[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-128354-en":3,"doc-seo-128354-105":31,"detail-sidebar-cat-0-en-105":92},{"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":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},128354,962085571259,"Theodora","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","Predicting Avian Influenza Outbreaks - Machine Learning and Neural Network approaches to anomalous mortality detection","Avian Influenza (AI) poses a major global threat due to its rapid spread and severe impacts on animal and public health. In Italy, recurring highly pathogenic avian influenza outbreaks have produced substantial economic losses in the poultry sector, underscoring the need for earlier monitoring and prevention. Current surveillance is often retrospective and reactive, reducing timeliness. This thesis builds machine learning models that use epidemiological, environmental, and biosecurity data to detect anomalous mortality patterns linked to AI outbreaks. It also outlines a structured real-time framework for veterinary authorities and farm operators.","University of Padova  \nDepartment of Mathematics “Tullio Levi-Civita”  \nMaster Thesis in Data Science  \nPredicting Avian Influenza Outbreaks:  \nMachine Learning and Neural Network  \napproaches to anomalous mortality  \ndetection  \nSupervisor Master Candidate  \nProf. Alessandro Sperduti Matteo Mazzucato  \nUniversity of Padova  \nCo-supervisor Student ID  \nDr. Paolo Mulatti 2019054  \nIstituto Zooprofilattico Sperimentale delle Venezie  \nAcademic Year  \n2024-2025  \nii  \niv  \nAbstract  \nAvian Influenza (AI) represents a critical global challenge due to its rapid spread and severe consequences for both animal and public health. In Italy, recurring outbreaks of highly pathogenic avian influenza (HPAI) have led to significant economic losses in the poultry industry, highlighting the urgent need for effective monitoring and prevention strategies.  \nCurrent surveillance systems primarily rely on retrospective analysis and reactive interventions, limiting the ability to predict outbreaks in a timely manner. This study aims to bridge this gap by leveraging Machine Learning models to predict AI outbreaks based on epidemiological, environmental, and biosecurity data.  \nA series of ML models, including One-Class Support Vector Machine, Isolation Forest, Random Forest, eXetreme Gradient Boosting, and Neural Networks, were trained to identify anomalous mortality patterns potentially indicative of AI outbreak that can be considered as first step for enhancing early detection capabilities.  \nFurthermore, this research proposes a structured framework for an integrated system that could be deployed in a real-time fashion to support veterinary authorities and farm operators in taking timely preventive actions.  \nvi  \nContents  \nAbstract v  \nList of figures ix  \nList of tables xiii  \nList of acronyms xv  \n1 Introduction 1  \n1. 1 General context . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1  \n1. 1. 1 Avian Influenza . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1  \n1.1.2 Avian Influenza in Italy ........................ 2  \n1.1.3 Istituto Zooprofilattico Sperimentale delle Venezie .......... 4  \n1.2 Gap of knowledge ............................... 5  \n1.3 Objectives ................................... 6  \n1.4 Summary of results .............................. 7  \n2 Technical Background 9  \n2.1 Original dataset and other useful data ..................... 10  \n2.1.1 Mortality-original dataset ...................... 10  \n2.1.2 Environmental data . . . . . . . . . . . . . . . . . . . . . . . . . . 11  \n2.1.3 Biosecurity .............................. 13  \n2.1.4 Other data .............................. 14  \n2.1.5 Wild birds .............................. 15  \n2.1.6 Symptoms derived from Epidemiological Investgation ........ 15  \n2.2 Overview of the applied Algorithms ...................... 16  \n2.2.1 Anomaly detection .......................... 16  \n2.2.2 Decision Tree models ......................... 19  \n2.2.3 Neural Networks ........................... 22  \n2.3 Other important aspects ............................ 23  \n3 Data acquisition and preparation 25  \n3.1 Data integration ................................ 25  \n3.1.1 Farm registry and production ..................... 26  \n3.1.2 Environmental data .......................... 26  \n3.1.3 Biosecurity data ............................ 29  \n3.1.4 Other data from private companies .................. 30  \n3.1.5 Wild birds data ............................ 30  \n3.1.6 Symptoms derived from Epidemiological Investigation ........ 31  \n3.1.7 Additional derived data ........................ 32  \n3.2 Descriptive analysis .............................. 34  \n3.3 Data preparation ............................... 48  \n3.3.1 Data splitting ............................. 48  \n3.3.2 Data re-balancing strategies ...................... 51  \n3.3.3 Features selection ........................... 52  \n4 Models implementation and Results 55  \n4.1 Anomaly detection .............................. 55  \n4","cbCaipFNa0cmqkXU","https://ap.wps.com/l/cbCaipFNa0cmqkXU","pdf",8285615,3,1,141,"English","en",105,"# Abstract\n# Contents\n## List of figures\n## List of tables\n## List of acronyms\n# 1 Introduction\n## 1.1 General context\n## 1.2 Gap of knowledge\n## 1.3 Objectives\n## 1.4 Summary of results\n# 2 Technical Background\n## 2.1 Original dataset and other useful data\n## 2.2 Overview of the applied Algorithms\n## 2.3 Other important aspects\n# 3 Data acquisition and preparation\n## 3.1 Data integration\n## 3.2 Descriptive analysis\n## 3.3 Data preparation\n# 4 Models implementation and Results\n## 4.1 Anomaly detection\n## 4.2 Decision Tree models\n## 4.3 Neural Networks\n## 4.4 Models consensus and ensemble\n## 4.5 Temporal comparisons\n## 4.6 Implementation aspects\n# 5 Proposed framework for a real-time system\n## 5.1 Data acquisition\n## 5.2 Models prediction\n## 5.3 Models prediction\n## 5.4 Models evaluation\n# 6 Discussion and Conclusions\n## 6.1 Synopsis of the study\n## 6.2 Discussion of results\n## 6.3 Practical Implications\n## 6.4 Methodological limitations\n## 6.5 Future directions\n# References\n# Acknowledgments","[{\"question\":\"Why is early prediction of avian influenza outbreaks important in Italy?\",\"answer\":\"Recurring highly pathogenic avian influenza outbreaks in Italy cause major economic losses in poultry and create urgent needs for effective monitoring and prevention. Reactive, retrospective surveillance limits timely outbreak anticipation.\"},{\"question\":\"Which data sources are used to predict anomalous avian influenza-related mortality?\",\"answer\":\"The study leverages epidemiological, environmental, and biosecurity information, including farm registry and production data, environmental variables, biosecurity records, wild-bird data, and symptom-derived variables from epidemiological investigation.\"},{\"question\":\"How do the proposed machine learning models detect potential AI outbreaks?\",\"answer\":\"Multiple models—such as One-Class Support Vector Machine, Isolation Forest, Random Forest, eXtreme Gradient Boosting, and Neural Networks—are trained to identify anomalous mortality patterns that may indicate an avian influenza outbreak.\"}]","Predicting Avian Influenza Outbreaks - Machine Learning and Neural Network approaches to anomalous mortality detection | PDF",1785947026,355,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":29},"predicting-avian-influenza-outbreaks-machine-learning-and-neural-network-approaches-to-anomalous-mortality-detection","",{"@graph":37,"@context":86},[38,54,69],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,49,51],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":48},"https://docshare.wps.com/document/","Document",2,{"item":50,"name":12,"@type":44,"position":20},"https://docshare.wps.com/document/research-report/",{"item":52,"name":13,"@type":44,"position":53},"https://docshare.wps.com/document/predicting-avian-influenza-outbreaks-machine-learning-and-neural-network-approaches-to-anomalous-mortality-detection/128354/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":42,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-26","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"Why is early prediction of avian influenza outbreaks important in Italy?","Question",{"text":76,"@type":77},"Recurring highly pathogenic avian influenza outbreaks in Italy cause major economic losses in poultry and create urgent needs for effective monitoring and prevention. Reactive, retrospective surveillance limits timely outbreak anticipation.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"Which data sources are used to predict anomalous avian influenza-related mortality?",{"text":81,"@type":77},"The study leverages epidemiological, environmental, and biosecurity information, including farm registry and production data, environmental variables, biosecurity records, wild-bird data, and symptom-derived variables from epidemiological investigation.",{"name":83,"@type":74,"acceptedAnswer":84},"How do the proposed machine learning models detect potential AI outbreaks?",{"text":85,"@type":77},"Multiple models—such as One-Class Support Vector Machine, Isolation Forest, Random Forest, eXtreme Gradient Boosting, and Neural Networks—are trained to identify anomalous mortality patterns that may indicate an avian influenza outbreak.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":48,"doc_module":4,"doc_module_name":47,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":47,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":47,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":47,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":47,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":47,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":47,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":47,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":47,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]