Flaw classification in ultrasonic guided waves signal using Wavelet Transform and PNN classifier

Partial discharge (PD) classification in power cable accessories and high voltage equipment in general is essential in evaluating the severity of the damage in the insulation. In this article, the PD classification was realised as a two-fold process. Firstly, measurements taken from a high-frequency current transformer (HFCT) sensor were represented as features by means of a transformation to the classifier and secondly, the probabilistic neural network (PNN) classifier itself was capable of effectively recognising features coming from different types of discharges. The feature that was used as a fingerprint for PD characterisation was extracted from the moments of the probability density function (PDF) of the wavelet coefficients at various scales, obtained through the wavelet packets transformation. The PNN classifier was used to classify the PDs and assess the suitability of this feature vector in PD classification. Four types of artificial PDs were created in a high voltage laboratory, namely corona discharge in air, floating discharge in oil, internal discharge in oil and surface discharge in air, at different applied voltages, and were used to train the PNN algorithm. The results obtained here (97.49, 91.9, 100 and 99.8% for the corona, the floating, the internal and the surface discharges, respectively) are very encouraging for the use of PNN in PD classification with this particular feature vector. This article suggests a feature extraction and classification algorithm for PD classification, which when combined together reduced the dimensionality of the feature space to a manageable dimension, and achieved very high levels of classification.

The energy crisis has promoted the development of solar photovoltaic power generation systems, but during the operation of solar panels, there will be hidden troubles such as ground fault, line-to-line fault, open-circuit fault, short-circuits fault and the hot spots. This will cause serious obstacles to the power generation of photovoltaic systems. Therefore, the immediate diagnosis and elimination of the fault of the photovoltaic system is the guarantee for the stable operation of the photovoltaic system. To address these issues, this paper makes contribution in the following Three aspects: (1) Building a 4×3 PV array model based on the key points and model parameters extracted from PV array by using Matlab, an efficient feature vector of five dimensions is proposed as the input of the fault diagnosis model; (2) The probabilistic neural network (PNN) is proposed as the fault classification tools, and achieving a good classification effect by using the simulated data after normalization to classify; (3) Performing the field test and inputting the experimental data into PNN for classification, with an accuracy of 97%. Both the simulation and experimental results show that the PNN can achieve high accuracy classification, provide a more favorable premise basis for the intelligent classification of faults in photovoltaic arrays.

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.

In this paper, feature subset selection from river-ice image samples for classification of river-ice types is proposed using extreme learning machine (ELM) and differential evolution feature selection (DEFS) technique called extreme learning machine-based differential evolution feature selection (ELM-DEFS). Although DEFS is a good feature selection technique, the feature weights are selected by cross over and mutation which may be trapped. So, ELM is integrated with DEFS to overcome the difficulties of selecting the weights. Feature subset selection plays the most important role to classify the river-ice types. First-and second-order statistical texture features are extracted from real river-ice images. All the original features extracted from feature extraction methods do not help in recognition of river-ice types, so it is essential to reduce the feature subset to improve classification accuracy. In this paper, experiments are conducted on real river-ice image samples with probabilistic neural network (PNN) classifier which classifies different ice types. Performances of ELM-DEFS are compared with genetic algorithm (GA) and DEFS by means of performance evaluation metrics. Experimental results show that ELM-DEFS convergence is better than both DEFS and GA in selecting top-most feature subset; ELM-DEFS-based PNN (ELM-DEFS-PNN) classifier exhibits higher performance with an accuracy of 93% which is approximately 1% higher than GA-based PNN (GA-PNN) and DEFSbased PNN (DEFS-PNN) classification.

Drones are becoming more prevalent across a variety of industries, including recreation, engineering, agriculture, farming, search and rescue, surveillance, and security.Aside from their advantages, drones have numerous drawbacks that come along with their rising popularity.These drawbacks include privacy concerns, safety risks, monitoring at airport and military systems, and vulnerability to hacking.In recent years, there have been numerous incidents of unauthorized drone usage at airports, causing significant disruptions to airline operations.Because they can appear identical when viewed from a distance, differentiating between drones and birds can occasionally be difficult.This paper offers a probabilistic neural network (PNN) learning-based approach for the effective detection and identification of drones as a solution to this issue.The proposed approach involves preprocessing the visible imagery to enhance relevant features and remove noise.Gabor filtering is applied to extract Gabor features from the images, which capture both spatial and frequency information.These features, along with other relevant attributes, are then fed into PNN for classification.Smaller datasets have a positive impact on PNN performance.Initial results show that the PNN algorithm, in conjunction with Gabor characteristics, is effective for classifying drones and birds.The suggested method is able to identify and separate drones from birds as well as determine whether drones are present or absent in a given area.

In this study, we evaluate and compare the diagnostic performance of ultrasound for non‐invasive axillary lymph node (ALN) metastasis detection. The study was based on fusing shear wave elastography (SWE) and B‐mode ultrasonography (USG) images. These images were subjected to pre‐processing and feature extraction, based on bi‐dimensional empirical mode decomposition and higher order spectra methods. The resulting nonlinear features were ranked according to theirp‐value, which was established with Student'st‐test. The ranked features were used to train and test six classification algorithms with 10‐fold cross‐validation. Initially, we considered B‐mode USG images in isolation. A probabilistic neural network (PNN) classifier was able to discriminate positive from negative cases with an accuracy of 74.77% using 15 features. Subsequently, only SWE images were used and as before, the PNN classifier delivered the best result with an accuracy of 87.85% based on 47 features. Finally, we combined SWE and B‐mode USG images. Again, the PNN classifier delivered the best result with an accuracy of 89.72% based on 71 features. These three tests indicate that SWE images contain more diagnostically relevant information when compared with B‐mode USG. Furthermore, there is scope in fusing SWE and B‐mode USG to improve non‐invasive ALN metastasis detection.

Breast cancer is considered as one of the life-threatening disease among woman population in developing as well as developed countries. This specific study reports on classification of breast thermograms using probabilistic neural network (PNN) with four statistical moments features mean, standard deviation, skewness and kurtosis and two entropy features, Shannon entropy and Wavelet packet entropy. The CLAHE histogram equalization algorithm with uniform and Rayleigh distributions were considered for contrast enhancement of breast thermal images. The asymmetry detection was performed by applying bilateral ratio. A total of 95 test images (normal = 53, abnormal = 42) was considered. Simulation study shows that CLAHE -RD with wavelet entropy features confirms the existence of symmetry on the right and left breast thermal images. An overall classification accuracy of 92.5% was achieved using the proposed multifeatures with PNN classifier. The proposed technique thus confirms the suitability as a screening tool for asymmetry detection as well as classification of breast thermograms.

Brain tumour classification using conventional techniques involving human intervention is prone to errors. Errors in feature extraction and/or classification may turn out to be fatal. Hence focus has shifted on automated techniques for the feature extraction and classification of brain tumour images. In the present work, a mechanism for the same has been proposed involving Artificial Neural Networks (ANN). Three categories have been incorporated in the present work, viz. normal brain, brain with benign tumour and brain with malignant tumour. In the present case, MRI images of the brain have been used to train an Artificial Neural Network which subsequently predicts the category of some new MRI data. The key challenge in designing such a system is attaining high accuracy of classification. This can be achieved by accurate feature extraction mechanism and then designing an appropriate Neural Network for training and testing. At the outset, segmentation has been employed to separate the region of the tumour (if any). Later the Discrete Wavelet Transform (DWT) is used as a preprocessing tool. The DWT helps in removing the non linearities of the image signal and smoothen it out. Since images exhibit abrupt changes in pixel values, conventional Fourier methods like the Fourier Transform prove to be unfit for image analysis. Subsequently, features like contrast, correlation, energy, homogeneity, mean, standard deviation, entropy, RMS value, variance, smoothness, kurtosis and skewness have been evaluated. Prior to training the Neural Network using the feature values, Principal Component Analysis (PCA) has been employed to find trends in the feature values. A Probabilistic Neural Network (PNN) has been designed and it has been trained using the feature values. I has been found that brain tumour MRI image are classified into normal, benign and malignant category using PNN classifier with an accuracy of 97% for the used data set which can be attributed to the efficacy of the proposed method. Key Words: Brain Tumor Classification, Machine Learning, Feature Extraction, Neural Networks, Confusion Matrix, Classification Accuracy.

In cloud classification from satellite imagery, temporal change in the images is one of the main factors that causes degradation in the classifier performance. In this paper, a novel temporal updating approach is developed for probabilistic neural network (PNN) classifiers that can be used to track temporal changes in a sequence of images. This is done by utilizing the temporal contextual information and adjusting the PNN to adapt to such changes. Whenever a new set of images arrives, an initial classification is first performed using the PNN updated up to the last frame while at the same time, a prediction using Markov chain models is also made based on the classification results of the previous frame. The results of both the old PNN and the predictor are then compared. Depending on the outcome, either a supervised or an unsupervised updating scheme is used to update the PNN classifier. Maximum likelihood (ML) criterion is adopted in both the training and updating schemes. The proposed scheme is examined on both a simulated data set and the Geostationary Operational Environmental Satellite (GOES) 8 satellite cloud imagery data. These results indicate the improvements in the classification accuracy when the proposed scheme is used.

Parkinson’s disease (PD) is one type of progressive neurodegenerative disease known as motor system syndrome, which is due to the death of dopamine-generating cells, a region of the human midbrain. PD normally affects people over 60 years of age, which at present has influenced a huge part of worldwide population. Lately, many researches have shown interest into the connection between PD and speech disorders. Researches have revealed that speech signals may be a suitable biomarker for distinguishing between people with Parkinson’s (PWP) from healthy subjects. Therefore, early diagnosis of PD through the speech signals can be considered for this aim. In this research, the speech data are acquired based on speech behaviour as the biomarker for differentiating PD severity levels (mild and moderate) from healthy subjects. Feature extraction algorithms applied are Mel Frequency Cepstral Coefficients (MFCC), Linear Predictive Coefficients (LPC), Linear Prediction Cepstral Coefficients (LPCC), and Weighted Linear Prediction Cepstral Coefficients (WLPCC). For classification, two types of classifiers are used: k-Nearest Neighbour (KNN) and Probabilistic Neural Network (PNN). The experimental results demonstrated that PNN classifier and KNN classifier achieve the best average classification performance of 92.63% and 88.56% respectively through 10-fold cross-validation measures. Favourably, the suggested techniques have the possibilities of becoming a new choice of promising tools for the PD detection with tremendous performance.

A method for automatic classification of Arrhythmias from Electrocardiogram based on features generated from a new Continuous Wavelet Transform (CWT) is presented in this paper. The classification performance was studied using the most commonly available database, the MIT-BIH arrhythmia database. The new wavelet for classification was evolved using Genetic Algorithm (GA). The optimum wavelet for classification was obtained after several runs of the GA algorithm. The class labeling was followed according to the Association for the Advancement of Medical Instrumentation (AAMI). The wavelet scales corresponding to the different frequency levels giving maximum classification performance was identified. Probabilistic Neural Network (PNN) classifier was used for classification. The proposed classification system offered an overall sensitivity of 97% for Normal beats (N), 75% for Supraventricular beats (Sv) and 93% for Ventricular beats (V) which is better than existing results reported in literature. This technique could exclusively identify some of the isolated abnormalities compared to other results reported.

Decision support system for fatty liver disease using GIST descriptors extracted from ultrasound images

This paper describes automatic detection and classification of v isual symptoms affected by fungal disease. Algorithms are developed to acquire and process color images of fungal disease affected on commercial crops like chili, cotton and sugarcane. The developed algorith ms are used to preprocess, segment, extract and reduce features fro m fungal affected parts of a crop. The feature extract ion is done with discrete wavelet transform (DWT) and features are further reduced by using Principal co mponent analysis (PCA). Reduced features are then used as inputs to classifiers and tests are performed to classify image samples. We have used statistical based Mahalanobis distance and Probabilistic neural network (PNN) classifiers. The average classification accuracies using Mahalanobis distance classifier are 83.17% and using PNN classifier are 86.48%.

An optical sensor was used to make digital recordings of wingbeat waveforms for the five most common aphids found on Guam: Aphis craccivora Koch, A. gossypii Glover, A. nerii Fonscolombe, Pentalonia nigronervosa Coquerel, and Toxoptera citricida (Kirkaldy). Wingbeat frequencies for each species overlapped all other species. However, mean wingbeat frequencies were significantly different for all species. Wingbeat frequencies and harmonic patterns were extracted from the recordings and submitted to cluster analysis, which failed to separate species completely. Several nearest neighbor and probabilistic neural network classifiers were built using time series, frequency spectra, wingbeat frequencies, and harmonic patterns as input variables. These classifiers were evaluated by having them identify wingbeat waveforms from aphids collected and recorded after their construction. The best performing classifier model was a probabilistic artificial neural network trained using 256-bin frequency spectra as input. Sixty-nine percent of the waveforms presented to this network were identified correctly. This study demonstrates the feasibility of developing an insect flight monitor that automatically counts and identifies individual flying insects. Essential components of the monitoring system are a photosensor, a multimedia personal computer, and software that identifies wingbeat frequency spectra using an artificial neural network.

Sentence alignment using P-NNT and GMM