scholarly journals Let's Do the Time Warp Again: Non-linear time series matching as a tool for sequentially structured data in ecology

2021 ◽  
Author(s):  
Jens C Hegg ◽  
Brian P Kennedy
Keyword(s):  
Time Series ◽  
Time Series Data ◽  
Linear Time ◽  
Temporal Structure ◽  
Structured Data ◽  
Series Data ◽  
Small Scale ◽  
Temporal Data ◽  
Ecological Data ◽  
Aggregation Techniques

Ecological patterns are often fundamentally chronological. However, generalization of data is necessarily accompanied by a loss of detail or resolution. Temporal data in particular contains information not only in data values but in the temporal structure, which is lost when these values are aggregated to provide point estimates. Dynamic Time Warping (DTW) is a time series comparison method that is capable of efficiently comparing series despite temporal offsets that confound other methods. The DTW method is both efficient and remarkably flexible, capable of efficiently matching not only time series but any sequentially structured dataset, which has made it a popular technique in machine learning, artificial intelligence, and big data analytical tasks. DTW is rarely used in ecology despite the ubiquity of temporally structured data. As technological advances have increased the richness of small-scale ecological data, DTW may be an attractive analysis technique because it is able to utilize the additional information contained in the temporal structure of many ecological datasets. In this study we use an example dataset of high-resolution fish movement records obtained from otolith microchemistry to compare traditional analysis techniques with DTW clustering. Our results suggest that DTW is capable of detecting subtle behavioral patterns within otolith datasets which traditional data aggregation techniques cannot. These results provide evidence that the DTW method may be useful across many of the temporal data types commonly collected in ecology, as well other sequentially ordered "pseudo time series" data such as classification of species by shape.

Validation of synthetic daily Landsat NDVI time series data generated by the improved spatial and temporal data fusion approach

2018 ◽  
Vol 40 ◽  
pp. 34-44 ◽  
Author(s):  
Mingquan Wu ◽  
Wenjiang Huang ◽  
Zheng Niu ◽  
Changyao Wang ◽  
Wang Li ◽  
...  
Keyword(s):  
Time Series ◽  
Data Fusion ◽  
Time Series Data ◽  
Series Data ◽  
Temporal Data ◽  
Ndvi Time Series ◽  
Fusion Approach

scholarly journals Time-series analysis of the risk factors for haemorrhagic fever with renal syndrome: comparison of statistical models

2006 ◽  
Vol 135 (2) ◽  
pp. 245-252 ◽  
Author(s):  
W. HU ◽  
K. MENGERSEN ◽  
P. BI ◽  
S. TONG
Keyword(s):  
Time Series ◽  
Water Level ◽  
Crop Production ◽  
Time Series Data ◽  
Linear Time ◽  
Additive Model ◽  
Series Data ◽  
Haemorrhagic Fever ◽  
Independent Variables ◽  
China Model

Three conventional regression models were compared using the time-series data of the occurrence of haemorrhagic fever with renal syndrome (HFRS) and several key climatic and occupational variables collected in low-lying land, Anhui Province, China. Model I was a linear time series with normally distributed residuals; model II was a generalized linear model with Poisson-distributed residuals and a log link; and model III was a generalized additive model with the same distributional features as model II. Model I was fitted using least squares whereas models II and III were fitted using maximum likelihood. The results show that the correlations between the HFRS incidence and the independent variables measured (i.e. difference in water level, autumn crop production and density of Apodemus agrarius) ranged from −0·40 to 0·89. The HFRS incidence was positively associated with density of A. agrarius and crop production, but was inversely associated with difference in water level. The residual analyses and the examination of the accuracy of the models indicate that model III may be the most suitable in the assessment of the relationship between the incidence of HFRS and the independent variables.

scholarly journals Deep learning classification of temporal data in ecology

2020 ◽  
Author(s):  
César Capinha ◽  
Ana Ceia-Hasse ◽  
Andrew M. Kramer ◽  
Christiaan Meijer
Keyword(s):  
Time Series ◽  
Deep Learning ◽  
Time Series Data ◽  
Meteorological Data ◽  
Species Distribution Modelling ◽  
Series Data ◽  
Temporal Data ◽  
Climate Time Series ◽  
Biological Entities

AbstractTemporal data is ubiquitous in ecology and ecologists often face the challenge of accurately differentiating these data into predefined classes, such as biological entities or ecological states. The usual approach transforms the temporal data into static predictors of the classes. However, recent deep learning techniques can perform the classification using raw time series, eliminating subjective and resource-consuming data transformation steps, and potentially improving classification results. We present a general approach for time series classification that considers multiple deep learning algorithms and illustrate it with three case studies: i) insect species identification from wingbeat spectrograms; ii) species distribution modelling from climate time series and iii) the classification of phenological phases from continuous meteorological data. The deep learning approach delivered ecologically sensible and accurate classifications, proving its potential for wide applicability across subfields of ecology. We recommend deep learning as an alternative to techniques requiring the transformation of time series data.

Short-Term Time Series Prediction for a Logistics Outsourcing Company

2013 ◽  
pp. 150-160
Author(s):  
Angeliki Papana
Keyword(s):  
Time Series ◽  
Time Series Data ◽  
Linear Time ◽  
Time Series Prediction ◽  
Service Level ◽  
Optimal Choice ◽  
Series Data ◽  
Short Term ◽  
Univariate Time Series ◽  
Nonlinear Components

In this chapter, tools from univariate time series analysis and forecasting are presented and applied. Time series components, such as trend and seasonality are introduced and discussed, while time series methods are analyzed based on the type of the time series components. In the literature, linear methods are the most commonly used. However, real time series data often include nonlinear components, so linear time series forecasting may not be the optimal choice. Therefore, also a basic nonlinear forecasting method is presented. The necessity of these methods to logistics service providers and 3PL companies is presented by case studies that present how the operational and management costs can be cut down in order to ensure a service level. Short term forecasts are useful in all the units of activation of 3PL companies, i.e. supplies, production, distribution, storage, transportation, and service of customers.

scholarly journals Linear time-varying models can reveal non-linear interactions of biomolecular regulatory networks using multiple time-series data

2008 ◽  
Vol 24 (10) ◽  
pp. 1286-1292 ◽  
Author(s):  
Jongrae Kim ◽  
Declan G. Bates ◽  
Ian Postlethwaite ◽  
Pat Heslop-Harrison ◽  
Kwang-Hyun Cho
Keyword(s):  
Time Series ◽  
Regulatory Networks ◽  
Time Series Data ◽  
Linear Time ◽  
Series Data ◽  
Multiple Time ◽  
Time Varying ◽  
Multiple Time Series ◽  
Linear Interactions ◽  
Time Varying Models

scholarly journals A Cycle Deep Belief Network Model for Multivariate Time Series Classification

2017 ◽  
Vol 2017 ◽  
pp. 1-7 ◽  
Author(s):  
Shuqin Wang ◽  
Gang Hua ◽  
Guosheng Hao ◽  
Chunli Xie
Keyword(s):  
Time Series ◽  
Network Model ◽  
Time Series Data ◽  
Multivariate Time Series ◽  
Deep Belief Network ◽  
Learning Ability ◽  
Series Data ◽  
Temporal Data ◽  
Belief Network ◽  
Data Objects

Multivariate time series (MTS) data is an important class of temporal data objects and it can be easily obtained. However, the MTS classification is a very difficult process because of the complexity of the data type. In this paper, we proposed a Cycle Deep Belief Network model to classify MTS and compared its performance with DBN and KNN. This model utilizes the presentation learning ability of DBN and the correlation between the time series data. The experimental results showed that this model outperforms other four algorithms: DBN, KNN_ED, KNN_DTW, and RNN.

scholarly journals Multivariate analysis of nonlinearity in sandbar behavior

2008 ◽  
Vol 15 (1) ◽  
pp. 145-158 ◽  
Author(s):  
L. Pape ◽  
B. G. Ruessink
Keyword(s):  
Time Series ◽  
Time Series Data ◽  
Nonlinear Models ◽  
Multivariate Time Series ◽  
Series Data ◽  
Small Scale ◽  
Synthetic Datasets ◽  
Long Term Prediction ◽  
Sandbar Migration

Abstract. Alongshore sandbars are often present in the nearshore zones of storm-dominated micro- to mesotidal coasts. Sandbar migration is the result of a large number of small-scale physical processes that are generated by the incoming waves and the interaction between the wave-generated processes and the morphology. The presence of nonlinearity in a sandbar system is an important factor determining its predictability. However, not all nonlinearities in the underlying system are equally expressed in the time-series of sandbar observations. Detecting the presence of nonlinearity in sandbar data is complicated by the dependence of sandbar migration on the external wave forcings. Here, a method for detecting nonlinearity in multivariate time-series data is introduced that can reveal the nonlinear nature of the dependencies between system state and forcing variables. First, this method is applied to four synthetic datasets to demonstrate its ability to qualify nonlinearity for all possible combinations of linear and nonlinear relations between two variables. Next, the method is applied to three sandbar datasets consisting of daily-observed cross-shore sandbar positions and hydrodynamic forcings, spanning between 5 and 9 years. Our analysis reveals the presence of nonlinearity in the time-series of sandbar and wave data, and the relative importance of nonlinearity for each variable. The relation between the results of each sandbar case and patterns in bar behavior are discussed, together with the effects of noise. The small effect of nonlinearity implies that long-term prediction of sandbar positions based on wave forcings might not require sophisticated nonlinear models.

scholarly journals Linear Time Complexity Time Series Clustering with Symbolic Pattern Forest

2019 ◽  
Author(s):  
Xiaosheng Li ◽  
Jessica Lin ◽  
Liang Zhao
Keyword(s):  
Time Series ◽  
Data Storage ◽  
Time Complexity ◽  
Clustering Algorithm ◽  
Time Series Data ◽  
Linear Time ◽  
Series Data ◽  
Data Generation ◽  
Time Series Clustering ◽  
Group Structures

With increasing powering of data storage and advances in data generation and collection technologies, large volumes of time series data become available and the content is changing rapidly. This requires the data mining methods to have low time complexity to handle the huge and fast-changing data. This paper presents a novel time series clustering algorithm that has linear time complexity. The proposed algorithm partitions the data by checking some randomly selected symbolic patterns in the time series. Theoretical analysis is provided to show that group structures in the data can be revealed from this process. We evaluate the proposed algorithm extensively on all 85 datasets from the well-known UCR time series archive, and compare with the state-of-the-art approaches with statistical analysis. The results show that the proposed method is faster, and achieves better accuracy compared with other rival methods.

scholarly journals Putting the “dynamic” back into dynamic functional connectivity

2017 ◽  
Author(s):  
Stewart Heitmann ◽  
Michael Breakspear
Keyword(s):  
Time Series ◽  
Functional Connectivity ◽  
Large Scale ◽  
Time Series Data ◽  
Temporal Structure ◽  
Series Data ◽  
Dynamic Functional Connectivity ◽  
Time Resolved ◽  
Phase Amplitude ◽  
The Brain

AbstractThe study of fluctuations in time-resolved functional connectivity is a topic of substantial current interest. As the term “dynamic functional connectivity” implies, such fluctuations are believed to arise from dynamics in the neuronal systems generating these signals. While considerable activity currently attends to methodological and statistical issues regarding dynamic functional connectivity, less attention has been paid toward its candidate causes. Here, we review candidate scenarios for dynamic (functional) connectivity that arise in dynamical systems with two or more subsystems; generalized synchronization, itinerancy (a form of metastability), and multistability. Each of these scenarios arise under different configurations of local dynamics and inter-system coupling: We show how they generate time series data with nonlinear and/or non-stationary multivariate statistics. The key issue is that time series generated by coupled nonlinear systems contain a richer temporal structure than matched multivariate (linear) stochastic processes. In turn, this temporal structure yields many of the phenomena proposed as important to large-scale communication and computation in the brain, such as phase-amplitude coupling, complexity and flexibility. The code for simulating these dynamics is available in a freeware software platform, the “Brain Dynamics Toolbox”.

Sign in / Sign up

Export Citation Format

Share Document