• Proceedings of the Korean Society of Computer Information Conference
• /
• 2018.07a
• /
• pp.343-344
• /
• 2018

장애인들의 안전사고 비율이 증가함에 따라 이에 대한 대비책에 대해 사회적인 관심이 집중되고 있다. 특히 청각장애인의 경우 실외에서 시야가 확보되지 않으면 상대적으로 위험에 취약하다. 본 논문은 청각장애인들이 듣지 못하는 위험한 상황에 대해 IoT 센서를 부착한 목걸이 형태의 웨어러블 기기를 통해 소리를 감지하고 알림을 주는 시스템을 제안한다. 제시된 시스템을 통해 감지된 소리를 진동과 함께 시각적으로 사용자에게 보여주어 위험한 상황을 대비할 수 있는 웨어러블 시스템을 설계하였다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2014.10a
• /
• pp.469-471
• /
• 2014

기존의 온도 측정 시스템은 사용자의 체온 혹은 주변의 온도를 알기 위해서 여러 매체들을 이용하여 조사하고, 또한 매체들을 통해서 나오는 온도들은 그 지역 혹은 장소의 평균적인 온도를 가르쳐 주므로 사용자의 온도 및 사용자 주변 온도를 알기가 어려웠다. 최근 사용자의 정보를 알기위해 의류와 IT를 융합한 웨어러블 제품들이 많이 출시되고 있지만 사용자의 온도 및 사용자 주변 온도를 측정하는 제품들은 아직 출시가 되어 있지 않다. 본 논문에서는 현재 시중에 제공되고 있는 웨어러블 제품들과 다른 사용자의 체온을 측정하고 사용자 주변의 온도를 측정하여 사용자의 편의를 제공하고, 사용자가 저체온증 같은 신체 온도위주의 병에 걸리지 않도록 알려주고 이를 통해 사용자가 인지하여 후속 조치를 할 수 있는 방법을 제시하였다.

• Annual Conference of KIPS
• /
• 2018.05a
• /
• pp.428-430
• /
• 2018

본 논문에서는 독감확산 예측을 위한 웨어러블 센서를 이용한 기침 감지 모델을 제안한다. 서로 상이한 기침 신체데이터를 사용하고 기침 감지 알고리즘의 구현없이 기계가 학습하는 방식인 멀티모달 DNN을 이용하여 설계하였다. 또한 웨어러블 센서를 통해 실생활의 기침 오디오 데이터와 기침 3축 가속도 데이터를 수집하였고, 두 개의 데이터중 하나의 데이터만으로도 감지를 위한 학습이 가능토록하기 위해 각각 MFCC와 FFT를 이용하여 특징 벡터를 추출하는 방법을 이용하였다.

• Journal of KIISE:Software and Applications
• /
• v.41 no.8
• /
• pp.586-597
• /
• 2014

The next generation mobile computing technology is recently attracting attention that smartphone and wearable device imbedded with various sensors are being deployed in the world. Existing activity and posture recognition research can be divided into two different ways considering feature of one's movement. While activity recognition focuses on catching distinct pattern according to continuous movement, posture recognition focuses on sudden change of posture and body orientation. There is a lack of research constructing a system mixing two separate patterns which could be applied in real world. In this paper, we propose a method to use both smartphone and wearable device to recognize activity and posture in the same time. To use smartphone and wearable sensor data together, we designed a pre-processing method and constructed recognition model mixing signal vector magnitude and orientation pattern features of vertical and horizontal. We considered cycling, fast/slow walking and running activities, and postures such as standing, sitting, and laying down. We confirmed the performance and validity by experiment, and proved the feasibility in real world.

• Journal of KIISE
• /
• v.43 no.5
• /
• pp.531-540
• /
• 2016

Development of various sensors attached to mobile and wearable devices has led to increasing recognition of current context-based service to the user. In this study, we proposed a probabilistic model for recognizing user's food intake context, which can occur in a great variety of contexts. The model uses low-level sensor data from mobile and wrist-wearable devices that can be widely available in daily life. To cope with innate complexity and fuzziness in high-level activities like food intake, a context model represents the relevant contexts systematically based on 4 components of activity theory and 5 W's, and tree-structured Bayesian network recognizes the probabilistic state. To verify the proposed method, we collected 383 minutes of data from 4 people in a week and found that the proposed method outperforms the conventional machine learning methods in accuracy (93.21%). Also, we conducted a scenario-based test and investigated the effect contribution of individual components for recognition.

• 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.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.13 no.4
• /
• pp.813-820
• /
• 2009

This paper describes the realization of ubiquitous healthcare monitoring system using wearable pulse oximeter based on a wireless sensor network. In order to obtain information of oxygen saturation from a patient, a small size and low power consumption wearable pulse oximeter was designed. Information of oxygen saturation collected by wireless sensor node was transmitted wirelessly to a base-station for storage and display purposes via wireless sensor network. Wireless sensor nodes were programmed by TinyOS application to perform data acquisition and transmission. Lab VIEW server program was designed to monitor information of oxygen saturation and process the measured PPG (photo plethysmogram) signals to APG(Accelerated plethysmogram) signals by appling second order derivatives. PPG signals are simple and cost effective technique to measure blood volume change.

• Journal of Internet Computing and Services
• /
• v.16 no.5
• /
• pp.11-17
• /
• 2015

In the general transmission power control model that is used for wearable sensor systems, if RSSI value gets out of the Target RSSI Margin, then the sink node finds new transmission power by using TPC(Transmission Power Control) Algorithm. At this time, the sink node sends the control packet to the sensor node for delivering the newly calculated transmission power. However, when the wireless network channel condition is poor, even it is consuming a lot of control packets, the sink node could not find an appropriate transmission power so it only waste of energy. Therefore, we proposed a new control packet transmission decision method that the sink node changes the transmission power when the wireless network channel condition is stabilized. It makes waste of energy decline. In this paper, we apply control packet transmission decision method to Binary TPC algorithms and analyze the results to evaluate the proposed method. We propose three methods that judge the state of wireless network channel. We experiment that methods and analysis the results.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.39B no.12
• /
• pp.842-855
• /
• 2014

Recently, the progress of smart phone market has retarded by oversupply therefore wearable computer has been the focus of new growth engine. Wearable computing system is a complex fusion of a variety of technologies such as wireless network, embedded, sensor and new material. Because these technologies involves utilization and mobility in addition to quality characteristic in existing software, application of ISO/IEC 9126 is not perfect when assessing quality of wearable computer. In this study, author suggested new quality assessment model for wearable computer by sorting quality attribute in ISO/IEC 9126 and adding new quality attribute. For this, author investigated features and functional requirements related to wearable computer. and then author suggested quality standard and metrics by identifying quality characteristic. Author confirmed practicality of quality assessment model by using suggested model in scenario and comparing quality assessment of three goods such as company S, L, G. This quality assessment model is expected to use guidelines for assessing quality of wearable computer.

• Journal of Korea Multimedia Society
• /
• v.15 no.7
• /
• pp.879-884
• /
• 2012

In this Paper, we propose an Energy Efficient Time Synchronization technique based on WUSB (Wireless USB) over WBAN (Wireless Body Area Networks) protocol required for Wearable Computer systems. For this purpose, the proposed Time Synchronization algorithm minimizes power consumption and estimates time information with accuracy. It is executed on the basis of WUSB over WBAN protocol at each sensor node comprising peripherals of a wearable computer system. It minimizes power consumption by exchanging time stamp packets and forming a hierarchical structure.