• The Korean Journal of Applied Statistics
• /
• v.32 no.5
• /
• pp.671-681
• /
• 2019

Studies on predicting arrhythmia using machine learning have been actively conducted with increasing number of arrhythmia patients. Existing studies have predicted arrhythmia based on multivariate data of feature variables extracted from RR interval data at a specific time point. In this study, we consider that the pattern of the heart state changes with time can be important information for the arrhythmia prediction. Therefore, we investigate the usefulness of predicting the arrhythmia with multivariate time series data obtained by extracting and accumulating the multivariate vectors of the feature variables at various time points. When considering 1-nearest neighbor classification method and its ensemble for comparison, it is confirmed that the multivariate time series data based method can have better classification performance than the multivariate data based method if we select an appropriate time series distance function.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.10a
• /
• pp.950-951
• /
• 2019

시계열 데이터에 대한 군집화 관련 연구는 주로 통계 분석을 통해 이뤄지기 때문에 데이터가 갖는 특성을 완전히 반영하는 데 한계를 갖는다. 본 논문에서는 다변량 데이터에서의 군집화를 위하여 변수별로 시간에 따른 변화와 특징을 추출하기 위한 CNN-GRU(Convolutional Neural Network - Gated Recurrent Unit) 기반의 신경망 모델을 제안한다. CNN을 활용하여 변수별로 갖는 특성을 파악하고자 하였으며, GRU을 통해 전체 시간에 따른 소비 추세를 도출하고자 하였다. 지역별로 업종에 따라 사용된 2년 치의 실제 카드 데이터를 활용하였으며, 유사한 소비 추세를 보이는 지역을 군집화하는데 이를 적용하였다. 결과적으로, 다변량 시계열 데이터를 통해 전체적인 흐름을 반영하여 패턴화했다는 점에서 의의를 갖는다.

• Journal of Convergence for Information Technology
• /
• v.12 no.1
• /
• pp.31-38
• /
• 2022

This paper applies an expert independent unsupervised neural network learning-based multivariate time series data analysis model, MSCRED(Multi-Scale Convolutional Recurrent Encoder-Decoder), and to overcome the limitation, because the MCRED is based on Auto-encoder model, that train data must not to be contaminated, by using learning data sampling technique, called Subset Sampling Validation. By using the vibration data of power plant equipment that has been labeled, the classification performance of MSCRED is evaluated with the Anomaly Score in many cases, 1) the abnormal data is mixed with the training data 2) when the abnormal data is removed from the training data in case 1. Through this, this paper presents an expert-independent anomaly diagnosis framework that is strong against error data, and presents a concise and accurate solution in various fields of multivariate time series data.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.33 no.1
• /
• pp.1-12
• /
• 2023

It is very time-intensive to obtain data with labels on anomaly detection tasks for multivariate time series. Therefore, several studies have been conducted on unsupervised learning that does not require any labels. However, a well-done integrative survey has not been conducted on in-depth discussion of learning architecture and property for multivariate time series anomaly detection. This study aims to explore the characteristic of well-known architectures in anomaly detection of multivariate time series. Additionally, architecture was categorized by using top-down and bottom-up approaches. In order toconsider real-world anomaly detection situation, we trained models with dataset such as power grids or Cyber Physical Systems that contains realistic anomalies. From experimental results, we compared and analyzed the comprehensive performance of each architecture. Quantitative performance were measured using precision, recall, and F1 scores.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.539-540
• /
• 2022

본 논문에서는 정확한 장기 시계열 예측을 위해 시계열 데이터의 다양한 스케일 (시간 규모)에서 표현을 학습하는 트랜스포머 모델을 제안한다. 제안하는 모델은 시계열의 다중 스케일 특징을 추출하고, 이를 트랜스포머에 반영하여 예측 시계열을 생성하는 구조로 되어 있다. 스케일 정규화 과정을 통해 시계열의 전역적 및 지역적인 시간 정보를 효율적으로 융합하여 종속성을 학습한다. 3 가지의 다변량 시계열 데이터를 이용한 실험을 통해 제안하는 방법의 우수성을 보인다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.210-212
• /
• 2022

In the manufacturing industry, various sensors are attached to monitor the status of production facility. In many cases, the data obtained through these sensors is time series data. In order to determine whether the status of the production facility is abnormal, the process of extracting patterns from time series data must be preceded. Also various methods for extracting patterns from time series data are studied. In this paper, we use matrix profile algorithm to extract patterns from the collected multivariate time series data. Through this, the pattern of multi sensor data currently being collected from the CNC machine is extracted.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.2
• /
• pp.81-86
• /
• 2022

Given that time series are used in various fields, such as finance, IoT, and manufacturing, data analytical methods for accurate time-series forecasting can serve to increase operational efficiency. Among time-series analysis methods, multi-horizon forecasting provides a better understanding of data because it can extract meaningful statistics and other characteristics of the entire time-series. Furthermore, time-series data with exogenous information can be accurately predicted by using multi-horizon forecasting methods. However, traditional deep learning-based models for time-series do not account for the heterogeneity of inputs. We proposed an improved time-series predicting method, called the temporal fusion transformer method, which combines multi-horizon forecasting with interpretable insights into temporal dynamics. Various real-world data such as stock prices, fine dust concentrates and electricity consumption were considered in experiments. Experimental results showed that our temporal fusion transformer method has better time-series forecasting performance than existing models.

• Journal of the Korean Data and Information Science Society
• /
• v.25 no.4
• /
• pp.807-817
• /
• 2014

This paper considers multivariate time series modelling of PM10 data in Korea collected from 2008 to 2011. We consider both temporal and spatial dependencies of PM10 by applying the sparse vector autoregressive (sVAR) modelling proposed by Davis et al. (2013). It utilizes the partial spectral coherence to measure cross correlation between different regions, in turn provides the sparsity in the model while balancing the parsimony of model and the goodness of fit. It is also shown that sVAR performs better than usual vector autoregressive model (VAR) in forecasting.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.11
• /
• pp.13-20
• /
• 2023

In this paper, we propose a water temperature prediction method using feature extraction and reconstructed data based on LSTM-Autoencoder. We used multivariate time series data such as sea surface water temperature in the Naksan area of the East Sea where the cold water zone phenomenon occurred, and wind direction and wind speed that affect water temperature. Using the LSTM-Autoencoder model, we used three types of data: feature data extracted through dimensionality reduction of the original data combined with multivariate data of the original data, reconstructed data, and original data. The three types of data were trained by the LSTM model to predict sea surface water temperature and evaluated the accuracy. As a result, the sea surface water temperature prediction accuracy using feature extraction of LSTM-Autoencoder confirmed the best performance with MAE 0.3652, RMSE 0.5604, MAPE 3.309%. The result of this study are expected to be able to prevent damage from natural disasters by improving the prediction accuracy of sea surface temperature changes rapidly such as the cold water zone.

• Journal of the Korean Data and Information Science Society
• /
• v.22 no.6
• /
• pp.1123-1135
• /
• 2011

This paper considers the multivariate integrated process control procedure for detecting special causes in a multivariate IMA(1, 1) process. When the multivariate control chart signals, the special cause will be detected and eliminated from the process. However, when the elimination of the special cause costs high or is not practically possible, an alternative action is to readjust the process with approximately modified adjustment scheme. In this paper, we propose the readjustment procedure after having a true signal, and show that the use of the readjustment can reduce the deviation of a process from the target.