• Proceedings of the Korea Information Processing Society Conference
• /
• 2017.11a
• /
• pp.885-886
• /
• 2017

본 연구에서는 스마트 깔창을 사용한 보행 분석을 위한 데이터 전처리 기법을 제안한다. 이를 위해 본 논문에서는 평지 보행, 오르막 보행, 내리막 보행, 계단 오르기, 계단 내려가기, 달리기, 빠른 보행의 7가지 종류의 보행 데이터를 수집하였다. 수집한 데이터에 대해 제안한 데이터 전처리 기법을 적용한 결과를 실제 걸음 수와 비교하였다. 실험결과 전처리한 결과가 실제 걸음 수에 가까운 결과를 보임을 확인하였다.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.10
• /
• pp.33-39
• /
• 2019

In this paper, we propose a parametric model for analyzing the motion information obtained from the acceleration sensors to measure the activity of the human body. The motion of the upper body and the lower body does not occur at the same time, and the motion analysis method using a single motion sensor involves a lot of errors. In this study, the 3-axis accelerometer is attached to the arms and legs, the body's activity data are measured, the momentum of the arms and legs are calculated for each channel, and the linear predictive coefficient is obtained for each channel. The periodicity of the upper body and the lower body is determined by analyzing the correlation between the channels. The linear predictive coefficient and the periodic value are used as data to measure the type of exercise and the amount of exercise. In the proposed method, we measured four types of movements such as walking, stair climbing, slow hill climbing, and fast hill descending. In order to verify the usefulness of the parameters, the recognition results are presented using the linear predictive coefficient and the periodic value for each motion as the neural network input.

• Journal of the Korea Convergence Society
• /
• v.9 no.11
• /
• pp.385-391
• /
• 2018

The purpose of this study was to examine the lower-extremity muscle activation of flat-footed and normal-footed subjects descending stairs while wearing high-heels, thereby identifying any imbalance between the medial and lateral muscles.Thirty female students volunteered to participate in this study. The navicular drop test (NDT) was applied to the selection criteria for the flat-footed group and the normal-footed group. Surface electromyographic data was collected from the medial and lateral quadriceps, hamstrings, and gastrocnemius. Activation of MG and LG was significantly lower in the flat-footed group than in the normal-footed group. Both groups showed significant increases in MQMH and MHMG, but the co-activation in the medial and lateral muscles was lower in the flat-footed group. The co-activation ratios showed a significantly greater MQMH/LQLH in the flat-footed group. Flat-footed subjects who wear high-heels are more likely to experience impaired knee joint alignment than normal-footed subjects. Therefore, flat-footed subjects should use caution when descending stairs while wearing high-heels.

• Korean Journal of Applied Biomechanics
• /
• v.16 no.4
• /
• pp.31-38
• /
• 2006

The purpose of this study was to investigate the effect of changing the steps height on the joint moment of lower extremity in stair-descent activity of elderly persons. Data were collected by 3-D cinematography and force platform. 9 male elderly subjects in the 60s and 70s participated in this study. All subjects performed a stair-descent in four different heights of stairs (10, 14, 18, 22cm) having 5 step staircase. The results were as follows. 1. For the step height of 22cm the maximum. plantarflexion moment was the smallest and the largest for the step height of 14cm. 2. There was not a statistical difference shown for the extension moment of the knee joint for the different height of steps. 3. There was not a statistical difference shown for the flexion moment of the hip joint for the varying height of steps but on average for the 18cm step this increased rapidly. 4. The smallest maximum. value for inversion moment was revealed for the step height of 10cm and this increased significantly for the step height of 22cm. 5. The smallest maximum. value for abduction moment of the hip joint was revealed for the step height of 10cm and this increased significantly for the step height of 22cm. 6. There was no significant difference shown for the maximum. abduction moment for the hip joint. The main conclusion is that there is a huge difference in the moment of the lower extremities for the elderly while walking down a stairs with a step height above 18 cm and that this moment increased or decreased rapidly under a condition of step height being 22cm. With the results from this research and related research of elderly walking upstairs it can be shown that the step height has a large role in the safety for the elderly.

• Journal of The Korean Society of Integrative Medicine
• /
• v.2 no.3
• /
• pp.57-63
• /
• 2014

Purpose : The purpose of this study was to identify the muscle activity of leg during stair down in the subjects with flatfoot and normal foot. Methods : The fourteen subjects with the flatfoot group and the fifteen subjects with the normal foot group volunteered for this study. All subjects descended the stairs that the height was 20cm and consisted 25 stairs. The target muscles for recording muscle activity were posterior fiber of gluteus medius, vastus medialis and vastus lateralis oblique, semitendinosus and biceps femoris, tibialis anterior, and medial and lateral fiber of gastrocnemius muscles. The muscle activity was recorded using the wireless EMG system. Results : The flatfoot group had significantly lower the muscle activity of posterior fiber of gluteus medius than the normal foot group in stance phase during stair down(p<.05). The flatfoot group had significantly higher the muscle activity of biceps femoris and tibialis anterior than the normal foot group in swing phase during stair down(p<.05). Conclusions : This study proposed that the subject with flatfoot should train the strengthening exercise for posterior fiber of gluteus medius.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.11
• /
• pp.29-38
• /
• 2022

This paper proposes a system for classifying gait types using an ensemble deep learning network for gait data measured by a smart insole equipped with multi-sensors. The gait type classification system consists of a part for normalizing the data measured by the insole, a part for extracting gait features using a deep learning network, and a part for classifying the gait type by inputting the extracted features. Two kinds of gait feature maps were extracted by independently learning networks based on CNNs and LSTMs with different characteristics. The final ensemble network classification results were obtained by combining the classification results. For the seven types of gait for adults in their 20s and 30s: walking, running, fast walking, going up and down stairs, and going up and down hills, multi-sensor data was classified into a proposed ensemble network. As a result, it was confirmed that the classification rate was higher than 90%.

• Journal of Nutrition and Health
• /
• v.50 no.6
• /
• pp.552-564
• /
• 2017

Purpose: The purpose of this study was to measure energy expenditure (EE) the metabolic equivalents (METs) of 13 common physical activities by using a portable telemetry gas exchange system ($K4b^2$) and to assess the accuracy of the accelerometer (Actigraph $GT3X^+$) by gender in Korean adults. Methods: A total of 109 adults (54 males, 55 females) with normal BMI (body mass index) participated in this study. EE and METs of 13 selected activities were simultaneously measured by the $K4b^2$ portable indirect calorimeter and predicted by the $GT3X^+$ Actigraph accelerometer. The accuracy of the accelerometer was assessed by comparing the predicted with the measured EE and METs. Results: EE (kcal/kg/hr) and METs of treadmill walking (3.2 km/h, 4.8 km/h and 5.6 km/h) and running (6.4 km/h) were significantly higher in female than in male participants (p < 0.05). On the other hand, the accelerometer significantly underestimated the EE and METs for all activities except descending stairs, moderate walking, and fast walking in males as well as descending stairs in females. Low intensity activities had the highest rate of accurate classifications (88.3% in males and 91.3% females), whereas vigorous intensity activities had the lowest rate of accurate classifications (43.6% in males and 27.7% in females). Across all activities, the rate of accurate classification was significantly higher in males than in females (75.2% and 58.3% respectively, p < 0.01). Error between the accelerometer and $K4b^2$ was smaller in males than in females, and EE and METs were more accurately estimated during treadmill activities than other activities in both males and females. Conclusion: The accelerometer underestimated EE and METs across various activities in Korean adults. In addition, there appears to be a gender difference in the rate of accurate accelerometer classification of activities according to intensity. Our results indicate the need to develop new accelerometer equations for this population, and gender differences should be considered.