An Optimal Wavelet Detailed-Coefficient Determination Using Time-Series Clustering

Time-series clustering is used to find out similar patterns which occur in a time-series data. Time-series sequences are characterized by many features. The trend and seasonality, for instance, are the two important features which reveal the behavior of a time-series sequence and can be used to group them. One of the common dimensionality reduction method for time-series data is the usage of wavelets. In this paper, we analyze the importance of wavelet-based time-series clustering which helps to reduce the length of time-series dimensions, in-turn reducing the time needed for the clustering task. Determining an optimal set of coefficients for wavelets is always challenging. While it plays an important role in reducing the time taken for clustering, to test/verify our claims, we analyze a renewable energy dataset which contains the periodical energy load of various generators located in Europe. The clustering of this time-series data helps to identify similar electrical nodes. We compared eight different clustering algorithms with and without using wavelet decomposition on the renewable energy data. Minibatch k-means and Brich clustering show better performance on using wavelet-based decomposition.

[1]  Liang Zhao,et al.  Time series clustering via community detection in networks , 2015, Inf. Sci..

[2]  Saeed Aghabozorgi,et al.  A Review of Subsequence Time Series Clustering , 2014, TheScientificWorldJournal.

[3]  A. Khosravi,et al.  Time-series prediction of wind speed using machine learning algorithms: A case study Osorio wind farm, Brazil , 2018 .

[4]  Qin Zhang,et al.  Time series feature learning with labeled and unlabeled data , 2019, Pattern Recognit..

[5]  Dirk Müller,et al.  A time series clustering approach for Building Automation and Control Systems , 2019 .

[6]  Yaqiong Yao,et al.  Time-series momentum in nearly 100 years of stock returns , 2018, Journal of Banking & Finance.

[7]  Witold Pedrycz,et al.  Time-series clustering based on linear fuzzy information granules , 2018, Appl. Soft Comput..

[8]  Hans-Peter Deutsch.  Time Series Modeling , 2004 .

[9]  Shanlin Yang,et al.  A shape-based clustering method for pattern recognition of residential electricity consumption , 2019, Journal of Cleaner Production.

[10]  Russel Pears,et al.  A wavelet approach for precursor pattern detection in time series , 2018, Journal of Electrical Systems and Information Technology.

[11]  Xiaozhe Wang,et al.  Characteristic-Based Clustering for Time Series Data , 2006, Data Mining and Knowledge Discovery.

[12]  Omid Motlagh,et al.  Clustering of residential electricity customers using load time series , 2019, Applied Energy.

[13]  Elizabeth Ann Maharaj,et al.  Time-Series Clustering , 2015 .

[14]  Ramesh S. V. Teegavarapu,et al.  Methods for Analysis of Trends and Changes in Hydroclimatological Time-Series , 2019, Trends and Changes in Hydroclimatic Variables.

[15]  Fábio Porto,et al.  Nonstationary time series transformation methods: An experimental review , 2019, Knowl. Based Syst..

[16]  Keyi Zhang,et al.  Application of wavelet decomposition in time-series forecasting , 2017 .

[17]  Gökay Bayrak.  Wavelet transform-based fault detection method for hydrogen energy-based distributed generators , 2018 .

[18]  Pedro Antonio Gutiérrez,et al.  Time-Series Clustering Based on the Characterization of Segment Typologies , 2018, IEEE Transactions on Cybernetics.

[19]  Yao Zhao,et al.  Landsat time series clustering under modified Dynamic Time Warping , 2016, 2016 4th International Workshop on Earth Observation and Remote Sensing Applications (EORSA).

[20]  Marco Aiello,et al.  Automating Vector Autoregression on Electronic Patient Diary Data , 2016, IEEE Journal of Biomedical and Health Informatics.

[21]  Shijun Liu,et al.  A fast shapelet selection algorithm for time series classification , 2019, Comput. Networks.

[22]  Ruizhe Ma,et al.  Distance and Density Clustering for Time Series Data , 2017, 2017 IEEE International Conference on Data Mining Workshops (ICDMW).