Browsing by Subject "PARTIAL LEAST-SQUARES"

Sort by: Order: Results:

Now showing items 1-4 of 4
  • Yetukuri, Laxman; Soderlund, Sanni; Koivuniemi, Artturi; Seppanen-Laakso, Tuulikki; Niemela, Perttu S.; Hyvonen, Marja; Taskinen, Marja-Riitta; Vattulainen, Ilpo Tapio; Jauhiainen, Matti; Oresic, Matej (2010)
  • Kauttonen, Janne; Hlushchuk, Yevhen; Tikka, Pia (2015)
    One of the challenges of naturalistic neurosciences using movie-viewing experiments is how to interpret observed brain activations in relation to the multiplicity of time-locked stimulus features. As previous studies have shown less inter-subject synchronization across viewers of random video footage than story-driven films, new methods need to be developed for analysis of less story-driven contents. To optimize the linkage between our fMRI data collected during viewing of a deliberately non-narrative silent film 'At Land' by Maya Deren (1944) and its annotated content, we combined the method of elastic-net regularization with the model-driven linear regression and the well-established data-driven independent component analysis (ICA) and inter-subject correlation (ISC) methods. In the linear regression analysis, both IC and region-of-interest (ROI) time-series were fitted with time-series of a total of 36 binary-valued and one real-valued tactile annotation of film features. The elastic-net regularization and cross-validation were applied in the ordinary least-squares linear regression in order to avoid over-fitting due to the multicollinearity of regressors, the results were compared against both the partial least-squares (PLS) regression and the un-regularized full-model regression. Nonparametric permutation testing scheme was applied to evaluate the statistical significance of regression. We found statistically significant correlation between the annotation model and 9 ICs out of 40 ICs. Regression analysis was also repeated for a large set of cubic ROIs covering the grey matter. Both IC- and ROI-based regression analyses revealed activations in parietal and occipital regions, with additional smaller clusters in the frontal lobe. Furthermore, we found elastic-net based regression more sensitive than PLS and un-regularized regression since it detected a larger number of significant ICs and ROIs. Along with the ISC ranking methods, our regression analysis proved a feasible method for ordering the ICs based on their functional relevance to the annotated cinematic features. The novelty of our method is - in comparison to the hypothesis-driven manual pre-selection and observation of some individual regressors biased by choice - in applying data-driven approach to all content features simultaneously. We found especially the combination of regularized regression and ICA useful when analyzing fMRI data obtained using non-narrative movie stimulus with a large set of complex and correlated features. (C) 2015 The Authors. Published by Elsevier Inc.
  • Hou, Meiting; Venalainen, Ari K.; Wang, Linping; Pirinen, Pentti; Gao, Yao; Jin, Shaofei; Zhu, Yuxiang; Qin, Fuying; Hu, Yonghong (2020)
    Spring greening in boreal forest ecosystems has been widely linked to increasing temperature, but few studies have attempted to unravel the relative effects of climate variables such as maximum temperature (TMX), minimum temperature (TMN), mean temperature (TMP), precipitation (PRE) and radiation (RAD) on vegetation growth at different stages of growing season. However, clarifying these effects is fundamental to better understand the relationship between vegetation and climate change. This study investigated spatio-temporal divergence in the responses of Finland's boreal forests to climate variables using the plant phenology index (PPI) calculated based on the latest Collection V006 MODIS BRDF-corrected surface reflectance products (MCD43C4) from 2002 to 2018, and identified the dominant climate variables controlling vegetation change during the growing season (May-September) on a monthly basis. Partial least squares (PLS) regression was used to quantify the response of PPI to climate variables and distinguish the separate impacts of different variables. The study results show the dominant effects of temperature on the PPI in May and June, with TMX, TMN and TMP being the most important explanatory variables for the variation of PPI depending on the location, respectively. Meanwhile, drought had an unexpectedly positive impact on vegetation in few areas. More than 50 % of the variation of PPI could be explained by climate variables for 68.5 % of the entire forest area in May and 87.7 % in June, respectively. During July to September, the PPI variance explained by climate and corresponding spatial extent rapidly decreased. Nevertheless, the RAD was found be the most important explanatory variable to July PPI in some areas. In contrast, the PPI in August and September was insensitive to climate in almost all of the regions studied. Our study gives useful insights on quantifying and identifying the relative importance of climate variables to boreal forest, which can be used to predict the possible response of forest under future warming.
  • Velagapudi, Vidya R.; Hezaveh, Rahil; Reigstad, Christopher S.; Gopalacharyulu, Peddinti; Yetukuri, Laxman; Islam, Sama; Felin, Jenny; Perkins, Rosie; Boren, Jan; Oresic, Matej; Backhed, Fredrik (2010)