• Proceedings of the KOSOMBE Conference
• /
• v.1991 no.11
• /
• pp.93-95
• /
• 1991

As the ensemble averaged dZ/dt signal during exercise is smoothed, it is difficult to find the distinctive marks. The cross correlation function was made use of estmating these marks. LVET was calculated based on the calculated parameters of the characteristic points. For the accuracy validation, LVET calculated by hand, by the ensemble average and the cross correl at ion were compared.

• Journal of Korea Multimedia Society
• /
• v.21 no.8
• /
• pp.982-990
• /
• 2018

In recent years, many wearable devices and mobile apps related to life care have been developed, and a service for measuring the movement during walking and showing the amount of exercise has been provided. However, they do not measure walking in detail, so there may be errors in the total calorie consumption. If the user's behavior is measured by a multi-axis sensor and learned by a machine learning algorithm to recognize the kind of behavior, the detailed operation of walking can be autonomously distinguished and the total calorie consumption can be calculated more than the conventional method. In order to verify this, we measured activities and created a model using a machine learning algorithm. As a result of the comparison experiment, it was confirmed that the average accuracy was 12.5% or more higher than that of the conventional method. Also, in the measurement of the momentum, the calorie consumption accuracy is more than 49.53% than that of the conventional method. If the activity recognition is performed using the wearable device and the machine learning algorithm, the accuracy can be improved and the energy consumption calculation accuracy can be improved.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.6
• /
• pp.37-46
• /
• 2021

In this paper, we designed and implemented a program to measure and to judge the accuracy of yoga postures using Azure Kinect. The program measures all joint positions of the user through Azure Kinect Camera and sensors. The measured values of joints are used as data to determine accuracy in two ways. The measured joint data are determined by trigonometry and Pythagoras theorem to determine the angle of the joint. In addition, the measured joint value is changed to relative position value. The calculated and obtained values are compared to the joint values and relative position values of the desired posture to determine the accuracy. Azure Kinect Camera organizes the screen so that users can check their posture and gives feedback on the user's posture accuracy to improve their posture.

• Journal of the Korea Convergence Society
• /
• v.11 no.4
• /
• pp.119-124
• /
• 2020

In this paper, in order to encourage the user's exercise, we presented an exercise goal that considers the user's weight and exercise state, and dealt with a study on an app that gives a goal using GPS information. Unlike the vague numbers and times suggested in the existing app, it is presented specifically with the surrounding buildings or structures using GPS information. In addition, to use competitive psychology to exercise encouragement, it shows the movement information of people connected to the app and allows users to use the competitive psychology to get the effect of exercising many people. The app creates coordinates of major buildings and sets markings using the Naver Map SDK location information to present specific targets. It is easy for users to get bored if they give a goal every time, and the boredom that the user feels decreases the interest in the exercise. In order to not to lose interest in athletic interest. the app switches to game mode and give a light goal that doesn't matter user's weight or exercise status, and rewards user for achieving the suggested goals. Game mode is added to app that connects a person's will to practice. It adds fun elements to create interest, and uses competitiveness to help you live a healthy life with a steady workout. Technically, to improve the accuracy of smart-phone map display using GPS and the tilt processing was to be able to display the exact location.

• 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 Korean Physical Therapy Science
• /
• v.11 no.3
• /
• pp.14-27
• /
• 2004

This study approaches the effects of Balance Training on excercise performance and the prevention from the injuries caused by excercise. The subjects of the Balance Training program are female exercise beginners and the research period covers 8 weeks from January 10 to March 7, 2003. The research objects are 19 female golf beginners in 30s to 40s, who live in Seoul or Seongnam in Gyeonggi province and have played golf less than 6 months. The programs of the Balance Training and exercise performance were conducted to an 11 experimental group among the 19 research objects at the same time, and only the exercise performance program was applied to an 8 control group for 8 weeks. Before and after 8 weeks' application of the research programs to each group, the research subjects were examined, especially the components of their bodies, the balance and the performance capability were measured both before and after the test. The frequency of injuries by exercise was measured after the test, and the difference of the frequency was compared with the frequency before exercise. First, the experimental group, in a measurement of balance, showed that SN, MB, SAr and SAg of static balance decreased in a situation of MEO, MEC, GEO, GEC, TBEO, TBO, FHEO, FEO(p <0.05), but the control group increased. Second, the analysis on the change of exercise performance indicated better improvement in distance, ball speed, and accuracy of the experimental group than the control group(p<0.05). Third, the experience of injuries showed that there were 2 injuries in the experimental group and 11 injuries in the control group. The injured parts were 2 cases in the hands and fingers of the experimental group, and 1 case in the shoulder, 4 in the elbows, 4 in the hands and fingers and 2 in the lumber of the control group. From the above-mentioned results, it is recognized that the Balance Training program improved the exercise performance of female golf beginners and had good effects on the prevention from injuries. Accordingly, if this program is applied to sports-beginners, it will contribute to the improvement of the public health.

• Journal of the Korean School Mathematics Society
• /
• v.5 no.2
• /
• pp.101-109
• /
• 2002

Among interactive dynamic geometry softwares, Cinderella has some merits on the accuracy of algorithms and compatibility with internet. In this paper we compare dynamic geometry softwares such as GSP, Cabri II, Cinderella briefly and we design a web based interactive learning materials using the exercise editor of Cinderella and some Java applets, and we propose a web based interactive teaching and learning model in which achievement test can be given by the clickings on the help icon.

• Journal of Biomedical Engineering Research
• /
• v.5 no.1
• /
• pp.5-8
• /
• 1984

As the ensemble averaged dz/dt signal during exercise gets smoothed, it is difficult to find the distinctive marks for estimation of stroke volume. The cross correlation function was made use of estmating these marks for automatic calculation by computer from the ensemble averaged dz/dt signal. LVET(Left Ventricular Ejection Time) and stroke volume were estimated based on the calculated parameters from the characteristic points. LVET, stroke volume calculated by hand, by the ensemble average and the cross correlation were compared for accuracy validation.

• Journal of Biomedical Engineering Research
• /
• v.31 no.4
• /
• pp.316-320
• /
• 2010

HRV(Heart rate variability) analysis parameter is widely used as an index to evaluate the autonomic nervous system and cardiac function. For reliable HRV analysis, we need to acquire the accurate ECG signals. Most of commercially available portable ECG devices have low sampling rate because of low power consumption and small size issues, which make it difficult to measure RR-interval accurately. This study is to improve the accuracy of RR-interval by developing R-wave interpolation technique, based on the morphological characteristics of the QRS complex. When the developed method was applied to ECG obtained at 200 Hz and the results were compared with 1000 Hz reference device, the error range decreased by 1.33 times in sitting and by 2.38 times in cycling exercise. Therefore, the proposed interpolation technique is thought to be useful to improve the accuracy of R-R interval in the portable ECG device with low sampling rate.

• The Korean Journal of Physiology
• /
• v.1 no.1
• /
• pp.83-90
• /
• 1967

In order to evaluate the accuracy of the measurement of maximal oxygen intake (MOI), the MOI in seven subjects was determined 3 to 4 times in each individual. Following a 10 minute warm-up on treadmill (4.3 km/hr with 9 degree grade), the subject was asked to run at a speed of 8.73 km/hr on treadmill for a period of 3 minutes at a given grade which was elevated in a step-wise manner from zero to the level of exhaustion. Following a 3 minute run, the subject was allowed to rest for a period of 3 to 5 minutes. During each period of running, several cardio-pulmonary functions were determined and the range of variability for each measurement was computed. The oxygen consumption during the maximal work load was taken as the MOI. The results may be summarized as follows: (1) The minute volume, the oxygen consumption and the heart rate increased linearly until the grade was elevated to 9 degree above which these values were leveled off. (2) The minute volume and the heart rate during maximal exorcise were $87.4{\pm}8.10\;1/min\;and\;187{\pm}3.7$ per minute, respectively. (3) The maximal oxygen intake which corresponds to the oxygen consumption during maximal exercise was averaged to 3.04 1/min. (4) The coefficient of variance for the maximal oxygen intake was 6.32% while the corresponding values for the minute volume and the heart rate during maximal exercise were 5.22 and 2. 14%, respectively.