• Communications for Statistical Applications and Methods
• /
• 제31권2호
• /
• pp.213-234
• /
• 2024

In recent decades, increasing research attention has been directed toward predicting the price of stocks in financial markets using deep learning methods. For instance, recurrent neural network (RNN) is known to be competitive for datasets with time-series data. Long short term memory (LSTM) further improves RNN by providing an alternative approach to the gradient loss problem. LSTM has its own advantage in predictive accuracy by retaining memory for a longer time. In this paper, we combine both supervised and unsupervised dimension reduction methods with LSTM to enhance the forecasting performance and refer to this as a dimension reduction based LSTM (DR-LSTM) approach. For a supervised dimension reduction method, we use methods such as sliced inverse regression (SIR), sparse SIR, and kernel SIR. Furthermore, principal component analysis (PCA), sparse PCA, and kernel PCA are used as unsupervised dimension reduction methods. Using datasets of real stock market index (S&P 500, STOXX Europe 600, and KOSPI), we present a comparative study on predictive accuracy between six DR-LSTM methods and time series modeling.

• 한국지하수토양환경학회:학술대회논문집
• /
• 한국지하수토양환경학회 2003년도 추계학술발표회
• /
• pp.199-201
• /
• 2003

The monitoring effectiveness not only depends on the effectiveness of the network, but also the costs of the network. Generally the costs of the monitoring network are mainly on the equipment and personnel; the implementation and maintenance; the observation and sample connection; the sample analysis; and the data storage and processing. The cost of the monitoring network can be expressed as a function of monitoring frequency because the monitoring method can be an automatic or a manual measurement. To determine the sampling frequency of subsidiary groundwater monitoring stations, time series data of national groundwater monitoring stations were used. The proposed optimal sampling frequency for subsidiary groundwater monitoring station is about 7 to 20 days and the average frequency is about 2 weeks.

• 디지털산업정보학회논문지
• /
• 제15권2호
• /
• pp.19-28
• /
• 2019

The purpose of this study is to examine the trends on machine learning and deep learning research in the published journals from the Web of Science Database. To achieve the study purpose, we used the abstracts of 20,664 articles published between 1990 and 2017, which include the word 'machine learning', 'deep learning', and 'artificial neural network' in their titles. Twenty major research topics were identified from topic modeling analysis and they were inclusive of classification accuracy, machine learning, optimization problem, time series model, temperature flow, engine variable, neuron layer, spectrum sample, image feature, strength property, extreme machine learning, control system, energy power, cancer patient, descriptor compound, fault diagnosis, soil map, concentration removal, protein gene, and job problem. The analysis of the time-series linear regression showed that all identified topics in machine learning research were 'hot' ones.

• 전자통신동향분석
• /
• 제36권4호
• /
• pp.145-153
• /
• 2021

Data imputation is a crucial issue in data analysis because quality data are highly correlated with the performance of AI models. Particularly, it is difficult to collect quality time-series data for uncertain situations (for example, electricity blackout, delays for network conditions). Thus, it is necessary to research effective methods of time-series data imputation. Many studies on time-series data imputation can be divided into 5 parts, including statistical based, matrix-based, regression-based, deep learning (RNN and GAN) based methodologies. This study reviews and organizes these methodologies. Recently, deep learning-based imputation methods are developed and show excellent performance. However, it is associated to some computational problems that make it difficult to use in real-time system. Thus, the direction of future work is to develop low computational but high-performance imputation methods for application in the real field.

• 한국인터넷방송통신학회논문지
• /
• 제16권6호
• /
• pp.1-7
• /
• 2016

새로운 정보통신 기술의 발전과 더불어 보안 위협도 나날이 지능화 고도화되고 있다. 본 논문은 네트워크 장치나 사물인터넷 경량 장치에서 일련의 주기를 통해 연속적으로 입력되는 시계열 데이터를 통계적 기법을 활용하여 분석하고, 분석 정보를 기반으로 장치의 이상 유무나 비정상 징후를 탐지할 수 있는 시스템을 제안한다. 제안 시스템은 과거에 입력된 데이터를 기반으로 1차 비정상 탐지를 수행하고, 시간 속성이나 그룹의 속성을 기반으로 저장되어있는 시계열 데이터를 기반으로 신뢰구간을 설정하여 2차 비정상 탐지를 수행한다. 다단계 분석은 판정 데이터의 다양성을 통해 신뢰성을 향상시키고 오탐율을 줄일 수 있다.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제5권6호
• /
• pp.295-306
• /
• 2016

본 연구는 데이터품질과 관련된 선행연구의 메타정보를 활용하여 연구경향을 분석하고 이를 통해서 산업계의 흐름을 예측하기 위한 목적의 연구이다. 다양한 분야에서 연구경향을 분석하려는 시도는 이어져 왔으나, 데이터품질 영역은 그 범위가 방대하여 선행 연구자료에 대한 분석을 수행하기 어려웠다. 본 연구는 Web of Science 색인DB에 수록된 최근 10년간의 연구 메타데이터를 수집하여 텍스트 마이닝, 사회연결망 분석기법을 활용한 시계열 네트워크 분석을 수행하였다. 연구주제 분석 결과, 수학 및 전산 생물학, 화학, 건강관리 과학 및 서비스, 생화학 및 분자 생물학, 운영 연구 및 경영 과학, 의료정보학은 연구비율이 감소하고 있었고, 환경, 수자원, 지질학, 계측기 및 계측의 연구비율은 증가하고 있었다. 또한 사회연결망 분석 결과 데이터품질 연구에서는 분석, 알고리즘, 네트워크의 주제가 중앙성이 높은 중요한 주제로 나타났으며, 이미지와 모델, 센서, 최적화가 데이터품질에서 중요한 주제로 등장하는 추세를 보였다. 데이터품질의 산업과 연관관계 분석 결과는 기술, 산업, 건강, 유틸리티, 고객서비스가 연관성이 높은 산업으로 나타났다. 본 연구의 결과는 데이터품질 연구의 패턴을 분석하고 산업과 연관관계를 찾는 데이터품질 관련 연구자 뿐아니라 산업계에도 유용한 자료로 활용되리라 판단된다.

• 정보처리학회논문지:컴퓨터 및 통신 시스템
• /
• 제9권5호
• /
• pp.113-120
• /
• 2020

한국과학기술정보연구원은 대용량 데이터를 초고속으로 생산·처리·활용할 수 있는 국가슈퍼컴퓨팅시스템을 구축·운영하여 사용자(대학, 연구소, 정부 및 산하기관, 기업체 등)에게 HPC(High Performance Computing) 서비스를 제공하고 있다. 2019년 1월 1일 공식 서비스를 개시한 국가슈퍼컴퓨터 누리온은 한국과학기술정보연구원에서 5번째로 구축한 시스템으로 이론성능 25.7 페타플롭스를 갖는다. 시스템 운영자나 사용자의 관점에서 슈퍼컴퓨터의 사용 방법과 운영 방식을 이해하는 것은 매우 중요하다. 이를 이해하는 작업은 네트워크 트래픽을 모니터링하고 분석하는 것에서 시작된다. 본 논문에서는 누리온 시스템과 슈퍼컴퓨팅서비스 네트워크 및 보안 구성에 대하여 간략히 소개한다. 그리고 슈퍼컴퓨팅서비스 현황을 실시간으로 확인하기 위한 모니터링 체계를 기술하고 서비스를 시작하고 11개월(2019년 1월~11월) 동안 수집된 슈퍼컴퓨팅서비스 네트워크의 인바운드 및 아웃바운드 트래픽과 비정상행위(공격) 탐지 IP 개수에 대한 시계열 및 상관관계 분석을 수행한다.

• 한국시뮬레이션학회논문지
• /
• 제11권4호
• /
• pp.15-23
• /
• 2002

As recently the network environment and application services have been more complex and diverse, there has. In this paper we introduce a scheme the extract useful information for network management by analyzing traffic data in user login file. For this purpose we use classification and association rule based on episode concept in data mining. Since login data has inherently time series characterization, convertible data mining algorithms cannot directly applied. We generate virtual transaction, classify transactions above threshold value in time window, and simulate the classification algorithm.

• Journal of information and communication convergence engineering
• /
• 제9권4호
• /
• pp.369-374
• /
• 2011

Generally the neural network and the Fuzzy compensative algorithms are applied to forecast the time series for power demand with the characteristics of a nonlinear dynamic system, but, relatively, they have a few prediction errors. They also make long term forecasts difficult because of sensitivity to the initial conditions. In this paper, we evaluate the chaotic characteristic of electrical power demand with qualitative and quantitative analysis methods and perform a forecast simulation of electrical power demand in regular sequence, attractor reconstruction and a time series forecast for multi dimension using Lyapunov Exponent (L.E.) quantitatively. We compare simulated results with previous methods and verify that the present method is more practical and effective than the previous methods. We also obtain the hourly predictability of time series for power demand using the L.E. and evaluate its accuracy.

• Journal of Information Processing Systems
• /
• 제15권3호
• /
• pp.694-706
• /
• 2019

In this study, we applied the long short-term memory (LSTM) model to classify the cryptocurrency price time series. We collected historic cryptocurrency price time series data and preprocessed them in order to make them clean for use as train and target data. After such preprocessing, the price time series data were systematically encoded into the three-dimensional price tensor representing the past price changes of cryptocurrencies. We also presented our LSTM model structure as well as how to use such price tensor as input data of the LSTM model. In particular, a grid search-based k-fold cross-validation technique was applied to find the most suitable LSTM model parameters. Lastly, through the comparison of the f1-score values, our study showed that the LSTM model outperforms the gradient boosting model, a general machine learning model known to have relatively good prediction performance, for the time series classification of the cryptocurrency price trend. With the LSTM model, we got a performance improvement of about 7% compared to using the GB model.