• 정보과학회 논문지
• /
• 제42권3호
• /
• pp.281-288
• /
• 2015

화산재해 피해 예측 시스템은 기상과 화산분화 시뮬레이션 결과를 기반으로 화산재해대응을 위한 판단을 도와주는 시스템이다. 이 시스템에서 Fall3D라는 프로그램은 기상정보를 바탕으로 화산분화 이후 화산재의 확산예측결과를 생성하고 기상정보를 생성하기 위해 WRF라는 기상수치예보모델을 사용한다. 두 시뮬레이션의 프로그램을 수정하지 않고, 전체 실행시간을 줄이기 위해서는 WRF의 기상예측모델의 시간별 부분결과가 발생할 때마다 Fall3D를 부분수행 할 수 있도록 하는 파이프라이닝 방식을 생각할 수 있다. 이를 위해서 Fall3D와 같은 후속계산은 선행계산의 부분결과가 생성될 때까지 일시정지하고, 계산에 필요한 정보가 발생하면 재개할 수 있어야한다. 비록 Fall3D가 이런 일시정지와 재개기능을 가지고 있지는 않지만 그 이전 계산을 이어서 진행할 수 있는 재시작기능을 활용하여 파이프라이닝 효과를 낼 수 있다. 본 논문에서는 이러한 실행 형태를 제어할 수 있는 워크플로우를 제안한다.

• 로봇학회논문지
• /
• 제13권1호
• /
• pp.45-54
• /
• 2018

This paper presents a vision-based fall detection system to automatically monitor and detect people's fall accidents, particularly those of elderly people or patients. For video analysis, the system should be able to extract both spatial and temporal features so that the model captures appearance and motion information simultaneously. Our approach is based on 3-dimensional convolutional neural networks, which can learn spatiotemporal features. In addition, we adopts a thermal camera in order to handle several issues regarding usability, day and night surveillance and privacy concerns. We design a pan-tilt camera with two actuators to extend the range of view. Performance is evaluated on our thermal dataset: TCL Fall Detection Dataset. The proposed model achieves 90.2% average clip accuracy which is better than other approaches.

• 패션비즈니스
• /
• 제26권2호
• /
• pp.143-155
• /
• 2022

The purpose of this study was to develop protective clothing that could alleviate fall impacts. Fall impact protection pants for elderly women were designed, and motion adaptable hip pads and knee pads printed by 3D printing were integrated into the pants and evaluated. First, the design of the fall impact protection pants with variable motion was semi-loose fitting pants that could be worn and detached from the protective pad. A pad pocket was made in the lining inside the pants so that the protective pad could be fixed to the protective area. Second, in the evaluation of the appearance of the fall impact protection pants, the wearer group had a good score of 4.60 or higher for all questions on color, material, ease, and fit. In the evaluation of the insertion method of the protective pad, the flexibility of the pad, and the weight of the pad, the subjects' scores were 4.30~4.80. The fit of the fall impact protection pants was excellent in the texture and elasticity of the outside and inside of the pants. There was no discomfort due to the pad(4.60), and no difficulty in movement during wearing activities was reported. During squatting, it was evaluated as 4.80, indicating that the motion adaptable hip joint and knee pads were highly effective during operation.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권12호
• /
• pp.3991-4007
• /
• 2022

In the public healthcare, a computational system that can automatically and efficiently detect and classify falls from a video sequence has significant potential. With the advancement of deep learning, which can extract temporal and spatial information, has become more widespread. However, traditional 3D CNNs that usually adopt shallow networks cannot obtain higher recognition accuracy than deeper networks. Additionally, some experiences of neural network show that the problem of gradient explosions occurs with increasing the network layers. As a result, an enhanced three-dimensional ResNet-based method for fall detection (3D-ERes-FD) is proposed to directly extract spatio-temporal features to address these issues. In our method, a 50-layer 3D residual network is used to deepen the network for improving fall recognition accuracy. Furthermore, enhanced residual units with four convolutional layers are developed to efficiently reduce the number of parameters and increase the depth of the network. According to the experimental results, the proposed method outperformed several state-of-the-art methods.

• 산업융합연구
• /
• 제16권3호
• /
• pp.1-7
• /
• 2018

본 연구는 지역사회 노인의 일반적 특성 및 건강관련 특성을 조사하여, 낙상두려움 요인을 규명하고, 낙상두려움, 낙상태도 및 낙상효능감과의 관계를 파악하기 위한 서술적 조사연구이다. 연구대상자는 D시의 복지관을 이용하는 노인 140명이었다. SPSS 21.0 프로그램을 이용하여 분석하였다. 연구결과 성별, 동거인, 주관적 건강상태, 통증, 불안전한 걸음걸이에서 낙상두려움의 차이가 있었다. 낙상두려움과 낙상태도(r=-.396, p<.001), 낙상두려움과 낙상효능감(r=-.184, p=.030)은 유의한 음의 상관관계를 보였고, 낙상태도와 낙상효능감(r=.411, <,001)은 양의 상관관계를 보였다. 본 연구결과에 기초하여 낙상두려움, 낙상태도 및 낙상효능감을 향상시킬 수 있는 낙상예방프로그램 개발 및 적용이 필요하다.

• 대한물리의학회지
• /
• 제11권3호
• /
• pp.73-80
• /
• 2016

PURPOSE: The purpose of this study was to investigate the quality of life related to fall experiences in chronic stroke patients. METHODS: This cross-sectional study included 117 patients with stroke from 3 hospitals in D metropolitan city. General characteristics, including fall experiences and quality of life, were assessed through a face-to-face interviews conducted in a quiet place using a questionnaire. Measurement of quality of life in stroke patients was conducted using the Korean Stroke Specific Quality of Life Scale (SS-QOL). To identify the SS-QOL items related to fall experiences, the items of the SS-QOL were considered as independent variables, and the variables that were significantly different according to fall experiences were identified using a univariate analysis. A binary logistic regression was then performed using fall experiences as the independent variable. RESULTS: According to the univariate analysis, self help activities, social role, and upper extremity function were significantly lower in the fall group than that in the non-fall group (p<.05). The findings of the binary logistic regression confirmed that social roles and upper extremity function were the SS-QOL items that were related to fall experience in chronic stroke patients. CONCLUSION: These findings suggest that social roles and upper extremity function may be risk factors for fall experience in patients with chronic stroke.

• Bulletin of the Korean Chemical Society
• /
• 제3권3호
• /
• pp.104-109
• /
• 1982

A method to calculate the magnetic moments for $d^1$ and $d^2$ complexes in a strong crystal field of trigonal symmetry has been developed in this work choosing the trigonal axis (Ⅲ) as the quantization axis. The calculated magnetic moments using this method for $d^1$ and $d^2$ complexes in a strong trigonal ligand field fall in the range of the experimental values. The dipolar shifts for $d^1$ and $d^2$ complexes in a strong trigonal ligand field are also calculated using the calculated magnetic susceptibility components. The calculated values of the dipolar shifts also fall in the reasonable range.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제10권3호
• /
• pp.85-90
• /
• 2021

본 논문에서는 고령자를 위한 개별 웨어러블(Wearable) 기기를 이용한 낙상 감지에 대해 논한다. 신뢰할 수 있는 낙상 감지를 위한 저비용 웨어러블 기기를 설계하기 위해서 대표적인 두 가지 모델을 종합적으로 분석하여 제시한다. 기계 학습 모델인 의사결정 나무(Decision Tree), 랜덤 포래스트(Random Forest), SVM(Support Vector Machine)과 심층 학습 모델인 일차원(One-Dimensional) 합성곱 신경망(Convolutional Neural Network)을 사용하여 낙상 감지 학습 능력을 정량화하였다. 또한 입력 데이터에 적용하기 위한 데이터 분할, 전처리, 특징 추출 방법 등을 고려하여 검토된 모델의 유효성을 평가한다. 실험 결과는 전반적인 성능 향상을 보여주며 심층학습 모델의 유효성을 검증한다.

• 한국의류학회지
• /
• 제41권5호
• /
• pp.939-949
• /
• 2017

This study uses 3D printing technology to design and fabricate a fall impact protection pad with a spacer fabric structure. The design of the pads consists of hexagonal three-dimensional units connected in a honey-comb shape; in addition, the unit consists of a surface layer and a spacer layer. Protect pads were designed as either a hexagonal type or diamond type according to the surface layer structure; subsequently, a spacer filament was also designed as the most basic I-shape type. Designed pads were printed using four types of flexible filaments to select suitable material for a fall impact protection pad. Impact protection performance and bending stiffness were evaluated for the eight type of pad outputs. As a result of the impact protection performance evaluation, when the force of 6,500N was applied, the force passed through the pad was in the range of 1,370-2,132N. FlexSolid$^{(R)}$ and Skinflex$^{TM}$ showed good protection performance and cubicon flexible filament showed the lowest protection. NinjaFlex$^{(R)}$ was found to be the most flexible in the bending stiffness evaluation.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.2451-2454
• /
• 2005

In recent years, the importance of the characterization of fall for a fracture prevention system keeps increasing since fracture from a fall can lead to serious health problems. Fall is one of the major sources which increase morbidity in elderly people. In terms of the cost and the influence to the quality of life, the most serious injury with hip fractures is caused by falls. The traditional methods in characterizing fall patterns have been mainly by the epidemiological surveys. With surveys, the exact data of fall patterns can not been acquired. In this paper, we measured and analyzed with the parameters related to fall pattern such as velocities and accelerations during the motion of falls using 3D motion capture program. We acquired the parameters of the fall pattern of intentional and unexpected fall. The result showed that the variation of velocity and acceleration during fall was very important in characterizing fall pattern, which of vital importance for the development of a fracture prevention system and for the safety of the elderly.