Support Vector Machine Theory Research Articles

Quantitative Detection and Long-Term Monitoring of Settle Dust Using Semisupervised Learning for Spectral Data

Classification of spectral data has recently drawn more and more attention in environmental and geoscience applications. In the past decade, this attention has been translated into an interest in employing unmixing techniques to retrieve accurate quantitative information suppressed in spectral data. The main task in real applications is to detect potential information regarding the physical and chemical nature of ground targets in different spectral data sources (point field and laboratory spectroscopy, hyperspectral imagery, etc.). Recently, semisupervised classification techniques have been proposed for spectral data by combining ground-truth and laboratory measured spectral signatures and advanced signal processing algorithms based on posterior probability support vector machine and Dempster-Shafer evidence theory. In this paper, the sensitivity of this combined classification method to extract and identify a small amount of settle dust over green vegetation canopy using field spectral data is examined and reported. The results are compared with the performance of selected semisupervised unmixing classification techniques.

Hybrid safety analysis method based on SVM and RST: An application to carrier landing of aircraft

To reduce landing mishap risk, one of the greatest challenges is how to accurately determine whether a landing process is safe or not. This paper presents a landing safety analysis method based on a combination of support vector machine (SVM) and rough set theory (RST). In this hybrid approach, the carrier landing data are first analyzed with RST to identify parameters that are sensitive to changes in the state of landing safety. With a landing data set composed of the identified sensitive parameters, the SVM model is trained and the optimal separating hyperplane is obtained to distinguish between the two classes of landing samples (i.e., safe and hazardous), so as to establish the relationship between landing parameters and safety. 635 real landing samples of the aircraft carrier USS Enterprise (CVN 65) are used in the case study, and it is shown that the proposed method is able to identify those parameters contributing more significantly to landing safety and thus deserving more attention paid to. Furthermore, the hyperplane is used as a basis for formulating landing parameter design and control requirements, so that the landing parameters match well and safe landing is guaranteed.

Signal Detection of Welding Joint Flaw Based on Wavelet-Support Vector Machine

The friction welded joints made by GH4169 heat metal alloys are detected by U1traPAC system of the ultrasonic wave explore instrument. Aimed at the blemish signal characteristics, this article introduce Support Vector Machine (SVM) theory, which is based on statistical theory and structural risk minimization principle, to carry out multi-classification study of the detection signal. We decompose de-noising signals with wavelet packet transform, and extract energy eigenvalues according to "energy- defects". In accordance with designed "1-to-v" SVMs scheme, we respectively input normalized eigenvector to the SVM model to obtain the Forecast data. It is verificated that the limited existing data and information is well used by SVM and the signal is accurately been classificated. All of these verify that SVM has a strong generalization ability.

Interpreting support vector machine models for multivariate group wise analysis in neuroimaging

Machine learning based classification algorithms like support vector machines (SVMs) have shown great promise for turning a high dimensional neuroimaging data into clinically useful decision criteria. However, tracing imaging based patterns that contribute significantly to classifier decisions remains an open problem. This is an issue of critical importance in imaging studies seeking to determine which anatomical or physiological imaging features contribute to the classifier's decision, thereby allowing users to critically evaluate the findings of such machine learning methods and to understand disease mechanisms. The majority of published work addresses the question of statistical inference for support vector classification using permutation tests based on SVM weight vectors. Such permutation testing ignores the SVM margin, which is critical in SVM theory. In this work we emphasize the use of a statistic that explicitly accounts for the SVM margin and show that the null distributions associated with this statistic are asymptotically normal. Further, our experiments show that this statistic is a lot less conservative as compared to weight based permutation tests and yet specific enough to tease out multivariate patterns in the data. Thus, we can better understand the multivariate patterns that the SVM uses for neuroimaging based classification.

Preliminary Discussion Regarding SVM Kernel Function Selection in the Twofold Rock Slope Prediction Model

AbstractThe kernel function, which is an important component of support vector machine (SVM) theory, directly affects the results of a prediction model. When establishing an effective prediction slope model, analysis factors such as slope angle, slope height, potential sliding body height and inclination, and cohesion and friction angle of each potential sliding surface need to be considered. As the results of an example design show, there is an appropriate regularity between analysis factors and kernel functions. For example, the radial basis function (RBF) kernel function is suitable for the geometry factors of a rock slope analysis, whereas the Sigmoid kernel function is better than RBF for analyzing the cohesion and friction angle of the back potential sliding surface; likewise, the linear kernel function is suitable for the material factors of a bottom sliding surface analysis. For these reasons, a combination of kernel functions is necessary for an overall analysis of complex rock slope problems. A ...

Thorough robot navigation based on SVM local planning

A prerequisite for autonomous robot navigation is the extraction of a path that is both efficient and safe in terms of collision. Towards this end, the paper in hand presents a novel local path planning method, incorporating the support vector machines (SVM) theory. The original SVM based module exploits a 2D map of points which are considered to be obstacles, so as to culminate in a collision free path. A unique attribute of the proposed SVM based local path planning algorithm is that it considers the consecutive positions of the global path trajectory, the embodiment of the robot and clusters the obstacles accordingly. Thus, the derived trajectory is a physically constrained path inasmuch as it considers the maximum margin notion of the SVM theory. Instead of providing a purely theoretical approach for local planning assessed using only artificial data, we integrate our local planner into an autonomous navigation system which is evaluated in real-world scenarios in order to show its efficacy. The latter framework firstly constructs a global 3D metric map of the perceived environment and then it converts it into a 2D map upon which a global path planner unrolls. The global map grows incrementally, by registering the collected point clouds over the robot’s route towards a goal position. Moreover, the navigation is supported by an obstacle detection strategy based on v-disparity images. The system–and, consequently, the presented local path planner–was evaluated in long range outdoors scenarios, navigating successfully within congestive environments.

Method and experiment of rainfall intensity inversion using a microwave link based on support vector machine

The precipitation is an important physical phenomenon. The real-time, accurate measurement of rainfall intensity has important significance in meteorological support, agriculture, weather forecasting, transportation industry and military mission. However, current methods, such as the rain gauge, the weather radar and meteorological satellite, are unable to meet the needs in all the areas above at present. The network of rain gauge is costly. Meanwhile, rain gauge has low spatial and temporal resolution. And the weather radar has a big deviation because of the ground clutter. Besides, the meteorological satellite is unable to measure the surface rainfall. Thus, a method of using the measurement of microwave rain-induced attenuation for rainfall estimation has been presented in meteorological field recently by meteorological experts and it has made some progress. The method based on microwave link has low cost because of using preexisting microwave device. There are also many preexisting microwave transmission networks, which can be used by rainfall field inversion in the future research. The method measures rainfall intensity more accurately because the propagation path of microwave is close to the surface. Many models for inversing rainfall intensity by rain-induced microwave attenuation have been put forward on account of the method advantages. The commonly used model for inversion of rain rate is given by International Telecommunication Union (ITU). However, the model presented by ITU ignores a number of meteorological factors such as temperature, humidity and air pressure, which to some degree reduces the accuracy of the rainfall inversion based on microwave link. Thus, based on the theory of support vector machine (SVM), an inversion method of the path rainfall intensity by using a microwave link is proposed. Starting from the theory of Mie scattering and the atmospheric gas absorption attenuation model, a model of rainfall intensity inversion of line-of-sight microwave links is proposed, which is based on support vector machine, the microwave rain attenuation characteristics and the Gamma drop-size distribution. One line-of-sight microwave link is designed and used to measure the microwave rain-induced attenuation and inverse rainfall. Compared with actual rainfall intensity measured by a disdrometer, inversion rainfall intensity shows a satisfactory result. The correlation coefficient of rain rate is inversed by microwave link based on SVM and that of disdrometer is higher than 0.6 mostly, and the maximum value is 0.9674; the minimum value of the root-mean-square error of the rain rate is 0.5780 mm/h; the minimum value of the error of accumulated rain amount is 0.0080 mm; the relative error of accumulated rain amount is less than 10% and its minimum value is 0.7425%. All these parameters above are superior to ITU's. Therefore, the inversion result demonstrates the validity, feasibility and accuracy of rainfall inversion model using a microwave link based on SVM. The model we present is of great significance for further improving the accuracy of inversion of rain rate based on microwave link and rainfall monitoring.

A Study on Fault Detection Method of Redundant Inertial Navigation System on Micro AUV

In order to improve the precision and reliability of the autonomous underwater vehicle (AUV) inertial navigation system, a redundant inertial measurement unit (RIMU) based on micro electromechanical system (MEMS) inertial sensors has been designed, then use support vector machine theory (SVM),construct multi-fault classifier training and combine three-step search parameter optimization method,to achieve rapid, automatic fault detection and isolation (FDI). With Monte Carlo simulation and experimental analysis, SVM method has more obvious advantages than conventional Generalized Likelihood ratio Test (GLT) on false alarm rate, undetected rate and correct isolation rate for common fault sources of RIMU, and can detect and identify the type and number of failure more effectively on redundant systems, and provide a guarantee for fault sensors isolation.

Resource Scheduling Optimization Model in Cloud Computing Environment

In the process of cloud computing, the dynamic hierarchical resource index is researched, and the independent confusion cloud computing is studied. This problem has become the focus of data processing. Therefore, it needs to establish improved dynamic layered resource index independent confuse cloud computing model. According to the theory of support vector machine, all of the resources are taken with dynamical layered processing, different levels of resources are taken with the independent confusion cloud computing. The experiment results show that, this algorithm is taken for the dynamic layered resource cloud computing, calculation efficiency can be improved, computational complexity and redundancy are reduced, meet the practical demands of dynamic hierarchical resource index independent confused cloud computing. It has good application value in the cloud computing application.

Support Vector Machine and its Application Status

Support vector machine is a beginning of the 1990s, based on statistical learning theory proposed new machine learning method, which structural risk minimization principle as the theoretical basis, by appropriately selecting a subset of functions and discriminant function in the subset, so the actual risk of learning machine to a minimum, to ensure that the limited training samples obtained through a small error classifier, an independent test set for testing error remains small. In this paper, support vector machine theory, algorithm, application status, etc. are discussed in detail.

Prediction of Classification of Rock Burst Risk Based on Genetic Algorithms with SVM

Due to the complex features of rock burst hazard assessment systems, a support vector machine (SVM) model for predicting of classification of rock burst was established based on the SVM theory and the actual characteristics of the project in this study. The main factors of rock burst, such as coal seam, dip, buried depth, structure situation, change of pitch angle, change of coal thickness, gas concentration, roof management, pressure relief and shooting were defined as the criterion indices for rock burst prediction in the proposed model. In order to determine reasonable and efficient the parameters of SVM, Firstly, the appropriate fitness function for genetic algorithms (GA) operation was determined, and then optimization parameters of SVM model were selected by real coded GA, therefore, the genetic algorithms and support vector machine (GSVM) model was established. A GSVM model was obtained through training 23 sets of measured data, the cross-validation method was introduced to verify the stability of GSVM model and the ratio of mis-discrimination is 0. Moreover, the proposed model was used to predict 12 new samples rock burst, the correct rate of prediction results is 91.6667% and are identical with actual situation. The results show that the genetic algorithm can speed up SVM parameter optimization search, the proposed model has a high credibility in the study of rock burst prediction of risk classification, which can be applied to practical engineering.

Wind Speed Forecasting Based on Least Squares Support Vector Machine and Particle Swarm Optimization

This paper is based on Least Squares Support Vector Machine theory to build the wind speed forecasting model. Meanwhile, as there is still no effective choice method of Least Squares Support Vector Ma-chine parameter, this paper tried to use Particle Swarm Optimization theory to optimization choice for parameter. And last, use wind farm observed wind speed (sampling interval is 1 minute) of three days to forecast the next minute wind speed through this paper's wind forecasting model, and prediction result is that the MAPE is only 4.63%, the prediction effect is relative ideal, confirm the feasibility of applying the Particle Swarm Optimization Algorithm and Least Squares Support Vector Machine theory to forecast the wind speed, it will provide theoretical support to wind farm layout and wind power forecasting and so on.

The Connector Blanking Fracture Surface Quality Prediction in Progressive Stamping Based on Support Vector Machine

The influencing factors of technical parameters on blanking fracture surface quality are quite few and complicated, including clearance, speed, die roughness and punch radius. And determination of these influencing factors and optimization of the process parameters combination are vital to the blanking with stability and duration. The determination of these parameters depending on experience of designer in production leads to a longer development period and higher cost in testing modes. In the current study, a kind of prediction method for fracture surface quality was put forward by using nonlinear mapping properties and learning capacity of the support vector machine theory in which nonlinear input can be mapped into higher dimensional space by selecting kernel function RBF, and compromise parameter with C=0, and expectation error of ε=0. 1. The final production model was obtained by practice with orthogonal experiment of four factors times three levels. Experimental verification was conducted by selecting a number of test data. Results have shown that the predicted values were in good agreement with those from tests.

The Study and Application of Middle School Teacher Evaluation System Based on Support Vector Machine

In this paper, the Support Vector Machine (SVM) theory is applied to secondary school teachers evaluation systems. And the evaluation attributes of secondary school teachers are set in accordance with certain requirements. Through the use of sample data on the teacher evaluation system for a certain amount of training, we get a trained model, then evaluate and analyze the teachers data to be measured. This approach can make secondary school teachers assessment more accurate and reasonable, greatly reduce the workload of teaching management, and reduce the number of artificially errors in the evaluation process.

Classification With Support Vector Machines and Kolmogorov–Smirnov Bounds

This article presents a new statistical inference method for classification. Instead of minimizing a loss function that solely takes residuals into account, it uses the Kolmogorov–Smirnov bounds for the cumulative distribution function of the residuals, as such taking conservative bounds for the underlying probability distribution for the population of residuals into account. The loss functions considered are based on the theory of support vector machines. Parameters for the discriminant functions are computed using a minimax criterion, and for a wide range of popular loss functions, the computations are shown to be feasible based on new optimization results presented in this article. The method is illustrated in examples, both with small simulated data sets and with real-world data.

Research on License Plate Recognition Algorithm based on Support Vector Machine

Support Vector Machine (SVM) as an important theory of machine learning and patternrecognition has been well applied to small sample clustering learning, nonlinear problems, outlierdetection and so on. The license plate automation recognition system has received extensiveattention as an important application of machine learning and pattern recognition in intelligent transport.The license plate recognition system is composed of three parts, license plate preprocessing and location, license plate character segment, license plate character recognition. In this paper, we mainly introduce the flow of license plate recognition, related technology and support vector machinetheory. Experimental results show the effectiveness of our method.

Quantitative Diagnosis of Rotor Vibration Fault Using Process Power Spectrum Entropy and Support Vector Machine Method

To improve the diagnosis capacity of rotor vibration fault in stochastic process, an effective fault diagnosis method (named Process Power Spectrum Entropy (PPSE) and Support Vector Machine (SVM) (PPSE-SVM, for short) method) was proposed. The fault diagnosis model of PPSE-SVM was established by fusing PPSE method and SVM theory. Based on the simulation experiment of rotor vibration fault, process data for four typical vibration faults (rotor imbalance, shaft misalignment, rotor-stator rubbing, and pedestal looseness) were collected under multipoint (multiple channels) and multispeed. By using PPSE method, the PPSE values of these data were extracted as fault feature vectors to establish the SVM model of rotor vibration fault diagnosis. From rotor vibration fault diagnosis, the results demonstrate that the proposed method possesses high precision, good learning ability, good generalization ability, and strong fault-tolerant ability (robustness) in four aspects of distinguishing fault types, fault severity, fault location, and noise immunity of rotor stochastic vibration. This paper presents a novel method (PPSE-SVM) for rotor vibration fault diagnosis and real-time vibration monitoring. The presented effort is promising to improve the fault diagnosis precision of rotating machinery like gas turbine.

Cloud Monitoring for Solar Plants with Support Vector Machine Based Fault Detection System

This study endeavors to develop a cloud monitoring system for solar plants. This system incorporates numerous subsystems, such as a geographic information system, an instantaneous power-consumption information system, a reporting system, and a failure diagnosis system. Visual C# was integrated with ASP.NET and SQL technologies for the proposed monitoring system. A user interface for database management system was developed to enable users to access solar power information and management systems. In addition, by using peer-to-peer (P2P) streaming technology and audio/video encoding/decoding technology, real-time video data can be transmitted to the client end, providing instantaneous and direct information. Regarding smart failure diagnosis, the proposed system employs the support vector machine (SVM) theory to train failure mathematical models. The solar power data are provided to the SVM for analysis in order to determine the failure types and subsequently eliminate failures at an early stage. The cloud energy-management platform developed in this study not only enhances the management and maintenance efficiency of solar power plants but also increases the market competitiveness of solar power generation and renewable energy.

Study of Driver's Gaze Behavior Recognition

The reliability and accuracy of driver gaze behavior detection was improved by the multi-dimensional feature fusion method. In view of the effects of the complexity of the driving environment, a variety of working conditions and the diversity of gaze behavior characteristics,with support vector machine (SVM) theory technique, the multi-dimensional feature decision-level fusion was proposed to estimate the different kind model of the driver's gaze behavior. The results show that the T characteristic curve proposed by the gaze behavior parameters of the transverse width between the eyes and the vertical distance between mouth and the midpoint of two eyes, combined with the driver's eyelid closure and the proportion and location characteristics of iris-sclera were studied to get the characterization of the driver gaze status. The simulation results indicate that the adaptability and accuracy as well as the intelligence level of the bad fixation characterization information screening are significantly improved by using the pattern classification and decision technology of multi-dimensional feature fusion.

Consumer Purchasing Behavior Extraction Using Statistical Learning Theory

Consumers classification is one of the most important task in the retail sector. RFID (Radio Frequency IDentification) - A wireless non-contact technology is made easier to classify the consumers’ in-store behavior, recently. This paper presents an extraction of consumer purchasing behavior using statistical learning theory SVM (Support Vector Machine). In this research, we present our recent investigation outcome on the consumers shopping behavior in a Japanese supermarket using RFID data. We observe that it is possible to express the individual difference of consumers how are they spending time (we call it stay time in this paper) on shopping in a certain area of the supermarket. The contribution of this research is in two folds: we employ a SVM model on dealing with the RFID data of the consumer in-store behaviour firstly, as compared with other forecast model such as linear regression analysis and bayesian network, SVM provides a significant improvement in the forecasting accuracy of purchase behaviour (from 81.49% to 88.18%). Secondly, the kernel trick is adopted inside the SVM theory to choose the appropriate kernel for consumer purchasing behavior extraction.