• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2008.04a
• /
• pp.343-346
• /
• 2008

휴머노이드 로봇이 넘어질 경우, 충격에 의한 손상이 발생할수 있다. 이를 최소화하는 넘어짐 자세의 생성을 위하여 개선된 PGA 기반의 탐색기법을 제안한다. 다목적함수를 고려한 군집 간 이주방식의 효율적 조합을 통해 넘어짐 충격을 최소화하는 각 관절 궤적을 구할수 있도록 하였다. 제안된 기법의 검증을 위하여 Sony QRIO 로봇에 대해서 ODE 기반의 Webots 시뮬레이션을 이용하여 실험을 수행하였다.

• Journal of Internet Computing and Services
• /
• v.13 no.4
• /
• pp.23-31
• /
• 2012

Nowadays, recognizing human activities is an important subject; it is exploited widely and applied to many fields in real-life, especially in health care and context aware application. Research achievements are mainly focused on activities of daily living which are useful for suggesting advises to health care applications. Falling event is one of the biggest risks to the health and well-being of the elderly especially in independent living because falling accidents may be caused from heart attack. Recognizing this activity still remains in difficult research area. Many systems equipped wearable sensors have been proposed but they are not useful if users forget to wear the clothes or lack ability to adapt themselves to mobile systems without specific wearable sensors. In this paper, we develop a novel method based on analyzing the change of acceleration, orientation when the fall occurs and measure their similarity to featured fall patterns. In this study, we recruit five volunteers in our experiment including various fall categories. The results are effective for recognizing fall activity. Our system is implemented on G1 smart phone which are already plugged accelerometer and orientation sensors. The popular phone is used to get data from accelerometer and results showthe feasibility of our method and significant contribution to fall detection.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.6
• /
• pp.843-848
• /
• 2007

This paper introduced an automatic generation method of falling motions for humanoid robots to minimize a damage. The proposed approach used a GA based optimization technique to find a set of joint trajectories which minimize a damage of the falling over and down. A couple of fitness functions are provided to generate various falling motions. To verify the proposed method, experiments for falling motions were executed for Sony QRIO robot in Webots simulation environments.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2007.11a
• /
• pp.77-81
• /
• 2007

본 논문은 휴머노이드 로봇의 넘어짐 자세 시 충격량 최소화를 위한 GA 기반의 자세 자동 생성 방법을 제안한다. 관절 공간에서 관절각의 최적 조합으로 충격량을 최소화 할 수 있는 자세의 자동 생성 기법을 구현하였다. 제안된 기법의 검증을 위하여 Sony QRIO 로봇에 대해서 ODE 기반 물리적 특성의 시뮬레이션이 가능한 Webots를 이용하여 실험을 수행하였다.

• 월간산업보건
• /
• s.281
• /
• pp.72-73
• /
• 2011

• The Safety technology
• /
• no.82
• /
• pp.8-15
• /
• 2004

• Proceedings of the Korean Society of Disaster Information Conference
• /
• 2015.11a
• /
• pp.243-245
• /
• 2015

본 논문은 사고의 발생은 안전하지 못한 장소나 상황으로부터 발생하며, 그러한 장소는 안전수준이 높은 지역이나 사회적 계층 및 가정보다는 그렇지 못한 취약지역이나 취약계층 또는 취약가정에서 상대적으로 높은 사고 발생율과 위험에 직면한 상황이 많이 발생할 것이다. 따라서 지역의 특성에 맞는 집중적인 안전관리 대책을 수립하는 것이 국가적 차원의 안전사고 발생율을 낮추고, 효과적인 사고 예방대책을 수립할 수 있다. 이를 위하여 도시계획구역에 따라 청소년 1,200명을 표본조사 하였으며, 자료처리 방법은 window spss pc 12.0 통계프로그램을 이용하여 분석하였다. 본 연구 결과 주요 사고 유형은 '추락/넘어짐/미끄러져 다친 사고'가 49.2%로 가장 많으며, 사고 장소는 학교주변, 집주변, 여가놀이시설주변이었다. 이것은 본 연구에서 아동청소년들의 주요 활동공간으로 제시한 곳과 일치한다. 용도지역에 따른 아동 청소년의 안전도 차이를 보면 도시 내 상업지역이 사고경험이 가장 많으며, 사고유형은 도시 내 상업지역은 화재, 이물질 섭취, 폭발, 부패 변질, 물체 접촉 등이 많고, 도시내 주거지역과 공업지역, 농어촌지역은 충돌이나 충격사고, 추락/넘어짐/ 미끄러져 다친 사고나 날카로운 물체에 베이거나 찔린 사고가 많은 것으로 나타났다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.191-193
• /
• 2022

유모차 사고는 추락/넘어짐/미끄러움으로 인해 발생하는 사고가 가장 큰 비율을 차지한다. 또한 보행이 불편한 고령자가 유모차 또는 보행기를 보조기구로 사용할 때에도 유모차와 유사한 사고 발생 확률이 높다. 기존의 유모차, 전동 휠체어, 보행기 등 출시 제품들은 넘어짐과 관련된 사고예방 기능은 구현되지 않았으므로 사고를 예방하기 힘들다. 이를 해결하기 위해 본 연구는 기울기에 따라 보행 중 안전을 보조하고, 속도에 따른 넘어짐 관련 사고를 예측하여 보호자 및 주변 사람들에게 위험을 알리는 사고예방을 위한 보행보조시스템을 설계하고 구현하였다. 이 시스템을 통해 유아 및 고령자가 이용하는 보행보조기를 더욱 안전하게 사용하여 2차 사고를 예방할 수 있는 효과를 기대할 수 있다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.8
• /
• pp.1165-1171
• /
• 2022

Human behavior recognition using an accelerometer has been applied to various fields. As smartphones have become used commonly, a method for human behavior recognition using the acceleration sensor built into the smartphone is being studied. In the case of the elderly, falling often leads to serious injuries, and falls are one of the major causes of accidents at construction fields. In this article, we proposed recognition method for human falling direction using built-in acceleration sensor and orientation sensor in the smartphone. In the past, it was a common method to use the magnitude of the acceleration vector to recognize human behavior. These days, deep learning has been actively studied and applied to various areas. In this article, we propose a method for recognizing the direction of human falling by applying the deep learning multilayer technique, which has been widely used recently.

• 한국노년학
• /
• v.37 no.1
• /
• pp.237-250
• /
• 2017

The purpose of this study is to analyze the effects of exercise program for prevention of falling on physical fitness, posture and fall prevention self-efficacy for elderly women. 30 females above the age of 65 were subjects for this study. Over an twelve week period, 14women in the experimental group performed exercise 2 times a week for 60 minutes per session. 16women in the control group didn't participate in the exercise program. The independent variable was a exercise program for prevention of falling. Dependent variables were physical fitness, posture and fall prevention self-efficacy. Prevention of falling exercise program is consisted of an elastic band using exercise and Korean dance movement exercise. Physical fitness consisted of grip strength, upper and lower body endurance, cardiovascular endurance, flexibility, balance, coordination. The posture was measured the static posture when standing, using a high-resolution camera, body style to automatically measure the distance and angle(M-zen, Korea). Posture was measured in both the coronal and sagittal plane via reference board. Fall prevention self-efficacy was measured via questionnaire using the Korea Falls Self-Efficacy Scale (FES-K). The physical fitness, posture and fall prevention self-efficacy were measured twice with pre and post exercise, and the difference between groups with Wilcox signed rank test, and the group-specific post verification was carried out with U-validated methods (Mann Whitney U test). Statistical significance level was verified by setting the p<.05. Lower body endurance, cardiovascular endurance, flexibility, balance and coordination significantly increased in the experimental group. The control group was no significant increase in physical fitness variables. shoulder slope angle, pelvic slope angle(coronal/sagittal), leg length difference, scapular inferior angle and left/right calcaneus angle significantly decreased in the experimental group. Both the experimental group and control group were no significant increase in fall prevention self efficacy. The prevention of falling exercise program for elderly women indicated the positive changes in physical fitness(except grip strength) and posture(except upper body slope). However, there are no significant differences of falling prevention self-efficacy between the both group. Thus, the prevention of falling exercise program for the elderly has been proved that it is highly efficient on improving physical fitness and posture proofreading. However, we still need to consider supplement exercise for grip strength and upper body slope.