Prediction In-Hospital Cardiac Arrest within 8 hours using Vital signs

Title : Prediction In-Hospital Cardiac Arrest within 8 hours using Vital signs
Published in : The 16th Asia Pacific International Conference
on Information Science and Technology (APIC-IST 2021)
Author : Minsu Chae, Sangwook Han, Hyo-Wook Gil, Jun Ma, Min Hong, HwaMin Lee
Corresponding author : HwaMin Lee
Location : Paradise Hotel Busan, Korea

Abstract
The rapid response system in the hospital uses the early warning score (EWS) to predict in-hospital cardiac arrest. However, the traditional EWS has low precision and low recall. Since the precision is less than 4%, there has a problem with false alarms. We performed a retrospective cohort study in Soonchunhyang University Cheonan Hospital, which is a tertiary teaching hospital in the Republic of Korea. We performed by changing the data slice size to 8, 16, 24, 32, 40, 48, 56 hours. The deep learning model implemented in this paper has higher precision and recall than the traditional EWS.

Acknowledgments
This research was supported by Basic Science Research Program and the Bio & Medical Technology Development Program of the National Research Foundation (NRF) funded by the Korean government (MSIT) (NRF-2021R1A2C1009290 & No. NRF-2019M3E5D1A02069073). This research was supported by X-mind Corps program of National Research Foundation of Korea(NRF) funded by the Ministry of Science, ICT (No. 2019H1D8A1105622)

Prediction of Cardiac Arrest using LSTM in Hospitalized Patients

Title : Prediction of Cardiac Arrest using LSTM in Hospitalized Patients
Published in : The 4th International Conference on Interdisciplinary research on Computer science, Psychology, and Education (ICICPE’ 2020)
Author : Geonil Yun, Minsu Chae, Hyo-Wook Gil, Nam-Jun Cho, HwaMin Lee
Corresponding author : HwaMin Lee
Location : RAMADA PLAZA JEJU Hotel, Jeju Island, Korea and Online

Abstract
It is necessary to detect unexpected cardiac arrest early in the general ward of the hospital. However, the conventional Track and Trigger System (TTS) has low sensitivity and a high false alarm rate, which may not guarantee the safety of heart attack patients. In addition, false alarms can lead to a waste of movement by medical staff. This can be life-threatening as other critically ill patients lose access to treatment. Therefore, in this paper, we propose an LSTM deep learning network model that predicts heart attack within 24 hours with high sensitivity and low false alarm rate using patient vital signs.

Acknowledgments
This research supported by the MSIT (Ministry of Science and ICT), Korea, under the ITRC (Information Technology Research Center) support program(IITP-2020-2015-0-00403) supervised by the IITP (Institute for Information & communications Technology Planning & Evaluation) and X-mind Corps program of National Research Foundation of Korea (NRF) funded by the Ministry of Science, ICT (No. 2019H1D8A1105622).

Deep Learning based Cardiac Arrest Prediction using Vital sign and Lab code

Title : Deep Learning based Cardiac Arrest Prediction using Vital sign and Lab code
Published in : The 12th International Conference on Internet (ICONI 2020)
Author : Minsu Chae, Sangwook Han, Geonil Yun, Hyo-Wook Gil, Min Hong, DoKyeong Lee, HwaMin Lee
Corresponding author : HwaMin Lee
Location : Jeju ShinhwaWorld, Jeju, Korea

Abstract
There are patients in hospitals who are hospitalized for a variety of reasons. We conducted a study on predicting cardiac arrest on patients at Soonchunhyang University Cheonan Hospital. We studied patients from 2016 to 2019. We used deep learning via the LSTM model and the GRU model. We check density of each input feature according to cardiac arrest. We compared only patients with vital signs and lab data. We removed DBP, SBP, BodyTemperature, AST, ALT, WBC, Creatinine, and Bilirubin variable density because there was little difference between those with cardiac arrest and other patients. We experimented with the LSTM model and GRU Model. In this paper, deep learning-based cardiac arrest prediction using vital signs and lab data has high precision. In particular, when using the GRU model, even if the cardiac arrest of 0 to 24 hours for each record is changed, it has a sensitivity of 60%.

Acknowledgments
This research was supported by the Bio & Medical Technology Development Program of the National Research Foundation (NRF) funded by the Korean government (MSIT) (No. NRF-2019M3E5D1A02069073) and supported by the MSIT(Ministry of Science and ICT), Korea, under the ITRC(Information Technology Research Center) support program(IITP-2020-2015-0-00403) supervised by the IITP(Institute for Information & communications Technology Planning & Evaluation)

CNN and LSTM models for predicting particulate matter in the Republic of Korea

Title : CNN and LSTM models for predicting particulate matter in the Republic of Korea
Published in : The 8th International Conference on Information, System and Convergence Applications International Symposium on Innovation in Information Technology and Application 2020 (ICISCA 2020)
Author : Minsu Chae, Sangwook Han, HwaMin Lee
Corresponding author : HwaMin Lee
Location : Ton Duc Thang University, Ho Chi Minh, Vietnam and Online

Abstract
Recently, fine dust has become a problem all over the world. Many countries set regulations for PM10 and PM2.5. Because fine dust adversely affects human health, it is important to alert PM10 and PM2.5 in each city. Predictions for PM10 and PM2.5 are required to alert. We propose a hybrid model of the CNN(Convolutional Neural Network) model and the LSTM(Long Short-Term Memory) model to predict the PM10 and PM2.5 in the Republic of Korea. In addition, we evaluate the performance of the CNN model, the LSTM model, and the proposed hybrid model. As a result of the performance evaluation, the proposed hybrid model has high accuracy.

Acknowledgments
This research was supported by Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Science, ICT & Future Planning (NRF-2017R1A2B4010570).

Design of middleware to support auto-scaling in Docker-based multi host environment

Title : Design of middleware to support auto-scaling in Docker-based multi host environment
Published in : The 14th KIPS International Conference on Ubiquitous Information Technologies and Applications (CUTE 2019)
Author : Minsu Chae, Sangwook Han, HwaMin Lee
Corresponding author : HwaMin Lee
Location : University of Macau, Macau, China

Abstract
With the spread of smart devices, the use of big data, and the proliferation of the Internet of Things, virtualization technology for cloud servers have become important worldwide. Also, research has been conducted to efficiently manage the resources of hosts in VMs. Container-based virtualization has less performance degradation than VMs because there is no emulation for the operating system. Using the Docker API is slow to measure. In this paper, we implement the resource measurement module of Job nodes and design middleware that supports auto-scaling in auto-scaling module and Docker-based multi-host environment.

Acknowledgments
This research supported by the MSIT(Ministry of Science and ICT), Korea, under the ITRC(Information Technology Research Center) support program(IITP-2019-2014-1-00720 & IITP-2019-2015-0-00403) supervised by the IITP(Institute for Information & communications Technology Planning & Evaluation).

A Design of Cardiac Arrest Early Warning System in Hospital

Title : A Design of Cardiac Arrest Early Warning System in Hospital
Published in : The 3rd International Conference on Interdisciplinary Research on Computer Science, Psychology, and Education (ICICPE’ 2019)
Author : SangWook Han, MinSu Chae, Min Hong, HwaMin Lee
Corresponding author : HwaMin Lee
Location : Vinoasis Phu Quoc Hotel, Phu Qoc, Vietnam

Abstract
Recently, increasing heart failure patients due to the increase in elderly patients, high probability for these patients, the arrhythmia. The number of cardiac arrests in hospitals is also increasing, and mortality rates are more than twice as high as those transferred from general wards to the intensive care unit through the emergency room or other routes. Existing patient monitoring methods in hospitals are measured using 24-hour Holter monitoring. This method requires carrying the device and measuring up to 48 hours. Also, the patient’s activities are very uncomfortable because of the communication line. Currently, many hospitals use the Modified Early Warning Score (MEWS) as a standard for early detection of deterioration in general ward patients. However, the prediction rate is very low and there is little help. Many people are working hard to detect heart attacks early because computerized systems vary from hospital to hospital, it is difficult to apply the developed system to various hospital environments. This study discusses the factors and methods necessary to solve these problems.

Acknowledgments
This research was supported by MSIT(Ministry of Science and ICT), Korea, under the ITRC(Information Technology Research Center) support program(IITP-2019-2014-1-00720) supervised by the IITP(Institute for Information & communications Technology Planning & Evaluation) and the Bio & Medical Technology Development Program of the National Research Foundation (NRF)(No.NRF-2019M3E5D1A02069073).

CNN and RNN models for predicting particulate matter in South Korea

Title : CNN and RNN models for predicting particulate matter in South Korea
Published in : The 11th International Conference on Internet (ICONI 2019)
Author : Guang Yang, Thanongsak Xayasouk, HwaMin Lee
Corresponding author : HwaMin Lee
Location : Lotte Hotels & Resorts Hanoi, Hanoi, Vietnam

Abstract
Particulate matter proved to have severe effects on human health. To implement a real-time predicting system for is indispensable for every country face air pollution problem. Based on the previous study, predicting models for local areas are implemented. In this paper, a convolutional network, a recurrent neural network and a hybrid model combines the convolutional layers with the recurrent layers apply to predict future one weeks PM10 and PM2.5 concentration in seven urban cities in South Korea. The main contribution in this paper is: proposed three predicting models, make a comparison of three different models for predicting the concentration of particulate matter, all models are proved capable to obtain reliable predicting results. Experiments show GRU archive best performance for most cities both for PM10 and PM2.5, CNN models speed up the training process with least time consumption. The hybrid model performance stable with less time for training.

Acknowledgments
This research supported by the MSIT(Ministry of Science and ICT), Korea, under the ITRC(Information Technology Research Center) support program(IITP-2019-2015-0-00403) supervised by the IITP(Institute for Information & communications Technology Planning & Evaluation) and Basic Science Research Program through the National Research Foundation of Korea (NRF-2017R1A2B4010570).

Docker-based Cloud System for Computer Programming Labs

Title : Docker-based Cloud System for Computer Programming Labs
Published in : The 14th International Conference on Computer Science & Education (ICCSE 2019)
Author : Minsu Chae, Sangwook Han, HwaMin Lee
Corresponding author : HwaMin Lee
Location : The Oshawa Campus of Durham College and University of Ontario Institute of Technology(UOIT) Durham College, Toronto, Canada
URL : https://ieeexplore.ieee.org/document/8845470

Abstract
Recently, the importance of software education has been emphasized all over the world. In Korea, software education has been introduced for elementary schools that have applied for software education since 2015, and software education has been adopted as a regular subject in all elementary schools since 2017. As the importance of the software industry grows, interest in coding education is increasing. In Korea, students must complete 16 hours of instruction in elementary school and 34 hours in middle school from 2019. In Korea, however, there are not enough professional teachers who majored in software, and many schools have poor laboratory environments. For successful software coding education, a basic hands-on environment should be supported. It is also difficult for the teacher to analyze and score all students’ program sources during class. In this paper, we propose a computer labs management system that can be executed within seconds by using images already generated by Docker for software education at school. And we implemented a programming practice management system using Docker. Our system provides the ability for teachers to automatically identify and score students’ source code as they conduct coding training.

Acknowledgments
This research was supported by Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Science, ICT & Future Planning (NRF-2017R1A2B4010570) and the ITRC (Information Technology Research Center) support program (IITP-2019-2015-0-00403) supervised by the IITP(Institute for Information & communications Technology Promotion).

Design of the Eccentric Viewing Training Contents for the Rehabilitation of the Peripheral Visual Function

Title : Design of the Eccentric Viewing Training Contents for the Rehabilitation of the Peripheral Visual Function
Published in : The International Conference on Big data, IoT, and Cloud Computing (BIC 2019)
Author : DoKyeong Lee, HwaMin Lee
Corresponding author : HwaMin Lee
Location : MAISONGLAD JEJU Hotel, Jeju, Korea

Abstract
This study proposes Eccentric Viewing Training Content for Peripheral Visual Function Training using PC rehabilitation contents produced by Unity. The disability caused by the living difficulties of central brigs in the central visual acuity. People with low vision who have central scotoma need constant visual rehabilitation. However, the existing OBVT(Office-based vision therapy) has low access to training and high difficulty for long-term training. To overcome this inefficiency, this study proposes a training content that can be an HVT(Home vision therapy). The purpose of this study is to improve the accessibility and efficiency of eccentric viewing training and to enable rehabilitation training within fun elements of the game domain.

Acknowledgments
This research was supported by the MSIT(Ministry of Science and ICT), Korea, under the ITRC(Information Technology Research Center) support program(IITP-2019-2014-1-00720) supervised by the IITP(Institute for Information & communications Technology Planning & Evaluation) and the “ICT Convergence Smart Rehabilitation Industrial Education Program” through the Ministry of Trade, Industry & Energy (MOTIE) and Korea Institute for Advancement of Technology (KIAT).

Arrhythmia Classification System Using Deep Neural Network

Title : Arrhythmia Classification System Using Deep Neural Network
Published in : The 11th International Conference on Ubiquitous and Future Networks(ICUFN 2019)
Author : EunKwang Jeon, Sangwook Han, MinSu Chae, HwaMin Lee
Corresponding author : HwaMin Lee
Location : SHERATON ZAGREB Hotel, Zagreb, Croatia

Abstract
Previous studies on arrhythmia were used to diagnose the abnormally fast, slow, or irregular heart rhythm through ECG (Electrocardiogram), which is one of the biological signals. ECG has the form of P-QRS-T wave, and many studies have been done to extract the features of QRS-complex and R-R interval. However, in the conventional method, the P-QRS-T wave must be accurately detected, and the feature value is extracted through the P-QRS-T wave. If an error occurs in the peak detection or feature extraction process, the accuracy becomes very low. Therefore, in this paper, we implement a system that can perform PVC (Premature Ventricular Contraction) and PAC (Premature Atrial Contraction) classification by using P-QRS-T peak value without feature extraction process using deep neural network. The parameters were updated for PVC and PAC classification in the learning process using P-QRS-T peak without feature value. As a result of the performance evaluation, we could confirm higher accuracy than the previous studies and omit the process of feature extraction, and the time required for the preprocessing process to construct the input data set is relatively reduced.

Acknowledgments
This research supported by the MSIT (Ministry of Science and ICT), Korea, under the ITRC (Information Technology Research Center) support program (IITP-2019-2014-1-00720) supervised by the IITP(Institute for Information & communications Technology Planning & Evaluation) and Basic Science Research Program through the National Research Foundation of Korea (NRF-2017R1A2B4010570).