完整後設資料紀錄
DC 欄位語言
dc.contributor.authorCho, Hsun-Jungen_US
dc.contributor.authorLi, Rih-Jinen_US
dc.contributor.authorLee, Hsiaen_US
dc.contributor.authorWu, Jennifer Yuh-Jenen_US
dc.date.accessioned2014-12-08T15:18:42Z-
dc.date.available2014-12-08T15:18:42Z-
dc.date.issued2009en_US
dc.identifier.isbn978-0-7354-0685-8en_US
dc.identifier.issn0094-243Xen_US
dc.identifier.urihttp://hdl.handle.net/11536/13445-
dc.description.abstractThis investigation involves the combination of support vector machines (SVM) and k-means clustering implemented on radar signal. SVM classifier based on k-means algorithm has an advance for classifying unlabeled data. To classify the vehicle types automatically, the combined method is implemented with radar signals. This paper proposed a classifier training algorithm based on SVM and k-means clustering as follows (i) using the k-means algorithm to label the input feature data extracted from radar signal into two subsets, (ii) train SVM with labeled data, and (iii) classify unidentified radar signal into large vehicle or small vehicle with the trained classifier. Training features of radar signal includes (i) signal volume and (ii) sum of signal variations, both in frequency domain. These features are taken as system input, while vehicle types as system output. The proposed algorithm is implemented and demonstrated with real FMCW radar signals. With the numerical experiment, satisfying result is obtained.en_US
dc.language.isoen_USen_US
dc.subjectVehicle Classificationen_US
dc.subjectSupport Vector Machines (SVM)en_US
dc.subjectk-means Clusteringen_US
dc.titleVehicle Classification using Support Vector Machines and k-means Clusteringen_US
dc.typeArticleen_US
dc.identifier.journalCOMPUTATIONAL METHODS IN SCIENCE AND ENGINEERING, VOL 2: ADVANCES IN COMPUTATIONAL SCIENCEen_US
dc.citation.volume1148en_US
dc.citation.spage449en_US
dc.citation.epage452en_US
dc.contributor.department運輸與物流管理系 註:原交通所+運管所zh_TW
dc.contributor.departmentDepartment of Transportation and Logistics Managementen_US
dc.identifier.wosnumberWOS:000280417500112-
顯示於類別:會議論文