• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제3권2호
• /
• pp.87-92
• /
• 2014

본 논문에서는 스마트폰 내장 가속도 센서를 이용한 2단계 행위 인식 시스템을 제안한다. 제안하는 행위 인식 시스템에서는 각 행위 별 가속도 데이터의 시간적 변화 패턴을 충분히 반영하기 위해, 1단계에서는 결정트리(DT) 학습을 수행하고, 2단계에서는 1단계 분류 결과들의 시퀀스를 이용하여 은닉 마코프 모델(HMM) 학습을 수행한다. 또한, 견고한 행위 인식기를 얻기 위해, 동일한 행위에 대해 서로 사용자와 서로 다른 스마트폰 위치와 방향으로부터 수집한 다양한 대용량 데이터를 이용하여 본 시스템을 훈련하였다. 6가지 실내 행위들에 대해 수집한 6720개의 가속도 센서 데이터를 이용한 실험을 통해, 본 시스템은 앞서 설명한 설계 방식을 기초로 높은 인식 성능을 보여주었다.

• 한국정보통신학회논문지
• /
• 제26권8호
• /
• pp.1165-1171
• /
• 2022

가속도 센서를 이용한 인간의 행동인식은 다양한 분야에 적용되고 있다. 스마트폰의 보급이 일반화되면서 스마트폰에 내장된 가속도 센서를 이용한 인간의 행동인식 방법이 연구되고 있다. 노인의 경우 넘어지게 되면 심각한 부상으로 이어지는 경우가 많으며 공사 현장에서도 넘어짐은 중요한 사고원인 중 하나이다. 본 연구는 스마트폰에 내장된 가속도 센서와 방향 센서를 이용하여 사람의 넘어지는 방향에 대해 연구하였다. 기존에는, 인간의 행동을 인식하기 위해서 가속도벡터의 크기를 활용하는 것이 일반적인 방법이었다. 본 연구는 최근 많이 활용되고 있는 딥러닝 기법을 적용하여 인간의 넘어지는 방향을 인식하는 방법을 제안하였다.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2021년도 춘계학술대회
• /
• pp.141-143
• /
• 2021

The Activity patterns of animal species are difficult to access and the behavior of freely moving individuals can not be assessed by direct observation. As it has become large challenge to understand the activity pattern of animals such as dogs, and cats etc. One approach for monitoring these behaviors is the continuous collection of data by human observers. Therefore, in this study we assess the activity patterns of dog using the wearable sensors data such as accelerometer and gyroscope. A wearable, sensor -based system is suitable for such ends, and it will be able to monitor the dogs in real-time. The basic purpose of this study was to develop a system that can detect the activities based on the accelerometer and gyroscope signals. Therefore, we purpose a method which is based on the data collected from 10 dogs, including different nine breeds of different sizes and ages, and both genders. We applied six different state-of-the-art classifiers such as Random forests (RF), Support vector machine (SVM), Gradient boosting machine (GBM), XGBoost, k-nearest neighbors (KNN), and Decision tree classifier, respectively. The Random Forest showed a good classification result. We achieved an accuracy 86.73% while the detecting the activity.

• 한국군사과학기술학회지
• /
• 제26권3호
• /
• pp.214-226
• /
• 2023

A transfer alignment is used to initialize, align, and calibrate a SINS(Slave INS) using a MINS(Master INS) in motion. This paper presents an airborne transfer alignment with velocity and azimuth matching to estimate inertial sensor biases under the wing flexure influence. This study also considers the lever arm, time delay and relative orientation between MINS and SINS. The traditional transfer alignment only uses velocity matching. In contrast, this paper utilizes the azimuth matching to prevent divergence of the azimuth when the aircraft is stationary or quasi-stationary since the azimuth is less affected by the wing flexibility. The performance of the proposed Kalman filter is analyzed using two factors; one is the estimation performance of gyroscope and accelerometer bias and the other is comparing aircraft dynamics and attitude covariance. The performance of the proposed filter is verified using a long term flight test. The test results show that the proposed scheme can be effectively applied to various platforms that require airborne transfer alignment.

• 반도체디스플레이기술학회지
• /
• 제22권2호
• /
• pp.112-119
• /
• 2023

In urban environments, signals of Global Positioning System (GPS) can be blocked and reflected by tall buildings, large vehicles, and complex components of road network. Therefore, the performance of the positioning system using the GPS module in urban areas can be degraded due to the loss of GPS signals necessary for the position estimation. To deal with this issue, various localization schemes using inertial measurement unit (IMU) sensors, such as gyroscope and accelerometer, and Bayesian filters, such as Kalman filter (KF) and particle filter (PF), have been designed to enhance the performance of the GPS-based positioning system. Among Bayesian filters, the PF has been widely used for the target tracking and vehicle navigation, since it can provide superior performance in estimating the state of a dynamic system under nonlinear/non-Gaussian circumstance. This paper presents a positioning system that uses the double-stacked particle filter (DSPF) as well as the accelerometer, gyroscope, and GPS receiver on the smartphone to provide higher pedestrian positioning accuracy in urban environments. The DSPF employs a nonparametric technique (Parzen-window) to create the multimodal target distribution that approximates the posterior distribution. Experimental results show that the DSPF-based positioning system can provide the significant improvement of the pedestrian position estimation in urban environments.

• Journal of Animal Science and Technology
• /
• 제65권4호
• /
• pp.748-758
• /
• 2023

This study was conducted to investigate the change in activity and mounting behavior in Hanwoo (Korean Native Cattle) during the peri-estrus period and its application to estrus detection. A total of 20 Hanwoo cows were fitted with a neck-collar accelerometer device, which measured the location and acceleration of cow movements and recorded the number of instances of mounting behavior by the altitude data. The data were analyzed in three periods (24-, 6-, and 2-h periods). Blood samples were collected for 5 days after the prostaglandin F2α (PGF2α) injection, and the concentrations of estradiol, progesterone, follicle-stimulating hormone, and luteinizing hormone were determined by enzyme-linked immunosorbent assays. Activity and mounting behavior recorded over 2-h periods significantly increased as estrus approached and were more efficient at detecting estrus than over 24- and 6-h periods (p < 0.05). Endocrine patterns did not differ with the variation of individual cows during the peri-estrus period (p > 0.05). Activity was selected as the best predictor through stepwise discriminant analysis. However, activity alone is not enough to detect estrus. We suggest that a combination of activity and mounting behavior may improve estrus detection efficiency in Hanwoo. Further research is necessary to validate the findings on a larger sample size.

• Safety and Health at Work
• /
• 제4권1호
• /
• pp.46-51
• /
• 2013

Objectives: Load carrying tasks are recognized as one of the primary occupational factors leading to slip and fall injuries. Nevertheless, the mechanisms associated with load carrying and walking stability remain illusive. The objective of the current study was to apply local dynamic stability measure in walking while carrying a load, and to investigate the possible adaptive gait stability changes. Methods: Current study involved 25 young adults in a biomechanics research laboratory. One tri-axial accelerometer was used to measure three-dimensional low back acceleration during continuous treadmill walking. Local dynamic stability was quantified by the maximum Lyapunov exponent (maxLE) from a nonlinear dynamics approach. Results: Long term maxLE was found to be significant higher under load condition than no-load condition in all three reference axes, indicating the declined local dynamic stability associated with load carrying. Conclusion: Current study confirmed the sensitivity of local dynamic stability measure in load carrying situation. It was concluded that load carrying tasks were associated with declined local dynamic stability, which may result in increased risk of fall accident. This finding has implications in preventing fall accidents associated with occupational load carrying.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2004년도 ICCAS
• /
• pp.87-91
• /
• 2004

High aged society is rapidly progressing in Japan. The rate of aged person more than 65 years old in the population are estimated 25 % in 2017 and rate of younger population will be decreased at same time. As a result, it is estimated that the human resources that is looking after or supporting for the aged person will be drained in Japan. In the other hand, the society has to provide high quality of life in order to be improved living environment for aged person. To decrease the share of nursing and caring for the aged person, it is required that new supporting systems for aged person have to build up as soon as possible. But it is required that various kind of measurement for posture and movement in activities with a simple and single detector for the aged person. The measurement instrument has to be lightweight and simple structure. The results give us a simple measurement method are classified that the posture of sitting down, lying down in stationary statuses and walking, running and going to up and down on the stairs in moving statuses. The detected data will plane to transmit to wireless mobile system to the host computer.

• 한국HCI학회:학술대회논문집
• /
• 한국HCI학회 2008년도 학술대회 1부
• /
• pp.1-6
• /
• 2008

본 연구에서는 게임에서의 몰입도 증가를 위해 기존 버튼 방식의 입력에 사용자의 자연스러운 동작을 이용한 입력과 진동 촉감을 출력하는 게임 컨트롤러를 제안한다. 동작을 이용한 입력장치는 가속도 추적기와 적외선 비디오 카메라를 동시에 사용한다. 두 정보의 장단점을 보완/융합해서 컨트롤러의 움직임을 추적하고, 사용자의 동작을 인식한다. 다양한 종류의 진동촉감은 보이스코일 진동자를 이용하여 제공된다. 또한, 제안하는 게임 컨트롤러를 게임의 상호작용에 적용하는 방법을 제공하고, 응용 프로그램에의 적용가능성을 살펴본다.

• 대한의용생체공학회:의공학회지
• /
• 제38권4호
• /
• pp.211-217
• /
• 2017

During the emergency situation such as cardiac arrest, cardiopulmonary resuscitation(CPR) is the most important treatment to maintain patient's blood circulation. Since the quality of CPR can not be easily measured or evaluated by the eye, an assistive device with an accelerometer can help to assess the pressure depth of CPR. In this study, we propose a single frequency analysis method to reduce the error of the accelerometer by extracting only one frequency component from the Fourier transform process. To verify the effectiveness of the single frequency analysis, acceleration data at CPR conditions were measured at a sampling rate of 50 / sec using a wristband equipped with an acceleration sensor. Then, We compared the existing distance estimation method and the single frequency analysis method using the measured data. The amplitude value proportional to the compression depth was obtained by applying the single frequency analysis method.