김하연 임윤섭 김도익 2025-09-05T02:30:17Z 2025-09-05T02:30:17Z 2025-09-05 2025-08 1225-9071 https://pubs.kist.re.kr/handle/201004/153128 Human activity recognition (HAR) has been actively researched in fields such as healthcare to understand and analyze human behavior in human-robot interaction. However, most studies have struggled to recognize activities like turning and motion transitions, which are often associated with dynamic balance. Therefore, we propose a novel HAR approach using a single sensor to collect and early fuse motion and position data. The aim is to enhance the accuracy of motion classification for daily activities and those that cause imbalance, which have traditionally been difficult to recognize. We constructed a quarantine room environment for data collection and to evaluate the impact of the suggested features on behavior. Five deep learning models were trained and evaluated to identify the optimal model. The collected data was classified and analyzed by the selected model, which demonstrated an average accuracy of 98.96%. Korean 한국정밀공학회 불균형을 유발하는 회전 및 전환 동작 감지 멀티모달 특징 기반 딥러닝을 통한 행동 인식 Detection of Imbalance-causing Turning and Motion Transitions in Activity Recognition via Multimodal Feature-based Deep Learning Article 10.7736/JKSPE.025.058 1 한국정밀공학회지, v.42, no.8, pp.649 - 656 한국정밀공학회지 42 8 649 656 Y scopus kci ART003230540 Y Human activity recognition Indoor positioning system Ambient assisted living 지능형 병원 지능형 집 사람 행동 인식 실내 위치추적 시스템 전천후 생활보조 Smart hospital Smart home