• International Journal of Internet, Broadcasting and Communication
• /
• 제12권2호
• /
• pp.120-126
• /
• 2020

Studies are being conducted regarding falling recognition using sensors on smartphonesto recognize falling in human daily life. These studies use a number of sensors, mostly acceleration sensors, gyro sensors, motion sensors, etc. Falling recognition system processes the values of sensor data by using a falling recognition algorithm and classifies behavior based on thresholds. If the threshold is ambiguous, the accuracy will be reduced. To solve this problem, Deep learning was introduced in the behavioral recognition system. Deep learning is a kind of machine learning technique that computers process and categorize input data rather than processing it by man-made algorithms. Thus, in this paper, we propose a falling recognition application system using deep learning based on smartphones. The proposed system is powered by apps on smartphones. It also consists of three layers and uses DataBase as a Service (DBaaS) to handle big data and address data heterogeneity. The proposed system uses deep learning to recognize the user's behavior, it can expect higher accuracy compared to the system in the general rule base.

• 전자공학회논문지SC
• /
• 제48권6호
• /
• pp.1-7
• /
• 2011

본 논문에서는 역진자 시스템과 이동로봇 시스템의 두 시스템으로 구성된 두 바퀴 구동 이동로봇의 구현 및 제어에 대해 논한다. 제어 목적은 균형을 유지하며 이동하는 것이다. 밸런싱 로봇은 한 점에서 회전이 가능하고 바닥으로 부터의 외란에 강건한 균형을 유지한다. 국부 및 전역 좌표계에서의 제어방식의 시뮬레이션을 수행하였다. 로봇이 대칭을 이루도록 만들어졌기 때문에 균형과 주행제어에 간단한 선형 제어기를 사용하였다. 기울어진 각도를 추출하기 위해 자이로와 기울기 센서를 융합하여 사용하였다. 주어진 원형 경로를 주행하는 실험을 수행하였다.

• 한국자동차공학회논문집
• /
• 제12권4호
• /
• pp.154-162
• /
• 2004

In this study, a mathematical model for analyzing the shifting transients of the passenger car with an automatic transmission is proposed. The proposed model comprises a power transmission system and a vehicle system, which are coupled. In order to extract the modeling parameters, on-road car test is carried out. The model is composed of a detailed powertrain, an engine/AT housing, a simplified suspension system, tires and a vehicle body model. On the test, the vehicle accelerations and pitch ratio are measured by using accelerometers and a gyro sensor. The speeds, the brake signal, and the throttle position are taken from sensors which already exist in the vehicle. Considering natural ftequencies, which is calculated from the measured accelerations, and the characteristic equation, vehicle model parameters are identified. Dynamic behaviors during upshift or downshift are simulated using the proposed vehicle model. By comparing and analyzing the simulation result and on-road car test data, the vibration of the Engine/AT housing influences the shifting transients. The effect of model parameters are also studied. Among model parameters, the location of engine mountings influences the vibration of the vehicle body.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2017년도 제56차 하계학술대회논문집 25권2호
• /
• pp.11-12
• /
• 2017

본 논문에서는 항공기 비행 자세를 직관적으로 이해하고 동작의 원리를 시각화 할 수 있는 비행 자세 시뮬레이터를 구현하였다. 항적 정보의 변화에 따라 6축 모션 플랫폼을 동작시키고, 자이로 센서로 부터 전달 받은 비행 자세를 시뮬레이터에 전달하여 시스템을 구성한다. 항공기의 자세를 분석하기 위하여 자이로 센서와 가속도 센서를 같이 사용하는데 자이로 센서는 적분과정의 누적오차가 발생하고 가속도 센서는 짧은 순간의 진동에 따른 노이즈가 심하여 상보 필터를 이용한 보정작업을 하였다. 산출된 센서 정보를 이용하여 6축 모터에 전달할 각도를 계산하여 모션 플랫폼을 동작시키게 되며 시각화 결과는 OpenGL을 이용하여 구현하였다. 본 연구의 결과는 향후, 항공관련 학생들의 교육 기자재로 활용될 수 있을 것으로 사료된다.

• Journal of Astronomy and Space Sciences
• /
• 제26권1호
• /
• pp.47-58
• /
• 2009

In this study, a Hardware-In-the-Loop (HIL) simulator using thrusters is developed to validate the spacecraft attitude system. To control the attitude of the simulator, eight cold gas thrusters are aligned with roll, pitch and yaw axis. Also linear actuators are applied to the HIL simulator for automatic mass balancing to compensate the center of mass offset from the center of rotation. The HIL simulator consists of an embedded computer (Onboard PC) for simulator system control, a wireless adapter for wireless network, a rate gyro sensor to measure 3-axis attitude of the simulator, an inclinometer to measure horizontal attitude, and a battery set to supply power for the simulator independently. For the performance test of the HIL simulator, a bang-bang controller and Pulse-Width Pulse-Frequency (PWPF) modulator are evaluated successfully. The maneuver of 68 deg. in yaw axis is tested for the comparison of the both controllers. The settling time of the bang -bang controller is faster than that of the PWPF modulator by six seconds in the experiment. The required fuel of the PWPF modulator is used as much as 51% of bang-bang controller in the experiment. Overall, the HIL simulator is appropriately developed to validate the control algorithms using thrusters.

• 스마트미디어저널
• /
• 제1권4호
• /
• pp.18-26
• /
• 2012

스마트폰 어플리케이션 수의 증가는 새로운 유저인터페이스에 대한 중요성을 증대시켰으며, 다양한 센서를 융합한 유저인터페이스 개발 연구의 관심을 유도하고 있다. 본 논문에서는 스마트폰에 있는 가속도 센서, 자계 센서, 자이로 센서 정보를 융합하여 사용자 모션 제스처를 인식할 수 있는 새로운 유저인터페이스를 제안한다. 제안 방법은 유합 센서 정보로부터 스마트폰의 3차원 방위 정보를 구하고, HMM(Hidden Markov Model)을 이용하여 손동작 제스처를 인식한다. 특히 제안된 스마트폰의 3차원 방위 좌표계를 구면 좌표계로 변환하는 양자화 방법은 기본 축 회전에 더욱 민감한 인식이 이루어지도록 하였다. 실험을 통하여 제안한 방법이 93%로의 인식률을 보였다.

• 한국인터넷방송통신학회논문지
• /
• 제13권4호
• /
• pp.149-156
• /
• 2013

최근 스마트 폰 기술의 급속한 성장과 더불어, 이를 위한 다양한 어플들의 개발과 보급이 활발하게 이루어지고 있다. 특히 스마트 기기의 카메라 모듈을 이용한 흥미로운 어플들이 지속적으로 개발되고 있어 우리들은 다양한 모바일 서비스를 사용할 수 있게 되었다. 본 논문에서는 스마트 기기의 카메라 모듈을 이용하여 촬영되는 피사체의 실물 크기를 정확하게 측정할 수 있는 어플에 사용되는 계측 알고리즘을 설계하고 구현하였다. 스마트 폰의 카메라 모듈로 피사체 이미지를 촬영할 때 3축 자이로 가속 센서를 이용하여 피사체간 거리와 기울기, 회전각을 실시간으로 측정하여 촬영 이미지 내의 피사체의 사이즈를 정확하게 계측하도록 하였다. 제안한 계측 알고리즘은 모의실험을 통해 그 계측 정확도를 비교 분석하였다.

• 제어로봇시스템학회논문지
• /
• 제18권3호
• /
• pp.275-284
• /
• 2012

This paper proposes an attitude and direction control of a single wheel balanced robot. A unicycle robot is controlled by two independent control laws: the mobile inverted pendulum control method for pitch axis and the reaction wheel pendulum control method for roll axis. It is assumed that both roll dynamics and pitch dynamics are decoupled. Therefore the roll and pitch dynamics are obtained independently considering the interaction as disturbances to each other. Each control law is implemented by a controller separately. The unicycle robot has two DC motors to drive the disk for roll and to drive the wheel for pitch. Since there is no force to change the yaw direction, the present paper proposes a method for changing the yaw direction. The angle data are obtained by a fusion of a gyro sensor and an accelerometer. Experimental results show the performance of the controller and verify the effectiveness of the proposed control algorithm.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2001년도 하계학술대회 논문집 D
• /
• pp.1984-1986
• /
• 2001

In order to provided continuous solutions, latest developing navigation systems tend to integrate GPS receiver with INS or DR. Using the GPS carrier-phase measurements, an attitude GPS receiver with three antennas obtain the 3-dimensional attitude such as roll, pitch, and heading as well as position and velocity. With these angle measurements, in the attitude GPS/INS integrated system, attitude or gyro errors can be directly compensated. In this paper, we develop an integrated navigation system that combines attitude GPS receiver with INS. The performance of real-time integrated navigation system is determined by not only the implements of integration filter but also the synchronization of measurements. To meet these real-time requirements, the navigation software is implemented in multi-tasking structure in this paper. We also employ time-synchronization technique in the multi-sensor fusion. Experimental results show that the performance of the attitude GPS/INS integrated system is consistent even when cycle-slip occurs in carrier-phase measurements.

• 로봇학회논문지
• /
• 제5권2호
• /
• pp.120-126
• /
• 2010

This paper presents to study the path tracking method of AGV(autonomous guided vehicle) which has a laser guidance system. An existing automatic guided vehicles(AGVs) which were able to drive on wired line only had a automatic guidance system. However, the automatic guidance systems that those used had the high cost of installation and maintenance, and the difficulty of system change according to variation of working environment. To solve such problems, we make the laser guidance system which is consisted of a laser navigation and gyro, encoder. That is robust against noise, and flexible according to working environment through sensor fusion. The laser guidance system can do a perfect autonomous driving. However, the commercialization of perfect autonomous driving system is difficult, because the perfect autonomous driving system must recognize the whole environment of working space. Hence, this paper studied the path tracking of AGV using laser guidance system without wired line. The path tracking method is consisted of virtual path generation method and driving control method. To experiment, we use the fork-type AGV which is made by ourselves, and do a path tracking experiments repeatedly on same experimental environment. In result, we verified that proposed system is efficient and stable for actual fork-type AGV.