• 한국운동역학회지
• /
• 제31권2호
• /
• pp.87-94
• /
• 2021

Objective: Identification of meaningful patterns and trends in large volumes of unstructured data is an important task in various research areas. In the present study, we gathered golf swing image data and did quantitative analysis of swing image. Method: We collected golf swing images of 30 novice players and 30 professional players in this study. Results: We selected important features of swing posture and employed data mining algorithm to classify whether a player is an expert or a novice. Moreover, our proposed method could offer quantitative advices for golf beginners for correcting their swing. Conclusion: Finally, we found a possibility that our proposed method can be expanded to golf swing correction system

• 대한가정학회지
• /
• 제30권3호
• /
• pp.56-62
• /
• 1992

The purpose of this study was to characterize the somatotype of children and to provide fundamental data for the construction of the dress figure. The subjects for anthropometric measurements were 384 elementary school children aged from 6 to 7 living in Seoul and Pucheon. The data were analyzed statistically according to SPSS/PC ＋ version 3.1. Through the factor analysis, six factors were obtained. The six factors represented the body girth and weight, the height and sleeve length, the trunk length, the shoulder size, the body curvature, and the posture of upper torso, respectively. The subjects were classified into six clusters. Among the six clusters, four clusters covered about 95.9% of the whole subjects were determined as the sources of fundamental data for the children's dress figure.

• 전자공학회논문지CI
• /
• 제45권3호
• /
• pp.135-141
• /
• 2008

본 논문은 3차원 가속 센서들과 장갑 형태로 제작한 RFID 리더기를 사용하여, 사용자의 신체 상태에 따른 동작 분석을 통해, 일상생활에서 사용자의 액티비티(Activity)를 자동으로 인식하는 새로운 방법을 제안한다. 두 개의 가속 센서로부터 획득한 움직임 정보로부터 선택 트리(Decision Tree) 방법을 통해 사용자의 5가지 자세 정보(Posture Information)를 구별하고, 손목에 장착된 가속 센서와 장갑 형태로 제작된 RFID 리더를 통해 인식한 객체와의 상호 작용을 통해서 도구를 사용하는 액티비티(Instrumental Activity)를 인식하는데 사용한다. 이를 위해, 객체 의존적인 손의 움직임을 학습에 의해 미리 5가지 카테고리로 분류한 후, 해당 객체와 인식된 움직임의 일치 여부를 확인한 후, 최종적으로 사용자의 신체 상태와 액티비티를 결정한다. 실험 결과에 의하면, 제안된 계층적 움직임 분석 방법은 20가지의 일상생활 액티비티들을 인식하는데 있어서 90%이상의 정확도를 보였다.

• Journal of Korean Neurosurgical Society
• /
• 제60권5호
• /
• pp.560-566
• /
• 2017

Objectvie : The global sagittal postural patterns as characterized by Roussouly classification have been previously described in various ethnicities, there were no studies investigated in Koreans. To analyze the distribution of the global sagittal postural patterns in Korean adults using Roussouly classification, the author prospectively studied. Methods : 252 asymptomatic Korean adults was recruited. Data was obtained by reviewing the films for each subject. Spinopelvic parameters were measured and sagittal postural patterns were then determined according to Roussouly classification. We compared the data across different ethnicities from our study and a previous study to further characterize Korean sagittal postures. Results : The subject included 151 males and 101 females, with mean age of $33.2{\pm}8.2years$. The average descriptive results were as below : thoracic kyphosis $28.6{\pm}7.7^{\circ}$, lumbar lordosis $48.3{\pm}10.2^{\circ}$, sacral slope $37.8{\pm}5.8^{\circ}$, pelvic incidence $45.1{\pm}7.5^{\circ}$, pelvic tilt $9.4{\pm}6.7^{\circ}$, spinosacral angle $130.1{\pm}5.4^{\circ}$, and sagittal vertical axis $16.25{\pm}22.5mm$. 125 subjects among 252 (49.6%) belonged to Roussouly type 3 (namely neutral). There were also 58 (23%), 33 (13.1%), and 36 (14.3) subjects in type 1, 2, and 4 (namely non-neutral), respectively. Conclusion : Enrolling 252 asymptomatic Korean adults, this prospective study found that 49.6% of asymptomatic Korean adults possessed a sagittal posture of Roussouly type 3. All radiologic parameters follows general concept of spinal sagittal balance pattern. Overall, this study might be a basis for further investigation of spinal sagittal balance.

• 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.

• The Journal of Korean Physical Therapy
• /
• 제31권5호
• /
• pp.279-285
• /
• 2019

Purpose: This study examined the effects of spinal stabilization exercises using visual feedback on the gross motor function and balance of the sitting posture in children with cerebral palsy. Methods: The subjects were 18 children with cerebral palsy aged 8-15 years in the I-III stages of the Gross Motor Function Classification System. The subjects were divided into an experimental group (n=9) and control group (n=9). The experimental group was treated with 30 minutes of neurodevelopmental treatment and 20 minutes of spinal stabilization exercises using visual feedback. The control group was treated with 30 minutes of neurodevelopmental treatment and 20 minutes of spinal stabilization exercises without visual feedback. Both groups participated in the experiment twice a week for eight weeks. The Gross Motor Function Measurement was performed to evaluate the changes between pre- and the post-intervention in gross motor function. The Seated Limit of Stability Surface Area was measured to evaluate the changes in trunk balance. Results: Both experimental and control groups showed a significant increase in the gross motor function and trunk balance (p<0.05). The experimental group showed a significant increase in gross motor function compared to the control group (p<0.05). The experimental group showed a significant increase in the dynamic trunk balance in all directions when measuring the Seated Limit of Stability Surface Area (p<0.05). Conclusion: Spinal stabilization exercises using visual feedback for the neurodevelopmental treatment of children with cerebral palsy can improve their gross motor function and trunk balance when in a sitting posture more effectively.

• 한국컴퓨터정보학회논문지
• /
• 제28권10호
• /
• pp.9-16
• /
• 2023

태권도 겨루기의 전자호구, 축구의 VAR 등 스포츠에서 기술 발전이 고도화되고 있다. 하지만 태권도 품새는 사람이 직접 자세를 눈으로 보고 판단하며 지도하기 때문에 때로는 대회의 현장에서 판정시비가 일어난다. 본 연구는 인공지능을 이용하여 태권도 동작을 더 정확하게 판단하고 평가할 수 있는 인공지능 모델을 제안한다. 본 연구에서는 촬영 및 수집한 데이터를 전처리한 후 학습, 테스트, 검증 세트로 분리한다. 분리한 데이터를 각 모델과 조건을 적용하여 학습한 후 비교하여 가장 좋은 성능의 모델을 제시한다. 각 조건의 모델은 정확도, Precision, Recall, F1-Score, 학습 소요 시간, Top-n error의 값을 비교하였고 그 결과 ResNet50과 Adam을 사용한 조건에서 학습한 모델의 성능이 가장 우수한 것으로 나타났다. 본 연구에서 제시한 모델을 활용하여 교육 현장이나 대회 등 다양한 방면에서 활용할 수 있을 것으로 기대한다.

• 문화기술의 융합
• /
• 제7권3호
• /
• pp.577-582
• /
• 2021

최근 AR, VR 및 스마트 디바이스 기술의 발전에 따라 피트니스 산업에서도 비대면 환경을 기반으로 한 서비스 수요가 증가하고 있다. 비대면 온라인 홈트레이닝 서비스는 기존의 오프라인 서비스에 비해 시간과 장소의 제약이 없다는 장점이 있으나 운동 기구의 부재 및 사용자의 정확한 운동 자세 유지여부, 운동량의 측정이 어려운 단점이 존재한다. 본 연구에서는 이러한 단점을 보완할 수 있는 표준 운동 프로그램을 개발하고 딥러닝 기반 신체 자세 추정 영상처리를 통하여 새로운 비대면 홈트레이닝 어플리케이션 알고리즘을 제안한다. 본 연구의 알고리즘 기반 어플리케이션을 활용한다면 표준 운동 프로그램 영상의 트레이너를 사용자가 직접 보고 따라하면서 사용자 스스로 자세를 교정하며 정확한 운동이 가능하다. 나아가 본 연구의 알고리즘을 용도에 맞게 커스터마이징 한다면 공연, 영화, 동아리 활동, 컨퍼런스 분야로의 적용도 가능할 것이다.

• 복식문화연구
• /
• 제19권1호
• /
• pp.176-190
• /
• 2011

Today's young generation in digital era has a rich education environment and convenient life, on the other hand, there was negative impact on growth as normal body type because of adverse impact on an excessive study and insufficient exercise, etc. Also, for these people in IT culture generation, using small mobile including computer for long time is becoming main issue as changing factor in posture and body type in terms of spine like their neck disc. This body-typed characteristic reaches to normal adult body type in the process of physical development of adult woman and has least modification in body type. Therefore, despite of early young generation, body suitability of upper body clothes might caused imbalance. So, for intended to early 20s women, to design clothes with consideration on imbalance of body type by bended and curved spine, body type studies about size of upper body and forms are needed. As this researcher measured the body type of early 20s college women in metropolitan area, changes in body type of young generation with use of digital equipment recently were recognized since straight body type was decreased unequally and had characteristic in terms of changes to be bended body type. The changes of these body type should be considered to make clothes. Also, since there are some restrictions on this research objects in terms of local and numbers of measured objects, a broad interpretation of result on this research should be really careful.

• 대한치과보철학회지
• /
• 제37권3호
• /
• pp.328-342
• /
• 1999

This study was performed to investigate the factors related to tooth wear. For this study, 78 patients with temporomandibular disorders and 76 dental students without any signs and symptoms of temporomandibular disorders were selected as the patients group and as the normal group, respectively. Preferred chewing side, Angle's classification, lateral guidance pattern, head and shoulder posture were observed clinically. Electromyographic activity of anterior temporalis and masseter muscle were recorded with $BioEMG^{(R)}$ and occlusal status were recorded with $T-Scan^{(R)}$. Wear facet area of each tooth was measured from working model of upper arch corresponding to the occlusal status from T-Scan. Wear facet area were measured with planimeter in $mm^2$. Total area were divided into incisal, canine, posterior tooth area. Anterior wearfacet area was incisor area plus canine area, and unilateral area was anterior area plus posterior area. The data collected were analyzed by SAS statistical program and the results of this study were as follows: 1. There was no significant difference between the two groups in total werafacet area, and male subjects showed tendency to have larger area in the normal group but female subjects showed tendency vice versa. 2. There was no significant difference related to preferred chewing side and Angle's classification, however some difference was observed by lateral guidance pattern. Anterior wear facet area in subjects of canine guidance was the largest in the three subgroups. 3. Subjects with head tilting to right side had larger posterior and total area, and subjects with higher shoulder in right side had larger canine and anterior area than any other subgrous. 4. Electromyographic activity of masseter muscle was more correlated with wear facet area than anterior temporalis muscle, and tooth contact number and force were significantly correlated with wear facet area, but the most important factor affecting tooth attrition was age.