Search

Atmospheric discharges offer great risks to the population and activities that involve different systems such as telecommunications, energy distribution and transportation. Lightning prediction can contribute to minimize the risks of this natural phenomenon. Therefore the present paper presents a model for lightning prediction based on satellite atmospheric sounding data, calibrated and validated with lightning data in an Amazon region particular area through an investigation that considered five period cases for validation of lightning prediction: case 1 (one hour), case 2 (two hours), case 3 (three hours), case 4 (four hours) and case 5 (five hours). The machine learning technique used to predict lightning was the Artificial Neural Network (ANN) trained with Levenberg-Marquardt backpropagation algorithm to classify modeling related to lightning prediction. This classification relied on the possibility of lightning prediction from the vertical profile of air temperature obtained from satellite NOAA-19. Results show that ANN was capable of identifying adequately the class to which a new event belongs to in relation to categories of occurrence and absence of lightning with better performance than traditional methodologies. [ABSTRACT FROM AUTHOR]

Vehicle developers and design engineers require understanding of human response to vibration for optimising the seat in order to meet the objective of passenger ride comfort. This paper attempts to develop an artificial neural networks (ANN) based model to measure biodynamic response seat to head transmissibility (STHT), incorporating factors like vibration frequency, vibration magnitude and posture for seated subjects exposed to random whole body vibration (WBV) in three different directions (vertical, fore-aft, lateral). After training the model is able to predict STHT with high accuracy when compared with the experimental values. Cross-axis coupling, i.e., excitation in one axis producing a response in the other axis, is also validated through ANN modelling in this paper. [ABSTRACT FROM AUTHOR]

Self-Organizing Maps (SOMs) are steadily more integrated as data-analysis tools in human movement and sport science. One of the issues limiting researchers' confidence in their applications and conclusions concerns the (arbitrary) selection of training parameters, their effect on the quality of the SOM and the sensitivity of any subsequent analyses. In this paper, we demonstrate how quality and sensitivity may be examined to increase the validity of SOM-based data-analysis. For this purpose, we use two related data sets where the research question concerns coordination variability in a volleyball spike. SOMs are an attractive tool for analysing this problem because of their ability to reduce the highdimensional time series to a two-dimensional problem while preserving the topological, non-linear relations in the original data. In a first step, we systematically search the SOM parameter space for a set of options that produces significantly lower continuity, accuracy and combined map errors and we discuss the sensitivity of SOM-based analyses of coordination variability to changes in training parameters. In a second step, we further investigate the effect of using different numbers of trials and variables on the SOM quality and sensitivity. These sensitivity analyses are able to validate the conclusions from statistical tests. Using this type of analysis can guide researchers to select SOM parameters that optimally represent their data and to examine how they affect the subsequent analyses. This may also enforce confidence in any conclusions that are drawn from studies using SOMs and enhance their integration in human movement and sport science. [ABSTRACT FROM AUTHOR]

This paper proposes a novel algorithm to combine two or more techniques of maximum power point tracking (MPPT) to increase the output dc power and the efficiency of photovoltaic (PV) arrays. Different MPPT methods have dissimilar responses for the same environmental circumstances. The combination of multiple methods has the advantage of ever acquiring maximum power as the environmental conditions change. The proposed algorithm is used to enhance the selection of the most suitable duty cycle of the combined methods, based on the power-voltage characteristics, to get the best tracking response. Multiple classical and/or artificial intelligence (AI)-based MPPT methods can be combined based on this selection algorithm. To demonstrate its effectiveness, two examples are illustrated. The first one is the combination of two classical MPPT methods, which are the incremental conductance (INC) and the perturb-and-observe (P&O). The second example is to combine two AI-based MPPT, which are the artificial neural network (ANN) and the fuzzy logic control (FLC). The simulation results of the application of the proposed algorithm to a grid-connected PV system model justify its capability to acquire better static and dynamic responses than the responses of individual MPPT methods. [ABSTRACT FROM AUTHOR]

Intelligent learning platforms and education information application platforms are gaining ground, owing to the wide application of modern technologies such as the Internet of Things, big data analysis, artificial intelligence, and cloud computing. However, the current platforms cannot solve specific teaching problems, and the relevant research mostly focuses on primary and secondary education. Therefore, this paper constructs and analyzes a framework of intelligent education system for higher education based on the deep learning. Firstly, the functional block diagram of the system was built up. Next, a face detection algorithm was proposed based on the multi-task convolutional neural network, a face recognition algorithm was developed based on the improved deep convolutional neural network, and the knowledge learning status of students was tracked based on the memory augmented neural network. Finally, the proposed framework was proved effective and swift through experiments. The research results expand the application scope of the deep learning in education. [ABSTRACT FROM AUTHOR]

The emergence of artificial intelligence (AI) driven keyword spotting (KWS) technologies has revolutionized human to machine interaction. Yet, the challenge of end-to-end energy efficiency, memory footprint and system complexity of current neural network (NN) powered AI-KWS pipelines has remained ever present. This paper evaluates KWS utilizing a learning automata powered machine learning algorithm called the Tsetlin Machine (TM). Through significant reduction in parameter requirements and choosing logic over arithmetic-based processing, the TM offers new opportunities for low-power KWS while maintaining high learning efficacy. In this paper, we explore a TM-based keyword spotting (KWS) pipeline to demonstrate low complexity with faster rate of convergence compared to NNs. Further, we investigate the scalability with increasing keywords and explore the potential for enabling low-power on-chip KWS. [ABSTRACT FROM AUTHOR]

A novel approach for efficient automatic voltage regulation (AVR) control using hybridized artificial neural network (ANN) model has been proposed in this research work. The novel automatic voltage regulator tuning using an improved neural network has been proposed in this paper. Artificial neural network has been used as focused time delay neural network (FTDNN). Validation is performed by comparing with the methods of feed-forward backpropagation neural networks, cascade-forward backpropagation neural networks, Elman-recurrent neural networks, focused time-delay neural networks and Distributed Time Delay Neural Networks (DTDNN). This hybridized ANN model incorporated a metaheuristic method namely Slime Mold Algorithm (SMA) for obtaining improved result on AVR control. SMA has characteristics that uses adaptive weights to simulate the process to generate feedback from the movement of biooscillator- based slime molds in foraging, exploring, and exploiting areas. The performance of the proposed method is focused on speed and rotor angle. The proposed method is compared with other neural network methods in a broad set of benchmarks to verify system efficiency. Promising results were obtained in tuning the AVR under 30 %, 60 % and 90 % loading conditions at slime mold count of 50. [ABSTRACT FROM AUTHOR]

This paper proposes a forecasting method for short-term peak electric loads a 3-layer neural network of locally active units. Each unit in the hidden layer of the neural network is activated only by input vectors in a bounded domain of vector space. This charateristic enables additional learning. Futhermore, it is supposed to provide the networks structure with information that helps to improve forcasting accurancy. The neural network is applied to daily peak load forecasting simulations in summer. The results show that the proposed method is superior to a conventional neural network with the backpropagation algorithm. To make the best use of the neural network, an error-oriented method of parameter modification is also examined. [ABSTRACT FROM AUTHOR]

Introduction: This study used artificial intelligence and strategic management to predict sports industry development in Taiwan. Through public government information, we aimed to determine the dynamics of the sports industry and analyze the current situation of domestic sports industries and sports industry sectors. We also explored national sports policies and development issues to construct a Taiwan Sports Industry Gross Domestic Product Forecasting Model that aligns with the requirements of government agencies and the sports industry. Methods: This study explored time series data for 12 sports industries and 40 sports industry sectors from 2009 to 2018. We used artificial neural networks to predict future gross domestic product (GDP). We also used the moving average method to calculate the trend direction and used strategic management and brand positioning analysis to analyze industry positioning and trend development. Results: Only one sports industry, Sports Venue or Facility Construction, had an optimistic forecast for growth, while the GDP of the remaining 11 sports industries was predicted to decline. The average GDP forecasting accuracy for the sports industry was 94% in 2017 and 97.2% in 2018. Among the 40 sports industry sectors, eight had growth forecasts, while the GDP of the other 32 sectors was predicted to decline. The average GDP forecasting accuracy for sports industry sectors was 99.5% in 2017 and 99.4% in 2018. In the strategic matrix analysis, all 12 sports industries showed a growth trend. All sports industries showed a consistent upward trend in the GDP time series, indicating overall continuous growth in the sports industry. Similarly, among the 40 sports industry sectors, the Star and Cash Cow sectors showed growth trends and trend lines in the strategic positioning matrix and GDP time series. In contrast, the Question Marks and Dogs sectors showed declining trends and trend lines. Conclusion: This study makes six specific recommendations: (1) Seek solutions for the sports industry through prediction and estimation, (2) use strategic management to chart the course for developing the sports industry, (3) explore and propose future trends in the sports industry, (4) explore and propose future trends in the various sports industry sectors, (5) define the scope of the sports industry and address significant data management and its implications, and (6) foster research and development in technology management and its academic applications. These recommendations aim to provide valuable insights and guidance for the advancement and strategic planning of the sports industry, considering future trends and technological advances. [ABSTRACT FROM AUTHOR]

Developing a photovoltaic system that successfully harvests the sun's power is one of the most difficult aspects of boosting power generation. Consequently, our study focuses on the development of a hybrid intelligent maximum power point tracking (MPPT) regulator that combines an innovative optimization approach based on the fireworks algorithm (FWA) and an artificial neural network (ANN) model. The proposed approach is examined in the first part of this study for various ANN configuration scenarios to identify the appropriate hyperparameters values and training algorithm required to converge toward the ideal objective function. After the optimization and training processes are completed, the selected FWA–ANN model is simulated as an MPPT controller using MATLAB/Simulink software and compared to the most commonly used MPPT techniques to demonstrate its effectiveness under various partial shading conditions. The results show that our proposed FWA–ANN technique using the BR and four neurons in the hidden layer reaches an excellent mean-squared error value equal to 0.1159 in the optimization process and 2.74e - 13 in the training phase. In addition, our suggested model is compared to the most widely used MPPT techniques notably, perturb and observe, particle swarm optimization, grey wolf optimization, whale optimization algorithm, and fuzzy logic controller. The obtained outcomes prove that the FWA–ANN overpasses the applied techniques by tracking the maximum power point faster with a response time between 0.0048 and 0.0261 s, a power efficiency higher than 99.5749%, that can up to 99.9977%, and an extreme reduction of oscillations in the transient and steady states for all tested cases. [ABSTRACT FROM AUTHOR]

Integration of the Internet of Things (IoT) into the fields of wastewater treatment and water quality prediction has the potential to revolutionize traditional approaches and address urgent challenges, considering the global demand for clean water and sustainable systems. This comprehensive article explores the transformative applications of smart IoT technologies, including artificial intelligence (AI) and machine learning (ML) models, in these areas. A successful example is the implementation of an IoT-based automated water quality monitoring system that utilizes cloud computing and ML methods to effectively address the above-mentioned issues. The IoT has been employed to optimize, simulate, and automate various aspects, such as monitoring and managing natural systems, water-treatment processes, wastewater-treatment applications, and water-related agricultural practices like hydroponics and aquaponics. This review presents a collection of significant water-based applications, which have been combined with the IoT, artificial neural networks, or ML and have undergone critical peer-reviewed assessment. These applications encompass chlorination, adsorption, membrane filtration, monitoring water quality indices, modeling water quality parameters, monitoring river levels, and automating/monitoring effluent wastewater treatment in aquaculture systems. Additionally, this review provides an overview of the IoT and discusses potential future applications, along with examples of how their algorithms have been utilized to evaluate the quality of treated water in diverse aquatic environments. [ABSTRACT FROM AUTHOR]

Copyright of Ingenius, Revista Ciencia y Tecnología is the property of Universidad Politecnica Salesiana and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Artvin Çoruh Üniversitesi Orman Fakültesi Dergisi is the property of Artvin Coruh University and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Highlights: The application of different types of RNA is very effective in the energy transition. ANNs are a very effective/useful tool in the fight against climate change. High capacity of ANNs to make predictions in different meteorological conditions. Artificial neural networks (ANNs) have become key methods for achieving global climate goals. The aim of this review is to carry out a detailed analysis of the applications of ANNs to the energy transition all over the world. Thus, the applications of ANNs to renewable energies such as solar, wind, and tidal energy or for the prediction of greenhouse gas emissions were studied. This review was conducted through keyword searches and research of publishers and research platforms such as Science Direct, Research Gate, Google Scholar, IEEE Xplore, Taylor and Francis, and MDPI. The dates of the most recent research were 2018 for wind energy, 2022 for solar energy, 2021 for tidal energy, and 2021 for the prediction of greenhouse gas emissions. The results obtained were classified according to the type of structure and the architecture used, the inputs/outputs used, the region studied, the activation function used, and the algorithms used as the main methods for synthesizing the results. To carry out the present review, 96 investigations were used, and among them, the predominant structure was that of the multilayer perceptron, with Purelin and Sigmoid as the most used activation functions. [ABSTRACT FROM AUTHOR]

Machine learning approaches for medical decision-making processes are valuable when both high classification accuracy and less feature requirements are satisfied. Artificial neural networks (ANNs) successfully meet the first goal with its adaptive engine, while nature-inspired algorithms are focusing on the feature selection (FS) process in order to eliminate less informative and less discriminant features. Besides engineering applications of ANN and FS algorithms, medical informatics is another emerging field using similar methods for medical data processing. Classification of psychiatric disorders is one of the major focus of medical informatics using artificial intelligence approaches. Being one of the most debilitating psychiatric diseases, bipolar disorder (BD) is frequently misdiagnosed as unipolar disorder (UD), leading to suboptimal treatment and poor outcomes. Thus, discriminating UD and BD at earlier stages of illness could therefore help to facilitate efficient and specific treatment. The use of quantitative electroencephalography (EEG) cordance as a biomarker has greatly enhanced the clinical utility of EEG in psychiatric and neurological subjects. In this context, the paper puts forward a study using two-step hybridized methodology: particle swarm optimization (PSO) algorithm for FS process and ANN for training process. The noteworthy performance of ANN-PSO approach stated that it is possible to discriminate 31 bipolar and 58 unipolar subjects using selected features from alpha and theta frequency bands with 89.89 % overall classification accuracy. [ABSTRACT FROM AUTHOR]

In this paper we will design a algorithm which used Hopfield neural network algorithm which is based on Feed Forward Back Propagation technique to avoid collision in wireless sensor network. Hopfield Neural Network uses the concepts of associative memory, pattern completion and error correction. The algorithm are design in such a way that itself is robust in case of missing data, and pattern correction in case of corrupted data to remove the collided packet from the network due to the association ability. It is based a single layer fully connected feedback network with no direct feedback connections, i.e. each single neuron is not directly connected to itself. [ABSTRACT FROM AUTHOR]

Developing a computational model for studying tribological performance is essential for computing accurate life cycle of various materials. Caused by the existence of complicated and nonlinear interactions between material surfaces, exact modeling of wear behavior is very difficult. Artificial intelligence (AI) can be used in distinguishing similar patterns in experimental data and predictive modeling of a certain material's wear behavior. In this paper, artificial neural networks (ANNs) approach, adaptive neural-based fuzzy inference system (ANFIS) technique, and fuzzy clustering method (FCM) are used to develop a simple, accurate, and applicable model for predicting the wear behavior of sinter-hardened steel parts. Three different cooling rates (0.5, 2, and 3 °C/s) were applied on six specimens made out of pre-alloyed Astaloy 85 Mo and Distaloy AB powders by powder metallurgy (PM) method. Reciprocating dry sliding wear tests were carried out on these specimens with three different loads. The empirical results were assorted in two different batches. One was used along with the mentioned artificial intelligence approaches to develop three wear behavior models. In order to verify and compare these models, predicted results gained from these models were compared to the second batch of the results. Outcome of the models were promising. Using magnitude of two statistical functions, root-mean squared error and coefficient of multiple determinations, we showed that our predictions are in great correlation with experimental data and the best performance can be obtained using ANN method. [ABSTRACT FROM AUTHOR]

In blasting works, the aim is to provide proper rock fragmentation and to avoid undesirable environmental impacts such as back-break. Therefore, predicting fragmentation and back-break is a significant step in achieving a technically and economically successful outcome. In this paper, considering the robustness of artificial intelligence methods utilized in engineering problems, an artificial neural network (ANN) was applied to predict rock fragmentation and back-break; an artificial bee colony (ABC) algorithm was also utilized to optimize the blasting pattern parameters. In this regard, blasting parameters, including burden, spacing, stemming length, hole length and powder factor, as well as back-break and fragmentation were collected at the Anguran mine in Iran. Root mean square error (RMSE) values equal to 2.76 and 0.53 for rock fragmentation and back-break, respectively, reveal the high reliability of the ANN model. In addition, ABC algorithm results suggest values of 29 cm and 3.25 m for fragmentation and back-break, respectively. For comparison purposes, an empirical model (Kuz-Ram) was performed to predict the mean fragment size in the Anguran mine. A mean fragment size of 33.5 cm shows the ABC algorithm can optimize rock fragmentation with a high degree of accuracy. [ABSTRACT FROM AUTHOR]

In recent years great attention has been paid to studies on artificial intelligence since it can be applied easily to several areas like medical diagnosis, engineering and economics, among others. In this paper we present an example in medicine which aims to diagnose the patients with high prostate cancer risk using a multi-criteria decision making method. Our datas set is prostate specific antigen (PSA), free prostate specific antigen (fPSA), prostate volume (PV) and age factors of 78 patients from Necmettin Erbakan University Meram Medicine Faculty. An artificial neural network related to the consistency of convergence coefficients calculated by the Fuzzy TOPSIS method [32] is established. Thus, we understand the accuracy of the results from the Fuzzy TOPSIS method. [ABSTRACT FROM AUTHOR]

The forecasting of prices for electricity balancing reserve power can essentially improve the trading positions of market participants in competitive auctions. Having identified a lack of literature related to forecasting balancing reserve prices, we deploy approaches originating from econometrics and artificial intelligence and set up a forecasting framework based on autoregressive and exogenous factors. We use SARIMAX models as well as neural networks with different structures and forecast based on a rolling one‐step forecast with reestimation of the models. It turns out that the naive forecast performs reasonably well but is outperformed by the more advanced models. In addition, neural network approaches outperform the econometric approach in terms of forecast quality, whereas for the further use of the generated models the econometric approach has advantages in terms of explaining price drivers. For the present application, more advanced configurations of the neural networks are not able to further improve the forecasting performance. [ABSTRACT FROM AUTHOR]

There are many approaches for accurate and automatic classification of brain MRI. In this paper, a simple approach for automatic detection and classification is presented. Artificial Neural Network has been utilized for brain MRI classification as malignant or benign. The approach consists of three stages namely pre processing, features' extraction and classification. In pre-processing stage, filters are applied for the removal of noise. In the features' extraction phase, color moments are extracted as mean features from the MRI images and the color moments extracted are presented to simple feed forward artificial neural network for classification. The method was applied using total 70 images with 25 normal images and 45 abnormal images. The classification accuracy was found to be 88.9% for training data, 94.9% for validation data and 94.2% for testing data whereas the overall accuracy of 91.8% was observed. [ABSTRACT FROM AUTHOR]

This paper deals with the implementation of an Artificial Neural Network on reconfigurable hardware. The authors developed an application for character recognition using a feedforward backpropagation neural network, developed on an FPGA. In order to carry out such implementation the computational model of the neural network is translated into a FPGA synthesizable model using the Matlab/Simulink environment as well as the System Generator Xilinx tool. The results are illustrated in a prototype developed on an Atlys board. The authors focus the analysis and discussion on the main aspects considered to synthetize an ANN on an FPGA as well as the methodology to follow during such implementation, which are the main contributions of this paper. [ABSTRACT FROM AUTHOR]

Void fraction plays a vital role in diverse industries like oil, petrochemical, etc., which involve a wide range of fluids, including two-phase and three-phase fluids. Various procedures are used for the measurement of the void fraction, with one of the most popular being capacitance-based sensors. The characteristics of the fluid inside the pipe affect the output of this type of sensor, and every property, such as temperature, pressure, and density, plays a role. This paper presents the use of an Artificial Neural Network (ANN) and a combined capacitance-based sensor to measure the void fraction of a two-phase air-water homogeneous fluid. The aim is to develop a system that can predict void fraction independent of temperature and pressure changes. To achieve this, the COMSOL Multiphysics software was used to design and simulate two widely used sensors, concave and ring, to create a combined capacitance sensor. Simulations were conducted for the implemented sensor in different temperature ranges (275–370 K) and pressure ranges (1–500 Bar). After a large number of simulations and producing 3780 data from the combined sensor, they were used as inputs to train the proposed MLP ANN network. The presented model provides a new metering system that can accurately estimate the amount of the void fraction of a two-phase air-water homogeneous fluid independent of temperature and pressure changes and had a low error which means the MAE is equal to 4.868. • A combined capacitive sensor and ANN were used to measure the void fraction. • This system can measure void fraction independent of temperature and pressure. • COMSOL was used to design and simulate the combined capacitive sensor. • After a large number of simulations, they were used as inputs of MLP network. • The MAE of presented system is equal to 4.868 which is a low error. [ABSTRACT FROM AUTHOR]

Voltage instability is a serious condition that can occur in a power system. An imbalance in reactive power, inadequate utilization of voltage control devices, loss of a component or an abrupt rise in load demand can cause this entire disturbance which leads a system to blackout, either partial or complete. In order to avoid the condition of voltage collapse, we need to predict the state of buses in the system so that we can prevent the occurrence of major outages. This research puts forward two methods for voltage collapse prediction. The first one is to compute a new line stability index (NLSI_1) through an artificial neural network, and the other one is to present a normalized power change index (NPCI) for the prediction. These indices are applied and examined on the IEEE-14 bus system; they check the state of the buses and tell us about the stability of the system. A detailed methodology and explanation are given in the following sections. According to the neural network outcomes, the normalized power change index (NPCI) proves to be more accurate than NLSI_1 for the test system. [ABSTRACT FROM AUTHOR]

Purpose: Artificial intelligence (AI) models are demonstrating day by day that they can find long-term solutions to improve wastewater treatment efficiency. Artificial neural networks (ANNs) are one of the most important of these models, and they are increasingly being used to forecast water resource variables. The goal of this study was to create an ANN model to estimate the removal efficiency of biological oxygen demand (BOD), total nitrogen (TN), total phosphorus (TP) and total suspended solids (TSS) at the effluent of various primary and secondary treatment methods in a wastewater treatment plant (WWTP). Design/methodology/approach: The MATLAB App Designer model was used to generate the data set. Various combinations of wastewater quality data, such as temperature(T), TN, TP and hydraulic retention time (HRT) are used as inputs into the ANN to assess the degree of effect of each of these variables on BOD, TN, TP and TSS removal efficiency. Two of the models reflect two different types of primary treatment, while the other nine models represent different types of subsequent treatment. The ANN model's findings are compared to the MATLAB App Designer model. For evaluating model performance, mean square error (MSE) and coefficient of determination statistics (R2) are utilized as comparative metrics. Findings: For both training and testing, the R values for the ANN models were greater than 0.99. Based on the comparisons, it was discovered that the ANN model can be used to estimate the removal efficiency of BOD, TN, TP and TSS in WWTP and that the ANN model produces very similar and satisfying results to the APPDESIGNER model. The R-value (Correlation coefficient) of 0.9909 and the MSE of 5.962 indicate that the model is accurate. Because of the many benefits of the ANN models used in this study, it has a lot of potential as a general modeling tool for a range of other complicated process systems that are difficult to solve using conventional modeling techniques. Originality/value: The objective of this study was to develop an ANN model that could be used to estimate the removal efficiency of pollutants such as BOD, TN, TP and TSS at the effluent of various primary and secondary treatment methods in a WWTP. In the future, the ANN could be used to design a new WWTP and forecast the removal efficiency of pollutants. [ABSTRACT FROM AUTHOR]

This paper presents LS-VisionDraughts: an efficient unsupervised evolutionary learning system for Checkers whose contribution is to automate the process of selecting an appropriate representation for the board states - by means of Evolutionary Computation - keeping a deep look-ahead (search depth) at the moment of choosing an adequate move. It corresponds to a player Multi Layer Perceptron Neural Network whose weights are updated through an evaluation function that is automatically adjusted by means of the Temporal Difference methods. A Genetic Algorithm automatically chooses a concise and efficient set of functions, which describe various scenarios associated with Checkers - called features - to represent the board states in the input layer of the Neural Network. It means that each individual of the Genetic Algorithm is a candidate set of features that is associated to a distinct Multi Layer Perceptron Neural Network. The output layer of the Neural Network is a real number ( prediction) that indicates to which extent the input state is favorable to provide a better agent performance. In LS-VisionDraughts, a particular version of the search algorithm Alpha-Beta, called fail-soft Alpha-Beta, combined with Table Transposition, Iterative Deepening and ordered tree, uses this prediction value to choose the best move corresponding to the current board state. The best individual is chosen by means of numerous tournaments involving these selfsame Neural Networks. The architecture of LS-VisionDraught is inspired on the agent NeuroDraughts. However, the former system enhances the performance of the latter by automating the selection of the features through Evolutionary Computation and by replacing its Minimax search algorithm with the improved search strategy resumed above. This procedure allows for a 95 % reduction in the search runtime. Further, it remarkably increases the search tree depth. The results obtained from evaluative tournaments confirm the advances of LS-VisionDraughts compared to its opponents. It is however important to point out that LS-VisionDraughts learns practically without human supervision, contrary to the current automatic world champion Chinook, which has been built in a strongly supervised manner. [ABSTRACT FROM AUTHOR]

Purpose – Nowadays, in order to improve current applications, industry incorporates to their solution approaches artificial intelligence techniques and methodologies like Fuzzy Logic, neural networks and/or genetic algorithms (GA). Artificial intelligence techniques complement classical methodologies and include concepts that simulate the way humans solve problems or how processes work in nature. In this work, the Fuzzy Logic system cancels the effects of load perturbances in an energy plant, by implementing a secondary controller which complements the main controller. The purpose of this paper is to use GA to tune this new secondary controller. The authors particularize the proposal for three specific applications: control the angular speed and position of a Direct Current (DC) motor and control the output voltage of a DC/DC buck converter. Design/methodology/approach – The authors use GA for tuning a Proportional-Integral Fuzzy Controller (PI-Fuzzy). The proposal defines a new objective function in comparison with literature approaches. The main key in the new objective function is combining the best features of Integral Square Error (ISE) function and taking out the overshoot response. Findings – In order to demonstrate the proposed methodology based on GA tuning a PI-Fuzzy, the authors apply the literature benchmark to the solution. The results are compared with the following techniques: Robust control, continuous PID control, discrete PID control, Optimal Control, Fuzzy Control and Artificial Neural Network based control. Comparisons are presented in terms of setting time and overshot. Originality/value – Results demonstrate that ISE or integral of absolute value of error function do not provide the desired response. Achieved results demonstrate the usefulness of the proposal to eliminate the overshoot of the traditional behaviour without lost any of the main features of the literature methodologies. [ABSTRACT FROM AUTHOR]

In this paper, artificial neural network (ANN) was applied to model and study the signature of hysteresis phenomena in hydrological processes for the Eel River watershed located in California. Because of the nonlinear and stochastic nature of hysteresis phenomena, it is reasonable to expect ANN to develop a model that efficiently considers hysteretic loops. In this study, hysteretic loops were studied from different aspects such as forms, classification, and effective factors of creation. In rainfall-runoff modeling, counterclockwise loops were mostly observed, whereas in the runoff-sediment process, clockwise loops prevailed. Random or eight-shaped loops were expected in runoff hydrographs with several peaks. A direct relationship was detected between the width of the loops and the area of the subbasin. Larger areas led to wider hysteretic loops. The results showed that ANN efficiently considers hysteresis signs when modeling hydrological processes and can lead to appropriate performance. [ABSTRACT FROM AUTHOR]

This paper presents a novel technique for hand gesture recognition through human-computer interaction based on shape analysis. The main objective of this effort is to explore the utility of a neural network-based approach to the recognition of the hand gestures. A unique multi-layer perception of neural network is built for classification by using back-propagation learning algorithm. The goal of static hand gesture recognition is to classify the given hand gesture data represented by some features into some predefined finite number of gesture classes. The proposed system presents a recognition algorithm to recognize a set of six specific static hand gestures, namely: Open, Close, Cut, Paste, Maximize, and Minimize. The hand gesture image is passed through three stages, preprocessing, feature extraction, and classification. In preprocessing stage some operations are applied to extract the hand gesture from its background and prepare the hand gesture image for the feature extraction stage. In the first method, the hand contour is used as a feature which treats scaling and translation of problems (in some cases). The complex moment algorithm is, however, used to describe the hand gesture and treat the rotation problem in addition to the scaling and translation. The algorithm used in a multi-layer neural network classifier which uses back-propagation learning algorithm. The results show that the first method has a performance of 70.83% recognition, while the second method, proposed in this article, has a better performance of 86.38% recognition rate. [ABSTRACT FROM AUTHOR]

Adaptive neural network-based fuzzy inference system (ANFIS) is an artificial intelligent neuro-fuzzy technique used for modeling and control of ill-defined and uncertain systems. The present paper proposes this novel technique of ANFIS to predict the tensile strength of inertia friction-welded tubular pipe joints with the aid of artificial neural network approach combined with the principle of fuzzy logic. The proposed model is multiple input–single output type of model which uses rotational speed and forge load as input signals. The set of rules has been generated directly from the experimental data using ANFIS. The performance of the proposed model is validated by comparing the predicted results with the actual practical results obtained by conducting the confirmation experiments. The application of χ2 test confirms that the values of tensile strength predicted by proposed ANFIS model are well in agreement with the experimental values at 0.1 % level of significance. The proposed model can also be used as intelligent online adaptive control model for pipeline welding. [ABSTRACT FROM AUTHOR]

Human falls are an issue that especially affects elderly people, resulting in permanent disabilities or even in the person's death. Preventing human falls is a social desire, but it is almost impossible to achieve because it is not possible to ensure full prevention. A possible solution is the detection of human falls in near real-time so that help can quickly be provided. This has the potential to greatly reduce the severity of the fall in long-term health consequences. This work proposes a solution based on the internet of things devices installed in people's homes. The proposed non-wearable solution is non-intrusive and can be deployed not only in homes but also in hospitals, rehabilitation facilities, and elderly homes. The solution uses a three-layered computation architecture composed of edge, fog, and cloud. A mathematical model using the Morlet wavelet and an artificial intelligence model using artificial neural networks are used for human fall classification; both approaches are compared. The results showed that the combination of both models is possible and brings benefits to the system, achieving an accuracy of 92.5% without false negatives. [ABSTRACT FROM AUTHOR]

The paper presents a new security aspect for a Mobile Ad-Hoc Network (MANET)-based IoT model using the concept of artificial intelligence. The Black Hole Attack (BHA) is considered one of the most affecting threats in the MANET in which the attacker node drops the entire data traffic and hence degrades the network performance. Therefore, it necessitates the designing of an algorithm that can protect the network from the BHA node. This article introduces Ad-hoc On-Demand Distance Vector (AODV), a new updated routing protocol that combines the advantages of the Artificial Bee Colony (ABC), Artificial Neural Network (ANN), and Support Vector Machine (SVM) techniques. The combination of the SVM with ANN is the novelty of the proposed model that helps to identify the attackers within the discovered route using the AODV routing mechanism. Here, the model is trained using ANN but the selection of training data is performed using the ABC fitness function followed by SVM. The role of ABC is to provide a better route for data transmission between the source and the destination node. The optimized route, suggested by ABC, is then passed to the SVM model along with the node's properties. Based on those properties ANN decides whether the node is a normal or an attacker node. The simulation analysis performed in MATLAB shows that the proposed work exhibits an improvement in terms of Packet Delivery Ratio (PDR), throughput, and delay. To validate the system efficiency, a comparative analysis is performed against the existing approaches such as Decision Tree and Random Forest that indicate that the utilization of the SVM with ANN is a beneficial step regarding the detection of BHA attackers in the MANET-based IoT networks. [ABSTRACT FROM AUTHOR]

Today, embedded systems (ES) tend towards miniaturization and the carrying out of complex tasks in applications such as the Internet of Things, medical systems, telecommunications, among others. Currently, ES structures based on artificial intelligence using hardware neural networks (HNNs) are becoming more common. In the design of HNN, the activation function (AF) requires special attention due to its impact on the HNN performance. Therefore, implementing activation functions (AFs) with good performance, low power consumption, and reduced hardware resources is critical for HNNs. In light of this, this paper presents a hardware-based activation function-core (AFC) to implement an HNN. In addition, this work shows a design framework for the AFC that applies a piecewise polynomial approximation (PPA) technique. The designed AFC has a reconfigurable architecture with a wordlength-efficient decoder, i.e., reduced hardware resources are used to satisfy the desired accuracy. Experimental results show a better performance of the proposed AFC in terms of hardware resources and power consumption when it is compared with state of the art implementations. Finally, two case studies were implemented to corroborate the AFC performance in widely used ANN applications. [ABSTRACT FROM AUTHOR]

Current methods of estimating the behaviour of marine composite structures under pressure due to slamming as a result of high waves are based on trial and error or oversimplification. Normally under these conditions the non-linearities of these structures are often neglected and, in order to compensate, an overestimated safety factor is employed. These conservative approaches can result in heavier and overdesigned structures. In this paper, a new semi-empirical method is proposed that overcomes some of these problems. This work involved the use of an artificial neural network (ANN) combined with strain gauge data to enable real-time in-service load monitoring of large marine structural panels. Such a tool has other important applications, such as monitoring slamming or other transient hydrostatic loads that can ultimately affect fatigue life. To develop this system, a glass fibre-reinforced polymer (GFRP) composite panel was used due to its potential for providing a non-linear response to pressure or slamming loads. It was found that the ANN was able to predict normal loads applied at different locations on the panel accurately. This method is also capable of predicting loads on the marine structure in real time. [ABSTRACT FROM AUTHOR]

Copyright of Arabian Journal for Science & Engineering (Springer Science & Business Media B.V. ) is the property of Springer Nature and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Various research projects have attempted to build a program that learns to play chess game, given little or no prior knowledge beyond the rule of the game. A typical chess playing engine exhaustively explores the moving possibilities from a chessboard configuration to choose what the next best move to play is. The brute- force method used by the Deep Blue chess machine has made huge impact in the field of artificial intelligence, but is immensely resource hungry. This paper presents a very simple and efficient approach to develop an intelligent chess engine which will hint at the best possible move using the evolutionary and adaptive computing technique on learning from the human grandmasters. [ABSTRACT FROM AUTHOR]

Many of today's most successful planners perform a forward heuristic search. The accuracy of the heuristic estimates and the cost of their computation determine the performance of the planner. Thanks to the efforts of researchers in the area of heuristic search planning, modern algorithms are able to generate high-quality estimates. In this paper we propose to learn heuristic functions using artificial neural networks and support vector machines. This approach can be used to learn standalone heuristic functions but also to improve standard planning heuristics. One of the most famous and successful variants for heuristic search planning is used by the Fast-Forward (FF) planner. We analyze the performance of standalone learned heuristics based on nature-inspired machine learning techniques and employ a comparison to the standard FF heuristic and other heuristic learning approaches. In the conducted experiments artificial neural networks and support vector machines were able to produce standalone heuristics of superior accuracy. Also, the resulting heuristics are computationally much more performant than related ones. [ABSTRACT FROM AUTHOR]

One of the first steps in marine structural design is to calculate the wave-induced loads and load combinations. In contrast with both the hydrostatic loads and the self-weight loads which can be evaluated with a high degree of confidence, it is more difficult to measure the in-service hydrodynamic loads generated by sea waves. Direct pressure load measurement techniques can currently provide only data at finite locations while classical analytical techniques require knowledge of all the parameters that influence the load and that each parameter is studied independently. Therefore, a novel technique is required to overcome these limitations by providing a method of measuring the pressure load over large areas with relatively few sensors and minimal data collection. This paper reports research undertaken to develop an inverse problem approach utilising an artificial neural network for measurement of the pressure loads experienced by marine structures. The suitability and performance of utilising an artificial neural network for quantifying the pressure load applied to a marine structure is presented. It was found that the artificial neural network was able to estimate accurately the pressure loads applied to up to 12 locations on the structure. It is concluded that the inverse problem approach can be used to estimate the applied loads on the marine structure in real time from strain measurements. [ABSTRACT FROM AUTHOR]

Abstract: This paper develops a high performance PI based controller for an Interior Permanent Magnet Synchronous Motor (IPMSM) drive. An artificial neural network is used for on-line tuning of the PI controller. The Genetic Algorithm (GA) has been used in this work in order to obtain the optimized values of the controller parameters for precise speed control for different operating conditions over a wide speed range. In this paper, an integral Anti-Windup (AW) strategy for the PI speed controller is also utilized to suppress the undesired side effect known as integrator windup when large set-point changes are made. The optimal behavior of the drive can be achieved by considering two control strategies: Maximum Torque Per Ampere (MTPA) and Flux-Weakening (FW). In developing the proposed controller, the PI controller parameters and, also, the anti-windup strategy are optimized by GA for some operating conditions, in a closed loop vector control scheme. By obtaining the parameters at a number of points in the possible operating region, a look-up table approach has been completed. Then, an ANN is trained by this look-up table. Ultimately, the well-trained ANN is utilized for on-line tuning of the controller parameters to ensure optimum drive performance under different disturbances and operating conditions. [Copyright &y& Elsevier]

Abstract: The joint challenge of global pollution and depletion of fossil fuels is driving intense search into alternative renewable sources. This paper reports the modeling and optimization of biogas production on mixed substrates of saw dust, cow dung, banana stem, rice bran and paper waste using Artificial Neural Network (ANN) coupling Genetic Algorithm (GA). Data from twenty five mini-pilot biogas fermentations were used to train and validate a structured ANN with a topology of 5-2-1. The model served as fitness function for GA optimization process. An optimized substrate profile emerged with a predicted biogas performance of 10.144L. Evaluation of the optimal profile gave a biogas production of 10.280L, thus an increase of 8.64%, and an early biogas production initiated on the 3rd day of fermentation against the 8th day in non-optimized system. ANN coupling GA efficiently modeled the non-linear behavior of the process. A recipe for an optimum biogas production using the above co-substrates has been elucidated. [Copyright &y& Elsevier]

This paper presents different artificial intelligence (AI) techniques for crack identification in curvilinear beams based on changes in vibration characteristics. Vibration analysis has been performed by applying the finite element method (FEM) to compute natural frequencies and frequency response functions (FRFs) for intact and damaged beams. The analysis reveals the changes in natural frequencies and amplitudes of FRFs of the beams for cracks of different sizes at different locations. These changes are used as input data for single and multiple artificial neural networks (ANN) and multiple adaptive neuro-fuzzy inference systems (ANFIS) in order to predict the size of the crack and its location. To avoid large models, the principal component analysis (PCA) approach has been carried out to reduce the computed FRFs data. The analysis of different techniques shows that the average prediction errors in the multiple ANN models is less than those in the single ANN model and in the multiple ANFIS. It is shown that the cracks longer than 5 mm can be located with satisfactory accuracy, even if the input data are corrupted with various level of noise. Multiple ANFIS is adopted to construct a more reliable and less sensitive model for noise excitation. [ABSTRACT FROM AUTHOR]

In this paper, an artificial neural network (ANN) model for the early-age autogenous shrinkage of concrete is proposed. The model inputs include the cement content, water-cement ratio (w/c), type and percentage of supplementary cementitious materials, total aggregate volume, curing temperature, and hydration age. The autogenous shrinkage of concrete is the model output. The autogenous shrinkage database assembled and used in the training of the proposed ANN is considered a contribution to the state of the art of knowledge; it includes testing results on modern concretes under various environmental conditions. The developed ANN model exhibited excellent capability in capturing complex effects and interactions among model inputs on the development of autogenous shrinkage. Subsequent to model validation, a parametric study was carried out to identify the effects of input variables on the evolution of autogenous shrinkage. The trained ANN model demonstrated the ability of predicting the autogenous shrinkage behavior, not only of traditional concrete mixtures, but also that of modern concrete mixtures such as reactive powder concrete, which are characterized by very low w/c. [ABSTRACT FROM AUTHOR]

The problem in cryptanalysis can be described as an unknown and the neural networks are ideal tools for black-box system identification. In this paper, a mathematical black-box model is developed and system identification techniques are combined with adaptive system techniques, to construct the Neuro-Identifier. The Neuro-Identifier is discussed as a black-box model to attack the target cipher systems. In this paper, a new addition in cryptography has been presented and the methods of block Simplified DES (SDES) crypto systems are discussed. The constructing of Neuro-Identifier mode is to achieve two objectives: The first is to emulator construction Neuro-model for the target cipher system, while the second is to (cryptanalysis) determine the key from given plaintext-ciphertext pair. [ABSTRACT FROM AUTHOR]

In this work we evolution the morphology and the behavior of the virtual creatures. The morphology is defined by rigid bodies as capsules, cylinders, cones, spheres, or parallelepipeds, and the mass and size may change. The rigid bodies are joined by spherical joints with customizable restrictions of angular limits within a given range in each degree of freedom, so to model any type of rotational joint. The behavior is modeled by an Artificial Neural Network, which receives data from all sensors and transmits the amount of moment of force that must be exerted by each effector, so to induce motion to the creature. Finally, the evolution of morphology and behavior is carried out using Particle Swarm Optimization (PSO), where each particle encodes the morphology and behavior of one creature. In this way, this paper proposes a co-evolutionary process where the behavior and the morphology of the creatures are defined. [ABSTRACT FROM PUBLISHER]

In open channels, free overfall can be used as a flow-measuring device in various flow regimes for different shapes of channels. The aim of this paper is to accurately estimate the discharge in rectangular channels by applying four soft computing models [i.e., artificial neural network (ANN), gene expression programming (GEP), multivariate adaptive regression spline (MARS) and M5 tree model]. The variables including brink depth, roughness coefficient, channel width and channel bed slope taken from earlier published works were used as inputs for the models. Data were divided according to three different splitting scenarios, 50%–50%, 60%–40% and 75%–25%, for training-testing phases to obtain more robust evaluation of the models. The computed discharges were then compared with experimental results. In order to evaluate the accuracy of discharge estimations by ANN, GEP, MARS and M5 tree models, six statistical measures including correlation coefficient (R), mean absolute error (MAE), root mean square error (RMSE), Nash-Sutcliffe (NS), Willmott index (WI) and Legates and McCabe index (LMI) have been applied. For different training-testing scenarios, the performance of the ANN model is better than the other methods. Regarding 50%–50% training-testing scenario, ANN has the best accuracy with R, RMSE, MAE, NS, WI and LMI of 0.994, 0.004 m3/s/m, 0.002 m3/s/m, 0.986, 0.999 and 0.909 by considering all inputs. • Soft computing models are used in predicting discharge with free overfall. • y e , n, b and S 0 variables are used as inputs of models. • Several training-testing scenarios were used for modeling the discharge. • The ANN model provides the best estimate. [ABSTRACT FROM AUTHOR]

Abstract In this paper, numerous aero-hydro-servo-elastic coupled simulations are carried out in time-domain to observe the performance of the real-time thrust acting on the rotor of the OC3-Hywind offshore floating wind turbine. And the studying focuses on investigating the correlation between inputs (surge motion, pitch motion, wind conditions, etc.) and the targeted output (rotor thrust) in the time domain. Besides, artificial intelligence (AI) techniques are used to estimate a prediction model of real-time thrust based on the data from simulations. To predict the thrust, data for four comparative coupled environmental conditions are considered, by which the effect of turbulence and wave spectrum on the thrust force is also investigated. Moreover, a series of simulations of frequency-increasing regular wave conditions and speed-increasing wind conditions are carried out to observe their effect on the real-time rotor thrust. Additionally, the impact of the pitch and surge RAOs of the floating foundation and the wind velocity are quantitatively studied. It reveals that the high-frequency response of thrust is dominated by wave change, whereas low-frequency response is dominated by wind change. Besides, one simulation model of the thrust acting on the rotor is estimated regarding high-frequency and low-frequency response separately to account the dominating influence. [ABSTRACT FROM AUTHOR]

This paper aims to introduce a computer-based estimation and compensation method for diametral errors in cantilever bar turning without additional hardware requirements. In the error estimation method, the error characteristics of workpieces are determined experimentally depending on cutting speed, depth of cut, feed rate, workpiece diameter, length from the chuck and the geometric error sum of CNC lathe. An Artificial Neural Network (ANN) model is trained using these experimental error characteristics for estimation of the error. The ANN model estimated the workpiece dimensional errors with a good accuracy. Error correction is realised via turning of workpieces with a CNC part program which modified based on the estimated error profile. The dimensional errors are reduced approximately by 90% with the proposed method. [ABSTRACT FROM AUTHOR]

This paper presents an efficient two-stage classifier based on artificial neural network (ANN) concept to discriminate different types of three-phase unbalanced voltage sags at the location of power quality monitoring. In the first stage, the general type of unbalanced voltage sag (C and D) in terms of number of phases undergoing voltage drop is detected. In the next stage, the symmetrical phase is identified. Different classification approaches such as six-phase (SP), symmetrical components (SC) and three-phase three-angle (TPTA) algorithms have been previously developed to characterize and discriminate six types of unbalanced voltage sags, but they are not fully reliable because of possible incorrect results reported. The proposed classifier is widely tested and compared with three aforementioned algorithms to validate its reliability and efficiency. It is concluded that the learning intelligence of the proposed classifier is its strong point to be superior to those classifiers exclusively employing mathematical operations. [ABSTRACT FROM AUTHOR]

Copyright of ITU Journal Series D: Engineering is the property of Istanbul Technical University and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

This paper describes two artificial intelligence techniques for prediction of maximum dry density (MDD) and unconfined compressive strength (UCS) of cement stabilized soil. The first technique uses various artificial neural network (ANN) models such as Bayesian regularization method (BRNN), Levenberg- Marquardt algorithm (LMNN) and differential evolution algorithm (DENN). The second technique uses the support vector machine (SVM) that is firmly based on the theory of statistical learning theory, uses regression technique by introducing ε-insensitive loss function has been adopted. The inputs of both models are liquid limit (LL), plasticity index (PI), clay fraction (CF)%, sand (S)%, gravel Gr (%), moisture content (MC) and cement content (Ce). The sensitivity analyses of the input parameters have been also done for both models. Based on different statistical criteria the SVM models are found to be better than ANN models for the prediction of MDD and UCS of cement stabilized soil. [ABSTRACT FROM AUTHOR]