Search

Soft computing (SC) techniques are being used by drilling experts to have proper control on drilling processes and decrease the overall expenditure of these operations by providing the possibility of pre-estimating the drilling incidents. In this research study, several methods including generalized reduced gradient (GRG) method and SC techniques such as multilayer perceptron (MLP) and radial basis function (RBF) are employed to model apparent viscosity (AV), plastic viscosity (PV) and yield point (YP) values of water-based drilling fluids (WBDFs). Furthermore, to ameliorate the estimation capability of the SC models, the performance of different MLP learning algorithms such as Levenberg–Marquardt (LM), Bayesian regularization (BR), scaled conjugate gradient (SCG) and resilient backpropagation (RB) were investigated and finally the four top models were unified into a paradigm using a committee machine intelligent system (CMIS). Moreover, to facilitate the on-site estimation of AV, PV and YP parameters, GRG method was adopted and three novel correlations were proposed. Finally, the performance analysis of all the constructed models is done and with respect to the obtained results, the CMIS method is found to be the most successful method for the tested dataset. The average absolute percent relative errors (AAPRE) of this model was found to be 6.51%, 8.01% and 11.72% for AV, PV and YP respectively, indicating that this model outperforms almost all the other predictive approaches existing so far. Although other models in the literature produced a better accuracy, dataset used in this study is more complicated and generalized. Additionally, in comparison with the existing correlations, more accurate results for the tested dataset were provided by the correlations developed in this study.

The breast thermography process is a physiological investigation that gives data dependent on the heat variations in the breast. It accounts for the heat circulation of a body utilizing the infrared radiation produced by the outside of that body. Precancerous tissue and the zone around a carcinogenic tumor have greater heats because of angiogenesis, and higher substance and blood vein action than a healthy breast; consequently, breast thermography can possibly recognize early strange changes in breast tissues. Thermography can identify the earliest indication of cancer initiation before mammography can notice. For the extraction of the scarce data from the breast, features like Energy, Effective information, Multi quadratic, Sigmoid, and Age of the patient are determined and applied to the neural network as inputs. Resilient backpropagation algorithm (RBPA) is a worldwide methodology managing weights; it is hard to get better subtleties from the breast image. To overcome the problems of RBPA, the artificial neural network (ANN) classifier is being used as a new derived Extension of Resilient backpropagation algorithm (ERBPA) for validation purposes. In this paper three ANN-based algorithms are used: Gradient descent, RBPA, and ERBPA are discussed and compared. As per the outcomes, the recently determined ERBPA is a progressively exact methodology to classify benign and malignant pathology. An accuracy of 99.90% has been obtained to bring about an effective strategy, which can recognize and cure breast cancer at an early stage.

Breast cancer is the most common among women that leads to death if not diagnosed at early stages. Early diagnosis plays a vital role in decreasing the mortality rate globally. Manual methods for diagnosing breast cancers suffer from human errors and inaccuracy, and consume time. A computer-aided diagnosis (CAD) can overcome the disadvantages of manual methods and helps radiologists for accurate decision-making. A CAD system based on artificial neural network (ANN) optimized using a swarm-based approach can improve the accuracy of breast cancer diagnosis due to its strong prediction capabilities. Artificial bee colony (ABC) and whale optimization are metaheuristic search algorithms used to solve combinatorial optimization problems. This paper proposes a hybrid artificial bee colony with whale optimization algorithm (HAW) by integrating the exploitative employee bee phase of ABC with the bubble net attacking method of whale optimization to propose an employee bee attacking phase. In the employee bee attacking phase, employee bees use exploitation of humpback whales for finding better food source positions. The weak exploration of standard ABC is improved using the proposed mutative initialization phase that forms the explorative phase of the HAW algorithm. HAW algorithm is used in simultaneous feature selection (FS) and parameter optimization of an ANN model. HAW is implemented using backpropagation learning that includes resilient backpropagation (HAW-RP), Levenberg–Marquart (HAW-LM) and momentum-based gradient descent (HAW-GD). These hybrid variants are evaluated using various breast cancer datasets in terms of accuracy, complexity and computational time. HAW-RP variant achieved higher accuracy of 99.2%, 98.5%, 96.3%, 98.8%, 98.7% and 99.1% with low-complexity ANN model when compared to HAW-LM and HAW-GD for WBCD, WDBC, WPBC, DDSM, MIAS and INbreast, respectively.

Despite the growing success of machine learning for predicting structure-property relationships in molecules and materials, such as predicting the dielectric properties of polymers, it is still in its infancy. We report on the effectiveness of solving structure-property relationships for a computer-generated database of dielectric polymers using recurrent neural network (RNN) models. The implementation of a series of optimization strategies was crucial to achieving high learning speeds and sufficient accuracy: (1) binary and nonbinary representations of SMILES (Simplified Molecular Input Line System) fingerprints and (2) backpropagation with affine transformation of the input sequence (ATransformedBP) and resilient backpropagation with initial weight update parameter optimizations (iRPROP- optimized). For the investigated database of polymers, the binary SMILES representation was found to be superior to the decimal representation with respect to the training and prediction performance. All developed and optimized Elman-type RNN algorithms outperformed nonoptimized RNN models in the efficient prediction of nonlinear structure-activity relationships. The average relative standard deviation (RSD) remained well below 5%, and the maximum RSD did not exceed 30%. Moreover, we provide a C++ codebase as a testbed for a new generation of open programming languages that target increasingly diverse computer architectures.

The repair method for pavements should be selected considering the structural capacity of sublayers, in addition to the conditions observed at the pavement surface, to reduce the recurrence of distress in the repaired area. However, it is practically impossible to include the structural capacity of sublayers in the database of the pavement management system (PMS) because this would require additional tests in all expressway sections. Therefore, an artificial neural network model for predicting the indirect tensile strength (ITS) of the intermediate layer of all asphalt pavement sections in an expressway was developed in this study, taking the international roughness index, rut depth, surface distress, and equivalent single axle load as independent variables. The ITS of specimens cored from target sections was measured in the laboratory, and the PMS data for the target sections were collected. The ITS was predicted by conducting a feedforward process prior to the training step. When the error between the predicted and measured ITSs exceeded the allowable error, the model was repetitively trained using the resilient backpropagation method until the error fell within the acceptable boundary. The model was validated by analyzing the correlations between the ITSs predicted from the data of the training and test sets. Finally, the model was complemented by the corresponding minimum and maximum values of the ITS measured at the target section.

Poverty is a topic that continues and is always discussed up to this time, as a benchmark indicator of how the level of welfare and prosperity in the lives of people in a country. Several attempts have been made by the central and regional governments to reduce poverty levels, including “Bantuan Langsung Tunai” (BLT) and the “Program Keluarga Harapan” (PKH). However, poverty reduction in Indonesia is still slowing down, including in South Sulawesi. Based on this, this study aims to predict poverty levels in South Sulawesi. Factors thought to influence poverty levels are the Human Development Index (HDI), the Open Unemployment Rate (TPT), and the Gross Regional Domestic Product (GRDP). The data used are data from 2010 to 2014. The method used is a backpropagation neural network with a resilient algorithm or better known as a resilient backpropagation neural network (RBNN). The results of the prediction of poverty levels using predictors of HDI, TPT, and GRDP showed that the analysis of the RBNN reached its optimum using architecture [3- 9 - 1] and reached convergence at the 81th iteration with an accuracy rate of 95.34%.

This work proposes a novel method for the detection of Left Ventricular Hypertrophy (LVH) from a multi-lead ECG signal. Left Ventricle walls become thick due to prolonged hypertension which may fail to pump heart effectively. The imaging techniques can be used as an alternative diagnose LVH; however, they are more expensive and time-consuming than proposed LVH. To overcome this issue, an algorithm to the diagnosis of LVH using ECG signal based on machine learning techniques were designed. In LVH detection, the pathological attributes such as R wave, S wave, inversion of QRS complex, changes in ST segment noticed in the ECG signal. This clinical information extracted as a feature by applying continuous wavelet transform. The signals were reconstructed with the frequency between 10 and 50 Hz from the wavelet. This followed by the detection of R wave and S wave peaks to obtain the relevant LVH diagnostic features. The Support Vector Machine (SVM), K-Nearest Neighbor (KNN), Ensemble of Bagged Tree, AdaBoost classifiers were employed and the results are compared with four neural network classifiers including Multilayer Perceptron (MLP), Scaled Conjugate Gradient Backpropagation Neural Network (SCG NN), Levenberg–Marquardt Neural Network (LMNN) and Resilient Backpropagation Neural network (RPROP). The data source includes Left Ventricular Hypertrophy and healthy ECG signal from PTB diagnostic ECG database and St Petersburg INCART 12-Lead Arrhythmia Database. The results revealed that the proposed work can diagnose LVH successfully using neural network classifiers. The accuracy in detecting LVH is 86.6%, 84.4%, 93.3%,75.6%, 95.6%, 97.8%, 97.8%, 88.9% using SVM, KNN, Ensemble of Bagged Tree, AdaBoost, MLP, SCG NN, LMNN and RPROP classifiers, respectively.

Several studies have applied particle swarm optimization (PSO) algorithms to train neural networks (NNs) for time series forecasting and the results indicated good performance. These studies, however, assumed static environments, making the PSO trained NNs unsuitable for forecasting many real-world time series which are generated by non-stationary processes. This study formulates training of a NN forecaster as a dynamic optimization problem, to investigate the application of a dynamic PSO algorithm to train NNs in forecasting time series in non-stationary environments. For this purpose, a set of experiments were conducted on three simulated and seven real-life time series forecasting problems under four different dynamic scenarios. Results obtained are compared to the results of NNs trained using a standard PSO and resilient backpropagation (Rprop). The results show that the NNs trained using dynamic PSO algorithms outperform the NNs trained using PSO and Rprop. These findings highlight the potential of using dynamic PSO in training NNs for real-world forecasting applications.

Backpropagation Neural Network (BPNN) is an artificial intelligence technique that has seen several applications in many fields of science and engineering. It is well-known that, the critical task in developing an effective and accurate BPNN model depends on an appropriate training algorithm, transfer function, number of hidden layers and number of hidden neurons. Despite the numerous contributing factors for the development of a BPNN model, training algorithm is key in achieving optimum BPNN model performance. This study is focused on evaluating and comparing the performance of 13 training algorithms in BPNN for the prediction of blast-induced ground vibration. The training algorithms considered include: Levenberg-Marquardt, Bayesian Regularisation, Broyden–Fletcher–Goldfarb–Shanno (BFGS) Quasi-Newton, Resilient Backpropagation, Scaled Conjugate Gradient, Conjugate Gradient with Powell/Beale Restarts, Fletcher-Powell Conjugate Gradient, Polak-Ribiére Conjugate Gradient, One Step Secant, Gradient Descent with Adaptive Learning Rate, Gradient Descent with Momentum, Gradient Descent, and Gradient Descent with Momentum and Adaptive Learning Rate. Using ranking values for the performance indicators of Mean Squared Error (MSE), correlation coefficient (R), number of training epoch (iteration) and the duration for convergence, the performance of the various training algorithms used to build the BPNN models were evaluated. The obtained overall ranking results showed that the BFGS Quasi-Newton algorithm outperformed the other training algorithms even though the Levenberg Marquardt algorithm was found to have the best computational speed and utilised the smallest number of epochs. Keywords: Artificial Intelligence, Blast-induced Ground Vibration, Backpropagation Training Algorithms

Short-term power load prediction is crucial for scheduling generators, securing transmission capacity, and determining economic market price. This paper proposes a Bigdata-based Artificial Neural Network (B-ANN) model for a short-term load forecasting by utilizing decision-tree method. The bigdata has been composed of 2018 time index, meteorological data, exchange rates, oil price, and past power demand in Seoul. The decision-tree method is applied to classify the data in accordance with the value of decreasing entropy. In addition, the resilient back propagation algorithm (RPROP) is applied for ANN that derives fast results and result in reduced error through variable learning rates. The applicability and effectiveness of the proposed model are verified by conducting simulations for forecasting 1-day hourly power load. The results confirm that the proposed model has decreased the mean absolute percentage error (MAPE) dramatically in comparison with other forecasting methods such as multiple regression analysis, time series analysis, and auto-regressive integrated moving average (ARIMA) model.

Music selection is difficult without efficient organization based on metadata or tags, and one effective tag scheme is based on the emotion expressed by the music. However, manual annotation is labor intensive and unstable because the perception of music emotion varies from person to person. This paper presents an emotion classification system for digital music with a resolution of eight emotional classes. Russell’s emotion model was adopted as common ground for emotional annotation. The music information retrieval (MIR) toolbox was employed to extract acoustic features from audio files. The classification system utilized a supervised machine learning technique to recognize acoustic features and create predictive models. Four predictive models were proposed and compared. The models were composed by crossmatching two types of neural networks, i.e., Levenberg-Marquardt (LM) and resilient backpropagation (Rprop), with two types of structures: a traditional multiclass model and the cascaded structure of a binary-class model. The performance of each model was evaluated via the MediaEval Database for Emotional Analysis (DEAM) benchmark. The best result was achieved by the model trained with the cascaded Rprop neural network (accuracy of 89.5%). In addition, correlation coefficient analysis showed that timbre features were the most impactful for prediction. Our work offers an opportunity for a competitive advantage in music classification because only a few music providers currently tag music with emotional terms.

Artificial neural network (ANN) models can be trained to simulate the dynamic behavior of biological systems. In the present study, an ANN model was developed upon multilayer perceptron neural network architecture with 23-20-1 configuration to predict the cell concentration of microalga Chlorella vulgaris at a given time. Irradiance level, photoperiod, temperature, air flow rate, CO2 percentage of the air stream, initial cell concentration, cultivation time and the nutrient concentrations of the media were considered as the input variables of the model. Resilient backpropagation learning algorithm was used to train the model by means of 484 experimental data belonging to four studies. Bias and accuracy factors of the developed model fall into the range of 0.95–1.11 indicating the model has an excellent prediction ability. Parity plot showed a good agreement between the predicted and experimental values with R2 = 0.98. Relative importance of the inputs was evaluated using Garson’s algorithm. The results of the study indicated that CO2 supply had the highest impact on the growth of C. vulgaris within the selected range of input parameters. Among macronutrients and micronutrients, highest influence was demonstrated by nitrogen and copper respectively.

In this study, we propose a new hybrid machine-learning algorithm called artificial multi-neural approach, for developing a multi-input single-output (MISO) model to estimate the hourly global solar radiation (HGSR) time series in Agdal site (latitude 31° 37′ N, longitude 08° 01′ W, elevation 466 m), Marrakesh, Morocco. To achieve this goal, three training algorithms (scaled conjugate gradient, Levenberg-Marquardt, and resilient backpropagation) are selected to train the developed model, using some accessible hourly meteorological variables recorded during 7 years (from 2008 to 2014) as exogenous inputs. Furthermore, a pertinence determination test (PDT) is used to point out the most pertinent inputs for the accurate HGSR estimation. The best configuration of the multi-neural model includes five known input parameters as the best scenario, i.e., acquisition hour, air temperature, relative humidity, wind speed, and precipitation. Some statistical indicators are used to evaluate the performance of the developed model. The obtained results demonstrate the reliability and the precision of our proposed machine-learning algorithm, representing a good solution for estimating solar radiation time series needed to design and manage solar energy systems compared to the present standards.

The next-generation cellular systems, including fifth-generation cellular systems (5G), are empowered with the recent advances in artificial intelligence (AI) and other recent paradigms. The internet of things (IoT) and the tactile internet are paradigms that can be empowered with AI solutions and integrated with 5G systems to deliver novel services that impact the future. Machine learning technologies (ML) can understand examples of nonlinearity from the environment and are suitable for network traffic prediction. Network traffic prediction is one of the most active research areas that integrates AI with information networks. Traffic prediction is an integral approach to ensure security, reliability, and quality of service (QoS) requirements. Nowadays, it can be used in various applications, such as network monitoring, resource management, congestion control, network bandwidth allocation, network intrusion detection, etc. This paper performs time series prediction for IoT and tactile internet delays, using the k-step-ahead prediction approach with nonlinear autoregressive with external input (NARX)-enabled recurrent neural network (RNN). The ML was trained with four different training functions: Bayesian regularization backpropagation (Trainbr), Levenberg–Marquardt backpropagation (Trainlm), conjugate gradient backpropagation with Fletcher–Reeves updates (Traincgf), and the resilient backpropagation algorithm (Trainrp). The accuracy of the predicted delay was measured using three functions based on ML: mean square error (MSE), root mean square error (RMSE), and mean absolute percentage error (MAPE).

This chapter focuses on cost control by analyzing the intelligent control system of waste paper deinking production line, and finally designs a solution. In the aspect of control index, machine learning has designed a solution that pays less attention to the benefit of a single control loop and focuses on maximizing the overall benefit of the production line. In the aspect of control demand, according to the complexity of waste paper deinking production line, a distributed control solution is designed Finally, according to the dynamic fuzziness in machine learning system, the basic concept of dynamic fuzzy machine learning is constructed by using dynamic fuzzy set The dynamic fuzzy machine learning model is described and the related learning algorithm is given. Finally, a simulation example is given, and satisfactory results are obtained by comparing with the elastic BP algorithm RPROP of neural network.

In the present research, an artificial neural network model was developed to predict the pool boiling heat transfer coefficient (HTC) of refrigerant-based nanofluids based on a large number of experimental data (1342) extracted from the literature. Diverse training algorithms, e.g., Bayesian regulation backpropagation, Levenberg–Marquardt (LM), Resilient backpropagation and scaled conjugate gradient were utilized. Besides, several transfer functions like log-sigmoid (logsig), radial basis (radbas), soft max transfer function (softmax), hard-limit (hardlim), tan-sigmoid (tansig) and triangular basis (tribas) were applied for the hidden layer, and their influences on model correctness were surveyed. The effects of heat flux, saturation pressure, nanoparticle thermal conductivity, base fluid thermal conductivity, nanoparticle concentration (mass%), nanoparticles size and lubricant concentration (mass%) on the pool boiling HTC of refrigerant-based nanofluids were determined over wide ranges of operating conditions. A network possessing one hidden layer with 19 neurons using tansig and purelin as transfer functions in hidden and output layers in a row was introduced as a model having the best performance. In addition, LM was known as a much more efficient train algorithm in comparison with others resulting in extremely precise prediction. The outcomes indicated the present model could accurately estimate the pool boiling HTC of refrigerant-based nanofluids with a correlation coefficient (R2) of 0.9948 and overall mean square error of 0.01529.

Unemployment is a big problem faced by the Indonesian people from year to year besides poverty. Therefore it is necessary to predict the level of open unemployment in Indonesia so that later the government and private parties have the right references and references to work together to overcome this problem. The prediction method used is Resilient Backpropagation which is one method of Artificial Neural Networks which is often used for data prediction. The research data used is open unemployment data according to the highest education completed in 2005-2018 based on the semester obtained from the website of the Indonesian Central Bureau of Statistics. Based on this data a network architecture model will be formed and determined, including 12-6-2, 12-12-2, 12-18-2, 12-24-2, 12-12-12-2, 12-12-18 -2, 12-18-18-2 and 12-18-24-2. From these 8 models after training and testing, the results show that the best architectural model is 12-18-2 (12 is the input layer, 18 is the number of hidden neurons and 2 is the output layer). The accuracy of the architectural model for semester 1 and semester 2 is 75% with an MSE value of 0.0022135087 and 0.0044974696

In this article, nano-crystalline titanium dioxide has been modeled by artificial neural networks (ANN) and resilient back-propagation (Rprop) training algorithm. For this purpose, composite hardness ( H c ), yield stress ( σ y ), and film hardness ( H f ) have been collected at different dwell time (t), temperature (T) and relative indentation depth (β). ANN was trained on the available experimental data. Many runs were tried to achieve good performance. Simulation results and predicted values were compared with the corresponding experimental data. This comparison shows that neural networks are very powerful in modeling the nano-crystalline titanium dioxide experimental data with very low percentage of error. Mathematical formula describes the relation between inputs (t, T, β) and outputs ( H c , σ y , H f ) obtained based on ANNs. Finally, this article showed that ANNs are very successful tools in modeling and are able to pursue the experimental data with a high exactness.

The aim of paper is to address the issues such as poor convergence, moderate BER, residual ISI associated with unsupervised (blind) weight adaptation technique employed for channel equalization. Tw...

This paper presents a clinical decision support system using Artificial Neural Networks (ANN). The system uses Multilayer Perceptron (MLP) feed forward neural network to predict the risk of developing Venous Thromboembolism (VTE) in hospitalized patients. The developed system classifies the risk of VTE into five risk levels ranging from low to high. The input layer of the system consists of 35 input variables grouped into six categories representing the risk factors of VTE according to Caprini model. The output layer consists of one node indicating a value representing the level of VTE risk. The number of hidden nodes and layers is determined through an iterative process. The system is trained using Resilient Backpropagation algorithm (Rprop). The dataset used for training and testing the system consists of 150 medical records obtained from Jordan University Hospital (JUH). Stratified ten-fold cross validation scheme is applied to assess the generalization of the proposed system. The results of the experiment show that the accuracy of the system is 81%. Keywords: Clinical decision support system, Venous thromboembolism, Artificial neural network, Multilayer perceptron, Resilient backpropagation

Neural Network and Binary Logistic Regression are modern and classical data mining analysis tools that can be used to classify data on Bidikmisi scholarship acceptance in East Java Province, Indonesia. One form of Neural Network model available for various applications is the Resilient Backpropagation Neural Network (Resilient BPNN). This study aims to compare the performance of the Resilient BPNN method as a Deep Learning Neural Network and Binary Logistic Regression method in determining the classification of Bidikmisi scholarship acceptance in East Java Province. After preprocessing data and dividing them into two parts, i.e. sets of testing and training data, with 10-foldcross-validation procedure, the Resilient BPNN and Binary Logistic Regression methods are implemented. The result shows that Resilient BPNN with two hidden layers is the best platformnetwork model. The classificationG-mean resulted by these both methods is that Resilient BPNN with two hidden layers is more representative with better performance than Binary Logistic Regression. The Resilient BPNN is recommended to be used topredict acceptance of Bidikmisi applicants yearly.

Microwave device design process requires repetitive and time-consuming electromagnetic simulations to extract device parameters. New methods are needed to accelerate the process and enable it for real time parameter calculations. Feed-forward backpropagation multilayer perceptron artificial neural network with 3 hidden layers is presented to predict S21 parameters of 3.5 GHz band-pass filter. Prediction results, received with neural network trained with Resilient Backpropagation, One Step Secant, Scaled Conjugate Gradient and BFGS Quasi-Newton training methods, are compared with each other. The best prediction results are received after training network with BFGS Quasi-Newton training method. Average mean squared error and root mean square error received is 0.0044 and 0.066 respectively. As predictions of neural network are noticeably faster than electromagnetic simulation and prediction errors are low, the method can be used to predict band-pass filter parameters in real time.

Epilepsy is a neurological disorder that adversely affects the social life of the affected people. Nearly 65 million people were affected worldwide. In many cases, (nearly30%) of this disease cannot be healed with medications. However, seizure prediction will help in disease prevention. Encephalogram is the common test that helps to diagnose the epilepsy. The electrical activity of human brain can be recorded as EEG signals. The manual inspection to detect abnormalities in the epileptic form is more time-consuming and inaccurate. This arises a need for automated framework that helps in precisely distinguishing EEG signals. Various researchers have employed different machine-learning models for seizure prediction. But achieving high performance is still a challenging task. The proposed model provides a reliable system for seizure prediction with improved performance by using different ANN models. Neural network is presently a blazing technique in machine learning paradigm, which constitutes noble success in several healthcare data analysis. There are many ML models available for seizure detection with EEG signals. The existing models preprocess the data and extract the feature before classification. According to our knowledge, there is no work with ANN for seizure classification has been done on the preprocessed clinical dataset. This research work proposes a framework with preprocessed dataset and extracted time domain features. The proposed system provides automated seizure prediction framework, which integrates random-forest method for feature selection and ANN classifiers for seizure prediction. There are several forms of neural network, where everyone have their individual precise use case. In the proposed framework, different ANN methods like ANN with resilient back-propagation with weights, ANN with resilient back-propagation without weights and two types of globally convergent methods are used as classifiers with sigmoid as activation function and they are trained and tested as trail and error method to find the best number of hidden layers and nodes in each layer. According to the results, this framework provides a expedite analysis with the selected attributes of EEG signals to detect seizures and reduces time complexity in analyzing the large datasets. Among different ANN methods(RPROP+, RPROP-, SAG, SLR), SLR provides good accuracy as 99.56 % and precision as 99.2%.

This study introduces the improvement of mathematical and predictive models of surface roughness parameter (Ra) in milling AA6061 alloy using carbide cutting tools coated with CVD-TiCN in dry condition. An experimental model has been improved for estimating the surface roughness using artificial neural networks (ANN) and response surface methodology (RSM). For these models, cutting speed, depth of cut, and feed rate were evaluated as input parameters for experimental design. For the ANN modelling, the standard backpropagation algorithm was established to be the optimum selection for training the model. In the forming of the network construction, five different learning algorithms were used: the conjugate gradient backpropagation, Levenberg-Marquardt, scaled conjugate gradient, quasi-Newton backpropagation, and resilient backpropagation. The best consequent with single hidden layers for the surface roughness was obtained by 3-8-1 network structures. The statistical analysis was performed with RSM-based second-order mathematics model. The influences of the cutting parameters on surface roughness were defined by using analysis of variance (ANOVA). The ANOVA results show that the depth of cut is the most effective parameter on surface roughness. Prediction models developed using ANN and RSM were compared in terms of prediction accuracy R2, MEP, and RMSE. The data estimated from ANN and RSM were realized to be very close to the data acquired from experimental studies. The value R-2 of RSM model was higher than the values of the ANN model which demonstrated the stability and sturdiness of the RSM method. WOS:000621837500001 2-s2.0-85101526619

Fused Filament Fabrication (FFF) or Fused Deposition Modelling (FDM) or three-dimension (3D) printing are rapid prototyping processes for workpieces. There are many factors which have a significant effect on surface quality, including bed temperature, printing speed, and layer thickness. This empirical study was conducted to determine the relationship between the above-mentioned factors and average surface roughness (Ra). Workpieces of cylindrical shape were fabricated by an FFF system with a Polylactic acid (PLA) filament. The surface roughness was measured at five different positions on the bottom and top surface. A response surface (Box-Behnken) method was utilised to design the experiment and statistically predict the response. The total number of treatments was sixteen, while five measurements (Ra1, Ra2, Ra3, Ra4 and Ra5) were carried out for each treatment. The settings of each factor were as follows: bed temperature (80, 85, and 90 °C), printing speed (40, 80 and 120 mm/s), and layer thickness (0.10, 0.25 and 0.40 mm). The prediction equation of surface roughness was then derived from the analysis. The same set of data was also used as the inputs for a machine learning method, an artificial neural network (ANN), to construct the prediction equation of surface roughness. Rectified linear unit (ReLU) was utilised as the activation function of ANN. Two training algorithms (resilient backpropagation with weight backtracking and globally convergent resilient backpropagation) were applied to train multi-layer perceptrons. Moreover, the different number of neurons in each hidden layer was also studied and compared. Another interesting aspect of this study is that the ANN was based on a limited number of training samples. Finally, the prediction errors of each method were compared, to benchmark the prediction performance of the two methods: Box-Behnken and ANN.

The accurate forecasting of electricity demand is an important issue. The objective of this study is the application of two forecasting methods, Box-Jenkin’s autoregressive integrated moving average (ARIMA) and artificial neural network (ANN), to fit a time series data of electricity demand. Three models of ARIMA, AR (1), ARMA (1, 1), and IMA (1, 1), were utilized to fit the demand data. Another method, ANN, was based on the activation function of rectified linear unit (ReLU) and the training algorithm of resilient backpropagation with weight-backtracking. The performance of these models was compared by considering the root mean square error (RMSE) which was used to measure the errors when each model was applied to fit the data.

Although regression is among the oldest areas of statistics, new approaches may still be found. One recent suggestion is Best Response Regression, where one tries to find a regression function that provides, for as many instances as possible, a better prediction than some reference regression function. In this paper we propose a new method for Best Response Regression that is based on gradient ascent rather than mixed integer programming. We evaluate our approach for a variety of noise (or error) distributions, showing that especially for heavy-tailed distributions best response regression outperforms, on unseen data, ordinary least squares regression, both w.r.t. the sum of squared errors as well as the number of instances for which better predictions are provided.

The adulteration of honey is common. Recently, High Throughput Sequencing (HTS)-based metabarcoding method has been applied successfully to pollen/honey identification to determine floral composition that, in turn, can be used to identify the geographical origins of honeys. However, the lack of local references materials posed a serious challenge for HTS-based pollen identification methods. Here, we sampled 28 honey samples from various geographic origins without prior knowledge of local floral information and applied a machine learning method to determine geographical origins. The machine learning method uses a resilient backpropagation algorithm to train a neural network. The results showed that biological components in honey provided characteristic traits that enabled accurate geographic tracing for nearly all honey samples, confidently discriminating honeys to their geographic origin with >99% success rates, including those separated by as little as 39 km.

With increasing traffic on motorways of international transport corridors, the demand for modern traffic control systems is generated. Based on the METANET model analysis and on-ramp control algorithms used in the United States, Canada, Australia, the Netherlands and several Asian countries: Fixed-time ALINEA, BOTTLENECK, ZONE, Demand Capacity (DC), VSL, HERO / RWS, PRMA, METALINE, SZM, SWARM, RPROP, DynaTAM etc., an algorithm is designed. This algorithm exploits the potential of Intelligent transportation and logistics system (ITLS) to implement proactive traffic control on the basis of its monitoring, forecasting intensity and direction, which allows one to anticipate the overloaded sections of the highway and ramps, develop control actions for the entrance traffic lights of ramps, traffic lights and placards that form the flows coming to the ramps, as well as recommended speeds and flow breaks in the entrance lane of the Expressway. The possibility of using self-driving cars to supplement information about traffic characteristics obtained from stationary sensors of the ITLS transport infrastructure is analyzed.

Flood prediction has gained prominence world over due to the calamitous socio-economic impacts this hazard has and the anticipated increase of its incidence in the near future. Artificial intelligence (AI) models have contributed significantly over the last few decades by providing improved accuracy and economical solutions to simulate physical flood processes. This study explores the potential of the AI computing paradigm to model the stream flow. Artificial neural network (ANN), fuzzy logic, and adaptive neuro-fuzzy inference system (ANFIS) algorithms are used to develop nine different flood prediction models using all the available training algorithms. The performance of the developed models is evaluated using multiple statistical performance evaluators. The predictability and robustness of the models are tested through the simulation of a major flood event in the study area. A total of 12 inputs were used in the development of the models. Five training algorithms were used to develop the ANN models (Bayesian regularization, Levenberg Marquardt, conjugate gradient, scaled conjugate gradient, and resilient backpropagation), two fuzzy inference systems to develop fuzzy models (Mamdani and Sugeno), and two training algorithms to develop the ANFIS models (hybrid and backpropagation). The ANFIS model developed using hybrid training algorithm gave the best performance metrics with Nash-Sutcliffe Model Efficiency (NSE) of 0.968, coefficient of correlation (R2) of 97.066%, mean square error (MSE) of 0.00034, root mean square error (RMSE) of 0.018, mean absolute error (MAE) of 0.0073, and combined accuracy (CA) of 0.018, implying the potential of using the developed models for flood forecasting. The significance of this research lies in the fact that a combination of multiple inputs and AI algorithms has been used to develop the flood models. In summary, this research revealed the potential of AI algorithm-based models in predicting floods and also developed some useful techniques that can be used by the Flood Control Departments of various states/regions/countries for flood prognosis.

In this paper, a vertically moving base inverted pendulum control analysis has been done using Matlab/Simulink Toolbox. Because the vertically moving base inverted pendulum system is nonlinear and highly unstable, a feedback control system is used to make the system controlled and stable. A nonlinear autoregressive moving average L2 controller which is a family of Neural Network controller is used with Resilient backpropagation and Levenberg Marquardt backpropagation Training Algorithm to improve the stability of the pendulum. Comparison of the vertically moving base inverted pendulum using NARMA-L2 with Resilient backpropagation and Levenberg Marquardt backpropagation Training Algorithm for tracking a desired angular position of the system using a step and random input signals and a promising results have been obtained succesfully.

Palynology is a botanical discipline devoted to the study of pollen and spores [1], focusing mainly on the analysis of the external morphology that presents structural patterns different from those of the variations in the exine, which is the external wall of the pollen grains. The study and microscopic analysis of its symmetry, wall opening, contour, shape, size, etc., have a taxonomic value and allows distinguishing different taxa at different levels: family, genera, species. The study of pollen grains is a difficult task, in its different phases, from small microscopic samples. The analysis of these is an important source of information for many scientific and industrial applications, making palynology a valuable tool for various areas of knowledge [1]. In palynology, neural networks have been successfully applied for the classification of pollen grains. For this purpose, RPROP was selected as a neural network training algorithm for the classification of a previously reported dataset.

The ideas and technology behind artificial neural networks have advanced considerably since their introduction in 1943 by Warren McCulloch and Walter Pitts. However, the complexity of large networks means that it may not be computationally feasible to retrain a network during the execution of another program, or to store a network in such a form that it can be traversed node by node. The purpose of this project is to design and implement a program that would train an artificial neural network and export source code for it so that the network may be used in other projects. After discussing some of this history of neural networks, I explain the mathematical principals behind them. Two related training algorithms are discussed: backpropagation and RPROP. I also go into detail about some of the more useful activation functions. The actual training portion of the project was not self implemented. Instead, a third party external library was used: Encog, developed by Heaton Research. After analyzing how Encog stores the weights of the network, and how the network is trained, I discuss how I used several of the more important classes. There are also details of the slight modifications I needed to make to one of the classes in the library. The actual implementation of the project consists of five classes, all of which are discussed in the fourth chapter. The program has two inputs by the user (a config file and a training data set), and returns two outputs (a training error report and the source code). The paper concludes with discussions about additional features that may be implemented in the future. Finally, an example is given, proving that the program works as intended.