A Radar Target Classification Algorithm Based on Dropout Constrained Deep Extreme Learning Machine
Radar target classification is very important in military and civilian fields. Extreme Learning Machines (ELMs) are widely used in classification because of their fast learning speed and good generalization performance. However, because of their shallow architecture, ELMs may not effectively capture...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
China Science Publishing & Media Ltd. (CSPM)
2018-10-01
|
| Series: | Leida xuebao |
| Subjects: | |
| Online Access: | http://radars.ie.ac.cn/fileup/HTML/R18048.htm |
| _version_ | 1797428096106758144 |
|---|---|
| author | Zhao Feixiang Liu Yongxiang Huo Kai |
| author_facet | Zhao Feixiang Liu Yongxiang Huo Kai |
| author_sort | Zhao Feixiang |
| collection | DOAJ |
| description | Radar target classification is very important in military and civilian fields. Extreme Learning Machines (ELMs) are widely used in classification because of their fast learning speed and good generalization performance. However, because of their shallow architecture, ELMs may not effectively capture the data high
level abstractions. Although many researchers have proposed the Deep Extreme Learning Machine (DELM), which can be used to automatically learn high level feature representations, the model easily falls into overfitting when the training sample is limited. To address this issue, Dropout Constrained Deep Extreme Learning Machine (DCDELM) is proposed in this paper. The experimental results on the measured radar data show that the accuracy of the proposed algorithm can reach 93.37%, which is 5.25% higher than that of the stacked autoencoder algorithm, and 8.16% higher than that of the traditional DELM algorithm. |
| first_indexed | 2024-03-09T08:53:10Z |
| format | Article |
| id | doaj.art-7bbfa29a099c427cb2e87e99c03cbabb |
| institution | Directory Open Access Journal |
| issn | 2095-283X 2095-283X |
| language | English |
| last_indexed | 2024-03-09T08:53:10Z |
| publishDate | 2018-10-01 |
| publisher | China Science Publishing & Media Ltd. (CSPM) |
| record_format | Article |
| series | Leida xuebao |
| spelling | doaj.art-7bbfa29a099c427cb2e87e99c03cbabb2023-12-02T13:41:43ZengChina Science Publishing & Media Ltd. (CSPM)Leida xuebao2095-283X2095-283X2018-10-017561362110.12000/JR18048A Radar Target Classification Algorithm Based on Dropout Constrained Deep Extreme Learning MachineZhao Feixiang0Liu Yongxiang1Huo Kai2(College of Electronic Science, National University of Defense Technology, Changsha 410073, China)(College of Electronic Science, National University of Defense Technology, Changsha 410073, China)(College of Electronic Science, National University of Defense Technology, Changsha 410073, China)Radar target classification is very important in military and civilian fields. Extreme Learning Machines (ELMs) are widely used in classification because of their fast learning speed and good generalization performance. However, because of their shallow architecture, ELMs may not effectively capture the data high level abstractions. Although many researchers have proposed the Deep Extreme Learning Machine (DELM), which can be used to automatically learn high level feature representations, the model easily falls into overfitting when the training sample is limited. To address this issue, Dropout Constrained Deep Extreme Learning Machine (DCDELM) is proposed in this paper. The experimental results on the measured radar data show that the accuracy of the proposed algorithm can reach 93.37%, which is 5.25% higher than that of the stacked autoencoder algorithm, and 8.16% higher than that of the traditional DELM algorithm.http://radars.ie.ac.cn/fileup/HTML/R18048.htmExtreme Learning Machine (ELM)Deep learningDropout constrainedRadar target classificationStacked autoencoder |
| spellingShingle | Zhao Feixiang Liu Yongxiang Huo Kai A Radar Target Classification Algorithm Based on Dropout Constrained Deep Extreme Learning Machine Leida xuebao Extreme Learning Machine (ELM) Deep learning Dropout constrained Radar target classification Stacked autoencoder |
| title | A Radar Target Classification Algorithm Based on Dropout Constrained Deep Extreme Learning Machine |
| title_full | A Radar Target Classification Algorithm Based on Dropout Constrained Deep Extreme Learning Machine |
| title_fullStr | A Radar Target Classification Algorithm Based on Dropout Constrained Deep Extreme Learning Machine |
| title_full_unstemmed | A Radar Target Classification Algorithm Based on Dropout Constrained Deep Extreme Learning Machine |
| title_short | A Radar Target Classification Algorithm Based on Dropout Constrained Deep Extreme Learning Machine |
| title_sort | radar target classification algorithm based on dropout constrained deep extreme learning machine |
| topic | Extreme Learning Machine (ELM) Deep learning Dropout constrained Radar target classification Stacked autoencoder |
| url | http://radars.ie.ac.cn/fileup/HTML/R18048.htm |
| work_keys_str_mv | AT zhaofeixiang aradartargetclassificationalgorithmbasedondropoutconstraineddeepextremelearningmachine AT liuyongxiang aradartargetclassificationalgorithmbasedondropoutconstraineddeepextremelearningmachine AT huokai aradartargetclassificationalgorithmbasedondropoutconstraineddeepextremelearningmachine AT zhaofeixiang radartargetclassificationalgorithmbasedondropoutconstraineddeepextremelearningmachine AT liuyongxiang radartargetclassificationalgorithmbasedondropoutconstraineddeepextremelearningmachine AT huokai radartargetclassificationalgorithmbasedondropoutconstraineddeepextremelearningmachine |