scholarly journals Time-dependent Canonical Correlation Analysis for Multilevel Time Series

2019 ◽  
Author(s):  
Xuefei Cao ◽  
Jun Ke ◽  
Björn Sandstede ◽  
Xi Luo
Keyword(s):  
Time Series ◽  
Correlation Analysis ◽  
Canonical Correlation Analysis ◽  
Canonical Correlation ◽  
Time Series Data ◽  
Temporal Dynamics ◽  
Temporal Variations ◽  
Time Dependent ◽  
Series Data ◽  
Aging Effects

AbstractCanonical Correlation Analysis is a technique in multivariate data analysis for finding linear projections that maximize the correlation between two groups of variables. The correlations are typically defined without accounting for the serial correlations between observations, a typical setting for time series data. To understand the coupling dynamics and temporal variations between the two time-varying sources, we introduce the time-dependent canonical correlation analysis (TDCCA), a method for inferring time-dependent canonical vectors from multilevel time series data. A convex formulation of the problem is proposed, which leverages the singular value decomposition (SVD) characterization of all solutions of the CCA problem. We use simulated datasets to validate the proposed algorithm. Moreover, we propose a novel measure, canonical correlation variation as another way to assess the dynamic pattern of brain connections and we apply it to a real resting state fMRI dataset to study the aging effects on brain connectivity. Additionally, we explore our proposed method in a task-related fMRI to detect the temporal dynamics due to different motor tasks. We show that, compared to extant methods, the TDCCA-based approach not only detect temporal changes but also improves feature extraction. Together, this paper contributes broadly to new computational methodologies in understanding multilevel time series.

Correlation analysis of continuous emotional response to music: Correcting for the effects of serial correlation

2001 ◽  
Vol 5 (1_suppl) ◽  
pp. 213-236 ◽  
Author(s):  
Emery Schubert
Keyword(s):  
Time Series ◽  
Correlation Analysis ◽  
Emotional Response ◽  
Serial Correlation ◽  
Time Series Data ◽  
Second Order ◽  
Series Data ◽  
First Order ◽  
The Relationship ◽  
Pearson Correlations

Publications of research concerning continuous emotional responses to music are increasing. The developing interest brings with it a need to understand the problems associated with the analysis of time series data. This article investigates growing concern in the use of conventional Pearson correlations for comparing time series data. Using continuous data collected in response to selected pieces of music, with two emotional dimensions for each piece, two falsification studies were conducted. The first study consisted of a factor analysis of the individual responses using the original data set and its first-order differenced transformation. The differenced data aligned according to theoretical constraints better than the untransformed data, supporting the use of first-order difference transformations. Using a similar method, the second study specifically investigated the relationship between Pearson correlations, difference transformations and the critical correlation coefficient above which the conventional correlation analysis remains internally valid. A falsification table was formulated and quantified through a hypothesis index function. The study revealed that correlations of undifferenced data must be greater than 0.75 for a valid interpretation of the relationship between bivariate emotional response time series data. First and second-order transformations were also investigated and found to be valid for correlation coefficients as low as 0.24. Of the three version of the data (untransformed, first-order differenced, and second-order differenced), first-order differenced data produced the fewest problems with serial correlation, whilst remaining a simple and meaningful transformation.

scholarly journals Assessing the Use of Sentinel-2 Time Series Data for Monitoring Cork Oak Decline in Portugal

2019 ◽  
Vol 11 (21) ◽  
pp. 2515 ◽  
Author(s):  
Ana Navarro ◽  
Joao Catalao ◽  
Joao Calvao
Keyword(s):  
Time Series ◽  
Vegetation Index ◽  
Normalized Difference Vegetation Index ◽  
Time Series Data ◽  
Temporal Dynamics ◽  
Cork Oak ◽  
Series Data ◽  
Tree Level ◽  
Oak Decline ◽  
Sentinel 2

In Portugal, cork oak (Quercus suber L.) stands cover 737 Mha, being the most predominant species of the montado agroforestry system, contributing to the economic, social and environmental development of the country. Cork oak decline is a known problem since the late years of the 19th century that has recently worsened. The causes of oak decline seem to be a result of slow and cumulative processes, although the role of each environmental factor is not yet established. The availability of Sentinel-2 high spatial and temporal resolution dense time series enables monitoring of gradual processes. These processes can be monitored using spectral vegetation indices (VI) as their temporal dynamics are expected to be related with green biomass and photosynthetic efficiency. The Normalized Difference Vegetation Index (NDVI) is sensitive to structural canopy changes, however it tends to saturate at moderate-to-dense canopies. Modified VI have been proposed to incorporate the reflectance in the red-edge spectral region, which is highly sensitive to chlorophyll content while largely unaffected by structural properties. In this research, in situ data on the location and vitality status of cork oak trees are used to assess the correlation between chlorophyll indices (CI) and NDVI time series trends and cork oak vitality at the tree level. Preliminary results seem to be promising since differences between healthy and unhealthy (diseased/dead) trees were observed.

scholarly journals Total Imports and Its Components Influence on Inflation in Kenya

2020 ◽  
pp. 54-62
Author(s):  
Evans Ovamba Kiganda ◽  
Margaret Atieno Omondi
Keyword(s):  
Time Series ◽  
Correlation Analysis ◽  
Central Bank ◽  
Granger Causality ◽  
Time Series Data ◽  
Negative Influence ◽  
Variance Decomposition ◽  
Series Data ◽  
Causality Tests ◽  
Granger Causality Tests

Aim: The purpose of this study was to analyze the influence of total imports (TIMP) and its components of commercial imports (CIMP) and government imports (GIMP) on inflation in           Kenya. Study Design: Quantitative approach was employed to analyze the influence of imports on inflation in Kenya. Methodology: Monthly time series data from Central Bank of Kenya for the period 2005 to 2018 was used for analysis involving correlation analysis, variance decomposition, impulse response and Granger causality tests. Results: Results indicated that total imports and commercial imports had negative influence on inflation while government imports did not significantly influence inflation in Kenya. Unidirectional causality from total imports and commercial imports to inflation was noted while there was no causality between government imports and inflation. Conclusion: The study concluded that imports influence inflation in Kenya but commercial imports highly determined total imports influence on inflation in Kenya.

scholarly journals Stochastic Claims Reserving Methods with State Space Representations: A Review

Risks ◽  
2021 ◽  
Vol 9 (11) ◽  
pp. 198
Author(s):  
Nataliya Chukhrova ◽  
Arne Johannssen
Keyword(s):  
Time Series ◽  
State Space ◽  
Life Insurance ◽  
Time Series Data ◽  
Temporal Dynamics ◽  
Insurance Companies ◽  
Series Data ◽  
Time Series Models ◽  
Life Insurer ◽  
High Flexibility

Often, the claims reserves exceed the available equity of non-life insurance companies and a change in the claims reserves by a small percentage has a large impact on the annual accounts. Therefore, it is of vital importance for any non-life insurer to handle claims reserving appropriately. Although claims data are time series data, the majority of the proposed (stochastic) claims reserving methods is not based on time series models. Among the time series models, state space models combined with Kalman filter learning algorithms have proven to be very advantageous as they provide high flexibility in modeling and an accurate detection of the temporal dynamics of a system. Against this backdrop, this paper aims to provide a comprehensive review of stochastic claims reserving methods that have been developed and analyzed in the context of state space representations. For this purpose, relevant articles are collected and categorized, and the contents are explained in detail and subjected to a conceptual comparison.

scholarly journals Intra-Annual Patterns in the Benthic-Pelagic Fluxes of Dissolved and Particulate Matter

2020 ◽  
Vol 7 ◽  
Author(s):  
Saskia Rühl ◽  
Charlie E. L. Thompson ◽  
Ana M. Queirós ◽  
Stephen Widdicombe
Keyword(s):  
Time Series ◽  
Biological Activity ◽  
Particulate Matter ◽  
Time Series Data ◽  
Temporal Variations ◽  
Series Data ◽  
Downward Flux ◽  
Dissolved Matter ◽  
Upward Flux

In coastal temperate environments, many processes known to affect the exchange of particulate and dissolved matter between the seafloor and the water column follow cyclical patterns of intra-annual variation. This study assesses the extent to which these individual short term temporal variations affect specific direct drivers of seafloor-water exchanges, how they interact with one another throughout the year, and what the resulting seasonal variation in the direction and magnitude of benthic-pelagic exchange is. Existing data from a multidisciplinary long-term time-series from the Western Channel Observatory, United Kingdom, were combined with new experimental and in situ data collected throughout a full seasonal cycle. These data, in combination with and contextualized by time-series data, were used to define an average year, split into five ‘periods’ (winter, pre-bloom, bloom, post-bloom, and autumn) based around the known importance of pelagic primary production and hydrodynamically active phases of the year. Multivariate analyses were used to identify specific sub-sets of parameters that described the various direct drivers of seafloor-water exchanges. Both dissolved and particulate exchange showed three distinct periods of significant flux during the year, although the specific timings of these periods and the cause-effect relationships to the direct and indirect drivers differed between the two types of flux. Dissolved matter exchange was dominated by an upward flux in the pre-bloom period driven by diffusion, then a biologically induced upward flux during the bloom and an autumn downward flux. The latter was attributable to the interactions of hydrodynamic and biological activity on the seafloor. Particulate matter exchanges exhibited a strongly hydrologically influenced upward flux during the winter, followed by a biologically induced downward flux during the bloom and a second period of downward flux throughout post-bloom and autumn periods. This was driven primarily through interactions between biological activity, and physical and meteorological drivers. The integrated, holistic and quantitative data-based analysis of intra-annual variability in benthic/pelagic fluxes presented in this study in a representative temperate coastal environment, demonstrates not only the various process’ inter-connectivity, but also their relative importance to each other. Future investigations or modeling efforts of similar systems will benefit greatly from the relationships and baseline rules established in this study.

scholarly journals A Robust Method for Generating High-Spatiotemporal-Resolution Surface Reflectance by Fusing MODIS and Landsat Data

2020 ◽  
Vol 12 (14) ◽  
pp. 2312
Author(s):  
Junming Yang ◽  
Yunjun Yao ◽  
Yongxia Wei ◽  
Yuhu Zhang ◽  
Kun Jia ◽  
...  
Keyword(s):  
Time Series ◽  
Data Fusion ◽  
Land Surface ◽  
Time Series Data ◽  
Temporal Variations ◽  
Series Data ◽  
Surface Reflectance ◽  
Spatiotemporal Resolution ◽  
Ecological Processes ◽  
Clustering Model

The methods for accurately fusing medium- and high-spatial-resolution satellite reflectance are vital for monitoring vegetation biomass, agricultural irrigation, ecological processes and climate change. However, the currently existing fusion methods cannot accurately capture the temporal variation in reflectance for heterogeneous landscapes. In this study, we proposed a new method, the spatial and temporal reflectance fusion method based on the unmixing theory and a fuzzy C-clustering model (FCMSTRFM), to generate Landsat-like time-series surface reflectance. Unlike other data fusion models, the FCMSTRFM improved the similarity of pixels grouped together by combining land cover maps and time-series data cluster algorithms to define endmembers. The proposed method was tested over a 2000 km2 study area in Heilongjiang Provence, China, in 2017 and 2018 using ten images. The results show that the accuracy of the FCMSTRFM is better than that of the popular enhanced spatial and temporal adaptive reflectance fusion model (ESTARFM) (correlation coefficient (R): 0.8413 vs. 0.7589; root mean square error (RMSE): 0.0267 vs. 0.0401) and the spatial-temporal data fusion approach (STDFA) (R: 0.8413 vs. 0.7666; RMSE: 0.0267 vs. 0.0307). Importantly, the FCMSTRFM was able to maintain the details of temporal variations in complicated landscapes. The proposed method provides an alternative method to monitor the dynamics of land surface variables over complicated heterogeneous regions.

Sign in / Sign up

Export Citation Format

Share Document