Support Vector Machine For Detection Research Articles

Robust principal component analysis and support vector machine for detection of microcracks with distributed optical fiber sensors

Development of a method for distributed detection of microcracks on structural elements with very small crack opening displacements is described in this study. Robust principal component analysis (RPCA) and support vector machine (SVM) techniques were employed for denoising and classification of the signals. The objective was to detect microcracks in structural elements less than 30 µm in size. The viability of the method was accomplished by experiments involving a 15-meter steel beam with known microcracks. A distributed optical fiber sensor system based on the Brillouin scattering technology was employed for distributed measurement of strains along the length of the 15-m long beam. Distributed strain signals based on Brillouin based sensors possess inherent system noise and ambient perturbations which in turn reduce the signal-to-noise ratio of the measurements. Therefore, it is not possible to detect the smaller microcracks with small crack opening displacements. Smaller CODs are lost within the noisy distributed strain signal acquired by the Brillouin system. Undetected microcracks result in larger cracks, corrosion, and other anomalies with severe economical and safety ramifications.The method introduced for denoising and enhancement of the signal in the present study enables manifestation of the singularities on the distributed strain data and detection of microcracks. The significant component containing those singularities is effectively separated from the noise component by RPCA-based matrix decomposition. An SVM classifier with Gaussian kernel function was designed, through which the crack detections are realized by singular and nonsingular binary classification. The experimental results demonstrated that it was possible to detect microcracks with CODs as low as 23 µm without errors.

Digital image technology based on PCA and SVM for detection and recognition of foreign bodies in lyophilized powder.

BACKGROUND: Digital image technology has made great progress in the field of foreign body detection and classification, which is of great help to drug purity extraction and impurity analysis and classification.OBJECTIVE: The detection and classification of foreign bodies in lyophilized powder are important. The method which can obtain a higher accuracy of recognition needs to be proposed.METHODS: We used digital image technology to detect and classify foreign bodies in lyophilized powder, and studied the process of image preprocessing, median filtering, Wiener filtering and average filtering balance to better detect and classify foreign bodies in lyophilized powder.RESULTS: Through industrial small sample data simulation, test results show that in the process of image preprocessing, 3 3 median filtering is best. In the aspect of foreign body recognition, the recognition based on principal component analysis (PCA) and support vector machine (SVM) algorithm and the recognition based on PCA and Third-Nearest Neighbor classification algorithm are compared and results show that the PCASVM algorithm is better.CONCLUSION: We demonstrated that integrating PCA and SVM to classify foreign bodies in lyophilized powder. Our proposed method is effective for the prediction of essential proteins.

High impedance fault detection and isolation in power distribution networks using support vector machines

This paper proposes an accurate High Impedance Fault (HIF) detection and isolation scheme in a power distribution network. The proposed scheme utilizes the data available from voltage and current sensors. The technique employs multiple algorithms consisting of Principal Component Analysis, Fisher Discriminant Analysis, Binary and Multiclass Support Vector Machine for detection and identification of the high impedance fault. These data-driven techniques have been tested on IEEE 13-node distribution network for detection and identification of high impedance faults with the broken and unbroken conductor. Further, the robustness of machine learning techniques has also been analysed by examining their performance with variation in loads for different faults. Simulation results for different faults at various locations have shown that proposed methods are fast and accurate in diagnosing high impedance faults. Multiclass Support Vector Machine gives the best result to detect and locate high impedance faults accurately. It ensures reliability, security and dependability of the distribution network.

Using Non-Linear Support Vector Machines for Detection of Activities of Daily Living

Activities of Daily Living (ADL) refers to different daily routine type activities which includes walking, running, jogging, standing, sitting etc. Recognition of ADLs has been of considerable interest to researchers for health assessment purposes. Furthermore, since more and more people choose to live alone in their house. ADL recognition serves as the first step towards developing a monitoring system for such people. This work proposes an algorithm that can be used to perform ADL detection using three types of data from inertial sensors (accelerometer, gyroscope and orientation) captured using a smart phone using non-linear Support Vector Machines. We have used a representative dataset named MobiACT and extracting sensor readings for a 10s window, Autoregression modeling has been used to model the sensor readings and we have detected six types of ADLs using a Support Vector Machine. We achieve an overall detection accuracy of 97.45%. The given method has been tested and proven to outperform other algorithms for the purpose of activity recognition. Keywords: Activities of Daily Living, Autoregressive Modelling, Inertial Sensor, Mobiact

Wavelet Entropy and Directed Acyclic Graph Support Vector Machine for Detection of Patients with Unilateral Hearing Loss in MRI Scanning.

Highlights We develop computer-aided diagnosis system for unilateral hearing loss detection in structural magnetic resonance imaging.Wavelet entropy is introduced to extract image global features from brain images. Directed acyclic graph is employed to endow support vector machine an ability to handle multi-class problems.The developed computer-aided diagnosis system achieves an overall accuracy of 95.1% for this three-class problem of differentiating left-sided and right-sided hearing loss from healthy controls. Aim: Sensorineural hearing loss (SNHL) is correlated to many neurodegenerative disease. Now more and more computer vision based methods are using to detect it in an automatic way.Materials: We have in total 49 subjects, scanned by 3.0T MRI (Siemens Medical Solutions, Erlangen, Germany). The subjects contain 14 patients with right-sided hearing loss (RHL), 15 patients with left-sided hearing loss (LHL), and 20 healthy controls (HC).Method: We treat this as a three-class classification problem: RHL, LHL, and HC. Wavelet entropy (WE) was selected from the magnetic resonance images of each subjects, and then submitted to a directed acyclic graph support vector machine (DAG-SVM).Results: The 10 repetition results of 10-fold cross validation shows 3-level decomposition will yield an overall accuracy of 95.10% for this three-class classification problem, higher than feedforward neural network, decision tree, and naive Bayesian classifier.Conclusions: This computer-aided diagnosis system is promising. We hope this study can attract more computer vision method for detecting hearing loss.

Support vector machines for detection of electrocardiographic changes in partial epileptic patients

The aim of this study is to evaluate the diagnostic accuracy of the support vector machines (SVMs) on the electrocardiogram (ECG) signals. Two types of ECG beats (normal and partial epilepsy) were obtained from the MIT-BIH database. Post-ictal heart rate oscillations were studied in a heterogeneous group of patients with partial epilepsy. Decision making was performed in two stages: feature extraction by computing the wavelet coefficients and classification using the classifier trained on the extracted features. The purpose was to determine an optimum classification scheme for this problem, and also to infer clues about the extracted features. The present research demonstrated that the wavelet coefficients are the features, which well represent the ECG signals, and the SVMs trained on these features achieved high classification accuracies (total classification accuracy was 99.44%).

Composite support vector machines for detection of faces across views and pose estimation

Abstract Support vector machines (SVMs) have shown great potential for learning classification functions that can be applied to object recognition. In this work, we extend SVMs to model the appearance of human faces which undergo non-linear change across multiple views. The approach uses inherent factors in the nature of the input images and the SVM classification algorithm to perform both multi-view face detection and pose estimation.

Support vector machines for detection and characterization of rolling element bearing faults

Support vector machines for detection and characterization of rolling element bearing faults

Support vector machines for detection and characterization of rolling element bearing faults

Artificial neural networks (ANNs) have been used to detect faults in rotating machinery for a number of years, using statistical estimates of the vibration signal as input features, and they have been shown to be highly successful in this type of application. Support vector machines (SVMs) are a more recent development, and little use has been made of them in the condition monitoring (CM) arena. The availability of a limited amount of training data creates some problems for the use of SVMs, and a strategy is offered that improves the generalization performance significantly in cases where only limited training data are available. This paper examines the performance of both types of classifier in one given scenario—a multiclass fault characterization example.