In this paper, we propose an improved Directed Acyclic Graph Support Vector Machine （DAGSVM） for multi-class classification. Compared with the traditional DAGSVM, the improved version has advantages that the structu...In this paper, we propose an improved Directed Acyclic Graph Support Vector Machine （DAGSVM） for multi-class classification. Compared with the traditional DAGSVM, the improved version has advantages that the structure of the directed acyclic graph is not chosen random and fixed, and it can be adaptive to be optimal according to the incoming testing samples, thus it has a good generalization performance. From experiments on six datasets, we can see that the proposed improved version of DAGSVM is better than the traditional one with respect to the accuracy rate.展开更多
In order to accurate measure micro displacement, the paper presents an accurate measuring system of distributed micro displacement. The system uses a linear CCD and FPGA and network communication technology to realize...In order to accurate measure micro displacement, the paper presents an accurate measuring system of distributed micro displacement. The system uses a linear CCD and FPGA and network communication technology to realize data acquisition and remote transmission. The test results show that the system can support 16 line array CCD test node to measure the micro deformation of the one- dimensional, the CCD data transmission rate is 3200 frames/s, node data transmission distance is greater than 200 m, and measurement accuracy is 500 micron.展开更多
文摘In this paper, we propose an improved Directed Acyclic Graph Support Vector Machine （DAGSVM） for multi-class classification. Compared with the traditional DAGSVM, the improved version has advantages that the structure of the directed acyclic graph is not chosen random and fixed, and it can be adaptive to be optimal according to the incoming testing samples, thus it has a good generalization performance. From experiments on six datasets, we can see that the proposed improved version of DAGSVM is better than the traditional one with respect to the accuracy rate.
文摘In order to accurate measure micro displacement, the paper presents an accurate measuring system of distributed micro displacement. The system uses a linear CCD and FPGA and network communication technology to realize data acquisition and remote transmission. The test results show that the system can support 16 line array CCD test node to measure the micro deformation of the one- dimensional, the CCD data transmission rate is 3200 frames/s, node data transmission distance is greater than 200 m, and measurement accuracy is 500 micron.
