• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.07a
• /
• pp.495-496
• /
• 2023

최근 보급되고 있는 스크린 야구장을 많은 이용자가 단순한 타격만을 하고 피드백이 없이 일회성으로 이용하고 있고 이용자의 타격 자세를 평가해주는 기능을 제공하지 않고 있다. 부정확한 자세로 타격을 하게 되면 부상의 위험도 있고, 타격 실력도 향상될 수 없다. 따라서 이용자가 올바른 타격자세를 취할 수 있도록 자세를 평가 해주는 시스템이 필요하다. 본 논문에서는 구글의 미디어 파이프와 딥러닝 기술을 활용하여 타격 자세 영상을 인식하여 타격 자세를 평가해주는 시스템을 개발하였다. 제안한 시스템은 사전에 다양한 영상을 LSTM 알고리즘으로 학습하여 이용자의 타격자세를 4개 등급으로 평가해준다. 이를 활용하여 스크린 야구장에서 카메라만 설치하여 간단하게 사용 가능하며 이용자들이 타격 자세를 자체 평가할 수 있다.

• Physical Therapy Korea
• /
• v.5 no.4
• /
• pp.20-29
• /
• 1998

연구의 배경 앉은 자세에서 일어서기는 일상생활동작중 흔한 동작중의 하나이다. 노인들을 포함한 많은 환자들은 앉은 자세에서 일어서기에 어려움이 있고 속도가 감소한다. 이 연구의 목적은 다른 두 속도로 앉은 자세에서 일어서는 동작을 실행할 때 최대 지면반발력의 세개의 요소를 비교하는 것이다. 대상자 22명의 건강한 성인 (20-36세)을 대상으로 하였다. 실험방법 앉은 자세에서 일어서기동작 수행중 최대 지면반발력을 측정하기 위하여 힘판을 사용하였다. 대상자들은 메트로놈을 이용하여 각각 느린 속도 (3초: 총 앉은 자세에서 일어서기동작 수행시간)와 빠른 속도(1.5초)에서 앉은 자세에서 일어서기를 수행하였다. 느린 속도와 빠른 속도중 최대 지면반발력을 비교하기 위해 짝비교 t-검정을 사용하였다. 결과 빠른 속도시 최대 지면반발력의 수직(p<0.05), 전-후(p<0.05), 내-외(p<0.05) 요소에서 느린 속도시와 차이가 있었다. 최대 지면반발력의 모든 요소가 움직임의 속도의 증가에 비례하여 증가하였다. 토의 및 결론 빠른 속도의 앉은 자세에서 일어서기를 수행하기 위해서는 최대 지면반발력의 수직, 전-후요소의 추진력이 요구된다. 최대 지면반발력의 내-외요소는 상전방으로 작용하는 모멘트의 증가에 대한 제동력으로 생각된다. 또한, 빠른 속도로 앉은 자세에서 일어서기 동작을 수행하기 위하여 추진력은 일어서는 순간의 모멘트에 대한 지면반발력의 내-외요소에 영향을 미친다. 이라한 결과들은 앉은 자세에서 일어서기 동작에 어려움을 갖는 노인이나 환자들의 노력을 덜기위해 느린 속도의 움직임이 필요함을 제안한다.

• Proceedings of the KIEE Conference
• /
• 2006.07d
• /
• pp.2175-2176
• /
• 2006

인간이 서서 걸으면서 나타나는 필연적인 증상의 하나인 요통은 전체 인구의 80%가 일생에 한 번 이상 경험하며, 20%정도는 항상 허리통증에 시달린다는 보고가 있다. 본 논문에서는 앉은 자세로 인한 요통에 대해서 연구하였다. 앉은 자세 변화에 따라 발생하는 작업자의 근육 근전도를 조사하고 분석하여, 인간공학적으로 적합한 앉은 자세 평가에 표면 전도의 유용성을 알아보았다. 개인에 따라 차이가 있지만 허리에 주는 부담은 앉아 있는 것이 누워 있을 때에 비해 7배, 서 있을 때보다 3배 정도로 크다. 머리를 숙이고 웅크리고 앉아 있거나 등을 구부정하게 앉아 있는 것은 체중이 골고루 분산되지 않아 허리에 주는 부담이 더 크다. 따라서 나쁜 자세로 인해 생기는 요통은 무엇보다 적절한 운동을 통해 복부와 허리의 근육을 강화시켜주는 것과 함께 자세를 바르게 갖도록 해야 한다. 등근육 근전도 신호를 이용하여 자신의 자세정보를 알 수 있도록 하여 앉은 자세를 관찰하고 자세가 바르지 못할 경우 스스로 바른 자세를 유지할 수 있도록 유도함으로써 나쁜 자세로 인한 요통 예방에 도움을 주고자 한다.

• Aerospace Engineering and Technology
• /
• v.10 no.1
• /
• pp.98-106
• /
• 2011

This paper is summarized for designing launch vehicle autopilot structure with attitude angle command from guidance algorithm and for evaluating performance of autopilot using launch vehicle six-degree of freedom simulation program. The suggested autopilot has heritage from KSR-III/KSLV-I upper stage autopilot designing experience, and it has two design point. The one is, it must have same performance with KSR-III/KSLV-I upper stage autopilot, the other is, it must be simple autopilot structure and use low number of variable to apply on-board system. It is evaluated the performance using launch vehicle six-degree of freedom simulation program in case of roll maneuvering and no roll control flight condition.

• Korean Journal of Applied Biomechanics
• /
• v.12 no.2
• /
• pp.131-142
• /
• 2002

The purpose of this study was to analyze kinematic variables of a Mae-ukemi (forward breakfall :MU) in Judo through 3-D image analysis with five Judoka with over 2 years' career (2nd dan, 3rd dan). The kinematic variables include posture, and distance variables; the mean values and the standard deviations for each variable were obtained to analyze kinematic variables of a MU in Judo. From the data analysis and discussion, the following conclusions were drawn : 1) Posture variables : The angles of wrists during right before Mae-ukemi (RBU) were extended from the just MU position(MUP) and flexed from in the right after MU(RAU), and there was a difference in the displacement between the angles of the right and left wrists. The angles of elbows were flexed in the ready position from in the RAU. The angles of ankles were flexed from the ready position to that down position, extended from the down position to that transition, and flexed from the transition positiont to that RAU. 2) Distance variables : The distance height between the mat and shoulders in the RBU(32.2cm) to in the MUP(18.3cm) and in the RAU(20.5cm). during that height between the mat and hips in the RBU(48.0cm) to in the MUP(23.4cm), and in the RAU(30.6cm).

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.47 no.2
• /
• pp.43-49
• /
• 2010

Autonomic nervous system (ANS) acts as a control system functioning largely below the level of consciousness, and controls visceral functions. The activity of the ANS has been assessed by means of the heart rate variability (HRV). It has been reported that HRV is dependent on sex, age, body mass index, and smoking, etc. However, the effects of posture and sleep deprivation on HRV have rarely been reported. Objective of our work was to find out which posture is appropriate for stable HRV. We measured the number of sleep deprivation and HRV using power spectrum in six stages for 30 minutes. Increased low frequency (LF) power and high frequency (HF) power indicate enhanced sympathetic and parasympathetic activity, respectively. We determined the LF/HF ratio to minimize individual difference. It was found that sleep deprivation by awakening up subjects was affected by posture, which resulted in changes of LF/HF. Although LF/HF varied with time, it was more stable in sitting than in supine. In conclusion, we recommend sitting posture when measuring HRV because of less sleep deprivation resulting in less variation in LF/HF.

• Journal of the Institute of Convergence Signal Processing
• /
• v.20 no.2
• /
• pp.99-104
• /
• 2019

Recently, modern people are increasing the incidence of various musculoskeletal diseases due to wrong posture. Prevention is possible through proper posture habit, but it is not easy to recognize posture by oneself. Various studies have been conducted to monitor persistent posture in daily life, but most studies using constrained measurement methods and high-cost measurement equipment are not suitable for daily life. In this paper, we implemented a posture discrimination system using a FSR sensor array that can induce posture correction spontaneously through sitting posture monitoring in daily life. The implemented system is designed as a cushion type so it is easy to apply to existing chair. In addition, it can identify five most common postures in everyday life, and can monitor real-time through Android-based smart-phone monitoring application. For the performance evaluation of the implemented system, each posture was measured 50 times repeatedly. As a result, 97.6% accuracy was confirmed.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.6
• /
• pp.1231-1236
• /
• 2017

In this study, we developed a system that can change position to improve obstructive sleep apnea. Blocking of the breathing airway caused by obstruction of the apnea, lateral position is provided by the airway to improve the apnea. We used a pressure sensor (FSR402) in the form of an array to determine the position of patient. The air cylinder was controlled to raise and lower the bed. As a result of calculating the pressure difference between the supine position and the lateral position, it was $0.41{\pm}0.30$ and $1.09{\pm}0.73$. In other words, when the patient is lateral position, the difference between the sensor values on the right and left side is large. Therefore, it is confirmed that the system can maintain airway to breath for improvement of obstructive sleep.

• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.3
• /
• pp.209-218
• /
• 2013

Early researches in human action recognition have focused on tracking and classifying articulated body motions. Such methods required accurate segmentation of body parts, which is a sticky task, particularly under realistic imaging conditions. Recent trends of work have become popular towards the use of more and low-level appearance features such as spatio-temporal interest points. Given the great progress in pose estimation over the past few years, redefined views about pose-based approach are needed. This paper addresses the issues of whether it is sufficient to train a classifier only on low-level appearance features in appearance approach and proposes effective pose-based approach with pose estimation for emotional action recognition. In order for these questions to be solved, we compare the performance of pose-based, appearance-based and its combination-based features respectively with respect to scenario of various emotional action recognition. The experiment results show that pose-based features outperform low-level appearance-based approach of features, even when heavily spoiled by noise, suggesting that pose-based approach with pose estimation is beneficial for the emotional action recognition.

• Industry Promotion Research
• /
• v.8 no.1
• /
• pp.11-22
• /
• 2023

This study proposes service content that helps people stay in the right posture in their daily lives to manage the pain of musculoskeletal diseases. Resistance factors and induction factors were analyzed through a survey of 143 people and Ethnography. Based on this, we propose an app service that helps practice the right posture by using EMG sensors and wearable devices. This study is meaningful in alleviating musculoskeletal pain and further improving the quality of life by helping to practice and maintain the right posture with service content based on self-objectification through user posture habit analysis.