• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.7
• /
• pp.3112-3127
• /
• 2018

Since time series clustering is performed without prior information, it is used for exploratory data analysis. In particular, clusters of time series with similar shapes can be used in various fields, such as business, medicine, finance, and communications. However, existing time series clustering algorithms have a problem in that time series with different shapes are included in the clusters. The reason for such a problem is that the existing algorithms do not consider the limitations on the size of the generated clusters, and use a dimension reduction method in which the information loss is large. In this paper, we propose a method to alleviate the disadvantages of existing methods and to find a better quality of cluster containing similarly shaped time series. In the data preprocessing step, we normalize the time series using z-transformation. Then, we use piecewise aggregate approximation (PAA) to reduce the dimension of the time series. In the clustering step, we use density-based spatial clustering of applications with noise (DBSCAN) to create a precluster. We then use a modified K-means algorithm to refine the preclusters containing differently shaped time series into subclusters containing only similarly shaped time series. In our experiments, our method showed better results than the existing method.

• Communications for Statistical Applications and Methods
• /
• v.27 no.6
• /
• pp.589-602
• /
• 2020

The development of smart grids has enabled the easy collection of a large amount of power data. There are some common patterns that make it useful to cluster power consumption patterns when analyzing s power big data. In this paper, clustering analysis is based on distance functions for time series and clustering algorithms to discover patterns for power consumption data. In clustering, we use 10 distance measures to find the clusters that consider the characteristics of time series data. A simulation study is done to compare the distance measures for clustering. Cluster validity measures are also calculated and compared such as error rate, similarity index, Dunn index and silhouette values. Real power consumption data are used for clustering, with five distance measures whose performances are better than others in the simulation.

• Journal of Industrial Technology
• /
• v.29 no.B
• /
• pp.17-23
• /
• 2009

In many cases, clustering algorithms have been used for extracting and discovering useful information from non-linear data. They have made a great effect on performances of the systems dealing with non-linear data. Thus, this paper presents a new approach called hierarchically structured clustering algorithm, and it is applied to the prediction system for non-linear time series data. The proposed hierarchically structured clustering algorithm (called HCKA: Hierarchical Cross-correlation and K-means clustering Algorithms) in which the cross-correlation and k-means clustering algorithm are combined can accept the correlationship of non-linear time series as well as statistical characteristics. First, the optimal differences of data are generated, which can suitably reveal the characteristics of non-linear time series. Second, the generated differences are classified into the upper clusters for their predictors by the cross-correlation clustering algorithm, and then each classified differences are classified again into the lower fuzzy sets by the k-means clustering algorithm. As a result, the proposed method can give an efficient classification and improve the performance. Finally, we demonstrates the effectiveness of the proposed HCKA via typical time series examples.

• The Korean Journal of Applied Statistics
• /
• v.29 no.1
• /
• pp.193-203
• /
• 2016

This paper forecasts electricity demand as a critical element of a demand management system in Smart Grid environment. We present a prediction method of using a combination of predictive values by time series clustering. Periodogram-based normalized clustering, predictive analysis clustering and dynamic time warping (DTW) clustering are proposed for time series clustering methods. Double Seasonal Holt-Winters (DSHW), Trigonometric, Box-Cox transform, ARMA errors, Trend and Seasonal components (TBATS), Fractional ARIMA (FARIMA) are used for demand forecasting based on clustering. Results show that the time series clustering method provides a better performances than the method using total amount of electricity demand in terms of the Mean Absolute Percentage Error (MAPE).

• The Korean Journal of Applied Statistics
• /
• v.31 no.6
• /
• pp.707-719
• /
• 2018

Various time series representation methods have been proposed for efficient time series clustering and classification. Lin et al. (DMKD, 15, 107-144, 2007) proposed a symbolic aggregate approximation (SAX) method based on symbolic representations after approximating the original time series using piecewise local mean. The performance of SAX therefore depends heavily on how well the piecewise local averages approximate original time series features. SAX equally divides the entire series into an arbitrary number of segments; however, it is not sufficient to capture key features from complex, large-scale time series data. Therefore, this paper considers data-adaptive local constant approximation of the time series using the unbalanced Haar wavelet transformation. The proposed method is shown to outperforms SAX in many real-world data applications.

• Smart Media Journal
• /
• v.10 no.3
• /
• pp.23-30
• /
• 2021

Although the manufacturing time series data clustering technique is an important grouping solution in the field of detecting and improving manufacturing large data-based equipment and process defects, it has a disadvantage of low accuracy when applying the existing static data target clustering technique to time series data. In this paper, an evolutionary computation-based time series cluster analysis approach is presented to improve the coherence of existing clustering techniques. To this end, first, the image shape resulting from the manufacturing process is converted into one-dimensional time series data using linear scanning, and the optimal sub-clusters for hierarchical cluster analysis and split cluster analysis are derived based on the Pearson distance metric as the target of the transformation data. Finally, by using a genetic algorithm, an optimal cluster combination with minimal similarity is derived for the two cluster analysis results. And the performance superiority of the proposed clustering is verified by comparing the performance with the existing clustering technique for the actual manufacturing process image.

• International Journal of Contents
• /
• v.10 no.1
• /
• pp.47-53
• /
• 2014

The paper considers the challenges involved in measuring the similarities between time series, such as time shifts and the mixture of frequencies. To improve recognition accuracy, we investigate an improved linear dynamical system for discovering prominent features by exploiting the evolving dynamics and correlations in a time series, as the quality of unsupervised pattern recognition relies strongly on the extracted features. The proposed approach yields a set of compact extracted features that boosts the accuracy and reliability of clustering for time series data. Experimental evaluations are carried out on time series applications from the scientific, socio-economic, and business domains. The results show that our method exhibits improved clustering performance compared to conventional methods. In addition, the computation time of the proposed approach increases linearly with the length of the time series.

• The Korean Journal of Applied Statistics
• /
• v.22 no.6
• /
• pp.1203-1214
• /
• 2009

In this paper we introduce the time series clustering methods in the time and frequency domains and discuss the merits or demerits of each method. We analyze 15 daily stock prices of KOSPI 200, and the nonparametric method using the wavelet shows the best clustering results. For the clustering of nonstationary time series using the spectral density, the EMD method remove the trend more effectively than the differencing.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.46 no.4
• /
• pp.63-73
• /
• 2023

This study explores modern portfolio theory by integrating the Black-Litterman portfolio with time-series clustering, specificially emphasizing K-shape clustering methodology. K-shape clustering enables grouping time-series data effectively, enhancing the ability to plan and manage investments in stock markets when combined with the Black-Litterman portfolio. Based on the patterns of stock markets, the objective is to understand the relationship between past market data and planning future investment strategies through backtesting. Additionally, by examining diverse learning and investment periods, it is identified optimal strategies to boost portfolio returns while efficiently managing associated risks. For comparative analysis, traditional Markowitz portfolio is also assessed in conjunction with clustering techniques utilizing K-Means and K-Means with Dynamic Time Warping. It is suggested that the combination of K-shape and the Black-Litterman model significantly enhances portfolio optimization in the stock market, providing valuable insights for making stable portfolio investment decisions. The achieved sharpe ratio of 0.722 indicates a significantly higher performance when compared to other benchmarks, underlining the effectiveness of the K-shape and Black-Litterman integration in portfolio optimization.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.10 no.6
• /
• pp.145-152
• /
• 2010

Bayesian information criterion is used to do clustering for time series data. To acquire more stable clusters, multiple seeds are chosen first for the algorithm. Once clusters being set up, most similar time series data in the cluster to the one under consideration are to be chosen for prediction test. These chosen time series data are used to extract valid Markov rules by which we test the prediction accuracy. We confirmed that clustering with multiple seeds led to better prediction performance.