Search

The recent studies on Artificial Intelligence (AI) accompanied by enhanced computing capabilities supports increasing attention into traditional control methods coupled with AI learning methods in an attempt to bringing adaptiveness and fast responding features. The Model Predictive Control (MPC) technique is a widely used, safe and reliable control method based on constraints. On the other hand, the Eddy Current dynamometers are highly nonlinear braking systems whose performance parameters are related to many processes related variables. This study is based on an adaptive model predictive control that utilizes selected AI methods. The presented approach presents an updated the mathematical model of an Eddy Current Dynamometer based on experimentally obtained system operational data. Finally, the comparison of AI methods and related learning performances based on the assessment technique of mean absolute percentage error (MAPE) issues are discussed. The results indicate that Single Hidden Layer Neural Network (SHLNN), General Regression Neural Network (GRNN), Radial Basis Network (RBNN), Neuro Fuzzy Network (ANFIS) coupled MPC have quite satisfying performances. The presented results indicate that, amongst them, GRNN appears to provide the best performance. [ABSTRACT FROM AUTHOR]

This paper presents a design and real-time application of an efficient Artificial Intelligence (AI) method assembled with PID controller of an eddy current dynamometer (ECD) for robustness due to highly nonlinear system by reason of some magnetism phenomena such as skin effect and dissipated heat of eddy currents. PID Control which is known as the most popular conventional control method in industry is inadequate for such nonlinear systems. On the other hand, Adaptive Neural Fuzzy Interference System (ANFIS), Single Hidden Layer Neural Network (SHLNN), General Regression Neural Network (GRNN), and Radial Basis Neural Network (RBNN) are examples used as artificial intelligence-based techniques that can increase the performance of conventional control systems in particular. The proposed control system proves changeable Kp (Proportional gain), Ki, (Integral gain) and Kd (Derivative gain) parameters in real-time to adapt and presents a good capacity to adapt nonlinearities and bring robustness using 4 different versatile soft computing methods of ANFIS, SHLNN, GRNN, and RBNN. The testing dataset is extracted from experimental studies and its robustness has also been verified with different Artificial Intelligence (AI) methods. The presented technique is observed to have a good performance in terms of response time (t) and accuracy of desired speed value (V) under different parameters such as non-linear dynamics (V, T) of the system elements and the varying load effects. [ABSTRACT FROM AUTHOR]

Although knowledge of the microstructure of food of vegetal origin helps us to understand the behavior of food materials, the variability in the microstructural elements complicates this analysis. In this regard, the construction of learning models that represent the actual microstructures of the tissue is important to extract relevant information and advance in the comprehension of such behavior. Consequently, the objective of this research is to compare two machine learning techniques—Convolutional Neural Networks (CNN) and Radial Basis Neural Networks (RBNN)—when used to enhance its microstructural analysis. Two main contributions can be highlighted from this research. First, a method is proposed to automatically analyze the microstructural elements of vegetal tissue; and second, a comparison was conducted to select a classifier to discriminate between tissue structures. For the comparison, a database of microstructural elements images was obtained from pumpkin (Cucurbita pepo L.) micrographs. Two classifiers were implemented using CNN and RBNN, and statistical performance metrics were computed using a 5-fold cross-validation scheme. This process was repeated one hundred times with a random selection of images in each repetition. The comparison showed that the classifiers based on CNN produced a better fit, obtaining F1–score average of 89.42% in front of 83.83% for RBNN. In this study, the performance of classifiers based on CNN was significantly higher compared to those based on RBNN in the discrimination of microstructural elements of vegetable foods. [ABSTRACT FROM AUTHOR]

Text classification technology, an important basis for text mining and information retrieval, is mainly to determine the text category according to the text content under a predetermined set of categories. Traditional manual text categorization has gradually failed to meet the needs, while automatic text categorization based on artificial intelligence has become an important research direction in the field of natural language processing. To this end, this paper introduced the RBNN-based classification algorithm by considering the high dimensionality, non-linearity and complex correlation between feature items, and the theoretical and feasibility analysis were carried out so as to apply it to text feature dimension reduction. Also, the effects of the distribution density of the radial basis function in the radial basis neural network and the normalized form of the input data on the classification results were studied. Through the computer simulation experiment, the influence rule of distribution density of the radial basis function in the radial basis neural network and the normalized form of the input data on the training precision and test accuracy of the classification process were demonstrated in the form of curves, which provides guidance for the application of RBNN in pattern recognition. [ABSTRACT FROM AUTHOR]

Generally, Magnetic Resonance Imaging (MRI) is utilised in radiology for diagnose the anatomy and the physiological processes of the body. Nowadays, the classification of tumour region plays a vital role in MRI brain imaging technique. Due to variance and complexity of tumours, the classification and segmentation of tumour are burdensome in MRI brain images. This paper proposes a Radial Basis Neural Network (RBNN) based on exponential cuckoo search algorithm for the automatic classification of tumour in the brain. Initially, the fuzzy c-means clustering is employed to the segmentation for the detection of tumour region. Then, the features are extracted from the tumour and nontumour regions that are concatenated to generate the feature vector. These features are applied to the proposed classifier RBNN. This classifier requires the optimal cluster centre which is iteratively evaluated by the newly proposed exponential cuckoo search algorithm. Thus, the classifier classifies the tumour and nontumour images and also determines the severity of tumour. The proposed system is analysed for the evaluation metrics, such as segmentation accuracy, MSE and accuracy. Thus, the proposed system attains the higher accuracy 89% which ensures, the better classification of MRI brain image. [ABSTRACT FROM AUTHOR]

Although knowledge of the microstructure of food of vegetal origin helps us to understand the behavior of food materials, the variability in the microstructural elements complicates this analysis. In this regard, the construction of learning models that represent the actual microstructures of the tissue is important to extract relevant information and advance in the comprehension of such behavior. Consequently, the objective of this research is to compare two machine learning techniques—Convolutional Neural Networks (CNN) and Radial Basis Neural Networks (RBNN)—when used to enhance its microstructural analysis. Two main contributions can be highlighted from this research. First, a method is proposed to automatically analyze the microstructural elements of vegetal tissue; and second, a comparison was conducted to select a classifier to discriminate between tissue structures. For the comparison, a database of microstructural elements images was obtained from pumpkin (Cucurbita pepo L.) micrographs. Two classifiers were implemented using CNN and RBNN, and statistical performance metrics were computed using a 5-fold cross-validation scheme. This process was repeated one hundred times with a random selection of images in each repetition. The comparison showed that the classifiers based on CNN produced a better fit, obtaining F1–score average of 89.42% in front of 83.83% for RBNN. In this study, the performance of classifiers based on CNN was significantly higher compared to those based on RBNN in the discrimination of microstructural elements of vegetable foods.

Optimum configuration of a micromixer with two-layer crossing microstructure was performed using mixing analysis, surrogate modeling, along with an optimization algorithm. Mixing performance was used to determine the optimum designs at Reynolds number 40. A surrogate modeling method based on a radial basis neural network (RBNN) was used to approximate the value of the objective function. The optimization study was carried out with three design variables; viz., the ratio of the main channel thickness to the pitch length (H/PI), the ratio of the thickness of the diagonal channel to the pitch length (W/PI), and the ratio of the depth of the channel to the pitch length (d/PI). Through a primary parametric study, the design space was constrained. The design points surrounded by the design constraints were chosen using a well-known technique called Latin hypercube sampling (LHS). The optimal design confirmed a 32.0% enhancement of the mixing index as compared to the reference design.

Early-stage diagnosis of Brain Tumor leads to better chance of cure from this deadliest disease across the globe. Existing schemes on brain tumor classification use machine learning, convolutional neural networks, Generative Adversarial Networks, and deep learning schemes. However, more execution time and uncertain predictions leading additional process to cross-check the obtained results. In this paper, a classification model Saliency-K-mean-SSO-RBNN is formulated including a new hybrid salience-K-mean segmentation technique along with utilizing the advantage of social spider optimization (SSO) algorithm in Radial Basis Neural Network (RBNN). Hybrid Saliency Map with K-means cluster-based segmentation approach is formulated to segment the tumor region. As Saliency map spotlights on eye catching region within target image, segmented image is fetched to feature extraction phase by considering multiresolution wavelet transform, Principal Component, Kurtosis, Skewness, Inverse Difference Moment (IDM), Cosine transform. Feature vector is then processed for an efficient classification using RBNN by optimizing the cluster center through SSO. RBNN with Gaussian kernel depicts a low complex model for classification. Saliency-K-mean-SSO-RBNN and new hybrid Saliency-K-mean segmentation are validated on standard datasets and compared with existing schemes with regard to specificity, precision, sensitivity, F1 score, MCC, Kappa coefficient and complexity. Saliency-K-mean-SSO-RBNN, yielding a classification accuracy in three datasets as 96%, 92%, and 94%. [Display omitted] • Presents a new hybrid Saliency-K-mean based segmentation technique. • Discusses novel texture and statistical based features. • Presents an efficient classification approach by combining SSO with RBNN. • Presents experimental validation for the proposed method. [ABSTRACT FROM AUTHOR]

Applicability of artificial neural networks is examined in determining the natural frequencies of intact beams and crack parameters of damaged beams. Multi-layer perceptron (MLP) and radial basis neural networks (RBNN) are utilized for training and validation of input data. In the first part of the study, the first four frequencies of free vibration are predicted based on beam properties by the networks. Showing the effectiveness of the neural networks in predicting the vibrational frequencies, the second part of the study is carried out. At this stage of the inverse problem, the frequencies and mode shape rotation deviations in addition to beam properties are used as input to the networks to determine the crack parameters. Different hidden nodes, epochs and spread values are tried to find the optimal neural networks that give the lowest error estimates. In both parts of the study, the RBNN model performs better. The robustness of the network models in the presence of noise is also shown. It is shown that the optimal MLP network predicts the crack parameters slightly better in the presence of noise. As a conclusion, the trained RBNN model can be used in health monitoring of beam-like structures as a crack identification algorithm.

In this paper, a multi-variable regression model, a back propagation neural network (BPNN) and a radial basis neural network (RBNN) have been utilized to correlate the cutting parameters and the performance while electro-discharge machining (EDM) of SiC/Al composites. The four cutting parameters are peak current ( I ), pulse-on time ( T ), pulse-off time ( T ), and servo voltage ( S ); the performance measures are material remove rate (MRR) and surface roughness (Ra). By testing a large number of BPNN architectures, 4-5-1 and 4-7-1 have been found to be the optimal one for MRR and Ra, respectively; and it can predict them with 10.61 % overall mean prediction error. As for RBNN architectures, it can predict them with 12.77 % overall mean prediction error. The multivariable regression model yields an overall mean prediction error of 13.93 %. All of these three models have been used to study the effect of input parameters on the material remove rate and surface roughness, and finally to optimize them with genetic algorithm (GA) and desirability function. Then, an intelligent optimization system with graphical user interface (GUI) has been built based on these multi-optimization techniques, in which users can obtain the optimized cutting parameters under the desired surface roughness (Ra). [ABSTRACT FROM AUTHOR]

Applicability of artificial neural networks is examined in determining the natural frequencies of intact beams and crack parameters of damaged beams. Multi-layer perceptron (MLP) and radial basis neural networks (RBNN) are utilized for training and validation of input data. In the first part of the study, the first four frequencies of free vibration are predicted based on beam properties by the networks. Showing the effectiveness of the neural networks in predicting the vibrational frequencies, the second part of the study is carried out. At this stage of the inverse problem, the frequencies and mode shape rotation deviations in addition to beam properties are used as input to the networks to determine the crack parameters. Different hidden nodes, epochs and spread values are tried to find the optimal neural networks that give the lowest error estimates. In both parts of the study, the RBNN model performs better. The robustness of the network models in the presence of noise is also shown. It is shown that the optimal MLP network predicts the crack parameters slightly better in the presence of noise. As a conclusion, the trained RBNN model can be used in health monitoring of beam-like structures as a crack identification algorithm. [ABSTRACT FROM AUTHOR]

The suggestion is prepared for Particle Swarm Optimization (PSO) Recurrent Neural Network (RNN) based Z-Source Inverter Fed Induction Motor Drive in this document. The proposed method is employed to develop the presentation of the induction motor while decreasing the Total Harmonic Distortion (THD), eliminating the oscillation period of the stator current, torque and speed. Currently, as the input parameters, the PSO technique uses the induction motor speed and reference speed. It optimizes the raise of the PI controller and produces the reference quadrature axis current from the input parameters. By employing the RNN the reference three phase current for accurate control pulses of the voltage source inverter is predicted. The RNN is trained by the input motor actual quadrature axis current and the reference quadrature axis current with the associated target reference three phase current. The training process used the supervised learning process. Next the proposed technique is implemented in the MATLAB/simulink platform and the competence is scrutinized by comparing with the other techniques such as PSO-Radial Biased Neural Network (RBNN) and PSO-Artificial Neural Network (ANN). The comparison results show the superiority of the proposed approach and confirm its potential to effort out the problem. [ABSTRACT FROM AUTHOR]

This paper deals with the identification and classification of internal fault current of power transformer occurring during the time of abnormal condition. The need of internal fault current classification is to avoid the complexity of the fault category. In this paper, the inrush current and short circuit current of the transformer internal windings are classified from the nominal current. Before the classification process, the analytical model parameters based identification of inrush current is described. The analytical model parameters considered are wave shape and wave peak of the current. The output of the power transformer is applied to classifier and then, the shape and peak of the waveform are extracted from the classifier. Here, an artificial intelligence based radial basis neural network (RBNN) classifier is used to extract the wave parameters. In the RBNN, the Gaussian function is considered as an activation function. The proposed internal fault identification and classification technique is implemented and tested with different ratings of transformer, and the fault classification performances are evaluated. Then, the evaluated results are compared with the feed-forward network. [ABSTRACT FROM AUTHOR]

The process-based Soil and Water Assessment Tool (SWAT) model and the data-driven radial basis neural network (RBNN) model were evaluated for simulating sediment load for the Nagwa watershed in Jharkhand, India, where soil erosion is a severe problem. The SWAT model calibration and uncertainty analysis were performed with the Sequential Uncertainty Fitting algorithm version 2 and the bootstrap technique was applied on the RBNN model to analyse uncertainty in model output. The percentage of data bracketed by the 95% prediction uncertainty (95PPU) and therfactor were the two measures used to assess the goodness of calibration. Comparison of the results of the two models shows that the value ofrfactor (r = 0.41) in the RBNN model is less than that of SWAT model (r = 0.79), which means there is a wider prediction interval for the SWAT model results. More values of observed sediment yield were bracketed by the 95PPU in the RBNN model. Thus, the RBNN model estimates the sediment yield values more accurately and with less uncertainty. EditorD. Koutsoyiannis;Associate editorH. Aksoy CitationSingh, A., Imtiyaz, M., Isaac, R.K., and Denis, D.M., 2014. Assessing the performance and uncertainty analysis of the SWAT and RBNN models for simulation of sediment yield in the Nagwa watershed, India.Hydrological Sciences Journal, 59 (2), 351–364. [ABSTRACT FROM PUBLISHER]

Optimum configuration of a micromixer with two-layer crossing microstructure was performed using mixing analysis, surrogate modeling, along with an optimization algorithm. Mixing performance was used to determine the optimum designs at Reynolds number 40. A surrogate modeling method based on a radial basis neural network (RBNN) was used to approximate the value of the objective function. The optimization study was carried out with three design variables; viz., the ratio of the main channel thickness to the pitch length (H/PI), the ratio of the thickness of the diagonal channel to the pitch length (W/PI), and the ratio of the depth of the channel to the pitch length (d/PI). Through a primary parametric study, the design space was constrained. The design points surrounded by the design constraints were chosen using a well-known technique called Latin hypercube sampling (LHS). The optimal design confirmed a 32.0% enhancement of the mixing index as compared to the reference design. [ABSTRACT FROM AUTHOR]

Hydrologic models are important tools for the successful management of water resources. In this study, a semi-distributed soil and water assessment tool (SWAT) model is used to simulate streamflow at the headwater of Çarşamba River, located at the Konya Closed Basin, Turkey. For that, first a sequential uncertainty fitting-2 (SUFI-2) algorithm is employed to calibrate the SWAT model. The SWAT model results are also compared with the results of the radial-based neural network (RBNN) and support vector machines (SVM). The SWAT model performed well at the calibration stage i.e., determination coefficient (R2) = 0.787 and Nash–Sutcliffe efficiency coefficient (NSE) = 0.779, and relatively lower values at the validation stage i.e., R2 = 0.508 and NSE = 0.502. Besides, the data-driven models were more successful than the SWAT model. Obviously, the physically-based SWAT model offers significant advantages such as performing a spatial analysis of the results, creating a streamflow model taking into account the environmental impacts. Also, we show that SWAT offers the ability to produce consistent solutions under varying scenarios whereas it requires a large number of inputs as compared to the data-driven models. [ABSTRACT FROM AUTHOR]