Non-crossing Quantile Regression Neural Network as a Calibration Tool for Ensemble Weather Forecasts

Despite the maturity of ensemble numerical weather prediction(NWP),the resulting forecasts are still,more often than not,under-dispersed.As such,forecast calibration tools have become popular.Among those tools,quantile regression(QR)is highly competitive in terms of both flexibility and predictive performance.Nevertheless,a long-standing problem of QR is quantile crossing,which greatly limits the interpretability of QR-calibrated forecasts.On this point,this study proposes a non-crossing quantile regression neural network(NCQRNN),for calibrating ensemble NWP forecasts into a set of reliable quantile forecasts without crossing.The overarching design principle of NCQRNN is to add on top of the conventional QRNN structure another hidden layer,which imposes a non-decreasing mapping between the combined output from nodes of the last hidden layer to the nodes of the output layer,through a triangular weight matrix with positive entries.The empirical part of the work considers a solar irradiance case study,in which four years of ensemble irradiance forecasts at seven locations,issued by the European Centre for Medium-Range Weather Forecasts,are calibrated via NCQRNN,as well as via an eclectic mix of benchmarking models,ranging from the naïve climatology to the state-of-the-art deep-learning and other non-crossing models.Formal and stringent forecast verification suggests that the forecasts post-processed via NCQRNN attain the maximum sharpness subject to calibration,amongst all competitors.Furthermore,the proposed conception to resolve quantile crossing is remarkably simple yet general,and thus has broad applicability as it can be integrated with many shallow-and deep-learning-based neural networks.

Nonparametric Statistical Feature Scaling Based Quadratic Regressive Convolution Deep Neural Network for Software Fault Prediction

The development of defect prediction plays a significant role in improving software quality. Such predictions are used to identify defective modules before the testing and to minimize the time and cost. The software with defects negatively impacts operational costs and finally affects customer satisfaction. Numerous approaches exist to predict software defects. However, the timely and accurate software bugs are the major challenging issues. To improve the timely and accurate software defect prediction, a novel technique called Nonparametric Statistical feature scaled QuAdratic regressive convolution Deep nEural Network (SQADEN) is introduced. The proposed SQADEN technique mainly includes two major processes namely metric or feature selection and classification. First, the SQADEN uses the nonparametric statistical Torgerson–Gower scaling technique for identifying the relevant software metrics by measuring the similarity using the dice coefficient. The feature selection process is used to minimize the time complexity of software fault prediction. With the selected metrics, software fault perdition with the help of the Quadratic Censored regressive convolution deep neural network-based classification. The deep learning classifier analyzes the training and testing samples using the contingency correlation coefficient. The softstep activation function is used to provide the final fault prediction results. To minimize the error, the Nelder–Mead method is applied to solve non-linear least-squares problems. Finally, accurate classification results with a minimum error are obtained at the output layer. Experimental evaluation is carried out with different quantitative metrics such as accuracy, precision, recall, F-measure, and time complexity. The analyzed results demonstrate the superior performance of our proposed SQADEN technique with maximum accuracy, sensitivity and specificity by 3%, 3%, 2% and 3% and minimum time and space by 13% and 15% when compared with the two state-of-the-art methods.

An Approach to Carbon Emissions Prediction Using Generalized Regression Neural Network Improved by Genetic Algorithm

The study on scientific analysis and prediction of China’s future carbon emissions is conducive to balancing the relationship between economic development and carbon emissions in the new era,and actively responding to climate change policy.Through the analysis of the application of the generalized regression neural network(GRNN)in prediction,this paper improved the prediction method of GRNN.Genetic algorithm(GA)was adopted to search the optimal smooth factor as the only factor of GRNN,which was then used for prediction in GRNN.During the prediction of carbon dioxide emissions using the improved method,the increments of data were taken into account.The target values were obtained after the calculation of the predicted results.Finally,compared with the results of GRNN,the improved method realized higher prediction accuracy.It thus offers a new way of predicting total carbon dioxide emissions,and the prediction results can provide macroscopic guidance and decision-making reference for China’s environmental protection and trading of carbon emissions.

Performance Prediction of Switched Reluctance Motor using Improved Generalized Regression Neural Networks for Design Optimization

Since practical mathematical model for the design optimization of switched reluctance motor(SRM)is difficult to derive because of the strong nonlinearity,precise prediction of electromagnetic characteristics is of great importance during the optimization procedure.In this paper,an improved generalized regression neural network(GRNN)optimized by fruit fly optimization algorithm(FOA)is proposed for the modeling of SRM that represent the relationship of torque ripple and efficiency with the optimization variables,stator pole arc,rotor pole arc and rotor yoke height.Finite element parametric analysis technology is used to obtain the sample data for GRNN training and verification.Comprehensive comparisons and analysis among back propagation neural network(BPNN),radial basis function neural network(RBFNN),extreme learning machine(ELM)and GRNN is made to test the effectiveness and superiority of FOA-GRNN.

A hybrid model for predicting spatial distribution of soil organic matter in a bamboo forest based on general regression neural network and interative algorithm

A general regression neural network model,combined with an interative algorithm(GRNNI)using sparsely distributed samples and auxiliary environmental variables was proposed to predict both spatial distribution and variability of soil organic matter(SOM)in a bamboo forest.The auxiliary environmental variables were:elevation,slope,mean annual temperature,mean annual precipitation,and normalized difference vegetation index.The prediction accuracy of this model was assessed via three accuracy indices,mean error(ME),mean absolute error(MAE),and root mean squared error(RMSE)for validation in sampling sites.Both the prediction accuracy and reliability of this model were compared to those of regression kriging(RK)and ordinary kriging(OK).The results show that the prediction accuracy of the GRNNI model was higher than that of both RK and OK.The three accuracy indices(ME,MAE,and RMSE)of the GRNNI model were lower than those of RK and OK.Relative improvements of RMSE of the GRNNI model compared with RK and OK were 13.6%and 17.5%,respectively.In addition,a more realistic spatial pattern of SOM was produced by the model because the GRNNI model was more suitable than multiple linear regression to capture the nonlinear relationship between SOM and the auxiliary environmental variables.Therefore,the GRNNI model can improve both prediction accuracy and reliability for determining spatial distribution and variability of SOM.

Modelling the impact of climate change on rangeland forage production using a generalized regression neural network:a case study in Isfahan Province,Central Iran

Monitoring of rangeland forage production at specified spatial and temporal scales is necessary for grazing management and also for implementation of rehabilitation projects in rangelands. This study focused on the capability of a generalized regression neural network（GRNN） model combined with GIS techniques to explore the impact of climate change on rangeland forage production. Specifically, a dataset of 115 monitored records of forage production were collected from 16 rangeland sites during the period 1998–2007 in Isfahan Province, Central Iran. Neural network models were designed using the monitored forage production values and available environmental data（including climate and topography data）, and the performance of each network model was assessed using the mean estimation error（MEE）, model efficiency factor（MEF）, and correlation coefficient（r）. The best neural network model was then selected and further applied to predict the forage production of rangelands in the future（in 2030 and 2080） under A1 B climate change scenario using Hadley Centre coupled model. The present and future forage production maps were also produced. Rangeland forage production exhibited strong correlations with environmental factors, such as slope, elevation, aspect and annual temperature. The present forage production in the study area varied from 25.6 to 574.1 kg/hm^2. Under climate change scenario, the annual temperature was predicted to increase and the annual precipitation was predicted to decrease. The prediction maps of forage production in the future indicated that the area with low level of forage production（0–100 kg/hm^2） will increase while the areas with moderate, moderately high and high levels of forage production（≥100 kg/hm^2） will decrease both in 2030 and in 2080, which may be attributable to the increasing annual temperature and decreasing annual precipitation. It was predicted that forage production of rangelands will decrease in the next couple of decades, especially in the western and southern parts of Isfahan Province. These changes are more pronounced in elevations between 2200 and 2900 m. Therefore, rangeland managers have to cope with these changes by holistic management approaches through mitigation and human adaptations.

Regression Method for Rail Fastener Tightness Based on Center-Line Projection Distance Feature and Neural Network

In the railway system,fasteners have the functions of damping,maintaining the track distance,and adjusting the track level.Therefore,routine maintenance and inspection of fasteners are important to ensure the safe operation of track lines.Currently,assessment methods for fastener tightness include manual observation,acoustic wave detection,and image detection.There are limitations such as low accuracy and efficiency,easy interference and misjudgment,and a lack of accurate,stable,and fast detection methods.Aiming at the small deformation characteristics and large elastic change of fasteners from full loosening to full tightening,this study proposes high-precision surface-structured light technology for fastener detection and fastener deformation feature extraction based on the center-line projection distance and a fastener tightness regression method based on neural networks.First,the method uses a 3D camera to obtain a fastener point cloud and then segments the elastic rod area based on the iterative closest point algorithm registration.Principal component analysis is used to calculate the normal vector of the segmented elastic rod surface and extract the point on the centerline of the elastic rod.The point is projected onto the upper surface of the bolt to calculate the projection distance.Subsequently,the mapping relationship between the projection distance sequence and fastener tightness is established,and the influence of each parameter on the fastener tightness prediction is analyzed.Finally,by setting up a fastener detection scene in the track experimental base,collecting data,and completing the algorithm verification,the results showed that the deviation between the fastener tightness regression value obtained after the algorithm processing and the actual measured value RMSE was 0.2196 mm,which significantly improved the effect compared with other tightness detection methods,and realized an effective fastener tightness regression.

Term Structure of Interest Rates Based on Artificial Neural Network

In light of the nonlinear approaching capability of artificial neural networks （ ANN）, the term structure of interest rates is predicted using The generalized regression neural network （GRNN） and back propagation （BP） neural networks models. The prediction performance is measured with US interest rate data. Then, RBF and BP models are compared with Vasicek＇s model and Cox-Ingersoll-Ross （CIR） model. The comparison reveals that neural network models outperform Vasicek＇s model and CIR model, which are more precise and closer to the real market situation.

Underwater Positioning Based on an Artificial Lateral Line and a Generalized Regression Neural Network

Taking advantage of the lateral line organ, fish can navigate, feed, and avoid predators and obstacles by sensing surrounding flow fields. The lateral line organ provides an important reference for the development of new underwater detection technology. Inspired by the lateral line organ, in this paper, for the sake of localizing the target dipole source in three-dimensional underwater space, an artificial lateral line consisting of nine underwater pressure sensors forming a cross-shaped sensor array is applied. Combined with the method of gener- alized regression neural network, which is suitable for solving nonlinear pattern recognition problems, a corresponding experimental platform has been built to sample data for training the neural network from a 12 cm by 12 cm by 24 cm cuboid space. The experimental results indicate that the cross-shaped artificial lateral line can localize the target dipole source two body-lengths away. The well- performing perceptual distance is below 13 cm away from the sensing array. Moreover, decreasing the data sampling interval and in- creasing the number of sensors utilized can help improve the positioning accuracy.

Short-term Load Forecasting of Regional Distribution Network Based on Generalized Regression Neural Network Optimized by Grey Wolf Optimization Algorithm

Short-term load forecasting of regional distribution network is the key to the economic operation of smart distribution systems,which not only requires high accuracy and fast calculation speed,but also has a diversity of influential factors and strong randomness.This paper proposes a short-term load forecasting model for regional distribution network combining the maximum information coefficient,factor analysis,gray wolf optimization,and generalized regression neural network(MIC-FA-GWO-GRNN).To screen and decrease the dimension of the multiple-input features of the short-term load forecasting model,MIC is first used to quantify the non-linear correlation between the load and input features,and to eliminate the ineffective features,and then FA is used to reduce the dimension of the screened input features on the premise of preserving the main information of input features.After that the high-precision short-term丨oad forecasting based on GWO-GRNN model is realized.GRNN is used to regressively analyze the input features after screening and dimension reduction,and the parameter of GRNN is optimized by using the GWO,which has strong global searching ability and fast convergence.Finally a case study of a regional distribution network in Tianjin,China verifies the accuracy and applicability of the proposed forecasting model.

Twin model-based fault detection and tolerance approach for in-core self-powered neutron detectors

The in-core self-powered neutron detector(SPND)acts as a key measuring device for the monitoring of parameters and evaluation of the operating conditions of nuclear reactors.Prompt detection and tolerance of faulty SPNDs are indispensable for reliable reactor management.To completely extract the correlated state information of SPNDs,we constructed a twin model based on a generalized regression neural network(GRNN)that represents the common relationships among overall signals.Faulty SPNDs were determined because of the functional concordance of the twin model and real monitoring sys-tems,which calculated the error probability distribution between the model outputs and real values.Fault detection follows a tolerance phase to reinforce the stability of the twin model in the case of massive failures.A weighted K-nearest neighbor model was employed to reasonably reconstruct the values of the faulty signals and guarantee data purity.The experimental evaluation of the proposed method showed promising results,with excellent output consistency and high detection accuracy for both single-and multiple-point faulty SPNDs.For unexpected excessive failures,the proposed tolerance approach can efficiently repair fault behaviors and enhance the prediction performance of the twin model.

Short-term traffic forecasting based on principal component analysis and a generalized regression neural network for satellite networks

With the rapid growth of satellite traffic, the ability to forecast traffic loads becomes vital for improving data transmission efficiency and resource management in satellite networks. To precisely forecast the short-term traffic loads in satellite networks, a forecasting algorithm based on principal component analysis and a generalized regression neural network （PCA-GRNN） is proposed. The PCA-GRNN algorithm exploits the hidden regularity of satellite networks and fully considers both the temporal and spatial correlations of satellite traffic. Specifically, it selects optimal time series of spatio-temporally correlated historical traffic from satellites as forecasting inputs and applies principal component analysis to reduce the input dimensions while preserving the main features of the data. Then, a generalized regression neural network is utilized to perform the final short-term load forecasting based on the obtained principal components. The PCA-GRNN algorithm is evaluated based on real-world traffic traces, and the results show that the PCA-GRNN method achieves a higher forecasting accuracy, has a shorter training time and is more robust than other state-of-the-art algorithms, even for incomplete traffic datasets. Therefore, the PCA- GRNN algorithm can be regarded as a preferred solution for use in real-time traffic forecasting for realistic satellite networks.

A Fast Charging–Cooling Coupled Scheduling Method for a Liquid Cooling-Based Thermal Management System for Lithium-Ion Batteries

Efficient fast-charging technology is necessary for the extension of the driving range of electric vehicles.However,lithium-ion cells generate immense heat at high-current charging rates.In order to address this problem,an efficient fast charging–cooling scheduling method is urgently needed.In this study,a liquid cooling-based thermal management system equipped with mini-channels was designed for the fastcharging process of a lithium-ion battery module.A neural network-based regression model was proposed based on 81 sets of experimental data,which consisted of three sub-models and considered three outputs:maximum temperature,temperature standard deviation,and energy consumption.Each sub-model had a desirable testing accuracy(99.353%,97.332%,and 98.381%)after training.The regression model was employed to predict all three outputs among a full dataset,which combined different charging current rates(0.5C,1C,1.5C,2C,and 2.5C(1C=5 A))at three different charging stages,and a range of coolant rates(0.0006,0.0012,and 0.0018 kg·s^(-1)).An optimal charging–cooling schedule was selected from the predicted dataset and was validated by the experiments.The results indicated that the battery module’s state of charge value increased by 0.5 after 15 min,with an energy consumption lower than 0.02 J.The maximum temperature and temperature standard deviation could be controlled within 33.35 and 0.8C,respectively.The approach described herein can be used by the electric vehicles industry in real fast-charging conditions.Moreover,optimal fast charging-cooling schedule can be predicted based on the experimental data obtained,that in turn,can significantly improve the efficiency of the charging process design as well as control energy consumption during cooling.

A Neural Regression Model for Predicting Thermal Conductivity of CNT Nanofluids with Multiple Base Fluids

High thermal conductivity of carbon nanotube nanofluids(k_(nf))has received great attention.However,the current researches are limited by experimental conditions and lack a comprehensive understanding of k_(nf) variation law.In view of proposition of data-driven methods in recent years,using experimental data to drive prediction is an effective way to obtain k_(nf),which could clarify variation law of k_(nf) and thus greatly save experimental and time costs.This work proposed a neural regression model for predicting k_(nf).It took into account four influencing factors,including carbon nanotube diameter,volume fraction,temperature and base fluid thermal conductivity(k_(f)).Where,four conventional fluids with k_(f),including R113,water,ethylene glycol and ethylene glycol-water mixed liquid were considered as base fluid considers.By training this model,it can predict k_(nf) with different factors.Also,change law of four influencing factors considered on the k_(nf) enhancement has discussed and the correlation between different influencing factors and k_(nf) enhancement is presented.Finally,compared with nine common machine learning methods,the proposed neural regression model shown the highest accuracy among these.

Quantifying social vulnerability for flood disasters of insurance company

Social vulnerability assessments are largely ignored when compared with biophysical vulnerability assessments. This is mainly due to the fact that there are more difficulties in quantifying them. Aiming at several pitfalls still existing in the Hoovering approach which is widely accepted, a suitable modified model is provided. In this modified model, the integrated vulnerability is made an analogy to the elasticity coefficient of a spring, and an objective evaluation criterion is established. With the evaluation criterion, the assessment indicators of social vulnerability are filtered and their weight assignments are accomplished. There is an application in the city of Changsha where floods occur often. With the relative data from the PICC Hunan Province Branch, a generalized regression neural network model is established in Matlab 7.0 and used to evaluate a company's flood social vulnerability index (SoVI). The results show that the average flood social vulnerability in Yuhua district is the highest, while Yuelu district is the lowest. It is good for disaster risk management and decision-making of insurance companies.

TYRE DYNAMICS MODELLING OF VEHICLE BASED ON SUPPORT VECTOR MACHINES

Various methods of tyre modelling are implemented from pure theoretical to empirical or semi-empirical models based on experimental results. A new way of representing tyre data obtained from measurements is presented via support vector machines （SVMs）. The feasibility of applying SVMs to steady-state tyre modelling is investigated by comparison with three-layer backpropagation （BP） neural network at pure slip and combined slip. The results indicate SVMs outperform the BP neural network in modelling the tyre characteristics with better generalization performance. The SVMsqyre is implemented in 8-DOF vehicle model for vehicle dynamics simulation by means of the PAC 2002 Magic Formula as reference. The SVMs-tyre can be a competitive and accurate method to model a tyre for vehicle dynamics simuLation.

Evaluating soil nutrients of Dacrydium pectinatum in China using machine learning techniques

Background: The accurate estimation of soil nutrient content is particularly important in view of its impact on plant growth and forest regeneration. In order to investigate soil nutrient content and quality for the natural regeneration of Dacrydium pectinatum communities in China, designing advanced and accurate estimation methods is necessary.Methods: This study uses machine learning techniques created a series of comprehensive and novel models from which to evaluate soil nutrient content. Soil nutrient evaluation methods were built by using six support vector machines and four artificial neural networks.Results: The generalized regression neural network model was the best artificial neural network evaluation model with the smallest root mean square error(5.1), mean error(-0.85), and mean square prediction error(29). The accuracy rate of the combined k-nearest neighbors(k-NN) local support vector machines model(i.e. k-nearest neighbors-support vector machine(KNNSVM)) for soil nutrient evaluation was high, comparing to the other five partial support vector machines models investigated. The area under curve value of generalized regression neural network(0.6572) was the highest, and the cross-validation result showed that the generalized regression neural network reached 92.5%.Conclusions: Both the KNNSVM and generalized regression neural network models can be effectively used to evaluate soil nutrient content and quality grades in conjunction with appropriate model variables. Developing a new feasible evaluation method to assess soil nutrient quality for Dacrydium pectinatum, results from this study can be used as a reference for the adaptive management of rare and endangered tree species. This study, however, found some uncertainties in data acquisition and model simulations, which will be investigated in upcoming studies.

Application and Simulation of GRNN for the Shotcrete Robot

The generalized regression neural network-one kind of RBF neural network, is chosen to construct the inverse-kinematics model for the shotcrete robot which has redundant degree-of-freedom. The inverse-kinematics model of the object is trained by the general learning method. In constructing model process, different partition methods is tried to divide the joint space and different diffusion coefficient value to train the neural network. The influence of the spread coefficient to the approach ability is also studied. The simulation method is adopted to test the performance of the neural network. The simulation result turns out to be satisfactory.

A Hybrid Model for Short-term PV Output Forecasting Based on PCA-GWO-GRNN

High-precision day-ahead short-term photovoltaic(PV)output forecasting is essential in PV integration to the smart distribution networks and multi-energy system,and provides the foundation for the security,stability,and economic operation of PV systems.This paper proposes a hybrid model based on principal component analysis,grey wolf optimization and generalized regression neural network(PCA-GWO-GRNN)for day-ahead short-term PV output forecasting,considering the features of multiple influencing factors and strong uncertainty.This paper first uses the PCA to reduce the dimension of meteorological features.Then,the high-precision day-ahead short-term PV output forecasting based on GWO-GRNN model is realized.GRNN is used to regressively analyze the input features after dimension reduction,and the parameter of GRNN is optimized by using GWO,which has strong global searching ability and fast convergence.The proposed PCA-GWO-GRNN model effectively achieves a high precision in day-ahead shortterm PV output forecasting,which is demonstrated in a case study on a real PV plant in Jiangsu province,China.The results have validated the accuracy and applicability of the proposed model in real scenarios.

Identification of Graves’ophthalmology by laser-induced breakdown spectroscopy combined with machine learning method

Diagnosis of the Graves’ophthalmology remains a significant challenge.We identified between Graves’ophthalmology tissues and healthy controls by using laser-induced breakdown spectroscopy(LIBS)combined with machine learning method.In this work,the paraffin-embedded samples of the Graves’ophthalmology were prepared for LIBS spectra acquisition.The metallic elements(Na,K,Al,Ca),non-metallic element(O)and molecular bands((C-N),(C-O))were selected for diagnosing Graves’ophthalmology.The selected spectral lines were inputted into the supervised classification methods including linear discriminant analysis(LDA),support vector machine(SVM),k-nearest neighbor(ANN),and generalized regression neural network(GRNN),respectively.The results showed that the predicted accuracy rates of LDA,SVM,ANN,GRNN were 76.33%,96.28%,96.56%,and 96.33%,respectively.The sensitivity of four models were 75.89%,93.78%,96.78%,and 96.67%,respectively.The specificity of four models were 76.78%,98.78%,96.33%,and 96.00%,respectively.This demonstrated that LIBS assisted with a nonlinear model can be used to identify Graves’ophthalmopathy with a higher rate of accuracy.The ANN had the best performance by comparing the three nonlinear models.Therefore,LIBS combined with machine learning method can be an effective way to discriminate Graves’ophthalmology.