scholarly journals SIMIT: Subjectively Interesting Motifs in Time Series

Entropy ◽  
2019 ◽  
Vol 21 (6) ◽  
pp. 566 ◽  
Author(s):  
Junning Deng ◽  
Jefrey Lijffijt ◽  
Bo Kang ◽  
Tijl De Bie
Keyword(s):  
Time Series ◽  
Time Series Data ◽  
Synthetic Data ◽  
Series Data ◽  
Theoretic Approach ◽  
Information Theoretic ◽  
Novel Approach ◽  
Approximate Form ◽  
Real World Datasets ◽  
Information Theoretic Approach

Numerical time series data are pervasive, originating from sources as diverse as wearable devices, medical equipment, to sensors in industrial plants. In many cases, time series contain interesting information in terms of subsequences that recur in approximate form, so-called motifs. Major open challenges in this area include how one can formalize the interestingness of such motifs and how the most interesting ones can be found. We introduce a novel approach that tackles these issues. We formalize the notion of such subsequence patterns in an intuitive manner and present an information-theoretic approach for quantifying their interestingness with respect to any prior expectation a user may have about the time series. The resulting interestingness measure is thus a subjective measure, enabling a user to find motifs that are truly interesting to them. Although finding the best motif appears computationally intractable, we develop relaxations and a branch-and-bound approach implemented in a constraint programming solver. As shown in experiments on synthetic data and two real-world datasets, this enables us to mine interesting patterns in small or mid-sized time series.

scholarly journals An Information Theoretic Approach for Creating 3D Spatial Images from 4D Time Series Data

2017 ◽  
Vol 23 (S1) ◽  
pp. 100-101
Author(s):  
Willy Wriggers ◽  
Julio Kovacs ◽  
Federica Castellani ◽  
P. Thomas Vernier ◽  
Dean J. Krusienski
Keyword(s):  
Time Series ◽  
Time Series Data ◽  
Series Data ◽  
Theoretic Approach ◽  
Information Theoretic ◽  
Information Theoretic Approach

scholarly journals Uncertainty quantification of the effects of biotic interactions on community dynamics from nonlinear time-series data

2018 ◽  
Vol 15 (147) ◽  
pp. 20180695 ◽  
Author(s):  
Simone Cenci ◽  
Serguei Saavedra
Keyword(s):  
Time Series ◽  
Community Dynamics ◽  
Time Series Data ◽  
Multivariate Time Series ◽  
Model Averaging ◽  
Biotic Interactions ◽  
Series Data ◽  
Time Intervals ◽  
Novel Approach ◽  
Data Generating Process

Biotic interactions are expected to play a major role in shaping the dynamics of ecological systems. Yet, quantifying the effects of biotic interactions has been challenging due to a lack of appropriate methods to extract accurate measurements of interaction parameters from experimental data. One of the main limitations of existing methods is that the parameters inferred from noisy, sparsely sampled, nonlinear data are seldom uniquely identifiable. That is, many different parameters can be compatible with the same dataset and can generalize to independent data equally well. Hence, it is difficult to justify conclusive assertions about the effect of biotic interactions without information about their associated uncertainty. Here, we develop an ensemble method based on model averaging to quantify the uncertainty associated with the effect of biotic interactions on community dynamics from non-equilibrium ecological time-series data. Our method is able to detect the most informative time intervals for each biotic interaction within a multivariate time series and can be easily adapted to different regression schemes. Overall, this novel approach can be used to associate a time-dependent uncertainty with the effect of biotic interactions. Moreover, because we quantify uncertainty with minimal assumptions about the data-generating process, our approach can be applied to any data for which interactions among variables strongly affect the overall dynamics of the system.

scholarly journals Information Guided Exploration of Scalar Values and Isocontours in Ensemble Datasets

Entropy ◽  
2018 ◽  
Vol 20 (7) ◽  
pp. 540 ◽  
Author(s):  
Subhashis Hazarika ◽  
Ayan Biswas ◽  
Soumya Dutta ◽  
Han-Wei Shen
Keyword(s):  
Weather Forecasting ◽  
Conditional Entropy ◽  
Specific Information ◽  
Theoretic Approach ◽  
Information Theoretic ◽  
Information Measures ◽  
New Information ◽  
Real World Datasets ◽  
The Individual ◽  
Information Theoretic Approach

Uncertainty of scalar values in an ensemble dataset is often represented by the collection of their corresponding isocontours. Various techniques such as contour-boxplot, contour variability plot, glyphs and probabilistic marching-cubes have been proposed to analyze and visualize ensemble isocontours. All these techniques assume that a scalar value of interest is already known to the user. Not much work has been done in guiding users to select the scalar values for such uncertainty analysis. Moreover, analyzing and visualizing a large collection of ensemble isocontours for a selected scalar value has its own challenges. Interpreting the visualizations of such large collections of isocontours is also a difficult task. In this work, we propose a new information-theoretic approach towards addressing these issues. Using specific information measures that estimate the predictability and surprise of specific scalar values, we evaluate the overall uncertainty associated with all the scalar values in an ensemble system. This helps the scientist to understand the effects of uncertainty on different data features. To understand in finer details the contribution of individual members towards the uncertainty of the ensemble isocontours of a selected scalar value, we propose a conditional entropy based algorithm to quantify the individual contributions. This can help simplify analysis and visualization for systems with more members by identifying the members contributing the most towards overall uncertainty. We demonstrate the efficacy of our method by applying it on real-world datasets from material sciences, weather forecasting and ocean simulation experiments.

scholarly journals Minimum Message Length in Hybrid ARMA and LSTM Model Forecasting

Entropy ◽  
2021 ◽  
Vol 23 (12) ◽  
pp. 1601
Author(s):  
Zheng Fang ◽  
David L. Dowe ◽  
Shelton Peiris ◽  
Dedi Rosadi
Keyword(s):  
Time Series ◽  
Environmental Science ◽  
Short Term Memory ◽  
Arima Model ◽  
Theoretic Approach ◽  
Arma Models ◽  
Information Theoretic ◽  
Minimum Message Length ◽  
Message Length ◽  
Real World Datasets

Modeling and analysis of time series are important in applications including economics, engineering, environmental science and social science. Selecting the best time series model with accurate parameters in forecasting is a challenging objective for scientists and academic researchers. Hybrid models combining neural networks and traditional Autoregressive Moving Average (ARMA) models are being used to improve the accuracy of modeling and forecasting time series. Most of the existing time series models are selected by information-theoretic approaches, such as AIC, BIC, and HQ. This paper revisits a model selection technique based on Minimum Message Length (MML) and investigates its use in hybrid time series analysis. MML is a Bayesian information-theoretic approach and has been used in selecting the best ARMA model. We utilize the long short-term memory (LSTM) approach to construct a hybrid ARMA-LSTM model and show that MML performs better than AIC, BIC, and HQ in selecting the model—both in the traditional ARMA models (without LSTM) and with hybrid ARMA-LSTM models. These results held on simulated data and both real-world datasets that we considered. We also develop a simple MML ARIMA model.

scholarly journals MITRE: predicting host status from microbiota time-series data

2018 ◽  
Author(s):  
Elijah Bogart ◽  
Richard Creswell ◽  
Georg K. Gerber
Keyword(s):  
Machine Learning ◽  
Time Series ◽  
Time Series Data ◽  
Synthetic Data ◽  
Black Box ◽  
Series Data ◽  
Learning Approaches ◽  
Rule Engine ◽  
Microbiome Composition ◽  
Host Status

AbstractLongitudinal studies are crucial for discovering casual relationships between the microbiome and human disease. We present Microbiome Interpretable Temporal Rule Engine (MITRE), the first machine learning method specifically designed for predicting host status from microbiome time-series data. Our method maintains interpretability by learning predictive rules over automatically inferred time-periods and phylogenetically related microbes. We validate MITRE’s performance on semi-synthetic data, and five real datasets measuring microbiome composition over time in infant and adult cohorts. Our results demonstrate that MITRE performs on par or outperforms “black box” machine learning approaches, providing a powerful new tool enabling discovery of biologically interpretable relationships between microbiome and human host.

scholarly journals TimeTrial: An Interactive Application for Optimizing the Design and Analysis of Transcriptomic Time-Series Data in Circadian Biology Research

2020 ◽  
Vol 35 (5) ◽  
pp. 439-451 ◽  
Author(s):  
Elan Ness-Cohn ◽  
Marta Iwanaszko ◽  
William L. Kath ◽  
Ravi Allada ◽  
Rosemary Braun
Keyword(s):  
Time Series ◽  
Experimental Design ◽  
Time Series Data ◽  
Synthetic Data ◽  
Optimal Choice ◽  
Series Data ◽  
Detection Accuracy ◽  
Periodic Patterns ◽  
Detection Algorithms ◽  
The Impact

The circadian rhythm drives the oscillatory expression of thousands of genes across all tissues, coordinating physiological processes. The effect of this rhythm on health has generated increasing interest in discovering genes under circadian control by searching for periodic patterns in transcriptomic time-series experiments. While algorithms for detecting cycling transcripts have advanced, there remains little guidance quantifying the effect of experimental design and analysis choices on cycling detection accuracy. We present TimeTrial, a user-friendly benchmarking framework using both real and synthetic data to investigate cycle detection algorithms’ performance and improve circadian experimental design. Results show that the optimal choice of analysis method depends on the sampling scheme, noise level, and shape of the waveform of interest and provides guidance on the impact of sampling frequency and duration on cycling detection accuracy. The TimeTrial software is freely available for download and may also be accessed through a web interface. By supplying a tool to vary and optimize experimental design considerations, TimeTrial will enhance circadian transcriptomics studies.

Sign in / Sign up

Export Citation Format

Share Document