Digital Library[ Search Result ]
Time Series Data Imbalance Resolution Techniques for Early Prediction
Eungseon An, Taehyoung Kwon, Doguk Kim
http://doi.org/10.5626/JOK.2025.52.7.593
Time series forecasting is a critical task that involves analyzing observed time series data to predict future values. However, when dealing with imbalanced data, model performance can degrade, leading to biased predictions. Although recent studies have explored various deep learning techniques and data augmentation methods, many fail to address challenges posed by data imbalance and the intrinsic characteristics of time series data simultaneously, leaving underlying issues unresolved. This study proposed a novel approach that could leverage temporal patterns to generate synthetic samples and extend the scope of early prediction. By identifying key moments that could effectively distinguish between positive and negative classes, our method enhanced the ability to predict further into the future. The method proposed in this study demonstrated superior performance to existing methods and proved the feasibility of early prediction for longer time lags.
Enhancing Clustering Quality on Mixed-Type Multivariate Time Series Data of HVAC Simulations through Feature Summarization
http://doi.org/10.5626/JOK.2025.52.5.424
Existing approaches for multivariate time series data clustering analysis often result in significant information loss, thereby reducing both clustering performance and interpretability. Moreover, most existing techniques primarily focus on numerical variables, making them less effective for real-world datasets that often include both numerical and categorical variables. To address these problems, this paper proposes a novel clustering technique for mixed-type multivariate time series data, enhancing interpretability by summarizing the data into representative features. The proposed technique is fundamentally different from existing methods in that it summarizes features to cluster mixed-type multivariate time series data. We evaluated the proposed method against existing techniques using three clustering evaluation metrics on two HVAC simulation datasets (MZVAV-1 and MZVAV-2-1). Experimental results showed that the proposed method outperformed existing techniques in clustering quality for over 61% of metric–cluster count combinations on MZVAV-1, and over 40% on MZVAV-2-1. These findings confirmed that the proposed technique could significantly improve clustering performance and interpretability for mixed-type time-series data.
A GRU-based Time-Series Forecasting Method using Patching
http://doi.org/10.5626/JOK.2024.51.7.663
Time series forecasting plays a crucial role in decision-making within various fields. Two recent approaches, namely, the patch time series Transformer (PatchTST) and the long-term time series foraging linear (LTSF-Linear) of the MLP structure have shown promising performance in this area. However, PatchTST requires significant time for both model training and inference, while LTSF-Linear has limited capacity due to its simplistic structure. To address these limitations, we propose a new approach called patch time series GRU (PatchTSG). By leveraging a Gated Recurrent Unit (GRU) on the patched data, PatchTSG reduces the training time and captures valuable information from the time series data. Compared to PatchTST, PatchTSG achieves an impressive reduction in learning time (up to 82%) and inference time (up to 46%).
Graph Structure Learning: Reflecting Types of Relationships between Sensors in Multivariate Time Series Anomaly Detection
http://doi.org/10.5626/JOK.2024.51.3.236
Sensors are used to monitor systems in various fields, such as water treatment systems and smart factories. Anomalies in the system can be detected by analyzing multivariate time series consisting of sensor data. To efficiently detect anomalies, information about the relationships between sensors is required, but this information is generally difficult to obtain. To solve this problem, the previous work used sensor data to identify relationships between sensors, which were then represented using a graph structure. However, in this process, the graph structure only reflects the presence of relationships between sensors, not the types of relationships between sensors. In this pap er, we considered the types of relationships between sensors in graph structure learning and analyzed multivariate time series to detect anomalies in the system. Experiments show that improving detection accuracy in graph structure learning for multivariate time series anomaly detection involves taking into account the different kinds of relationships among sensors.
A GCN-based Time-Series Data Anomaly Detection Method using Sensor-specific Time Lagged Cross Correlation
Kangwoo Lee, Yunyeong Kim, Sungwon Jung
http://doi.org/10.5626/JOK.2023.50.9.805
Anomaly detection of equipment through time series data is a very important because it can prevent further damage and contribute to productivity improvement. Although research studies on time series data anomaly detection are being actively conducted, but they have the following restrictions. First, unnecessary false alarms occur because correlations with other sensors are not considered. Second, although complete graph modeling and GAT have been applied to analyze the correlation of each sensor, this method requires a lot of time due to the increase in unnecessary operations. In this paper, we propose SC-GCNAD(Sensor-specific Correlation GCN Anomaly Detection) to address these problems. SC-GCNAD can analyze the exact correlation of each sensor by applying TLCC that reflects characteristics of time series data. It utilize GCN with excellent model expressiveness. As a result, SC-GCNAD can improve F1-Score by up to 6.37% and reduce analysis time by up to 95.31% compared to the baseline model.
CLS Token Additional Embedding Method Using GASF and CNN for Transformer based Time Series Data Classification Tasks
Jaejin Seo, Sangwon Lee, Wonik Choi
http://doi.org/10.5626/JOK.2023.50.7.573
Time series data refer to a sequentially determined data set collected for a certain period of time. They are used for prediction, classification, and outlier detection. Although existing artificial intelligence models in the field of time series are mainly based on the Recurrent Neural Network, recent research trends are changing to transformer based models. Although these transformer based models show good performance for time series data prediction problem, they show relatively insufficient performance for classification tasks. In this paper, we propose an embedding method to add special classification tokens generated using Gramian Angular Summation Field and Convolution Neural Network to utilize time series data as input to transformers and found that we could leverage the pre-trained method to improve performance. To show the efficacy of our method, we conducted extensive experiments with 12 different models using the University of California, Riverside dataset. Experimental results show that our proposed model improved the average accuracy of 85 datasets from 1.4% to up to 21.1%.
The Multivariate Sensor Data Classification using Time Series Imaging
http://doi.org/10.5626/JOK.2022.49.8.593
Various methods have been proposed in order to predict the future, from statistical-based time series analysis methods to deep learning-based prediction models, such as LSTM. However, the real industry data are highly complex due to various unpredictable factors. Therefore, it is difficult for the prediction models alone to extract valuable information from the data. Time series imaging is a method for converting time series into two-dimensional images, enabling the extraction of information that is difficult to interpret from raw data. In this paper, we transform the multivariate sensor data into two-dimensional multichannel images, and based on them, we propose a time series classification method. Furthermore, we compare the proposed method with the previous time series prediction methods to verify its usefulness.
Ensemble Model for Detecting Abnormal Symptoms of IT Infrastructure using Time Series Access Log Data
http://doi.org/10.5626/JOK.2021.48.9.1035
When operating large-scale IT services, multiple systems need to be managed for the detection of abnormalities. Since the monitoring and control personnel can hardly have all the domain knowledge required for these systems and services, there have been increasing needs for automated models that detect abnormalities by analyzing the characteristics of each service and learning patterns. In this experiment, we use the time-series data in the access log of the web server to examine the capability of the existing spectrum residual method model in detecting the anomalies in real-time, and propose an improved detection model which can respond more quickly to an abnormal situation. Our experiment showed that the proposed model was able to predict abnormal symptoms before actual failure occurs, and to respond in advance.
Denoising Multivariate Time Series Modeling for Multi-step Time Series Prediction
Jungsoo Hong, Jinuk Park, Jieun Lee, Kyeonghun Kim, Seung-Kyun Hong, Sanghyun Park
http://doi.org/10.5626/JOK.2021.48.8.892
The research field of time series forecasting predicts the future time point using seasonality in time series. In the industrial environment, since decision-making through continuous perspective prediction of the future is important, multi-step time series forecasting is necessary. However, multi-step prediction is highly unstable because of its dependency on predicted value of previous time prediction result. Therefore, the traditional time series forecasting makes a statistical prediction for the single time point. To address this limitation, we propose a novel encoder-decoder based neural network named ‘DTSNet’ which predicts multi-step time points for multivariate time series. To stabilize multi-step prediction, we exploit positional encoding to enhance representation for time point and propose a novel denoising training method. Moreover, we propose dual attention to resolve long-term dependencies and modeling complex patterns in time series, and we adopt multi-head strategy at linear projection layer for variable-specific modeling. To verify the performance improvement of our approach, we compare and analyze it with baseline models, and we demonstrate the proposed methods through comparison tests, such as, component ablation study and denoising degree experiment.
Visualization of Convolutional Neural Networks for Time Series Input Data
http://doi.org/10.5626/JOK.2020.47.5.445
Globally, the use of artificial intelligence (AI) applications has increased in a variety of industries from manufacturing, to health care to the financial sector. As a result, there is a growing interest in explainable artificial intelligence (XAI), which can provide explanations of what happens inside AI. Unlike previous work using image data, we visualize hidden nodes for a time series. To interpret which patterns of a node make more effective model decisions, we propose a method of arranging nodes in a hidden layer. The hidden nodes sorted by weight matrix values show which patterns significantly affected the classification. Visualizing hidden nodes explains a process inside the deep learning model, as well as enables the users to improve their understanding of time series data.
Search
Journal of KIISE
- ISSN : 2383-630X(Print)
- ISSN : 2383-6296(Electronic)
- KCI Accredited Journal
Editorial Office
- Tel. +82-2-588-9240
- Fax. +82-2-521-1352
- E-mail. chwoo@kiise.or.kr