• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2017.11a
• /
• pp.38-40
• /
• 2017

본 논문에서는 사람의 걸음걸이 분석을 위한 소형 웨어러블 시스템을 개발한다. 신발 내 깔창에 부착 가능한 소형화된 모듈을 설계하고, 압력 센서 및 가속도 센서를 이용하여 사용자의 걸음걸이에 대한 정보를 측정하고 측정 데이터를 바탕으로 사용자의 자세를 분석한다. 분석한 결과는 블루투스 통신을 이용하여 사용자의 스마트폰으로 전송이 가능하고, 사용자는 자신의 걸음걸이에 대한 정보를 실시간으로 확인하여 스스로 자세교정을 할 수 있도록 유도한다.

• Proceedings of the Korean Society of Disaster Information Conference
• /
• 2016.11a
• /
• pp.175-178
• /
• 2016

실내에서의 화재 등의 재난 상황에서는 비장애인과 장애인 모두 시야 확보가 어려워져 안전하게 대피하기 어려운 위험에 직면하게 된다. 본 논문에서는 시각정보 부재 시에 보행자의 다양한 장애물에 대한 회피 및 충돌상황 방지를 위한 안전 기술에 대한 연구를 수행하였다. 특히 주변의 다양한 위험 정보를 인지하기 어려운 시각 및 청각장애인들이 안전에 위협을 느낄 수 있는 복잡한 실내외 구조물과, 시시각각 변하는 주변의 장애물 환경에 대처하기 위하여 MCU를 활용한 보드에 진동 모터, 초음파, LED 센서를 장착하여 탈부착이 가능한 웨어러블(Wearable) 모듈을 제작하였다. 장애물 감지를 위한 센서부는 사용자의 상체부 전반에 장착되어 주변의 장애물들을 보다 넓은 범위로 인식하고 대처할 수 있으며, 이후 다양한 관제시스템에 활용 가능하도록 모듈과 사용자간의 인터넷 통신을 이용하여 실시간으로 시각 및 청각장애인들의 위험감지를 보호자에게 신속하게 알려줄 수 있는 시스템을 개발하여 그 가능성을 확인하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2017.11a
• /
• pp.1222-1224
• /
• 2017

사람들은 예측하지 못한 순간에 발생할 수 있는 안전 사고에 대해 항상 불안해한다. 매년 노년층 인구 비율이 증가함에 따라 낙상 사고 발생 빈도도 비례적으로 증가하고 있다. 낙상 사고는 대체로 골든 타임이 짧으므로 보호자와 함께 생활하지 않는 노인에게 낙상 사고가 발생한 경우 이를 대처하는 것은 매우 어렵다. 본 논문에서는 비콘과 웨어러블 밴드로 활용하여 낙상 사고 발생을 효과적으로 감지하고 초동 응급 대처가 가능할 수 있도록 돕는 알림 시스템을 설계하고, 이러한 기능을 수행하는 모바일 애플리케이션을 구현하고자 한다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2016.11a
• /
• pp.154-156
• /
• 2016

현대사회에서 헬스케어가 대두하고 있는 동시에 자신의 몸 상태와 관련된 정보에 대해 직접 모니터링을 원하는 사람들이 늘어나고 있다. 이에, 본 논문에서는 사용자의 스마트한 건강관리를 위한 웨어러블 (wearable) 기기 및 어플리케이션을 개발한다. 사람의 발은 신체 건강과 밀접한 연관이 있으므로 개발된 시스템은 신발 내에 부착된 압력 및 온습도 센서를 통하여 발의 건강상태를 실시간으로 모니터링할 수 있다. 또한, 제안한 시스템은 하나의 신발에 내장되어 있으므로 사용자가 일상생활 중에 간편하게 발의 건강상태를 스스로 모니터링할 수 있다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.5
• /
• pp.10-15
• /
• 2017

Research interest has strongly focused on developing a method for effectively transmitting bio-signals over a distance using a wireless wearable device. In this paper, we describe a procedure for the design and fabrication of a wearable antenna based on embroidering conductive threads to clothing capable of transmitting electrocardiogram signals. 3D electromagnetic simulation software and embroidery software were used to design and fabricate the conductive thread-based antenna, respectively. The measurement results show that the reflection coefficient of the fabricated antenna prototype exhibits excellent antenna impedance matching characteristics of less than -10dB in the Zigbee 2.4GHz frequency band. We also verified that the electrocardiogram data could be effectively received and monitored in real-time by a receiver 220m away from the transmitter.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.7
• /
• pp.1619-1627
• /
• 2014

Wearable computer systems can use the wireless universal serial bus (WUSB) that refers to USB technology that is merged with WiMedia PHY/MAC technical specifications. In this paper, we focus on an integrated system of the wireless USB over the IEEE 802.15.6 wireless body area networks (WBAN) for wireless wearable computer systems supporting U-health services. And a communication structure that performs the time-synchronization is proposed for WUSB over IEEE 802.15.6 hierarchical protocol. Proposed time-synchronization mechanisms adopt the WBAN Polling Access and combine it with a time-synchronization middleware using time stamps. In our performance evaluations, time-synchronization performances with only WBAN Polling Access scheme are analyzed first. After that, performances combined with the time-synchronization middleware are analyzed to evaluate the effectiveness of proposed time-synchronization structure in WUSB over IEEE 802.15.6.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.11 no.1
• /
• pp.114-120
• /
• 2018

In this paper we implemented an EMG sensor system for wearable devices to obtain and analyze of EMG signals. The performance of the implemented sensor system is evaluated by the correlation analysis of muscle fatigue and muscle activation to clinical EMG system and compared with power consumption of the measured power of our system and commercial systems. In experiments with biceps and triceps brachii of 5 objects, The correlation values of muscle fatigue and muscle activation between our system and the clinical EMG system is 1.1~1.4 and about 1.0, respectively. And also the power consumption of our system is 25~50% less than that of some commercial EMG sensor systems.

• KIPS Transactions on Computer and Communication Systems
• /
• v.6 no.2
• /
• pp.67-74
• /
• 2017

This paper proposes a method of user authentication through the patterns of arm movement with a wrist-type wearable device. Using the accelerometer sensor which is built in the device, the 3-axis accelerometer data are collected. Then, the collected data are integrated and the periodic cycle are extracted. In the cycle, the features of frequency are generated with the accelerometer. With the frequency features, 2D Gaussian mixture are modelled. For authenticating an user, the data(the accelerometer) of the user at some point are tested with confidence interval of the Gaussian distribution. The model showed a valuable results for the user authentication with an example, which is average 92% accuracy with 95% confidence interval.

• The Journal of Korean Institute of Next Generation Computing
• /
• v.15 no.2
• /
• pp.7-16
• /
• 2019

Neural networks can be implemented in variety of ways, and specialized chips is being developed for hardware improvement. In order to apply such neural networks to wearable devices, the compactness and the low power operation are essential. In this point of view, a suitable implementation method is a digital circuit design using field programmable gate array (FPGA). To implement this system, the learning algorithm which takes up a large part in neural networks must be implemented within FPGA for better performance. In this paper, a back propagation algorithm among various learning algorithms is implemented using FPGA, and this neural network is verified by OR gate operation. In addition, it is confirmed that this neural network can be used to analyze various users' bio signal measurement results by learning algorithm.

• KIPS Transactions on Computer and Communication Systems
• /
• v.8 no.4
• /
• pp.93-102
• /
• 2019

As interest in wellness grows, There is a lot of research about monitoring individual health using wearable devices. Accordingly, a variety of methods have been studied to distinguish exercise from daily activities using wearable devices. Most of these existing studies are machine learning methods. However, there are problems with over-fitting on individual person's learning, data discontinuously recognition by independent segmenting and fake activity. This paper suggests a detection method for exercise activity based on the physiological response principle of heart rate up and down during exercise. This proposed method calculates activity intensity and heart rate from triaxial and photoplethysmography sensor to determine a heart rate recovery, then detects exercise by estimating activity intensity or detecting a heart rate rising state. Experimental results show that our proposed algorithm has 98.64% of averaged accuracy, 98.05% of averaged precision and 98.62% of averaged recall.