Filters








200,187 Hits in 6.1 sec

DISTANCES OF TIME SERIES COMPONENTS BY MEANS OF SYMBOLIC DYNAMICS

KARSTEN KELLER, KATHARINA WITTFELD
2004 International Journal of Bifurcation and Chaos in Applied Sciences and Engineering  
On the base of symbolic dynamics, the time series is turned into a series of matrices whose rows quantify pattern types in the components of the original series.  ...  In this note we describe a simple method for visualizing time-dependent similarities and dissimilarities between the components of a high-dimensional time series.  ...  I would like to thank Heinz Lauffer from the Department of Pediatric Medicine of the University Greifswald for many fruitful discussions and for providing the EEG data.  ... 
doi:10.1142/s0218127404009387 fatcat:43nnem3irvhanjruwnozqt7tqe

A new time series similarity measurement method based on the morphological pattern and symbolic aggregate approximation

Jiancheng Yin, Rixin Wang, Huailiang Zheng, Yuantao Yang, Yuqing Li, Minqiang Xu
2019 IEEE Access  
Finally, the similarity of the time series is obtained by weighted aggregation of the similarity of trend component and detail component.  ...  Then, the similarity of the trend component under morphological pattern coding and that of the detail component under symbolic aggregate approximation coding are respectively calculated by the longest  ...  The similarity measurement of time series was first proposed by Agrawal et al. [2] , in which the similarity of time series was measured by Euclidean distance.  ... 
doi:10.1109/access.2019.2934109 fatcat:4cerm5ngs5gxbgzel4ejqdhpmy

Anomaly Detection in Aircraft Gas Turbine Engines

Devendra Kumar Tolani, Murat Yasar, Asok Ray, Vigor Yang
2006 Journal of Aerospace Computing Information and Communication  
loss of dynamical information in the time series data.  ...  From a sampled time series data under the nominal condition, the mean µ and the central moment θ α are calculated as: µ = 1 N N k=1 x k and θ α = N k=1 |x k − µ| α (2) The distance between any vector x  ... 
doi:10.2514/1.15768 fatcat:eglsyc7645az7iju2yofaglxmu

An application of minimal spanning trees and hierarchical trees to the study of Latin American exchange rates

Erick Limas
2019 Journal of Dynamics & Games  
Symbolic Time Series Analysis consists in the transformation of a given time series into a symbolic sequence with the aim of identifying patterns in the set of data.  ...  The paper combines two methods, Symbolic Time Series Analysis (STSA) and a clustering method based on the Minimal Spanning Tree (MST), from which we obtain a Hierarchical Tree (HT).  ...  Comments by two anonymous referees helped improve the paper considerably.  ... 
doi:10.3934/jdg.2019010 fatcat:5jbgd2sqcjdxtkkzgxawcbunzy

An Evaluation of Classification Methods for 3D Printing Time-Series Data [article]

Vivek Mahato, Muhannad Ahmed Obeidi, Dermot Brabazon, Padraig Cunningham
2020 arXiv   pre-print
The results we present suggests that Dynamic Time Warping is an effective distance measure compared with alternatives for 3D printing data of this type.  ...  In line with other Machine Learning research on time-series classification we use k-Nearest Neighbour classifiers.  ...  ACKNOWLEDGEMENTS This publication has resulted from research supported in part by a grant from Science Foundation Ireland (SFI) under Grant Number 16/RC/3872 and is co-funded under the European Regional  ... 
arXiv:2010.00903v1 fatcat:xzovs2o2jbbwpncihebqcas3wi

Symbolic analysis of slow solar wind data using rank order statistics

Vinita Suyal, Awadhesh Prasad, Harinder P. Singh
2012 Planetary and Space Science  
We selected a total of 18 datasets measured by the Helios spacecraft at a distance of 0.32 AU from the sun in the inner heliosphere.  ...  We analyze time series data of the fluctuations of slow solar wind velocity using rank order statistics.  ...  If the two time series are similar (from same dynamical system) Figure 4 : 4 Distances D L for different combinations of time series obtained from nonlinear dynamical systems (a) for time series of length  ... 
doi:10.1016/j.pss.2011.12.007 fatcat:sp4uziwo6zb3xgwf6fzcbsz3zi

Analyzing multimodal time series as dynamical systems

Shohei Hidaka, Chen Yu
2010 International Conference on Multimodal Interfaces and the Workshop on Machine Learning for Multimodal Interaction on - ICMI-MLMI '10  
In light this, our approach is based on the concept of generating partition which is the theoretically best symbolization of time series maximizing the information of the underlying original continuous  ...  over a symbol set for each data point in a time series.  ...  This research is supported by NSF BCS 0924248, AFOSR FA9550-09-1-0665 and The Ogasawara Foundation for the Promotion of Science and Emgineering.  ... 
doi:10.1145/1891903.1891968 dblp:conf/icmi/HidakaY10 fatcat:5df37633f5h6zgzn527jezbhjm

Multi-dimensional sparse time series: feature extraction [article]

Marco Franciosi, Giulia Menconi
2008 arXiv   pre-print
The leading component and the trend of the series with respect to a mobile window analysis result from the entropy analysis and label the dynamical evolution of the series.  ...  We show an analysis of multi-dimensional time series via entropy and statistical linguistic techniques.  ...  These techniques can be applied to some time series X = (x 1 x 2 . . . x t ) by considering a translation into a finite symbol sequence, usually given by means of a uniform partition of its range (see  ... 
arXiv:0803.0405v1 fatcat:652wpn6ntjgidjiyf2ywaruviy

Detecting event-related recurrences by symbolic analysis: applications to human language processing

P. beim Graben, A. Hutt
2014 Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences  
In this study we elaborate a recent approach for detecting quasistationary states as recurrence domains by means of recurrence analysis and subsequent symbolisation methods.  ...  In order to detect them from time series, several segmentation techniques have been proposed.  ...  In this study we reanalysed a language processing EEG data set by courtesy of Stefan  ... 
doi:10.1098/rsta.2014.0089 pmid:25548270 pmcid:PMC4281863 fatcat:paimwdha6nghnewqsndx5mjpem

Entropy and Gaussianity - Measures of Deterministic Dynamics of Heart Rate and Blood Pressure Signals of Rats

T. Loncar-Turukalo, S. Milosavljevic, O. Sarenac, N. Japundzic-Zigon, D. Bajic
2007 2007 5th International Symposium on Intelligent Systems and Informatics  
This paper investigates the measure of entropy of HR and BP time series as a consequence of the involvement of the autonomic nervous system, assessed in conscious telemetred rats under blockade of β-adrenergic  ...  The analysis include traditional statistical analytical tools and a number of methods based on nonlinear system theory, recently developed to give better insight into complex HR and BP time series.  ...  Acknowledgement This paper was supported in part by Fundamental research grant no. 145062, Ministry of Science, Serbia.  ... 
doi:10.1109/sisy.2007.4342617 fatcat:d2quaglpgrds7ja5ifakroxizq

A Method for Comparing Multivariate Time Series with Different Dimensions

Avraam Tapinos, Pedro Mendes, Rafael Josef Najmanovich
2013 PLoS ONE  
While there are widely used methods for comparing univariate time series, most dynamical systems are characterized by multivariate time series.  ...  Yet, comparison of multivariate time series has been limited to cases where they share a common dimensionality.  ...  Kell and Kieran Smallbone for comments on the manuscript and for early discussions on the topic of time series data mining. Author Contributions Conceived and designed the experiments: AT PM.  ... 
doi:10.1371/journal.pone.0054201 pmid:23393554 pmcid:PMC3564859 fatcat:xforkc35gjddfm6vizdaxku7mm

Fault diagnosis and isolation in aircraft gas turbine engines

Soumik Sarkar, Kushal Mukherjee, Asok Ray, Murat Yasar
2008 2008 American Control Conference  
The fault diagnosis and isolation (F DI) algorithm is based upon Symbolic Dynamic Filtering (SDF ) that has been recently reported in literature and relies on the principles of Symbolic Dynamics, Statistical  ...  In addition to abrupt large faults, the proposed method is capable of detecting and isolating slowly evolving anomalies (i.e., deviations from the nominal behavior), based on analysis of time series data  ...  OVERVIEW OF SYMBOLIC DYNAMIC FILTERING The theory of symbolic dynamic filtering (SDF ) for time series data analysis is built upon the underlying principles of Nonlinear Dynamics [10] , Symbolic Dynamics  ... 
doi:10.1109/acc.2008.4586813 dblp:conf/amcc/SarkarMRY08 fatcat:u2zbko7ovrcfrbcht5vlmct5tm

Discovery of Time-Series Motif from Multi-Dimensional Data Based on MDL Principle

Yoshiki Tanaka, Kazuhisa Iwamoto, Kuniaki Uehara
2005 Machine Learning  
In addition, the algorithm can extract motifs from multi-dimensional time-series data by using Principal Component Analysis (PCA).  ...  Motifs are useful for various time-series data mining tasks.  ...  Therefore, we must introduce DTW (Dynamic Time Warping) (Myers & Rabiner, 1981) distance function rather than Euclidean distance function.  ... 
doi:10.1007/s10994-005-5829-2 fatcat:kueiyan3r5fbfivfpntxq4k7hi

Irregularities and nonlinearities in fetal heart period time series in the course of pregnancy

D. Cysarz, P. Van Leeuwen, H. Bettermann
2000 Herzschrittmachertherapie & Elektrophysiologie  
The aim of this study was to examine fetal heart period irregularity by focussing on nonlinear dynamical components.  ...  Reducing information by constructing time series using binary symbolization which ignores the absolute beat durations resulted in a loss of dependency on gestational age but a retention of nonlinearity  ...  Then, incremental comparison is done by increasing the number of vector components by one and comparing the distances of previously neighbored vectors.  ... 
doi:10.1007/s003990070037 fatcat:kq7r2afsyrfipgqkby2chwsnjy

Feature Extraction for Gait Identification by Using Trajectory Attractors

Takuma Akiduki, Zhong Zhang, Hirotaka Takahashi
2019 ICIC Express Letters  
In our approach, the time series of the periodical signals are expressed by dynamical systems having attractors, which symbolize the time series in state space.  ...  In this study, we address a time-series analysis method for human motion analysis based on the symbolization of sensor data.  ...  This work was supported in part by JSPS KAKENHI a Grant-in-Aid No. 16K06156 (T. Akiduki) and No. 17K05437 (H. Takahashi).  ... 
doi:10.24507/icicel.13.06.529 fatcat:iuszi5d3yrclpidss2nwkoeoke
« Previous Showing results 1 — 15 out of 200,187 results