A new time-series clustering method using slope-based similarity and PSO.
problem Clustering time-series data efficiently and accurately.
method Developed a novel slope-based similarity measure combined with Particle Swarm Optimization (PSO) for clustering.
result The proposed similarity measure outperforms existing measures in clustering time-series data.
NeuralWarp aligns time-series indices using deep learning for improved similarity.
problem Need for elastic time-series similarity measures.
method Proposes NeuralWarp, a deep learning model for aligning time-series indices.
result NeuralWarp outperforms non-parametric and un-warped deep models.
Paper develops multivariate time series similarity and distance measures.
problem Compensating for misalignments in multivariate time series data.
method Adapted Independent and Dependent DTW strategies to seven elastic similarity and distance measures.
result Each measure achieves highest accuracy on at least one dataset, supporting their value.
This paper improves forecasts for diverse time series by averaging similar ones.
problem Forecasting challenges in heterogeneous time series.
method Dynamic Time Warping to find similar time series, k-Nearest Neighbor averaging.
result Averaging improves forecasts of simple models.
With the advent of Big Data, nowadays in many applications databases containing large quantities of similar time series are available. Forecasting time series in these domains with traditional univariate forecasting procedures leaves great potentials for producing accurate forecasts untapped. Recurrent neural networks …
A new tool, matrix profile, finds all pair similarities in time series data.
problem Finding all pair similarities in time series data.
method Near universal time series data mining tool called matrix profile.
result Matrix profile solves the all-pairs-similarity-search problem for time series subsequences.
Wavelet scattering spectra model non-Gaussian time-series, proving scale invariance for self-similar processes.
problem Modeling non-Gaussian time-series with stationary increments.
method Complex wavelet transform for scale variations, joint correlation matrix for scale dependencies, second wavelet transform for diagonalization, maximum entropy models conditioned by scattering spectra coefficients.
result Scattering spectra of self-similar processes are scale invariant, allowing statistical testing and generation of new time-series.
Time series are ubiquitous, and a measure to assess their similarity is a core part of many computational systems. In particular, the similarity measure is the most essential ingredient of time series clustering and classification systems. Because of this importance, countless approaches to estimate time series similar…
Two possible definitions of fixed points in the self-similar analysis of time series are considered. One definition is based on the minimal-difference condition and another, on a simple averaging. From studying stock market time series, one may conclude that these two definitions are practically equivalent. A forecast …
A new stable similarity measure for time series using persistent homology.
problem Constructing a robust measure of time series similarity.
method Persistent homology for stability, bi-conditional periodicity score for similarity.
result Stability of the bi-conditional periodicity score under perturbations and dimension reduction.
Study finds Bitcoin crypto currency rate correlates with social network activity.
problem Detecting correlation between crypto currency rate and social network activity.
method Comparative correlation and fractal analysis of time series data.
result Time series of Bitcoin rate and social network activities exhibit self-similar and multifractal properties.
Model predicts competition between similar products in sales.
problem Predicting cannibalization between similar products in sales.
method Developed a neural network model that computes a 'competitiveness' function based on product features.
result The model outperforms traditional methods in predicting market share.
I propose a frequency domain adaptation of the Expectation Maximization (EM) algorithm to group a family of time series in classes of similar dynamic structure. It does this by viewing the magnitude of the discrete Fourier transform (DFT) of each signal (or power spectrum) as a probability density/mass function (pdf/pm…
An approach is suggested for analyzing time series by means of resummation techniques of theoretical physics. A particular form of such an analysis, based on the algebraic self-similar renormalization, is developed and illustrated by several examples from the stock market time series.
Archive of 20 time series datasets for forecasting evaluation.
problem Lack of comprehensive time series forecasting datasets.
method Compilation and characterisation of 20 datasets from various domains.
result Characterisation and performance evaluation of datasets.
Develops a kernel for financial time series analysis.
problem Measuring similarity between evolving financial networks.
method Commute time matrix, dynamic time warping, Shannon entropy.
result Proposes a kernel for financial time series analysis.
Similarity-based approaches represent a promising direction for time series analysis. However, many such methods rely on parameter tuning, and some have shortcomings if the time series are multivariate (MTS), due to dependencies between attributes, or the time series contain missing data. In this paper, we address thes…
kdiff measures distances for time series and structured data.
problem Estimating distances between time series and structured data.
method kdiff uses non-linear kernel distances based on matching overlapping distributions.
result kdiff is more robust to noise and partial occlusions.
We tackle the problem of classifying Electrocardiography (ECG) signals with the aim of predicting the onset of Paroxysmal Atrial Fibrillation (PAF). Atrial fibrillation is the most common type of arrhythmia, but in many cases PAF episodes are asymptomatic. Therefore, in order to help diagnosing PAF, it is important to …
Proposes a robust similarity measure for sparse time series data.
problem Sparse time course data in biological settings.
method Gaussian processes (GP) similarity measure based on log-likelihood ratio.
result Enhanced robustness to noise compared to Euclidean distance.
A framework for forecasting high-dimensional time-series data using clustering.
problem Forecasting high-dimensional time-series data with intra-cluster similarity.
method Three-stage framework: univariate time series parameter estimation, clustering, multivariate time series parameter computation.
result Framework achieves state-of-the-art results on benchmark datasets, sometimes outperforming deep-learning-based approaches.
Adversarial regularization helps learn interpretable shapelets for time series classification.
problem Difficult to interpret learned shapelets in time series classification.
method Use of adversarial regularization to constrain model to learn more interpretable shapelets.
result Adversarially regularized method learns interpretable shapelets.
This paper describes a time-series-based classification approach to identify similarities between bio-medical-based situations. The proposed approach allows classifying collections of time-series representing bio-medical measurements, i.e., situations, regardless of the type, the length and the quantity of the time-ser…
SPINEX improves time series forecasting with explainable neighbors.
problem Enhancing time series forecasting accuracy and interpretability.
method Leverages similarity and higher-order temporal interactions across multiple scales.
result SPINEX consistently ranks among top performers in forecasting precision.
The paper uses pattern similarity-based methods for mid-term electricity demand forecasting.
problem Forecasting monthly electricity demand with seasonal patterns.
method Pattern similarity-based machine learning models (nearest neighbor, fuzzy neighborhood, kernel regression, GRNN).
result The proposed models outperform classical and state-of-the-art models in accuracy and simplicity.
We find prominent similarities in the features of the time series for the (model earthquakes or) overlap of two Cantor sets when one set moves with uniform relative velocity over the other and time series of stock prices. An anticipation method for some of the crashes have been proposed here, based on these observation…
We find prominent similarities in the features of the time series for the overlap of two Cantor sets when one set moves with uniform relative velocity over the other and time series of stock prices. An anticipation method for some of the crashes have been proposed here, based on these observations.
There are many studies dealing with the analysis of similarity among currencies in foreign exchange market by using network analysis approach. In those studies, each currency is represented by a univariate time series of exchange rate return. This is the standard practice to analyze the underlying information in the fo…
Extends shapelet transform to irregular time series, improving interpretability and efficiency.
problem Limitations of shapelet transform for irregular, partially observed time series.
method Continuous-time formulation, regularisation penalty, learned pseudometric.
result Efficient training without sacrificing interpretability for irregular, partially observed time series.
A novel time series clustering method that considers segment typologies.
problem Lack of consideration for the similarity of different subsequences in time series clustering.
method Two-stage clustering: polynomial segmentation followed by hierarchical clustering of segments, then final clustering of time series.
result The method outperforms state-of-the-art techniques on UCR Time Series Classification Archive datasets.
Dynamic Time Warping improves regression accuracy on spectroscopy data.
problem Improving regression accuracy on spectroscopy data with DTW when data is across multiple wavelengths.
method Illustrated DTW's effectiveness on spectroscopy time-series data, showing its benefits in improving regression accuracy when only a single wavelength is considered. DTW combined with k-Nearest Neighbour reveals similarities and differences at the time-series level.
result DTW improves regression accuracy on spectroscopy data, especially when considering a single wavelength.
Adaptive transfer learning improves time series classification.
problem Improving generalization in time series classification.
method Proposed a general adaptive transfer learning framework for multi-view time series data.
result Framework maintains desirable generalization ability.
In this paper, we propose a technique for time series clustering using community detection in complex networks. Firstly, we present a method to transform a set of time series into a network using different distance functions, where each time series is represented by a vertex and the most similar ones are connected. The…
Investigations have been performed into using clustering methods in data mining time-series data from smart meters. The problem is to identify patterns and trends in energy usage profiles of commercial and industrial customers over 24-hour periods, and group similar profiles. We tested our method on energy usage data p…
A novel approach to analyzing time series generated by complex systems, such as markets, is presented. The basic idea of the approach is the {\it Law of Self-Similar Evolution}, according to which any complex system develops self-similarly. There always exist some internal laws governing the evolution of a system, say …
Study forecasts monthly electricity demand using pattern similarity-based methods.
problem Forecasting monthly electricity demand accurately.
method Pattern similarity-based forecasting methods (PSFMs) including k-NN, fuzzy, kernel regression, and GRNN.
result Ensemble models outperform individual PSFMs in forecasting accuracy.
Deep learning clusters patient time-series data for better prognosis.
problem Clustering time-series data for patient phenotyping and prognosis.
method Deep predictive clustering with novel loss functions for future outcome distribution.
result Model achieves superior clustering performance and identifies meaningful patient subgroups.
Coherent Multiplex analyzes real-time wavelet coherence among multiple signals.
problem Identifying and visualizing coherence among multiple time series.
method Fast spectral similarity based on cosine similarity metrics of Fourier-transformed signals and sparse time-frequency wavelet coherence.
result Scalable real-time system for low-latency inference and monitoring of inter-signal relationships.
An algorithm based on Renormalization Group (RG) to analyze time series forecasting was proposed in cond-mat/0110285. In this paper we explicitly code and test it. We choose in particular some financial time series (stocks, indexes and commodities) with daily data and compute one step ahead forecasts. We then construct…
WF distance measures time series similarity via spectral density displacement.
problem Measuring similarity between time series.
method Wasserstein-Fourier distance between normalised power spectral densities.
result WF establishes as a general-purpose metric for time series.
Paper introduces MJ distances for better anomaly detection in time series.
problem Anomaly detection in large collections of time series.
method Introduces semi-metric MJ distances for measuring structural breaks.
result MJ distances outperform existing metrics in detecting similarity and anomalies.
This study aimed to find temporal clusters for several commodity prices using the threshold non-linear autoregressive model. It is expected that the process of determining the commodity groups that are time-dependent will advance the current knowledge about the dynamics of co-moving and coherent prices, and can serve a…
New algorithms select and rank features from MTS without feature extraction.
problem Feature extraction step for MTS classification.
method Directly computes similarity between time series and assesses cluster structure matching labels.
result Techniques match labels well without feature extraction.
Develops a deep learning approach for statistical arbitrage.
problem Temporal price differences between similar assets.
method Constructs arbitrage portfolios using latent asset pricing factors and a convolutional transformer for time series signals.
result High risk-adjusted returns and Sharpe ratios with optimal trading policy.
This study improves cryptocurrency price forecasting using time series categorization and deep learning.
problem Accurate prediction of cryptocurrency prices is challenging due to limited data and diverse behaviors.
method The approach involves categorizing financial time series, creating deep learning models for each category, and combining data from other cryptocurrencies to increase training data.
result The method increases prediction accuracy by learning each subseries category with similar behavior and combining data from other cryptocurrencies.
Brain Electroencephalography (EEG) classification is widely applied to analyze cerebral diseases in recent years. Unfortunately, invalid/noisy EEGs degrade the diagnosis performance and most previously developed methods ignore the necessity of EEG selection for classification. To this end, this paper proposes a novel m…
Paper proposes LATC for multivariate time series prediction and missing data imputation.
problem Large-scale, incomplete, and corrupted multivariate time series data.
method Transforms multivariate time series into a tensor structure, models global and local trends, and uses autoregressive norm.
result Integration of global and local trends improves missing data imputation and rolling prediction.
Optimizes ESN hyperparameters for time series datasets using Bayesian optimization.
problem Determining optimal ESN hyperparameters for efficient model training.
method Bayesian optimization to find hyperparameters that generalize across similar time series.
result Reduces the number of ESN models needed for a dataset while maintaining good performance.