Basis Probabilistic Neural Network Research Articles

Improved probabilistic neural networks with self-adaptive strategies for transformer fault diagnosis problem

Probabilistic neural network has successfully solved all kinds of engineering problems in various fields since it is proposed. In probabilistic neural network, Spread has great influence on its performance, and probabilistic neural network will generate bad prediction results if it is improperly selected. It is difficult to select the optimal manually. In this article, a variant of probabilistic neural network with self-adaptive strategy, called self-adaptive probabilistic neural network, is proposed. In self-adaptive probabilistic neural network, Spread can be self-adaptively adjusted and selected and then the best selected Spread is used to guide the self-adaptive probabilistic neural network train and test. In addition, two simplified strategies are incorporated into the proposed self-adaptive probabilistic neural network with the aim of further improving its performance and then two versions of simplified self-adaptive probabilistic neural network (simplified self-adaptive probabilistic neural networks 1 and 2) are proposed. The variants of self-adaptive probabilistic neural networks are further applied to solve the transformer fault diagnosis problem. By comparing them with basic probabilistic neural network, and the traditional back propagation, extreme learning machine, general regression neural network, and self-adaptive extreme learning machine, the results have experimentally proven that self-adaptive probabilistic neural networks have a more accurate prediction and better generalization performance when addressing the transformer fault diagnosis problem.

MONITORING RUBBER FACTORY MALODOUR USING ARTIFICIAL NEURAL NETWORK

Malodour from rubber factory activities is a nuisance to the residence in the surrounding area. The volatile chemical compounds emitted from the factory are identified as the major source of the malodour. This research proposes a study of malodour monitoring for the rubber factory using Electronic Nose (e-nose) system to enable effective malodour monitoring. The proposed system will able to predict and monitor the malodour concentration in the surrounding area of the factory. The finding will be used as a guideline for monitoring the violations of environmental guidelines. The malodour and environment parameters such as temperature, wind speeds and directions are recorded. These parameters are measured on-site and monitored using wireless sensor network (WSN) system. The malodour concentration model of each location will generate using three types of Artificial Neural Network (ANN) i.e. Multilayer Perceptron (MLP), Radial Basis Function (RBF) and Probabilistic Neural Network (PNN). These indices will be used to generate the malodour concentration mapping model of the factory and surrounding areas. The initial results show that the system can be effectively used for real time rubber factory malodour monitoring.

A novel sensor fault diagnosis method based on Modified Ensemble Empirical Mode Decomposition and Probabilistic Neural Network

A novel fault diagnosis method based on Modified Ensemble Empirical Mode Decomposition (MEEMD) and Probabilistic Neural Network (PNN) is presented in this paper. It aims to achieve more accurate and reliable sensor fault diagnosis in thermal power plant. To restrain the mode mixing problem in traditional EMD, an MEEMD is proposed based on signal reconstruction and pseudo component identification. The MEEMD is applied to decompose the original thermal parameter signals into a finite number of Intrinsic Mode Functions (IMFs) and a residual to extract the sensor fault feature. After analyzing the inherent physical meanings of each IMF and residual, the variances of them are extracted as feature eigenvectors to express the signal feature. Finally, PNN is used as the classifier for detection and identification of sensor faults. Based on the practical normal signals, which are collected from a main steam temperature sensor of a CLN600–24.2/566/566 steam turbine, three types of representative sensor fault signals are simulated to test the proposed method. By analyzing simulation and real signal, the analysis results indicate that the MEEMD can restrain the mode mixing problem in traditional EMD effectively, and the proposed fault diagnosis method had better performance than the other two fault diagnosis methods including basic PNN and EMD–PNN.

Invariant face recognition using Zernike moments combined with feed forward neural network

The paper proposes a face recognition system using Zernike moments ZM and feed forward neural network as a classifier. Magnitudes of the ZM, which are invariant to rotation, are used as feature vectors for efficient representation of the images. The experiment was conducted on the ORL and Texas 3D Face Recognition Database which has both colour and range images. The recognition performance with measures like overall recognition accuracy, false acceptance rate, false rejection rate and true rejection rate was evaluated with multilayer perceptron neural network, radial basis function neural network and probabilistic neural network for variable lengths of the feature vector using confusion matrix. The simulation results indicates that the invariant ZM with neural network classifier was successful in recognising the images constrained to different variations and illumination conditions. The overall classification accuracy of 99.7% with MLPNN and 99.6% with MLPNN was achieved with range images and grey images from Texas 3D Face Recognition Database, respectively. Furthermore, 99.5% accuracy with RBFNN was achieved from ORL database.

Adaptive neural network models for automatic incident detection on freeways

Automated incident detection (AID) is an essential component of an Advanced Traffic Management and Information Systems (ATMIS), which provides round the clock incident detection, and helps initiate the required action in case of an accident or incident. This paper evaluates three promising neural network models: multi-layer feed-forward neural network (MLF), basic probabilistic neural network (BPNN) and constructive probabilistic neural network (CPNN) for their incident detection performance. An important consideration in neural network-based incident detection systems is the deployment of a trained neural network on traffic systems with considerably different driving conditions. The models were developed and tested on an original freeway site in Singapore, and tested on a new freeway site in the US for their adaptability. The paper presents comparative evaluation in terms of their classification accuracy, adaptability, and network size. Results indicate that although the MLF model gives excellent classification results on the development site, the CPNN model outperforms the other two in terms of its adaptability and flexible structure. The results suggest that CPNN model has the highest potential for use in an operational automatic incident detection system for freeways.

Evaluation of Adaptive Neural Network Models for Freeway Incident Detection

Automated incident detection is an essential component of a modern freeway traffic monitoring system. A number of neural network (NN)-based incident detection models have been tested independently over the past decade. This paper evaluates the adaptability of three promising NN models for this problem: a multilayer feed-forward NN (MLFNN), a basic probabilistic NN (BPNN) and a constructive probabilistic NN (CPNN). These three models have been developed on an original freeway site in Singapore and then adapted to a new freeway site in California. In addition to their incident detection performance, their ability to adapt to new freeway sites, and network sizes have also been compared. A novel updating scheme has been used for adjustment of smoothing parameter of the BPNN. Results of this study show that the MLFNN model has the best incident detection performance at the development site while CPNN model has the best performance after model adaptation at the new site. In addition, the adaptation method for CPNN model is less laborious. The efficient network pruning procedure for the CPNN network resulted in a smaller network size, making it easier to implement it for real-time application. The results suggest that CPNN model has good potential for application in an operational automatic incident detection system for freeways.

Development and adaptation of constructive probabilistic neural network in freeway incident detection

This paper investigates the use of constructive probabilistic neural network (CPNN) in freeway incident detection, including model development and adaptation. The CPNN was structured based on mixture Gaussian model and trained by a dynamic decay adjustment algorithm. The model was first trained and evaluated on a simulated incident database in Singapore. The adaptation of CPNN on the I-880 freeway in California was then investigated in both on-line and off-line environments. This paper also compares the performance of the CPNN model with a basic probabilistic neural network (BPNN) model. The results show that CPNN has three main advantages over BPNN: (1) CPNN has clustering ability and therefore could achieve similarly good incident-detection performance with a much smaller network size; (2) each Gaussian component in CPNN has its own smoothing parameter that can be obtained by the dynamic decay adjustment algorithm with a few epochs of training; and (3) the CPNN adaptation methods have the ability to prune obsolete Gaussian components and therefore the size of the network is always within control. CPNN has shown to have better application potentials than BPNN in this research.

An iterative feature reduction algorithm for probabilistic neural networks

The issue of noise and redundant feature variables in classification problems has been well addressed in statistical stepwise discriminant analysis. However, no feature reduction algorithm designed specifically for Probabilistic Neural Network (PNN) is found in literature. In this study, we develop an ad hoc iterative feature (variable) reduction algorithm for basic PNNs to identify noise and redundant variables. A basic PNN applying the same smoothing factor to all variables does not distinguish variables adding little or no predictive power to the model from others. The proposed iterative approach utilizes a weighted PNN with one smoothing factor for each variable in the feature reduction stage. Once a subset of variables is selected, a basic PNN is developed on the chosen variables for future applications. Computational experiments on five data sets obtained from publicly available sources indicate that the basic PNN with variables chosen by the ad hoc approach outperforms the PNN using variables selected by two benchmark methods, back-propagation neural network and stepwise linear discriminant analysis.

Influence of Data Preprocessing and Kernel Selection on Probabilistic Neural Network Modeling of the Acute Toxicity of Chemicals to the Fathead Minnow and Vibrio fischeri Bacteria

Abstract We investigated the connection between the data preprocessing strategy and kernel choice on the quality of the associated basic probabilistic neural network models for the acute toxicity of various chemicals to the fathead minnow and to Vibrio fischeri bacteria. The models employ exclusively structural parameters and physicochemical properties as inputs. Results show that the Gaussian kernel is preferable over the reciprocal kernel model. Data preprocessing based on the hyperbolic tangent and the sigmoid logistic transforms provides the best results at the level of the cross validation experiment. Improved models based on cross validation partial models and linear corrections were also investigated. The results show that the improved models with data preprocessing based on the hyperbolic tangent and the finite interval transforms are the best with practically identical quality of predictions.