• 한국멀티미디어학회논문지
• /
• 제21권8호
• /
• pp.982-990
• /
• 2018

In recent years, many wearable devices and mobile apps related to life care have been developed, and a service for measuring the movement during walking and showing the amount of exercise has been provided. However, they do not measure walking in detail, so there may be errors in the total calorie consumption. If the user's behavior is measured by a multi-axis sensor and learned by a machine learning algorithm to recognize the kind of behavior, the detailed operation of walking can be autonomously distinguished and the total calorie consumption can be calculated more than the conventional method. In order to verify this, we measured activities and created a model using a machine learning algorithm. As a result of the comparison experiment, it was confirmed that the average accuracy was 12.5% or more higher than that of the conventional method. Also, in the measurement of the momentum, the calorie consumption accuracy is more than 49.53% than that of the conventional method. If the activity recognition is performed using the wearable device and the machine learning algorithm, the accuracy can be improved and the energy consumption calculation accuracy can be improved.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2007년도 춘계종합학술대회
• /
• pp.667-670
• /
• 2007

착용형 컴퓨팅을 응용한 건강모니터링 분야는 급격한 성장이 이루어지고 있다. 본 연구의 목적은 유비쿼터스 헬스케어를 위해 착용형 ECG모니터링 시스템을 구현하는 것이다. 본 논문에서는 구현된 프로토타입의 착용형 건강모니터링 시스템의 계측성능, 무선전송, 계측된 ECG신호의 분석 등에 대해 기술하고자 한다. 구현된 하드웨어 시스템은 지그비 통신을 이용하여 무선으로 체스트 벨트타입의 센서에서 PC서버로 전송한다. 그리고 구현된 시스템을 이용하여 ECG 모니터링 테스트를 수행한 결과 원격 모니터링의 가능성을 확인하였다.

• 센서학회지
• /
• 제20권6호
• /
• pp.382-387
• /
• 2011

Whether a person is feeling sleepy or reasonably awake is important safety information in many areas, such as humans operating in traffic or in heavy industry. The changes of body signals have been mostly researched by looking at electroencephalogram(EEG) signals but more and more other medical signals are being examined. In our study, an electrocardiogram(ECG) signal is measured at a sampling rate of 100 Hz and used to try to distinguish the possible differences in signal between the two states: awake and drowsy. Practical tests are conducted using a wireless sensor node connected to a wearable ECG sensor, and an ECG signal is transmitted wirelessly to a base station connected to a server PC. Through the QRS complex in the ECG analysis it is possible to obtain much information that is helpful for diagnosing different types of cardiovascular disease. A program is made with MATLAB for digital signal filtering and graphing as well as recognizing the parts of the QRS complex within the signal. Drowsiness detection is performed by evaluating the R peaks, R-R interval, interval between R and S peaks and the duration of the QRS complex..

• Journal of Electrical Engineering and Technology
• /
• 제13권4호
• /
• pp.1732-1739
• /
• 2018

With the explosion of digital devices, interaction technologies between human and devices are required more than ever. Especially, hand gesture recognition is advantageous in that it can be easily used. It is divided into the two groups: the contact sensor and the non-contact sensor. Compared with non-contact gesture recognition, the advantage of contact gesture recognition is that it is able to classify gestures that disappear from the sensor's sight. Also, since there is direct contacted with the user, relatively accurate information can be acquired. Electromyography (EMG) and force-sensitive resistors (FSRs) are the typical methods used for contact gesture recognition based on muscle activities. The sensors, however, are generally too sensitive to environmental disturbances such as electrical noises, electromagnetic signals and so on. In this paper, we propose a novel contact gesture recognition method based on Flexible Epidermal Tactile Sensor Array (FETSA) that is used to measure electrical signals according to movements of the wrist. To recognize gestures using FETSA, we extracted feature sets, and the gestures were subsequently classified using the support vector machine. The performance of the proposed gesture recognition method is very promising in comparison with two previous non-contact and contact gesture recognition studies.

• 전기전자학회논문지
• /
• 제23권3호
• /
• pp.793-799
• /
• 2019

본 연구에서는 웨어러블 Fabric(Nylon) + MWCNT 가스센서 내부에서 열확산을 해석하기 위해서 요소해석 프로그램(comsol)을 이용하여 센서 내부에서의 열용량의 확산 과정과 열용량 분포 경도를 확인하였다. 열용량의 확산과정을 해석하기 위해서 가스센서의 구조체에 대하여 이차원으로 모델링을 진행하였으며, 제시된 모델링에 대해서 센서 구성 부분에 대한 특성값을 제시하여 메시 요소법(FEM)을 이용하여 설계된 웨어러블 가스센서에 대해서 열용량이 확산되는 정도와 열용량 경도를 구하기 위해서 지배방정식으로 1계 편미분방정식을 제안하여 해석하였으며, 열속도 전달식을 제안하여 전극층과 가스 검출부의 10[K/mm] 온도 경도를 구하였다.

• 패션비즈니스
• /
• 제25권1호
• /
• pp.133-149
• /
• 2021

This study presents a new fashion wearable product, a classical music stage costume design, using an Arduino LilyPad that can control light-emitting diodes(LEDs) and a sound sensor that can set an environmental range of LED light. As a theoretical background, LED fashion design research and stage costume design research status were reviewed, and Arduino LilyPads, sensors, LEDs, and batteries required for LED stage costume production were investigated. Based on prior research, the LED stage costume design for the soprano stage was presented in a three-step process of design planning, development, and production, and an actual prototype was produced. This process produced meaningful information and materials for making clothes with the added function of a wearable computer. In particular, fashion designers or fashion majors can easily access the Arduino LillyPad and use not only LEDs, but other light emitting materials. It is expected that it will be used as a basic material for the use of the Arduino LillyPad that can develop new creations that have been utilized.

• 한국전자통신학회논문지
• /
• 제18권4호
• /
• pp.731-736
• /
• 2023

보행은 특정 단계를 반복하는 주기적인 동작으로 사람의 기본 이동방법이다. 보행 분석을 통해 여러 가지 근골격계의 건강상태를 판별할 수 있다. 본 연구에서는 공간의 제약 없이 보행 분석을 할 수 있는 착용형 센서 시스템을 제안한다. 거리를 측정하는 ToF(: Time-of-Flight) 센서와 기울기를 측정하는 IMU(: Inertial Measurement Unit) 센서로 보행 중의 뒤꿈치 궤적을 도출한다. 낙상의 위험이 있는 이상보행을 할 때의 뒤꿈치 궤적의 변화 양상을 분석하여 보행을 평가한다.

• 로봇학회논문지
• /
• 제18권2호
• /
• pp.189-196
• /
• 2023

An abdominal brace is a recommended treatment for patients with lumbar spinal disorders. However, due to the nature of the static brace, it uniformly compresses the lumbar region, which can weaken the lumbar muscles or create a psychological dependence that worsens the condition of the spine when worn for an extended period of time. Due to these issues, doctors limit the wearing time when prescribing it to patients. In this paper, we propose a device that can dynamically provide abdominal pressure and support according to the lumbar motion. The proposed device is a wearable robot in the form of a brace, with actuators and a driving unit mounted on the brace. To enhance wearability and reduce the weight of the device, worm gears actuator and a multi-pulley mechanism were adopted. Based on the spinal motion of the wearer measured by the Inertia measurement unit sensors, the drives wire by driving pulley, which provide tension to the multi-pulley mechanism on both sides, dynamically tightening or loosening the device. Finally, the device can dynamically provide abdominal pressure and support. We describe the hardware and system configuration of the device and demonstrate its potential through basic control experiments.

• 센서학회지
• /
• 제30권4호
• /
• pp.218-222
• /
• 2021

Wearable multi-sensors based on nanocrystals have attracted significant attention, and studies on patterning technology to implement such multi-sensors are underway. Conventional patterning processes may affect material properties based on high temperatures and harsh chemical conditions. In this study, we developed an inkjet printing technique that can overcome these drawbacks through the application of patterning processes at room temperature and atmospheric pressure. Nanocrystal-based ink is used to adjust properties efficiently. Additionally, the viscosity and surface tension of the solvents are investigated and optimized to increase patterning performance. In the patterning process, the electrical, electrothermal, and electromechanical properties of the nanocrystal pattern are controlled by the ligand exchange process. Experimental results demonstrate that a multi-sensor with a temperature coefficient of resistance of 3.82 × 10^-3 K^-1 and gauge factor of 30.6 can be successfully fabricated using one-step inkjet printing.

• 전기전자학회논문지
• /
• 제23권3호
• /
• pp.844-851
• /
• 2019

웨어러블 디바이스의 대중화에 따라 디바이스 내에 탑재된 다양한 센서를 활용하여 동작 인식, 헬스케어, 안전 보조 등 다양한 스마트 서비스를 제공하는 애플리케이션이 급증하고 있다. 본 논문에서는 9축 관성 센서가 탑재된 스마트워치를 이용하여 운전자를 인식하고, 운전 중 운전자의 자동차 핸들의 회전각을 탐지하는 방법을 제안한다. 제안하는 시스템은 i) 스마트워치 위치 인식, ii) 운전자 인식, iii) 핸들의 회전각 계산, 3가지 단계로 구성되어 있다. 이를 위해, IMU 센서와 아두이노(Arduino)를 이용하여 웨어러블 디바이스의 시제품을 자체 제작하고 제안하는 시스템을 구현 하였다. 실험을 통해 핸들의 회전 방향을 높은 정확도로 계산할 수 있고 회전각 또한 평균 $11.77^{\circ}$의 낮은 오차를 보여 제안하는 시스템의 실효성을 입증하였다.