Results 271 to 280 of about 655,816 (301)

Time series classification with their image representation

Neurocomputing
The study is concerned with the problem of classification of multivariate time series using convolutional neural networks (CNNs). As CNNs regard inputs in the form of images, an original image -like format of temporal data is proposed. Along this line, several design alternatives are studied by forming images with the two corresponding coordinates ...
Wladyslaw Homenda, Agnieszka Jastrzebska, Witold Pedrycz, Mariusz Wrzesien   +3 more
openaire   +2 more sources

Signal2Vec: Time Series Embedding Representation

2019
The rise of Internet-of-Things (IoT) and the exponential increase of devices using sensors, has lead to an increasing interest in data mining of time series. In this context, several representation methods have been proposed. Signal2vec is a novel framework, which can represent any time-series in a vector space.
Christoforos Nalmpantis, Dimitris Vrakas
openaire   +1 more source

Exploiting Representational Diversity for Time Series Classification

2012 11th International Conference on Machine Learning and Applications, 2012
More than a decade of research has produced numerous representations and similarity measures to support time series classification and clustering. Yet most of the work in the field is so focused on the representation or similarity measure that it ignores the possibility of improving performance using ensembles of representations or classifiers.
Tim Oates 0001, Colin F. Mackenzie, Deborah M. Stein, Lynn G. Stansbury, Joseph Dubose, Bizhan Aarabi, Peter Fu-Ming Hu   +6 more
openaire   +1 more source

Representation of Time Series

1987
Basically, one can describe time series either in the time domain or in the frequency domain. Difference equations are used in the former, and frequency spectra or transfer functions are used in the latter to specify the dynamic structure of time series. Both representations are used in this book.
openaire   +1 more source

Temporal representation learning for time series classification

Neural Computing and Applications, 2020
Recent years have witnessed the exponential growth of time series data as the popularity of sensing devices and development of IoT techniques; time series classification has been considered as one of the most challenging studies in time series data mining, attracting great interest over the last two decades.
Yupeng Hu 0003, Peng Zhan, Yang Xu 0025, Jia Zhao, Yujun Li, Xueqing Li   +5 more
openaire   +1 more source

Time Series Representation

1983
Economic data are inherently noisy. We regard them as (discrete-time) stochastic processes, using the first and second order moments to characterize them. By removing known mean values from data yt, the first moments can be taken to be zero. So we focus on the structure of second order moments.
openaire   +1 more source

State Representations From Finite Time Series

Proceedings of the 44th IEEE Conference on Decision and Control, 2006
We present two algorithms for construction of a state sequence of a linear time-invariant system from a finite exact trajectory of that system. The first algorithm uses the classical in subspace identification splitting of the data into "past" and "future" and computes a bases for the past-future intersection.
Ivan Markovsky, Jan C. Willems, Bart De Moor   +2 more
openaire   +1 more source

The Representation and Decomposition of Integrated Stationary Time Series

Advances in Applied Probability, 1994
Learning from Matheron's representation (1973), and using the increment vector (PIV) methodology introduced by Cressie (1988) and developed by Chen and Anderson (1994), this paper presents a theory for the representation and decomposition of integrated stationary time series and gives some applications.
Chen, Zhao-Guo, Anderson, Oliver D.
openaire   +2 more sources

Discrete Representation Learning for Multivariate Time Series

2024 32nd European Signal Processing Conference (EUSIPCO)
This paper focuses on discrete representation learning for multivariate time series with Gaussian processes. To overcome the challenges inherent in incorporating discrete latent variables into deep learning models, our approach uses a Gumbel-softmax reparameterization trick to address non-differentiability, enabling joint clustering and embedding ...
Marzieh Ajirak, Immanuel Elbau, Nili Solomonov, Logan Grosenick   +3 more
openaire   +3 more sources

Time Series Representation: A Random Shifting Perspective

2013
A long standing challenge for time series analysis is to develop representation techniques for dimension reduction while still preserving their fundamental features. As an effective representation technique, Symbolic Aggregate Approximation (SAX) has been widely used for dimension reduction in time series analysis.
Xue Bai, Yun Xiong, Yangyong Zhu, Hengshu Zhu   +3 more
openaire   +1 more source