Weighted probabilistic neural network

Digital image recognition of plant diseases could reduce the dependence of agricultural production on the professional and technical personnel in plant protection field and is conducive to the development of plant protection informatization. In order to find out a method to realize image recognition of plant diseases, four kinds of neural networks including backpropagation (BP) networks, radial basis function (RBF) neural networks, generalized regression networks (GRNNs) and probabilistic neural networks (PNNs) were used to distinguish wheat stripe rust from wheat leaf rust and to distinguish grape downy mildew from grape powdery mildew based on color features, shape features and texture features extracted from the disease images. The results showed that identification and diagnosis of the plant diseases could be effectively achieved using BP networks, RBF neural networks, GRNNs and PNNs based on image processing. For the two kinds of wheat diseases, the best prediction accuracy was 100% with the fitting accuracy equal to 100% while BP networks, GRNNs or PNNs were used, and the best prediction accuracy was 97.50% with the fitting accuracy equal to 100% while RBF neural networks were used. For the two kinds of grape diseases, the best prediction accuracy was 100% with the fitting accuracy equal to 100% while BP networks, GRNNs or PNNs were used, and the best prediction accuracy was 94.29% with the fitting accuracy equal to 100% while RBF neural networks were used.

The automatic pattern recognition of single and multiple power quality (PQ) disturbances is a very important task for the detection and monitoring of multiple faults and events in electrical power system. This paper presents an automatic classification algorithm for PQ disturbances based on wavelet norm entropy features and probabilistic neural network (PNN) as an effective pattern classifier. The proposed method employs the discrete wavelet transform based on multi-resolution analysis technique to extract the most important and constructive features of PQ disturbances at various resolution levels. The distinctive norm entropy features of the PQ disturbances have been extracted and were employed as inputs to the PNN. Various other architectures of artificial neural network such as multilayer perceptron and radial basis function neural network have also been employed for comparison. The PNN is found the most suitable pattern recognition tool for the classification of the PQ disturbances. Various PQ disturbances used for analysis were generated by simulating a typical 11-kV distribution system. The simulation results obtained show that the proposed approach can detect and classify the PQ disturbances effectively and can be implemented successfully in real-time electrical power distribution networks.

Our work provides an effective feature based method for analyzing both steady state and short duration non-stationary power signal disturbances using a Local Linear Radial Basis Function Neural Network (LLRBFNN). In contrast to the normalized probabilistic neural network (PNN), the proposed LLRBFNN is an excellent approximation network, which performs the classification task with minimal amount of computational power than probabilistic neural network (PNN). The difference of the LLRBFNN with conventional Radial Basis Function Neural Network (RBFNN) is that a local linear model replaces the connection of weights between the hidden layer and output layer of conventional RBFNN. Both normalized time domain and frequency domain features are used for the training purpose. It is noticed that spectral entropy is an effective frequency domain feature for non-stationary power signal classification. Moreover the local linear model provides a robust model for network learning, which is not prone to local linear points. This is supported by the observation that both the LLRBFNN model and the global search optimization techniques like Genetic algorithm provide similar results.

Dissolved oxygen (DO) as one of the most fundamental parameters of water quality plays a vital role in aquatic life. This study was conducted to predict DO, biological oxygen demand (BOD), and chemical oxygen demand (COD) in an intensive rainbow trout rearing system with different biomass (B). The multilayer perceptron (MLP) and the radial basis function (RBF) neural networks were employed for evaluating the impacts of food parameters (crude protein (CP), consumed feed (CF)), fish parameters (different values of B, and weight gain (WG)), and water quality parameters including temperature (T) and flow rate (Q) on variation of DO, BOD, and COD concentrations. This study's results showed that although both MLP and RBF neural networks are capable to estimate DO, BOD, and COD concentrations, RBF neural network showed better performance compared to MLP neural network. The results of sensitivity analysis indicated that the parameter CF has the highest effect on DO concentration estimation. Independent variables CF, CP, WG, and B showed the highest to the lowest rank of impacts on BOD estimation, respectively. The results also illustrated a decreasing trend of the effects on the estimation error of COD changes simulation by all independent variables, including B, T, WG, CF, CP, and Q, respectively. RBF neural network based on better stability and generalization ability with average root mean square error (RMSE) and mean absolute percentage error (MAPE) values of less than 0.12 and 3% was superior to MLP in DO, BOD, and COD concentration prediction. Moreover, CF was identified as the most effective factor in estima12tion process. Based on the present study results, there are direct relationships between DO, BOD, and COD concentrations and water quality parameters, fish parameters, and food parameters. Food parameters relative to fish and water quality parameters imposed the greatest effects. Improvement in feeding process such as application of intelligence feeding methods and change in fish diet and feeding time can considerably reduce losses in production system. Graphical abstract.

The prediction of meteorological time series plays very important role in several fields. In this paper, an application of least squares support vector machine (LS-SVM) for short-term prediction of meteorological time series (e.g. solar irradiation, air temperature, relative humidity, wind speed, wind direction and pressure) is presented. In order to check the generalization capability of the LS-SVM approach, a K-fold cross-validation and Kolmogorov–Smirnov test have been carried out. A comparison between LS-SVM and different artificial neural network (ANN) architectures (recurrent neural network, multi-layered perceptron, radial basis function and probabilistic neural network) is presented and discussed. The comparison showed that the LS-SVM produced significantly better results than ANN architectures. It also indicates that LS-SVM provides promising results for short-term prediction of meteorological data.

Revisiting probabilistic neural networks: a comparative study with support vector machines and the microhabitat suitability for the Eastern Iberian chub (Squalius valentinus)

The early diagnosis of induction machine faults has become an exigency in all industrial process, as it reduces the breakdowns occurrence. Therefore, the importance of motor defect detection and their classification has recently result numerous research studies on the application of artificial neural network. In this paper, an effectual radial basis function neural networks (RBFN) and probabilistic neural networks (PNN) based method with dimensionality diminution is suggested for online motor current signal analysis. In order to minimize huge databases, Principal Component analysis is developed for selecting convenient training parameters. The classification performance comparison of RBFN and PNN is applied for the proposed method.

This paper uses a radial basis function (RBF) neural network for star identification. A feature vector consisting of distance and angle cosine values is constructed as a library of recognition feature stars and input to the neural network. Then, the network’s output is the number of the corresponding primary star. Comparing the training efficiency and robustness of the grid algorithm with the BP neural network and radial basis function neural network for star identification, the experimental results show that the radial basis function neural network has a strong anti-interference ability against noise and pseudo-star interference. The following conclusions are drawn from the simulation tests: the sample recognition rate of radial basis function neural network algorithm can reach 96% for star position and star addition noise; when the proportion of pseudo-star reaches 20%, the sample recognition rate of radial basis function neural network algorithm is still higher than grid algorithm and BP neural network, which indicates that the radial basis function neural network algorithm has the solid anti-interference ability to both noise and pseudo-star. Therefore, the radial basis function neural network algorithm based on star Identification has specific application prospects.

Good water quality is important for normal production processes in industrial aquaculture. However, in situ or real-time monitoring is generally not available for many aquacultural systems due to relatively high monitoring costs. Therefore, it is necessary to predict water quality parameters in industrial aquaculture systems to obtain useful information for managing production activities. This study used back propagation neural network (BPNN), radial basis function neural network (RBFNN), support vector machine (SVM), and least squares support vector machine (LSSVM) to simulate and predict water quality parameters including dissolved oxygen (DO), pH, ammonium-nitrogen (NH3-N), nitrate nitrogen (NO3-N), and nitrite-nitrogen (NO2-N). Published data were used to compare the prediction accuracy of different methods. The correlation coefficients of BPNN, RBFNN, SVM, and LSSVM for predicting DO were 0.60, 0.99, 0.99, and 0.99, respectively. The correlation coefficients of BPNN, RBFNN, SVM, and LSSVM for predicting pH were 0.56, 0.84, 0.99, and 0.57. The correlation coefficients of BPNN, RBFNN, SVM, and LSSVM for predicting NH3-N were 0.28, 0.88, 0.99, and 0.25, respectively. The correlation coefficients of BPNN, RBFNN, SVM, and LSSVM for predicting NO3-N were 0.96, 0.87, 0.99, and 0.87, respectively. The correlation coefficients of BPNN, RBFNN, SVM, and LSSVM predicted NO2-N with correlation coefficients of 0.87, 0.08, 0.99, and 0.75, respectively. SVM obtained the most accurate and stable prediction results, and SVM was used for predicting the water quality parameters of industrial aquaculture systems with groundwater as the source water. The results showed that the SVM achieved the best prediction effect with accuracy of 99% for both published data and measured data from a typical industrial aquaculture system. The SVM model is recommended for simulating and predicting the water quality in industrial aquaculture systems.

Artificial Neural Networks (ANNs) have been studied intensively in the field of computer science in recent years and have been shown to be a powerful tool for a variety of data-classification and pattern-recognition tasks. In this work, computerised diagnostic performance of hepatitis disease was investigated by various ANNs. Multilayer Perceptron, Radial Basis Function Neural Network, Conic Section Function Neural Network, Probabilistic Neural Network, and General Regression Neural Network structures have been used for this purpose. To determine diagnostic performance of networks for hepatitis disease, cross validation method and ROC analysis were applied.KeywordsRadial Basis FunctionReceiver Operating Characteristic AnalysisRadial Basis Function Neural NetworkRadial Basis Function NetworkHide UnitThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

With the development of the Internet, the Intrusion Detection has been gradually playing a more and more important role in Network Security. Radial Basis Function Neural Network are widely used in Intrusion Detection, especially Probabilistic Neural Network. However, the detection speed is a problem which impedes it to be applied to Real-time Intrusion Detection. In this paper, for increasing the Detection Speed, the Incremental Training Method replaces the Exact Training Method. The simulation experiment shows that the detection speed of Incremental Probabilistic Neural Network is much faster than that of Exact Probabilistic Neural Network. Therefore, the Incremental Probabilistic Neural Network is more suitable for real-time intrusion detection than Exact Probabilistic Neural Network.

Aiming at the high locating error and the underutilization of redundancy bearing mea surement in Pyroelectric Infrared Sensor (PIR) location system, a novel method of bearing location based on Radial Basis Function Neural Network (RBFNN) is presented. After illustrating the region partition model of PIR sensor node, we take advantage of the K-means clustering method and the gradient-descent method to train the neural network. By comparing different sizes of training samples, we select a neural network model with lower locating error, and we have made a c omparison of RBFNN and the geometric algorithm. The result of simulation shows that the neural network model has 18% higher locating accuracy and the locating error is much less than the geometric algorithm when the target is near the boundary of the detecting area. In troduction With the popularity of PIR's application, researchers come to do researches on target location method based on Wireless Sensor Nerworks (WSNs) and PIR technology. Dr. Qi Hao et al first studied the feasibility of the use of PIR in motion detection. In (1), with the Field of View (FOV) of PIR sensor nodes partitioned into several sub-regions and encoded, the locaction of target is estimated through grid approximation. In (2), a target location estimation method is put forward using the angular bisectors of the FOV. In (3), Probabilistic Neural Network (PNN) is used for assureing which sub-region the target is in. Then the crossing localization based on neural network region partition (CLBNNRP) method is used for estimating the accurate location of the target, which will largely improve the locating accuracy . B y now, most of the target location methods based on PIR focus on geometry and grid approximation algorithms, by measuring the angular information of target through sensor nodes. Geometric Algorithm(GA) is simple and clear, but the bearing error and the distance between target and sensor node may largely lead to loss of locating accuracy with large locating error. Thu s, this paper put forward a bearing location algorithm based on RBFNN. Section 2 presents the sensing model of the detecting area and the codes of every sub-region. Section 3 makes use of the nonlinear mapping relationship between numerous position information of training samples and the angular measurement that PIR sensor nodes acquire to establish a neural network model of target location. Section 4 demonstrates and analyses simulation results. Section 5 concludes the paper and points out the further study.

Anchoring technology is widely used in slope, tunnels and underground engineering. However, the rock bolt quality is still a hot problem which is difficult to solve. Considering the shortcoming of pull-out testing, defect identification in a non-destructive way is necessary. In this paper, the signal decomposition is obtained by rock bolt quality detector and wavelet packet transform and energy feature is extracted; the normalised energy eigenvector is converted as input of probabilistic neural network (PNN); the smoothing factor in PNN is optimised based on particle swarm optimisation algorithm and the defect identification rate of PNN is improved. With a higher accuracy than radial basis functions (RBF) neural network and PNN, the improved PNN can provide a reference for defect identification of rock bolt in engineering without destruction.

The Distribution Static Synchronous Compensator (DSTATCOM) has emerged as a vital solution for enhancing power quality and providing reactive power support in distribution networks. This study investigates the application of DSTATCOM in a multi-machine 9-bus system to achieve effective reactive power compensation and maintain a stable voltage profile under various operating conditions. Optimal placement of the DSTATCOM is determined through load flow analysis, targeting voltage regulation during normal operation as well as in the presence of voltage sag and swell scenarios. Further, this work extends into fault analysis by integrating Discrete Wavelet Transform (DWT) and Radial Basis Function Neural Networks (RBFNN) to detect and classify diverse fault events. Fault current signals are decomposed using the Daubechies-4 (Db4) mother wavelet at level 1, enabling the extraction of critical features. Fault Index (FI) and Fault Threshold (FTH) values are computed and compared to distinguish between normal and abnormal system conditions. The extracted DWT coefficients serve as inputs for training and testing the RBFNN, which is employed to accurately identify and categorize different fault types across various buses. To ensure the robustness and reliability of the proposed methodology, a comparative analysis is performed using Feedforward Neural Networks (FFNN), Probabilistic neural network (PNN), Recurrent current neural network (RNN) and Elman neural network (ENN). Additionally, RBFNN demonstrated faster convergence and better generalization capabilities, making it the most effective tool for fault detection in this study. Comprehensive simulations are performed in MATLAB Simulink under varying network conditions and neural network architectures to validate the approach. The results confirm that the proposed method offers a fast, accurate, and reliable solution for real-time fault detection and classification in power distribution systems.

The prognosis of childhood nephrotic syndrome directly hinges on the accurate prediction of negative conversion days (NCDs). Therefore, this paper designs a hybrid approach of principal component analysis (PCA) and backpropagation (BP)-adaptive boosting (AdaBoost) neural network (NN), and applies the method to predict the NCDs for children with nephrotic syndrome. Specifically, PCA method was employed for dimension reduction. Six principal components were extracted from multiple physiological features, and taken as input variables of three-tiered neural networks. The boosted predictor of BP-AdaBoost model, together with three predictors of BP NN, support vector machine (SVM) and radial basis function (RBF) NN, was trained for NCDs prediction. The experimental results show that the predictor of BP-AdaBoost NN achieves the mean absolute error of 0.2334, the mean relative error of 3.2789%, the SD of 4.6804 and the RSD of 50.8053% in NCDs prediction, and it outperforms other predictors of BP NN, SVM and RBF NN on both accuracy and precision. Furthermore, comparison experiments are conducted on PCA processed testing data and raw testing data for BP-AdaBoost NN and demonstrate the excellent effect of PCA. The hybrid approach of PCA and BP-AdaBoost NN is simple and reliable for NCDs prediction of childhood nephrotic syndrome, and it can help pediatricians prognose childhood nephrotic syndrome accurately and further provide patients with better care and treatment.