• Journal of Biomedical Engineering Research
• /
• v.42 no.4
• /
• pp.175-185
• /
• 2021

Purpose: Vital sign are used to help assess the general physical health of a person, give clues to possible diseases, and show progress toward recovery. Researchers are using vital sign data and AI(artificial intelligence) to manage a variety of diseases and predict mortality. In order to analyze vital sign data using AI, it is important to select and extract vital sign data suitable for research purposes. Methods: We developed a method to visualize vital sign and early warning scores by processing retrospective vital sign data collected from EMR(electronic medical records) and patient monitoring devices. The vital sign data used for development were obtained using the open EMR big data MIMIC-III and the wearable patient monitoring device(CareTaker). Data processing and visualization were developed using Python. We used the development results with machine learning to process the prediction of mortality in ICU patients. Results: We calculated NEWS(National Early Warning Score) to understand the patient's condition. Vital sign data with different measurement times and frequencies were sampled at equal time intervals, and missing data were interpolated to reconstruct data. The normal and abnormal states of vital sign were visualized as color-coded graphs. Mortality prediction result with processed data and machine learning was AUC of 0.892. Conclusion: This visualization method will help researchers to easily understand a patient's vital sign status over time and extract the necessary data.

• Journal of Sensor Science and Technology
• /
• v.31 no.6
• /
• pp.433-440
• /
• 2022

Recently, owing to global warming, average summer temperatures are increasing and the number of hot days is increasing is increasing, which leads to an increase in heat stroke. In particular, outdoor workers directly exposed to the heat are at higher risk of heat stroke; therefore, preventing heat-related illnesses and managing safety have become important. Although various wearable devices have been developed to prevent heat stroke for outdoor workers, applying various sensors to the safety helmets that workers must wear is an excellent alternative. In this study, we developed a smart helmet that measures various vital signs of the wearer such as body temperature, heart rate, and sweat rate; external environmental signals such as temperature and humidity; and movement signals of the wearer such as roll and pitch angles. The smart helmet can acquire the various data by connecting with a smartphone application. Environmental data can check the status of heat wave advisory, and the individual vital signs can monitor the health of workers. In addition, we developed an algorithm that classifies the risk of heat-related illness as normal and abnormal by inputting a set of vital signs of the wearer using a support vector machine technique, which is a machine learning technique that allows for rapid binary classification with high reliability. Furthermore, the classified results suggest that the safety manager can supervise the prevention of heat stroke by receiving feedback from the control system.

• Fashion & Textile Research Journal
• /
• v.24 no.1
• /
• pp.146-155
• /
• 2022

We proposed a simple process of creating electroconductive textiles by using PEDOT:PSS(Poly(3,4-ethylenedioxythiophene):poly(styrenesulfonate))/non-oxidized graphene to coat polyamide or polyurethane knitted fabric for smart healthcare purposes. Electroconductive textiles were obtained through a coating process that used different amounts of PEDOT:PSS/non-oxidized graphene solutions on polyamide/polyurethane knitted fabric. Subsequently, the surface, electrical, chemical, weight change, and elongation properties were evaluated according to the ratio of PEDOT:PSS/non-oxidized graphene composite(1.3 wt%:1.0 wt%; 1.3 wt%:0.6 wt%; 1.3 wt%:0.3 wt%) and the number of applications(once, twice, or thrice). The specimens' surface morphology was observed by FE-SEM. Further, their chemical structures were characterized using FTIR and Raman spectroscopy. The electrical properties measurement (sheet resistance) of the specimens, which was conducted by four-point contacts, shows the increase in conductivity with non-oxidized graphene and the number of applications in the composite system. Moreover, a test of the fabrics' mechanical properties shows that PEDOT:PSS/non-oxidized graphene-treated fabrics exhibited less elongation and better ability to recover their original length than untreated samples. Furthermore, the PEDOT:PSS/non-oxidized graphene polyamide/polyurethane knitted fabric was tested by performing tensile operations 1,000 times with a tensile strength of 20%; Consequently, sensors maintained a constant resistance without noticeable damage. This indicates that PEDOT:PSS/non-oxidized graphene strain sensors have sufficient durability and conductivity to be used as smart wearable devices.

• The Journal of Korean Physical Therapy
• /
• v.34 no.1
• /
• pp.45-50
• /
• 2022

Purpose: The purpose of this study was to compare the spatiotemporal and kinematic gait parameters and muscle activity of the lower extremities between forward walking on sand (FWS) and backward walking on sand (BWS) in normal adults. Methods: This study was conducted on 13 healthy adults. Subjects performed FWS and BWS and the spatiotemporal and kinematic gait parameters of stride time, stride length, velocity, cadence, step length, stance, swing, double support, and hip range of motion (ROM), knee ROM were measured by a wearable inertial measurement unit system. In addition, the muscle activity of the rectus femoris (RF), biceps femoris (BF), tibialis anterior (TA), and gastrocnemius (GA) was measured. Results: The stride length, stride velocity, cadence, and step length in the BWS were significantly lower than FWS (p<0.05), and stride time was significantly greater (p<0.05). However, there was no significant difference in the ratio of stance, swing, and double support between the two (p>0.05). The kinematic gait parameters, including hip and knee joint range of motion in BWS, were significantly lower than FWS (p<0.05). The muscle activity of the RF in BWS was significantly higher than FWS (p<0.05), but the muscle activity of the BF, TA, GA did not show any significant differences between the two movements (p>0.05). Conclusion: A strategy to increase stability by changing the gait parameters is used in BWS, and this study confirmed that BWS was a safe and effective movement to increase RF muscle activity without straining the joints. Therefore, BWS can be recommended for effective activation of the RF.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.47 no.3
• /
• pp.577-592
• /
• 2023

In this study, nanofiber-based textile sensors were developed for motion detection and monitoring. Poly(vinylidene fluoride) (PVDF) nanofibers containing zinc oxide (ZnO) nanoparticles and silver nanowires (AgNW) were fabricated using electrospinning. PVDF was chosen as a piezoelectric polymer, zinc oxide as a piezoelectric ceramic, and AgNW as a metal to improve electric conductivity. The PVDF/ZnO/AgNW nanocomposite fibers were used to develop a textile sensor, which was then incorporated into an elbow band to develop a wearable smart band. Changes in the output voltage and peak-to-peak voltage (V_p-p) generated by the joint's flexion and extension were investigated using a dummy elbow. The β-phase crystallinity of pure PVDF nanofibers was 58% when analyzed using Fourier transform infrared spectroscopy; however, the β-phase crystallinity increased to 70% in PVDF nanofibers containing ZnO and to 78% in PVDF nanocomposite fibers containing both ZnO and AgNW. The textile sensor's output voltage values varied with joint-bending angle; upon increasing the joint angle from 45° to 90° to 150°, the V_p-p value increased from 0.321 V_p-p to 0.542 V_p-p to 0.660 V_p-p respectively. This suggests that the textile sensor can be used to detect and monitor body movements.

• Journal of the Korean Society of Safety
• /
• v.39 no.1
• /
• pp.41-54
• /
• 2024

Efforts to reduce on-site safety incidents have expanded, leading to active research in this domain. However, a systematic analysis to improve the utility of technology is lacking. In this study, we conducted a survey on the various institutional and technical improvement measures to promote the application of smart construction safety technology over three years after the implementation of the "Smart Safety Equipment Support Project." The results showed that financial constraint was the primary obstacle in the adoption of this innovation. Fostering a flexible environment in the utilization of management fees and financial support of projects was determined to aid in the extensive application of the technology. Ensuring cost efficiency and user-friendliness were principally necessary for technical enhancements in the smart construction safety technology. Technologies, such as VR/AR safety education, real-time location tracking, wearable devices, and innovation on streamlining safety-related work efficiency, had been anticipated to contribute to on-site safety. Operating a smart safety control center was expected to be beneficial in the systematic securing of data and reduction of safety blind spots. Effective methods had been suggested to overcome the barriers that hindered the development and application of smart construction safety technology. This study facilitates in the technological improvements in this field.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.39C no.10
• /
• pp.920-929
• /
• 2014

Recently, embedded system which demand is explosively increasing in the fields of communication, traffic, medical and industry facilities, expands to cyber physical system (CPS) which monitors and controls the networked embedded systems. In addition, internet of things(IoT) technology using wearable devices such as Google Glass, Samsung Galaxy Gear and Sony Smart Watch are gaining attention. In this situation, Samsung Smart Home and LG Home Chat are released one after another. However, since these services can be available only between smart phones and home appliances, there is a disadvantage that information cannot be passed to other terminals without commercial global messaging server. In this paper, to solve above issues, we propose the structure of an indoor location network based on unit space, which prevents the information of the devices or each individual person from leaking to outside and can selectively communicate to all existent terminals in the network using IoT chatting. Also, it is possible to control general devices and prevent external leakage of private information.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.38C no.12
• /
• pp.1106-1113
• /
• 2013

For patients who have senile mental disorder such as dementia, quantity of excercise and amount of sunlight are important clue for dose and the treatment. Therefore, monitoring health information of daily life is necessary for patients' safety and healthy life. Portable & wearable sensor device and server configuration monitoring data are needed to provide these services for patients. Watch-type device(smart watch) which patients wear and server system are developed in this paper. Smart watch developed includes GPS, accelerometer and illumination sensor, and can obtain real time health information by measuring the position of patients, quantity of exercise and amount of sunlight. Server system includes the sensor data analysis algorithm and web server that doctor and protector can monitor through sensor data acquired from smart watch. The proposed data analysis algorithm acquires quantity of exercise information and detects step count in patients' motion acquired from acceleration sensor and to verify this, the three cases with fast pace, slow pace, and walking pace show 96% of the experimental result. If developed u-Healthcare System for dementia patients is applied, more high-quality medical service can be provided to patients.

• The Journal of the Korea Contents Association
• /
• v.14 no.11
• /
• pp.467-475
• /
• 2014

With the development of genomics, wearable device and IT/NT, a vast amount of bio-medical data are generated recently. Also, healthcare industries based on big-data are booming and big-data technology based on bio-medical data is rising rapidly as a core technology for improving the national health and aged society. A pathway is the biological deep knowledge that represents the relations of dynamics and interaction among proteins, genes and cells by a network. A pathway is wildly being used as an important part of a bio-medical big-data analysis. However, a pathway analysis requires a lot of time and effort because a pathway is very diverse and high volume. Also, multidimensional analysis systems for various pathways are nonexistent even now. In this paper, we proposed a pathway analysis system that collects user interest pathways from KEGG pathway database that supports the most widely used pathways, constructs a network based on a hierarchy structure of pathways and analyzes the relations of dynamics and interaction among pathways by clustering and selecting core pathways from the network. Finally, to verify the superiority of our pathway analysis system, we evaluate the performance of our system in various experiments.

• The Journal of the Korea Contents Association
• /
• v.16 no.6
• /
• pp.260-269
• /
• 2016

With the development of genomics, wearable device and IT/NT, a vast amount of bio-medical data are generated recently. Also, healthcare industries based on big-data are booming and big-data technology based on bio-medical data is rising rapidly as a core technology for improving the national health and aged society. Also, oriental medicine research is focused with modern research technology and validate it's various biochemical effect by combining with molecular biology technology. However there are few searching system for finding biochemical mechanism which is related to major compounds in oriental medicine. Therefore, in this paper, we collected papers related with medical herbs from PubMed and constructed a medical herbs database to store and manage chemical, gene/protein and biological interaction information extracted by a literature analysis on the papers. Also, to supporting a multidimensional analysis on the database, we developed a network analysis system based on a hierarchy structure of chemical, gene/protein and biological interaction information. Finally, we expect this system will be used the major tool to discover various biochemical effect by combining with molecular biology technology.