Extreme Learning Machine-based Differential Evolution Feature Selection Approach for Feature Subset Selection from Digital Images

In the deregulated power systems, the available transfer capability (ATC) should be known for secure and reliable operation. ATC mainly depends on load for a particular transaction. Due to complex nature of load, it is better if the ATC estimator is able to handle this complex nature. This paper presents fully complex-valued radial basis function (FC-RBF) neural network approach for ATC estimation for bilateral transaction under normal condition. The training patterns for neural network are generated using differential evolution algorithm (DEA). The important feature of the proposed method is the use of input reduction techniques to improve the performance of the developed network. Differential evolution feature selection (DEFS) technique is proposed to reduce the complexity and training time of neural network. The proposed method is tested on IEEE 118 bus system, and results are compared with DEA and repeated power flow (RPF) results. The test results show that the proposed method reduces the training time and it is suitable for online application.

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.

In this paper, a synthesized algorithm for flaw classification in ultrasonic guided waves signal is presented, in which Wavelet Transform is utilized in the process of noise suppression and envelop extraction, and the Probabilistic Neural Network (PNN) is introduced for flaw classification of the ultrasonic testing signal. Besides, in the process of feature extraction, the necessity of attenuation correction and feature selection of ultrasonic signal is discussed. The comparison of the performances of PNN and BP classifier is made in the last chapter, which demonstrates that the performance of flaw classification is significantly improved by the synthesized algorithm presented in this paper.

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.

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.

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.

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.

This paper presents transient stability assessment of a large actual power system using the probabilistic neural network (PNN) with enhanced feature selection and extraction method. The investigated large power system is divided into five smaller areas depending on the coherency of the areas when subjected to disturbances. This is to reduce the amount of data sets collected for the respective areas. Transient stability of the power system is first determined based on the generator relative rotor angles obtained from time domain simulations carried out by considering three phase faults at different loading conditions. The data collected from the time domain simulations are then used as inputs to the PNN. An enhanced feature selection and extraction methods are then incorporated to reduce the input features to the PNN which is used as a classifier to determine whether the power system is stable or unstable. It can be concluded that the PNN with enhanced feature selection and extraction methods reduces the time taken to train the PNN without affecting the accuracy of the classification results.

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.

In this proposed work, the moving object is localized using curvelet transform, soft thresholding and frame differencing. The feature extraction techniques are applied on to the localized object and the texture, color and shape information of objects are considered. To extract the shape information, Speeded Up Robust Features (SURF) is used. To extract the texture features, the Enhanced Local Vector Pattern (ELVP) and to extract color features, Histogram of Gradient (HOG) are used and then reduced feature set obtained using genetic algorithm are fused to form a single feature vector and given into the Extreme Learning Machine (ELM) to classify the objects. The performance of the proposed work is compared with Naive Bayes, Support Vector Machine, Feed Forward Neural Network and Probabilistic Neural Network and inferred that the proposed method performs better.

Quality based classification of gasoline samples by ATR-FTIR spectrometry using spectral feature selection with quadratic discriminant analysis

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.

Sentence alignment using P-NNT and GMM

Determining different mentions of chemical names from texts has a wide-spread application in real life. Chemical names are complex in nature and there exist several representations and nomenclatures (like SMILES, InChI, IUPAC) which create a big challenge to their automatic identification and classification. In this paper we present a feature selection approach for appropriate feature subset selection from a well-known supervised machine learning approach namely conditional random field based classifier (CRF). Several features are identified and extracted without using any domain specific knowledge and/or resources for determining mentions of IUPAC and IUPAC-like names from scientific text using some supervised classification technique. The appropriate set of features for a particular supervised classification technique is extracted from this huge collection of features using some single objective genetic algorithm based feature selection technique. Experiments are carried out on the benchmark patent dataset. Evaluation shows encouraging performance with the overall F-measure values of 70.01% by single objective optimization based approach on patent 2008 test data set.

Despite the great benefits accruable from the debut of computer and the internet, efforts are constantly being put up by fraudulent and mischievous individuals to compromise the integrity, confidentiality or availability of electronic information systems. In Cyber-security parlance, this is termed ‘intrusion’. Hence, this has necessitated the introduction of Intrusion Detection Systems (IDS) to help detect and curb different types of attack. However, based on the high volume of data traffic involved in a network system, effects of redundant and irrelevant data should be minimized if a qualitative intrusion detection mechanism is genuinely desirous. Several attempts, especially feature subset selection approach using Bee Algorithm (BA), Linear Genetic Programming (LGP), Support Vector Decision Function Ranking (SVDF), Rough, Rough-DPSO, and Mutivariate Regression Splines (MARS) have been advanced in the past to measure the dependability and quality of a typical IDS. The observed problem among these approaches has to do with their general performance. This has therefore motivated this research work. We hereby propose a new but robust algorithm called membrane algorithm to improve the Bee Algorithm based feature subset selection technique. This Membrane computing paradigm is a class of parallel computing devices. Data used were taken from KDD-Cup 99 Dataset which is the acceptable standard benchmark for intrusion detection. When the final results were compared to those of the existing approaches, using the three standard IDS measurements-Attack Detection, False Alarm and Classification Accuracy Rates, it was discovered that Bee Algorithm-Membrane Computing (BA-MC) approach is a better technique. This is because our approach produced very high attack detection rate of 89.11%, classification accuracy of 95.60% and also generated a reasonable decrease in false alarm rate of 0.004. Receiver Operating Characteristic (ROC) curve was used for results interpretation.