34,742 Hits in 12.3 sec

A Bit Level Representation for Time Series Data Mining with Shape Based Similarity

Anthony Bagnall, Chotirat "Ann" Ratanamahatana, Eamonn Keogh, Stefano Lonardi, Gareth Janacek
2006 Data mining and knowledge discovery  
Clipping is the process of transforming a real valued series into a sequence of bits representing whether 10 each data is above or below the average.  ...  In this paper we argue that clipping is a useful and flexible transformation 11 for the exploratory analysis of large time dependent data sets.  ...  For any two time series Q and C of length n, LB clipped(Q, c) ≤ 173 D E (Q, C). 174 Proof: 175 BIT LEVEL REPRESENTATION FOR TIME SERIES DATA MINING and (2), LB clipped(x, y) = 0 by definition  ... 
doi:10.1007/s10618-005-0028-0 fatcat:gkksdvkiqreqbh72prrq4mr3ju

On K-Means Cluster Preservation Using Quantization Schemes

Deepak S. Turaga, Michail Vlachos, Olivier Verscheure
2009 2009 Ninth IEEE International Conference on Data Mining  
Merits of the proposed compression technique include: a) reduced storage requirements with clustering guarantees, b) data privacy on the original values, and c) shape preservation for data visualization  ...  Our analytical derivation indicate that a 1-bit moment preserving quantizer per cluster is sufficient to retain the original data clusters.  ...  [9] present a piecewise vector quantized approximation for time-series data, which preserves with high accuracy the shape of the original sequences.  ... 
doi:10.1109/icdm.2009.12 dblp:conf/icdm/TuragaVV09 fatcat:oc7wvryh6rczrfpfxfsczscuei

Time-series clustering – A decade review

Saeed Aghabozorgi, Ali Seyed Shirkhorshidi, Teh Ying Wah
2015 Information Systems  
time-series approaches during the last decade and enlighten new paths for future works. .my, (A.  ...  Information Systems 53 (2015) 16-38 Applications of time-series clustering Clustering of time-series data is mostly utilized for discovery of interesting patterns in time-series datasets [27, 28] .  ...  The authors in [206] also propose a new multi-level approach for shape based time-series clustering.  ... 
doi:10.1016/ fatcat:pygcqxztjng5ppoifpnee5evja

T3: On Mapping Text To Time Series

Tao Yang, Dongwon Lee
2009 Alberto Mendelzon Workshop on Foundations of Data Management  
We investigate if the mapping between text and time series data is feasible such that relevant data mining problems in text can find their counterparts in time series (and vice versa).  ...  As a preliminary work, we present the T 3 (T ext T o T ime series) framework that utilizes different combinations of granularity (e.g., character or word level) and n-grams (e.g., unigram or bigram).  ...  We can easily see that the time series of the first two records preserve similar shapes in real-value domain (with some shifting) while the time series of the third record has a rather different shape.  ... 
dblp:conf/amw/YangL09 fatcat:nkfaclkf2jgqxjwip46ffudbu4

Time-series data mining

Philippe Esling, Carlos Agon
2012 ACM Computing Surveys  
In this paper we intend to provide a survey of the techniques applied for time series data mining.  ...  The purpose of time series data mining is to try to extract all meaningful knowledge from the shape of data.  ...  Jean Claude Lejosne, Professor of English for Special Purposes (ESP) for having improved the English wording of the manuscript.  ... 
doi:10.1145/2379776.2379788 fatcat:prjlpze5arefrkrnkrpsx3inke

Experiencing SAX: a novel symbolic representation of time series

Jessica Lin, Eamonn Keogh, Li Wei, Stefano Lonardi
2007 Data mining and knowledge discovery  
Many high level representations of time series have been proposed for data mining, including Fourier transforms, wavelets, eigenwaves, piecewise polynomial models, etc.  ...  First, the dimensionality of the symbolic representation is the same as the original data, and virtually all data mining algorithms scale poorly with dimensionality.  ...  Introduction Many high level representations of time series have been proposed for data mining.  ... 
doi:10.1007/s10618-007-0064-z fatcat:xhz3bths7benjmwn3cojgcyufa

Discovery of Meaningful Rules by using DTW based on Cubic Spline Interpolation

Luis Alexander Calvo-Valverde, David Elías Alfaro-Barboza
2020 Tecnología en Marcha  
Short-term predictions based on "the shape" of meaningful rules lead to a vast number of applications.  ...  In this work, we do believe that Dynamic Time Warping based on Cubic Spline Interpolation (SIDTW), can be useful to carry out the similarity computation for two specific algorithms: 1- DiscoverRules()  ...  with time series with different lengths; a fundamental data preparation activity, required before applying any similarity computation.  ... 
doi:10.18845/tm.v33i2.4073 fatcat:yvfcdys3ercy7exigjp4ugl7ma

Visually mining and monitoring massive time series

Jessica Lin, Eamonn Keogh, Stefano Lonardi, Jeffrey P. Lankford, Donna M. Nystrom
2004 Proceedings of the 2004 ACM SIGKDD international conference on Knowledge discovery and data mining - KDD '04  
Our visualization approach works by transforming the time series into a symbolic representation, and encoding the data in a modified suffix tree in which the frequency and other properties of patterns  ...  We will introduce VizTree, a novel time-series visualization tool to aid the Aerospace analysts who must make these engineering assessments.  ...  Intuitively, time series data with similar structures can be expected to have similar subsequence trees, and in turn, a sparse diff-tree.  ... 
doi:10.1145/1014052.1014104 dblp:conf/kdd/LinKLLN04 fatcat:wnyuysshsjb6bdmodhuuzlpblq

Data Mining Techniques using Time Series Research

2019 International journal of recent technology and engineering  
The similarity measure plays a primary role in time series data mining, which improves the accuracy of data mining task.  ...  Time series data mining is used to mine all useful knowledge from the profile of data. Obviously, we have a potential to perform these works, but it leads to a vague crisis.  ...  In other words, data preparation, searching for similar time series, clustering and even forecasting within or beyond the segments are fundamental steps in time series data mining processes.  ... 
doi:10.35940/ijrte.b1020.0982s1119 fatcat:6l4l7o2j5fdd5l3zbngjou7yfu

1d-SAX: A Novel Symbolic Representation for Time Series [chapter]

Simon Malinowski, Thomas Guyet, René Quiniou, Romain Tavenard
2013 Lecture Notes in Computer Science  
We compare the efficiency of SAX and 1d-SAX in terms of i) goodness-of-fit and ii) retrieval performance for querying a time series database with an asymmetric scheme.  ...  SAX (Symbolic Aggregate approXimation) is one of the main symbolization technique for time series. A well-known limitation of SAX is that trends are not taken into account in the symbolization.  ...  Introduction Time series data mining (TSDM) has recently attracted the attention of researchers in data mining due to the increase availability of data with temporal dependency.  ... 
doi:10.1007/978-3-642-41398-8_24 fatcat:ivjg5g5dtjaxhi7tu6oqfi5im4

Discovering the Intrinsic Cardinality and Dimensionality of Time Series Using MDL

Bing Hu, Thanawin Rakthanmanon, Yuan Hao, Scott Evans, Stefano Lonardi, Eamonn Keogh
2011 2011 IEEE 11th International Conference on Data Mining  
Choosing the best representation and abstraction level for a given task/dataset is arguably the most critical step in time series data mining.  ...  Most algorithms for mining or indexing time series data do not operate directly on the original data, but instead they consider alternative representations that include transforms, quantization, approximation  ...  INTRODUCTION Most algorithms for indexing or mining time series data operate on higher-level representations of the data, which include transforms, quantization, approximations and multiresolution approaches  ... 
doi:10.1109/icdm.2011.54 dblp:conf/icdm/HuRHELK11 fatcat:njbuibjnybdi3lm3e43mjlyxfe

Visualizing and Discovering Non-Trivial Patterns in Large Time Series Databases

Jessica Lin, Eamonn Keogh, Stefano Lonardi
2005 Information Visualization  
Data visualization techniques are very important for data analysis, since the human eye has been frequently advocated as the ultimate data-mining tool.  ...  VizTree works by transforming the time series into a symbolic representation, and encoding the data in a modified suffix tree in which the frequency and other properties of patterns are mapped onto colors  ...  Acknowledgments Thanks to Victor Zordan and Bhrigu Celly for providing the yoga postures data.  ... 
doi:10.1057/palgrave.ivs.9500089 fatcat:kmqlsnlm4fcyhlalhe6shahekq


John Paparrizos, Michael J. Franklin
2019 Proceedings of the VLDB Endowment  
The effectiveness and the scalability of time-series mining techniques critically depend on design choices for three components responsible for (i) representing; (ii) comparing; and (iii) indexing time  ...  GRAIL shows promise as a new primitive for highly accurate, yet scalable, time-series analysis.  ...  We also thank Christos Faloutsos and Eamonn Keogh for useful discussions and Luis Gravano and Daniel Hsu for invaluable feedback.  ... 
doi:10.14778/3342263.3342648 fatcat:m7gtrlakgzb4peibo2wvtszvq4

Multimedia Data Mining Using P-Trees [chapter]

William Perrizo, William Jockheck, Amal Perera, Dongmei Ren, Weihua Wu, Yi Zhang
2003 Lecture Notes in Computer Science  
MA data presents a one-time, gene expression level map of thousands of genes subjected to hundreds of conditions.  ...  The P-tree data structure is designed for just such a data mining setting.  ...  Video-Audio data mining and other multimedia data mining often involves a preliminary feature extraction step in which the pertinent data is formed into a relation of tuples or possibly time series of  ... 
doi:10.1007/978-3-540-39666-6_7 fatcat:upgcv2i2ang25ekzkjufkzzq4a

Elastic Product Quantization for Time Series [article]

Pieter Robberechts, Wannes Meert, Jesse Davis
2022 arXiv   pre-print
In this paper, we propose the use of product quantization for efficient similarity-based comparison of time series under time warping.  ...  Therefore, techniques have been proposed to generate compact similarity-preserving representations of time series, enabling real-time similarity search on large in-memory data collections.  ...  Data mining applications Similarity comparisons between pairs of series are a core subroutine in most time series data mining approaches.  ... 
arXiv:2201.01856v2 fatcat:cbykmmx3nbdtxiz5q5qc56vbve
« Previous Showing results 1 — 15 out of 34,742 results