Search

Today according to social media, the internet, Etc. Data is rapidly produced and occupies a large space in systems that have resulted in enormous data warehouses; the progress in information technology has significantly increased the speed and ease of data flow.text mining is one of the most important methods for extracting a useful model through extracting and adapting knowledge from data sets. However, many studies have been conducted based on the usage of deep learning for text processing and text mining issues.The idea and method of text mining are one of the fields that seek to extract useful information from unstructured textual data that is used very today. Deep learning and machine learning techniques in classification and text mining and their type are discussed in this paper as well. Neural networks of various kinds, namely, ANN, RNN, CNN, and LSTM, are the subject of study to select the best technique. In this study, we conducted a Systematic Literature Review to extract and associate the algorithms and features that have been used in this area. Based on our search criteria, we retrieved 130 relevant studies from electronic databases between 1997 and 2021; we have selected 43 studies for further analysis using inclusion and exclusion criteria in Section 3.2. According to this study, hybrid LSTM is the most widely used deep learning algorithm in these studies, and SVM in machine learning method high accuracy in result shown. [ABSTRACT FROM AUTHOR]

As the world's transport infrastructure ages, the importance of bridge condition monitoring is becoming increasingly acknowledged. Large-scale deployment of existing inspection and monitoring techniques is infeasible due to cost and logistical challenges. The concept of using sensors located within vehicles for low cost 'drive-by' monitoring has become the focus of much attention in recent years. This paper presents a new data-driven approach for drive-by bridge monitoring. Machine learning techniques are leveraged to allow the influence of vehicle speed to be considered and the Operating Deflection Shape Ratio (ODSR) is presented as an alternative damage-sensitive feature to the commonly used frequency spectrum. Extensive laboratory experiments demonstrate that the method is capable of detecting midspan cracking and seized bearings. A statistical classification approach is adopted to classify damage indicators as either 'damaged' or 'healthy'. Classification accuracy is seen to vary between 65-96% and is similar whether using the frequency spectrum or ODSR. Based on the results of the laboratory testing, it is expected that this approach could be implemented on a large scale to act as an early warning tool for infrastructure owners to identify bridges presenting signs of distress or deterioration. [ABSTRACT FROM AUTHOR]

In the epoch characterized by the anticipation of autonomous vehicles, the quality of the embedded system software, its reliability, safety, and security is significant. The testing of embedded software is an increasingly significant element of the development process. The application of artificial intelligence (AI) algorithms in the process of testing embedded software in vehicles constitutes a significant area of both research and practical consideration, arising from the escalating complexity of these systems. This paper presents the preliminary development of the AVESYS framework which facilitates the application of open-source artificial intelligence algorithms in the embedded system testing process. The aim of this work is to evaluate its effectiveness in identifying anomalies in the test environment that could potentially affect testing results. The raw data from the test environment, mainly communication signals and readings from temperature, as well as current and voltage sensors are pre-processed and used to train machine learning models. A verification study is carried out, proving the high practical potential of the application of AI algorithms in embedded software testing. [ABSTRACT FROM AUTHOR]

Numerous data centers have adopted heterogeneous computing server to accelerate the processing speed with various applications. However, as the growth of efficiency, the issue of high power consumption is increasingly becoming crucial. Traditional researchers focus on the developing strategies for power efficiency that neglects the importance of power prediction that substantially impacts on energy planning on data center. Different to the previous work, this paper utilizes the advantage of Artificial Neural Network (ANN) to design and implement an improved algorithm of power consumption prediction on heterogeneous computing server with various types of jobs. First, the impact of multi-type of jobs has been taken into account, i.e., CPU-intensive, memory-intensive, I/O-intensive and GPU-intensive. We collect the data trace from these jobs by a set of benchmarks. Then, based on the collected data trace, power prediction algorithm has been established, so that developing an improved ANN-based power consumption prediction algorithm with CNN-BiLSTM neural network and attention mechanism. Specifically, one dimensional CNN is utilized to perform local feature extraction and dimension reduction on the input, the BiLSTM network is adopted to extract high-level features from the above results. The miscellaneous features extracted are filtered out by using attention mechanism. Last, the experiment has been conducted, and the peculiarity for four types of jobs has been discussed. Compared with the latest proposed ANN-based prediction power algorithms, our proposed algorithm has better performance in prediction accuracy on power consumption. [ABSTRACT FROM AUTHOR]

A smart grid is a promising use-case of AIoT (AI (artificial intelligence) across IoT (internet of things)) that enables bidirectional communication among utilities that arises with demand response (DR) schemes for demand-side management (DSM) and consumers that manage their power demands according to received DR signals. Disaggregating composite electric energy consumption data from a single minimal set of plug-panel current and voltage sensors installed at the electric panel in a practical field of interest, nonintrusive appliance load monitoring (NIALM), a cost-effective load disaggregation approach for (residential) DSM, is able to discern individual electrical appliances concerned without accessing each of them by individual plug-load power meters (smart plugs) deployed intrusively. The most common load disaggregation approaches are based on machine learning algorithms such as artificial neural networks, while approaches based on evolutionary computing, metaheuristic algorithms considered as global optimization and search techniques, have recently caught the attention of researchers. This paper presents a genetic algorithm, developed in consideration of parallel evolutionary computing, and aims to address NIALM, whereby load disaggregation from composite electric energy consumption data is declared as a combinatorial optimization problem and is solved by the algorithm. The algorithm is accelerated in parallel, as it would involve large amounts of NIALM data disaggregated through evolutionary computing, chromosomes, and/or evolutionary cycles to dominate its performance in load disaggregation and excessively cost its execution time. Moreover, the evolutionary computing implementation based on parallel computing, a feed-forward, multilayer artificial neural network that can learn from training data across all available workers of a parallel pool on a machine (in parallel computing) addresses the same NIALM/load disaggregation. Where, a comparative study is made in this paper. The presented methodology is experimentally validated by and applied on a publicly available reference dataset. [ABSTRACT FROM AUTHOR]

Introduction: Multi-modal neuroimaging metrics in combination with advanced machine learning techniques have attracted more and more attention for an effective multi-class identification of Alzheimer’s disease (AD), mild cognitive impairment (MCI) and health controls (HC) recently. Methods: In this paper, a total of 180 subjects consisting of 44 AD, 66 MCI and 58 HC subjects were enrolled, and the multi-modalities of the resting-state functional magnetic resonance imaging (rs-fMRI) and the structural MRI (sMRI) for all participants were obtained. Then, four kinds of metrics including the Hurst exponent (HE) metric and bilateral hippocampus seed independently based connectivity metrics generated from fMRI data, and the gray matter volume (GMV) metric obtained from sMRI data, were calculated and extracted in each region of interest (ROI) based on a newly proposed automated anatomical Labeling (AAL3) atlas after data pre-processing. Next, these metrics were selected with a minimal redundancy maximal relevance (MRMR) method and a sequential feature collection (SFC) algorithm, and only a subset of optimal features were retained after this step. Finally, the support vector machine (SVM) based classification methods and artificial neural network (ANN) algorithm were utilized to identify the multi-class of AD, MCI and HC subjects in single modal and multi-modal metrics respectively, and a nested ten-fold cross-validation was utilized to estimate the final classification performance. Results: The results of the SVM and ANN based methods indicated the best accuracies of 80.36 and 74.40%, respectively, by utilizing all the multi-modal metrics, and the optimal accuracies for AD, MCI and HC were 79.55, 78.79 and 82.76%, respectively, in the SVM based method. In contrast, when using single modal metric, the SVM based method obtained a best accuracy of 72.62% with the HE metric, and the accuracies for AD, MCI and HC subjects were just 56.82, 80.30 and 75.86%, respectively. Moreover, the overlapping abnormal brain regions detected by multi-modal metrics were mainly located at posterior cingulate gyrus, superior frontal gyrus and cuneus. Conclusion: Taken together, the SVM based method with multi-modal metrics could provide effective diagnostic information for identifying AD, MCI and HC subject. [ABSTRACT FROM AUTHOR]

This paper aims to optimize the quality characteristics of the drilling process in glass fiber-reinforced polymer (GFRP) composites. It focuses on optimizing the drilling parameters with drill point angles concerning delamination damage and energy consumption, simultaneously. The effects of drilling process parameters on machinability were analyzed by evaluating the machinability characteristics. The cutting power was modeled through drilling parameters (speed and feed), drill point angle, and laminate thickness. The response surface analysis and artificial neural networks enhanced by the particle swarm optimization algorithm were applied for modeling and evaluating the effect of process parameters on the machinability of the drilling process. The most influential parameters on machinability properties and delamination were determined by analysis of variance (ANOVA). A multi-response optimization was performed to optimize drilling process parameters for sustainable drilling quality characteristics. The obtained models were applied to predict drilling process characteristics, and exhibited an excellent harmony with the experiment results. The optimal drilling process factors were the highest spindle speed and the lowest feed, with a drill point angle of 118° for the laminate of 4.75 mm thickness. [ABSTRACT FROM AUTHOR]

Surface roughness is one of the major factor affecting the work piece surface finish in face milling operation. The main criteria discussed on this paper is to predict the ideal cutting performance of cryogenic treatment tool in surface roughness optimization. The surface roughness in machining process is generally formed by the irregularities in cutting tool properties like strength, hardness, toughness etc. For the optimization process, the cutting tool is initially subjected to cryogenic treatment for the improvement in the tool property. The cryogenic treatment is cold treatment process at low temperature to increase the material property. In this paper, the face milling operation processed out in the cryo treated tool which can lower the surface roughness of the machined material. For the validation of the machined work carried out in this paper is verified theoretically by the developing a foreboding prototype by Bat Optimization based artificial Neural Network (BONN) technique using a real time experimental data. The gathered outcome is executed in mathematical modelling using Mat lab and the result shows that cryogenic treatment tool is more efficient than untreated tool with higher cutting accuracy and tool life. Thus, the bat algorithm coupled with artificial neural network is a dynamic and specific method in advancing the overall least possible method for surface roughness prediction in face milling operations. [ABSTRACT FROM AUTHOR]

Artificial neural networks (ANN) exhibit excellent performance in complex problems and have been increasingly applied in the research field of construction management (CM) over the last few decades. However, few papers draw up a systematic review to evaluate the state-of-the-art research on ANN in CM. In this paper, content analysis is performed to comprehensively analyze 112 related bibliographic records retrieved from seven selected top journals published between 2000 and 2020. The results indicate that the applications of ANN of interest in CM research have been significantly increasing since 2015. Back-propagation was the most widely used algorithm in training ANN. Integrated ANN with fuzzy logic/genetic algorithm was the most commonly employed way of addressing the CM problem. In addition, 11 application fields and 31 research topics were identified, with the primary research interests focusing on cost, performance, and safety. Lastly, challenges and future directions for ANN in CM were put forward from four main areas of input data, modeling, application fields, and emerging technologies. This paper provides a comprehensive understanding of the application of ANN in CM research and useful reference for the future. [ABSTRACT FROM AUTHOR]

Commonly, simultaneous localization and mapping (SLAM) algorithm is developed using high-end sensors. Alternatively, some researchers use low-end sensors due to the lower cost of the robot. However, the low-end sensor produces noisy sensor measurements that can affect the SLAM algorithm, which is prone to error. Therefore, in this paper, a SLAM algorithm, which is a Rao-Blackwellized particle filter (RBPF) integrated with artificial neural networks (ANN) sensor model, is introduced to improve the measurement accuracy of a low-end laser distance sensor (LDS) and subsequently improve the performance of SLAM. The RBPF integrated with the ANN sensor model is experimented with by using the Turtlebot3 mobile robot in simulation and real-world experiments. The experiment is validated by comparing the occupancy grid maps estimated by RBPF integrated with the ANN sensor model and RBPF without ANN. Both the results in simulation and real-world experiments show that the SLAM performance of RBPF integrated with the ANN sensor model is better than the RBPF without ANN. In the real-world experiment results, the performance of the occupied cells integrated with the ANN sensor model is increased by 107.59%. In conclusion, the SLAM algorithm integrated with the ANN sensor model is able to improve the accuracy of the map estimate for mobile robots using low-end LDS sensors. [ABSTRACT FROM AUTHOR]

One of the common examples of cybercrime are identity theft and violating of intellectual property that commonly occur in social media. Authorship attribution (AA) techniques are used to extract and use several features of the text in order to identify the original author. These features are used to differentiate the writing style of one author from others. Several machine learning methods have been used to identify the AA using different languages. Few studies were conducted for Arabic AA. This paper aims to investigate the performance of deep learning-based artificial neural network (ANN) for identifying the attribution of authors using Arabic text. The applied model helps protect users in social media from identity theft and violating of their intellectual property. The experiments of this study used a dataset that includes 4,686 Arabic texts for 15 different authors. The performance of the deep learning method was compared with several machine learning methods. The experimental results showed the superior performance of deep learning for AA in Arabic language using different evaluation criteria such as F-score, accuracy, precision, and recall measures. [ABSTRACT FROM AUTHOR]

As there are increasing numbers of mobile subscriber and the market demands of reaching customer personally, Short Message Service (SMS) has become a target of unsolicited text message known as Spam that resulting waste in time, money, and privacy. Many text classification methods using traditional machine learning algorithm has been proposed to prevent spam. However, none of these solutions can guarantee 100% spam-proof solution as each filtering and modeling technique has their own weaknesses and strengths. The objective of this paper is to propose SMS spam classification using Vector Space Model (VSM) and Artificial Neural Network techniques on the publicly available SMS dataset. The result shows a significant improvement based on the accuracy which is 99.10%. This paper will contribute on practical applications and provide contribution to the body of knowledge. [ABSTRACT FROM AUTHOR]

A neural network algorithm is a meta-heuristic algorithm inspired by an artificial neural network, which has a strong global search ability and can be used to solve global optimization problems. However, a neural network algorithm sometimes shows the disadvantage of slow convergence speed when solving some complex problems. In order to improve the convergence speed, this paper proposes the neural network algorithm with dropout using elite selection. In the neural network algorithm with dropout using elite selection, the neural network algorithm is viewed from the perspective of an evolutionary algorithm. In the crossover phase, the dropout strategy in the neural network is introduced: a certain proportion of the individuals who do not perform well are dropped and they do not participate in the crossover process to ensure the outstanding performance of the population. Additionally, in the selection stage, a certain proportion of the individuals of the previous generation with the best performance are retained and directly enter the next generation. In order to verify the effectiveness of the improved strategy, the neural network algorithm with dropout using elite selection is used on 18 well-known benchmark functions. The experimental results show that the introduced dropout strategy improves the optimization performance of the neural network algorithm. Moreover, the neural network algorithm with dropout using elite selection is compared with other meta-heuristic algorithms to illustrate it is a powerful algorithm in solving optimization problems. [ABSTRACT FROM AUTHOR]

In this paper, a calibration algorithm for forecasting the significant wave height (SWH) in nearshore areas is proposed, based on artificial neural networks. The algorithm has two features: first, it is based on SOM−BRFnn (self−organizing map–radial basis function neural network) to better reflect the clustering characteristics of the input parameters regarding wind and wave. In addition, the high-frequency variation part and the low-frequency variation part of SWH are separated by a threshold of 24 h to better describe the diurnal variation of SWH under the influence of tidal current. The algorithm is applied to the nearshore region of Nan-ao Island in the northeastern South China Sea. The results show that the algorithm can effectively correct the modeling results of nearshore SWH. Compared with the original outputs of the ERA5 model, the correlation coefficient is increased from 0.472 to 0.774, the root mean square error is reduced from 0.252 m to 0.103 m, and the mean relative error is reduced from 41% to 17.6%, respectively. Further analysis indicates that the frequency division is crucial in realizing the correction of the high-frequency variation of SWH. The results have reference significance for the application of wave numerical models in coastal areas. [ABSTRACT FROM AUTHOR]

The calorific value of coal is the basic technical basis for calculating parameters such as boiler heat balance, thermal efficiency, and boiler output. The calorific value of coal has different meanings, such as the calorific value of the cartridge, the high calorific value of coal, and the low calorific value of coal to generate heat at a high level of constant humidity and no ash. This paper focuses on the analysis of the structure and algorithm characteristics of artificial neural network and RBF neural network. On this basis, the predictive modelling of the received low-level calorific value is carried out. Through the test summary, the predictiveness of the neural network is better than the empirical formula. For the prediction problem with small sample size, the RBF network has better prediction performance. In addition, the quality of the sample, including its quantity and comprehensiveness, has an important impact on the predictive performance and generalization ability of the model. [ABSTRACT FROM AUTHOR]

Deep learning of multilayered computational models allowed processing to recognize the representation of data at multiple levels of abstraction. These technologies have significantly improved to identify breast cancer. Convolutional Neural Network (CNN) is a type of radiological basis for classification problems and is based on the Bayes decision-making base, which reduces the expected error in classification. In this paper,it is proposed to detect breast cancer using CNN of the mammography system to classify the mammogram to noncancerous abnormality and cancerous abnormality. The goal of Breast Cancer Detection based on CNN for speeding up diagnosis by helping a particular diagnose and classify breast cancer.A set of images of a mammogram is used to perform the pre-processing of the histogram equalization and adjust the appropriate parameters for the CNN work. Then, the whole changed images are set in CNN to classify as a training source. A CNN classifies can be produced as a model foridentifying the mammogram. the BCDCNN method with the mammography classification utilizing MCCANN comparison with BCDCNN improved the classificationaccuracy on mammographic. Therefore, the results showed that the proposed system has a higher resolution than the other recently existing systems, and the only mass containing all was maximized from 0.84 to 0.88 and 0.70 to 0.82 accuracy. [ABSTRACT FROM AUTHOR]

Production of high-quality software at lower cost has always been the main concern of developers. However, due to exponential increases in size and complexity, the development of qualitative software with lower costs is almost impossible. This issue can be resolved by identifying defects at the early stages of the development lifecycle. As a significant amount of resources are consumed in testing activities, if only those software modules are shortlisted for testing that is identified as defective, then the overall cost of development can be reduced with the assurance of high quality. An artificial neural network is considered as one of the extensively used machine-learning techniques for predicting defect-prone software modules. In this paper, a cloud-based framework for real-time software defect prediction is presented. In the proposed framework, empirical analysis is performed to compare the performance of four training algorithms of the backpropagation technique on software-defect prediction: Bayesian regularization (BR), Scaled Conjugate Gradient, Broyden–Fletcher–Goldfarb–Shanno QuasiNewton, and Levenberg-Marquardt algorithms. The proposed framework also includes a fuzzy layer to identify the best training function based on performance. Publicly available cleaned versions of NASA datasets are used in this study. Various measures are used for performance evaluation including specificity, precision, recall, F-measure, an area under the receiver operating characteristic curve, accuracy, R2, and mean-square error. Two graphical user interface tools are developed in MatLab software to implement the proposed framework. The first tool is developed for comparing training functions as well as for extracting the results; the second tool is developed for the selection of the best training function using fuzzy logic. A BR training algorithm is selected by the fuzzy layer as it outperformed the others in most of the performance measures. The accuracy of the BR training function is also compared with other widely used machine-learning techniques, from which it was found that the BR performed better among all training functions. [ABSTRACT FROM AUTHOR]

For the first time, a deep learning (DL) algorithm is presented to study the effect of the source of variability on the performance of semiconductor nanodevice. This paper reports the possibility of an alternative solution of device simulation in order to optimize the source variation. It is based on the statistical distribution of work function fluctuation (WKF) on the metal gate depending on the orientation and location of metal grains. It has been revealed that the WKF of a metal gate can lead to different fluctuations in electrical characteristics. Therefore, an emerging DL algorithm, artificial neural network (ANN) is utilized to identify the appropriate WKF patterns on the metal gate that can reduce the impact of characteristic fluctuation, i.e., $\sigma V_{TH}, \sigma I_{ON}$ and $\sigma I_{OFF}$ , simultaneously. The application of the DL-ANN algorithm to multichannel gate-all-around silicon nanosheet MOSFETs is explored to suppress the effect of WKF on the characteristic fluctuation. Consequently, it can be further utilized to investigate the implication of WKF for the process variation, modeling the nanodevices and analysis of circuit design. Notably, this technique can be extended to study the diverse random sources and process variation effects for emerging nano-CMOS devices and can effectively accelerate the device simulation and optimization. [ABSTRACT FROM AUTHOR]

The significant benefits of cloud computing (CC) resulted in an explosion of their usage in the last several years. From the security perspective, CC systems have to offer solutions that fulfil international standards and regulations. In this paper, we propose a model for a hash function having a scalable output. The model is based on an artificial neural network trained to mimic the chaotic behaviour of the Mackey–Glass time series. This hashing method can be used for data integrity checking and digital signature generation. It enables constructing cryptographic services according to the user requirements and time constraints due to scalable output. Extensive simulation experiments are conduced to prove its cryptographic strength, including three tests: a bit prediction test, a series test, and a Hamming distance test. Additionally, flexible hashing function performance tests are run using the CloudSim simulator mimicking a cloud with a global scheduler to investigate the possibility of idle time consumption of virtual machines that may be spent on the scalable hashing protocol. The results obtained show that the proposed hashing method can be used for building light cryptographic protocols. It also enables incorporating the integrity checking algorithm that lowers the idle time of virtual machines during batch task processing. [ABSTRACT FROM AUTHOR]

Depression has become a common issue among IT industry professionals today. Lifestyle changes and new work culture increase the risk of depression among employees. Various companies and organizations offer mental health plans and try to pacify the work environment. However, the problem is already out of control. This research paper proposes an effective deep learning model for stress prediction among working employees with the help of lion optimization-based optimal artificial neural network (OANN) model. Here, the features are selected using optimal ANN technique and the diseases are predicted using lion optimization method. ANN technique eliminates inappropriate and unnecessary attributes in a significant manner, once the information on calculated characteristics and weight is disseminated to lion optimization classifier. The test results inferred that the artificial neural network is highly efficient than the current OANN algorithm method, based on lion optimization. The study evaluated the data and found that the performance of employees working under normal conditions was higher when compared to the performance of employees who work under stress. Furthermore, attitude-coping efforts may be a cognitive behavioral mechanism, which explains how workload is related to courage and work performance of employees with high stress level. [ABSTRACT FROM AUTHOR]

In recent decades, researches on optimizing the parameter of the artificial neural network (ANN) model has attracted significant attention from researchers. Hybridization of superior algorithms helps improving optimization performance and capable of solving complex applications. As a traditional gradient-based learning algorithm, ANN suffers from a slow learning rate and is easily trapped in local minima when training techniques such as gradient descent (GD) and back-propagation (BP) algorithm are used. The characteristics of randomization and selection of the best or near-optimal solution of metaheuristic algorithm provide an effective and robust solution; therefore, it has always been used in training of ANN to improve and overcome the above problems. New metaheuristic algorithms are proposed every year. Therefore, the review of its latest developments is essential. This article attempts to summarize the metaheuristic algorithms which have been proposed from the year 1975 to 2020 from various journals, conferences, technical papers, and books. The comparison of the popularity of the metaheuristic algorithm is presented in two time frames, such as algorithms proposed in the recent 20 years and those proposed earlier. Then, some of the popular metaheuristic algorithms and their working principle are reviewed. This article further categorizes the latest metaheuristic search algorithm in the literature to indicate their efficiency in training ANN for various industry applications. More and more researchers tend to develop new hybrid optimization tools by combining two or more metaheuristic algorithms to optimize the training parameters of ANN. Generally, the algorithm's optimal performance must be able to achieve a fine balance of their exploration and exploitation characteristics. Hence, this article tries to compare and summarize the properties of various metaheuristic algorithms in terms of their convergence rate and the ability to avoid the local minima. This information is useful for researchers working on algorithm hybridization by providing a good understanding of the convergence rate and the ability to find a global optimum. [ABSTRACT FROM AUTHOR]

In this paper, calculations of the (n , t) reaction cross-sections at 14.5 MeV have been presented by utilizing artificial neural network algorithms (ANNs). The systematics are based on the account for the non-equilibrium reaction mechanism and the corresponding analytical formulas of the pre-equilibrium exciton model. Experimental results, obtained from the EXFOR database, have been used to train the ANN with the Levenberg–Marquardt (LM) algorithm which is a feed-forward algorithm and is considered one of the well-known and most effective methods in neural networks. The Regression (R) values for the ANN estimation have been determined as 0.9998, 0.9927 and 0.9895 for training, testing and for all process. The (n , t) reaction cross-sections have been reproduced with the TALYS 1.95 and the EMPIRE 3.2 codes. In summary, it has been demonstrated that the ANN algorithms can be used to calculate the (n , t) reaction cross-section with the semi-empirical systematics. [ABSTRACT FROM AUTHOR]

Shot peening is an important process for the forming in aerospace industries. However, it is difficult to design the process parameters because of the complex nonlinear relationship between shot peening parameters and the deformation response of shot peened components which is affected by various nonlinear factors such as geometric nonlinearity, material nonlinearity, and coupling effects between process parameters. In this paper, a back propagation artificial neural network (BP-ANN) optimized by genetic algorithm (GA) method, called GA-ANN, is presented for the prediction of shot peen forming parameters. GA is applied to optimize the initial parameters of the BP-ANN to avoid falling into local minimum error. The initially optimized BP-ANN is then directly used to simulate the complex nonlinear relationships between the shot peening parameters (e.g. air pressure, shot mass flow, workpiece feeding speed, etc.) and the mechanical responses of the workpiece (e.g. the bending radius of target workpiece). The experimental results show that the shot peen forming process parameters can be effectively predicted by BP-ANN and that the prediction accuracy can be significantly improved when the ANN model is optimized first using a GA algorithm. [ABSTRACT FROM AUTHOR]

Artificial neural network (ANN) is modeled to predict and classify problems. However, in the training phase of ANNs discovering faultless values of the weights of a network is extremely troublesome. Traditional weight updating methods often get stuck into local optima and converge to optimal solutions very slowly. Therefore, to overcome these drawbacks a modified version of a nature-based algorithm which merges meta-heuristics with weight-updating technique of ANN has been used in this paper. Whale optimization algorithm (WOA) is a well-established, efficient and competitive algorithm inspired by the hunting mechanism of the whales including their behavior in finding and attacking their prey with their bubble-net feeding technique. In WOA, the next location of the search individuals or whales is modified depending on some probability. Due to the high exploration rate of WOA, there is a disproportion between exploration and exploitation in the WOA and it also converges to the solution slowly. Thus, to establish an equilibrium between exploration and exploitation a new variant of WOA called modified whale optimization algorithm (MWOA) is proposed to overcome the problem of delayed convergence. In MWOA, roulette wheel selection is combined with WOA to enhance the convergence speed of WOA. MWOA is tested on 11 benchmark functions, and the outcomes are compared with WOA. The results prove that MWOA has gained success in overcoming the problem of the slow convergence of WOA. Also, the results show that the proposed MWOA technique, when applied to ANN, can overcome the problems of traditional techniques and has improved the results. [ABSTRACT FROM AUTHOR]

We explore a new approach for training neural networks where all loss functions are replaced by hard constraints. The same approach is very successful in phase retrieval, where signals are reconstructed from magnitude constraints and general characteristics (sparsity, support, etc.). Instead of taking gradient steps, the optimizer in the constraint based approach, called relaxed–reflect–reflect (RRR), derives its steps from projections to local constraints. In neural networks one such projection makes the minimal modification to the inputs x, the associated weights w, and the pre-activation value y at each neuron, to satisfy the equation x ⋅ w = y . These projections, along with a host of other local projections (constraining pre- and post-activations, etc.) can be partitioned into two sets such that all the projections in each set can be applied concurrently—across the network and across all data in the training batch. This partitioning into two sets is analogous to the situation in phase retrieval and the setting for which the general purpose RRR optimizer was designed. Owing to the novelty of the method, this paper also serves as a self-contained tutorial. Starting with a single-layer network that performs nonnegative matrix factorization, and concluding with a generative model comprising an autoencoder and classifier, all applications and their implementations by projections are described in complete detail. Although the new approach has the potential to extend the scope of neural networks (e.g. by defining activation not through functions but constraint sets), most of the featured models are standard to allow comparison with stochastic gradient descent. [ABSTRACT FROM AUTHOR]

When working on underground projects, especially where ground is burst prone, it is of a high significance to accurately predict the risk of rockburst. The present paper integrates the firefly algorithm (FA) and artificial neural network (ANN) aiming at modeling the complex relationship between the rockburst risk in deep mines and tunnels and factors effective on this phenomenon. The model was established and validated through the use of a data set extracted from previously conducted studies. The data set involves a total of 196 reliable rockburst cases. The use of smart systems was used to classify and determine patterns in this research using model development. The hybrid FA–ANN model provides a solution for determining different classes of hazard under different conditions. The capability of these developed systems was implemented to determine the four types of levels defined for this phenomenon. The results of these systems led to new solutions to classify this phenomenon by success rates. Each system, given its performance, yields a unique error. Finally, by combining the number of correctly classified classes and their error values, the success rates in the classification of rockburst phenomena in mines and underground tunnels were evaluated. [ABSTRACT FROM AUTHOR]

Fuzzy clustering theory is widely used in data mining of full-face tunnel boring machine. However, the traditional fuzzy clustering algorithm based on objective function is difficult to effectively cluster functional data. We propose a new Fuzzy clustering algorithm, namely FCM--ANN algorithm. The algorithm replaces the clustering prototype of the FCM algorithm with the predicted value of the artificial neural network. This makes the algorithm not only satisfy the clustering based on the traditional similarity criterion, but also can effectively cluster the functional data. In this paper, we first use the t-test as an evaluation index and apply the FCM--ANN algorithm to the synthetic datasets for validity testing. Then the algorithm is applied to TBM operation data and combined with the cross-validation method to predict the tunneling speed. The predicted results are evaluated by RMSE and R². According to the experimental results on the synthetic datasets, we obtain the relationship among the membership threshold, the number of samples, the number of attributes and the noise. Accordingly, the datasets can be effectively adjusted. Applying the FCM--ANN algorithm to the TBM operation data can accurately predict the tunneling speed. The FCM--ANN algorithm has improved the traditional fuzzy clustering algorithm, which can be used not only for the prediction of tunneling speed of TBM but also for clustering or prediction of other functional data. [ABSTRACT FROM AUTHOR]

This paper deals with image processing algorithm that gives a solution for the problem of medical image segmentation. Biological neural network is an artificial abstract model of different parts of the brain or nervous system, featuring essential properties of the system using biologically realistic models. Artificial Neura Networks (ANNs) have been developed for a wide range of applications such as image analysis, enhancement, segmentation, feature extraction and pattern recognition. Among these, image segmentation is more important as it is widely used for object recognition. The watershed transformation algorithm used for segmentation of blood vessels from angiographic images results in some faulty segmented pixels while the use of neural network technique increases the performance with occurrence of some errors. Artificial neural network results in improved quality of image segmentation reflecting the mean square error to be minimum. The proposed algorithm using the combination of morphological filters and back propagation neural network are used for extracting blood vessels from angiographic images of human heart as they have linear structure and Gaussian like profile. Results on various medical data from a set of normal patients are presented and show that this algorithm can be used as a robust segmentation tool. [ABSTRACT FROM AUTHOR]

It is of a high importance to introduce intelligent systems for estimation and optimization of blasting-induced ground vibration because it is one the most unwanted phenomena of blasting and it can damage surrounding structures. Hence, in this paper, estimation and minimization of blast-induced peak particle velocity (PPV) were conducted in two separate phases, namely prediction and optimization. In the prediction phase, an artificial neural network (ANN) model was developed to forecast PPV using as model inputs burden, spacing, distance from blast face, and charge per delay. The results of prediction phase showed that the ANN model, with coefficient of determinations of 0.938 and 0.977 for training and testing stages, respectively, can provide a high level of accuracy. In the optimization phase, the developed ANN model was used as an objective function of firefly algorithm (FA) in order to minimize the PPV. Many FA models were constructed to see the effects of FA parameters on the optimization results. Eventually, it was found that the FA-based optimization was able to decrease PPV to 17 mm/s (or 60% reduction). In addition, burden of 3.1 m, spacing of 3.9 m, and charge per delay of 247 kg were obtained as the values optimized by FA. The results confirmed that both developed techniques of ANN and FA are powerful, accurate, and applicable in estimating and minimizing blasting-induced ground vibration and they can be used with caution in similar fields. [ABSTRACT FROM AUTHOR]

Hands are the main environmental manipulator for the human being. After losing a hand, the only alternative for the victim is to use a prosthesis. Despite the progress of science, the modern prosthesis has the same age-old problem of accurate force estimation. Among different kinds of force, clench force is the most important one. Because of this importance, this paper presents a hardware system that has been designed and implemented to estimate the desired clench force using surface Electromyography signals recorded from lower-arm muscles. The implementation includes a two-layer artificial neural network with a surface electromyography integrator. The neural network was trained with the Levenberg–Marquardt back propagation algorithm and was implemented in a field programmable gate array using an off-chip training method. The results from 10 datasets, recorded from five subjects, show that the hardware model is very accurate, with an average mean square error of 0.003. This suggests that the proposed design can mimic the behavior of clench force that a real limb does, and therefore this intelligent system could be a useful tool for any application related to prostheses. [ABSTRACT FROM AUTHOR]

Copyright of Przeglad Elektrotechniczny is the property of Przeglad Elektrotechniczny 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.)

Delay Tolerant Network (DTN) is a kind of network that there is no continuous network connectivity among nodes. There are no end-to-end and constant connection paths from source nodes to destination nodes due to the mobility nature of nodes. In such networks there exists an inevitable long delivery delay. DTN is designed to perform properly over intermittent connections among nodes. Because of mobile nature of nodes, routing in DTN is based on store-carry-forward patterns to forward messages. Store-carry-forward means when a node receives a message from one of its contacts, it stores the message in its buffer and carries the message until it encounters another Contact node with Better conditions to Take the message to the Destination node (CBTD). Recognizing one of visited nodes as CBTD is a challenging problem. After recognizing CBTD, forwarding messages to CBTDs is required and necessary for routing efficiency and performance, because the messages will be delivered to the destination faster through CBTDs. In this paper, routing is performed by recognizing CBTDs and forwarding messages to them using RPRTD algorithm. RPRTD algorithm is based on Remaining Time to encounter nodes with Destination node (RTD). A node with smaller RTD, encounters the destination node in less time than the others. RPRTD algorithm tries to take message somehow to the node with the smallest RTD value among all nodes. RTD is calculated with the help of predicting future coordinates of nodes based on artificial neural networks (ANN). Simulation results show that this algorithm makes the best decision and efficiently determines the most appropriate and the best route to deliver messages to the destination node, increases routing performance, improves number of delivered messages, and decreases delivery delay compared to the state of the art. [ABSTRACT FROM AUTHOR]

Learning disability (LD) is a neurological condition that affects a child's brain and impairs his ability to carry out one or many specific tasks. LD affects about 10% of children enrolled in schools. There is no cure for learning disabilities and they are lifelong. The problems of children with specific learning disabilities have been a cause of concern to parents and teachers for some time. Just as there are many different types of LDs, there are a variety of tests that may be done to pinpoint the problem The information gained from an evaluation is crucial for finding out how the parents and the school authorities can provide the best possible learning environment for child. This paper proposes a new approach in artificial neural network (ANN) for identifying LD in children at early stages so as to solve the problems faced by them and to get the benefits to the students, their parents and school authorities. In this study, we propose a closest fit algorithm data preprocessing with ANN classification to handle missing attribute values. This algorithm imputes the missing values in the preprocessing stage. Ignoring of missing attribute values is a common trend in all classifying algorithms. But, in this paper, we use an algorithm in a systematic approach for classification, which gives a satisfactory result in the prediction of LD. It acts as a tool for predicting the LD accurately, and good information of the child is made available to the concerned. [ABSTRACT FROM AUTHOR]

Load signature is the unique consumption pattern intrinsic to each individual electrical appliance/piece of equipment. This paper focus on building a universal platform to better understand and explore the nature of electricity consumption patterns using load signatures and advanced technology, such as feature extraction and intelligent computing. Through this knowledge, we can explore and develop innovative applications to achieve better utilization of resources and develop more intelligent ways of operation. This paper depicts the basic concept, features of load signatures, structure and methodology of applying mathematical programming techniques, pattern recognition tools, and committee decision mechanism to perform load disaggregation. New indices are also introduced to aid our understanding of the nature of load signatures and different disaggregation algorithms. [ABSTRACT FROM AUTHOR]

The paper contains a description of the implementation and performance evaluation of the agent-based population learning algorithm used to train the feed-forward artificial neural networks. The goal of the research was to evaluate efficiency of the agent-based approach and to establish experimentally which different factors representing the A-Team structure and topology affect the performance of the analyzed agent-based algorithm. The paper includes a general overview of the JABAT environment used to deploy the ANN training algorithm, a description of different agents employed and their roles, as well as the computational experiment plan and the discussion of the performance evaluation results. [ABSTRACT FROM AUTHOR]

Organizations (manufacturing, service, healthcare etc.) buy goods and services for their operational needs from reliable and subject-optimized companies frequently. In fact, procurement processes follow stringent procedures to ensure that the process is fair and efficient with a minimal wastage of resources. The main challenge of all such procurement processes is the selection of optimal bidder(s) such that they satisfy the 'best value for money' criteria than accomplishing the 'best optimized price' criteria alone. In fact, choosing an optimal bidder requires, in general, consideration of both technical and financial criteria with appropriate assignment of weightage for each. In this work, an innovative approach is proposed where only an optimal set of shortlisted bidders is made to undergo quality and cost-based selection (QCBS) evaluation procedure. The proposed method combines a few significant algorithms together for effective results. These algorithms are studied and implemented in the following order: hyper sphere cluster density (HSCD) algorithm; K-means algorithm; artificial neural network (ANN) model and QCBS evaluation model. Initially, the coupling of HSCD algorithm with standard K-means is done for creating robust and reliable non-overlapping clusters. Then, the multi-layer perceptron (MLP) model of ANN is applied to determine optimal cluster from set of all non-overlapping clusters. This model is effective in reducing the laborious task of unnecessarily evaluating all the shortlisted bidders. Next, the QCBS evaluation is done to select the optimal bidder from the already chosen optimal cluster. Numerical example is considered to demonstrate the proposed procedure. Several conclusions are drawn based on which recommendations for the application of the proposed method are made. [ABSTRACT FROM AUTHOR]

Application of back-propagation (BP) artificial neural network (ANN) as an accurate, practical and quick tool in indirect estimation of uniaxial compressive strength (UCS) of rocks has recently been highlighted in the literature. This is mainly due to difficulty in direct determination of UCS in laboratory as preparing the core samples for this test is troublesome and time-consuming. However, ANN technique has some limitations such as getting trapped in local minima. These limitations can be minimized by combining the ANNs with robust optimization algorithms like particle swarm optimization (PSO). This paper gives insight into development of a hybrid PSO-BP predictive model of UCS. For this reason, dataset comprising the results of 228 laboratory tests including dry density, moisture content, P wave velocity, point load index test, slake durability index and UCS was prepared. These tests were conducted on 38 sandstone samples which were taken from two excavation sites in Malaysia. Findings showed that PSO-BP model performs well in predicting UCS. Nevertheless, to compare the prediction performance of the PSO-BP model, the UCS is predicted using ANN-based PSO and BP models. The correlation coefficient, R, values equal to 0.988 and 0.999 for training and testing datasets, respectively, suggest that the PSO-BP model outperforms the other predictive models. [ABSTRACT FROM AUTHOR]

There have been gradually increasing interests in the stratospheric airship (SSA) as a cost-effective alternative to earth orbit satellites for telecommunication and high-resolution earth observation. Lightweight and high strength envelopes are the keys to the design of SSAs as it directly determines the endurance flight performance and loading deformation characteristics of the airship. Typical SSA envelope material is a laminated fabric, which is composed of fabric layer and other functional layers. Compared with conventional composite structures, the laminated fabric has complex nonlinear mechanical characteristics. Artificial neural network (ANN) has good processing ability to nonlinear information so that it is suitable to model the constitutive relation of laminated fabrics. In this work, an ANN based on the Scaled Conjugate Gradient (SCG) algorithm is proposed firstly to model the constitutive relation of fabric Uretek3216LV. Considering significant errors of the SCG ANN results, the network model is optimized through methods of selecting the number of hidden-layer nodes and training algorithms. Results show that the improved network model based on Bayesian Regularization (BR) algorithm and eight nodes of single hidden layer can better describe the constitutive relation of the laminated fabric than other conventional training algorithms. The proposed constitutive modelling method with ANN is expected to gain a deeper understanding of the mechanical mechanism and guide structural design of envelope material in further work. [ABSTRACT FROM AUTHOR]

In this paper we purpose to compare two methods of maximum power point tracking (MPPT). This comparison relates the photovoltaic conversion efficiency, response time and system performance. These two techniques are, on the one hand, the artificial neural network model based on the architecture Multi-Layer Perceptron (MLP) whose training is based on experimental data and on the other hand, the "Perturb and Observe" algorithm (P & O) using the perturbation of the duty cycle ratio. Both methods are used to specify the duty cycle was applied to DC-DC boost converter corresponding to the MPPT of solar photovoltaic generator, under different atmospheric conditions. The performance of both approaches is validated by experimental data confronted to simulations obtained using the MATLAB / Simulink software. [ABSTRACT FROM AUTHOR]

In this paper a modified wavelet synthesis algorithm for continuous wavelet transform is proposed, allowing one to obtain a guaranteed approximation of the maternal wavelet to the sample of the analyzed signal (overlap match) and, at the same time, a formalized representation of the wavelet. What distinguishes this method from similar ones? During the procedure of wavelets' synthesis for continuous wavelet transform it is proposed to use splines and artificial neural networks. The paper also suggests a comparative analysis of polynomial, neural network, and wavelet spline models. It also deals with feasibility of using these models in the synthesis of wavelets during such studies like fine structure of signals, as well as in analysis of large parts of signals whose shape is variable. A number of studies have shown that during the wavelets' synthesis, the use of artificial neural networks (based on radial basis functions) and cubic splines enables the possibility of obtaining guaranteed accuracy in approaching the maternal wavelet to the signal's sample (with no approximation error). It also allows for its formalized representation, which is especially important during software implementation of the algorithm for calculating the continuous conversions at digital signal processors and microcontrollers. This paper demonstrates the possibility of using synthesized wavelet, obtained based on polynomial, neural network, and spline models, during the performance of an inverse continuous wavelet transform. [ABSTRACT FROM AUTHOR]

Artificial neural networks (ANN) are extensively utilized in structural health monitoring. Nevertheless, the definition of a rigorous method for the optimization of their structure is still an unresolved issue, especially when applied to safety critical systems. In this paper, an approach typically adopted in the design of experiments and based on the analysis of variance (ANOVA) is used to statistically determine the number of hidden neurons in a three-layer ANN structure. Repeated trainings of the same network structure provide multiple observations of the performance index here, based on the root mean square error. Different levels of network structure complexity are statistically compared, based on the number of hidden nodes. ANOVA is used to determine whether there is statistical evidence that the network performance is influenced by the number of hidden nodes. This analysis allows defining the threshold number of hidden nodes above which there is no statistical evidence of a performance benefit by the increase of the ANN structure complexity. The method is applied to the optimization of a set of algorithms for the diagnosis of fatigue damage on a typical aeronautical structure, consisting of a metallic panel with a riveted skin-stringer construction. The ANNs for damage detection, localization, and quantification are trained and validated with finite element simulated strain data and are finally tested on experimental strain signals, acquired in real-time in a fatigue crack growth laboratory test program including a skin crack artificially initiated in a panel bay and two stringers that had failed naturally under fatigue load. [ABSTRACT FROM AUTHOR]

There are numerous models of data envelopment analysis (DEA) for solving the efficiency evaluation a set of homogeneous Decision-Making Units (DMUs) that use similar sources to produce similar outputs. However, the efficiency boundary in these models is very sensitive to outliers and random factors. In this way, researchers have always sought a method that, in addition to having the high exibility of nonparametric methods, compensates for the weaknesses of this view. The approach suggested by scholars in this regard is the use of a combination of Artificial Neural Network (ANN) and DEA. In this paper, a new method of combining ANN and DEA (ANN-DEA) presented in which the input and output values for a large number of DMUs determined as neural network inputs. It can be seen that the use of the neural network to solve the data envelopment analysis problem does not require solving the model for each DMU, and therefore compared with the conventional method, in the proposed algorithm processing time and memory usage significantly reduced. We have also compared the new model with the existing approach of ANN-DEA. To illustrate the ability of the proposed methodology some case studies are used, including a set of 500 Iranian bank branches. The results indicate a high accuracy and less computational time of the proposed hybrid model and have practical outcomes for decision makers. [ABSTRACT FROM AUTHOR]

In this paper, an application of an adaptive differential evolution (DE) algorithm with multiple trial vectors for training artificial neural networks (ANNs) is presented. The proposed method is \DE-ANNT+, which is a DE-ANN Training (DE-ANNT) modified by adding a multiple trial vectors technique. \DE-ANNT+ allows one to train an ANN of arbitrary architectures, and it offers a nondifferentiable neuron activation function. In contrast to a basic DE algorithm, \DE-ANNT+ possesses two modifications. In \DE-ANNT+, adaptive selection of control parameters and a multiple trial vectors technique are introduced. Adaptive selection means that the number of required parameters of the algorithm is decreased. The multiple trial vectors technique increases the probability of generating a better solution because a greater number of temporary solutions is generated around the existing solutions. The \DE-ANNT+ algorithm, with these two modifications, is used for ANN training to classify the parity-p problem. The results from the obtained algorithm have been compared with results from the following algorithms: an evolutionary algorithm, a DE algorithm without multiple trial vectors, gradient training methods, such as error back-propagation, and the Levenberg-Marquardt method. [ABSTRACT FROM PUBLISHER]

This paper describes the capability of artificial neural network for predicting the critical clearing time of power system. It combines the advantages of time domain integration schemes with artificial neural network for real time transient stability assessment. The training of ANN is done using selected features as input and critical fault clearing time (CCT) as desire target. A single contingency was applied and the target CCT was found using time domain simulation. Multi layer feed forward neural network trained with Levenberg Marquardt (LM) back propagation algorithm is used to provide the estimated CCT. The effectiveness of ANN, the method is demonstrated on single machine infinite bus system (SMIB). The simulation shows that ANN can provide fast and accurate mapping which makes it applicable to real time scenario. [ABSTRACT FROM AUTHOR]

The paper provides an alternative approach to protein structural class prediction employing artificial neural network. Existing works on protein structural class prediction are computationally intensive. The method employs SOFM for extraction of representative feature vectors, for the four different structural classes and then uses Principal Component Analysis for finding optimum feature vector dimension. Nearest neighborhood classification technique is finally utilised; to classify these protein datapoints to their respective classes. The proposed work presented in this paper, maintains the same level of classification accuracy in minimum computation time, as it employs most prominent and reduced number of feature set for classification. [ABSTRACT FROM AUTHOR]

Capability assessment plays a crucial role in the demonstration and construction of equipment. To improve the accuracy and stability of capability assessment, we study the neural network learning algorithms in the field of capability assessment and index sensitivity. Aiming at the problem of overfitting and parameter optimization in neural network learning, the paper proposes an improved machine learning algorithm—the Ensemble Learning Based on Policy Optimization Neural Networks (ELPONN) with the policy optimization and ensemble learning. This algorithm presents an optimized neural network learning algorithm through different strategies evolution, and builds an ensemble learning model of multi-intelligent algorithms to assess the capability and analyze the sensitivity of the indexes. Through the assessment of capabilities, the algorithm effectively avoids parameter optimization from entering the minimum point in performance to improve the accuracy of equipment capability assessment, which is significantly better than previous neural network assessment methods. The experimental results show that the mean relative error is 4.10%, which is better than BP, GABP, and early stopping. The ELPONN algorithm has better accuracy and stability performance, and meets the requirements of capability assessment. [ABSTRACT FROM AUTHOR]

This paper describes a new approach for predicting tertiary structure of protein using artificial neural network and particle swarm optimization technique. The paper is concetrated around the well known Ab-initio approach for global minimisation of energy function. It predicts the native structure of protein by finding the main chain dihedral angles; through the optimization of CHARMM energy function, using particle swarm optimization algorithm. Side chain dihedral angle are predicted using three layered artificial neural network, realised with back propagation algorithm. This approach has merit as it reduces the dimensionality of the search space and computationally outperforms all other classical technique in atleast 80% cases. [ABSTRACT FROM AUTHOR]

One of the most powerful techniques to diagnose cardiovascular diseases is to analyze the electrocardiogram (ECG). To increase diagnostic sensitivity, the ECG might need to be acquired using an ambulatory system, as symptoms may occur during a patient's daily life. In this paper, we propose using an ambulatory ECG (aECG) recording device with a low number of leads and then estimating the views that would have been obtained with a standard ECG location, reconstructing the complete Standard 12-Lead System, the most widely used system for diagnosis by cardiologists. Four approaches have been explored, including Linear Regression with ECG segmentation and Artificial Neural Networks (ANN). The best reconstruction algorithm is based on ANN, which reconstructs the actual ECG signal with high precision, as the results bring a high accuracy (RMS Error < 13 μ V and CC > 99.7%) for the set of patients analyzed in this paper. This study supports the hypothesis that it is possible to reconstruct the Standard 12-Lead System using an aECG recording device with less leads. [ABSTRACT FROM AUTHOR]

This paper presents a hybrid Artificial Neural Network (ANN)/rule-based phoneme synthesizer for Farsi text. A new variable called Vowel State (VS) is also introduced which efficiently decreases the size of computations. The proposed system uses VS along with the written form of the words to determine their pronunciation. Some rules are also applied to the system to decrease network interconnections. These rules are performed in the Normalization Unit and the Phoneme Extraction Unit before and after the ANN. A multilayer perceptron with 48, 90 and 3 neurons in the input layer, hidden layer and output layer respectively is chosen to determine the Vowel State of each letter. Each letter in a word enters the ANN in the heart of a window in order to recognize the VS of the letter. An asymmetric 8-letter windowing is suggested; 3 letters before the letter along with 4 letters after it enter the ANN as the input. For training and testing the system, 2359 words are extracted from some online available resources. The results of test show that using 65% of the corpus as training set and testing over the entire corpus gives the result of 84% correct answers for the ANN, and 90% correct answer for the entire system considering additional rules. The performance index of the ANN increases to 88, 92, 98 and 99 percent when the percentage of the training set increases to 75, 85, 95 and 100, respectively. The system also shows the performance of 93% correct answers on an independent word database. The proposed hybrid ANN/rule-based method imposes small size of calculation in comparison with similar systems. In this system, the output of ANN is a 5-value variable Vowel State instead of numerous phonemes. This fact decreases the neurons in the output layer of ANN considerably. Besides, adding some rules before and after the network helps to increase performance. The overall system shows a decrement of 70% in the size of computations comparing with other reported approaches. [ABSTRACT FROM AUTHOR]

With the aid of machine learning method, namely artificial neural networks, we established data-driven proxy models that could be utilized to maximize the net present value of a waterflooding process by adjusting the well control injection rates over a production period. These data-driven proxies were maneuvered on two different case studies, which included a synthetic 2D reservoir model and a 3D reservoir model (the Egg Model). Regarding the algorithms, we applied two different nature-inspired metaheuristic algorithms, i.e., particle swarm optimization and grey wolf optimization, to perform the optimization task. Pertaining to the development of the proxy models, we demonstrated that the training and blind validation results were excellent (with coefficient of determination, R2 being about 0.99). For both case studies and the optimization algorithms employed, the optimization results obtained using the proxy models were all within 5% error (satisfied level of accuracy) compared with reservoir simulator. These results confirm the usefulness of the methodology in developing the proxy models. Besides that, the computational cost of optimization was significantly reduced using the proxies. This further highlights the significant benefits of employing the proxy models for practical use despite being subject to a few constraints. [ABSTRACT FROM AUTHOR]