Abstract: The extended state observer (ESO)-based deadbeat active disturbance rejection control (DB-ADRC) is commonly employed for high-performance torque or current control, however, it performs poorly when rejecting current harmonics caused by periodic disturbances, such as inverter nonlinearities and flux harmonics. The internal model-based method, such as resonant control, can be combined with ESO to mitigate current ripples when the harmonic frequencies are known, which however is not always the case in real applications. In this article, an online-trained radial basis function neural network (RBFNN) compensator with fast training process is integrated into the DB-ADRC system to simultaneously suppress the aperiodic and harmonic disturbances without knowing harmonic frequencies. By using the proposed scheme, current harmonics under various speed and load conditions can be effectively suppressed without affecting dynamic performance. Various experiments are conducted on the test bench based on the dSPACE MicroLabBox and permanentmagnet synchronous motor to validate the effectiveness of the proposed method.

Abstract: Electricity consumption forecasting stands as a critical research domain within electrical engineering, with myriad of traditional forecasting models and artificial intelligence techniques undergoing rigorous examination. This paper is devoted to a comparison of three Machine Learning approaches to surrogate modelling and forecasting of the daily electricity consumption in Tirana, Albania: A Radial Basis Function (RBF) approach, a feed forward Neural Network approach and a Recurrent Neural Network approach. Through meticulous experimentation across four distinct scenarios encompassing variations in training/testing splits, historical data utilization, and hyper parameter optimization, we thoroughly evaluate the performance of each model. Comparative analysis is conducted based on model fit, computational efficiency, and error measurement metrics. Our findings highlight the remarkable performance of the RBF ARX approach, underscoring its effectiveness in accurately forecasting electricity consumption.

Abstract: In order to better predict chaotic time series, this paper proposes a normalized detrended spatiotemporal radial basis function network (ND-ST-RBFNN) based on the traditional radial basis function neural network (RBFNN) and the spatiotemporal radial basis function network (ST-RBFNN). The input data is normalized and detrended using a linear regression model before entering the network. This method is used to predict the Chebyshev chaotic time series. Compared to the traditional ST-RBFNN, this method reduces the mean squared error of the predictions and improves prediction accuracy. Experimental results illustrate the efficacy of this approach, showing good performance and flexibility in chaotic time series prediction problems.

Abstract: With the more and more extensive use of robot technology in industrial production, the trajectory planning requirements of industrial robots are constantly increasing. In order to solve the problem that the trajectory is difficult to fit due to the nonlinearity in the continuous trajectory planning of robot, this paper presents a trajectory planning method of industrial robots which combines RBF (radial basis function) neural network and PSO (particle swarm optimization) algorithm. When RBF neural network has fewer hidden layer nodes, PSO algorithm is used to optimize the connection weight and threshold of RBF neural network. Through simulation analysis, the RBF neural network before and after improvement is compared. The results show that compared with the trajectory planning algorithm before improvement, the PSO-RBF neural network has smaller error and stronger adaptability, which meets the expected requirements of industrial robot trajectory planning.

Abstract: Radial Basis Function Neural Networks (RBFNNs) have been widely used for classification and function approximation tasks.‎ Hence, it is worthy to try improving and developing new learning algorithms for RBFNNs in order to get better results.‎ This paper presents a new learning method for RBFNNs.‎ An improved algorithm for center adjustment of RBFNNs and a novel algorithm for width determination have been proposed to optimize the efficiency of the Optimum Steepest Decent (OSD) algorithm.‎ To initialize the radial basis function units more accurately, a modified approach based on Particle Swarm Optimization (PSO) is presented.‎ The obtained results show fast convergence speed, better and same network response in fewer train data which states the generalization power of the improved neural network.‎ The Improved PSO–OSD and Three-phased PSO–OSD algorithms have been tested on five benchmark problems and the results have been compared.‎ Finally, using the improved radial basis function neural network we propose a new method for object image retrieval.‎ The images to be retrieved are object images that can be divided into foreground and background.‎ Experimental results show that the proposed method is really promising and achieves high performance.‎

Abstract: Predicting breast cancer poses a challenge in the field of medical data analysis. Healthcare professionals, including doctors and pathologists, necessitate automated tools to aid in decision-making and to distinguish between malignant and benign tumors. The radial basis function neural network is a feedforward artificial neural network employing radial basis functions as activation functions in the hidden layer. In this paper, we present a novel model aimed at optimizing the selection of radial basis functions, centers, variances, and weights for the output layer. The optimization problem is structured as a mixed-variable optimization problem with linear constraints. To address this challenge, the authors suggest employing a genetic algorithm-based approach. Subsequently, this methodology is applied to breast cancer prediction, utilizing the optimized parameters to enhance the overall performance of the model.

Abstract: This study presents a thorough methodology for predicting software reliability by employing Radial Basis Function Networks (RBFNs). By using machine learning methodologies such as Radial Basis Function Networks (RBFNs), software development teams are enabled to make well-informed decisions, optimize resource allocation, and proactively mitigate potential dependability concerns. Consequently, this results in improved software quality and heightened customer happiness. This methodology involves multiple stages, starting with data collection and preprocessing. We assemble a comprehensive dataset comprising historical software performance metrics, defect reports, and relevant development process information. After data cleansing and feature engineering, we split the dataset into training, validation, and testing subsets. The core of this approach lies in the construction and training of RBFNs. These neural networks consist of an input layer, a hidden layer with radial basis functions, and an output layer. The architecture parameters, particularly the number of hidden neurons and the spread parameter of the radial basis functions, are optimized through a systematic hyperparameter tuning process using the validation dataset. Upon achieving an optimal model configuration, we rigorously evaluate the RBFN predictive capabilities using the testing dataset.

Abstract: To explore the prediction effect of network security situational awareness on network vulnerabilities and attacks under the background of big data, this study constructs a predictive index system based on the network security situational awareness model. Based on the improved cuckoo algorithm, the cuckoo search radial basis function neural network is used to predict the situation. The weight value in the model is determined by the hierarchical analysis method, vulnerability simulation is conducted by Nessus software and network attack simulation is conducted by Snort software, and then the situation is evaluated by a fuzzy comprehensive evaluation method. Finally, Jquery and Bootstrap software is used to develop the system. The results show that the cuckoo search radial basis function model proposed in this study could predict network security situations more accurately than the radial basis function model, cuckoo search back-propagation neural network model, genetic algorithm radial basis function model and Support vector machine model based on particle swarm optimization model.

Abstract: This paper introduces a hybrid approach combining Radial Basis Function Networks (RBFN) and Grey Wolf Optimization (GWO) to address the challenges of energy efficiency and security in Intelligent IoT networks for precision farming. Our proposed method utilizes RBFN for feature extraction and classification of network states, while GWO optimizes the routing parameters to achieve an optimal balance between energy conservation and security. The hybrid RBFN-GWO algorithm adapts to dynamic network conditions and evolving security threats in real-time. Extensive simulations using real-world precision farming data demonstrate that our approach outperforms existing protocols, achieving a 20% increase in network lifetime and a 15% improvement in intrusion detection accuracy. This research contributes to the development of more efficient and secure IoT infrastructures for precision agriculture applications.

Abstract: This study presents a novel approach for esti-mating lateral velocity, an important parameter for vehicle stability characterization. Aiming to resolve the problems of poor estimation accuracy caused by the insufficient modeling of traditional model-based methods and issues with sampled and delayed measurements, a sampled delay data neural network method for lateral velocity estimation is designed. Our approach incorporates a compensating injector to fill information gaps between samples, an extended compensation dynamic to reduce delays' impact, and a radial basis function neural network to mimic vehicle motions. Continuous weight updates ensure adaptability, and stability is demonstrated using the Lyapunov methodology. Experimental results confirm the effectiveness of our approach, providing promising insights to enhance lateral velocity estimation and improve control and stability in autonomous vehicle systems.

Abstract: This paper proposes a linear quadratic regulation (LQR) tracking control method based on a radial basis function (RBF) that successfully compensates for the shortcomings of the LQR method. The LQR method depends on the linearity of a model. Specifically, an RBF neural network is used to approximate and compensate for the nonlinear part of a controlled object in the PID type-I, type-II and type-III control loops to improve the performance of the system. Through the simulation of different industrial systems, such as underdamped, overdamped and critically damped systems, the method significantly improves the dynamic response performance indices, such as the rise time and settling time, of the system.

Abstract: Accurately estimating the lateral velocity of automatic ground vehicles is a complex task, especially when faced with sensor-sampled measurements and unfamiliar mathematical models. In order to overcome these difficulties, the study presented here proposes a novel approach that makes use of a sampled-data neural network observer. In order to fill in the information gap between successive samples, a compensating injector is introduced to the continuous state observer on which the observer is based. In order to replicate unknown dynamic vehicle systems, a radial basis function neural network is also implemented. A special weight update mechanism is used to update the weights continually. The Lyapunov methodology is used to demonstrate the stability of the suggested method. Experimental findings validate the effectiveness of the sampled-data neural network observer, providing promising insights for improving lateral velocity estimation and enhancing the control and stability of autonomous vehicle systems.

Abstract: To explore the prediction effect of network security situational awareness on network vulnerabilities and attacks under the background of big data, this study constructs a predictive index system based on the network security situational awareness model. Based on the improved cuckoo algorithm, the cuckoo search radial basis function neural network is used to predict the situation. The weight value in the model is determined by the hierarchical analysis method, vulnerability simulation is conducted by Nessus software and network attack simulation is conducted by Snort software, and then the situation is evaluated by a fuzzy comprehensive evaluation method. Finally, Jquery and Bootstrap software is used to develop the system. The results show that the cuckoo search radial basis function model proposed in this study could predict network security situations more accurately than the radial basis function model, cuckoo search back-propagation neural network model, genetic algorithm radial basis function model and Support vector machine model based on particle swarm optimization model.

Abstract: Rehabilitation robots based on variable stiffness elastic actuators exhibit strong human-robot interaction char-acteristics due to the specific features of the actuators, including flexible drive and variable stiffness output capabilities. However, to ensure the robot can achieve rehabilitation actions smoothly, safely, and precisely, accurate modeling and control of the variable stiffness elastic actuators becomes a burning question. In order to address this challenge, a dynamic model is established considering the actuator's own gravity factor and the influence of disturbances, and a nominal dynamic model is designed. Accurate tracking of output location and stiffness is reached by designing a radial basis function (RBF) network to approximate the actual dynamic model. Through simulation experiments, it is verified that the block approximation RBF network adaptive controller designed in this article has lower actuator tracking error and higher control accuracy than the proportional integral derivative (PID) controller.

Abstract: In the process of developing present higher education reform, peoples pay much attention to the research of college English education. The goal to enhance college English education is to improve education quality, learning evaluation to enhance the education quality and training. This research proposed a Radial Basis Function (RBF) neural network for English teaching quality evaluation and prediction. The collected dataset is used here and it is preprocessed by The RPF is adoptable for z-score normalization. The preprocessed data features are selected by Chi-square technique and teaching quality is predicted by RBF neural network. The RPF is adoptable for handling non-linear relationship among input and output of teaching quality due to its ability to handle complex, non-linear relationship and generate predictions based on several input factors. The f1-score, precision, accuracy and recall are used for evaluating RBF performance. The RBF achieves $\mathbf{9 6. 2 5} \%$ f1-score, $96.81 \%$ precision, $97.16 \%$ accuracy, $\mathbf{9 6. 3 8 \%}$ recall when compared to state-of-art methods.