Full metadata record
DC FieldValueLanguage
dc.contributor.authorWu, Cheng-Weien_US
dc.contributor.authorYang, Hua-Zhien_US
dc.contributor.authorChen, Yan-Annen_US
dc.contributor.authorEnsa, Bajoen_US
dc.contributor.authorRen, Yien_US
dc.contributor.authorTseng, Yu-Cheeen_US
dc.date.accessioned2018-08-21T05:57:13Z-
dc.date.available2018-08-21T05:57:13Z-
dc.date.issued2017-01-01en_US
dc.identifier.issn2325-5986en_US
dc.identifier.urihttp://hdl.handle.net/11536/147191-
dc.description.abstractRecently, some studies for head gestures recognition have been proposed, but most of them are based on image processing technology. Moreover, there is less focus on the use of wearable devices in recognizing head gestures. In this paper, we apply machine learning techniques to recognize some common head activities using a head-mounted wearable device. We use the wearable device to collect sensor data related to user's head activities. Then, we apply energy-based segmentation method on the collected data to find out the data segments where the activities may occur. Finally, we extract candidate features from the segments and feed them into a pre-trained classifier to identify the type of head gesture. We implement the prototype of above methods on Arduino platform and evaluate the efficiency of the proposed methods on real datasets. The experiment results show that our proposed methods can effectively and efficiently identify different types of head gestures with an average accuracy rate of 95%.en_US
dc.language.isoen_USen_US
dc.subjectgesture recognitionen_US
dc.subjecthuman-computer interaction interfaceen_US
dc.subjectmobile computingen_US
dc.subjectmachine learningen_US
dc.subjectwearable devicesen_US
dc.titleApplying Machine Learning to Head Gesture Recognition using Wearablesen_US
dc.typeProceedings Paperen_US
dc.identifier.journal2017 IEEE 8TH INTERNATIONAL CONFERENCE ON AWARENESS SCIENCE AND TECHNOLOGY (ICAST)en_US
dc.citation.spage436en_US
dc.citation.epage440en_US
dc.contributor.department資訊工程學系zh_TW
dc.contributor.departmentDepartment of Computer Scienceen_US
dc.identifier.wosnumberWOS:000428078800083en_US
Appears in Collections:Conferences Paper