• Journal of the Korea Society for Simulation
• /
• v.23 no.2
• /
• pp.73-84
• /
• 2014

Recently, researches on the application of IT technology to various fields including traditional industries are becoming more popular. One challenge in the field of education is to understand the way how technology may support learning, and research on self-directed learning has been accelerated by integrating education and IT technology. The process of self-directed learning in e-learning applications such as Car Maintenance Training is very difficult and complicated. Previous studies on car maintenance training applications provided simple training scenarios with predetermined action sequences. To incorporate self-directed learning in car maintenance training, however, trainees must be able to perform various maintenance operations himself and experience various situations. To provide such functionality, it is necessary to obtain an accurate response for various operations of trainees, but it requires complicated calculations with respect to varieties in the electrical and mechanical processes of a car. In this paper, we develop a logic simulation agent using JESS inference engine in which self-directed learning is achieved by capturing the behavior of trainees and simulating car operations without complicated physical simulations in car maintenance training.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.24 no.1
• /
• pp.15-19
• /
• 2020

Purpose Generative Adversarial Network(GAN) is one of deep learning technologies. This is a way to create a real fake image after learning the real image. In this study, after acquiring artificial intelligence images through GAN, We were compared and evaluated with real scan time images. We want to see if these technologies are potentially useful. Materials and Methods 30 patients who underwent ¹⁸F-FDG Brain PET/CT scanning at Severance Hospital, were acquired in 15-minute List mode and reconstructed into 1,2,3,4,5 and 15minute images, respectively. 25 out of 30 patients were used as learning images for learning of GAN and 5 patients used as verification images for confirming the learning model. The program was implemented using the Python and Tensorflow frameworks. After learning using the Pix2Pix model of GAN technology, this learning model generated artificial intelligence images. The artificial intelligence image generated in this way were evaluated as Mean Square Error(MSE), Peak Signal to Noise Ratio(PSNR), and Structural Similarity Index(SSIM) with real scan time image. Results The trained model was evaluated with the verification image. As a result, The 15-minute image created by the 5-minute image rather than 1-minute after the start of the scan showed a smaller MSE, and the PSNR and SSIM increased. Conclusion Through this study, it was confirmed that AI imaging technology is applicable. In the future, if these artificial intelligence imaging technologies are applied to nuclear medicine imaging, it will be possible to acquire images even with a short scan time, which can be expected to reduce artifacts caused by patient movement and increase the efficiency of the scanning room.

• Journal of the Korea Convergence Society
• /
• v.12 no.3
• /
• pp.165-176
• /
• 2021

Recently, interest in home training and changes in lifestyle are expanding the market in the healthcare field, and high value-added fashion products reflecting the dumbbell economy phenomenon are being released. This study had the following objectives: to investigate the possibility of developing a fashion item that can be applied to the dumbbell economy phenomenon; to develop the UI/UX of a smartphone application for beginners who wish to work out their upper and lower bodies regardless of time and space; and to create a wearable customized smart athleisure fashion device. First, the study identified factors related to exercise methods, breathing techniques, and range of exercises for beginners by investigating the postures of workouts of the upper and lower bodies by angles. Based on the results, the study collected empirical data through a user needs analysis from muscle strengthening exercise experts to verify the significance of the study and use as fundamental data. Second, the study developed the UI/UX of a smartphone application with three different contents: counting, suggesting exercise postures, and providing exercise calendars. Further, the study analyzed necessary user-centered concepts and characteristics in terms of design and technology and developed a wearable customized smart athleisure fashion device based on the results.

• KIPS Transactions on Computer and Communication Systems
• /
• v.11 no.5
• /
• pp.157-166
• /
• 2022

Exercise is necessary for a healthy life, but it is recommended that it be conducted in a non-face-to-face environment in the context of an epidemic such as COVID-19. However, in the existing non-face-to-face exercise content, it is possible to recognize exercise movements, but the process of interpreting and providing feedback information is not automated. Therefore, in this paper, to solve this problem, we propose a method of creating a formalized rule to track the contents of exercise and the motions that constitute it. To make such a rule, first make a rule for the overall exercise content, and then create a tracking rule for the motions that make up the exercise. A motion tracking rule can be created by dividing the motion into steps and defining a key frame pose that divides the steps, and creating a transition rule between states and states represented by the key frame poses. The rules created in this way are premised on the use of posture and motion recognition technology using motion capture equipment, and are used for logical development for automation of application of these technologies. By using the rules proposed in this paper, not only recognizing the motions appearing in the exercise process, but also automating the interpretation of the entire motion process, making it possible to produce more advanced contents such as an artificial intelligence training system. Accordingly, the quality of feedback on the exercise process can be improved.

• 한국체육학회지인문사회과학편
• /
• v.54 no.1
• /
• pp.535-544
• /
• 2015

This study was performed to determine the effect of low-intensity resistance training with blood flow restriction (BFR) on muscle volume and strength in elderly women. Sixteen elderly women (70.9±4.6 years) were divided into low (30% 1RM) and high (75% 1RM) intense resistance training groups. Tourniquet cuff (Zimmer, Germany) for BFR was applied only to the right leg during the training period. All subjects performed unilateral leg press, leg extension and leg curl (3 sets×12 repetitions) for 10 weeks (2d/wk). Blood pressure was increased from 110 to 240 mmHg during the training period at the most proximal region of exercised leg. Muscle volume and cross-sectional area (CSA) were measured by MRI and body composition was monitored by dual-energy X-ray absorptiometry (DEXA) and isokinetic muscular strength were analyzed in both legs. The quadriceps CSA (15.2%, p<.001) and muscle volume (13.8%, p<.001) were increased in high-intense trained leg with BFR and the increased rate was highest among groups. The quadriceps CSA (9.8%, p<.001) and muscle volume (6.9%, p<.001) were increased in low-intensity training group with BFR and their increased rates were higher than control groups. The strength by exercise training was significantly improved in all groups and tended to be higher in BFR groups. These results demonstrate low-intensity resistance training with blood flow restriction could be an effective way to improve muscle volume and strength in elderly women.

• Journal of Intelligence and Information Systems
• /
• v.28 no.2
• /
• pp.19-31
• /
• 2022

In Machine learning, we usually divide the entire data into training data and test data, train the model using training data, and use test data to determine the accuracy and generalization performance of the model. In the case of models with low generalization performance, the prediction accuracy of newly data is significantly reduced, and the model is said to be overfit. This study is about a method of generating training data based on central limit theorem and combining it with existed training data to increase normality and using this data to train models and increase generalization performance. To this, data were generated using sample mean and standard deviation for each feature of the data by utilizing the characteristic of central limit theorem, and new training data was constructed by combining them with existed training data. To determine the degree of increase in normality, the Kolmogorov-Smirnov normality test was conducted, and it was confirmed that the new training data showed increased normality compared to the existed data. Generalization performance was measured through differences in prediction accuracy for training data and test data. As a result of measuring the degree of increase in generalization performance by applying this to K-Nearest Neighbors (KNN), Logistic Regression, and Linear Discriminant Analysis (LDA), it was confirmed that generalization performance was improved for KNN, a non-parametric technique, and LDA, which assumes normality between model building.

• Korean Journal of Applied Biomechanics
• /
• v.18 no.1
• /
• pp.85-95
• /
• 2008

This study is analyzing about application of taping by movement about shoulder joint's isometric contraction. M. college students take part in experiment. WEMG-8 and HUMAC system are used. Findings were as follows: EMG of muscle's MVIC at each angle before and after taping. 1. In flexion, EMG with taping is effective for supra spinatus at $0^{\circ}{\cdot}45^{\circ}{\cdot}90^{\circ}$, anterior deltoid at $0^{\circ}{\cdot}45^{\circ}$ and biceps brachii at $0^{\circ}{\cdot}90^{\circ}$. 2. In extension, EMG with taping is effective for triceps brachii at $0^{\circ}$, latissimus dorsi at $90^{\circ}$ and posterior deltoid at $45^{\circ}{\cdot}90^{\circ}$. 3. Each angle viewpoint, EMG of latissimus dorsi in extension can be arranged in its high order as $90^{\circ}<45^{\circ}$, $0^{\circ}$ without taping and $90^{\circ}<0^{\circ}$ respectively. EMG of posterior deltoid in extension is in its high order as $90^{\circ}<45^{\circ}<0^{\circ}$ without taping and $90^{\circ}<0^{\circ}$.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.3
• /
• pp.423-429
• /
• 2018

Objective: This study was conducted to investigate the effects of WBVE on biomechanical factor analysis of drop landing jumps before and after a four week training program. Methods: Participants were divided into two group: VEG (n=5, age: $25.7{\pm}2.3yrs$, height: $170{\pm}7.6cm$, weight: $69.3{\pm}8.3kg$) and OEG (n=5, age: $24.6{\pm}3.4yrs$, height: $164{\pm}4.9cm$, weight: $58.8{\pm}9.2kg$). Ten infrared cameras (Vicon, UK) with a sampling rate of 100 Hz were used in two GRF measurement systems (AMTI, USA). Results: The variability of the center of mass was largest at the falling phase, and there was a great risk of injury when landing after the jump. Second, the jumping heights of the VEG (vibration exercise group) were higher than those of the OEG (only exercise group), regardless of training period. Third, there were significant differences in the hip joint P1 (flexion) and knee joint P2 (extension) between the exercise groups after 4 weeks of training. However, there were no significant differences among training periods or phases. Conclusion: regardless of training periods, the VEG showed increased jump height compared with the OEG, but the consistency between the jump height and the lower joint power could not be determined.

• Journal of Life Science
• /
• v.8 no.5
• /
• pp.563-570
• /
• 1998

The seven (7) housewives were used as subjects at three times per weeks for twelve (12) weeks in order to find out the effects of aerobic exercise and weight training on body composition and blood lipid. Each subject's weight, lean body mass, percent body fat, BMI and blood lipid were measured immediately after the training and the results compared with the same prior to exercises were obtained as follows ; 1. The weight and percent body fat of the subjects were slightly but not significantly decreased, however the lean body mass following training was significantly increased with 1.3 %. BMI S RBW were also not significantly decreased. 2. Calory intake was 1929.9 cal before the training and 1896.0 cal after the training, which doesn't shows much difference. 3. The blood lipid such as TC and LDL-C were a little increased after the training, but HDL-C shows significant increase of 22.7 %, and HDL-C/TC was significantly increased with 13.2 % (p<.05 ) as well. However, TG shows significant decrease (p<.05 ).

• Journal of the Korean Data and Information Science Society
• /
• v.24 no.6
• /
• pp.1241-1251
• /
• 2013

The purpose of this study was to investigate and compare the effects of aerobic and complex exercise on body composition and blood lipids in the middle-aged women. Sixteen women whose ages ranged in 40 to 50 years were included in the sample of the study. The sample was divided into two groups: (a) aerobic exercise group (n = 8) and (b) combined exercise training group (n = 8). The aerobic exercise program consisted of bicycle ergometer, stepper, and treadmill, whereas; the combined exercise program was designed to improve muscular strength and aerobic capacity. Both programs took place 4 times a week for 12 weeks with the gradual increase of intensity (HRmax 60% 75% and 1 RM 60% 80%). Data were analyzed by nonparametric methods for pre-post within group mean differences (Wilcoxon signed rank test) and for between group mean differences (Wilcoxon rank sum test). Results indicated that there were statistically significant differences in BMI, body fat mass, and triglyceride within the sample of combined exercise; whereas, no significance existed in any variables within the aerobic exercise group. Results also revealed that statistical significance did exist in body fat mass between the combined and aerobic exercise group. These results implies that the combined exercise may be superior to aerobic only excercise for the body composition and blood lipid of the middle-aged women.