• Journal of Digital Convergence
• /
• v.20 no.2
• /
• pp.261-268
• /
• 2022

Recently, the number of elderly living alone suffering from loneliness and depression is also increasing significantly due to the rapid aging of the population and nuclear families. In this paper, we propose a smart aging system that increases life satisfaction by providing the elderly with the optimal service tailored to the elderly with the help of IT according to their residential environment and health status. It is possible to provide an advanced customized support system for the elderly by fully utilizing IoT, AI, and Metaverse techniques not only for the elderly who want to live an active life in society but also for the elderly who need care in a nursing hospital. The proposed system provides human satisfaction by providing social connection in real space and virtual space in accordance with the residential environment and health status to the elderly suffering from loneliness in hospital (hospital care) facilities and at home. This paper proposes a new path for future-oriented welfare policy for the elderly by providing a user-customized smart aging system by combining AI and Metaverse technology with a rapidly changing social environment.

• Journal of Intelligence and Information Systems
• /
• v.7 no.1
• /
• pp.63-79
• /
• 2001

Data Envelopment Analysis(DEA), a non-parametric productivity analysis tool, has become an accepted approach for assessing efficiency in a wide range of fields. Despite of its extensive applications and merits, some features of DEA remain bothersome. DEA offers no guideline about to which direction relatively inefficient DMUs improve since a reference set of an inefficient DMU, several efficient DMUs, hardly provides a stepwise path for improving the efficiency of the inefficient DMU. In this paper, we aim to show that DEA can be used to evaluate the efficiency of life insurance companies while overcoming its limitation with the aids of machine learning methods.

• Annual Conference of KIPS
• /
• 2017.04a
• /
• pp.822-825
• /
• 2017

본 연구는 키넥트를 통해 사람의 걸음걸이를 측정하고 의사결정트리(Decision Tree)를 통해 분석함으로써 현재의 걸음걸이를 통해 측정자의 허리 또는 무릎에서 발생할 가능성이 높은 문제 또는 질병들을 예측하고 해당결과를 측정자에게 알린다. 본 연구를 진행하며 첫 번째 단계에서는 관련 논문이나 병원 자료 결과들을 통해 판별할 속성들을 정하였다. 두 번째 단계에서는 키넥트를 통해 측정한 실제 데이터를 적용하기에 앞서 첫 번째 단계에서 정한 속성들이 측정자의 문제 또는 질병들을 판단해내는 연관 정도가 높은지 테스트 데이터를 이용하였고 의사결정나무를 통해 분석하였다. 그 결과 7개의 속성 중 6개로 약 85.7%정도의 연관이 있었다. 마지막 세 번째 단계에서는 판별식을 세우고 실제 데이터들을 쌓아나가며 69명의 측정한 데이터를 분석한 결과 6개의 속성 중 5개의 속성이 허리와 연관정도가 높았고 이는 두 번째 단계에서 나왔던 결과인 약85.7%에 가까운 약83%의 결과가 도출되었다. 이를 기반으로 시스템을 개발해 나가며 판별 정확도를 향상시키기 위해 계속 측정해 데이터를 쌓아가고 관련된 식들의 문제점을 보완하며 또한 어떤 환경에서 키넥트의 측정값의 정확도가 올라가는지 연구할 예정이다.

• Proceedings of the Korea Contents Association Conference
• /
• 2006.05a
• /
• pp.479-482
• /
• 2006

Mobile Telemedicine uses common technologies that provide a conduit for information exchange between physicians nurses and patients. In addition to patient records, medical professionals will obtain vital signs and other reference data through Ubiquitous Sensor networks(USN). In this paper about a design and implementation of RFID reader platform that received RFID tag information from patients tags, transmit the data to SBC(Single board computer) based on Intel PXA255 ARM CPU and SBC transmit the data to MySQL server in hospital using by Wireless Internet. his system that based on Embedded Linux is composed of RFID module, ARM processor, RS-232 interface, and Wireless LAN. This paper also provides a brief overview and concept of RFID reader, and proposes the design and implementations of the RFID reader platform used QT and MySQL based on Embedded Linux.

• Asia pacific journal of information systems
• /
• v.15 no.1
• /
• pp.81-113
• /
• 2005

IT has affected the hospital management via information systems and multimedia systems such as hospital information systems(HIS) and Order Communication System(OCS). A large number of researches have been done on the topic of success factors of information systems implementation, but a few on the topics of hospital information systems. Thus in this study, the success factors of the military hospital information systems implementation was analysed. To this end, a number of previous researches were reviewed and about 71 items of success factors were deduced. For doing empirical analysis, a questionnaire with 71 items was prepared and sent to proper organizations. The statistical analysis such as factor analysis was applied to about 400 of them returned. The six success factors and 20 sub success factors were resulted from factor analysis. The six success factors include systems management factor, technology and organization factor, the efficiency of IT department factor, technology application factor, outsourcing factor and environment factors. This study finds the outsourcing and environment factors are very important factors as much as other success factors which previously were mentioned.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2003.10a
• /
• pp.325-328
• /
• 2003

This paper is studied about the DC motor synchronization control for robot driving DC motor where is located in long distance place. The DC motors are received the speed order through internet with realtime. We designed the PID controller that related to PWM voltage and revolution given by 80C196KC $\mu$-Processor to move DC motors, so two motors were synchronized quickly about the order of random speed or location by PID controller. Furthermore, we controlled motors with realtime through internet by using lava platform that had a excellent compatibility, and monitored the speed of two motors.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2001.05a
• /
• pp.437-442
• /
• 2001

Recently, transformerless inverters have been studied to reduce sizes and costs of utility-connected PV systems. This paper presents a transformerless PV inverter using a two-phase boost converter of reduced ripples in input current and output voltage, low voltage stress of semiconductor device and reduced size of input reactor. And new PWM method is introduced, whose on-off time is calculated from simultaneous equation induced by fourier series. To verify a validity of the proposed transformerless inverter, computer simulation has been carried out.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2018.10a
• /
• pp.286-287
• /
• 2018

As the number of single-person households is increasing in Korea, the demand for emergency support networks for the elderly and women is also growing. To meet the need, systemic solutions, such as a wide distribution of cell phones with embedded motion sensors that can alert the first responders or police in case of health or safety crisis, are regarded as critical issues. This paper introduces a design which registers the user's motions to process emergency reports via a mobile app running in the background. The method offers an affordable solution to reporting emergencies taking place both indoors and outdoors as it does not require an addition of hardware but only simple hand gestures.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.3 no.1
• /
• pp.97-104
• /
• 1999

In this study we show a telemedicine system using a DSP, which gives fast and exact medical data such as the ECG signal of the external emergency patient and enables the patient to get temporary treatments under the direction of a doctor in the hospital. This transceiver, which is able to treat the real time transmission of dynamic medical data captured by the measuring instrument and bidirectional communication of voice signal, is implemented using DSB-SC as modulation and demodulation technique and digital filter of each terminal are implemented as FIR filter. The system designed with DSP in this study is very small and compact and it can k, furthermore, to support additional biomedical signals just by renewing the software.

• Annual Conference of KIPS
• /
• 2021.11a
• /
• pp.805-807
• /
• 2021

In-hospital cardiac arrest is a significant problem for medical systems. Although the traditional early warning systems have been widely applied, they still contain many drawbacks, such as the high false warning rate and low sensitivity. This paper proposed a strategy that involves a deep learning approach based on a novel interpretable deep tabular data learning architecture, named TabNet, for the Rapid Response System. This study has been processed and validated on a dataset collected from two hospitals of Chonnam National University, Korea, in over 10 years. The learning metrics used for the experiment are the area under the receiver operating characteristic curve score (AUROC) and the area under the precision-recall curve score (AUPRC). The experiment on a large real-time dataset shows that our method improves compared to other machine learning-based approaches.