• 대한물리치료과학회지
• /
• 제5권3호
• /
• pp.617-624
• /
• 1998

A variety of neuromuscular diseases in children cause muscle imbalance. impaired function, and resultant deformity of the lower extremities. Equinovarus, equinos, adductor contracture are common deformity of lower extremities in the children. Generally, the transfer was successful in improving or maintaining range of motion, stability of the joint and gait. Postoperative physical therapy is important. Physical therapy was instituted after cast removal. All children received stretching exercise, range of motion exercise for the joint, proprioceptive neuromuscular fascilitation and gait training was administered. This article describes our experience with the physical therapy for tendon transfered spastic cerebral palsy and discusses the therapeutic protocol.

• Journal of the Korean Statistical Society
• /
• 제36권1호
• /
• pp.175-182
• /
• 2007

The support vector machine has been successful in many applications because of its flexibility and high accuracy. However, when a training data set is large or imbalanced, the support vector machine may suffer from significant computational problem or loss of accuracy in predicting minority classes. We propose a modified version of the support vector machine using the K-means clustering that exploits the information in class labels during the clustering process. For large data sets, our method can save the computation time by reducing the number of data points without significant loss of accuracy. Moreover, our method can deal with imbalanced data sets effectively by alleviating the influence of dominant class.

• 한국응용과학기술학회지
• /
• 제36권3호
• /
• pp.797-803
• /
• 2019

Recently, osteosarcopenic obesity (OSO) has been identified and notified world wide. Therefore, this study reviewed OSO related to lifestyle factors such as nutritional intake and exercise. Due to aging, OSO may be initiated by dietary factors and obesity related factors. Reduced muscle mass and increased fat mass may negatively impact bone health causing OSO. The complication of OSO development should be related to dietary imbalance combined with declined exercise and this may contribute to induce OSO by decreasing bone mass, muscle mass, and increasing obesity with aging. To prevent OSO, reaching peak bone mass and building optimal muscle and fat mass through exercise would be recommended. For treating OSO, balanced dietary intake and regular exercise through a whole life would be needed. In addition, sufficient carbohydrate and fat intake for minimizing protein catabolism would be recommended to prevent OSO. The combination of aerobic exercise and resistance training also would be an effective intervention for OSO population.

• International journal of advanced smart convergence
• /
• 제9권4호
• /
• pp.52-61
• /
• 2020

The AHP method was used in 30 provinces of China to construct the index system of creative space efficiency evaluation and determine the weight of each index. The fuzzy comprehensive evaluation method was further used to score the indexes at all levels, and then the total efficiency score was sorted. The purpose of this study is to adjust the regional layout of creative space reasonably and implement financial policies accurately through the evaluation of the efficiency of creative space. The results is ranking top in weight of several indicators, which include the number of incubated Startups, the number of innovation and entrepreneurship mentors, the survival rate of incubator, the innovative training activities, etc. It was also found that Beijing, Shanghai, Jiangsu, Guangdong and Zhejiang ranked first in the score of creative space efficiency. This study is meaningful in that it was In order to effectively solve the problem of the imbalance of the creative space efficiency in China's province, by coordinating the regional pattern, establishing a sound service system and improving the efficiency evaluation system.

• 한국정보과학회 언어공학연구회:학술대회논문집(한글 및 한국어 정보처리)
• /
• 한국정보과학회언어공학연구회 2019년도 제31회 한글 및 한국어 정보처리 학술대회
• /
• pp.434-439
• /
• 2019

딥러닝 기반 분류 모델에 있어 데이터의 클래스 불균형 문제는 소수 클래스의 분류 성능을 크게 저하시킨다. 본 논문에서는 앞서 언급한 클래스 불균형 문제를 보완하기 위한 방안으로 적대적 학습 기법을 제안한다. 적대적 학습 기법의 성능 향상 여부를 확인하기 위해 총 4종의 딥러닝 기반 분류 모델을 정의하였으며, 해당 모델 간 분류 성능을 비교하였다. 실험 결과, 대화 데이터셋을 이용한 모델 학습 시 적대적 학습 기법을 적용할 경우 다수 클래스의 분류 성능은 유지하면서 동시에 소수 클래스의 분류 성능을 크게 향상시킬 수 있음을 확인하였다.

• 한국운동역학회지
• /
• 제25권3호
• /
• pp.265-274
• /
• 2015

Objective : The purpose of this study was to analyze the effect of the elastic band on ballet arabesque based on kinematics analysis. Methods : To observe the effect of the elastic band, the availability of the elastic band during movement was set as the independent variable, and the dependent variables were set by using factors from two different categories such as motor mechanics and kinematics variables. For motor mechanics variable, the muscle activity and the center of pressure(COP)'s trajectory and velocity were used. Furthermore, the physical angle was used for kinematic variables. Data samples from the experiment was used to understand the correlation between independent and dependent variables while using paired samples t-test as a data analysis tool. Results : After analyzing the result of experiment, the usage of the Elastic band on ballet arabesque movement seemed to increase the activity of the agonistic muscle, which is mainly used for movement, and to improve the stability of the supporting leg by decreasing the trajectory and velocity of the center of pressure(COP). Moreover, the elastic band increased the level of elevation of the stretching leg with reducing the angle of the hip joint that resulted into a more stable movement and furthermore providing more beauty while standing on it. Conclusion : The movement training program while the using elastic band are expected to lead to appropriate muscular development and reduce the muscle imbalance, which usually occurs to dancers, during training with unfamiliar specific movements or strengthening muscular strength for a specific movement. In addition, this work is expected to be used as a training reference to understand and learn the fundamentals of movements of ballet and other dance fields.

• 한국콘텐츠학회논문지
• /
• 제22권10호
• /
• pp.861-869
• /
• 2022

투렛증후군 환자에게서 뮤파(Mu wave) 동기화가 깨졌을 때 틱이 발생하고, 그 반대로 뮤파 동기화를 이루면 틱이 발생하지 않는다. 연구시험 결과는 전운동피질(Frontal Cortical 3 사이트)에서 뮤파 동기화를 틱 환자가 인위적으로 하지 않고 뉴로피드백 훈련처럼 자율적으로 뇌파 조절이 이뤄진다면 마찬가지 결과로 틱이 발생하지 않는다는 사실을 시사한다. 피시험자에게 틱을 억제시켰을 때 인지 제어 반응 프로세스가 변경된다. 변경된 인지 제어를 뇌파 주파수 파워를 조절하는 뉴로피드백으로 훈련하면 환자가 인위적으로 틱을 억제하지 않아도 자율적으로 치료가 된다. 연구시험 결과는 뇌 운동영역의 뮤파 통제를 통해 틱이 발생하지 않는 생체신호 지표가 뉴로피드백 훈련의 치료프로토콜이 될 수 있는 단초를 마련하였다. 기존 뉴로피드백 치료 프로토콜인 SMR강화, 세타파-베타파 불균형 수정, 알파파 강화 등에 뮤파 강화를 추가할 수 있게 되었다. 본 연구가 투렛증후군 환자 치료법인 뉴로피드백 치료 프로토콜을 보다 과학적으로 검증하는 후속 연구와 임상시험에 활용될 것이다.

• 스마트미디어저널
• /
• 제10권4호
• /
• pp.45-54
• /
• 2021

피부는 외부 오염으로부터 일차적으로 몸을 보호하는 역할을 한다. 피부병이 발생하게 되면 피부의 보호 기능이 저하되므로 신속한 진단과 처치가 필요하다. 최근 인공지능의 발달로 인해 여러 분야에 기술적용을 위한 연구가 이루어지고 있으며, 피부과에서도 인공지능을 활용해 오진율을 줄여 신속한 치료를 받을 수 있는 환경을 만들기 위한 연구가 진행되고 있다. 종래 연구들의 주된 흐름은 발생 빈도가 낮은 피부질환의 진단이었지만, 본 논문에서는 사람들에게 흔히 발생할 수 있고, 개인이 명확히 판별하기 힘든 티눈과 사마귀를 합성곱 신경망을 통해 분류하는 방법을 제안한다. 사용한 데이터셋은 3개의 클래스로 이루어져 있으며, 총 2,515장의 이미지를 가지고 있다, 학습 데이터 부족과 클래스 불균형 문제가 존재한다. 모델의 학습에는 deep metric 손실 함수와 교차 손실 함수를 이용해 각각 성능을 분석하였으며, 정밀도, 재현율, F1 점수, 정확도의 측면에서 비교한 결과 deep metric 손실 함수에서 더 우수한 성능을 보였다.

• 대한의용생체공학회:의공학회지
• /
• 제43권4호
• /
• pp.241-250
• /
• 2022

It is known that chronic pain and injury of upper limb joint tissue in manual wheelchair users is usually caused by muscle imbalance, and the propulsion speed is reported to increase this muscle imbalance. In this study, kinematic variables, electromyography, and ultrasonographic images of the upper limb were measured and analyzed at two different propulsion speeds to provide a quantitative basis for the risk of upper extremity joint injury. Eleven patients with spinal cord injury for the experimental group (G_E) and 27 healthy adults for the control group (G_C) participated in this study. Joint angles and electromyography were measured while subjects performed self-selected comfortable and fast-speed wheelchair propulsion. Ultrasound images were recorded before and after each propulsion task to measure the acromiohumeral distance (AHD). The range of motion of the shoulder (14.35 deg in G_E; 20.24 deg in G_C) and elbow (5.25 deg in G_E; 2.57 deg in G_C) joints were significantly decreased (p<0.001). Muscle activation levels of the anterior deltoid, posterior deltoid, biceps brachii, and triceps brachii increased at fast propulsion. Specifically, triceps brachii showed a significant increase in muscle activation at fast propulsion. AHD decreased at fast propulsion. Moreover, the AHD of G_E was already narrowed by about 60% compared to the G_C from the pre-tests. Increased load on wheelchair propulsion, such as fast propulsion, is considered to cause upper limb joint impingement and soft tissue injury due to overuse of the extensor muscles in a narrow joint space. It is expected that the results of this study can be a quantitative and objective basis for training and rehabilitation for manual wheelchair users to prevent joint pain and damage.

• 미래기술융합논문지
• /
• 제2권3호
• /
• pp.59-66
• /
• 2023

본 디지털 전환에서 가장 중요한 것은 SW 기술이다. 그러나 많은 기업이 SW 기술 및 인력 확보에 어려움을 겪고 있다. 특히 SW 인력 부족은 더욱 증가할 것이라 보고되고 있다. 정부는 SW 인력 수급정책을 해소하기 위해 인력양성 정책과 많은 지원사업을 수행하고 있지만, 이러한 정책이 효과적으로 수립되기 위해서는 소프트웨어 산업의 수요와 공급에 대한 정확한 예측이 필수적이다. 따라서 본 연구는 소프트웨어 산업의 수급 불균형을 해소하기 위해 동태적 구조 분석을 수행할 수 있는 시스템 다이내믹스 방법론을 활용하여 시뮬레이션을 개발하였다. 시스템 다이내믹스는 소프트웨어 산업의 인력 수급 불균형 현상에 대해 동태적인 시각에서 그 원인과 정책대안을 찾기에 적절하다. 세부적으로 미국의 노동통계국의(U.S. Bureau of Labor Statistics, BLS) 방법론을 사용하여 적용하여 소프트웨어 산업의 인력 수요 및 공급 예측 모델을 개발하였고, 시나리오 분석을 수행하여 정책적 시사점을 도출하였다.