{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"submitter":["Stern U"],"funding":["NIGMS NIH HHS"],"pagination":["14351"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC4585819"],"repository":["biostudies-literature"],"omics_type":["Unknown"],"volume":["5"],"pubmed_abstract":["High-throughput analysis of animal behavior requires software to analyze videos. Such software analyzes each frame individually, detecting animals' body parts. But the image analysis rarely attempts to recognize \"behavioral states\"-e.g., actions or facial expressions-directly from the image instead of using the detected body parts. Here, we show that convolutional neural networks (CNNs)-a machine learning approach that recently became the leading technique for object recognition, human pose estimation, and human action recognition-were able to recognize directly from images whether Drosophila were \"on\" (standing or walking) or \"off\" (not in physical contact with) egg-laying substrates for each frame of our videos. We used multiple nets and image transformations to optimize accuracy for our"],"journal":["Scientific reports"],"pubmed_title":["Analyzing animal behavior via classifying each video frame using convolutional neural networks."],"pmcid":["PMC4585819"],"funding_grant_id":["R01GM100027","R01 GM100027"],"pubmed_authors":["Stern U","Yang CH","He R"],"additional_accession":[]},"is_claimable":false,"name":"Analyzing animal behavior via classifying each video frame using convolutional neural networks.","description":"High-throughput analysis of animal behavior requires software to analyze videos. Such software analyzes each frame individually, detecting animals' body parts. But the image analysis rarely attempts to recognize \"behavioral states\"-e.g., actions or facial expressions-directly from the image instead of using the detected body parts. Here, we show that convolutional neural networks (CNNs)-a machine learning approach that recently became the leading technique for object recognition, human pose estimation, and human action recognition-were able to recognize directly from images whether Drosophila were \"on\" (standing or walking) or \"off\" (not in physical contact with) egg-laying substrates for each frame of our videos. We used multiple nets and image transformations to optimize accuracy for our","dates":{"release":"2015-01-01T00:00:00Z","publication":"2015 Sep","modification":"2025-04-21T20:21:17.844Z","creation":"2019-03-27T01:59:06Z"},"accession":"S-EPMC4585819","cross_references":{"pubmed":["26394695"],"doi":["10.1038/srep14351"]}}