[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-120776-en":3,"doc-seo-120776-105":29,"detail-sidebar-cat-0-en-105":89},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":20,"language":21,"language_code":22,"site_id":23,"html_lang":22,"table_of_contents":24,"faqs":25,"seo_title":26,"seo_description":14,"update_tm":27,"read_time":28},120776,34359740700684,"Finn","https://ap-avatar.wpscdn.com/avatar/1f400023980c374ae676?_k=1777273430885731487",8,"Research & Report","Machine Learning Analysis for Animal Behavior in Predator-Exposed Rodents - Presentation","Machine learning analysis supports behavioral laboratory studies by quantifying how different rodents react to predator exposure across strain, sex, age, and housing conditions. The setup uses a 3D-printed owl predator that surges toward the arena center, while tracking pose-specific body-point markers. Behavioral patterns such as hiding, freezing, fleeing, wall proximity, and movement trajectories can be characterized before, during, and after exposure. Early results indicate distinct rat versus mouse reactions that depend on biological and housing variables.","Machine Learning Analysis for Animal Behavior in Predator-Exposed Rodents  \nHoda AbouEich, Michael Mains, Bailey Wells, & Phillip Baker  \nDepartment of Biological Structure, University of Washington, Seattle, WA, 98195 USA  \nAbstract  \nNext Steps  \nMachine Learning Analysis  \n● With the rise of artificial intelligence (AI), machine learning analysis will likely become standard use within behavioral laboratory settings.  \n● Using machine learning analysis, we analyzed behavior expressed by both rats and mice of different strain, sex, age, and housing in order to more closely evaluate behavioral differences in exposure to a predator stimulus.  \n● The predator stimulus was a 3D printed owl predator that surges towards the center of an arena.  \n● A training network was taught to base its evaluations of behavior on specific points that correspond with body parts of the rodent.  \n● As the rodent responded to the stimulus, we were able to evaluate behavioral patterns, such as time spent in hiding, freezing, fleeing, or near the walls of the arena.  \n● This will allow us to look at the overall movement trajectories prior to and during predator exposure.  \n● Based upon the early stages of behavioral analysis, we found that rats and mice seem to have different behavioral reactions to predator exposures, and these seem to be dependent on rodent strain, sex, and housing condition.  \n● We hope to further investigate the differences between species, strain, and sex using machine learning analysis.  \nSubjects  \n● 35 mice  \n○ 6 CD1 single-housed females  \n○ 5 CD1 co-housed old males  \n○ 8 C57 co-housed old males  \n○ 5 C57 co-housed females  \n○ 6 C57 young males  \n○ 5 C57 young females  \n● 8 rats  \n○ 4 Sprague Dawley co-housed males  \n○ 4 Sprague Dawley co-housed females  \nMeasures  \n● Habituation  \n○ 20 mins in the hide with 10 sugar pellets once a day for 2 days  \n● Foraging  \n○ 5 mins with increasing distance of pellet from hide  \n○ 6 days  \n● Predator Exposure  \n○ When the rodent gets within about 30 cm of the pellet in the arena, the owl surges approximately 100 cm over the food pellet toward the hide at about 70 cm/s.  \n○ This process is run for 3 minutes, regardless of the number of surges.  \n○ 2 days  \n● Machine Learning  \n○ Simple Behavioral Analysis (SimBA)  \n■ SimbBA is a program that uses machine learning to describe animal behavior in realtime.  \n■ It was used to crop the videos to adjust the area space, accounting for the arena.  \n■ Open Source code can be found here: [https://github.com/sgoldenlab/simba](https://github.com/sgoldenlab/simba)  \n○ DeepLabCut  \n■ DeepLabCut is a program that allows us to train a machine learning model in order to predict rodent movement and behavior.  \n■ After cropping, 20 frames were extracted from each video in order to label body parts by hand on the rodent, owl, and owl shadow, as seen in Figures 1 and 2 .  \n■ These frames were then used to train the model on rodent movement and the location of the owl and the owl shadow.  \n■ Once the model is fully trained, it can be used to analyze rodent movement and behavior (such as grooming and foraging) before, during, and after predator exposure.  \n■ Open Source code can be found here: [https://github.com/DeepLabCut/DeepLabCut](https://github.com/DeepLabCut/DeepLabCut)  \nExperimental Timeline  \nFigure 1. Predator exposure arena pre-owl surge. This is during the pose-estimation tracking section of the machine learning process.  \nFigure 2. Predator exposure arena post-owl surge  \nFigure 3. Model of predator exposure arena  \nFigure 4. This section of code for the training program is the only section of code that must be manually changed. It corresponds to the body parts in the labeling process. Because this is a multi-animal model, it is evaluating the movements of three individuals: the rodent, the owl, and the owl shadow. This way, the program can track how changes in the owl cause behavioral changes in the rodent (e.g. , asthe owl surges to the center of","cbCaibwo9KOwtPFn","https://ap.wps.com/l/cbCaibwo9KOwtPFn","pdf",1101027,1,"English","en",105,"# Abstract\n## Machine Learning Analysis\n## Subjects and Measures\n### Habituation\n### Foraging\n### Predator Exposure\n### Machine Learning Methods\n## Experimental Timeline and Outputs","[{\"question\":\"What animal behavior is analyzed in predator-exposed rodents?\",\"answer\":\"The study evaluates behaviors including time spent hiding, freezing, fleeing, proximity to arena walls, and overall movement trajectories before, during, and after predator exposure.\"},{\"question\":\"How is the predator stimulus delivered in the experiment?\",\"answer\":\"A 3D-printed owl predator surges toward the arena center, and the rodent’s response is observed while the owl targets the hide area after reaching the defined distance threshold.\"},{\"question\":\"Which machine learning tools are used to process video and train models?\",\"answer\":\"SimBA is used for cropping, pose-estimation tracking corrections, and event classification, while DeepLabCut is used to train a model by labeling extracted video frames to predict body part locations and movements.\"}]","Machine Learning Analysis for Animal Behavior in Predator-Exposed Rodents - Presentation | PDF",1785731984,3,{"code":4,"msg":30,"data":31},"ok",{"site_id":23,"language":22,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":84,"head_meta":86,"extra_data":88,"updated_unix":27},"machine-learning-analysis-for-animal-behavior-in-predator-exposed-rodents-presentation","",{"@graph":35,"@context":83},[36,52,66],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,49],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":28},"https://docshare.wps.com/document/research-report/",{"item":50,"name":13,"@type":42,"position":51},"https://docshare.wps.com/document/machine-learning-analysis-for-animal-behavior-in-predator-exposed-rodents-presentation/120776/",4,{"url":50,"name":13,"@type":53,"author":54,"headline":13,"publisher":56,"fileFormat":59,"inLanguage":22,"description":14,"dateModified":60,"datePublished":60,"encodingFormat":59,"isAccessibleForFree":61,"interactionStatistic":62},"DigitalDocument",{"name":9,"@type":55},"Person",{"url":40,"name":57,"@type":58},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":63,"interactionType":64,"userInteractionCount":4},"InteractionCounter",{"@type":65},"ViewAction",{"@type":67,"mainEntity":68},"FAQPage",[69,75,79],{"name":70,"@type":71,"acceptedAnswer":72},"What animal behavior is analyzed in predator-exposed rodents?","Question",{"text":73,"@type":74},"The study evaluates behaviors including time spent hiding, freezing, fleeing, proximity to arena walls, and overall movement trajectories before, during, and after predator exposure.","Answer",{"name":76,"@type":71,"acceptedAnswer":77},"How is the predator stimulus delivered in the experiment?",{"text":78,"@type":74},"A 3D-printed owl predator surges toward the arena center, and the rodent’s response is observed while the owl targets the hide area after reaching the defined distance threshold.",{"name":80,"@type":71,"acceptedAnswer":81},"Which machine learning tools are used to process video and train models?",{"text":82,"@type":74},"SimBA is used for cropping, pose-estimation tracking corrections, and event classification, while DeepLabCut is used to train a model by labeling extracted video frames to predict body part locations and movements.","https://schema.org",{"og:url":50,"og:type":85,"og:title":13,"og:site_name":57,"og:description":14},"article",{"robots":87,"canonical":50},"index,follow",{"doc_id":7,"site_id":23},{"code":4,"msg":5,"data":90},[91,95,99,103,108,113,118,121,126,129,133],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":92,"show_sort_weight":93,"slug":94},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":96,"show_sort_weight":97,"slug":98},"Literature",80,"literature",{"id":51,"doc_module":4,"doc_module_name":45,"category_name":100,"show_sort_weight":101,"slug":102},"Exam",70,"exam",{"id":104,"doc_module":4,"doc_module_name":45,"category_name":105,"show_sort_weight":106,"slug":107},5,"Comic",60,"comic",{"id":109,"doc_module":4,"doc_module_name":45,"category_name":110,"show_sort_weight":111,"slug":112},6,"Technology",50,"technology",{"id":114,"doc_module":4,"doc_module_name":45,"category_name":115,"show_sort_weight":116,"slug":117},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":119,"slug":120},30,"research-report",{"id":122,"doc_module":4,"doc_module_name":45,"category_name":123,"show_sort_weight":124,"slug":125},9,"Religion & Spirituality",20,"religion-spirituality",{"id":124,"doc_module":4,"doc_module_name":45,"category_name":127,"show_sort_weight":124,"slug":128},"World Cup","world-cup",{"id":130,"doc_module":4,"doc_module_name":45,"category_name":131,"show_sort_weight":130,"slug":132},10,"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":45,"category_name":135,"show_sort_weight":104,"slug":136},19,"General","general"]