Search

In this paper, the author introduced a sentiment analysis-based customer loyalty prediction model in mobile applications using word embedding models, deep learning algorithms, and deep contextualized word representations. This method showed better performances than usual state-of-the-art methods in separate data sets along with the combined data set on both gender and region classification. Intelligent Systems can be thought of as a concept with a very broad scope. [Extracted from the article]

In multi-antenna systems, advanced techniques such as massive multiple-input multiple-output (MIMO), beamforming, and beam selection depend heavily on the accurate acquisition of the channel state. However, pilot contamination (PC) can be a major source of interference which degrades they are performance. Moreover, the severity of PC increases as more pilots are reused between users in the wireless systems. Researchers have shown that PC can be mitigated by using deep learning (DL) approaches. Nevertheless, when minimizing PC, the examination that identifies the applications and factors that distinguish these DL approaches is still limited. This paper reviews these DL approaches and the improvements needed to enhance their performance. Simulation results confirm that DL networks that learn to predict the channels directly have superior performance under PC. [ABSTRACT FROM AUTHOR]

The stability of Wireless Sensor Networks (WSNs) is a crucial requirement in real-time applications such as military, defense, and other surveillance systems. Clustering in WSNs is one of the most predominant techniques, offering benefits such as minimizing communication time, optimizing energy utilization, lengthening the network lifespan, and ensuring network stability. Moreover, achieving the balance between energy consumption and maintaining network stability is significantly influenced by the cluster size. This research paper addresses the challenges associated with clustered-based routing and cluster formation paradigm, introducing a novel algorithm employing the principle of Artificial Neural Networks (ANN). In particular, the proposed algorithm integrates a hybrid strategy of Self Organizing Map (SOM) and K-mean clustering to form energy-efficient clusters, even ensuring the energy distribution evenly among them. The validity of the proposed algorithm has been confirmed through experimental analysis conducted using MATLAB. The simulation results demonstrate that the hybrid combination of SOM and K-means clustering is highly efficient in minimizing energy consumption and maintaining network stability. The findings also reveal an average of 80% stable network lifetime and achieve a packet reception ratio (PRR) of 98% which is much higher than two other protocols i.e. LEACH and MODLEACH protocols. [ABSTRACT FROM AUTHOR]

In this paper, we offer a new modelling approach for hepatitis C virus (HCV) infection models with cytotoxic T lymphocytes (CTL) immune responses. The standard neural network models with reaction-diffusion terms are generalized to the discontinuous case considering impulsive controllers. Also, the conformable approach is proposed as a more adjustable modelling apparatus which overcomes existing difficulties in the application of the fractional-order modelling technique. In addition, the existence of integral manifolds for the proposed model is investigated and efficient criteria are established. Since stability and control of a neural network model are essential for its proper application, stability results for the constructed integral manifold are presented. These results extend and generalize the stability results for steady states of proposed HCV models with CTL immune responses and contribute to the development of new innovative modelling approaches in biology. The qualitative analysis is performed via the conformable Lyapunov function method. The established results are demonstrated through an example. [ABSTRACT FROM AUTHOR]

Sustainable entrepreneurship is essential for solving the issue of economic and social stability. This paper is about the determinants of entrepreneurship among green innovation and strategic innovation. The research studies the communication and R&D variables that impact entrepreneurship development. The literature shows that green innovation is vital in developing strategic orientation. Entrepreneurship must work on R&D to gain economic and social stability. Entrepreneurship development is a dependent variable, and communication and R&D are independent variables. This paper evaluates the performance of Multiple Linear Regression (MLR) and the Artificial Neural Network Regression (ANN) approach for estimating entrepreneurship development (ED) in China from 2000 to 2021. For this work, nine independent variables related to entrepreneurial development were selected, which include CO2 emissions (CO2), GDP growth (GDP), Total greenhouse gas emissions (GHG), Computer, communications, and other services (CCS), Nitrous oxide emissions (NO2), Personal remittances, received (PRR), Research and development expenditure (R&D), New businesses registered (NBR), and patents in environment-related technologies (PERT). Data were gathered from the World Bank (WB) official data bank portal. The highest correlation (−0.85 and −0.71) with ED was observed with GHG, followed by a strong correlation with R & D. The MLR model generated 0.78 R2 (error = 0.26) whereas the ANN model produces 0.83 R2 (error = 0.01). The results of the ANN showed that the association among parameters is strong. Ten input variables and 15 hidden neurons were used to estimate the dependent variable. The process took 87 steps, and the optimum result had a Sum of Square Error of 0.001.The top 5 essential variables are NO, NBR, GHG, R&D, and CO2. The least essential variables are PPR and CCS, respectively, with the lowest variable importance (VI) score. This work is unique in the sense that it covers the research gap with new advanced techniques (ANN) applied to time series data. We believe the idea that we developed is a novel approach for social scientists, entrepreneurial development, social stability, and a sustainable environment. The findings of this research can benefit entrepreneurs in many different ways. By understanding the effects of social environmental stability on their success, entrepreneurs can better tailor their strategies to ensure they get the best possible results. [ABSTRACT FROM AUTHOR]

In this paper, an integrated forecast method is proposed based on multi-resources data, which improves the maximum deviation similarity criterion (MDSC) of time-segment BP neural network. The existing short-term load forecast methods for power systems will lead to the low accuracy or even failure of the load prediction method since the multi-stage load change and weather fluctuation factors are not considered. The improved similar day category screening method with the time-segment BP neural network model is employed to deal with the above problem in this paper, where a regional load characteristic law is used to divide the load into seven time periods such that a time-segment BP neural network model is proposed. Based on the feature vector and the real-time meteorological data of the forecast day, the trained forecast model can provide the load value of the forecast day and overcome the restriction of the historical load data. Meanwhile, the prediction accuracy and the training time are also improved under the fluctuating meteorological conditions. Finally, a load forecast of a certain area is given to show the prediction accuracy of different types of days can reach more than 96%,illustrate the effectiveness of the proposed methods. [ABSTRACT FROM AUTHOR]

This paper describes deep neural network (DNN) models based on hyperparameter optimization for the prediction of the compressive strength of concrete. The novelty of this research lies in the implementation of optimized hyperparameters to train the DNN models with the aim to enhance their predictive accuracy. Utilizing the Keras Tuner library, the most effective hyperparameters for the DNN models were identified. These models are then trained and evaluated using an experimental dataset of 1030 instances, encompassing nine quantitative variables that include various concrete mix ingredients and age. The target variable for all models is the compressive strength of concrete. The assessment of model performance, based on metrics like mean squared error (MSE) and R² values, was conducted on previously unseen test data. The optimal configuration for the hidden layers in the model was identified as five layers, containing 12, 16, 16, 40, and 26 neurons, respectively. The optimal learning rate for the model was 0.001. With this set of optimal hyperparameters, the best DNN model achieved an MSE of 28.76 and an R² value of 0.89 on the testing data. The results demonstrate a significant improvement in the DNN models' performance when trained with the optimized hyperparameters. In comparison to the regression model, the performance of the DNN models was significantly better. Adopting the predictive models developed in this research offers the potential for substantial cost and time savings by circumventing the need for labour-intensive and time-consuming laboratory tests. [ABSTRACT FROM AUTHOR]

This paper presents an indoor floor positioning method with the smartphone's barometer for the purpose of solving the problem of low availability and high environmental dependence of the traditional floor positioning technology. First, an initial floor position algorithm with the "entering" detection algorithm has been obtained. Second, the user's going upstairs or downstairs activities are identified by the characteristics of the air pressure fluctuation. Third, the moving distance in the vertical direction and the floor change during going upstairs or downstairs are estimated to obtain the accurate floor position. In order to solve the problem of the floor misjudgment from different mobile phone's barometers, this paper calculates the pressure data from the different cell phones, and effectively reduce the errors of the air pressure estimating the elevation which is caused by the heterogeneity of the mobile phones. The experiment results show that the average correct rate of the floor identification is more than 85% for three types of the cell phones while reducing environmental dependence and improving availability. Further, this paper compares and analyzes the three common floor location methods – the WLAN Floor Location (WFL) method based on the fingerprint, the Neural Network Floor Location (NFL) methods, and the Magnetic Floor Location (MFL) method with our method. The experiment results achieve 94.2% correct rate of the floor identification with Huawei mate10 Pro mobile phone. [ABSTRACT FROM AUTHOR]

In order to alleviate the congestion in the mainline of urban expressway caused by the uncertainty of the traffic flow, a linked-bottleneck control method for urban expressway on-ramp is proposed in this paper. Firstly, the downstream dynamic critical occupancy of the on-ramp under uncertainty is predicted by using ESN (Echo State Network). Then, a function for dividing the master-slave ramps is designed to dynamically determine the ramp numbers required coordination and expand the range of coordination control. Considering the designed function changes over time and some factors such as the traffic accidents, weather and so on also affect it, the BP neural network is used to improve its accuracy. The proposed method calculates the on-ramp regulating rate based on the downstream dynamic critical occupancy and expand the range of coordination control by the designed function, which can adapt the changes of actual traffic flow and overcome the defects of some methods such as Bottleneck, Linked-control, Swarm and so on. The simulations show that, compared with some existing methods, the congestion duration and the high density duration in the mainline of the urban expressway are significantly reduced by using the proposed method in this paper. [ABSTRACT FROM AUTHOR]

Urban land subsidence is a slow-density geology disaster caused by the withdrawal of groundwater or the application of water at the land surface. Developing a method of effectively monitoring, predicting and preventing land subsidence has become an urgent urban disaster issue and a great challenge. Traditional mathematical statistics prediction models lack physical meaning. Thus, in this paper, an improved third-order gray prediction GM(1, 3) model that combines terrain factors and neural network error corrections is proposed for urban land subsidence prediction. First, the correlation between land subsidence and terrain factors is verified through a correlation analysis. Second, a geospatial weight matrix based on the terrain factors is presented for auxiliary variable selection. Finally, a neural network is used to model the prediction errors to improve the model accuracy. Precision levelling data for Haiyan County, Zhejiang Province, China from 1999 to 2016 are used as the experimental data. The results show that the proposed method can achieve the same accuracy level as precision levelling. The average absolute error of three-phrase prediction is less than 10 mm, and the relative error can reach 0.4%. The proposed method can be expected to replace precision levelling for the prediction of long-term land subsidence and provide decision support for urban settlement disaster prevention. [ABSTRACT FROM AUTHOR]

Traffic flow prediction is an essential part of the intelligent transport system. This is the accurate estimation of traffic flow in a given region at a particular interval of time in the future. The study of traffic forecasting is useful in mitigating congestion and make safer and cost-efficient travel. While traditional models use shallow networks, there has been an exponential growth in the number of vehicles in recent times and these traditional machine learning models fail to work in current scenarios. In our paper, we review some of the latest works in deep learning for traffic flow prediction. Many deep learning architectures include Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), Long ShortTerm Memory (LSTM), Restricted Boltzmann Machines (RBM), and Stacked Auto Encoder (SAE). These deep learning models use multiple layers to extract higher level of features from raw input progressively. The latest deep learning models developed to tackle this very problem are reviewed and due to the complexity of transport networks, this review gives the reader information about how various factors influence these models and what models work best in different scenarios. [ABSTRACT FROM AUTHOR]

Volatility is usually a proxy indicator for market variation or tendency, containing essential information for investors and policy-makers. This paper proposes a novel hybrid deep neural network model (HDNN) with temporal embedding for volatility forecasting. The main idea of our HDNN is that it encodes one-dimensional time-series data as two-dimensional GAF images, which enables the follow-up convolution neural network (CNN) to learn volatility-related feature mappings automatically. Specifically, HDNN adopts an elegant end-to-end learning paradigm for volatility forecasting, which consists of feature embedding and regression components. The feature embedding component explores the volatility-related temporal information from GAF images via the elaborate CNN in an underlying temporal embedding space. Then, the regression component takes these embedding vectors as input for volatility forecasting tasks. Finally, we examine the feasibility of HDNN on four synthetic GBM datasets and five real-world Stock Index datasets in terms of five regression metrics. The results demonstrate that HDNN has better performance in most cases than the baseline forecasting models of GARCH, EGACH, SVR, and NN. It confirms that the volatility-related temporal features extracted by HDNN indeed improve the forecasting ability. Furthermore, the Friedman test verifies that HDNN is statistically superior to the compared forecasting models. [ABSTRACT FROM AUTHOR]

This paper presents a novel approach for enhancing long-term runoff simulations through the integration of empirical mode decomposition (EMD) with four machine learning (ML) models: ensemble, support vector machine (SVM), convolutional neural networks (CNN), and artificial neural networks with backpropagation (ANN-BP). The proposed methodology uses EMD to decompose precipitation and temperature time-series into intrinsic mode functions, thereby revealing underlying data patterns. Subsequently, these components are incorporated into the ML models to simulate the runoff time-series. The effectiveness of the hybrid models is evaluated using streamflow runoff data obtained from the Grand, Winnipeg, and Moosonee Rivers in Ontario, Canada. Four widely used performance indices, namely, correlation coefficient, root mean square error (RMSE), mean absolute relative error, and Nash--Sutcliffe efficiency, are employed to assess the models' performance. The results demonstrate that the hybrid EMD-ML models exhibit significantly superior performance compared with the standalone ML methods. During the validation phase, the EMD-Ensemble, EMD-SVM, EMD-CNN, and EMD-ANN-BP models exhibit notable reductions in the RMSEs of monthly streamflow estimates for the Grand River, amounting to 11%, 22%, 8%, and 33%, respectively, compared with their non-EMD counterparts. Additionally, these hybrid models exhibit improved RMSEs for yearly simulations in the Winnipeg River, with reductions of 54%, 0.08%, 6%, and 4.5% respectively. To further enhance the accuracy of monthly and yearly streamflow estimates, an SVM-recursive feature elimination technique is employed to select a more appropriate EMD dataset in all study cases. This research underscores the potential of integrating EMD with ML models to enhance long-term runoff simulations. The outcomes highlight the superior performance of the hybrid EMD-ML models, demonstrating their ability in generating lower biases than the standalone ML methods. These findings hold significant implications for the field of computational fluid mechanics and can contribute to the understanding of hydrological processes. [ABSTRACT FROM AUTHOR]

The attainment of energy sustainability in the building sector can be realised by implementing a green building programme, which has grown significantly over the last thirty years. Green building is considered a technical and management strategy within the building and construction industries. Many different prediction methods, both complex and simple, have been put out in recent years and used to solve a wide variety of issues. Several case studies have highlighted factors that impede energy and resource usage in green buildings. The utilisation, trends, and consequences of wall and thermal insulation materials are examined. The main scope of this investigation is to predict buildings' heat loss by applying artificial neural networks according to the heat transfer coefficients of walls and coating materials, as well as indoor, outdoor, and external surface temperatures. The data has been normalised and presented to two selected neural networks (Harmony search (HS) and particle swarm optimisation are used and contrasted (PSO)). For evaluating the accuracy of models, two statistical indexes are used (R² and RMSE). Model performance of PSO-MLP is shown by R² amounts of 0.97055 and 0.87381, respectively, and RMSE amounts of 0.02534 and 0.09685. Similarly, HS-MLP model accuracy is also indicated by R² amounts of 0.93839 and 0.84176 and RMSE amounts of 0.03635 and 0.10753. The analysis in this paper shows that PSO-MLP predicts heat loss with higher accuracy and improved performance. [ABSTRACT FROM AUTHOR]

Heating and thermal comfort have remarkable share of final energy consumption. Until now, most of the demand for heating applications in buildings is supplied by fossil fuels and electrical technologies. Concerning the exhaustion of fossil fuels in the future and the environmental problems related to their consumption, making use of renewable energy sources can be a practical alternative. On this point, solar energy is an appropriate source to be applied for heating by utilizing different technologies. The function and output of solar heaters depends on numerous factors, and this causes difficulties in the prediction of their performance and modelling. In this scenario, intelligent techniques are helpful and have been used by several scholars in recent years. This paper reviews proposed models for the prediction of the performance of different solar heaters. The literature review reveals that artificial neural Networks represent one of the most used approaches for the performance prediction of solar heaters; however, other intelligent techniques, namely support vector machines, have been used for this purpose too. Moreover, it is found that these methods have the ability to predict with great precision by applying the appropriate approach and architecture. In addition, it can be noted that the function of the models generated based on intelligent techniques are associated with some elements such as the employed function and architecture of the model. [ABSTRACT FROM AUTHOR]

Among the main fault locations of wind turbines, downtime accidents caused by bearing faults account for the majority. Therefore, it is of practical significance to detect the fault signal of the fan bearing as early as possible, and to arrange the maintenance plan reasonably, which is of practical significance to reduce the maintenance cost and increase the power generation time. Therefore, this paper proposes an early fault vibration detection and analysis model for wind power transmission based on deep neural networks and sensors. First of all, this paper studies the failure mechanism, vibration mechanism and signal characteristics of common failures of rolling bearings, combined with sensor technology, summarises and designs various bearing failures and failure signal detection models. Secondly, the deep neural network algorithm is used for the interference situation of rolling bearing vibration signal and the process of data re-analysis. The experimental and simulation results verify the adaptability of the early fault vibration detection model of wind power transmission in the early fault processing results, which can provide a reference for the early weak fault signal processing of wind turbine bearings. [ABSTRACT FROM AUTHOR]

Relating specifically to human–computer interaction (HCI), computer vision research has placed a substantial emphasis on intelligent emotion recognition in recent years. The primary emphasis lies in investigating speech aspects and bodily motions, while the knowledge of recognizing emotions from facial expressions remains relatively unexplored. Automated facial emotion detection allows a machine to assess and understand a person’s emotional state, allowing the system to predict intent by analyzing facial expressions. Therefore, this research provides a novel parameter selection strategy using swarm intelligence and a fitness function for intelligent recognition of micro emotions. This paper presents a novel method based on geometric visual representation obtained from facial landmark points. We employ the Deep Neural Networks (DNN) model to analyze the input features from the normalized angle and distance values derived from these landmarks. The results of the experiments show that Particle Swarm Optimization (PSO) worked very well by using only a few carefully chosen features. The method achieved a recognition success rate of 98.76% on the MUG dataset and 97.79% on the GEMEP datasets. [ABSTRACT FROM AUTHOR]

In this study, a bibliometric analysis technique is used for performance analysis and science mapping of artificial intelligence (AI) applications in streamflow research. This paper examines the current trends in the literature using the Scopus database over the last 37 years. RStudio Bibliometrix software was used to analyse the titles, keywords, abstracts, and full texts of 3000 publications to identify trends in AI models, publication types, journals, citations, authors, countries, and regions. The highest frequency AI-related keyword is "artificial neural networks," which was used in a total of 25587 times. The most common publication type, at 82.1%, is journal articles, and the highest rate of country production is 25% for China. In recent years, streamflow research studies have significantly increased their use of AI applications. [ABSTRACT FROM AUTHOR]

An interval type-2 fuzzy logic system (IT2FLS) can function well with uncertain data, with which a type-1 fuzzy logic system (T1FLS) is ineffective because its membership function rests upon crisp values. However, similar to T1FLSs, there are challenges associated with IT2FLSs in selecting parameters, which can significantly affect the accuracy of the classification results with their relatively high sensitivity. This paper discusses and proposes a hybrid model based on IT2FLS and particle swarm optimization (PSO) for prediction problems. The main objective of this paper is to find the optimal solution for the unknown fuzzy systems using labelled data for training the fuzzy system. The PSO technique was used to find the optimal parameters of the Gaussian membership functions which utilized for IT2FLSs. The authors tested two data sets for each of the two prediction problems, namely: burnt forest area prediction and wine quality prediction. The predictive results were compared with other predictive methods including random forest (RF), support vector machines (SVM), artificial neural network (ANN), adaptive neuro fuzzy inference system (ANFIS) and IT2FLS with parameters generated by using the fuzzy c-means algorithm (IT2FLS-FCM). Experiment results showed that the proposed method could significantly improve accuracy compared to several other predictive techniques. [ABSTRACT FROM AUTHOR]

The purpose of this paper is to predict the maximum pressure of journal bearing using ANN. The maximum pressure values are analysed using FEM and predicted using ANN. The FEM analysis is performed for micropolar lubricated hybrid journal bearing, and the results are used for training and testing the ANN model. Feedforward backpropagation algorithm is used for ANN model development. The externally applied load and rotational speed of the journal are considered as input parameters for performance predictions. ANN predictions are made within and outside the prescribed range of input parameters. This approach shows better predictions for journal bearing performance. Results obtained from FEM and ANN are in close agreement with each other. The percentage error less than 0.5 is observed for training and testing of the ANN model. The prediction error is in the range of −0.6% to 0.48%. In this paper, a mathematical model is established using FEM. The performance predictions obtained using ANN are very useful because much time can be saved which would be otherwise consumed in the experimental or theoretical bearing analysis. [ABSTRACT FROM AUTHOR]

The paper explores the potential study of artificial neural network (ANN) for prediction of response surface roughness (Ra) in face milling operation with respect to cryogenic approach. The model of Ra was expressed as the main factor in face milling of spindle speed, feed rate, depth of cut and coolant type. The ANN is trained using four various back propagation algorithms (BPA). The emphasis of the paper is to investigate the performance and the accuracy of the attained results depicts the effectiveness of the trained ANN in identifying the predicted Ra. The incorporated various BPA in predicting the Ra. The performance comparative study is made among statistical (Response Surface Methodology (RSM)) and ANN (BPA – training algorithm) methods. The various incorporated BPA algorithms are Gradient Descent (GD), Scaled Conjugate Gradient Descent (SCGD), Levenberg Marquardt (LM) and Bayesian Neural Network (BNN). Afterwards the best suitable BPA is identified in predicting Ra for AISI 316 in face milling operation using liquid nitrogen (LN2) as cutting fluid. The outperformed BPA is identified based on the attained deviation percentage and time required for the training the network. [ABSTRACT FROM AUTHOR]

In this paper, the exponential stability problem is considered for a class of hysteretic Hopfield neural networks with stochastic disturbances. The hysteretic nonlinearities are characterized by a Lipschitz-type constraint where the internal parameters of the hysteretic function are reflected. By resorting to Lyapunov function approach and stochastic analysis, a sufficient condition has been obtained under which the underlying hysteretic Hopfield neural network is exponentially stable in the mean square. The obtained condition is expressed in terms of linear matrix inequalities (LMIs) which can be easily checked via the Matlab toolbox. Finally, an illustrative example is provided to show the effectiveness of the results derived in this paper. [ABSTRACT FROM AUTHOR]

Entity and relation extraction has been widely studied in natural language processing, and some joint methods have been proposed in recent years. However, existing studies still suffer from two problems. Firstly, the token space information has been fully utilized in those studies, while the label space information is underutilized. However, a few preliminary works have proven that the label space information could contribute to this task. Secondly, the performance of relevant entities detection is still unsatisfactory in entity and relation extraction tasks. In this paper, a new model GANCE (Gated and Attentive Network Collaborative Extracting) is proposed to address these problems. Firstly, GANCE exploits the label space information by applying a gating mechanism, which could improve the performance of the relation extraction. Then, two multi-head attention modules are designed to update the token and token-label fusion representation. In this way, the relevant entities detection could be solved. Experimental results demonstrate that GANCE has better accuracy than several competitive approaches in terms of entity recognition and relation extraction on the CoNLL04 dataset at 90.32% and 73.59%, respectively. Moreover, the F1 score of relation extraction increased by 1.24% over existing approaches in the ADE dataset. [ABSTRACT FROM AUTHOR]

This paper aims to discover a suitable combination of contemporary feature selection techniques and robust prediction classifiers. As such, to examine the impact of the feature selection method on classifier performance, we use two Chinese and three other real-world credit scoring datasets. The utilized feature selection methods are the least absolute shrinkage and selection operator (LASSO), multivariate adaptive regression splines (MARS). In contrast, the examined classifiers are the classification and regression trees (CART), logistic regression (LR), artificial neural network (ANN), and support vector machines (SVM). Empirical findings confirm that LASSO's feature selection method, followed by robust classifier SVM, demonstrates remarkable improvement and outperforms other competitive classifiers. Moreover, ANN also offers improved accuracy with feature selection methods; LR only can improve classification efficiency through performing feature selection via LASSO. Nonetheless, CART does not provide any indication of improvement in any combination. The proposed credit scoring modeling strategy may use to develop policy, progressive ideas, operational guidelines for effective credit risk management of lending, and other financial institutions. The finding of this study has practical value, as to date, there is no consensus about the combination of feature selection method and prediction classifiers. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Natural Fibers is the property of Taylor & Francis Ltd 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.)

Natural streamflow data is required in many hydrological applications. However, many basins are located in data-scarce regions or are impacted by human construction and activities. In this paper, we explore three machine learning algorithms, namely artificial neural networks, random forest and light gradient boosting machine, to simultaneously estimate all the parameters of the coupled modèle du Génie Rural à 4 paramètres Journaliers (GR4J) and snow accounting routine called CemaNeige model. A database of 675 basins in the USA and Quebec is used to train and test ensembles. After using the estimated parameters in GR4J, the resulting naturalized streamflow series are compared with those obtained by the established drainage area ratio and spatial proximity transfer methods in 11 test basins. The results indicate that the machine learning algorithms outperform the drainage area ratio and spatial proximity transfer methods. Among machine learning algorithms, random forests obtain lower (better) continuous ranked probability scores than the other methods for 10 out of 11 test basins. [ABSTRACT FROM AUTHOR]

This paper presents a study of the resistive behavior of a Shape Memory Alloy spring, with a focus on the application of electrical resistance feedback in control systems. Artificial Neural Networks of different topologies were designed to learn the relation between spring electrical resistance and the force exerted. The feedback between layers in Neural Networks is demonstrated to be a key parameter in learning the non-linear and hysteretic behavior of Shape Memory Alloys. Experiments with closed-loop systems showed that shape memory alloy springs generated forces that converged satisfactorily to the desired reference values. The scientific contribution of this work is the use of electrical resistance variation as feedback for controlling the spring force, eliminating the use of an external force sensor. Neural networks were used for both, the sensing process and the system control; in that way the nonlinear and hysterical behavior of the shape memory alloy actuator was well considered. [ABSTRACT FROM AUTHOR]

This paper presents a heterogeneous ensemble classifier for price trend prediction of a stock, in which the prediction results are subsequently used in trading recommendation. The proposed ensemble model is based on Support vector machine, Artificial neural networks, Random forest, Extreme gradient boosting, and Light gradient boosting machine. A feature selection is performed to choose an optimal set of 45 technical indicators as input attributes of the model. Each base classifier is executed with an extensive hyperparameter tuning to improve performance. The prediction results from five base classifiers are aggregated through a modified majority voting among three classifiers with the highest accuracies, to obtain final prediction result. The performance of proposed ensemble classifier is evaluated using daily historical prices of 20 stocks from Stock Exchange of Thailand, with 3 overlapping datasets of 5-year intervals during 2014-2020 for different market conditions. The experimental results show that the proposed ensemble classifier clearly outperforms buy-and-hold strategy, individual base classifiers, and the ensemble with straightforward majority voting in terms of both trading return and Sharpe ratio. [ABSTRACT FROM AUTHOR]

In recent years, the rates of firearm-related violent acts worldwide have risen significantly. It is a severe social problem that compromises the safety of every individual to some extent. This situation has motivated researchers to find new ways to improve the current state-of-the-art solutions, such as automatic surveillance systems, to detect and classify the presence of firearms within a specific scene. These systems reduce the drawbacks of using direct human supervision. Among the available solutions for the classification task, the performance of Deep Learning models stands out, especially those based on Convolutional Neural Networks. Since they start learning directly from raw data (e.g., images), their learning process can be improved even further by using Transfer Learning techniques. However, the classification accuracy depends significantly on choosing the optimum set of values for the different hyper-parameters composing them. Thus, this paper analyses the improvement in the performance of an image-based handgun classification algorithm when tuning its hypermeters values instead of using its default values. In this work, we evaluated the performance variation using two benchmarks Convolutional Neural Networks architectures: AlexNet and Inception V3. We obtained a maximum accuracy of 94.11% when using the Inception V3 network and transfer learning. We employed Nadam as the optimizer and a learning rate equal to 0.0001, a batch size equal 256, and a total of 13 epochs. Experimental results suggest an essential relationship between the performance of the classification model and the data set, the specific combinations of values for the selected optimizer, the batch size, and the learning rate. The obtained improvement in the accuracy was up to 10.33% after the tuning process. [ABSTRACT FROM AUTHOR]

Agent-based modelling is a powerful tool when simulating human systems, yet when human behaviour cannot be described by simple rules or maximizing one's own profit, we quickly reach the limits of this methodology. Machine learning has the potential to bridge this gap by providing a link between what people observe and how they act in order to reach their goal. In this paper we use a framework for agent-based modelling that utilizes human values like fairness, conformity and altruism. Using this framework we simulate a public goods game and compare to experimental results. We can report good agreement between simulation and experiment and furthermore find that the presented framework outperforms strict reinforcement learning. Both the framework and the utility function are generic enough that they can be used for arbitrary systems, which makes this method a promising candidate for a foundation of a universal agent-based model. [ABSTRACT FROM AUTHOR]

This paper proposes a new, improved COmmon Software Measurement International Consortium function point (COSMIC FP) method that uses Artificial Neural Network (ANN) architectures based on Taguchi's Orthogonal Array to estimate software development effort. The minimum magnitude relative error (MRE) to evaluate these architectures considering the cost effect function, the type of data used in the training, testing, and validation of the proposed models, was used. Applying the fuzzification and clustering method to obtain seven different datasets, we would like to achieve excellent reliability and accuracy of the obtained results. Besides examining the influence of four input values, we aim to reduce the risks of potential errors, increase the coverage of a wide range of different projects and increase the efficiency and success of completing many various software projects. The main contributions of our work are as follows: the influence of four input values of the COSMIC FP method on the change of mean (MRE), development of two simple ANN architectures, the attainment of a small number of performed iterations in software effort estimation (less than 7), reduced software effort estimation time, the use of different values of the International Software Benchmarking Standards Group and other datasets used in the experiment. [ABSTRACT FROM AUTHOR]

Driven by the rapid development of Internet, more e-commerce product reviews are available on e-commerce platforms, which can help enterprises make business decisions. Currently, bidirectional encoder representations from transformers (BERT) applied in the embedding layer contributes to achieve promising results in English text sentiment analysis (SA). This paper proposes a novel model Chinese BERT with fused deep neural networks (CBERT-FDNN), extracting richer and more accurate semantic and grammatical information in Chinese text. First, Chinese BERT with whole word masking (Chinese-BERT-wwm) is used in the embedding layer to generate dynamic sentence representation vectors. It is a Chinese pre-training model based on the whole word masking (WWM) technology, which is more effective for Chinese text contextual embedding. Second, multi-channel and multi-scale convolutional neural networks (CNN) and bidirectional long short-term memory (BiLSTM) are designed to capture further crucial features in the feature extraction layer. To obtain more comprehensive sentence attributes, these features are concatenated together. Last, the model is evaluated on 100,000 sentence-level Chinese e-commerce product reviews for sentiment binary classification. The accuracy and F1 score can achieve 94.37% and 94.34%, respectively. Compared with the baseline models, the experiments show that our proposed model has higher accuracy and better prediction performance. [ABSTRACT FROM AUTHOR]

In this paper, a feed-forward artificial neural network (ANN) is used to price Johannesburg Stock Exchange (JSE) Top 40 European call options using a constructed implied volatility surface. The prices generated by the ANN were compared to the prices obtained using the Black-Scholes (BS) model. It was found that the pricing performance of the ANN significantly improves when the number of training samples are increased and that ANNs are able to price European call options in the South African market with a high degree of accuracy. [ABSTRACT FROM AUTHOR]

The article focuses on modelling reference crop evapotranspiration using vector machines. It relates the evapotranspiration modelling work of O. Kisi and M. Cimen wherein support vector machines and artificial neural networks were applied to a non-complex hydrological modelling problem. It mentions that four meteorological input measurements were utilized in the modeling work including solar radiation (Rs), air temperature (T), and relative humidity (RH). It suggests that measurement units for all input and output variables must be provided in each scientific reporting of data in data-driven modelling paper. It adds that each paper must consist of a numerical description of every variable used in the model.

In view of the local extreme problem of the gradient descent algorithm, which makes the working face of mine gas emission prediction uncertainly, this paper combined Wolf pack algorithm (WPA) with complex neural network nonlinear prediction method to the established new prediction model. The WPA shows good global convergence and computational robustness in the solving process of complex high-dimensional functions. Working face in a coal mine as a case, this paper selects seven factors as input variables of the mine gas emission prediction, uses training data to mature prediction model and adopted it to predict six group gas emission data. Research results show that the mean absolute percentage value of the complex neural network model which has been optimized by WPA is 0.06%, the root mean square error value is 0.0191, the mean absolute error value is 0.0175 and the equal coefficient value is 0.9979. The prediction results are very close to the real value, and the change trend is highly consistent with the actual situation. [ABSTRACT FROM AUTHOR]

In this paper, we solve the mean-square exponential input-to-state stability problem for a class of stochastic delayed recurrent neural networks with time-varying coefficients. With the aid of stochastic analysis theory and a Lyapunov-Krasovskii functional, we derive a novel criterion that ensures the given system is mean-square exponentially input-to-state stable. Furthermore, the new criterion generalizes and improves some known results. Finally, two examples and their numerical simulations are provided to demonstrate the theoretical results. [ABSTRACT FROM AUTHOR]

In this paper, we address the problem of robust sliding mode control (SMC) for a class of discrete-time stochastic systems with parameter uncertainties, time-varying delay and randomly varying nonlinearities (RVNs) under uncertain occurrence probability. Here, the norm-bounded parameter uncertainties are considered. The time-varying delay is bounded with known upper and lower bounds. In addition, the RVNs are depicted by using a Bernoulli distributed stochastic variable with uncertain occurrence probability. The aim of the paper is to provide an SMC method such that, for all parameter uncertainties, time-varying delay and RVNs, the robust asymptotic stability with a prescribed disturbance attenuation level is guaranteed for the sliding mode dynamics by providing a new sufficient condition. Moreover, the reachability analysis is carried out simultaneously, i.e. the states of the closed-loop system are driven onto a neighborhood of pre-designed sliding surface by synthesizing a robust sliding mode controller. Finally, the usefulness of the aforementioned control technique is verified by a numerical example. [ABSTRACT FROM AUTHOR]

This paper proposes runoff models based on machine learning to estimate daily streamflows in Oued Sebaou watershed, a Mediterranean coastal basin located in northern Algeria. Therefore, we applied random forest (RF), artificial neural networks (ANN – under different training algorithms), and locally weighted linear regression (LWLR) using as input combinations of current and past rainfall amounts and previous values of streamflow. We selected streamflow and rainfall records to calibrate and validate the stated approaches. We used root mean square error (RMSE) and correlation coefficient (R) to evaluate the accuracy of the models. Analyses of the results show that RF provided the best outcomes for both training (RMSE = 4.7458 and R = 0.9834) and validation (RMSE = 2.3617 and R = 0.9719). The ANN calibrated with the Levenberg-Marquardt algorithm presented the second-best result, outperforming its counterparts and LWLR. [ABSTRACT FROM AUTHOR]

This paper provides a study of the changes in land use in urban environments in two cities, Wuhan, China and western Sydney in Australia. Since mixed pixels are a characteristic of medium resolution images such as Landsat, when used for the classification of urban areas, due to changes in urban ground cover within a pixel, Multiple Endmember Spectral Mixture Analysis (MESMA) together with Super-Resolution Mapping (SRM) are employed to derive class fractions to generate classification maps at a higher spatial resolution using an Artificial Neural Network (ANN) predicted Wavelet method. Landsat images over the two cities for a 30-year period, are classified in terms of vegetation, buildings, soil and water. The classifications are then processed using Indifrag software to assess the levels of fragmentation caused by changes in the areas of buildings, vegetation, water and soil over the 30 years. The extents of fragmentation of vegetation, buildings, water and soil for the two cities are compared, while the percentages of vegetation are compared with recommended percentages of green space for urban areas for the benefit of health and well-being of inhabitants. Changes in Ecosystem Service Values (ESVs) resulting from the urbanization have been assessed for Wuhan and Sydney. The UN Sustainable Development Goals (SDG) for urban areas are being assessed by researchers to better understand how to achieve the sustainability of cities. [ABSTRACT FROM AUTHOR]

In order to maintain the safe operation of various types of equipment, the health status of main components should be monitored in real-time, and the demand for intelligent fault diagnosis algorithm has increased sharply. However, the traditional intelligent diagnosis algorithm is based on the manual method for signal feature extraction, which has high requirements for expert experience and poor generality. A convolutional neural network, with big data as its engine, is the most effective pattern classification algorithm at present. In this paper, the convolutional neural network is applied to time-domain vibration signal fault diagnosis, taking the bearing as an example, and an intelligent diagnosis method of bearing based on convolution neural network is proposed. The proposed method does not need manual feature extraction, and can automatically complete feature extraction and automatic fault recognition. The convolutional neural network has three convolutional layers. We use data enhancement techniques for the input raw signal and convert the one-dimensional original time-domain vibration signal into a two-dimensional signal. The model shows good results on CWRU dataset and the recognition accuracy of the algorithm in the CWRU bearing database is more than 96%. [ABSTRACT FROM AUTHOR]

Detecting defects and classifying them is a primary requirement for textile industries. Manual methods of defect identification and classification happens in most cases for which the accuracy could not exceed more than 70%. A real time, fast and automated system for defect detection and classification is required for textile industries. This paper addresses this challenge and explores the use of different machine-learning models for the global features such as GLCM and Tamura extracted from checked pattern fabrics. In the training phase, machine-learning models produce an accuracy of > 90% and testing with new fabric images provides a maximum accuracy of 65%. To improve the accuracy of the classification system, an artificial neural network-based machine-learning model with features fusing has been proposed. Using the proposed approach, a testing accuracy of 80% is observed, and an accuracy of 96.1% is achieved in the training phase. [ABSTRACT FROM AUTHOR]

Accurate modelling of power transformers is beneficial for fault diagnosis and the health condition assessment of the power transformers. However, measuring the internal parameters of power transformers while they are in operation is not feasible due to the costs involved in interrupting the power supply and dismantling the components. To address this issue, this paper proposes a new method that uses artificial neural networks and genetic algorithms to synthesise the power transformer lumped parameter network based on the frequency response. The proposed methodology can be utilised to model power transformers and obtain lumped parameter values with minimal cost and time. A physically realisable transfer function derived using the sweep frequency response test data of a power transformer is the input of the proposed model. The combined approach of an artificial neural network and genetic algorithms generates the output as resistive, inductive, and capacitive components of the lumped parameter circuit of power transformers. Furthermore, the entire approach is explained using a case study and validated by means of error analysis. The proposed method is an easy-to-implement process to develop in a computer program that can be used effectively for accurate fault identification in power transformers and health assessments. [ABSTRACT FROM AUTHOR]

Missing data is ubiquitous in hydrology. This phenomenon poses difficulty in the development of datadriven models. Events of missing data in groundwater pollution monitoring networks may occur due to failure of recording devices, malfunctioning of sensors, etc. Handling such missing data implies filling the missing portions of the data structure. Though several studies are available for dealing with missing data in the field of hydrology, literature dealing with such scenarios in groundwater pollution prediction is scarce. This paper assesses four imputation techniques-viz. linear, cubic spline, piece-wise cubic Hermite and modified Akima with cubic Hermite interpolation methods-for developing groundwater pollution prediction models using artificial neural network (ANN). The study employs the development of cascade-forward back-propagation ANN models using missing data ranging from 5% to 75% and evaluating their performance. Results show that imputation techniques can be effective in such circumstances. [ABSTRACT FROM AUTHOR]

Humanoid robots are expected to manipulate the objects they have not previously seen in real-life environments. Hence, it is important that the robots have the object recognition capability. However, object recognition is still a challenging problem at different locations and different object positions in real time. The current paper presents four novel models with small structure, based on Convolutional Neural Networks (CNNs) for object recognition with humanoid robots. In the proposed models, a few combinations of convolutions are used to recognize the class labels. The MNIST and CIFAR-10 benchmark datasets are first tested on our models. The performance of the proposed models is shown by comparisons to that of the best state-of-the-art models. The models are then applied on the Robotis-Op3 humanoid robot to recognize the objects of different shapes. The results of the models are compared to those of the models, such as VGG-16 and Residual Network-20 (ResNet-20), in terms of training and validation accuracy and loss, parameter number and training time. The experimental results show that the proposed model exhibits high accurate recognition by the lower parameter number and smaller training time than complex models. Consequently, the proposed models can be considered promising powerful models for object recognition with humanoid robots. [ABSTRACT FROM AUTHOR]

Dengue fever modelling in endemic locations is critical to reducing outbreaks and improving vector-borne illness control. Early projections of dengue are a crucial tool for disease control because of the unavailability of treatments and universal vaccination. Neural networks have made significant contributions to public health in a variety of ways. In this paper, we developed a deep learning modelling using random forest (RF) that helps to extract the features of the dengue fever from the text datasets. The proposed modelling involves the data collection, preprocessing of the input texts, and feature extraction. The extracted features are studied to test how well the feature extraction using RF is effective on dengue datasets. The simulation result shows that the proposed method achieves higher degree of accuracy that offers an improvement of more than 12% than the existing methods in extracting the features from the input datasets than the other feature extraction methods that have laid a foundation for Artificial Neural Network (ANN) model efficacy test. Further, the study reduces the errors associated with feature extraction that is 10% lesser than the other existing methods and this shows the efficacy of the model. [ABSTRACT FROM AUTHOR]

Due to a lack of solar radiation measurement instruments in various regions across the world, particularly in Ethiopia, many empirical models have been developed to estimate global solar radiation. Reliable global solar radiation infor- mation is essential for the design and development of solar energy systems.Thus, the aim of this paper is to investigate the feasibility of using Artificial Neural Network (ANN) to predict mean daily global solar radiation (GSR) and to compare the performance of ANN and empirical models based on sunshine in estimating mean daily global solar irradiation on a horizontal surface.For the ANN model, network inputs were daily data for a number of days, average daily data (sunshine hours, maximum temperature, minimum temperature, wind speed, relative humidity, and pressure), and while daily averaged global solar radiation was the network output.After training, the model had R values of 0.891 for training, 0.932 for validation, 0.920 for testing, and 0.903 for all, with validation performance of 0.0797.The results of the ANN model were compared to the empirical equations using statistical error evaluation (MBEANN = 0.0005, RMSEANN = 0.3310, and R2ANN = 0.7998).The agreement between the values of NASA and estimated values reveals that the ANN exhibits good performance in studying daily GSR. The result also shows that the mean daily GSR is varying between 3.675KWh/m² (August-1) and 6.935 KWh/m² (April-19) in the study site. [ABSTRACT FROM AUTHOR]

The paper investigates Passivity of Simpson 1/3 rule fuzzy neural network controller by teleoperation-based wheeled mobile robot navigation and wheel slippage. To render the obstacle avoidance for wheeled mobile robot and ensuring incident-free navigation particularly unlimited workspace and surface slippage of coordination for master robot position and slave robot velocity, a passivity controller mode is employed. Effective control strategies are formulated to achieve system stability in which soft-computing methodology is accessed to bypass robot wheel slippage and skidding. Soft-computing based fuzzy neural network system is framed through Simpson 1/3 rule for reducing master/slave robot position error on behalf of unavoidable and acceptable forces, which is confirmed by teleoperation system. We concluded mathematically, the system stability which has been shown via its passivity of the fuzzy neural network controller. The forces which can be handled by the human operator are approximately equal to the forces applied by the environmental force and sensor predictor of slave robot whichever comes under the unlimited workspace. Simulation results are verified with the effect of the proposed controller. Index Terms: Autonomous wheeled mobile robot, Passivity, adaptive network fuzzy inference system, Simpson's 1/3 rule, teleoperation system. [ABSTRACT FROM AUTHOR]

Coal is a principal source of energy and the combustion of coal supplies around one-third of the global electricity generation. Coal mines are also an important source of CH4 emissions, the second most important greenhouse gas. Monitoring CH4 emissions caused by coal mining using earth observation will require the exact location of coal mines. This paper aims to determine surface coal mines from satellite images through deep learning techniques by treating them as a land use/land cover classification task. This is achieved using Convolutional Neural Networks (CNN) that has proven to be capable of complex land use/land cover classification tasks. With a list of known coal mine locations from various countries, a training dataset of "Coal Mine" and "No Coal Mine" image patches is prepared using Sentinel-2 satellite images with 13 spectral bands. Various pre-trained CNN network architectures (VGG, ResNet, DenseNet) are trained and validated with our prepared coal mine dataset of 3500 "Coal Mine" and 3000 "No Coal Mine" image patches. After several experiments with the VGG network combined with transfer learning is found to be an optimal model for this task. Classification accuracy of 98% has been achieved for the validation dataset of the pre-trained VGG architecture. The model produces more than 95% overall accuracy when tested on unseen satellite images from different countries outside the training dataset and evaluated against visual classification. [ABSTRACT FROM AUTHOR]

Neural network models for complex dynamical systems typically do not explicitly account for structural engineering insight and mutual interrelations of various subprocesses that are related to the multi-physics nature of such systems. For that reason, they are commonly interpreted as a kind of data-driven, black box modelling option that is in opposition to a physically inspired equation-based system representation for which suitable parameters are subsequently identified in a grey box sense. To bridge the gap between data-driven and equation-based modelling paradigms, this paper proposes a novel approach for a physics-inspired structuring of neural networks. The derivation of this kind of structuring, an optimal choice of network inputs and numbers of neurons in a hidden layer as well as the achievable modelling accuracy are demonstrated for the thermal and electrochemical behaviour of high-temperature fuel cells. Finally, different network structures are compared against experimental data. [ABSTRACT FROM AUTHOR]

Accurate prediction of the scour hole depth and dimensions downstream of ski-jump spillways has been an important issue among hydraulic researchers for decades. In recent years, computing methods such as Artificial Neural Networks (ANNs), Adaptive Neuro-Fuzzy Inference Systems (ANFISs) and Support Vector Regression (SVR) have shown a powerful performance in the prediction of scour characteristics owing to their flexibility and learning nature. In the present paper, a new hybrid approach has been proposed for the first time in order to improve the estimation power of the SVR tool for scour hole geometry prediction below ski-jump spillways. The principal characteristics of the scour hole pattern in the equilibrium phase have been predicted using SVR optimized with Fruitfly Optimization Algorithms (FOAs). The hybrid model is compared with the corresponding simple SVR model. To evaluate the proposed hybrid model further, it is also compared with other machine learning and empirical methods, such as ANNs, ANFISs and regression equations. The results show that the proposed SVR-FOA method performs well, improves remarkably on Support Vector Machines (SVMs) results, estimates scour hole geometrical parameters more accurately than the simple SVR model, and can be applied as an alternative reliable scheme for estimations on which simple SVR and other methods demonstrate shortcomings. The proposed hybrid method improves the precision level for scour depth prediction by about 8% compared with simple SVM in terms of the correlation coefficient. [ABSTRACT FROM AUTHOR]