[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-124226-en":3,"doc-seo-124226-105":30,"detail-sidebar-cat-0-en-105":91},{"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":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},124226,1099514067438,"River Wang","https://ap-avatar.wpscdn.com/avatar/100002539ee87300030?x-image-process=image/resize,m_fixed,w_180,h_180&k=1780474512215547542",8,"Research & Report","Machine learning for identification of individual salmon behaviour in aquaculture - Master's thesis","The modern aquaculture industry faces limited observability and control in fish cages, making fish behaviour difficult to monitor reliably under both routine and stressful conditions. This project applies machine learning to identify distinct behavioural modes of individual salmon using positional data from acoustic telemetry tags. Trajectories are reconstructed and transformed into descriptive variables, then compared via conventional analysis and principal component analysis, and clustered with HDBScan. Results show time-of-day differences, multiple detectable modes, and varying prevalence across individuals, demonstrating practical potential for machine learning in aquaculture.","Master's thesis  \nFaculty of Information Technology and Electrical Engineering  \nNorwegian University of Science and Technology  \nNTNU  \nDepartment of Engineering Cybernetics  \nEven Age Smedshaug  \n## Machine learning for identification ofindividual salmon behaviour inaquaculture\n\nMaster's thesis in Cybernetics and RoboticsSupervisor:Martin Fore  \nJuly 2023  \n# Machine learning for identification ofindividual salmon behaviour inaquaculture\n\nMaster's thesis in Cybernetics and RoboticsSupervisor:Martin ForeJuly 2023  \nNorwegian University of Science and Technology  \nFaculty of Information Technology and Electrical EngineeringDepartment of Engineering Cybernetics  \n# NTNU\n\nNorwegian University ofScience and Technology  \nPreface  \nThis project is the culmination of five years of education in Cybernetics and Roboticswith a specialization in biomedical cybernetics at the Norwegian University of Scienceand Technology(NTNU).  \nI would like to thank my supervisor Martin Fore for good conversations,both on and offtopic,in addition to believing in the methods when results were not forthcoming.I wouldalso like to thank my friends and family for putting up with increasingly fish-themedconversations.  \nTrondheim,July 2023Even Age Smedshaug  \n*工  \n### Abstract\n\nThe modern aquaculture industry suffers from low observability and control of condi-tions in the aquaculture cages.In order to better understand fish behaviour in both normaland stressful conditions,more knowledge of how fish behave is needed.The purpose ofthis project was to use machine learning methods to identify different modes of individualsalmon behaviour with positional data from acoustic telemetry tags.Positional data fromsix different fish from two different cages at two different times of year was processed inorder to create discrete fish swimming trajectories.Additional variables were calculatedbased on positional data:average depth,depth difference per second,track length per sec-ond,angle change per second,average distance from cage center per second and distancemoved in relation to cage center.Every trajectory had one value for each of these vari-ables.These trajectories were analysed based on both traditional methods and principalcomponent analysis,in addition to being clustered with the HDBScan algorithm.In gen-eral,fish were more active at day and swam closer to the surface at night,and this was thecase for every fish except one.Average depth distribution was the variable that differedmost betweeen individuals.The variables that differed the least between individuals werethe two variables based on distance from center,and these did not contribute to the clus-tering.Correlation structure at night was somewhat similar for most fish,as the variablesaverage depth,depth difference,and track length were more correlated at night.Multi-ple modes of behaviour were detected,including feeding,circular swimming,and a thirdmode consisting of idle,non-circular swimming.For most fish,circular swimming was themost prevalent behavioural mode in the day,while short,high angle change,non-circular,idle trajectories close to the surface was the dominating swimming pattern at night.Theresults show that salmon behaviour has definable modes that can be detected from posi-tional data,and that the prevalence of these modes differs from night to day.Moreover,theresults show the potential of the application of machine learning methods in aquaculture.  \nTable of Contents  \nPreface  \ni  \nExecutive summary  \n##### ii\n\nvi  \nList of Tables  \nList of Figures  \n#### X\n\n1 Introduction  \n1  \n1.1 Aquaculture………………………………………………………………………  \n……………………………………1  \n1.1.1 Precision Fish Farming…………………………………………………………………………………1  \n1.2 Individual fish monitoring and Telemetry ……………………………………………………………3  \n1.3 Machine and Statistical learning ……………………………………………………………………………3  \n1.4 Scope of the Project………………………………………………………………………………………………………4  \n2 Theory  \n5  \n2.1 Classification ……………………………………………………………………………………………………………………………………5","cbCaimPMwmFPeInJ","https://ap.wps.com/l/cbCaimPMwmFPeInJ","pdf",12006054,1,118,"English","en",105,"# Preface\n# Executive summary\n# 1 Introduction\n## Aquaculture\n## Individual fish monitoring and Telemetry\n## Machine and Statistical learning\n## Scope of the Project\n# 2 Theory\n## Classification\n### Supervised Classification\n### Unsupervised Classification\n## Unsupervised learning -cluster analysis\n### Non-parametric cluster analysis -K-means\n### Density-based Clustering-DBScan\n### Hierarchical Density-Based clustering-HDBScan\n## PCA-Principal component analysis\n# 3 Method\n## The Dataset\n### Datasets\n## Creating Trajectories\n### Recreating fish path\n### Creating variables\n## Statistical analysis and visualisation\n### Mean and Variance\n### Basic conventional analysis\n### Principal Component analysis\n### HDBScan Clustering\n# 4 Results\n## Mean and Variance\n## Histograms of Variables\n## Scatterplots of variables","[{\"question\":\"What data source is used to identify salmon behaviour in the cages?\",\"answer\":\"The project uses positional data from acoustic telemetry tags, processed to reconstruct discrete swimming trajectories for individual fish.\"},{\"question\":\"How are fish trajectories converted into features for analysis?\",\"answer\":\"Each trajectory is summarized using calculated variables such as average depth, depth change per second, track length per second, angle change per second, average distance from cage center per second, and distance moved relative to the cage center.\"},{\"question\":\"Which analytical approaches and clustering method are employed?\",\"answer\":\"The study combines traditional analysis with principal component analysis, and clusters trajectories using the HDBScan algorithm to detect behavioural patterns.\"}]","Machine learning for identification of individual salmon behaviour in aquaculture - Master's thesis | PDF",1785821107,297,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"machine-learning-for-identification-of-individual-salmon-behaviour-in-aquaculture-masters-thesis","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/machine-learning-for-identification-of-individual-salmon-behaviour-in-aquaculture-masters-thesis/124226/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What data source is used to identify salmon behaviour in the cages?","Question",{"text":75,"@type":76},"The project uses positional data from acoustic telemetry tags, processed to reconstruct discrete swimming trajectories for individual fish.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How are fish trajectories converted into features for analysis?",{"text":80,"@type":76},"Each trajectory is summarized using calculated variables such as average depth, depth change per second, track length per second, angle change per second, average distance from cage center per second, and distance moved relative to the cage center.",{"name":82,"@type":73,"acceptedAnswer":83},"Which analytical approaches and clustering method are employed?",{"text":84,"@type":76},"The study combines traditional analysis with principal component analysis, and clusters trajectories using the HDBScan algorithm to detect behavioural patterns.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]