Two-stage fast training method based on core vector machine and support vector machine

2013 ◽  
Vol 32 (2) ◽  
pp. 419-424 ◽  
Author(s):  
Jun-yi PU ◽  
Xiu-ren LEI
Keyword(s):  
Support Vector Machine ◽  
Support Vector ◽  
Training Method ◽  
Two Stage ◽  
Fast Training

scholarly journals A Novel Fast Training Method for SVM and Its Application in Fault Diagnosis of Service Robot

2015 ◽  
Vol 11 (6) ◽  
pp. 4 ◽  
Author(s):  
Xianfeng Yuan ◽  
Mumin Song ◽  
Fengyu Zhou ◽  
Yugang Wang ◽  
Zhumin Chen
Keyword(s):  
Fault Diagnosis ◽  
Classification Accuracy ◽  
Machine Learning Algorithms ◽  
Sensor Data ◽  
Service Robot ◽  
Support Vector ◽  
Svm Classifier ◽  
Processing Unit ◽  
Training Method ◽  
Fast Training

Support Vector Machines (SVM) is a set of popular machine learning algorithms which have been successfully applied in diverse aspects, but for large training data sets the processing time and computational costs are prohibitive. This paper presents a novel fast training method for SVM, which is applied in the fault diagnosis of service robot. Firstly, sensor data are sampled under different running conditions of the robot and those samples are divided as training sets and testing sets. Secondly, the sampled data are preprocessed and the principal component analysis (PCA) model is established for fault feature extraction. Thirdly, the feature vectors are used to train the SVM classifier, which achieves the fault diagnosis of the robot. To speed up the training process of SVM, on the one hand, sample reduction is done using the proposed support vectors selection (SVS) algorithm, which can ensure good classification accuracy and generalization capability. On the other hand, we take advantage of the excellent parallel computing abilities of Graphics Processing Unit (GPU) to pre-calculate the kernel matrix, which avoids the recalculation during the cross validation process. Experimental results illustrate that the proposed method can significantly reduce the training time without decreasing the classification accuracy.

A two-stage-training support vector machine approach to predicting unintentional vehicle lane departure

2016 ◽  
Vol 21 (1) ◽  
pp. 41-51 ◽  
Author(s):  
Alhadi Ali Albousefi ◽  
Hao Ying ◽  
Dimitar Filev ◽  
Fazal Syed ◽  
Kwaku O. Prakah-Asante ◽  
...  
Keyword(s):  
Support Vector Machine ◽  
Support Vector ◽  
Two Stage ◽  
Training Support ◽  
Lane Departure

scholarly journals A two-stage classification method for borehole-wall images with support vector machine

PLoS ONE ◽  
2018 ◽  
Vol 13 (6) ◽  
pp. e0199749
Author(s):  
Zhaopeng Deng ◽  
Maoyong Cao ◽  
Laxmisha Rai ◽  
Wei Gao
Keyword(s):  
Support Vector Machine ◽  
Borehole Wall ◽  
Classification Method ◽  
Support Vector ◽  
Two Stage ◽  
Stage Classification

Typhoon flood forecasting using integrated two-stage Support Vector Machine approach

2013 ◽  
Vol 486 ◽  
pp. 334-342 ◽  
Author(s):  
Gwo-Fong Lin ◽  
Yang-Ching Chou ◽  
Ming-Chang Wu
Keyword(s):  
Support Vector Machine ◽  
Flood Forecasting ◽  
Support Vector ◽  
Two Stage

Kinematics-based end-effector path control of a mobile manipulator system on an uneven terrain using a two-stage Support Vector Machine

Robotica ◽  
2019 ◽  
Vol 38 (8) ◽  
pp. 1415-1433 ◽  
Author(s):  
Hitesh Jangid ◽  
Subham Jain ◽  
Beteley Teka ◽  
Rekha Raja ◽  
Ashish Dutta
Keyword(s):  
Support Vector Machine ◽  
Control Method ◽  
Microsoft Kinect ◽  
Mobile Manipulator ◽  
Support Vector ◽  
Joint Probability Distribution ◽  
Total System ◽  
Two Stage ◽  
End Effector ◽  
Uneven Terrain

SUMMARYA mobile manipulator system (MMS) consists of a robotic arm mounted on a mobile platform that is used in rescue and relief, space exploration, warehouse automation, etc. As the total system has 14 Degrees of Freedom (DOF), it does not have a closed-form inverse kinematics (IK) solution. A learning-based method is proposed, which uses the forward kinematics data to learn the IK relation for motion of an MMS on a rough terrain, using a one-class support vector machine (SVM) framework. Once trained, the model estimates the joint probability distribution of the MMS configuration and end-effector position. This distribution is used to find the MMS configuration for a given desired end-effector path. Past research using a Kohonen Self organizing map (KSOM) neural network-based open-loop control method has shown that the MMS deviates from its desired path while moving on an uneven terrain due to unknown disturbances such as wheel slip, slide, and terrain deformation. Therefore, a new sequential two-stage SVM-based end-effector path-tracking control scheme is proposed to control the end-effector path. In this scheme, the error in the end-effector path is continuously tracked with the help of a Microsoft Kinect 2.0 (Microsoft Regional Sales, Singapore 119968) and is sent as a feedback to the controller. Once the error reaches a threshold value, the error correction step of the controller gets activated to correct the error until the desired accuracy is reached. The effectiveness of the proposed approach is proved through extensive simulations and experiments conducted on 3D terrain in which it is shown that the end effector can follow the desired path with an average experimental error of around 2 cm between the desired and final corrected path.

Sign in / Sign up

Export Citation Format

Share Document