single objective and multi-objective. Single objective optimization has only one objective function; whereas, multi-objective optimization has multiple objective functions that generate the Pareto set; therefore, solving a multi-objective problem is a challenging problem. This paper presents a new multi-objective optimization method (called MWDEO) based on improved whale optimization algorithm (WOA) by combining the differential evolution (DE) algorithm and the opposition-based learning (OBL). The MWDEO uses the WOA to perform a global exploration, whereas DE is used to exploit the search space; while the OBL is applied to improve the exploration and exploitation by generating the opposite values. The proposed algorithm is evaluated using 32 multi-objective test problems besides a set of benchmark problems of CEC'2017. The experimental results are compared with nine state-of-the-art multi-objective methods. The analysis of the results showed that the proposed MWDEO outperformed all other algorithms in most of the test problems which indicates that the proposed MWDEO is competitive and effective in solving different types of multi-objective problems. [ABSTRACT FROM AUTHOR]

Here we present a new compact design of a vertical water distillation tower based on solar stills. The experimental setup consisted of a vertical tower with five water trays, supported by a metal duct and surrounded by a glass enclosure. The water yield and thermal, exergic, and economic features of the tower were investigated and analyzed. A new performance prediction hybrid model was also developed. A powerful artificial intelligence tool called the random vector functional link (RVFL) neural network was integrated with the Runge Kutta optimizer (RUN) to predict the water yield and temperature of the established tower. The model efficiency was compared to that of pure RVFL and an optimized RVFL model using a particle swarm optimizer (PSO). The drinkable water yield of the proposed design was 2.1 L/m2 (considering the tray area) and 5.3 L/m2 (considering the land use area); energy and exergy efficiencies were ∼31.7% and ∼3.3%, respectively. The cost of the produced drinkable water was approximately $0.013/L. The developed system provides considerable improvement compared with conventional designs of solar stills. The proposed RVFL–RUN model outperformed the pure RVFL and RVFL–PSO models for predicting system performance. The coefficients of determination between the experimental water productivity and water temperature and the predicted values, using the RVFL–RUN model, were 0.91 and 0.97, respectively. [Display omitted] • A new compact design of a vertical water distillation tower based is developed. • The tower was tested under actual coastal conditions. • The produced drinkable water had a low cost of $0.013/L. • The system performance was predicted by a hybrid machine learning model. [ABSTRACT FROM AUTHOR]

Nowadays, people use smart devices everywhere and for different applications such as healthcare. The Internet of Healthcare Things (IoHT) generates enormous amounts of data daily, which need exploitation and analysis to help healthcare professionals make decisions and provide a fast diagnosis. Human Activity Recognition (HAR) has received more attention due to its importance in elderly care, lifestyle improvement, and IoT systems. This paper presents a novel HAR system based on optimizing two algorithms: convolutional neural network (CNN) and the recently proposed optimization algorithm, Arithmetic Optimization Algorithm (AOA), to boost the HAR performance with fewer resources. The proposed CNN is applied to learn and extract features from input data where a modified AOA algorithm, called Binary AOA (BAOA), is used to select the most optimal features. Finally, the support vector machine (SVM) is adopted to classify the selected feature based on different activities. We evaluate the proposed HAR model with three different public datasets, UCI-HAR, WISDM-HAR, and KU-HAR datasets. Moreover, we compare the feature selection method, BAOA, to various optimization algorithms using several evaluation measures, and we found that BAOA recorded the best performance. Furthermore, we compare the proposed model to several existing HAR methods. The outcomes confirmed the competitive performance of the proposed model, which achieved 95.23%, 99.5%, and 96.8% for UCI-HAR, WISDM-HAR, and KU-HAR datasets, respectively. • Propose a new HAR system using the advantages of Metaheuristic and deep learning. • Develop a feature extraction method using deep CNN to expose relevant features. • Propose a feature selection method based on Binary Athematic Optimization Algorithm • Implement extensive evaluation experiment using three public HAR datasets. [ABSTRACT FROM AUTHOR]

Some of the important rock physics parameters, such as the shear-wave velocity and Poisson's ratio, are conventionally calculated from compressional and shear sonic well logs. Although these parameters are vital for geomechanical purposes, these types of shear sonic logs are rarely recorded for most wells. Therefore, this study aims to use ordinary well log and seismic data to predict the Poisson's ratio using some of the machine learning algorithms that are based on a proposed model calculated from a modified version of the Random Vector Functional Link (RVFL) using the Wild Geese Algorithm (WGA). This is applied as a case study in the Scarab gas field in the West Delta Deep Marine (WDDM) concession, Egypt. The main aim of using WGA is to determine the best configuration from the parameters of RVFL to enhance the process of prediction. The rock physics templates are used for interpreting the lithology and pore-fluid from well log data and RVFL-WGA. This is achieved using the cross-plot of P-impedance versus Poisson's ratio, Lambda-Rho versus Mu-Rho, Poisson's ratio versus bulk modulus and P-impedance versus Vp/Vs ratio from both methods. All cross plots are color-coded by the shale volume and hydrocarbon saturation. • The WGA method is used as a novel technique for computing the Poisson's ratio. • Computing Poisson's ratio from seismic data in the absence of some well log data. • Use of well log and seismic data to predict Poisson's ratio using machine learning. • The RVFL-WGA used to increase the validity of the prediction of Poisson's ratio. • Good matching between logs shows that machine learning tool is a reliable method. [ABSTRACT FROM AUTHOR]