Generalized Regression Neural Network Research Articles

Boruta extra tree-bidirectional long short-term memory model development for Pan evaporation forecasting: Investigation of arid climate condition

In this study, two deep learning approaches, bidirectional long short-term memory (BiLSTM) and long short-term memory (LSTM), were used along with adaptive boosting and general regression neural network to forecast multi-step-ahead pan evaporation in two arid climate stations in Iran (Ahvaz and Yazd). Lagged time series of meteorological data and pan evaporation data were input to the machine learning models. Two feature selection methods, i.e., the Boruta extra tree and XGBoost, were used to select significant inputs to reduce the number of inputs and model complexity. Different statistical metrics were used to investigate the model performance. The results demonstrated that Boruta-extra-tree-based models were more accurate than XGBoost-based models. Compared with the machine learning techniques, the combination of Boruta extra tree and BiLSTM enabled more accurate one-day-ahead forecasting of pan evaporation for both sites (Root Mean Square Error (RMSE) = 1.6857, for the Ahvaz station, and RMSE = 1.3996 for the Yazd station). The proposed model was used to forecast up to 30 days ahead of pan evaporation in both stations. The results showed that the Boruta-BiLSTM model could accurately forecast the pan evaporation for up to 30 days in both stations.

An Ensemble Method for the Regression Model Parameter Adjustments: Direct Approach

Intelligence analysis of tabular datasets in the field of biomedical engineering is a complex task. This is explained both by the multidimensional datasets and the complex relationships between the components of the set, and by the high price of the error in the prediction. The task becomes more difficult in the case of limited data for training, which often occurs in this field. This is due to the enormous time, material, or human resources required to collect enough data to implement training procedures with classical machine learning tools. This paper presents a new approach to solving this task. The author has developed a new ensemble method for the regression model parameters adjustments (direct approach) with the possibility of cyclically increasing the accuracy of intellectual analysis of short datasets. The basis of the method is the use of the rational fraction and two machine learning algorithms for its parametric identification. Modeling of the method's efficiency on a real-world short set of data from the field of biomedical engineering demonstrated the high accuracy of the developed method's operation. In particular, the prediction accuracy of the General Regression Neural Network was increased by more than 14% (based on the coefficient of determination. That is why the developed method can be used to solve various applied biomedical engineering tasks in the case of the need to analyze small amounts of data

Smart algorithms for power prediction in smart EV charging stations

Power prediction in solar powered electric vehicle (EV) charging stations is very essential for smooth and uninterrupted operations due to the high oscillatory output of renewables and their dependence on various atmospheric factors. The need for early prediction helps EV stations improve their power performance and utilize available power by designing intelligent charge scheduling algorithms. This study introduces a novel design approach for an off-grid photovoltaic (PV)-powered EV charging station, which involves three main stages: evaluating and analyzing different solar irradiance prediction models (theoretical, empirical, and artificial neural network (ANN) models), forecasting day-ahead solar power profiles, and optimizing charge scheduling for pre-booked vehicles using energy storage systems (ESS). The effectiveness of various solar irradiance prediction models is assessed to identify the best-performing model. The proposed approach employs a novel algorithmic procedure to fine-tune the selected model using a basic dataset. Power prediction simulations are conducted using MATLAB, while Python is utilized for model development. The feed forward neural network (FFNN) model for irradiance prediction has a 0.88 R2 score; the anisotropic general regression neural network (AGRNN), isotropic GRNN both have 0.94 and 0.95 R2 values for direct PV current prediction, providing a strong base for reliable forecasting models. The significance of ESS backup for effective charging stations is clearly demonstrated by a remarkable 20 kW peak shaving.

Developing a Novel Long Short-Term Memory Networks with Seasonal Wavelet Transform for Long-Term Wind Power Output Forecasting

Long-term wind power forecasting is a challenging endeavor that requires predictions that span years into the future. Accurate forecasting is crucial for optimizing energy production, grid integration, maintenance scheduling, and financial planning. This study attempts to first develop the long short-term memory networks (LSTM) with a seasonal wavelet transform forecasting model for practical long-term wind power forecasting problems with seasonal and regional influences on wind power and the instability of data signals. This model encapsulates wavelet transformation and seasonal decomposition, and employs LSTM for forecasting. The new prediction model adopted seasonal decompositions and two LSTMs to approach low- and high-frequency series datasets, as well as the wavelet synthesis prediction values. Furthermore, the parameters of the LSTM models are selected using stochastic optimization. For a comprehensive evaluation, the proposed LSTM with seasonal wavelet transform is compared with seven methods, including seasonal LSTM (SLSTM), wavelet LSTM (WLSTM), and the seasonal auto-regressive integrated moving average (SARIMA), back propagation neural network (BPNN), generalized regression neural network (GRNN), least square support vector regression (LSSVR), and support vector regression (SVR) were employed for long-term wind power output forecasting of wind farms. The empirical results underscore that the performance of the proposed forecasting model is better than other methods in terms of forecasting accuracy, which could efficiently provide reliable long-term predictions for long-term wind power output forecasting.

A Refined Zenith Tropospheric Delay Model Based on a Generalized Regression Neural Network and the GPT3 Model in Europe

A Refined Zenith Tropospheric Delay Model Based on a Generalized Regression Neural Network and the GPT3 Model in Europe

The effect of consanguineous marriage on reading disability based on deep neural networks

For knowledge acquisition and social engagement, reading comprehension is essential. However, 20% or so of younger students have trouble with it. In order to predict the effects of consanguineous marriage on reading handicap and customize adaptive learning experiences, the study proposes an Intelligent Adaptive Learning and Prediction Framework (IALPF). This framework is proposed as a transformative solution that smoothly combines cutting-edge AI approaches. IALPF provides precise predictions and individualized learning pathways by utilizing extensive cognitive profiling, data gathering, and hybrid neural network design. It includes early warning systems, flexible content distribution, and ongoing development based on active learning and feedback loops. The IALPF represents a significant change in education that has wide-ranging effects. We evaluated reading skills among 770 students in a study that included two experimental groups, a control group, and 22 pupils from first-cousin marriages and 21 children of unrelated parents, respectively. Tests were given for word identification and reading comprehension, among other things. The findings showed that children of first cousin parents had a higher chance of reading difficulties than those of parents from other families. The outstanding performance of IALPF, which outperformed conventional techniques like Back Propagation (BP) and General Regression Neural Network (GRNN), was further supported by empirical evaluation. This demonstrates IALPF's success in reinventing personalized learning and predictive analysis, strengthening its potential to improve education in a variety of scenarios. The seamless integration of cutting-edge AI methods into IALPF, which forecasts the effect of consanguineous marriage on reading handicap, is a significant innovation. To set it apart from conventional approaches, this special framework integrates cognitive profile, information gathering, and hybrid neural networks for accurate predictions. The empirical analysis demonstrates the revolutionary potential of IALPF by demonstrating its improved predictive accuracy when compared to Back Propagation (BP) and General Regression Neural Network (GRNN).

Prediction of comprehensive dynamic performance for probability screen based on AR model-box dimension

In order to evaluate the comprehensive dynamic performance of probability screen and select the appropriate working conditions, a dynamic model of probability screen vibration system is established. Then, the calculation method of the dynamic characteristic parameters, based on the time series Auto Regression (AR) model of vibration test, is used. The relationship among the comprehensive dynamic characteristics, the screening efficiency and the box dimension of probability screen vibration system is analyzed, and Least Square Support Vector Machine (LSSVM), Generalized Regression Neural Network (GRNN) and Back Propagation Neural Network (BPNN) are used to predict the screening efficiency with box dimension. The analysis result shows that the screening efficiency, the stability, the response rapidity and the comprehensive dynamic characteristic of the system are all related to the box dimension of time series. As for the complexity of probability screen vibration system, it affects the comprehensive dynamic performance, and ultimately touches the screening efficiency of the probability screen; The best working conditions for the system are selected by the curve between box dimension and the working condition parameter; Taking box dimension as the only input variable, the prediction accuracy of the screening efficiency is high by using LSSVM,GRNN and BPNN methods, the prediction results are stable and reliable, and the box dimension can be used as a single input variable to predict the screening efficiency, it has the advantages of fewer input parameters, high prediction efficiency, and high prediction accuracy, which has great potential for expanding application space and further research value.

Two-dimensional acoustic emission source localization on layered engineered wood by machine learning: a case study of laminated veneer lumber plate structure

Engineered wood or mass timber has gained increasing popularity in building construction, and layered engineered wood is a major category of mass timber design since it enables manufacturing structural members with a wide range of geometry. Thus, there is a potential rising demand for structural health monitoring on engineered wood-based structural members and buildings. This study investigates the feasibility of using an important and practical acoustic emission (AE) method for damage localization, specifically two-dimensional (2D) AE source localization, in a representative layered engineered wood sample, namely laminated veneer lumber (LVL) plate. While 2D AE source localization is generally straightforward in isotropic materials, the problem becomes challenging for anisotropic materials with angle-dependent wave velocities. It is even more complicated if heterogeneity involves, which turns out to be the case for layered engineered wood. In this study, we rely on the AE feature of difference in time of arrival (dTOA) and develop three methods to address the challenges of 2D AE source localization raised by anisotropy and heterogeneity in an LVL plate. The benchmark velocity profile method (VPM) is first implemented in an LVL plate. With knowledge of the angle-dependent velocity, the source location predictions by the VPM are generally erroneous even with predicted source location outside of the region of interest. Furthermore, the general regression neural network (GRNN) is developed using different combinations of dTOA components, resulting in improved prediction performance. Third, the Gaussian process regression (GPR) is developed by maximizing the marginal likelihood of the training dataset. Moreover, to lessen the computation burden, the lower bound of the logarithm likelihood of the whole models is derived and decomposed through Jensen’s inequality and Bayes’ theorem, providing the theoretical background for training models with different combinations of dTOAs individually.

Machine Learning-based Investigation of the Influencing Factors on the Hardness of Steel Materials

The hardness of steel is often regarded as a crucial indicator of its production and application. The influences of chemical composition and process parameters on the hardness of steel exhibit strong non-linearity, making it challenging to accurately predict hardness through traditional multivariate regression or orthogonal experiments. Although machine learning has achieved distinguished success in diverse applications, its use in studying Metal materials has emerged only recently. Inspired by Sunčana et al.’s work, we select the Jominy distance as an input variable for the chemical composition, and instead of his subtly finding the best artificial neural networks, we simply use Generalized Regression Neural Network (GRNN) and due to the heterogeneity of the data, a second-order clustering method is employed as a data pre-processing step. The predicted hardness values were obtained using leave-one-out cross-validation, and the optimal smoothing factor (spread) was selected based on the Root Mean Square Error (RMSE) criterion. The optimal prediction results showed that in Configuration I, the RMSEs of the two types of data were 62.41 HV and 20.51 HV, respectively, while in Configuration II, they were 66.38 HV and 29.51 HV. Results showed Configuration I was more successful than Configuration II. This research presents a novel approach for predicting the hardness of metal materials using GRNN which is designed to address the need for quick adaptation to changes in design methods and the increasing demand for high-quality manufactured products.

Evaluation Index System of Green Public Open Space Based on Internet of Things and Mental Health

ABSTRACT With the emergence of the IoT era, wireless sensor networks will be more and more widely used. In addition to collecting, transmitting and processing simple data such as humidity, temperature and density of the dome, they can also provide multimedia information services such as video and images. It enables more comprehensive and accurate environmental monitoring. Therefore, MSDs have a huge demand in military, daily, forestry, biomedicine and other fields. The intensive city model has obvious advantages in meeting people's diverse needs and comfortable life. Most obviously, it speeds up the rhythm of life for residents, thereby increasing efficiency and saving time. Starting from this aspect, this paper conducts a research on the evaluation index system of public built on the following areas of open space IoT and mental health. In this paper, the GRNN neural network model is constructed, the mean condition is calculated, the density function can be estimated, the network output, and the schematic diagram of the generalized regression neural network is improved. Using the established system, the index in 2018 is selected as the base year, and after transformation, the standardized values of the past years are formed, which are substituted into the cells to form different matrices. The value of each cell is counted to obtain the subsystem coordination degree, and the global coordination degree is obtained through calculation. The evaluation results of ecological civilization construction and development in 2018 and 2019, 2020 and 2021 were compared. The experimental data shows that compared with 2018, economic development will change from 1 to 2.000, social harmony will change from 1 to 2.480, ecological health will decrease to 0.850, environmental friendliness will decrease to 0.750, and comprehensive evaluation will decrease to 0.513. This shows that while the economy is developing this year, the construction of ecological civilization has been gradually carried out, and good results have been achieved. This reflects the effectiveness of the system. The subject of the evaluation index system of green public open space based on the Internet of Things and mental health has been well completed.

Cooperative coevolutionary surrogate ensemble-assisted differential evolution with efficient dual differential grouping for large-scale expensive optimization problems

This paper proposes a novel algorithm named surrogate ensemble assisted differential evolution with efficient dual differential grouping (SEADECC-EDDG) to deal with large-scale expensive optimization problems (LSEOPs) based on the CC framework. In the decomposition phase, our proposed EDDG inherits the framework of efficient recursive differential grouping (ERDG) and embeds the multiplicative interaction identification technique of Dual DG (DDG), which can detect the additive and multiplicative interactions simultaneously without extra fitness evaluation consumption. Inspired by RDG2 and RDG3, we design the adaptive determination threshold and further decompose relatively large-scale sub-components to alleviate the curse of dimensionality. In the optimization phase, the SEADE is adopted as the basic optimizer, where the global and the local surrogate model are constructed by generalized regression neural network (GRNN) with all historical samples and Gaussian process regression (GPR) with recent samples. Expected improvement (EI) infill sampling criterion cooperated with random search is employed to search elite solutions in the surrogate model. To evaluate the performance of our proposal, we implement comprehensive experiments on CEC2013 benchmark functions compared with state-of-the-art decomposition techniques. Experimental and statistical results show that our proposed EDDG is competitive with these advanced decomposition techniques, and the introduction of SEADE can accelerate the convergence of optimization significantly.

Prediction of NOx emission from two-stage combustion of NH3–H2 mixtures under various conditions using artificial neural networks

This study aims to predict NOx emission from the combustion of ammonia (NH3) and hydrogen (H2) mixtures using Artificial Neural Network (ANN) models. Chemical Reactor Network (CRN) models were utilized to calculate the NOx emission during the Rich-Quench-Lean (RQL) two-stage combustion of NH3–H2 mixtures under various conditions, such as fuel pressures, inlet temperatures, primary air humidification fractions, total equivalent ratios and primary equivalent ratios. The simulation results served as a data set for training and validation of three different ANN models: Backpropagation (BP), Radial Basis Function (RBF), and Generalized Regression Neural Network (GRNN). The results show that all three ANN models can effectively replace the CRN model in accurately predicting NOx concentrations. In particular, the BP model, optimized with 37 hidden neurons, showcased superior performance, achieving a correlation coefficient (R) value of 0.99826 with the simulated results. It had the lowest Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE) values of 61.3 and 96.1, respectively. In addition, it achieved the highest coefficient of determination (R2) and Model Efficiency (ME) values of 0.9950 and 0.9908 respectively, surpassing the RBF and GRNN models. These results suggest that the BP model has significant potential as an alternative to the CRN model for predicting NOx emissions from two-stage combustion of NH3–H2 mixtures, demonstrating both accuracy and efficiency.

A framework for detection of cyber attacks by the classification of intrusion detection datasets

Recognition of the consequence for advanced tools and techniques to secure the network infrastructure from the security risks has prompted the advancement of many machine learning-based intrusion detection strategies. However, it is a big challenge for the researchers to make improvements in an Intrusion Detection System with desired advantages and constraints. This paper has developed a proficient soft computing framework using Grey Wolf Optimization and Entropy-Based Graph (GWO-EBG) to classify intrusion detection datasets to reduce the false rate. In the proposed scheme, initially, the input data is preprocessed by the data transformation and normalization procedure. After the preprocessing, optimal features have been chosen for the dimension reduction from the preprocessed data using the grey wolf optimization (GWO) algorithm. Then, the Entropy value has estimated from the idyllically selected features. Lastly, an Entropy-Based Graph (EBG) has been constructed to classify data into intrusion or normal data. The experimental results demonstrate that the developed method outperforms other existing methods in various performance measures. The detection rate of the developed GWO-EBG is found to be 94.6%, which is higher than 91.24 % of EBG, 75.60 % K-Nearest Neighbors (KNN), 73.36 % of Support Vector Machine (SVM), and 74.88 % of Generalized Regression Neural Network (GRNN) on 5000 connection vectors data obtained from KDD CUP’99 testing dataset. The false-positive rate of developed strategy (GWO-EBG) is 0.35 %%, which is lower than 2.18 % of EBG, 7.32 % KNN, 8.15 % of SVM, and 8.13 % of GRNN with 5000 testing datasets.

A secure energy trading in a smart community by integrating Blockchain and machine learning approach

ABSTRACT In today’s smart communities, small-scale energy systems are essential for sustainable development and efficient resource management. However, ensuring the confidentiality, safety, and accurate prediction of energy consumption patterns in energy trading is a major challenge. To address these issues, an innovative solution that synergistically combines two cutting-edge technologies: blockchain and machine learning is proposed. This paper unveils a novel approach that harmoniously merges blockchain with the Recalling-Enhanced Recurrent Neural Network (RERNN) to revolutionize energy trading systems called ‘Blockchain-Enhanced Energy Trading with Recalling-Enhanced Recurrent Neural Network (BET-RERNN).’ Data from IoT-enabled smart devices is securely stored in blockchain blocks, ensuring data integrity and immutability. Blockchain’s decentralized nature creates a trust-less environment for energy trading, protecting the privacy and anonymity of participants while maintaining transparency. At the heart of our system lies the advanced machine-learning capabilities of the RERNN model. By processing the data stored on the blockchain, RERNN accurately predicts optimal power generation for small-scale energy systems, enabling smart communities to make informed decisions and optimize their energy consumption. The BET-RERNN scheme provides a plethora of strengths. First, participants can securely engage in energy trading without compromising sensitive information, fostering a more resilient and efficient market. Second, blockchain technology ensures that all energy-related data is protected from tampering and unauthorized access, ensuring system reliability and trust. An in-depth comparison of RERNN’s performance to traditional General Regression Neural Network (GRNN) and Gradient Boost Decision Tree (GBDT) methods is conducted. To verify the strategy’s effectiveness, MATLAB simulations are employed, demonstrating its real-world applicability and scalability. By combining blockchain and machine learning, a secure and privacy-preserving smart community is established, promoting sustainable energy practices for a greener future.

An adaptive sliding mode controller for electro‐hydraulic servo systems combining offline training and online estimation

AbstractIn order to improve the tracking accuracy of electro‐hydraulic servo systems under nonlinear disturbance, an adaptive sliding mode controller (SMC) based on generalized regression neural network (GRNN) is proposed. The nonlinear factors and external disturbances of systems are considered in the controller, and an improved GRNN is used. In addition, the neural network achieves nonlinear approximation of the unknown part by online learning, determines the parameters of the SMC in real time by training the model offline, and reduces the impact of online estimation errors on the system to improve control accuracy. Finally, the effectiveness of the control method is verified by simulation.

Physical fingerprint transformation of herbal medicines powders using near-infrared spectroscopy

To achieve the rapid determination of physical parameters of herbal medicine. A method based on near-infrared (NIR) spectroscopy was proposed. The potential of direct standardization, partial least squares regression and generalized regression neural network (GRNN) for physical fingerprint transformation of Paeoniae Radix Alba, Scutellariae Radix, Sinomenii Caulis, and Pueraria Lobatae Radix, were investigated. The results revealed that the predictive capacity of GRNN models was the best. Except for a few parameters in the validation samples of Pueraria Lobatae Radix and Sinomenii Caulis, the mean absolute deviations of all other physical parameters were less than 0.5. The similarity between the actual and predicted physical fingerprints of all validation samples and test samples was high when using the GRNN models (cosine coefficient > 0.99, Mahalanobis distance < 1.30). Additionally, the simplified GRNN models based on the 40 selected variables of hygroscopicity and angle of repose still showed the ideal predictive capacity.

Optimised weighted mean temperature model based on generalised regression neural network

Optimised weighted mean temperature model based on generalised regression neural network

Novel General Regression Neural Networks for Improving Control Accuracy of Nonlinear MIMO Discrete-Time Systems.

In this article, a novel version of the general regression neural network (Imp_GRNN) is developed to control a class of multiinput and multioutput (MIMO) nonlinear discrete-time (DT) systems. The improvements retain the features of the original GRNN along with a significant improvement of the control accuracy. The enhancements include developing a method to set the input-hidden weights of GRNN using the inputs recursive statistical means, introducing a new output layer and adaptable forward weighted connections from the inputs to the new layer, and suggesting an interval-type smoothing parameter to eradicate the need for selecting the parameter beforehand or adapting it online. Also, controller stability is studied using Lyapunov's method for DT systems. The controller performance is tested with different simulation examples and compared with the original GRNN to verify its superiority over it. Also, Imp_GRNN performance is compared with an adaptive radial basis function network controller, an adaptive feedforward neural-network (NN) controller, and a proportional-integral-derivative (PID) controller, where it demonstrated higher accuracy in comparison with them. In comparison with the formerly proposed control methods for MIMO DT systems, our controller is capable of producing high control accuracy while it is model free, does not require complex mathematics, has low computational complexity, and can be utilized for a wide range of DT dynamic systems. Also, it is one of the few methods that aims to improve the control system accuracy by improving the NN structure.

Compliance Prediction for Structural Topology Optimization on the Basis of Moment Invariants and a Generalized Regression Neural Network.

Topology optimization techniques are essential for manufacturing industries, such as designing fiber-reinforced polymer composites (FRPCs) and structures with outstanding strength-to-weight ratios and light weights. In the SIMP approach, artificial intelligence algorithms are commonly utilized to enhance traditional FEM-based compliance minimization procedures. Based on an effective generalized regression neural network (GRNN), a new deep learning algorithm of compliance prediction for structural topology optimization is proposed. The algorithm learns the structural information using a fourth-order moment invariant analysis of the structural topology obtained from FEA at different iterations of classical topology optimization. A cantilever and a simply supported beam problem are used as ground-truth datasets, and the moment invariants are used as independent variables for input features. By comparing it with the well-known convolutional neural network (CNN) and deep neural network (DNN) models, the proposed GRNN model achieves a high prediction accuracy (R2 > 0.97) and drastically shortens the training and prediction cost. Furthermore, the GRNN algorithm exhibits excellent generalization ability on the prediction performance of the optimized topology with rotations and varied material volume fractions. This algorithm is promising for the replacement of the FEA calculation in the SIMP method, and can be applied to real-time optimization for advanced FRPC structure design.

An integrated modelling framework for multiple pollution source identification in surface water

Pollution source identification is vital in water safety management. An integrated simulation-optimization modelling framework comprising a process-based hydrodynamic water quality model, artificial neural network surrogate model and particle swarm optimization (PSO) was proposed to achieve rapid, accurate and reliable pollution source identification. In this study, the hydrodynamics and water quality processes in a straight lab-based flume were simulated to test pollution source identification under steady flow conditions. Additionally, the pollution source identification in the unsteady flow conditions was examined using a real-life estuary, specifically the Yangtze River estuary. First, we developed two process-based models to simulate hydrodynamics and water quality in the flume and estuary. Then, the data generated from the process-based models were used to develop surrogate models. Three typical artificial neural networks (ANNs) algorithms: backpropagation (BP), radial basis function (RBF) and general regression neural networks (GRNN) were selected to develop surrogates for process-based models (PBMs), and they were coupled with PSO algorithm to achieve the hybrid modelling framework for pollution source identification. Our results showed that hybrid PBM-ANNs-PSO models could be applied to identify the pollution source and quantify release intensity in spatial distribution when the discharge type was assumed as the point source with a continuous release. Multiple-performance criteria metrics, in terms of the coefficient of determination, root-mean-square error, mean absolute error, evaluated the model performance as “Excellent prediction”. The BP-PSO models consistently appear to be the top-performing source identification model within the developed models, with most cases of relative error (RE) values lower than 5%. The new insights from the hybrid modelling framework would provide useful information for the local government agency to make reasonable decisions regarding pollution source identification issues.