• Journal of rehabilitation welfare engineering & assistive technology
• /
• v.6 no.1
• /
• pp.1-8
• /
• 2012

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 33 participants(15 males and 18 females) that performed walking and running on treadmill at 2 ~ 11 km/h speeds(each stage increase 1km/h). Algorithm for energy expenditure of physical activities were implemented with $VO_2$ consumption and SVM correlation between the data. Algorithm consists of three kinds and hip, wrist, waist and hip can be used to apply.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.391-393
• /
• 2021

In this paper, we introduce a long short-term memory (LSTM)-based fall detection system using TensorFlow that can detect falls occurring in the elderly in daily living. 3-axis accelerometer data are aggregated for fall detection, and then three types of parameter are calculated. 4 types of activity of daily living (ADL) and 3 types of fall situation patterns are classified. The parameterized data applied to LSTM. Learning proceeds until the Loss value becomes 0.5 or less. The results are calculated for each parameter θ, SVM, and GSVM. The best result was GSVM, which showed Sensitivity 98.75%, Specificity 99.68%, and Accuracy 99.28%.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.2 no.4
• /
• pp.53-58
• /
• 2009

In recently years, the research and application for sensor has increased in each field. In this paper, the system which can perceive and detect using 3-axis accelerometer sensor and serial communication is proposed. Also, the user has GUI environment for monitor in real-time. In order to reduce unstable data and error defect of electronic rechargeable liquid tilt sensor used digital 3-axis accelerometer sensor which has AD convertor. Therefore, this system provide exact data and a problem of objects for user more easier.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.11
• /
• pp.1649-1654
• /
• 2021

In this paper, we introduce a regularization of long short-term memory (LSTM) based fall detection system using TensorFlow that can detect falls that can occur in the elderly. Fall detection uses data from a 3-axis acceleration sensor attached to the body of an elderly person and learns about a total of 7 behavior patterns, each of which is a pattern that occurs in daily life, and the remaining 3 are patterns for falls. During training, a normalization process is performed to effectively reduce the loss function, and the normalization performs a maximum-minimum normalization for data and a L2 regularization for the loss function. The optimal regularization conditions of LSTM using several falling parameters obtained from the 3-axis accelerometer is explained. When normalization and regularization rate λ for sum vector magnitude (SVM) are 127 and 0.00015, respectively, the best sensitivity, specificity, and accuracy are 98.4, 94.8, and 96.9%, respectively.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.516-518
• /
• 2022

In this paper, we introduce a dependence of number of nodes of hidden-layer in fall detection system using Long Short-Term Memory that can detect falls. Its training is carried out using the parameter theta(θ), which indicates the angle formed by the x, y, and z-axis data for the direction of gravity using a 3-axis acceleration sensor. In its learning, validation is performed and divided into training data and test data in a ratio of 8:2, and training is performed by changing the number of nodes in the hidden layer to increase efficiency. When the number of nodes is 128, the best accuracy is shown with Accuracy = 99.82%, Specificity = 99.58%, and Sensitivity = 100%.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.12 no.6
• /
• pp.1057-1064
• /
• 2017

High sensitivity magnetic sensor having foreign metal detection capability is proposed utilizing giant magneto-impedance effect. Strip sensor showed the increasing output voltage when the external magnetic field was applied along with strip from strip grounding point, although the initial DC voltage varied depending on the pointing direction of strip sensor. Proposed sensor was able to eliminate more than half of background noise using active noise filter to achive high sensitivity, and it showed the capability to detect magnetized foreign metal object independent of ambient electro-magnetic noise and earth magnet. In case of ferrous sphere, the metal detection up to 0.8mm diameter was experimentally demonstrated at 5mm distance from strip sensor.

• Journal of Astronomy and Space Sciences
• /
• v.13 no.2
• /
• pp.173-180
• /
• 1996

This paper briefly describes the KITSAT-1 and KITSAT-2 spacecrafts and presents the functions, calibration procedures and in-orbit results of the KITSAT-2 analog sun sensors have been flown as an experimental payload for the future mission. We have two constraints in their design: small size and very low power consumption due to the tight mass and power budget of the spacecraft. Two one-dimensional analog sun sensors are mounted on the top facet of the KITSAT-2 spaceraft. Each has $\pm$60 degrees of view angle and they cover 210 degree field of view in total as the 30 degree view angles are overlapped. Only the relative sun angle around the Z-axis (yaw-axis) and the spin rate of the spacecraft can be achieved as the one dimensional sun sensors are used and they are aligned with the Z-axis. The calibration formulae are obtained using the fifth order line fitting algorithm for each sun sensor on the ground and they are applied to the obtained in-orbit data. ASS-1 with silicon solar cells has maximum error of 1.5 degree and ASS-2 with silicon photocells manufactured at KAIST has maximum error of 0.5 degree except near 0 degree of sun ray incident anagle where random reflection of incident sun ray is maximum in orbit. The results are presented in chapter 4. The performance of each sun sensor and the possible mounting errors are stated in chapter 5.

• The Journal of the Acoustical Society of Korea
• /
• v.21 no.8
• /
• pp.719-726
• /
• 2002

In this paper, we present a layered watermarking technique for digital audio data that is capable of detecting timing change and adapting complexity in detection. The proposed watermarking uses echo hiding as the first layer, which enables the detector to estimate linear speed change. The spread spectrum watermark is then inserted in the second layer which includes additional information like copyright data. We use two kinds of sequences in the second layer, one of which is for synchronization and the other is for data. The results of previous layer are used to make estimate of timing change in the next layer. The detector in the presented method can select detecting range form the first layer to the first layer, second pre-layer, or second main-layer due to the required system specification. Experimental results show that the proposed watermarking technique is robust to several processing attacks including timing change.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2015.10a
• /
• pp.1384-1387
• /
• 2015

고령화 사회로 진입하면서 노인들은 노화과정에 의한 보행능력의 감소 및 근력 약화와 같은 신체적 변화로 인해 잦은 낙상을 경험한다. 이에 따라 낙상 사고를 감지하는 연구가 활발히 진행되고 있다. 낙상은 사전 예방도 중요하지만 사고 발생 후의 신속한 대처도 중요하다. 낙상을 감지하고 의료진에게 즉시 낙상정보를 제공하여 후속적 조치를 취하는 것은 사고 후 대처의 핵심이다. 본 논문에서는 스마트폰 환경에서 사용자의 낙상 후 방향을 판별하기 위해 두 가지 센서 데이터의 특정 값들을 추출하였으며, 이에 5 가지 기계학습 알고리즘을 적용하였다. 사용자는 스마트폰을 착용한 상태로 전후좌우 4 방향 낙상 실험을 진행하며 스마트폰 내에 내장된 3 축 가속도 센서와 3 축 자이로 센서값을 측정한다. 피험자 11 명을 대상으로 낙상 실험 결과, 5 가지의 분류기 중 k-NN에서 98.6%의 인식률을 나타내었다. 뽑아낸 특징 값과 분류 알고리즘은 낙상의 방향 검출에 유용한 것으로 판단된다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2001.11b
• /
• pp.175-179
• /
• 2001

본 논문에서는 디지털 오디오 데이터에 부가 정보를 삽입하는 기술로써 계층적 워터마크를 사용하여 시간 변형을 감지할 수 있고, 필요에 따라 검출 복잡도를 조절할 수 있는 기법을 제안한다. 1계층 워터마크는 오디오 데이터의 시간축 변형을 감지할 수 있도록 오디오 데이터의 반향을 이용하고, 2계층 워터마크는 1계층 워터마크된 오디오 데이터를 기준으로 대역 확산 기법을 이용하여 저작권 정보 등의 요구량이 많은 부가 정보를 삽입한다. 이 때, 2계층 워터마크는 프레임의 동기 확보를 위한 동기 수열, 부가 정보 삽입을 위한 데이터 수열, 두 개를 이용한다. 검출기에서는 시스템의 요구 사항에 따라 1계층, 2계층 전단계, 2계층 본 단계 등의 계층적 순서로 검출할 수 있으며, 각 계층은 데이터에 가해진 변형 정도를 추정하여 다음 계층의 검출단에 정보를 제공한다. 여러 가지 실험 결과를 통하여 제안한 방식이 다양한 신호 처리에 강인함을 보였다.