http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
현경학(Kyung Hak Hyun),김은호(Eun Ho Kim),심형철(Hyung Cheoul Shim),곽윤근(Yoon Keun Kwak) 대한기계학회 2006 대한기계학회 춘추학술대회 Vol.2006 No.11
In service robot or personal robot, it is important to recognize human emotion or intend for friendly interaction between human and robot. Many works about emotion features have been reported, however, there are lots of types of features and many combinations of features, so study for feature selection is needed. In this paper, we studied the feature selection based on frequency characteristics and compared it with existing method.
음성의 특정 주파수 범위를 이용한 잡음환경에서의 감정인식
김은호(Eun Ho Kim),현경학(Kyung Hak Hyun),곽윤근(Yoon Keun Kwak) Korean Society for Precision Engineering 2006 한국정밀공학회지 Vol.23 No.5
The ability to recognize human emotion is one of the hallmarks of human-robot interaction. Hence this paper describes the realization of emotion recognition. For emotion recognition from voice, we propose a new feature called frequency range of meaningful signal. With this feature, we reached average recognition rate of 76% in speaker-dependent. From the experimental results, we confirm the usefulness of the proposed feature. We also define the noise environment and conduct the noise-environment test. In contrast to other features, the proposed feature is robust in a noise-environment.
최근하(Keun Ha Choi),정해관(Hae Kwan Jeong),현경학(Kyung Hak Hyun),곽윤근(Yoon Keun Kwak) Korean Society for Precision Engineering 2008 한국정밀공학회지 Vol.25 No.2
In this paper, we propose a new driving mode control algorithm for a mobile robot based on obstacle detection. The robot has a variable geometry single-tracked mechanism, so it can maximize a contact length with ground for the adaptability to off-road and puesue a stable system due to the lower center of gravity. However this robot system embodied passive type according to operator. In this reason, several problems are detected. So, this research presents a new method of obstacle detection using PSD infrared sensors and translates the variable tracks on the best suited driving mode actively. And experimental results about mentioned are presented.