Matches in SemOpenAlex for { <https://semopenalex.org/work/W4377233024> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W4377233024 abstract "Abstract The rodent vibrissal system remains pivotal in advancing neuroscience research, particularly for studies of cortical plasticity, learning, decision-making, sensory encoding and sensorimotor integration. While this model system provides notable advantages for quantifying active tactile input, it is hindered by the labor-intensive process of curating touch events across millions of video frames. Even with the aid of automated tools like the Janelia Whisker Tracker, millisecond-accurate touch curation often requires >3 hours of manual review / million video frames. We address this limitation by introducing Whisker Automatic Contact Classifier (WhACC), a python package designed to identify touch periods from high-speed videos of head-fixed behaving rodents with human-level performance. For our model design, we train ResNet50V2 on whisker images and extract features. Next, we engineer features to improve performance with an emphasis on temporal consistency. Finally, we select only the most important features and use them to train a LightGBM classifier. Classification accuracy is assessed against three expert human curators on over one million frames. WhACC shows pairwise touch classification agreement on 99.5% of video frames, equal to between-human agreement. Additionally, comparison between an expert curator and WhACC on a holdout dataset comprising nearly four million frames and 16 single-unit electrophysiology recordings shows negligible differences in neural characterization metrics. Finally, we offer an easy way to select and curate a subset of data to adaptively retrain WhACC. Including this retraining step, we reduce human hours required to curate a 100 million frame dataset from ∼333 hours to ∼6 hours." @default.
- W4377233024 created "2023-05-23" @default.
- W4377233024 creator A5030331177 @default.
- W4377233024 creator A5038651563 @default.
- W4377233024 creator A5045492238 @default.
- W4377233024 creator A5076973397 @default.
- W4377233024 creator A5077943352 @default.
- W4377233024 date "2023-05-22" @default.
- W4377233024 modified "2023-09-26" @default.
- W4377233024 title "WhACC: Whisker Automatic Contact Classifier with Expert Human-Level Performance" @default.
- W4377233024 cites W153156118 @default.
- W4377233024 cites W1990606357 @default.
- W4377233024 cites W2013011999 @default.
- W4377233024 cites W2018796939 @default.
- W4377233024 cites W2028399966 @default.
- W4377233024 cites W2140050887 @default.
- W4377233024 cites W2161516666 @default.
- W4377233024 cites W2168232109 @default.
- W4377233024 cites W2170902730 @default.
- W4377233024 cites W2183341477 @default.
- W4377233024 cites W2302255633 @default.
- W4377233024 cites W2531409750 @default.
- W4377233024 cites W2754970036 @default.
- W4377233024 cites W2807973442 @default.
- W4377233024 cites W2883429621 @default.
- W4377233024 cites W2949676527 @default.
- W4377233024 cites W2963919481 @default.
- W4377233024 cites W2963923251 @default.
- W4377233024 cites W2970489962 @default.
- W4377233024 cites W2970513610 @default.
- W4377233024 cites W2982083293 @default.
- W4377233024 cites W3046626379 @default.
- W4377233024 cites W3089783877 @default.
- W4377233024 cites W3097819836 @default.
- W4377233024 cites W3100650809 @default.
- W4377233024 cites W4200441181 @default.
- W4377233024 cites W4224053304 @default.
- W4377233024 cites W4255367522 @default.
- W4377233024 doi "https://doi.org/10.1101/2023.05.19.541544" @default.
- W4377233024 hasPublicationYear "2023" @default.
- W4377233024 type Work @default.
- W4377233024 citedByCount "0" @default.
- W4377233024 crossrefType "posted-content" @default.
- W4377233024 hasAuthorship W4377233024A5030331177 @default.
- W4377233024 hasAuthorship W4377233024A5038651563 @default.
- W4377233024 hasAuthorship W4377233024A5045492238 @default.
- W4377233024 hasAuthorship W4377233024A5076973397 @default.
- W4377233024 hasAuthorship W4377233024A5077943352 @default.
- W4377233024 hasBestOaLocation W43772330241 @default.
- W4377233024 hasConcept C107457646 @default.
- W4377233024 hasConcept C119857082 @default.
- W4377233024 hasConcept C144133560 @default.
- W4377233024 hasConcept C153180895 @default.
- W4377233024 hasConcept C154945302 @default.
- W4377233024 hasConcept C155202549 @default.
- W4377233024 hasConcept C205427263 @default.
- W4377233024 hasConcept C2522767166 @default.
- W4377233024 hasConcept C2778712577 @default.
- W4377233024 hasConcept C31972630 @default.
- W4377233024 hasConcept C3261483 @default.
- W4377233024 hasConcept C41008148 @default.
- W4377233024 hasConcept C95623464 @default.
- W4377233024 hasConceptScore W4377233024C107457646 @default.
- W4377233024 hasConceptScore W4377233024C119857082 @default.
- W4377233024 hasConceptScore W4377233024C144133560 @default.
- W4377233024 hasConceptScore W4377233024C153180895 @default.
- W4377233024 hasConceptScore W4377233024C154945302 @default.
- W4377233024 hasConceptScore W4377233024C155202549 @default.
- W4377233024 hasConceptScore W4377233024C205427263 @default.
- W4377233024 hasConceptScore W4377233024C2522767166 @default.
- W4377233024 hasConceptScore W4377233024C2778712577 @default.
- W4377233024 hasConceptScore W4377233024C31972630 @default.
- W4377233024 hasConceptScore W4377233024C3261483 @default.
- W4377233024 hasConceptScore W4377233024C41008148 @default.
- W4377233024 hasConceptScore W4377233024C95623464 @default.
- W4377233024 hasLocation W43772330241 @default.
- W4377233024 hasOpenAccess W4377233024 @default.
- W4377233024 hasPrimaryLocation W43772330241 @default.
- W4377233024 hasRelatedWork W2001652754 @default.
- W4377233024 hasRelatedWork W2549006548 @default.
- W4377233024 hasRelatedWork W2563096758 @default.
- W4377233024 hasRelatedWork W2623427976 @default.
- W4377233024 hasRelatedWork W2807311372 @default.
- W4377233024 hasRelatedWork W2921036759 @default.
- W4377233024 hasRelatedWork W2961085424 @default.
- W4377233024 hasRelatedWork W3120243212 @default.
- W4377233024 hasRelatedWork W4214932115 @default.
- W4377233024 hasRelatedWork W3158004940 @default.
- W4377233024 isParatext "false" @default.
- W4377233024 isRetracted "false" @default.
- W4377233024 workType "article" @default.