Papers by Keyword: Feature Extraction

Abstract: — Thermal imaging technique is a very convenient, versatile and non-contact method which has been used for fault condition diagnosis of electrical equipment. The fault condition diagnosis is composed with data acquisition, data pre-processing, data analysis and decision making. Some important features contain in thermal image can be extracted for equipment condition monitoring and fault diagnosis. This paper attempts to extract some important features from the zinc oxide (ZnO) surge arrester using first order statistical histogram extraction to classify the fault condition using neural network. The experimental work was carried out to capture thermal image of 120 kV rated ZnO surge arrester. The thermal images were segmented and plotted histogram using dedicated software. Some features such as the maximum, minimum, mean, standard deviation, and variance were extracted using the extraction method, classification of aging was carried out using the neural network based on the leakage current values. The health states consist of normal, defection and faulty. The results show that the thermal image features extracted using the extraction method can be used to classify the fault condition of the ZnO surge arresters

Abstract: This research presents a model for malware detection on mobile operating system based on analyzing the operation codes. The research processes are as follows: (1) achieving of both malicious and benign codes on android operating system, (2) extracting features based on the distribution of n-grams frequency where the parameter n = 3 is used, and (3) constructing a model for classification the malicious codes using the extracted features for both malicious and benign codes. In the experiment, 304 malicious codes and 553 benign codes were using to construct the model. The experiment shows that the model achieved more than 85.52% accuracy. For the sensitivity and specificity, the model achieved 71.26% and 90.52%, respectively.

Abstract: A statistical measure is needed to estimate a probability density function (PDF) of EMG signals to choose the suitable feature extraction methods for EMG pattern recognition system. The utility of L-kurtosis was investigated in estimating the PDFs of three different dynamic EMG involving transient and steady-state signals during four hand motions measured from two forearm muscles, and was compared with the kurtosis. The results show that the L-kurtosis can identify the PDF of EMG for all cases. In contrast, the kurtosis is inaccuracy and less robust when measured EMG signals have a higher amplitude and are more non-stationary during a transient period.

Abstract: Application of Fast Fourier Transform (FFT) in machinery faults detection is known to be only effective if fault is of repetitive in nature and considering severe. While minor and transient faults are usually remain undetected based on vibration spectrum analysis. Wavelet analysis is relatively new technique which is still suffered from inadequately in its time-frequency resolution. In this paper, ahmedrabak_time wavelet is proposed based on the wavelet reassignment technique for Morlet mother wavelet. The proposed wavelet analysis is compared to the conventional wavelet analysis for machinery faults detection based on simulated signal. The results showed that the proposed wavelet has a better resolution than conventional wavelet analysis which could clearly indicate the presence and the location of the fault.

Abstract: In the paper, design and Implementation of cloud-dust based intelligent system is proposed. For achieving applications of intelligent system, such as records, surveillance, assessments, predictions, diagnosis, prescription, scheduling and fool-proofing checks, an architecture named Cloud-Dust is developed. The intelligent system is separated into the cloud system and the dust system. The dust system contains (1) Wireless sensors network (2) Features extraction circuits (3) Intelligent computing circuits (4) Embedded system. It can play a role as real-time preprocessor very well, just like an intelligent agent. However, the cloud system contains (1) Cloud database (2) Intelligent computing engine (3) Ubiquitous human-machine-interface. It can flexibly use computing resources and integrate information from many different dust systems. By the experiments, we can find the advantages of the cloud-dust based intelligent system. It meets the both needs of real-time and integration for intelligent systems. So it is necessary to develop the cloud-dust based system for design and implementation of the intelligent system.

Abstract: Health assessment and fault diagnosis for rolling bearings mostly adopt traditional methods, such as time-frequency, spectral, and wavelet packet analyses, to extract the feature vector. These methods are suitable for processing data with a linear structure. However, for the non-linear and non-stationary signal, the result of these methods is not ideal. Thus, this study proposes a suitable method to extract the feature vector in nonlinear signals. Local tangent space alignment of a manifold algorithm is employed to extract the feature vector from the rolling bearings. Results verify the advantage of the manifold algorithm for non-linear and non-stationary signals.

Abstract: Extracting acceleration of boost phase is the key technology of establishing the ballistic profiles. An algorithm based on orthogonal curve fitting is presented to extract acceleration of boost phase, using the line of sight (LOS) measurements. Then, an error model is established and the theoretical error of the method is analyzed. The new fitting method improves the curve fitting error of the terminals. Sufficient simulations on some typical scenarios are performed, and the results indicate that the method presented is efficient.

Abstract: Singular Value Decomposition used in spectrum feature extraction, often discards small component that may be important for identifying mineral oil products. This work presents a new method using the Singular Value Division (SVD) on Wavelet Transform (WT) with three-dimensional fluorescence spectra as the source of oil features. WT-SVD feature based fuzzy classification (FCM) is implemented and comparable or better results are yielded in more accurate, and more robust than SVD performance under random noise conditions. The result means that WT-SVD method can strike a balance between data compression and preservation of small valid information in feature extraction of three-dimensional fluorescence spectra of mineral oils. This method is conducive to oil discrimination and pollution analysis in water environment monitoring.

Abstract: In order to study different types of partial discharge inspired by defects in GIS and increase the rate of correct identification on defects, four kinds of typical insulation defects physical model are designed based on the insulation defects of 110 kV GIS and its partial discharge characteristics. Ten feature parameters including the signal peak and kurtosis are acquired from 222 groups of partial discharge signal data, and recognized by BP neural network which is optimized by input genetic algorithm. Recognition results show that this method works well, owning a higher recognition rate than adaptive momentum BP neural network

Abstract: This paper proposes a new method of image recognition based on the theory of high-dimensional information geometry. Firstly, we used the linear algebra to describe the high-dimensional information geometry and studied the effectiveness of included angle cosine in different dimensional spaces. Secondly, the image could be expressed as a vector and the cosine value of angle between two vectors was used as the discriminant conditions of classifier to identify images. Finally, a face recognition system extracting facial features based on a fast principal component analysis (PCA) was designed, using Euclidean distance and included angle cosine value to measure the nearest neighbor classifier respectively for comparision. The experiments results proved that the proposed method has a higher accuracy and better performance than a traditional recognition system.