[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-123295-en":3,"doc-seo-123295-105":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},123295,687197207057,"Sage","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","Machine Learning for Conservation - Evaluating Deep Learning and Feature Extraction in Bird Species Classification in New Zealand","Automated classification of bird sounds supports biodiversity monitoring and conservation. Focusing on New Zealand, the study compares feature extraction methods and machine learning models for bird species classification using an audio dataset. Models evaluated include GRU, LSTM recurrent neural networks, ANN, and CNN, with accuracies reported for GRU-MFCC (0.78), LSTM-MFCC (0.91), ANN-MFCC (0.091), and CNN-MFCC (0.997). The best-performing CNN with MFCC is used to motivate a user interface for bird-sound anticipation and identification.","Machine Learning for Conservation: Evaluating Deep Learning and Feature Extraction in Bird Species Classification in New Zealand  \n1st Mahsa Mohaghegh  \nAuckland University of Technology (AUT) Auckland, New Zealand 0000-0003-2228-8300  \n3rd Minh Hoang  \nAuckland University of Technology (AUT) Auckland, New Zealand [tumihoang2002@gmail.com](tumihoang2002@gmail.com)  \n2nd Khaula Alizai  \nAuckland University of Technology (AUT) Auckland, New Zealand [khaulaalizai786@gmail.com](khaulaalizai786@gmail.com)  \n4th Kapil Patel  \nAuckland University of Technology (AUT) Auckland, New Zealand [kappatel408@gmail.com](kappatel408@gmail.com)  \n5th June Lee  \nAuckland University of Technology (AUT) Auckland, New Zealand [ssr2801@autuni.ac.nz](ssr2801@autuni.ac.nz)  \nAbstract—Automated classification of bird sounds plays an important role in monitoring and protecting biodiversity. Recently, similar efforts have been carried out for birds from all over the world, but New Zealand is one that has been overlooked. Hence in this study, we will be comparing feature extraction methods and machine learning models using a dataset that primarily contains bird species from New Zealand. Machine learning models such as Gated Recurrent Unit (GRU), Long Short-term Memory (LSTM) Recurrent Neural Network, Artificial Neural Network (ANN), and Convolution Neural Network (CNN) were used for audio classification. The accuracies achieved from the training of these models resulted in GRU-MFCC with 0.78, LSTM-MFCC with 0.91, ANN-MFCC with 0.091, and CNN-MFCC with 0.997 accuracy respectively. In order to design a user interface that can anticipate bird sounds and identify them appropriately, we employed our highest-performing model, CNN, with MFCC acting as the extractor.  \nIndex Terms—audio classification, feature extraction, accuracy, models, machine learning, user interface, predict  \nI. INTRODUCTION  \nBirds play an important role in maintaining a balanced ecosystem by removing pests and acting as pollinators. New Zealand, known for its unique avian biodiversity, could particularly benefit from such innovative conservation efforts. With the decreasing number of species of birds [3], it is vital to monitor the avian population in New Zealand to prevent them from becoming extinct such as birds from the flightless family as they can be extinct due to lurking predators around. While manual methods can be used to keep an eye on bird numbers, this may be time-consuming and expensive. However, automated methods combining acoustic sensors and automated bird categorization algorithms may be utilized to  \nquickly and efficiently assess a species’ conservation status with minimal human input and expertise.  \nBirds utilize sound for a number of functions, including creating territories for male birds, attracting a partner formating, responding to their surroundings, and determining whether or not there is a threat. Previously, ornithologists, who are experts in bird sound, would identify bird cries and record and report on the birds found in different locations. However, it is becoming more and more difficult to find ornithologists for the manual classification of birds. Another issue is that with every passing generation of ornithologists, the amount of knowledge passed to the next generation is waning resulting in loss of valuable expertise [4] . Therefore, it is vital to be able to store and train artificial intelligence to be able to recognize the different bird species and help maintain the species conservation status. As a result, manual classification of birds is becoming increasingly undesirable, and there is a trend towards automation rather than manual classification. In order to maintain our ecology and prevent a drop in the number of birds and bird species, Machine Learning and Deep Learning Models are trained with bird sound data to apply the classification of bird calls.  \nIn this study, data is gathered, segmented, and cleaned utilizing Audacity software in orde","cbCaibbsRzbsoFlb","https://ap.wps.com/l/cbCaibbsRzbsoFlb","pdf",423904,1,6,"English","en",105,"# Abstract\n# Introduction\n# Literature Survey","[{\"question\":\"Why is automated bird-sound classification important for conservation in New Zealand?\",\"answer\":\"New Zealand has unique avian biodiversity, and bird populations can decline due to factors like predators and reduced expertise in manual monitoring. Automated acoustic monitoring can assess conservation status with less human input.\"},{\"question\":\"Which machine learning and deep learning models were evaluated, and what were the reported accuracies?\",\"answer\":\"The study evaluates GRU, LSTM, ANN, and CNN using MFCC features. Reported accuracies are GRU-MFCC 0.78, LSTM-MFCC 0.91, ANN-MFCC 0.091, and CNN-MFCC 0.997.\"},{\"question\":\"How were the dataset and features prepared before training and testing?\",\"answer\":\"The data was gathered, segmented, and cleaned using Audacity. Augmentation and oversampling techniques, including SMOTE, were used to balance and supplement the dataset to reduce overfitting and underfitting.\"}]","Machine Learning for Conservation - Evaluating Deep Learning and Feature Extraction in Bird Species Classification in New Zealand | PDF",1785815793,15,{"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-conservation-evaluating-deep-learning-and-feature-extraction-in-bird-species-classification-in-new-zealand","",{"@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-conservation-evaluating-deep-learning-and-feature-extraction-in-bird-species-classification-in-new-zealand/123295/",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},"Why is automated bird-sound classification important for conservation in New Zealand?","Question",{"text":75,"@type":76},"New Zealand has unique avian biodiversity, and bird populations can decline due to factors like predators and reduced expertise in manual monitoring. Automated acoustic monitoring can assess conservation status with less human input.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which machine learning and deep learning models were evaluated, and what were the reported accuracies?",{"text":80,"@type":76},"The study evaluates GRU, LSTM, ANN, and CNN using MFCC features. Reported accuracies are GRU-MFCC 0.78, LSTM-MFCC 0.91, ANN-MFCC 0.091, and CNN-MFCC 0.997.",{"name":82,"@type":73,"acceptedAnswer":83},"How were the dataset and features prepared before training and testing?",{"text":84,"@type":76},"The data was gathered, segmented, and cleaned using Audacity. Augmentation and oversampling techniques, including SMOTE, were used to balance and supplement the dataset to reduce overfitting and underfitting.","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},[93,97,101,105,110,114,119,122,127,130,134],{"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":21,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]