• Journal of Korea Multimedia Society
• /
• v.18 no.3
• /
• pp.408-418
• /
• 2015

This paper describes the design and implementation of situation recognition system with smart phone sensors, which recognizes the dangerous situation at anytime, anywhere through intuitive data analysis of the combination of the sensor. The implemented system consists of wearable heart rate sensor and acceleration sensor of smart phone instead of existing sensor that is attached to the body. It is also designed to get more effective results of recognition about the dangerous situation using merged displacement values of acceleration sensor and heart rate sensor which are measured in the process of recognizing dangerous situations. This research, in accordance with the wide penetration of smartphones, achieves the fast status determination through the combination of an acceleration sensor and a heart rate sensor applied to its own status perception algorithm for anyone who needs the stable perception of risk without the need for a separate provision of the sensor.

• Journal of Information Technology Services
• /
• v.10 no.1
• /
• pp.65-72
• /
• 2011

In this paper, we consist of three dimensional acceleration sensor as a small-sized sensor module to acquire base technologies that need to estimate exhibition audience' moving distance. and that we developed algorism and device that can calculate acceleration in gravity direction with attaching it to people's body part without regard to three dimensional direction. By making use of the sensor module, we have to process the data that let it quantitatively process possible to measure people's walk and movement by computer system. We normalized sensor output data in the process of change from sensor module to acquisition of data, rectangular coordinates and single scalar acceleration value in gravity direction. Printed out sensor data attaching sensor module to people's body part is used for motion pattern detection after normalization, Motion sensor devised mode change algorism because it print data of other pattern according to attached position of body. For algorism design, we collected data occurring during walking about subject and we also defined occurring problem domain after analyzing the data. We settle defined problem domain and that we simulated the walking number measuring instrument with highly efficient in restricted environment.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2019.05a
• /
• pp.486-487
• /
• 2019

Smartphones have various sensors built in. In particular, acceleration sensors are used to analyze human behavior because they can detect movement of objects. Previous studies have analyzed the behavior of people by analyzing the magnitude of acceleration sensor values. In this study, we proposed a method of detecting the motion by applying the K-average of the acceleration sensor value built in the smartphone. We proposed a method of recognizing walking and running, which is basic human behavior, by applying K-average of acceleration sensor value of smartphone.

• International Journal of Ocean System Engineering
• /
• v.1 no.3
• /
• pp.165-170
• /
• 2011

In this paper, for the accurate estimation of the position and orientation of the UUV (unmanned underwater vehicle), an AHRS (Attitude Heading Reference System) was developed using the IMU (inertial measurement unit) sensor which provides information on acceleration and orientation in the object coordinate and the initial alignment algorithm and the E-KF (extended Kalman Filter). The initial position and orientation of the UUV are estimated using the initial alignment algorithm with 3-axis acceleration and geomagnetic information of the IMU sensor. The position and orientation of the UUV are estimated using the AHRS composed of 3-axis acceleration, velocity, and geomagnetic information and the E-KF. For the performance test of the orientation estimation of the AHRS, a testbed using IMU sensor(ADIS16405) and DSP28335 coded with an E-KF algorithm was developed and its performance was verified through tests.

• Proceedings of the KSME Conference
• /
• 2004.04a
• /
• pp.946-949
• /
• 2004

It is necessary to detect the tilt angle for control or monitoring of various systems such as ship, aircraft recreation facilities etc as well as bridge or building systems. However the electronic liquid charge type tilt sensor which is one of typical tilt sensor has many problems. Those are remarkably slow response time and limited mounting condition because or liquid viscosity coefficient and inertia etc. In this study we propose a tilt angle instrumentation method using piezoelectricity acceleration sensor. The method can he applied on moving mount We verified the validity of the method through experiment.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.6
• /
• pp.91-98
• /
• 2020

In order to prevent a collision accident during sudden braking, we have proposed an hazard lamps automatic operation system that can be easily installed in existing vehicles that do not have hazard lamps automatic operation. There are several ways to recognize sudden braking. Using GPS, the system does not work in a tunnel, and it is difficult to install the system additionally on an existing vehicle using a vehicle speed sensor. Therefore, the proposed system eliminates these problems by using the acceleration sensor and makes it possible to recognize even the sudden turning and bounce of the vehicle.

• Physical Therapy Rehabilitation Science
• /
• v.11 no.3
• /
• pp.311-320
• /
• 2022

Objective: To investigate the reliability and validity of static balance measurements using an acceleration sensor and a gyroscope sensor in smart phone inertial sensors. Design: Equivalent control group pretest-posttest. Methods: Subjects were forty five healthy adults aged twenty to fifty-years-old who had no disease that could affect the experiment. After pre-test, all participants wore a waist band with smart phone, and conducted six static balance measurements on the force plate twice for 35 seconds each. To investigate the test-retest reliability of both smart phone inertial sensors, we compared the intra-correlation coefficient (ICC 3, 1) between primary and secondary measurements with the calculated root mean scale-total data. To determine the validity of the two sensors, it was measured simultaneously with force plate, and the comparision was done by Pearson's correlation. Results: The test-retest reliability showed excellent correlation for acceleration sensor, and it also showed excellent to good correlation for gyroscope sensor(p<0.05). The concurrent validity of smartphone inertial sensors showed a mostly poor to fair correlation for tandem-stance and one-leg-stance (p<0.05) and unacceptable correlation for the other postures (p>0.05). The gyroscope sensor showed a fair correlation for most of the RMS-Total data, and the other data also showed poor to fair correlation (p<0.05). Conclusions: The result indicates that both acceleration sensor and gyroscope sensor has good reliability, and that compared to force plate, acceleration sensor has unacceptable or poor correlation, and gyroscope sensor has mostly fair correlation.

• Journal of Sensor Science and Technology
• /
• v.6 no.6
• /
• pp.430-436
• /
• 1997

A piezoresistive acceleration sensor for 30 G has been fabricated by silicon micromachining method using SDB(silicon direct bonding) wafer. The structure of the piezoresistive acceleration sensor consists of a seismic square pillar type mass and four beams. This structure was fabricated by reactive ion etching and chemical etching using KOH-etchant. The rectangular square structure is used in order to compensate the deformation of the edges due to underetching. The fabricated sensor showed a linear output voltage-acceleration characteristics and its sensitivity was about $88{\mu}V/V{\cdot}g$ from 0 to 10 G.

• Journal of Sensor Science and Technology
• /
• v.2 no.1
• /
• pp.11-17
• /
• 1993

We have constructed an acceleration sensor which is based on the maximum magnetic induction changes of amorphous wire as a measurand. The frequency bandwith of the constructed sensor depends on the mass of a sensing element. For $Co_{72.5}Si_{12.5}B_{15}$ amorphous wire, the bandwith is DC-700 Hz for $1{\times}10^{-3}kg$ sensing element and DC-200 Hz for $5{\times}10^{-3}kg$. The linearity of the acceleration sensor was less than 1% within the acceleration of 5 g.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.8
• /
• pp.1165-1171
• /
• 2022

Human behavior recognition using an accelerometer has been applied to various fields. As smartphones have become used commonly, a method for human behavior recognition using the acceleration sensor built into the smartphone is being studied. In the case of the elderly, falling often leads to serious injuries, and falls are one of the major causes of accidents at construction fields. In this article, we proposed recognition method for human falling direction using built-in acceleration sensor and orientation sensor in the smartphone. In the past, it was a common method to use the magnitude of the acceleration vector to recognize human behavior. These days, deep learning has been actively studied and applied to various areas. In this article, we propose a method for recognizing the direction of human falling by applying the deep learning multilayer technique, which has been widely used recently.