• 한국컴퓨터정보학회논문지
• /
• 제19권11호
• /
• pp.63-72
• /
• 2014

본 논문에서는 깊이 카메라를 이용한 사용자의 손 모양 인식 시스템을 제안한다. 특히, 본 시스템에서 이용된 손 모양 템플릿은 수화 언어 중 한국어를 채택 하였다. 손 모양 인식 시스템은 손의 특징 검출과 특징들을 이용한 손 인식으로 크게 2 단계의 작업으로 나눌 수 있다. 손의 특징으로는 손가락의 개수, 길이, 손바닥의 넓이 등이 있다. 특징을 추출하기 위해 본 논문에서는 거리 변환(Distance Transform)을 이용한 손의 뼈대 검출 방법을 제안한다. 이 방법을 사용하면 기존의 윤곽선(Contour)을 이용한 손가락 검출보다 정확도 측면에서 향상된다. 손 모양 인식으로 손의 특징을 이용하여 각 분기를 잘 나눌 수 있는 결정 트리(Decision Tree)를 사용한다. 사용자의 입력을 이용하면 분기값이 정확하게 나오지 못하므로 이 분기 값을 결정하기 위해 해당 분기마다 SVM을 이용하여 분기값을 결정하였다. 실험결과에서는 기존의 연구 방법보다 제안된 방법이 특징 추출과 인식하는데 있어 더욱 개선되었음을 보인다.

• 대한안전경영과학회지
• /
• 제26권2호
• /
• pp.87-92
• /
• 2024

This study aims to compare six observational methods for assessing arm- and hand-intensive tasks, based on literature review. The comparison was conducted in viewpoints of body regions, force/external load, motion repetition, other factors including static posture, coupling, duration/break, pace, temperature, precision task, and final risk or exposure level. The number of risk factors assessed was more, and assessment procedure was more complex than the observational methods for assessing whole-body postural loads such as Ovako Working Posture Analysis System(OWAS), Rapid Upper Limb Assessment(RULA), and Rapid Entire Body Assessment(REBA). Due to these, the intra- and inter-reliabilities were not high. A past study showed that while Hand Arm Risk Assessment Method(HARM) identified the smallest proportion of the work tasks as high risk, Strain Index(SI) and Quick Exposure Check(QEC) hand/wrist were the most rigorous with classifying most work tasks as high risk. This study showed that depending on the observational technique compared, the evaluation factors, risk or exposure level, and evaluation results were different, making it necessary to select a technique appropriate for the characteristics of the work being assessed.

• Safety and Health at Work
• /
• 제5권1호
• /
• pp.27-31
• /
• 2014

Background: Carpal tunnel syndrome (CTS) is a common work-related peripheral neuropathy. In addition to grip force and repetitive hand exertions, wrist posture (hyperextension and hyperflexion) may be a risk factor for CTS among workers. However, findings of studies evaluating the relationship between wrist posture and CTS are inconsistent. The purpose of this paper was to conduct a meta-analysis of existing studies to evaluate the evidence of the relationship between wrist posture at work and risk of CTS. Methods: PubMed and Google Scholar were searched to identify relevant studies published between 1980 and 2012. The following search terms were used: "work related", "carpal tunnel syndrome", "wrist posture", and "epidemiology". The studies defined wrist posture as the deviation of the wrist in extension or flexion from a neutral wrist posture. Relative risk (RR) of individual studies for postural risk was pooled to evaluate the overall risk of wrist posture on CTS. Results: Nine studies met the inclusion criteria. All were cross-sectional or case-control designs and relied on self-report or observer's estimates for wrist posture assessment. The pooled RR of work-related CTS increased with increasing hours of exposure to wrist deviation or extension/flexion [RR = 2.01; 95% confidence interval (CI): 1.646-2.43; p < 0.01: Shore-adjusted 95% CI: 1.32-2.97]. Conclusion: We found evidence that prolonged exposure to non-neutral wrist postures is associated with a twofold increased risk for CTS compared with low hours of exposure to non-neutral wrist postures. Workplace interventions to prevent CTS should incorporate training and engineering interventions that reduce sustained non-neutral wrist postures.

• 디지털융복합연구
• /
• 제10권9호
• /
• pp.435-441
• /
• 2012

본 연구는 정상 성인을 대상으로 광범위한 어깨관절 각도의 팔자세 유형에서 여러 가지 손의 쥐기 강도의 차이에 따라 어깨주위근 활성도를 측정하여, 직업과 관련된 어깨 손상을 예방하고 치료하는데 유용한 기초임상자료로 제공하고자 한다. 팔자세의 유형에 따라 다양한 강도로 쥐기를 시행 할 때 어깨 주위 근육의 활성도를 알아보기 위해 모든 대상자들은 MVC를 측정하였고 동일한 자세에서 어깨관절 $0^{\circ}$, $90^{\circ}$, $160^{\circ}$에서 각각 최대 쥐기 강도의 30%, 50%, 70%를 무작위로 실시하여 팔자세의 유형에서 쥐기강도에 따른 앞세모근, 가시위근, 위등세모근, 가시아래근의 %MVC를 구하여 어깨근 활성도를 알아보았다. 팔자세의 유형에 따른 각 집단의 %MVC를 비교하기 위하여 $0^{\circ}$에서 최대 힘의 30%, 50%, 70%로 쥐기를 비교한 결과 앞세모근, 가시위근, 위등세모근, 가시아래근 간의 근활성도에서는 유의한 차이가 나타나지 않았으나, $90^{\circ}$와 $160^{\circ}$에서는 앞세모근, 가시위근, 위등세모근, 가시아래근에서 유의한 차이가 나타났으며(p<.001). 사후검정결과 모든 각도에서 앞세모근과 가시아래근의 근활성도가 높게 나타났으며, 위등세모근의 근활성도는 가장 낮게 나타났다. 다양한 산업현장의 근로 여건 등을 고려하여 과도한 손의 움직임은 안정성과 가동성에 기여를 하는 어깨주위 근육들에 손상을 초래할 수 있다. 본 연구에서는 특히 가시아래근의 경우 팔의 각도가 클수록 그리고 쥐기 힘이 커질수록 근활성도가 증가 하는 양상을 보였다. 이러한 양상은 머리위로 손을 올려 사용하는 작업현장에서의 어깨손상예방과 손상된 근육을 선택적으로 재활하는 측면에서 기초 임상 자료로 활용 될 수 있을 것이다.

• 대한의용생체공학회:의공학회지
• /
• 제43권5호
• /
• pp.361-368
• /
• 2022

The purpose of this study was to develop a hand rehabilitation training system for hemiplegic patients. We also tried to find out five hand postures (WF: Wrist Flexion, WE: Wrist Extension, BG: Ball Grip, HG: Hook Grip, RE: Rest) in real-time using multi-channel EMG-based deep learning. We performed a pre-processing method that converts to Spider Chart image data for the classification of hand movement from five test subjects (total 1,500 data sets) using Convolution Neural Networks (CNN) deep learning with an 8-channel armband. As a result of this study, the recognition accuracy was 92% for WF, 94% for WE, 76% for BG, 82% for HG, and 88% for RE. Also, ten physical therapists participated for the usability evaluation. The questionnaire consisted of 7 items of acceptance, interest, and satisfaction, and the mean and standard deviation were calculated by dividing each into a 5-point scale. As a result, high scores were obtained in immersion and interest in game (4.6±0.43), convenience of the device (4.9±0.30), and satisfaction after treatment (4.1±0.48). On the other hand, Conformity of intention for treatment (3.90±0.49) was relatively low. This is thought to be because the game play may be difficult depending on the degree of spasticity of the hemiplegic patient, and compensation may occur in patient with weakened target muscles. Therefore, it is necessary to develop a rehabilitation program suitable for the degree of disability of the patient.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2006년도 하계종합학술대회
• /
• pp.739-740
• /
• 2006

본 논문에서는 입력한 데이터를 분석하고 비교하여 손 모양 데이터 편집기의 기준 손 모양을 결정하는 방법을 제안한다. 즉, 입력한 손 모양 데이터에 대해 빈도수 혹은 평균값을 사용하여 기준 손 모양을 결정하는 방법을 제안한다. 입력한 손 모양 데이터로부터 제안한 방법을 통해 얻어진 손 모양이 실제 표현하고 자 한 손 모양과 일치하는지 실험을 통해 비교하였는데, 6,135개의 입력 데이터에 대해 두 가지 방법 모두 90.6% 일치하였다.

• 대한산업공학회지
• /
• 제42권2호
• /
• pp.122-128
• /
• 2016

The purpose of this study is to improve the firing elevation driving method for towed howitzer to prevent the musculoskeletal disorders. To adjust the firing elevation, it is required to rotate the hand wheel and this work has been done manually in the firing test range as the same method as field artillery troops. In the firing test range, the motor-driven firing elevation adjustment device was developed to improve the working efficiency and safety. These were compared by using posture classification scheme of RULA and REBA. It was measured elapsed time to investigate the improved operational efficiency. The optimal posture of upper body to operate the hand wheel for field artillery troops was proposed.

• 정보처리학회논문지B
• /
• 제15B권5호
• /
• pp.435-448
• /
• 2008

사용자 포즈의 3차원 데이터 생성을 통한 3차원 포즈 인식은 2차원 포즈 인식의 문제점을 해결하기 위해서 많이 연구되고 있지만, 3차원 표면 데이터의 방대한 양으로 포즈 인식에서 중요한 특징 추출(feature extraction)이 어렵고 수행 시간이 많이 걸리는 문제점을 가지고 있다. 본 논문에서는 3차원 포즈 인식의 두 가지 문제점인 특징 추출의 어려움과 느린 처리속도를 개선하기 위해서 3차원 형상복원 기술로 모델의 3차원 표면 점들로 구성된 데이터를 2차원 데이터로 변환하는 차원 축소(dimension reduction) 방법을 제안한다. 실린더형 외곽점을 이용한 메쉬없는 매개변수화(meshless parameterization) 방법은 방대한 데이터인 3차원 포즈 데이터를 2차원 데이터로 변환하여 특징 추출과 매칭과정의 연산 속도를 향상 시키며, 특징 추출의 효율성 검증을 위해 간단한 환경에서 실험이 가능한 손 포즈 인식 및 인간 포즈 인식에 적용하였다.

• Journal of Preventive Medicine and Public Health
• /
• 제29권3호
• /
• pp.565-577
• /
• 1996

This study was conducted to evaluate the association of work posture with cervical spine abnormality toward 106 microwave-oven assemblers. A self-administered questionnaire was used to obtain a general characteristics and a work history of workers. The posture of neck and shoulder joint of workers were measured with video tape recording and the simple X-ray of cervical spine was checked-up to observe the X-ray abnormality including degenerative change, curvature abnormality, disc space narrowing or disc canal narrowing. The result were as follows. 1. The prevalence of degenerative change among cervicobrachial disorder workers was 44.3% (47 persons), curvature abnormality was 43.4%(46 persons), disc space narrowing was 21.7%(23 persons), and disc canal narrowing was 21.7%(23 persons). 2. The prevalence of degenerative change at cervical spine was increased with the degree of neck flexion(flexed versus neutral, odds ratio [OR]=2.7), the total work posture of neck(mild or severe awkward versus neutral ; OR=1.2, 3.4). 3. The prevalence of degenerative change at cervical spine was increased with the degree of the right shoulder flexion, the heaviness of the materials carried by the right hand and the degree of awkwardness at the total work posture of right shoulder(p<0.05). 4. There was no evidence of association between curvature abnormality, disc space narrowing, disc canal narrowing and work posture. In conclusion the awkward work posture was related with degenerative change of cervical spine among microwave oven assembling workers and the further study in these field must be made to prove the association objectively.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2003년도 ISIS 2003
• /
• pp.50-53
• /
• 2003

We describe a method for estimating new hand views from a single 2D hand image using decomposed approach with subgroup-based scheme. With this method, we can get the simplicity in the sense of computation by comparing the image with models in the promising subgroup instead of comparing with all models. It shows more effectiveness in recognition by process depend on each subgroup and easy of extension.