원문정보
초록
영어
Due to the problem of low imaging accuracy and slow imaging speed when applying SVM image reconstruction algorithm in ECT system to dealing with a large amount of sample data set, the method of combining feature dimension reduction with SVM algorithm is proposed. This method classifies the sample data by using the way of clustering and extracts the feature parameter, finds out the connection between each sample and the feature, and deals the sample data with dimension reduction, thus finally getting the high-quality training sample. Then it trains the simplified sample data by applying SVM algorithm and obtains decision function, then the decision function is used to predict and image. The experimental results of image reconstruction show that this method greatly reduces the running time and improves the accuracy of imaging compared to using the SVM algorithm alone.
목차
1. Introduction
2. Image Reconstruction Theory Based on SVM
2.1. The Basic Structure of ECT System
2.2. Teaching Model of ECT Sensor
2.3. SVM
3. Realization of FDRSVM Image Reconstruction Algorithm
3.1. Build a Model
3.2. Feature Extraction and Feature Dimension Reduction
3.3. The Realization of FDRSVM Algorithm
4. Analyses of Experimental Results
5. Conclusion
Acknowledgements
References