Probabilistic Neural Network Algorithm Research Articles

An expert model for self-care problems classification using probabilistic neural network and feature selection approach

Self-care problems classification is one of the important challenges for occupational therapists. Extent and variety of disorders make the self-care problems classification process complex and time-consuming. To overcome this challenge, an expert model is proposed innovatively in this research. The proposed model is based on Probabilistic Neural Network (PNN) and Genetic Algorithm (GA) for classifying self-care problems of children with physical and motor disability. In this model, PNN is employed as a classifier and GA is applied for feature selection. The PNN is trained by using a standard ICF-CY dataset. Based on ICF-CY, occupational therapists must evaluate many features to diagnose self-care problems. According to the experiences of occupational therapists, these features have different effects on classification. Hence, GA is employed to select relevant and important features in self-care problems classification. Since the classification rules are important for occupational therapists, the self-care problems classification rules are extracted additionally by using the CART algorithm. The experimental results show that by using the feature selection algorithm, the accuracy and time complexity of classification are improved in comparison to other models. The proposed model can classify self-care problems of children with 94.28% accuracy by using only 16.5% of all features.

The assessment of fresh and spoiled beef meat using a prototype device based on GigE Vision camera and DSP

Beef meat freshness was evaluated using artificial vision technique and pattern recognition algorithms. Color and texture features were extracted from the saturation images. The wavelet transform was used to characterize texture and a range of features was used to better characterize color. Two classes of beef meat samples were obtained from the projection of color, texture, and color associated with texture datasets using Principal Component Analysis (PCA) method. The first class corresponds to fresh beef meat samples that have undergone 6 days of cold storage and the second class presents spoiled meat. Probabilistic Neural Network (PNN) and Linear Discriminant Analysis (LDA) algorithms were used to classify and predict beef meat samples into fresh or spoiled samples. Results show that the classification and identification rates obtained by PNN are superior to LDA algorithm using the datasets of color, texture, and color associated with texture. In addition, results show that texture features associated with color features give the best classification and identification rates. An implementation of all proposed algorithms was carried out on a real time embedded system.

Predicting Porosity by Multivariate Regression and Probabilistic Neural Network using Model-based and Coloured Inversion as External Attributes: A Quantitative Comparison

Abstract The acoustic impedance (AI) inversion aims to obtain a high-resolution impedance volume by integrating well-log and band-limited seismic data. Two AI inversion schemes: the coloured inversion (CI) and the model-based inversion (MBI) are utilized to characterize possible sand channel from the post-stack seismic section and log data from 13 wells from the Blackfoot region, Alberta, Canada. The results from analyses indicate that both the model-based and coloured inversion methods provide mutually consistent impedance volumes with an average correlation coefficient of 0.986 and 0.886 for MBI and CI, respectively. Both inversions show low-impedances ranging from 6750-7350m/s*g/cc between 1060ms and 1065ms time interval which is interpreted as a sand channel. The slice of the acoustic impedance variation along all cross line and inline validates the presence of low impedances along the interpreted sand channel. Thereafter, the multivariate regression and the Probabilistic Neural Network (PNN) are employed to predict porosity volumes using CI and MBI inverted impedance as external attributes. The cross-plots between predicted porosities and actual porosities using multivariate regression and PNN algorithms indicate that PNN produces better statistical estimates of porosity distribution compared to those predicted from the multivariate regression. Both methods show high porosity values along the sand channel. The maximum porosity in the sand channel is 18% when MBI derived impedance is used as an external attribute while it is 16% in the case of CI. The results suggest that given seismic and well log data for a region, a combination of model-based inversion and PNN can produce a more reliable estimate of the petrophysical properties of the sub-surface.

Developing of robust and high accurate ECG beat classification by combining Gaussian mixtures and wavelets features.

Electrocardiogram (ECG) beat classification is a significant application in computer-aided analysis and diagnosis technologies. This paper proposed a method to detect, extract informative features, and classify ECG beats utilizing real ECG signals available in the standard MIT-BIH Arrhythmia database, with 10,502 beats had been extracted from it. The present study classifies the ECG beat into six classes, normal beat (N), Left bundle branch block beat, Right bundle branch block beat, Premature ventricular contraction, atrial premature beat, and aberrated atrial premature, using Gaussian mixture and wavelets features, and by applying principal component analysis for feature set reduction. The classification process is implemented utilizing two classifier techniques, the probabilistic neural network (PNN) algorithm and Random Forest (RF) algorithm. The achieved accuracy is 99.99%, and 99.97% for PNN and RF respectively. The precision is 99.99%, and 99.98% for PNN and RF respectively. The sensitivity is 99.99%, and 99.81% for PNN and RF respectively, while the specificity is 99.97%, 99.96% for PNN and RF respectively. It has been shown that the combination of Gaussian mixtures coefficients and the wavelets features have provided a valuable information about the heart performance and can be used significantly in arrhythmia classification.

Prediction of kidney disease stages using data mining algorithms

Abstract Early detection and characterization are considered to be critical factors in the management and control of chronic kidney disease. Herein, use of efficient data mining techniques is shown to reveal and extract hidden information from clinical and laboratory patient data, which can be helpful to assist physicians in maximizing accuracy for identification of disease severity stage. The results of applying Probabilistic Neural Networks (PNN), Multilayer Perceptron (MLP), Support Vector Machine (SVM) and Radial Basis Function (RBF) algorithms have been compared, and our findings show that the PNN algorithm provides better classification and prediction performance for determining severity stage in chronic kidney disease.

A Hybrid Grey Wolf Optimiser Algorithm for Solving Time Series Classification Problems

Abstract One of the major objectives of any classification technique is to categorise the incoming input values based on their various attributes. Many techniques have been described in the literature, one of them being the probabilistic neural network (PNN). There were many comparisons made between the various published techniques depending on their precision. In this study, the researchers investigated the search capability of the grey wolf optimiser (GWO) algorithm for determining the optimised values of the PNN weights. To the best of our knowledge, we report for the first time on a GWO algorithm along with the PNN for solving the classification of time series problem. PNN was used for obtaining the primary solution, and thereby the PNN weights were adjusted using the GWO for solving the time series data and further decreasing the error rate. In this study, the main goal was to investigate the application of the GWO algorithm along with the PNN classifier for improving the classification precision and enhancing the balance between exploitation and exploration in the GWO search algorithm. The hybrid GWO-PNN algorithm was used in this study, and the results obtained were compared with the published literature. The experimental results for six benchmark time series datasets showed that this hybrid GWO-PNN outperformed the PNN algorithm for the studied datasets. It has been seen that hybrid classification techniques are more precise and reliable for solving classification problems. A comparison with other algorithms in the published literature showed that the hybrid GWO-PNN could decrease the error rate and could also generate a better result for five of the datasets studied.

Qualitative and quantitative comparison of geostatistical techniques of porosity prediction from the seismic and logging data: a case study from the Blackfoot Field, Alberta, Canada

In present study, three recently developed geostatistical methods, single attribute analysis, multi-attribute analysis and probabilistic neural network algorithm have been used to predict porosity in inter well region for Blackfoot field, Alberta, Canada, an offshore oil field. These techniques make use of seismic attributes, generated by model based inversion and colored inversion techniques. The principle objective of the study is to find the suitable combination of seismic inversion and geostatistical techniques to predict porosity and identification of prospective zones in 3D seismic volume. The porosity estimated from these geostatistical approaches is corroborated with the well log porosity. The results suggest that all the three implemented geostatistical methods are efficient and reliable to predict the porosity but the multi-attribute and probabilistic neural network analysis provide more accurate and high resolution porosity sections. A low impedance (6000–8000 m/s g/cc) and high porosity (> 15%) zone is interpreted from inverted impedance and porosity sections respectively between 1060 and 1075 ms time interval and is characterized as reservoir. The qualitative and quantitative results demonstrate that of all the employed geostatistical methods, the probabilistic neural network along with model based inversion is the most efficient method for predicting porosity in inter well region.

Determination of the best microstructure and titanium alloy powders properties using neural network

Purpose: Create a software product using a probabilistic neural network (PNN) and database based on experimental research of titanium alloys to definition of the best microstructure and properties of aerospace components. Design/methodology/approach: The database creation process for artificial neural network training was preceded by the investigation of the granulometric composition of the titanium powder alloys, study of microstructure, phase composition and evaluation of micromechanical properties of these alloys by the method of material plasticity estimation in the conditions of hard pyramidal indenters application. A granulometric analysis was done using a special complex of materials science for the images analysis ImageJ. Metallographic investigations of the powder structure morphology were carried out on the scanning electron microscope EVO 40XVP. Specimens for micromechanical testing were obtained by overlaying the titanium alloy powders on the substrate made of the material close to chemical composition. Substrates were prepared by pressing the powder mixture under the load of 400 MPa and following sintering at 1300°C for 1 hour. Overlaying was performed by an electron gun ELA-6 (beam current – 16 mA). Findings: According to the modelling results, a threshold of the PNN accuracy was established to be over 80%. A high level of experimental data reproduction allows us a full or partial replacement of a number of experimental investigations by neural network modelling, noticeably decreasing, in this case, the cost of the material creation possessing the preset properties with preserved quality. It is expected that this software can be used for solving other problems in materials science too. Research limitations/implications: The accuracy of the PNN algorithm depends on the number of input parameters obtained experimentally and forms a database for the training of the system. For our case, the amount of input data is limited. Practical implications: Previously trained system based on the PNN algorithm will reduce the number of experiments that significantly reduce costs and time to study. Originality/value: A software product on the basis of the PNN network was developed. The training sample was built based on a series of laboratory studies granulometric composition of the titanium powder alloys, study of microstructure, phase composition and evaluation of micromechanical properties of powder materials. The proposed approach allows us to determine the best properties of the investigated material for the design of aerospace components.

PCM-SABRE: a platform for benchmarking and comparing outcome prediction methods in precision cancer medicine

BackgroundNumerous publications attempt to predict cancer survival outcome from gene expression data using machine-learning methods. A direct comparison of these works is challenging for the following reasons: (1) inconsistent measures used to evaluate the performance of different models, and (2) incomplete specification of critical stages in the process of knowledge discovery. There is a need for a platform that would allow researchers to replicate previous works and to test the impact of changes in the knowledge discovery process on the accuracy of the induced models.ResultsWe developed the PCM-SABRE platform, which supports the entire knowledge discovery process for cancer outcome analysis. PCM-SABRE was developed using KNIME. By using PCM-SABRE to reproduce the results of previously published works on breast cancer survival, we define a baseline for evaluating future attempts to predict cancer outcome with machine learning. We used PCM-SABRE to replicate previous work that describe predictive models of breast cancer recurrence, and tested the performance of all possible combinations of feature selection methods and data mining algorithms that was used in either of the works. We reconstructed the work of Chou et al. observing similar trends – superior performance of Probabilistic Neural Network (PNN) and logistic regression (LR) algorithms and inconclusive impact of feature pre-selection with the decision tree algorithm on subsequent analysis.ConclusionsPCM-SABRE is a software tool that provides an intuitive environment for rapid development of predictive models in cancer precision medicine.

Impedance Based Health Monitoring Technique with Probabilistic Neural Network for Possible Wall Thinning Detection of Metal Structures

Corrosion of structures and wall thinning of pipes can severely affect the mechanical strength as wall thickness is reduced. Thus a cost effective structural health monitoring technique plays an important role when managing a structure. The electromechanical impedance (EMI) method is a local method that has limited sensing range, resulting in a high cost when covering large areas. In this study, a reattachable EMI method is investigated using a stack of multiple metal plates to conduct an experiment involving thickness reduction. In addition, the main problem of the impedance signatures changing subjected to reattaching the piezoelectric transducer is solved by using the probabilistic neural network algorithm presented for the study. The proposed approach successfully identifies the thickness of two different structures with high accuracy.

Application of a Hybrid System of Probabilistic Neural Networks and Artificial Bee Colony Algorithm for Prediction of Brand Share in the Market

Manufacturers and retailers are interested in how prices, promotions, discounts and other marketing variables can influence the sales and shares of the products that they produce or sell. Therefore, many models have been developed to predict the brand share. Since the customer choice models are usually used to predict the market share, here we use hybrid model of Probabilistic Neural Network and Artificial Bee colony Algorithm (PNN-ABC) that we have introduced to model consumer choice to predict brand share. The evaluation process is carried out using the same data set that we have used for modeling individual consumer choices in a retail coffee market. Then, to show good performance of this model we compare it with Artificial Neural Network with one hidden layer, Artificial Neural Network with two hidden layer, Artificial Neural Network trained with genetic algorithms (ANN-GA), and Probabilistic Neural Network. The evaluated results show that the offered model is outperforms better than other previous models, so it can be use as an effective tool for modeling consumer choice and predicting market share.

Cutting State Diagnosis for Shearer through the Vibration of Rocker Transmission Part with an Improved Probabilistic Neural Network.

In order to achieve more accurate and reliable identification of shearer cutting state, this paper employs the vibration of rocker transmission part and proposes a diagnosis method based on a probabilistic neural network (PNN) and fruit fly optimization algorithm (FOA). The original FOA is modified with a multi-swarm strategy to enhance the search performance and the modified FOA is utilized to optimize the smoothing parameters of the PNN. The vibration signals of rocker transmission part are decomposed by the ensemble empirical mode decomposition and the Kullback-Leibler divergence is used to choose several appropriate components. Forty-five features are extracted to estimate the decomposed components and original signal, and the distance-based evaluation approach is employed to select a subset of state-sensitive features by removing the irrelevant features. Finally, the effectiveness of the proposed method is demonstrated via the simulation studies of shearer cutting state diagnosis and the comparison results indicate that the proposed method outperforms the competing methods in terms of diagnosis accuracy.

Oil-immersed Power Transformer Internal Fault Diagnosis Research Based on Probabilistic Neural Network

Oil-immersed power transformer is one of the key devices in power system. And the reliability of power grid is guaranteed by its safe operation. Therefore, it is necessary to reduce transformer failures with precautionary measures. Nowadays, three-ratio method of dissolved gas analysis (DGA) is the most effective and convenient method in transformer fault diagnosis. However, when using three-ratio method as the judgment, it exists some disadvantages such as coding defects and threshold criterion defect. A new way for this problem is provided by artificial neural network, which has the advantages such as parallel processing, self-adaptation self-study, association memory, non-linear mapping and other features. Oil-immersed transformer internal faults are predicted in this paper by using probabilistic neural network algorithm, which brings its ability of processing non-linear problem into full play. What's more, the DGA judgment process is optimized and convenient setting of parameters is achieved. The high accuracy of diagnosis is confirmed by simulation results in KNIME platform.

Mechanical Fault Diagnosis Using Color Image Recognition of Vibration Spectrogram Based on Quaternion Invariable Moment

Automatic extraction of time-frequency spectral image of mechanical faults can be achieved and faults can be identified consequently when rotating machinery spectral image processing technology is applied to fault diagnosis, which is an advantage. Acquired mechanical vibration signals can be converted into color time-frequency spectrum images by the processing of pseudo Wigner-Ville distribution. Then a feature extraction method based on quaternion invariant moment was proposed, combining image processing technology and multiweight neural network technology. The paper adopted quaternion invariant moment feature extraction method and gray level-gradient cooccurrence matrix feature extraction method and combined them with geometric learning algorithm and probabilistic neural network algorithm, respectively, and compared the recognition rates of rolling bearing faults. The experimental results show that the recognition rates of quaternion invariant moment are higher than gray level-gradient cooccurrence matrix in the same recognition method. The recognition rates of geometric learning algorithm are higher than probabilistic neural network algorithm in the same feature extraction method. So the method based on quaternion invariant moment geometric learning and multiweight neural network is superior. What is more, this algorithm has preferable generalization performance under the condition of fewer samples, and it has practical value and acceptation on the field of fault diagnosis for rotating machinery as well.

Probabilistic Neural Network Algorithm for using Radon Emanations as an Earthquake Precursor

Abstract: The investigation throughout the world in past two decades provides evidence which indicate that significance variation of radon and other soil gases occur in association with major geophysical events such as earthquake. The traditional statistical algorithm includes regression to remove the effect of the meteorological parameters from the raw radon and anomalies are calculated either taking the periodicity in seasonal variations or periodicity computed using Fast Fourier Transform. In case of neural networks the regression step is avoided. A neural network model can be found which can learn the behavior of radon with respect to meteorological parameter in order that changing emission patterns may be adapted to by the model on its own. The output of this neural model is the estimated radon values. This estimated radon value is used to decide whether anomalous behavior of radon has occurred and a valid precursor may be identified. The neural network model developed using Radial Basis function network gave a prediction rate of 87.7%. The same was accompanied by huge false alarms. The present paper deals with improved neural network algorithm using Probabilistic Neural Networks that requires neither an explicit step of regression nor use of any specific period. This neural network model reduces the false alarms to zero and gave same prediction rate as RBF networks.

The Recognition and Research of Improved Probabilistic Neural Network

Probabilistic neural network compared with the traditional BP neural network structure is simpler and it is faster to be identificated, so it is widely used in the field of pattern recognition. This paper is mainly focused on similar gesture recognition research, propose an probabilistic neural network gesture recognition algorithm. The simulation results show that the improved probabilistic neural network algorithm on the recognition rate and training time is better than the traditional BP network.

Research on indoor positioning algorithm based on powerline

In this research, the basic principle of data acquisition based on powerline is introduced.Probabilistic neural network (PNN) is applied to indoor location system aiming at environment of strong noise indoor and the reason of PNN applied to indoor location system based on powerline is discussed in detail. According to characteristics of transmitted signal by powerline, the signal is firstly pretreated and then transformed by Fast Fourier Transform (FFT) before it is transmitted to PNN algorithm in order to effectively extract position information included in data by PNN. The test shows that network training speed of PNN is fast, it has a strong ability to resist interference, with having good indoor positioning accuracy and PNN is much better than K-Nearest Neighbor (KNN) and Counter Propagation Network (CPN) indoor positioning algorithm in indoor position system based on powerline. Key words: Probabilistic neural network (PNN) algorithm, power line, indoor positioning, received signal strength indicator (RSSI).

An enhanced classification approach for reliability estimation of structural systems

The accuracy of a classification-based surrogate model for reliability assessment can be improved by augmenting the training data (labeled data or data with known responses) with a large number of unlabeled data (data with unknown responses) in semi-supervised learning methods. In this research, an enhanced Probabilistic Neural Network (PNN) algorithm is proposed where the Gaussians at each labeled point are not assumed to be spherical. Each of the Gaussians has a `full' covariance matrix instead of simply assuming the Gaussian with a `spherical' covariance matrix. First, the Expectation-Maximization algorithm is applied on the labeled and unlabeled data while assuming that the number of `full' Gaussians is equal to the number of labeled datapoints. The contribution of each of these `full' Gaussians at a particular datapoint is found by using the Bayes Theorem. The Bayes decision criterion is then used in the final output layer of the PNN to classify test patterns into either the safe or the failure class. The primary benefit of the proposed method comes from utilizing unlabeled data for better estimation of `full' covariance matrices of constituting Gaussian clusters of underlying data, which are then used to estimate the Probability Density Functions of classes for classification. This procedure does not require additional computational costs to improve the accuracy of the classification results since the cost of unlabeled data is negligible in general. Two examples including an analytic problem and a truss problem are presented in order to validate the proposed reliability estimation process. The results reflect considerable improvements of the classifier performance for estimating reliability while maintaining sufficient accuracy.

Skull segmentation of UTE MR images by probabilistic neural network for attenuation correction in PET/MR

Aim: Due to space and technical limitations in PET/MR scanners one of the difficulties is the generation of an attenuation correction (AC) map to correct the PET image data. Different methods have been suggested that make use of the images acquired with an ultrashort echo time (UTE) sequence. However, in most of them precise thresholds need to be defined and these may depend on the sequence parameters. In this study an algorithm based on a probabilistic neural network (PNN) is presented requiring little user interaction. Material and methods: An MR UTE sequence delivering two images (UTE1 and UTE2) by using two different echo times (0.07ms and 2.46ms, respectively) was acquired. The input features for the PNN algorithm consist of two patches of MR intensities chosen in both the co-registered UTE1 and UTE2 images. At the end, the PNN generates an image classified into four different classes: brain+soft tissue, air, csf, and bone. CT and MR data were acquired in four subjects, whereby the CT data were used for comparison. For each patient co-classification of the different classified classes and the Dice coefficients (D) were calculated between the MR segmented image and the respective CT image. Results: An overall voxel classification accuracy (compared with CT) of 92% was obtained. Also, the resulting D with regard to the skull and calculated for the four subjects show a mean of 0.83 and a standard deviation of 0.07. Discussion: Our results show that a reliable bone segmentation of MRI images as well as the generation of a reliable attenuation map is possible. Conclusion: The developed algorithms possess several advantages over current methods using UTE sequence such as a quick and an easy optimization for different sequence parameters.

Forecasting New Product Adoption with Probabilistic Neural Networks

Forecasting the adoption of innovative products is an important managerial task. In this paper we examine the usefulness of a probabilistic neural network (PNN) algorithm for forecasting new product adoption. We compare this approach with one widely accepted forecasting procedure, the binomial logit model, and two other neural network algorithms: a feed-forward neural network model estimated with backward propagation (NNBP), and a feed-forward neural network model estimated with a genetic algorithm (NNGA). To test the relative forecasting accuracy of these algorithms, we examine the first-time adoption of DVD players. Our analysis is based on longitudinal consumer data collected between March 2000 and March 2001. We find that the PNN algorithm significantly outperforms the logit model and the two remaining neural network algorithms.