FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4367187249> ?p ?o ?g. }

• W4367187249 abstract "Abstract Neuroscience studies face challenges in gathering large datasets, which limits the use of machine learning (ML) approaches. One possible solution is to incorporate additional data from large public datasets; however, data collected in different contexts often exhibit systematic differences called dataset shifts. Various factors, e . g ., site, device type, experimental protocol, or social characteristics, can lead to substantial divergence of brain signals that can hinder the success of ML across datasets. In this work, we focus on dataset shifts in recordings of brain activity using MEG and EEG. State-of-the-art predictive approaches on M/EEG signals classically represent the data by covariance matrices. Model-based dataset alignment methods can leverage the geometry of covariance matrices, leading to three steps: recentering, re-scaling, and rotation correction. This work explains theoretically how differences in brain activity, anatomy, or device configuration lead to certain shifts in data covariances. Using controlled simulations, the different alignment methods are evaluated. Their practical relevance is evaluated for brain age prediction on one MEG dataset (Cam-CAN, n =646) and two EEG datasets (TUAB, n =1385; LEMON, n =213). When the target sample included recordings from the same subjects with a different task among the same dataset, paired rotation correction was essential ( (rest-passive) or +0.17 (rest-smt)). When the target dataset included new subjects and a new task, re-centering led to improved performance ( for rest-passive, for rest-smt). For generalization to an independent dataset sampled from a different population and recorded with a different device, re-centering was necessary to achieve brain age prediction performance close to within domain prediction performance. This study demonstrates that the generalization of M/EEG-based regression models across datasets can be substantially enhanced by applying domain adaptation procedures that can statistically harmonize diverse datasets." @default.
• W4367187249 created "2023-04-28" @default.
• W4367187249 creator A5000806684 @default.
• W4367187249 creator A5018256474 @default.
• W4367187249 creator A5026515170 @default.
• W4367187249 creator A5027334117 @default.
• W4367187249 creator A5040139150 @default.
• W4367187249 date "2023-04-27" @default.
• W4367187249 modified "2023-09-26" @default.
• W4367187249 title "Harmonizing and aligning M/EEG datasets with covariance-based techniques to enhance predictive regression modeling" @default.
• W4367187249 cites W1592510033 @default.
• W4367187249 cites W1824528708 @default.
• W4367187249 cites W1968426398 @default.
• W4367187249 cites W1985244573 @default.
• W4367187249 cites W1995506038 @default.
• W4367187249 cites W2011301426 @default.
• W4367187249 cites W2032236594 @default.
• W4367187249 cites W2035715639 @default.
• W4367187249 cites W2042076346 @default.
• W4367187249 cites W2080966422 @default.
• W4367187249 cites W2096597330 @default.
• W4367187249 cites W2106628957 @default.
• W4367187249 cites W2119963163 @default.
• W4367187249 cites W2162651021 @default.
• W4367187249 cites W2536023058 @default.
• W4367187249 cites W2584886900 @default.
• W4367187249 cites W2599251041 @default.
• W4367187249 cites W2741907166 @default.
• W4367187249 cites W2746829572 @default.
• W4367187249 cites W2794345050 @default.
• W4367187249 cites W2804449593 @default.
• W4367187249 cites W2805766146 @default.
• W4367187249 cites W2906104384 @default.
• W4367187249 cites W2937610289 @default.
• W4367187249 cites W2949122071 @default.
• W4367187249 cites W2963187488 @default.
• W4367187249 cites W2963355311 @default.
• W4367187249 cites W2963919481 @default.
• W4367187249 cites W2996586346 @default.
• W4367187249 cites W3027507201 @default.
• W4367187249 cites W3027718029 @default.
• W4367187249 cites W3031967244 @default.
• W4367187249 cites W3099878876 @default.
• W4367187249 cites W3103145119 @default.
• W4367187249 cites W3118838274 @default.
• W4367187249 cites W3129030047 @default.
• W4367187249 cites W3156463266 @default.
• W4367187249 cites W3183267169 @default.
• W4367187249 cites W4200631478 @default.
• W4367187249 cites W4206086399 @default.
• W4367187249 cites W4223434129 @default.
• W4367187249 cites W4288045497 @default.
• W4367187249 doi "https://doi.org/10.1101/2023.04.27.538550" @default.
• W4367187249 hasPublicationYear "2023" @default.
• W4367187249 type Work @default.
• W4367187249 citedByCount "1" @default.
• W4367187249 countsByYear W43671872492023 @default.
• W4367187249 crossrefType "posted-content" @default.
• W4367187249 hasAuthorship W4367187249A5000806684 @default.
• W4367187249 hasAuthorship W4367187249A5018256474 @default.
• W4367187249 hasAuthorship W4367187249A5026515170 @default.
• W4367187249 hasAuthorship W4367187249A5027334117 @default.
• W4367187249 hasAuthorship W4367187249A5040139150 @default.
• W4367187249 hasBestOaLocation W43671872491 @default.
• W4367187249 hasConcept C105795698 @default.
• W4367187249 hasConcept C118552586 @default.
• W4367187249 hasConcept C119857082 @default.
• W4367187249 hasConcept C134306372 @default.
• W4367187249 hasConcept C138885662 @default.
• W4367187249 hasConcept C144024400 @default.
• W4367187249 hasConcept C149923435 @default.
• W4367187249 hasConcept C153083717 @default.
• W4367187249 hasConcept C153180895 @default.
• W4367187249 hasConcept C154945302 @default.
• W4367187249 hasConcept C15744967 @default.
• W4367187249 hasConcept C162324750 @default.
• W4367187249 hasConcept C177148314 @default.
• W4367187249 hasConcept C178650346 @default.
• W4367187249 hasConcept C187736073 @default.
• W4367187249 hasConcept C207390915 @default.
• W4367187249 hasConcept C2780451532 @default.
• W4367187249 hasConcept C2908647359 @default.
• W4367187249 hasConcept C33923547 @default.
• W4367187249 hasConcept C41008148 @default.
• W4367187249 hasConcept C41895202 @default.
• W4367187249 hasConcept C522805319 @default.
• W4367187249 hasConcept C83546350 @default.
• W4367187249 hasConceptScore W4367187249C105795698 @default.
• W4367187249 hasConceptScore W4367187249C118552586 @default.
• W4367187249 hasConceptScore W4367187249C119857082 @default.
• W4367187249 hasConceptScore W4367187249C134306372 @default.
• W4367187249 hasConceptScore W4367187249C138885662 @default.
• W4367187249 hasConceptScore W4367187249C144024400 @default.
• W4367187249 hasConceptScore W4367187249C149923435 @default.
• W4367187249 hasConceptScore W4367187249C153083717 @default.
• W4367187249 hasConceptScore W4367187249C153180895 @default.
• W4367187249 hasConceptScore W4367187249C154945302 @default.
• W4367187249 hasConceptScore W4367187249C15744967 @default.
• W4367187249 hasConceptScore W4367187249C162324750 @default.
• W4367187249 hasConceptScore W4367187249C177148314 @default.

• next