• The Journal of Asian Finance, Economics and Business
• /
• 제8권2호
• /
• pp.737-745
• /
• 2021

This study aims to determine whether there are differences in the average abnormal return, trading volume activity, and trading frequency activity in pharmaceutical stocks before and after the announcement of the first case of the coronavirus (COVID-19) in Indonesia. The sample was selected using a purposive sampling method and collected as many as nine pharmaceutical companies listed on the Indonesia Stock Exchange during 2019-2020. The data used in this study were secondary data in the form of daily data on stock closing prices, Composite Stock Price Index (IHSG), stock volume trading, number of shares outstanding, and stock trading frequency. This study was an event study with an observation period of 14 days, namely seven days before and seven days after the announcement of the coronavirus's first positive case in Indonesia. Hypothesis testing employed the paired sample t-test method. Based on the results, it was found that there was no difference in the average abnormal return of pharmaceutical stocks before and after the announcement of the first case of COVID-19. However, there was a difference in the average trading volume activity and the average trading frequency activity in pharmaceutical stocks before and after the announcement of the first case of COVID-19.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2022년도 춘계학술대회
• /
• pp.498-500
• /
• 2022

CCTV는 위험 상황을 파악하고 신속히 대응함으로써, 인명과 자산을 안전하게 보호한다. 하지만, 점점 많아지는 CCTV 영상을 지속적으로 모니터링하기는 어렵다. 이런 이유로 CCTV 영상을 지속적으로 모니터링하면서 이상행동이 발생했을 때 알려주는 장치가 필요하다. 최근 영상데이터 분석에 인공지능 모델을 활용한 많은 연구가 이루어지고 있다. 본 연구는 CCTV 영상에서 관측할 수 있는 다양한 이상 행동을 분류하기 위해 영상데이터 사이의 공간적, 시간적 특성 정보를 동시에 학습한다. 학습에 이용되는 인공지능 모델로 End-to-End 방식의 3D-Convolution Neural Network(CNN)와 ResNet을 결합한 다중 분류 딥러닝 모델을 제안한다.

• Nuclear Engineering and Technology
• /
• 제55권2호
• /
• pp.506-515
• /
• 2023

This study is to find a method to learn engine sound after the start-up of a diesel generator installed in nuclear power plant with an unsupervised deep learning algorithm (CNN autoencoder) and a new method to predict the failure of a diesel generator using it. In order to learn the sound of a diesel generator with a deep learning algorithm, sound data recorded before and after the start-up of two diesel generators was used. The sound data of 20 min and 2 h were cut into 7 s, and the split sound was converted into a spectrogram image. 1200 and 7200 spectrogram images were created from sound data of 20 min and 2 h, respectively. Using two different deep learning algorithms (CNN autoencoder and binary classification), it was investigated whether the diesel generator post-start sounds were learned as normal. It was possible to accurately determine the post-start sounds as normal and the pre-start sounds as abnormal. It was also confirmed that the deep learning algorithm could detect the virtual abnormal sounds created by mixing the unusual sounds with the post-start sounds. This study showed that the unsupervised anomaly detection algorithm has a good accuracy increased about 3% with comparing to the binary classification algorithm.

• 정보과학회 논문지
• /
• 제41권12호
• /
• pp.1066-1074
• /
• 2014

본 논문에서는 시공간 정보를 포함하는 트윗 스트림에서 비정상적인 이벤트에 대한 상관관계를 사용자에게 시각적으로 분석하는 방법을 다양한 실험을 통하여 제안한다. 제안하는 방법으로는 트윗에서 토픽 모델링을 수행한 다음 계절요인과 추세요인을 반영한 시계열 분석 기법을 이용하여 비정상적인 이벤트 후보군을 추출한다. 추출된 토픽이 포함되어 있는 데이터를 대상으로 다시 한 번 토픽을 추출하여 시계열 분석을 수행한 다음 앞서 추출한 토픽과의 상관관계를 분석하여 비정상적인 이벤트를 탐지할 수 있도록 하였다. 비정상 이벤트를 탐지하는 모든 과정에 시각적 분석 방법을 이용하여 단순한 수치 정보가 아닌 시각적 패턴 형태로 나타냄으로써 사용자는 직관적으로 비정상 이벤트의 동향과 주기적인 패턴을 분석할 수 있도록 하였다. 실험은 2014년 1월 1일부터 2014년 6월 30일까지 국내에서 발생한 트윗을 대상으로 2개의 사건[경주 마우나 리조트 붕괴 사건(2014.02.17.), 진도 여객선 침몰 사건(2014.04.16.)]에 대해 시각적 분석 시스템을 적용하여 사용자는 쉽게 데이터를 분석하고 이해할 수 있음을 보였다.

• 한국전자통신학회논문지
• /
• 제7권3호
• /
• pp.671-677
• /
• 2012

수면 중에 부정기적으로 발생하는 인체 이상유형을 모니터링하기 위한 블랙박스 프로그램을 구현하였다. 인체 블랙박스 시스템은 생체 신호를 계측하는 센서와 알람, 전등, 네트워크 카메라와 같은 보조 장치 및 신호를 모니터링 하는 컴퓨터로 구성되어 있다. 신체 이상 증상의 원인을 정확하게 규명하기 위하여 PPG, EOG, EEG, 호흡센서, 온도센서, G-센서 및 마이크로폰과 같은 다양한 센서를 이용하였다. 이상 증상이 발생하면 시스템은 치료에 활용할 수 있는 정보를 제공하기 위해서 환자의 상태를 기록한다. 신체 이상유형을 감지하게 위하여 적절한 센서 위치를 선정한다. 측정 데이터의 유형별 정상 범위에 근거하여, 신체 이상유형을 구별하기 위한 신호 수준을 선정하였다. 이상 신호가 계측되면 전등 및 알람, 네트워크 카메라가 동시에 작동하고, 센서 신호 및 비디오 데이터가 저장된다.

• 통합자연과학논문집
• /
• 제17권2호
• /
• pp.33-41
• /
• 2024

Abnormal climate is a phenomenon in which meteorological factors such as temperature and precipitation are significantly higher or lower than normal, and is defined by the World Meteorological Organization as a 30-year period. However, over the past 30 years, abnormal climate phenomena have occurred more frequently around the world than in the past. In Korea, abnormal climate phenomena such as abnormally high temperatures on the Korean Peninsula, drought, heatwave and heavy rain in summer are occurring in March 2023. Among them, heatwaves are expected to increase in frequency compared to other abnormal climates. This suggests that heatwave should be recognised as a disaster rather than just another extreme weather event. According to several previous studies, greenhouse gases and meteorological factors are expected to affect heatwaves, so this paper uses logistic regression and discriminant analysis on meteorological element data and greenhouse gas data in Gwangju from 2008 to 2022. We analyzed the impact of heatwaves. As a result of the analysis, greenhouse gases were selected as effective variables for heatwaves compared to the past, and among them, chlorofluorocarbons were judged to have a stronger effect on heatwaves than other greenhouse gases. Since greenhouse gases have a significant impact on heatwaves, in order to overcome heatwaves and abnormal climates, greenhouse gases must be minimized to overcome heatwaves and abnormal climates.

• 한국초지조사료학회지
• /
• 제42권2호
• /
• pp.127-136
• /
• 2022

본 연구는 기계학습을 기반으로 제작한 수량예측모델을 통해 이상기상에 따른 사일리지용 옥수수(WCM)의 피해량 산정 및 전자지도를 작성할 목적으로 수행하였다. WCM 데이터는 수입적응성 시험보고서(n = 1,219), 국립축산과학원 시험연구보고서(n = 1,294), 한국축산학회지(n = 8), 한국초지조사료학회지(n = 707) 및 학위논문(n = 4)에서 총 3,232점을 수집하였으며 기상 데이터는 기상청의 기상자료개방포털에서 수집하였다. 본 연구에서 이상기상에 따른 WCM의 피해량은 WMO 방식을 준용하여 산정하였다. 정상기상에서 DMY 예측값은 13,845~19,347 kg/ha 범위로 나타났으며 피해량은 이상기온, 이상강수량 및 이상풍속에서 각각 -305~310, -54~89 및 -610~813 kg/ha 범위로 나타났다. 최대 피해량은 이상풍속에서 813 kg/ha로 나타났다. WMO 방식을 통해 산정한 WCM의 피해량은 QGIS를 이용하여 전자지도로 제시하였다. 이상기상에 따른 WCM의 피해량 산정시 데이터가 없어 공백인 지역이 존재하여 이를 보완하기 위해 종관기상대보다 많은 지점의 데이터를 제공하고 있는 방재기상대를 이용하면 보다 세밀한 피해량을 산정할 수 있을 것이다.

• Smart Structures and Systems
• /
• 제20권2호
• /
• pp.219-229
• /
• 2017

Outlier detection is an imperative task to identify the occurrence of abnormal events before the structures are suffered from sudden failure during their service lives. This paper proposes a two-phase method for the outlier detection of Global Positioning System (GPS) monitoring data. Prompt judgment of the occurrence of abnormal data is firstly carried out by use of the relational analysis as the relationship among the data obtained from the adjacent locations following a certain rule. Then, a negative selection algorithm (NSA) is adopted for further accurate localization of the abnormal data. To reduce the computation cost in the NSA, an improved scheme by integrating the adjustable radius into the training stage is designed and implemented. Numerical simulations and experimental verifications demonstrate that the proposed method is encouraging compared with the original method in the aspects of efficiency and reliability. This method is only based on the monitoring data without the requirement of the engineer expertise on the structural operational characteristics, which can be easily embedded in a software system for the continuous and reliable monitoring of civil infrastructure.

• International Journal of Internet, Broadcasting and Communication
• /
• 제15권2호
• /
• pp.240-247
• /
• 2023

In this paper, effective data management in industrial sites such as intelligent factories using time series data was studied. For effective management of time series data, variables considering the significance of the data were used, and hyper parameters calculated through LSTM AE were applied. We propose an optimized modeling considering the importance of each data section, and through this, outlier data of time series data can be efficiently processed. In the case of applying data significance and applying hyper parameters to which the research in this paper was applied, it was confirmed that the error rate was measured at 5.4%/4.8%/3.3%, and the significance of each data section and the significance of applying hyper parameters to optimize modeling were confirmed.

• 부모자녀건강학회지
• /
• 제5권2호
• /
• pp.177-190
• /
• 2002

This study were conducted to assess the physical growth and developmental status of infants in orphanage in order to provide an empirical data. The subjects for this study were 104 infants and toddlers who were reared in an orphanage in D Metropolitan city. The instrument used for this study were anthropometric assessment and DDST for normative data of development. Data has been collected from September 1st, 1998 to August 31st, 2000 and were analyzed using SPSS/PC(Version 10.0) with frequency, mean, standard deviation, ANOVA and Chi-square test. The results of this study were as follows; 1. 30.8% of infants in orphanage had abnormal weight, 26.9% had abnormal length, and 22.1% had abnormal head circumference and most of them were distributed below 50 percentile of growth chart. 2. 53.8% of infants in orphanage had normal, 27.9% had qustionable, and 18.3% had abnormal developmental screening test results, especially, 31.5% of infants in orphanage ages 3 to 5 years had abnormal developmental screening test results, according to the Denver Developmental Screening Test(DDST). There was a significant developmental delay noted in the language and fine motor-adaptive sector. 3. It is anticipated that developmental delays would increase in severity by older the mean age of orphanage infants and longer the time being raised in orphanage. It would be concluded that the physical growth and developmental status of orphaned infants were very vulnerable and serious and it is suggested that there needed an effective intervention strategies to promote growth and development of infants in orphanage.