• 대한안전경영과학회지
• /
• 제14권1호
• /
• pp.87-93
• /
• 2012

The purpose of this study suggests a personalized algorithm of physical activity energy expenditure prediction through comparison and analysis of individual physical activity. The research for a 3-axial accelerometer sensor has increased the role of physical activity in promoting health and preventing chronic disease has long been established. Estimating algorithm of physical activity energy expenditure was implemented by using a tri-axial accelerometer motion detector of the SVM(Signal Vector Magnitude) of 3-axis(x, y, z). A total of 10 participants(5 males and 5 females aged between 20 and 30 years). The activities protocol consisted of three types on treadmill; participants performed three treadmill activity at three speeds(3, 5, 8 km/h). These activities were repeated four weeks.

• 재활복지공학회논문지
• /
• 제6권1호
• /
• pp.1-8
• /
• 2012

본 논문에서는 3축 가속도 동작 감지기를 이용하여 신체활동 에너지 소비량 예측 알고리즘을 구현 하였다. 피험자 33명(남성: 15, 여성: 18명)을 대상으로 트레드밀에서 호흡가스분석기, 3축 가속도 동작 감지기(피트미터)를 허리와 손목에 착용 후 2 km/h ~ 11 km/h 까지 각 단계별 2분 수행 후, 1 km/h 씩 증가 시키면 실험을 진행하였다. 3축 가속도 동작 감지기의 x, y, z축 출력 값을 하나의 대표 값으로 처리하는 신호벡터크기(Signal Vector Magnitude: SVM)와 산소소비량과의 회귀분석을 통하여 신체활동 에너지 소비량 예측 알고리즘을 구현 하였다. 허리, 손목, 허리와 손목의 3축 가속도 동작 감지기 착용 위치에 따라 알고리즘을 구현하고 각각의 알고리즘 별로 비교하여 신체활동의 특성에 따라 선택적으로 이용할 수 있도록 구현 하였다.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2013년도 춘계학술대회 논문집
• /
• pp.1475-1476
• /
• 2013

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2008년도 춘계종합학술대회 A
• /
• pp.229-232
• /
• 2008

A Neural network classification of human activity data is presented. The data acquisition system involves a tri-axial accelerometer in wireless sensor network environment. The wireless ad-hoc system has the advantage of small size, convenience for wearability and cost effectiveness. The system can further improve the range of user mobility with the inclusion of ad-hoc environment. The classification is based on the frequencies of the involved activities. The most significant Fast Fourier coefficients, of the acceleration of the body movement, are used for classification of the daily activities like, Rest walk and Run. A supervised learning approach is used. The work presents classification accuracy with the available fast batch training algorithms i.e. Levenberg-Marquardt and Resilient back propagation scheme is used for training and calculation of accuracy.

• 대한의용생체공학회:의공학회지
• /
• 제32권2호
• /
• pp.79-84
• /
• 2011

The purpose of this study was to investigate the relevance of the prediction equations derived from the relationship between metabolic energy expenditure and kinetic energy, for different speeds of walking and running over the treadmill. Seven male subjects participated in this study. A tri-axial accelerometer was attached on between the left and right posterior superior iliac spines. Kinetic energy was calculated by the integration of acceleration data and compared with the metabolic energy measured by a gas analyzer. Correlation coefficients were determined to find a relationship between the kinetic energy and the metabolic energy expenditure. Also, the difference between measured and predicted values was used to find the relevance for individual and group equations. Results showed a relatively good correlation between the measured metabolic energy and the calculated kinetic energy. In addition, a dramatic increase in kinetic energy was observed at the transition speed of walking and running (6 km/h). There was no difference in how to predict the kinetic energy expenditure for individual and group even though people have different physical characteristics. This study would be useful to predict metabolic energy expenditures by the regression analysis with acceleration data.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2002년도 추계학술대회 논문집
• /
• pp.1066-1069
• /
• 2002

Dynamic postural control varies with the environmental context, specific task and intentions of the subject. In this paper, dynamic postural control against forward-backward perturbations of a platform was estimated using tri-axial accelerometers and a force plate. Ten young healthy volunteers stood upright in comfortable condition on the perturbation system which was controlled by an AC servo motor. With anterior-posterior perturbations, movements of ankle, knee and hip Joints were obtained by tri-axial accelerometers. and ground reaction forces with corresponding displacements of the center of pressure(CoP) by the force plate. The result showed that the ankle moved first and the trunk forward, which implies that the mechanism of the dynamic postural control in forward-backward perturbations, occurred in the procedure of the ankle, the knee and the hip. Knee flexion and hip extension in the period of acceleration, constant velocity and deceleration phase is very important fur the balance recovery. These responses depends on the magnitude and timing of the perturbation. From the present study the accelerometry-system appears to be a promising tool for understanding kinematic accelerative In response to a transient platform perturbation. A more through understanding of balance recovery mechanism may aid in designing methods for reducing falls and the resulting injuries.

• 인터넷정보학회논문지
• /
• 제12권3호
• /
• pp.17-26
• /
• 2011

본 논문에서는 3축 가속도 센서를 이용하여 사람이 보행 시 발생하는 센서 데이터를 획득하여 실시간 걸음 수 검출이 가능한 웨어러블 디바이스를 개발하였다. 피험자 59명을 대상으로 트레드밀에서 Actical 과 본 연구에서 개발된 디바이스를 착용 후 36분 동안 테스트 프로토콜에 따라 느리게 걷기, 걷기, 빠르게 걷기, 천천히 뛰기, 뛰기, 빠르게 뛰기 등의 다양한 걸음 속력에서 테스트를 진행하였다. 3축 가속도 센서의 X, Y, Z축 출력 값을 하나의 대표 값으로 처리하는 신호벡터크기(Signal Vector Magnitude : SVM)를 사용하였다. 또한 정확한 걸음 수를 검출하기 위해 휴리스틱 알고리즘(Heuristic Algorithm : HA)을 제안하고 적응적인 임계값 알고리즘(Adaptive Threshold Algorithm : ATA), 적응적인 잠금 구간 알고리즘(Adaptive Locking Period Algorithm : ALPA)을 제안한다. 실험결과 제안하는 알고리즘의 걸음 수 인식률은 97.34%로 Actical의 인식률(91.74%)보다 5.6%향상 되었다.

• 센서학회지
• /
• 제18권6호
• /
• pp.432-440
• /
• 2009

This paper presents an accelerometer based system for physical activity decision that are capable of recognizing three different types of physical activities, i.e., standing, walking and running, using by rough sets. To collect physical acceleration data, we developed the body sensor node which consists of two custom boards for physical activity monitoring applications, a wireless sensor node and an accelerometer sensor module. The physical activity decision is based on the acceleration data collected from body sensor node attached on the user's chest. We proposed a method to classify physical activities using rough sets which can be generated rules as attributes of the preprocessed data and by constructing a new decision table, rules reduction. Our experimental results have successfully validated that performance of the rule patterns after removing the redundant attribute values are better and exactly same compare with before.

• Journal of information and communication convergence engineering
• /
• 제11권3호
• /
• pp.199-206
• /
• 2013

An emergency monitoring system for the elderly, which uses acceleration data measured with an accelerometer, angular velocity data measured with a gyroscope, and heart rate measured with an electrocardiogram, is proposed. The proposed fall detection algorithm uses multiple parameter combinations in which all parameters, calculated using tri-axial accelerations and bi-axial angular velocities, are above a certain threshold within a time period. Further, we propose an emergency detection algorithm that monitors the movements of the fallen elderly person, after a fall is detected. The results show that the proposed algorithms can distinguish various types of falls from activities of daily living with 100% sensitivity and 98.75% specificity. In addition, when falls are detected, the emergency detection rate is 100%. This suggests that the presented fall and emergency detection method provides an effective automatic fall detection and emergency alarm system. The proposed algorithms are simple enough to be implemented into an embedded system such as 8051-based microcontroller with 128 kbyte ROM.

• 대한의용생체공학회:의공학회지
• /
• 제32권2호
• /
• pp.177-184
• /
• 2011

In this study, the system for application of the bone stimulation was implemented using high frequency and low strain method. The whole system consists of the high frequency and low strain vibration stimulation system 177 for stimulating bone, LVDT sensor, and wireless sensor based on tri-axial accelerometer. To evaluate the usefulness of the system, the frequencies and accelerations from function generator were applied to the vibration stimulation system. The range of frequency was 17 Hz, 30 Hz, 45 Hz, 50 Hz and the range of acceleration was set 0.3 g, 0.6 g, 1g, and 2 g. The measured frequencies and acceleration using LVDT (linear variable difference transformer) sensor and 3-axial accelerometer were estimated and compared. The range of frequencies average difference was from 0.0 to 0.004 Hz. As the standard deviation of frequencies estimated by LVDT sensor and accelerometer was below 0.03 Hz and the output frequencies of function generator were similar: Also the results of t-test were satisfied with conditions of p > 0.05. And the acquired frequencies and acceleration from vibration measuring device module were estimated and analyzed. As the mean of accelerations was similar to the acceleration applied from function generator. And the standard deviation of acceleration estimated from vibration measuring device module was ranged from 0.019 g to 0.038 g. Also the results of t-test were satisfied with conditions of p > 0.05. Therefore, these results were airy similar to the acceleration applied from function generator. As a result, the usefulness of the system was confirmed. n a further study, clinical experiment will be carried out with the authorization of IRB (institutional review board) so that appropriate frequency and strain would be investigated in clinical field.