• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2005.11a
• /
• pp.155-158
• /
• 2005

MRI 스캔시 화상평면내에서 촬상대상물체의 회전은 MRI 신호에 위상오차와 불균일 표본화를 일으킨다. MRI 신호의 위상오차와 불균일 표본화에 대한 문제의 모델은 화상평면내 임의 중심과 원점에 관한 회전운동에 의해 열화된 MRI 신호들사이에 위상차가 존재함을 나타낸다. 이에 아티팩트가 포함된 MR 화상의 화질을 개선하기위해서 다음과 같은 방법을 제안한다. 우선, 2차원 회전운동의 회전각은 이미 알려져 있고, 회전중심의 위치가 미지인 경우에 대해 위상보정에 기초한 아티팩트를 보정하는 알고리즘과, 다음으로, 회전중심과 각도가 모두 미지인 2차원 회전운동에 대해 아티팩트를 보정하는 알고리즘을 제안한다. 이때, 미지 운동 파라메타를 예측하기위해 촬상대상물체의 경계바깥쪽에서 이상적인 MR 화상의 에너지는 최소가 되고, 촬상대상물체의 회전이 존재할 때 측정된 에너지는 증가한다는 성질을 이용한다. 이러한 성질을 이용해서 각 위상부호화 단계에서 미지의 회전각 크기를 추정하기위한 평가함수가 도입된다. 최종적으로 시뮬레이션 화상 및 실제화상에 적용해서 제안한 본 방법의 유효성을 확인한다.

• Journal of the Korea Convergence Society
• /
• v.11 no.8
• /
• pp.269-278
• /
• 2020

The purpose of this study was to investigate the effect of left ventricular diastolic function on exercise capacity in hypertensive patients with obesity compared to the obese group. Adults who visited a general hospital in Gyeonggi-do from 2016 to 2019(man: 308, women: 192) were divided into 4 groups according to hypertension and obesity. In the hypertensive obesity group(IV), the A wave and E/E' wave were significantly higher than the normotensive obesity group(II), and the E' wave was significantly lower(respectively p<0.001). The group IV had significantly lower METS(metabolic equivalents) and exercise duration than the group II(respectively p<0.001). In group IV, E/A ratio was positively correlated with METS(p=0.025) and exercise duration(p=0.026). In contrast, E/E' wave in these groups showed a negative correlation with the exercise duration(p=0.046).

• Journal of the Korea Convergence Society
• /
• v.11 no.2
• /
• pp.271-279
• /
• 2020

Squats and lunges are important exercises for strengthening the trunk and lower body among various free weight exercises. It should be achieved safe and effective excise through establishing of theoretical basis for exercise posture and standard movement. Therefore, it's necessary to develop the exercise model in order to prepare the scientific countermeasures for the prevent injuries and error movement through optimal exercise movement. For this purpose, it is effective to use appropriate instruments for motion compensation according to the optical motion and error motion. In this paper, we develop a motion model analysis system based on dynamic motion through the four-point load cell for dynamic motion analysis. Proposed analytical method, the optimal and the error motion numerical data is obtained through the dynamic motion analysis. And we verified that dynamic movement is simplified to establish the motion modeling according to the classification motion and the numerical quantification data for analyzing.

• Journal of the Korea Convergence Society
• /
• v.10 no.2
• /
• pp.309-313
• /
• 2019

This study examined the response of the EMG of URA, LRA, IO, EO and RFM of various types of abdominal motion (crunch, spine V-up on ball, prone V-up on slide board, prone V-up on TRX, and prone V-up power wheel). The subjects performed anisometric contact of abs during these exercises. Tests have shown that there were no statistically significant differences between EO, URA and LRA between any movements. However, during the inspection of IO, the positive-wawed V-up motion showed significantly greater muscle activity than during the slide movement. Also, EMG activity during crunch was significantly lower than any other five exercises. These results indicate that in the implementation of equilateral absolutism, the equipment-free based exercise gives an impetus similar to equipment-based exercise. Abdominal muscle tissue is considered one of the five components that make up an individual's core. The abdominal muscles also ensure proper functioning of the lumbar spine. Although all abdominal muscles contribute to lumbar stabilization, TA & IO has been shown to perform major stabilizers.

• Journal of the Korea Convergence Society
• /
• v.9 no.4
• /
• pp.261-269
• /
• 2018

The purpose of this study was to determined the converge effects of Kaatsu treatment on body compositions, physical fitness and dynamic and static balance during unmilled rice dumbbell exercise in older women. They are divided into three groups(Kaatsu treatment+exercise, n=12, non-Kaatsu treatment+exercise, n=11, Control, n=12). In this study, there were a no significant differences on body weight and lean body mass and body mass index between the group, but there was a significant differences on percent of body fat between the group(P<.001). There was a significant differences on left grip strength between the group, and significant differences on flexibility and agility after the unmilled rice dumbbell exercise training. There were a significant differences on the dynamic and static balance between the group after the unmilled rice dumbbell exercise training(respectively P<.001, P<.05).

• Journal of the Korea Convergence Society
• /
• v.8 no.7
• /
• pp.305-313
• /
• 2017

The purpose of this study is to investigate the effect of the level of participation in sports for the disabled on the community attachment. The subjects of this study were 227 persons with physical disabilities in D city. The analysis method was analyzed by factor analysis, frequency analysis, independent t-test, one-way ANOVA and multiple regression analysis using SPSS 21.0 program. The results of this study are as follows: First, there is a high level of community attachment to male(sex), 40's and 50's(by age group) and 1st and 2nd grade(by disability grade). Second, in the degree of participation, the duration of exercise and duration of exercise, duration of exercise in dependency, and duration of exercise and intensity of exercise were found to have a positive effect on identity. As a result, it affected the consciousness of local community. In future research, it is necessary to study the psychological effect connected with community.

• Journal of the Institute of Convergence Signal Processing
• /
• v.23 no.4
• /
• pp.234-240
• /
• 2022

This paper proposes a customized AI exercise recommendation service for balancing the relative amount of exercise according to the working environment by each occupation. WISDM database is collected by using acceleration and gyro sensors, and is a dataset that classifies physical activities into 18 categories. Our system recommends a adaptive exercise using the analyzed activity type after classifying 18 physical activities into 3 physical activities types such as whole body, upper body and lower body. 1 Dimensional convolutional neural network is used for classifying a physical activity in this paper. Proposed model is composed of a convolution blocks in which 1D convolution layers with a various sized kernel are connected in parallel. Convolution blocks can extract a detailed local features of input pattern effectively that can be extracted from deep neural network models, as applying multi 1D convolution layers to input pattern. To evaluate performance of the proposed neural network model, as a result of comparing the previous recurrent neural network, our method showed a remarkable 98.4% accuracy.

• Journal of the Korea Convergence Society
• /
• v.11 no.8
• /
• pp.159-163
• /
• 2020

In this study, the flow analyses around according to the existence or non- existence of the trailer's deflector and the shapes were carried out. In the absence of a deflector, the kinetic energy of the turbulence behind the container also generates higher kinetic energy in a wider area than in the presence of a deflector, which adversely affects the vehicle's driving performance. As a trailer's wind deflector-free model has unstable flow rates around the trailer and high kinetic energy of turbulence than a model with a deflector, it can be thought that the increase of fuel economy can be expected by installing a deflector in the trailer. By applying the study result on flow analysis near trailer due to shape of wind deflector, this study is seen to be suitable for the aesthetic convergence.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.6
• /
• pp.155-161
• /
• 2021

Gesture recognition analytics through a camera in real time have been widely studied in recent years. Since a small number of features from human joints are extracted, low accuracy of classifying models is get in conventional gesture recognition studies. In this paper, CBAM (Convolutional Block Attention Module) with high accuracy for classifying images is proposed as a classification model and algorithm calculating the angle of joints depending on actions is presented to solve the issues. Employing five exercise gestures images from the fitness posture images provided by AI Hub, the images are applied to the classification model. Important 8-joint angles information for classifying the exercise gestures is extracted from the images by using MediaPipe, a graph-based framework provided by Google. Setting the features as input of the classification model, the classification model is learned. From the simulation results, it is confirmed that the exercise gestures are classified with high accuracy in the proposed model.

• Journal of the Korea Convergence Society
• /
• v.10 no.10
• /
• pp.337-346
• /
• 2019

The purpose of this study was to investigate the convergence factors affecting disease management efforts of the middle-aged population who have comorbidities of all three metabolic diseases: type 2 diabetes, hypertension, and dyslipidemia. This study used raw data from the 2015 community health survey(CHS). A multiple hierarchical regression analysis was performed that the included variables explained 20.1% of the variance in weight-loss efforts, 6.8% of exercise efforts and 5.3% diet efforts respectively. This study revealed associations among gender, socioeconomic status, and behavioral habits of smoking and drinking with disease-management efforts. It is important to design a health service or supportive intervention with consideration of multiple factors for patients with multiple metabolic disease.