The Incremental 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.

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.

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 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.

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.

Probabilistic Neural Network(PNN) based on Alphastable distribution is proposed to improve former algorithm's poor fitting ability caused by independent identically distributed Gaussian assumption in intrusion detection's non-Gaussian data. Fast Fourier Transform Numerical Computation is used in the algorithm to establish its Alphastable distribution probability density function(PDF), and then the Samples Characteristic Function Algorithm is adopted to estimate the parameters, and finally Alpha-stable distribution PDF instead of Gaussian function is used as the activation function of PNN. In the simulation, intrusion detection dataset, KDD CUP 99, is used to validate the algorithm, which shows that compared with previous PNN and BPNN, the new algorithm has a stronger ability of fitting the non-Gaussian data and has improved the detection rate and false negative rate in intrusion detection greatly while the false alarm rate is stable.

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.

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.

Weighted probabilistic neural network

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.

Prediction of biological targets for molecules from their chemical structures is beneficial for generating focused libraries, selecting compounds for screening, and annotating biological activities for those compounds whose activities are unknown. We studied the ability of a probabilistic neural network (PNN), a variant of normalized radial basis function (RBF) neural networks, to predict biological activities for a set of 799 compounds having activities against seven biological targets. The compounds were taken from the MDDR database, and they were carefully selected to comprise distinct biological activities and diverse structures. The structural characteristics of compounds were represented by a set of 24 atom-type descriptors defined by 2D topological chemical structures. The modeling was done in two ways: (1). compounds having one certain activity were discriminated from those not having that activity and (2). all compounds were classified into seven biological classes. In both cases, around 90% of the compounds were correctly classified. Further validation of the modeled PNNs was done with 26 317 compounds having biological activities against various targets except for the seven targets used for modeling, and 67-98% compounds were correctly classified depending upon the targets. A PNN trains much more quickly than widely used neural networks such as a feed-forward neural network with error back-propagation. Calculation of atom-type descriptors is easy even for a large-size chemical library. Combination of PNN and atom-type descriptors thus provides a powerful way to predict biological activities from structural information.

Seismic inversion methods are routinely used to estimate attributes such as P-impedance, S-impedance, density, P-wave and S-wave velocity, and elastic impedances from seismic and well log data. These attributes help to understand subsurface lithology and fluid content. There are several types of seismic inversion methods available in which model-based inversion has got more attention. In the present study, the model-based inversion and geostatistical methods namely probabilistic neural network (PNN), multi-layer feed-forward neural network (MLFN) and radial basis function neural network (RBFNN) are implemented to estimate acoustic impedance, porosity, density, gamma-ray volume and P-wave velocity in the inter-well region of the F-3 block, Netherlands. The aim of the study is to predict a number of petrophysical parameters and demonstrate how they can be used to interpret seismic reflection data. A comparative study is also performed to estimate the best suitable method to predict various petrophysical parameters. The assessment of inverted results demonstrates that the impedance in the region varies from 2550 m/s*g/cc to 6150 m/s/*g/cc, which is relatively low and indicates the presence of loose formation in the area. The correlation between synthetic seismic trace and initial seismic trace is estimated to be 0.98, and the synthetic relative error as 0.19, indicating excellent algorithm output. Further, the assessment of the geostatistical methods is carried out to predict petrophysical parameters in conjunction with Multi-Attribute Transform Analysis. The analysis shows that among the geostatistical methods, the PNN provides slightly better results. The petrophysical parameters that are estimated in this study are porosity, density, gamma-ray, and P-wave velocity volumes. These parameters reinforce the interpretation of seismic data, which is a significant step in any project of exploration and production. The technique is first implemented to the composite traces near to the well location, and the findings are analysed with well log data. Second, the entire seismic section is inverted for porosity, density, gamma-ray, and P-wave velocity after achieving satisfactory outcomes in the first step. The assessment demonstrates very high-resolution subsurface petrophysical parameters which strengthen the seismic data interpretation.

Fault diagnosis for wireless sensor is very important to ensure signal acquisition precision. Radial basis function (RBF) neural network has strong classification ability. However, the selection of the connection weights, the hidden centers and the widths has an important influence on the classification performance of the RBF neural network in the learning process of RBF neural network. Thus, ant colony optimization is employ to gain the parameters of radial basis function neural network. Therefore, a novel method for fault diagnosis of wireless sensor based on RBF neural network and ant colony optimization is presented. The results of computational experiments show that ACO- RBF neural network has a great higher than RBF neural network.

Neural Network (NN) system is an information-processing that has characteristics similar to the neural network in living beings. A model of Neural Network is used for classification is Probabilistic Neural Network (PNN). PNN structured by four layers, the input layer, layer pattern, the summation layer and output layer. One of classification problems that can be solved by PNN is a classification of Diabetes Mellitus’s status. Diabetes mellitus is a chronic disease that occurs either when the pancreas does not produce enough insulin or when the body cannot effectively use the insulin produced. To facilitate the classification of diabetes mellitus, it is used a software-based Graphical User Interface (GUI) of Matlab to build a software of PNN. GUI that is formed can do PNN classification and predict the status of one’s Diabetes Mellitus. PNN structure that is formed resulting the highest accuracy 0.9143548 on the training process and 0.919512 on the testing process obtained by the percentage of training data than testing data by 90%:10% with holdout accuracy evaluation method, and a smoothing value of 1. This classification resulting 23 patients were classified as negative diabetes and 18 patients were classified as positive diabetes. Keywords : Neural Network, Probabilistics Neural Network, diabetes mellitus, GUI, holdout, smoothing parameter.