[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-125266-en":3,"doc-seo-125266-105":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},125266,687197207057,"Sage","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","Machine Learning Based Calibration Techniques for Low-Cost Air Quality Sensors - Doctor of Philosophy Thesis","Breathable air is fundamental for life, yet polluted urban air containing particulate matter and harmful gases creates significant health and environmental risks. Ambient air monitoring supports public health awareness and sustainable city planning, but conventional stations are limited by cost and size, restricting spatial resolution. Low-cost sensor technologies enable high spatio-temporal monitoring, though their readings require calibration for accuracy. This thesis develops and benchmarks machine learning-based calibration techniques for low-cost ambient gas sensors using rigorous training, validation, and testing. Results show 1DCNN and GBR deliver consistently accurate performance, and additional covariates such as deployment duration and time of day substantially improve calibration accuracy.","Copyright is owned by the Author of the thesis. Permission is given fora copy to be downloaded by an individual for the purpose of research and private study only. The thesis may not be reproduced elsewhere without the permission of the Author.  \nMachine Learning Based Calibration Techniques for Low-Cost Air Quality Sensors  \nMohammad Sharafat Ali  \nElectronic and Computer Engineering Massey University  \nThesis  \nFor  \nDoctor of Philosophy  \nACKNOWLEDGEMENT  \nFirst and foremost, I convey my deepest gratitude to the Almighty, the most merciful and gracious, for giving me the guidance, patience, knowledge, and determination to complete this research. This thesis is the result of the work where many people have accompanied and supported me. I now have the opportunity to express my gratitude to all of them. I want to convey my sincerest gratitude, regards and thanks to my supervisors, Professor Fakhrul Alam, Dr. Khalid Arif and Professor Johan Potgieter, for their support and guidance. I am especially indebted to Professor Alam whose mentorship has been instrumental throughout this doctoral study. As my supervisor, he has taught me more than I could ever give him credit for. It was my great pleasure to be a part of the Department of Mechanical and Electrical Engineering, School of Food and Advanced Technology and Massey University. I am also grateful for the financial support in the form of a doctoral scholarship offered by the New Zealand Product Accelerator (NZPA) . I thank Auckland Council and National Institute of Water and Atmospheric Research (NIWA) for their support, as well as all the members of the CAIRNet team for their assistance with the sensor development. I would also like to thank all my fellow researchers, faculty members and administrators for their heartiest cooperation. I also acknowledge Dr. Nasim Ahmed and Dr. Daniel Konings for their valuable time and suggestions. I thank De Vito et al. and Liang et al. for making their research data available for this study. Finally, I thank my family for always being there as an inspiration and for their continuous support and encouragement throughout all my studies and work. My late father Dr. Maksud Ali, who was an excellent researcher in his own right, is andwill always be my inspiration. I want to thank my mother, Shirin Ahmed, whose love, wisdom, and guidance are with me in whatever I pursue. Most importantly, I wish to thank my loving and supportive wife, Fatima Zohora, for providing me with unending inspiration in the pursuit of this doctoral study.  \nABSTRACT  \nBreathable air is the single most essential element for life on earth. Polluted air, contaminated by particulate matter and harmful gases, poses numerous risks to health and the environment, especially in urban areas with large populations and many active sources of air pollution. Therefore, researchers from a wide range of disciplines have been working on mitigating the impact of air pollution. Monitoring ambient air pollution is oneof the means to ensure public health safety, raise public awareness and build a sustainable urban environment. However, conventional air quality monitoring stations are mostly confined to a few locations due to their costly equipment and large sizes. As a result, although these monitoring stations provide accurate air pollution data, they can only offera low-fidelity picture of air quality in a large city, leading to a poor spatial resolution of urban pollution data. Low-cost sensor (LCS) technologies aim to address this challenge and intend to make it possible to monitor air quality at a high spatio-temporal resolution. The pollutant data captured by these LCSs are less accurate than their conventional counterparts and thus require calibration techniques to improve their accuracy and reliability. Researchers have proposed different calibration methods and techniques to improve the accuracy ofthe LCSs, including machine learning based calibration models. This thesis investigates ","cbCaiaaUNQK8KvTG","https://ap.wps.com/l/cbCaiaaUNQK8KvTG","pdf",11971180,1,183,"English","en",105,"# Acknowledgement\n# Abstract\n# Table of Contents\n# List of Tables\n# List of Figures\n# List of Abbreviations\n# Chapter 1 Introduction\n## Introduction\n## Problem Statement\n## Scope of Work\n## Organization of the Report\n# Chapter 2 Literature Review\n## Air Pollutants\n## Air Pollutant Concentration Measurement Units\n## Low-Cost Sensors (LCS)\n## Sensor Calibration\n# Chapter 3 Methodology\n## Dataset Utilized\n## Dataset Description\n## Dataset Cleaning\n## Feature Scaling\n## Calibration Process","[{\"question\":\"Why do low-cost air quality sensors need calibration?\",\"answer\":\"Low-cost sensors provide less accurate pollutant data than conventional monitoring stations, so calibration is required to improve accuracy and reliability.\"},{\"question\":\"Which machine learning models are shown to perform consistently well in the thesis?\",\"answer\":\"The thesis reports consistently accurate calibration performance from a 1DCNN (One Dimensional Convolutional Neural Network) and a GBR (Gradient Boosting Regression) model.\"},{\"question\":\"How do additional covariates improve calibration accuracy?\",\"answer\":\"Using readily available covariates that were not previously emphasized—such as the number of days the sensor has been deployed and the time of day of the reading—significantly improves calibration accuracy.\"}]","Machine Learning Based Calibration Techniques for Low-Cost Air Quality Sensors - Doctor of Philosophy Thesis | PDF",1785897804,461,{"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-based-calibration-techniques-for-low-cost-air-quality-sensors-doctor-of-philosophy-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-based-calibration-techniques-for-low-cost-air-quality-sensors-doctor-of-philosophy-thesis/125266/",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","2026-08-05",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 do low-cost air quality sensors need calibration?","Question",{"text":75,"@type":76},"Low-cost sensors provide less accurate pollutant data than conventional monitoring stations, so calibration is required to improve accuracy and reliability.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which machine learning models are shown to perform consistently well in the thesis?",{"text":80,"@type":76},"The thesis reports consistently accurate calibration performance from a 1DCNN (One Dimensional Convolutional Neural Network) and a GBR (Gradient Boosting Regression) model.",{"name":82,"@type":73,"acceptedAnswer":83},"How do additional covariates improve calibration accuracy?",{"text":84,"@type":76},"Using readily available covariates that were not previously emphasized—such as the number of days the sensor has been deployed and the time of day of the reading—significantly improves calibration accuracy.","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"]