• International journal of advanced smart convergence
• /
• v.7 no.2
• /
• pp.95-100
• /
• 2018

In this paper, we propose a binarized multi-scale module to accelerate the speed of the pose estimating deep neural network. Recently, deep learning is also used for fine-tuned tasks such as pose estimation. One of the best performing pose estimation methods is based on the usage of two neural networks where one computes the heat maps of the body parts and the other computes the part affinity fields between the body parts. However, the convolution filtering with a large kernel filter takes much time in this model. To accelerate the speed in this model, we propose to change the large kernel filters with binarized multi-scale modules. The large receptive field is captured by the multi-scale structure which also prevents the dropdown of the accuracy in the binarized module. The computation cost and number of parameters becomes small which results in increased speed performance.

• Proceedings of the KIEE Conference
• /
• 2007.04a
• /
• pp.423-425
• /
• 2007

In this paper, Medium Access Control(MAC) protocol designed for Wireless Body area Sensor Network(Bio-MAC) is proposed, Because in WBSN, the number of node is limited and each node has different characteristics. Also, reliability in transmitting vital data sensed at each node and periodic transmission should be considered so that general MAC protocol cannot satisfy such requirements of biomedical sensors in WBSN. Bio-MAC aims at optimal MAC protocol in WBSN. For this, Bio-MAC used Pattern -SuperFrame, which modified IEE E 802.15.4-based SuperFrame structurely. Bio-MAC based on TDMA uses Medium Access-priority and Pattern eXchange -Beacon method for dynamic slot allocation by considering critical sensing data or power consumption level of sensor no de etc. Also, because of the least delay time. Bio-MAC is suitable in the periodic transmission of vital signal data. The simulation results demonstrate that a efficient performance in WBSN can be achieved through the proposed Bio-MAC.

• JSTS:Journal of Semiconductor Technology and Science
• /
• v.11 no.1
• /
• pp.23-32
• /
• 2011

A 40 fJ/c-s, 1 V, 10-bit SAR ADC is presented for energy constrained wearable body sensor network application. The proposed 10-bit dual sampling capacitive DAC topology reduces switching energy by 62% compared with 10-bit conventional SAR ADC. Also, it is more robust to capacitor mismatch than the conventional architecture due to its cancelling effect of each capacitive DAC. The proposed SAR ADC is fabricated in 0.18 ${\mu}m$ 1P6M CMOS technology and occupies 1.17 $mm^2$ including pads. It dissipates only 1.1 ${\mu}W$ with 1 V supply voltage while operating at 100 kS/s.

• Information and Communications Magazine
• /
• v.25 no.2
• /
• pp.6-10
• /
• 2008

WBAN(Wireless Body Area Network)은 인체를 기준으로 하여 인체내부 및 인체로부터3미터 이내의 무선통신으로 정의하고 있다. 이에따라 WBAN은 현재 다양한 용도로 응용되고 있는데 크게 분류하면 의료용과 비의료용 무선기기로 구분할 수 있다. 즉 가전기기(Comsumer Electronics)들간 의 통신을 목적으로 하는 비의료용 분야와 인체내부에 이식되어 인체내부의 건강상태에 대한 모니터링이나 인체에 이상이 발생시 대처해 주는 인체이식형 무선기기와 인체외부 3미터 이내에서 의료용 sensor로부터 송수신하는 인체외부 기기로 구분할 수 있다. IEEE802.15.6에서 2006년 하반기부터 WBAN(Wireless Body Area Network)시스템에 대한 표준화를 진행하고 있으며, 2008년도에는 표준 제안서를 각국에서 받아 2009년도에 완료할 예정에 있다. 본 고에서는 기존 WBAN으로 사용하고 있던 무선장비들에 대한 각국의 인체내부와 외부의 주파수 분배동향을 분석한 후 WBAN표준화시 대두될 PHY/MODEM/MAC제안에 결정적 영향을 미치는 WBAN의 주파수에 대한 방향을 제시하였다.

• International journal of advanced smart convergence
• /
• v.8 no.2
• /
• pp.147-154
• /
• 2019

In this paper, we conducted a study that utilizes deep learning to calculate appropriate physical exercise information when basic human factors such as sex, age, height, and weight of users come in. To apply deep learning, a method was applied to calculate the amount of fat needed to calculate the amount of one repetition maximum by utilizing the structure of the basic Deep Neural Network. By applying Accuracy improvement methods such as Relu, Weight initialization, and Dropout to existing deep learning structures, we have improved Accuracy to derive a lean body weight that is closer to actual results. In addition, the results were derived by applying a formula for calculating the one repetition maximum load on upper and lower body movements for use in actual physical exercise. If studies continue, such as the way they are applied in this paper, they will be able to suggest effective physical exercise options for different conditions as well as conditions for users.

• International Journal of Computer Science & Network Security
• /
• v.21 no.2
• /
• pp.221-228
• /
• 2021

Recent improvements on the quality, fidelity and availability of biometric data have led to effective human physical activity detection (HPAD) in real time which adds significant value to applications such as human behavior identification, healthcare monitoring, and user authentication. Current approaches usually use machine-learning techniques for human physical activity recognition based on the data collected from wearable accelerometer sensor from a single wearable smart device on the user. However, collecting data from a single wearable smart device may not provide the complete user activity data as it is usually attached to only single part of the user's body. In addition, in case of the absence of the single sensor, then no data can be collected. Hence, in this paper, a continuous HPAD will be presented to effectively perform user activity detection with mobile service infrastructure using multiple wearable smart devices, namely smartphone and smartwatch placed in various locations on user's body for more accurate HPAD. A case study on a comprehensive dataset of classified human physical activities with our HAPD approach shows substantial improvement in HPAD accuracy.

• Asia pacific journal of information systems
• /
• v.27 no.1
• /
• pp.38-53
• /
• 2017

As sensor technologies and image processing technologies make collecting information on users' behavior easy, many researchers have examined automatic emotion recognition based on facial expressions, body expressions, and tone of voice, among others. Specifically, many studies have used normal cameras in the multimodal case using facial and body expressions. Thus, previous studies used a limited number of information because normal cameras generally produce only two-dimensional images. In the present research, we propose an artificial neural network-based model using a high-definition webcam and Kinect to recognize users' emotions from facial and bodily expressions when watching a movie trailer. We validate the proposed model in a naturally occurring field environment rather than in an artificially controlled laboratory environment. The result of this research will be helpful in the wide use of emotion recognition models in advertisements, exhibitions, and interactive shows.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.7 no.3
• /
• pp.671-677
• /
• 2012

A black-box program was implemented in order to monitor abnormal symptoms of human body irregularly occurring during sleep. The system consists of sensor probing body signals, auxiliary devices such as the alarm, lamp, network camera, and signal monitoring computer. Various types of sensors, PPG, ECG, EEG, temperature, respiration sensor, G-sensor, and microphone were used to more exactly identify the causes of abnormal symptoms. If a symptom occurs, the system records the patient's condition to provide information being utilized in the treatment. The sensors are attached on some locations of body being proper to check a specific type of abnormal reaction. Based on the normal range and type of measurement data, criteria of signal levels were set to distinguish abnormal reaction. An abnormal signal being probed, the program starts to operate the lamp, alarm, and network camera at the same time and stores the signal and video data.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.10 no.4
• /
• pp.17-22
• /
• 2010

As the services of ubiquitous environment has become accessible everywhere, it has been developed in various fields. Additionally interests in the u-Healthcare has sharply increased. In this paper, the BAN (Body Area Network) has been applied through ECG sensor and Zigbee communication of the existing ubiquitous sensor network environment to measure one's vital signs. The measured vital signs were then implemented in a system that enabled doctors and specialists to monitor by using 3G(WCDMA) communication. Furthermore, a location search device has been designed using the Smartphone's GPS modules to locate patients in the case of an emergency. The data field definition and designed system was based on the Smartphone's iPhone platform which has been in the spotlight for the previous months.

• Journal of the Korean housing association
• /
• v.19 no.5
• /
• pp.111-120
• /
• 2008

The aim of this study is to present the design methods about manifold location being installed and size and to draw out the proper piping size as comparing the fluctuation of discharge with manifold size and residence size through the piping network analysis, when using the same faucet in accordance. The findings are summarized as follows, 1) an appropriate header main body pipe diameter was deemed to be $32{\sim}50\;mm$. 2) the research presented design measures for the application of appropriate water supply inlet pipe diameters according to residential buildings with various sizes. 3) the header direct branch piping method is ideal for small and medium-sized residential complexes, and the header branching and semi header methods are deemed to be more favorable for large residential complexes. 4) this study offered design measures for appropriate header system main body pipe diameters, water supply inlet pipe diameters, header system piping methods, application methods for functional auxiliary equipment units, and header system installation spaces and location.