Support Vector Machine Theory Research Articles

The Application of Support Vector Machine in Load Forecasting

The forecasting to mid-long term load is important because it can provide important evidence to the power planning. Traditional forecast techniques apply a single forecaster to carry out the task. However, this forecaster might not be the best for all situations or databases. A combinational model on the basis of Support Vector Machine (SVM) theory is proposed in this paper. During the process of the forecast, several single forecasting methods such as trend prediction model, exponent model, non-linear regression model, improved grey predictive model and improved grey verhulst predictive model, are used to form a model group, and then the fitted results by different traditional predictive models in time sequence act as the input of the support vector machine regression (SVMR) model, then by relative SVMR approach based on known input and output samples, we can obtain the test model. In the paper, the procedure of the combinational prediction on transformer faults based on SVMR is discussed in details. The example on load data has proven that the proposed model can give good results on both the fitting to the known data in time sequence and the extrapolation to the data to be predicted. Moreover, compared with other predictive approaches, both single model and other combinational model, the proposed combinational forecasting model has higher prediction accuracy.

The Application of PCA and SVM in Rolling Bearing Fault Diagnosis

The key to the fault diagnosis is feature extracting and fault pattern classifying. Principal components analysis (PCA) and support vector machine (SVM) method are introduced to recognize the fault pattern of the rolling bearing in this paper. Multidimensional correlated variable is converted into low dimensional independent eigenvector by means of PCA. The pattern recognition and the nonlinear regression are achieved by the method of SVM. In the light of the feature of vibrating signals, eigenvector is obtained using PCA, fault diagnosis of rolling bearing is recognized correspondingly using SVM fault classifier. Theory and experiment show that the recognition of fault diagnosis of rolling bearing based on PCA and SVM theory is available in the fault pattern recognition and provides a new approach to intelligent fault diagnosis.

Deformation prediction model of surrounding rock based on GA-LSSVM-markov

Command protection engineering is the important component of national protection engineering system. To raise the level of its construction, a deformation prediction model is given based on Genetic Algorithm (GA), Least Square Support Vector Machines (LSSVM) and markov theory. Genetic algorithm is used to improve the parameter of LSSVM. Markov predict method is used to improve the precision of the prediction model. Finally, be used to a certain command protection engineering, the accuracy of the algorithm is improved obviously. The model is proved to be credible and precise.

3D Modeling with Support Vector Machines

We developed a new approach based on Support Vector Machines (SVM) to model solids defined by a set of points on their surface. In problems of classification, regression and support of distribution, SVM are focused in the hyper-planes of maximum margin in the feature space. However, the forms that could be described by these surfaces when they return to the input space have not been studied in depth. In this paper, these surfaces are used to model complex objects, connected or non- connected, with a great amount of points, in order of tens of thousands, and with various topologies (hollow, branches, etc.). Two constrains were kept: 1) The use of traditional algorithms of SVM theory; and 2) The design of the appropriate training sets from the object. This combination produced a novel tool and the results obtained illustrated the potential of the proposed method. Therefore, this new application of SVM of Vapnik is capable of creating surfaces of decision and estimation functions, which are well fitted to objects of complex topology.

Research on optimal measurement area of flexible coordinate measuring machines

When we measure a workpiece in the optimal measurement area of the flexible coordinate measuring machines (FCMMs), the measuring precision can be improved. The flexible CMM’s measuring space is given. Then its spatial error distribution model is build by using support vector machine theory. Finally, the two solutions of the optimal measurement area are discussed and solved through experiments. The high precision measurement results can be realized by using a low-precision measuring machine without any increase in hardware manufacturing cost. This is of great theoretical value and practical significance for the flexible CMM’s further development.

Multi‐scale image segmentation algorithm based on support vector machine approximation criteria

SUMMARYA new multi‐scale image segmentation algorithm based on support vector machine (SVM) approximation criteria has been discussed in this paper. Most current multi‐scale image segmentation algorithms are based on the restricted empirical risk minimization, and the approximation of multi‐scale image segmentation was poor. As the SVM theory was one based on the structural risk minimization, the best approximation results could be reached. So, it was combined with multi‐scale image segmentation algorithms, and one‐image multi‐resolution analysis approximation algorithms based on the SVM theory were presented in this paper, which could obtain more accurate multi‐scale image segmentation. By numerical results, the algorithm was further verified that more accurate image segmentation results were unfolded. Copyright © 2011 John Wiley & Sons, Ltd.

New Method for Construction Land Prediction Incorporating Genetic Algorithm and Support Vector Machines

Considering the increasingly tense relationship between construction land supply and demand, we study the inherent rules and the spatial evolution in construction land use. In order to solve the problem of parameter optimization effectively, we analysis the fundamental theory of Support Vector Machine and finally accomplish the combination of genetic algorithm and support vector machine. Meanwhile we apply this model to analysis the construction land use and propose a new model, which is based on the support vector machines with genetic algorithm, for construction land evolution. Taking Guandu district in Kunming, Yunnan as a case, we find out that the new model is far superior to recent models in terms of predicting accuracy, algorithm complexity and computational efficiency. And therefore, we believe that this is highly precise, practical and efficient model for forecasting construction land use and evolution.

Fault Diagnosis Method in Controlled Rectifier Based on Support Vector Machines

Based on support vector machines (SVM) theory, a new method of fault diagnosis for controlled rectifier circuits is proposed in this paper. Fault diagnose method of power electronic converter has been studied on the basis of direct waveform analysis and SVM. Three-phase bridge rectifier circuit fault is presented as an example, coupled with the results of a certain power electronic circuit experiment, indicates that the method can accurately diagnose and locate fault for controlled rectifier circuits, which is justified practical and applicable for controlled rectifier circuit fault diagnosis.

Study on Support Vector Machine Based on Nonlinear Correction of Double Parallel Beam Weighing Transducer

According to the non-linear problem caused by temperature and circuit interference during the detection process of the double parallel beam weighing transducer, a nonlinear compensation method is proposed based on the support vector machine theory. The nonlinear characteristics of measured values of sensor are analyzed, and the support vector machine (SVM) inverse model is established while the displacement parameters as the output and voltage parameter as input. The effectiveness of SVM inverse model is verified by the simulation. Compared with the RBF neural network model, the SVM model is efficiency. The average error of the model prediction is 0.027g mm, so it has good linearity, and nonlinear compensation of the double Parallel beam weighing transducer is realized.

A Short-Term Load Forecasting Method of Warship Based on PSO-SVM Method

The power load characteristics of warship on a specific task was analyzed,and a task-based forecasting method for warship short-term load forecasting was presented. the new influencing factors of warship power load were used in modeling which is different with the land grid and civilian vessels grid. Theory of particle swarm optimization and Support vector machine was disscused first, and the method of particle swarm optimization was improved to have the ability of adaptive parameter optimization. and the method of support vector machine was improved by the adaptive PSO optimizational method. then a new adaptive short-term load forecasting model was established by the adaptive PSO-SVM method. finally Through simulation results show that the adaptive PSO-SVM method is highly feasible to predict with high accuracy and high generalization capability.

An Improved Short-Term Load Forecasting Method of Warship

The power load characteristics of warship on a specific task was analyzed,and a task-based forecasting method for warship short-term load forecasting was presented. the new influencing factors of warship power load were used in modeling which is different with the land grid and civilian vessels grid. Theory of particle swarm optimization and Support vector machine was disscused first, and the method of particle swarm optimization was improved to have the ability of adaptive parameter optimization. and the method of support vector machine was improved by the adaptive PSO optimizational method. then a new adaptive short-term load forecasting model was established by the adaptive PSO-SVM method. finally Through simulation results show that the adaptive PSO-SVM method is highly feasible to predict with high accuracy and high generalization capability.

PREDICTION OF PASSENGER FLOW ON THE HIGHWAY BASED ON THE LEAST SQUARE SUPPOERT VECTOR MACHINE / MAŽIAUSIŲ KVADRATŲ ATRAMINIŲ VEKTORIŲ METODO TAIKYMAS KELEIVIŲ SRAUTUI GREITKELYJE PROGNOZUOTI / ПРИМЕНЕНИЕ МЕТОДА ОПОРНЫХ ВЕКТОРОВ С КВАДРАТИЧНОЙ ФУНКЦИЕЙ ПОТЕРЬ ДЛЯ ПРОГНОЗИРОВАНИЯ ПАССАЖИРСКИХ ПОТОКОВ НА АВТОМАГИСТРАЛЯХ

A support vector machine is a machine learning method based on the statistical learning theory and structural risk minimization. The support vector machine is a much better method than ever, because it may solve some actual problems in small samples, high dimension, nonlinear and local minima etc. The article utilizes the theory and method of support vector machine (SVM) regression and establishes the regressive model based on the least square support vector machine (LS-SVM). Through predicting passenger flow on Hangzhou highway in 2000–2008, the paper shows that the regressive model of LS-SVM has much higher accuracy and reliability of prediction, and therefore may effectively predict passenger flow on the highway. Santrauka Atraminių vektorių metodas (Support Vector Machine – SVM) yra skaičiuojamasis metodas, paremtas statistikos teorija, struktūriniu požiūriu mažinant riziką. SVM metodas, palyginti su kitais metodais, yra patikimesnis metodas, nes juo remiantis galima išspręsti realias problemas, esant įvairioms sąlygoms. Tyrimams naudojama SVM metodo regresijos teorija ir sukuriamas regresinis modelis, kuris grindžiamas mažiausių kvadratų atraminių vektorių metodu (Least Squares Support Vector Machine – LS-SVM). Straipsnio autoriai prognozuoja keleivių srautą Hangdžou (Kinija) greitkelyje 2000–2008 m. Gauti rezultatai rodo, kad regresinis LS-SVM modelis yra labai tikslus ir patikimas, todėl gali būti efektyviai taikomas keleivių srautams prognozuoti greitkeliuose. Резюме Метод опорных векторов (Support Vector Machine – SVM) – это набор аналогичных алгоритмов вида «обучение с учителем», использующихся для задач классификации и регрессионного анализа. Метод SVM принадлежит к семейству линейных классификаторов. Основная идея метода SVM заключается в переводе исходных векторов в пространство более высокой размерности и поиске разделяющей гиперплоскости с максимальным зазором в этом пространстве. Алгоритм работает в предположении, что чем больше разница или расстояние между параллельными гиперплоскостями, тем меньше будет средняя ошибка классификатора. В сравнении с другими методами метод SVM более надежен и позволяет решать проблемы с различными условиями. Для исследования был использован метод SVM и регрессионный анализ, затем создана регрессионная модель, основанная на методе опорных векторов с квадратичной функцией потерь (Least Squares Support Vector Machine – LS-SVM). Авторы прогнозировали пассажирский поток на автомагистрали Ханчжоу (Китай) в 2000–2008 гг. Полученные результаты показывают, что регрессионная модель LS-SVM является надежной и может быть применена для прогнозирования пассажирских потоков на других магистралях.

Time series prediction of mining subsidence based on a SVM

In order to study dynamic laws of surface movements over coal mines due to mining activities, a dynamic prediction model of surface movements was established, based on the theory of support vector machines (SVM) and times-series analysis. An engineering application was used to verify the correctness of the model. Measurements from observation stations were analyzed and processed to obtain equal-time interval surface movement data and subjected to tests of stationary, zero means and normality. Then the data were used to train the SVM model. A time series model was established to predict mining subsidence by rational choices of embedding dimensions and SVM parameters. MAPE and WIA were used as indicators to evaluate the accuracy of the model and for generalization performance. In the end, the model was used to predict future surface movements. Data from observation stations in Huaibei coal mining area were used as an example. The results show that the maximum absolute error of subsidence is 9 mm, the maximum relative error 1.5%, the maximum absolute error of displacement 7 mm and the maximum relative error 1.8%. The accuracy and reliability of the model meet the requirements of on-site engineering. The results of the study provide a new approach to investigate the dynamics of surface movements.

Study on Application of Support Vector Machine to Prediction of Blasting Vibration Velocity

Based on the nonlinear regression theory of Support Vector Machine, SVM model was put forward to predict blasting vibration velocity by using monitoring data obtained in blasting site as training samples. By comparing the results of the two prediction models of the improved Sadaovsk and SVM, the feasibility of the new learning method of SVM model was verified, which will provide a new way to predict and control intensity of blasting vibration. The best way to select the parameters of SVM needs to be further explored.

Prediction of rotor spun yarn strength using support vector machines method

A new method for rotor spun yarn prediction from fiber properties based on the theory of support vector machines (SVM) was introduced. The SVM represents a new approach to supervised pattern classification and has been successfully applied to a wide range of pattern recognition problems. In this study, high volume instrument (HVI) and advanced fiber information system (Uster AFIS) fiber test results consisting of different fiber properties are used to predict the rotor spun yarn strength. The results obtained through this study indicated that the SVM method would become a powerful tool for predicting rotor spun yarn strength. The relative importance of each fiber property on the rotor spun yarn strength is also expected. The study shows also that the combination of SVM parameters and optimal search method chosen in the model development played an important role in better performance of the model. The predictive performances are estimated and compared to those provided by ANFIS model.

Decision-based filter based on SVM and evidence theory for image noise removal

A decision-based filtering technique is proposed for removing impulsive noise while preserving image details in corrupted images. The proposed filter is based on support vector machines (SVMs), evidence theory, and the least mean square (LMS) learning algorithm. The fusion of evidence based on the Dempster–Shafer evidence theory provides a feature vector that is used as the input data of the proposed SVM impulse detector, which is used to judge whether an input pixel is noisy. If a pixel is detected as noisy, an adaptive CWM filter based on a weight controller is triggered to replace it; otherwise, the pixel stays unchanged. The optimal weights of the adaptive CWM filter are obtained using scalar quantization and the LMS learning algorithm. Experimental results demonstrate that the proposed filter achieves much better performance than the state-of-the-art filters in terms of noise suppression and detail preservation.

The Prediction Model of Chaotic Series Based on Support Vector Machine and its Application to Runoff

Chaos and support vector machine theory has opened up a new route to study complicated and changeable non-linear hydrology time series. Applying the Chaos and non-linear time series based on the support vector machine regression principle, this paper proposes a method and its characteristic and the choosing of key parameters to forecast and set up models. According to Phase Space Reconstruction theory carry on reconstruction of Phase Space to monthly surface flow course, have discussed that probed into the non-linear prediction model of time series of Chaos of the support vector machine, application in the monthly surface flow, have introduce it through to the nuclear function of the base in the course of setting up the model of support vector machine, has simplified the course of solving the non-linear problems. The instance indicates that the model can deal with the complicated hydrology data array well, and there is the good prediction precision.

Support Vector Machine Active Learning Through Significance Space Construction

Active learning is showing to be a useful approach to improve the efficiency of the classification process for remote sensing images. This letter introduces a new active learning strategy specifically developed for support vector machine (SVM) classification. It relies on the idea of the following: 1) reformulating the original classification problem into a new problem where it is needed to discriminate between significant and nonsignificant samples, according to a concept of significance which is proper to the SVM theory; and 2) constructing the corresponding significance space to suitably guide the selection of the samples potentially useful to better deal with the original classification problem. Experiments were conducted on both multi- and hyperspectral images. Results show interesting advantages of the proposed method in terms of convergence speed, stability, and sparseness.

THE USE OF LS-SVM FOR SHORT-TERM PASSENGER FLOW PREDICTION / MAŽIAUSIŲ KVADRATŲ ATRAMINIŲ VEKTORIŲ METODO TAIKYMAS TRUMPALAIKIAM KELEIVIŲ SRAUTUI PROGNOZUOTI / ПРИМЕНЕНИЕ МЕТОДА ОПОРНЫХ ВЕКТОРОВ С КВАДРАТИЧНОЙ ФУНКЦИЕЙ ПОТЕРЬ ДЛЯ ПРОГНОЗИРОВАНИЯ КРАТКОСРОЧНЫХ ПОТОКОВ ПАССАЖИРОВ

Transit flow is the basement of transit planning and scheduling. The paper presents a new transit flow prediction model based on Least Squares Support Vector Machine (LS-SVM). With reference to the theory of Support Vector Machine and Genetic Algorithm, a new short-term passenger flow prediction model is built employing LSSVM, and a new evaluation indicator is used for presenting training permanence. An improved genetic algorithm is designed by enhancing crossover and variation in the use of optimizing the penalty parameter γ and kernel parameter s in LS-SVM. By using this method, passenger flow in a certain bus route is predicted in Changchun. The obtained result shows that there is little difference between actual value and prediction, and the majority of the equal coefficients of a training set are larger than 0.90, which shows the validity of the approach. Santrauka Tranzito srautas yra tranzito planavimo ir eismo tvarkaraščių sudarymo pagrindas. Straipsnis pateikia naują tranzitinio srauto prognozavimo modelį, grindžiamą mažiausių kvadratų atraminių vektorių metodu (Least Squares Support Vector machine, LS-SVm). Remiantis atraminių vektorių metodu (Support Vector machine) ir genetiniu algoritmu (Genetic Algorithm), sudarytas naujas trumpalaikis keleivių srauto prognozavimo modelis, pasitelkiant LS-SVM ir pristatomas naujas vertinimo rodiklis. Taikant naują metodą prognozuojamas keleivių srautas konkrečiame autobuso maršrute Čangčuno mieste Kinijoje. Gautos prognozės rezultatai lyginami su faktiniais. Резюме Транзитный поток – основной фактор при планировании транзита и составлении расписаний движения. В статье представлена новая модель прогноз*а транзитного потока, основанная на методе опорных векторов с квадратичной функцией потерь (Least Squares Support Vector machine – LS-SVm). Представленный новый метод используется для прогноза потока пассажиров на конкретном автобусном маршруте города Чаньчуня (Китай). Результаты прогноза сравниваются с фактическими результатами.

Unobtrusive Assessment of Motor Patterns During Sleep Based on Mattress Indentation Measurements

This study investigates how integrated bed measurements can be used to assess motor patterns (movements and postures) during sleep. An algorithm has been developed that detects movements based on the time derivate of mattress surface indentation. After each movement, the algorithm recognizes the adopted sleep posture based on an image feature vector and an optimal separating hyperplane constructed with the theory of support vector machines. The developed algorithm has been tested on a dataset of 30 fully recorded nights in a sleep laboratory. Movement detection has been compared to actigraphy, whereas posture recognition has been validated with a manual posture scoring based on video frames and chest orientation. Results show a high sensitivity for movement detection (91.2%) and posture recognition (between 83.6% and 95.9%), indicating that mattress indentation provides an accurate and unobtrusive measure to assess motor patterns during sleep.