• Journal of Sleep Medicine
• /
• v.15 no.2
• /
• pp.48-54
• /
• 2018

Objectives: The aim of this study was to develop a predicting model for the optimal continuous positive airway pressure (CPAP) for obstructive sleep apnea (OSA) patient with obesity by using a machine learning. Methods: We retrospectively investigated the medical records of 162 OSA patients who had obesity [body mass index (BMI) ≥ 25] and undertaken successful CPAP titration study. We divided the data to a training set (90%) and a test set (10%), randomly. We made a random forest model and a least absolute shrinkage and selection operator (lasso) regression model to predict the optimal pressure by using the training set, and then applied our models and previous reported equations to the test set. To compare the fitness of each models, we used a correlation coefficient (CC) and a mean absolute error (MAE). Results: The random forest model showed the best performance {CC 0.78 [95% confidence interval (CI) 0.43-0.93], MAE 1.20}. The lasso regression model also showed the improved result [CC 0.78 (95% CI 0.42-0.93), MAE 1.26] compared to the Hoffstein equation [CC 0.68 (95% CI 0.23-0.89), MAE 1.34] and the Choi's equation [CC 0.72 (95% CI 0.30-0.90), MAE 1.40]. Conclusions: Our random forest model and lasso model ($26.213+0.084{\times}BMI+0.004{\times}$apnea-hypopnea index+$0.004{\times}oxygen$ desaturation index-$0.215{\times}mean$ oxygen saturation) showed the improved performance compared to the previous reported equations. The further study for other subgroup or phenotype of OSA is required.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.6
• /
• pp.19-28
• /
• 2021

Nowadays, interest in health care is increasing due to Coronavirus (COVID-19), and a lot of people are doing home training as there are more difficulties in using fitness centers and public facilities that are used together. In this paper, we propose a personalized exercise recommendation algorithm using personalized propensity information to provide more accurate and meaningful exercise recommendation to home training users. Thus, we classify the data according to the criteria for obesity with a k-nearest neighbor algorithm using personal information that can represent individuals, such as eating habits information and physical conditions. Furthermore, we differentiate the exercise dataset by the level of exercise activities. Based on the neighborhood information of each dataset, we provide personalized exercise recommendations to users through a dimensionality reduction algorithm (SVD) among model-based collaborative filtering methods. Therefore, we can solve the problem of data sparsity and scalability of memory-based collaborative filtering recommendation techniques and we verify the accuracy and performance of the proposed algorithms.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.5
• /
• pp.177-183
• /
• 2022

Recently, interesting of home training is getting bigger due to COVID-19. Accordingly, research on applying HAR(human activity recognition) technology to home training has been conducted. However, existing paper of HAR proposed static activity instead of dynamic activity. In this paper, the deep learning model where dynamic exercise posture can be analyzed and the accuracy of the user's exercise posture can be shown is proposed. Fitness images of AI-hub are analyzed by blaze pose. The experiment is compared with three types of deep learning model: RNN(recurrent neural network), LSTM(long short-term memory), CNN(convolution neural network). In simulation results, it was shown that the f1-score of RNN, LSTM and CNN is 0.49, 0.87 and 0.98, respectively. It was confirmed that CNN is more suitable for human activity recognition than other models from simulation results. More exercise postures can be analyzed using a variety learning data.

• Journal of Life Science
• /
• v.22 no.4
• /
• pp.545-551
• /
• 2012

Pressurization walk training (PWT) with blood flow occlusion has been investigated with regard to muscle hypertrophy and physical fitness function in athletes and healthy people. However, the cardiorespiratory and cardiovascular responses of obese people to PWT are unknown. Thus, we investigated the effects of PWT on body composition (Weight, FM, LBM, %fat, BMI), cardiovascular responses (HR, SV, CO, TVC), and cardiorespiratory responses ($VO_2max$, VEmax, HRmax) in middle-aged obese women. They participated in walk training with (n=15) blood flow occlusion and cross-sectional areas of the quadriceps on both legs. Five sets of 3-min walking (5.5 km/h at 5% grade) and 1-min resting were performed twice a day, 5 days/week for 3 weeks. The results showed that the LBM was significantly increased, and decreased body weight of reducing FM, %bodyfat in PWT ($p$<0.05). For the cardiovascular response, SBP and TPR were significantly decreased ($p$<0.05), and CO increased ($p$<0.05). In addition, the $VO_2max$ and VEmax were improved through PWT. Therefore, this study suggests that the presence of obesity in middle-aged women may result in body composition, cardiorespiratory, and cardiovascular responses caused by PWT.

• Journal of Life Science
• /
• v.22 no.2
• /
• pp.184-191
• /
• 2012

The purpose of this study was to examine the effect of 16 weeks of resistance training on the fatigue factor, muscle soreness, oxidative stress, and myokine in elite weightlifters. A total of 10 subjects (six male, four female) participated in this study. The results were compared according to baseline, 8 weeks, and 16 weeks. Ammonia and Pi were increased through 16 weeks of resistance training, but this result was not significant. CK was significantly (p<0.05) increased at 8 weeks and 16 weeks compared to baseline, while LDH was significantly (p<0.05) increased at 8 weeks compared to baseline. The MDA of the oxidative stress factor was significantly (p<0.05) increased at 8 weeks compared to baseline and 16 weeks, and TAS of the antioxidant factor was significantly (p<0.05) increased at 8 weeks compared to baseline. The IL-15 of the myokine was significantly (p<0.05) increased at baseline compared to 8 weeks and 16 weeks. In conclusion, 16 weeks of high-intensity resistance training may have a positive effect on peripheral fatigue factors, muscle soreness, oxidative stress, and myokine in elite weightlifters.

• Journal of Korea Water Resources Association
• /
• v.33 no.2
• /
• pp.247-262
• /
• 2000

In this paper, the WSANN(Water Stage Analysis with Neural Network) model was presented so as to predict flood water stage at Jindong which has been the major stream gauging station in Nakdong river basin. The WSANN model used the improved backpropagation training algorithm which was complemented by the momentum method, improvement of initial condition and adaptive-learning rate and the data which were used for this study were classified into training and testing data sets. An empirical equation was derived to determine optimal hidden layer node between the hidden layer node and threshold iteration number. And, the calibration of the WSANN model was performed by the four training data sets. As a result of calibration, the WSANN22 and WSANN32 model were selected for the optimal models which would be used for model verification. The model verification was carried out so as to evaluate model fitness with the two-untrained testing data sets. And, flood water stages were reasonably predicted through the results of statistical analysis. As results of this study, further research activities are needed for the construction of a real-time warning of the impending flood and for the control of flood water stage with neural network method in river basin. basin.

• Journal of rehabilitation welfare engineering & assistive technology
• /
• v.12 no.1
• /
• pp.53-62
• /
• 2018

In this study, we developed a smart 1RM system for national health management and physical fitness, which enables quantitative 1RM measurement in various types of exercise using digital pulley technology, and to test the effect on training by using it. We developed the smart 1RM system, which is composed of portable muscle strength measuring device, Bluetooth communication based mobile phone data transmission and circuit diagram, and height adjustable system body. We recruited the 30 participants with 20th aged and divided into training and non-performing groups with 15 participants randomly. The participants performed 5 sets of elbow, lumbar, knee extension / flexion 10 times using smart 1RM system and the experimental period was 3 days a week for a total of 8 weeks. The experimental results showed that the maximum strength of the elbow, lumbar, and knee joints was significantly improved before and after maximal muscle strength training in the training group. Oxygen intakes during 1RM exercise mode showed 10.91% than endurance. To verify the validity of the smart 1RM maximal strength data, the reliability was 0.895 (* p <0.00). This study can be applied to the early rehabilitation treatment of the elderly and rehabilitation patients more quantitatively using the national health care.

• Journal of the Korean Applied Science and Technology
• /
• v.38 no.2
• /
• pp.608-617
• /
• 2021

The purpose of this study was to investigate the effects of 8 weeks of core training on the abdominal muscle strength, sargent lumps, Y-balance and equilibrium freestyle skiers'. Fourteen freestyle players were randomly assigned to the exercise group(Ex)(n=7) and control groups(Con)(n=7). Ex undertook a 8-week training program that included exercises for the Bench, Sideway bench, and Nordic hamstring whereas Con performed their usual activities. Muscular fitness were significant effect observed, but there was no difference between groups. The Y-balance test was effective in the front left, and the left and right left posteromedial showed significantly differences between the groups. In the total score, the Ex decreased to 7.5cm in the left and right difference and 1.66cm in the post, but the control group increased from 3.73cm in the pre-test to 7.01cm in the post-test. In the Equilibrium test, there was significant result in condition(C) in C2, C5, and C6. In conclusion, the 8-week core training was found to have a beneficial effect on the postural control in freestyle skiers'.

• Journal of the Korean Applied Science and Technology
• /
• v.41 no.2
• /
• pp.413-423
• /
• 2024

Sixteen male college students were divided into two groups: a face-to-face group(n=8) and a real-time non-face-to-face exercise group(n=8), engaging in 30minute sessions twice a week for a duration of 8 weeks. Body composition and physical strength were measured as dependent variables before and after the home training period. For data analysis, a two-way ANOVA with repeated measures was conducted to evaluate the effects on body composition and physical strength, considering differences in exercise methods and measurement periods. Post hoc analysis using Bonferroni correction was applied. To compare the mean difference in change between groups, the pre-post difference was calculated, and an independent t-test was performed. The statistical significance level was set at p<.05. The results showed that 8 weeks of home training led to an increase in skeletal muscle mass and improvements in muscle strength, muscular endurance, and cardiorespiratory endurance in male college students, regardless of whether they participated in face-to-face or real-time non-face-to-face exercise. Moreover, there was no significant difference in exercise effectiveness between the face-to-face and real-time non-face-to-face exercise methods. Thus, these findings suggest that real-time non-face-to-face exercise can be as effective as face-to-face exercise in enhancing skeletal muscles and physical strength in male college students. Additionally, if a real-time non-face-to-face exercise program is validated for individuals with mobility issues or the elderly, it could serve as an effective alternative for those who face challenges in participating in face-to-face exercise sessions.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.2
• /
• pp.702-723
• /
• 2020

The application of machine learning (ML) in intrusion detection has attracted much attention with the rapid growth of information security threat. As an efficient multi-label classifier, kernel extreme learning machine (KELM) has been gradually used in intrusion detection system. However, the performance of KELM heavily relies on the kernel selection. In this paper, a novel multiple kernel extreme learning machine (MKELM) model combining the ReliefF with nature-inspired methods is proposed for intrusion detection. The MKELM is designed to estimate whether the attack is carried out and the ReliefF is used as a preprocessor of MKELM to select appropriate features. In addition, the nature-inspired methods whose fitness functions are defined based on the kernel alignment are employed to build the optimal composite kernel in the MKELM. The KDD99, NSL and Kyoto datasets are used to evaluate the performance of the model. The experimental results indicate that the optimal composite kernel function can be determined by using any heuristic optimization method, including PSO, GA, GWO, BA and DE. Since the filter-based feature selection method is combined with the multiple kernel learning approach independent of the classifier, the proposed model can have a good performance while saving a lot of training time.