{"id":{"repo_id":"birmingham","oai_identifier":"oai:etheses.bham.ac.uk:16308"},"canonical_url":"https://search.ndltd.org/etd/birmingham/oai:etheses.bham.ac.uk:16308","repository":{"repo_id":"birmingham","name":"University of Birmingham","base_url":"https://etheses.bham.ac.uk/cgi/oai2"},"display":{"title":"Machine learning enabled intelligent microfluidics for bioparticle detection and monitoring","abstract":"Traditional detection and monitoring methods in environmental and biomedical applications are often centralised, high-cost, and time-consuming, requiring specialised laboratories, complex instruments, and trained personnel. These limitations have been highlighted by recent global challenges such as disease control and environmental issues. The COVID-19 pandemic underscored the urgent need for decentralised, rapid, and accurate diagnostic tools. Additionally, environmental issues like climate change and its effect on public health demand real-time monitoring solutions that are accessible and efficient. Microfluidics, as a multidisciplinary technology, offers significant advantages in developing low-cost, rapid, and portable testing platforms by integrating sample preparation, pretreatment, and detection into compact devices. Despite its potential, traditional microfluidic systems often struggle to fully meet the needs for decentralisation and affordability due to complex fabrication processes and the requirement for supporting analytical equipment. Concurrently, advancements in artificial intelligence, particularly machine learning (ML) and convolutional neural networks (CNNs), have revolutionised data processing and analysis in vision-based applications. Integrating microfluidics with ML, which forms intelligent microfluidics, holds the promise of retaining the benefits of microfluidic data collection while leveraging ML for efficient data analysis, optimisation, and improved detection methods. The thesis presents the development of two innovative platforms. The first is an Automated and Intelligent Microfluidic Platform (AIMP) designed for environmental monitoring, specifically for microalgae detection and analysis. Utilising components with total cost < £170 and a trained ML model, the AIMP demonstrated high accuracy in detecting and classifying various microalgae species, facilitating efficient and decentralised environmental surveillance. The second platform is an Artificial Intelligence-Driven Point-of-Care Testing (AID-POCT) device for biomedical diagnostics. This platform employs magnetic microbeads coated with specific antibodies to capture target cytokines, forming distinct patterns under a magnetic field. By capturing and analysing these patterns using a mobile phone and a deployed ML model, the AID-POCT platform enables rapid and quantitative detection of biomarkers such as interferon-gamma, with demonstrated adaptability to detect other cytokines. By overcoming the limitations of traditional methods, these intelligent microfluidic systems offer accessible, efficient, and accurate diagnostic solutions. The thesis lays the groundwork for the broader adoption of intelligent microfluidics, highlighting its transformative potential in environmental monitoring and healthcare.","abstract_html":"Traditional detection and monitoring methods in environmental and biomedical applications are often centralised, high-cost, and time-consuming, requiring specialised laboratories, complex instruments, and trained personnel. These limitations have been highlighted by recent global challenges such as disease control and environmental issues. The COVID-19 pandemic underscored the urgent need for decentralised, rapid, and accurate diagnostic tools. Additionally, environmental issues like climate change and its effect on public health demand real-time monitoring solutions that are accessible and efficient. Microfluidics, as a multidisciplinary technology, offers significant advantages in developing low-cost, rapid, and portable testing platforms by integrating sample preparation, pretreatment, and detection into compact devices. Despite its potential, traditional microfluidic systems often struggle to fully meet the needs for decentralisation and affordability due to complex fabrication processes and the requirement for supporting analytical equipment. Concurrently, advancements in artificial intelligence, particularly machine learning (ML) and convolutional neural networks (CNNs), have revolutionised data processing and analysis in vision-based applications. Integrating microfluidics with ML, which forms intelligent microfluidics, holds the promise of retaining the benefits of microfluidic data collection while leveraging ML for efficient data analysis, optimisation, and improved detection methods. The thesis presents the development of two innovative platforms. The first is an Automated and Intelligent Microfluidic Platform (AIMP) designed for environmental monitoring, specifically for microalgae detection and analysis. Utilising components with total cost &lt; £170 and a trained ML model, the AIMP demonstrated high accuracy in detecting and classifying various microalgae species, facilitating efficient and decentralised environmental surveillance. The second platform is an Artificial Intelligence-Driven Point-of-Care Testing (AID-POCT) device for biomedical diagnostics. This platform employs magnetic microbeads coated with specific antibodies to capture target cytokines, forming distinct patterns under a magnetic field. By capturing and analysing these patterns using a mobile phone and a deployed ML model, the AID-POCT platform enables rapid and quantitative detection of biomarkers such as interferon-gamma, with demonstrated adaptability to detect other cytokines. By overcoming the limitations of traditional methods, these intelligent microfluidic systems offer accessible, efficient, and accurate diagnostic solutions. The thesis lays the groundwork for the broader adoption of intelligent microfluidics, highlighting its transformative potential in environmental monitoring and healthcare.","abstract_has_math":false,"creators":["Zheng, Jiahao"],"institution":"University of Birmingham","degree_name":"d_ph","degree_level":"d_ph","degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025-07","date_published":"2025-07","updated_at":"2026-11-19T09:33:12Z","subjects":["TA Engineering (General). Civil engineering (General)"],"languages":["eng"],"rights":[],"rights_urls":[],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":null,"outbound_label":null,"outbound_source":null,"record_url":null,"record_label":null,"record_kind":null,"record_source":null,"download_url":"http://etheses.bham.ac.uk//id/eprint/16308/1/Zheng2025PhD.pdf","download_label":"Download PDF","download_source":"dc:identifier.uri","access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://etheses.bham.ac.uk/cgi/oai2?verb=GetRecord&metadataPrefix=uketd_dc&identifier=oai%3Aetheses.bham.ac.uk%3A16308","prefix":"uketd_dc"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.sponsor","label":"Sponsor","values":["na"]},{"key":"dc:creator","label":"Author","values":["Zheng, Jiahao"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2025-07-16"]},{"key":"dc:date.issued","label":"Date","values":["2025-07"]},{"key":"dc:publisher.department","label":"Dc Publisher Department","values":["College of Engineering & Physical Sciences","School of Mechanical Engineering"]},{"key":"dc:publisher.institution","label":"Dc Publisher Institution","values":["University of Birmingham"]},{"key":"dc:relation.isreferencedby","label":"Dc Relation Isreferencedby","values":["http://etheses.bham.ac.uk//id/eprint/16308/"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"dc:type.qualificationlevel","label":"Dc Type Qualificationlevel","values":["d_ph"]},{"key":"dc:type.qualificationname","label":"Dc Type Qualificationname","values":["d_ph"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["TA Engineering (General). Civil engineering (General)"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.dcterms_iso639_2","label":"Language (ISO 639-2)","values":["eng"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["http://etheses.bham.ac.uk//id/eprint/16308/1/Zheng2025PhD.pdf"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Traditional detection and monitoring methods in environmental and biomedical applications are often centralised, high-cost, and time-consuming, requiring specialised laboratories, complex instruments, and trained personnel. These limitations have been highlighted by recent global challenges such as disease control and environmental issues. The COVID-19 pandemic underscored the urgent need for decentralised, rapid, and accurate diagnostic tools. Additionally, environmental issues like climate change and its effect on public health demand real-time monitoring solutions that are accessible and efficient. Microfluidics, as a multidisciplinary technology, offers significant advantages in developing low-cost, rapid, and portable testing platforms by integrating sample preparation, pretreatment, and detection into compact devices. Despite its potential, traditional microfluidic systems often struggle to fully meet the needs for decentralisation and affordability due to complex fabrication processes and the requirement for supporting analytical equipment. Concurrently, advancements in artificial intelligence, particularly machine learning (ML) and convolutional neural networks (CNNs), have revolutionised data processing and analysis in vision-based applications. Integrating microfluidics with ML, which forms intelligent microfluidics, holds the promise of retaining the benefits of microfluidic data collection while leveraging ML for efficient data analysis, optimisation, and improved detection methods. The thesis presents the development of two innovative platforms. The first is an Automated and Intelligent Microfluidic Platform (AIMP) designed for environmental monitoring, specifically for microalgae detection and analysis. Utilising components with total cost < £170 and a trained ML model, the AIMP demonstrated high accuracy in detecting and classifying various microalgae species, facilitating efficient and decentralised environmental surveillance. The second platform is an Artificial Intelligence-Driven Point-of-Care Testing (AID-POCT) device for biomedical diagnostics. This platform employs magnetic microbeads coated with specific antibodies to capture target cytokines, forming distinct patterns under a magnetic field. By capturing and analysing these patterns using a mobile phone and a deployed ML model, the AID-POCT platform enables rapid and quantitative detection of biomarkers such as interferon-gamma, with demonstrated adaptability to detect other cytokines. By overcoming the limitations of traditional methods, these intelligent microfluidic systems offer accessible, efficient, and accurate diagnostic solutions. The thesis lays the groundwork for the broader adoption of intelligent microfluidics, highlighting its transformative potential in environmental monitoring and healthcare."]},{"key":"dc:format","label":"Dc Format","values":["text"]},{"key":"dcterms:accessrights","label":"Dcterms Accessrights","values":["public"]},{"key":"dc:title","label":"Title","values":["Machine learning enabled intelligent microfluidics for bioparticle detection and monitoring"]}]}],"canonical_facts":{"dc:contributor.sponsor":["na"],"dc:creator":["Zheng, Jiahao"],"dc:date":["2025-07-16"],"dc:date.issued":["2025-07"],"dc:description.abstract":["Traditional detection and monitoring methods in environmental and biomedical applications are often centralised, high-cost, and time-consuming, requiring specialised laboratories, complex instruments, and trained personnel. These limitations have been highlighted by recent global challenges such as disease control and environmental issues. The COVID-19 pandemic underscored the urgent need for decentralised, rapid, and accurate diagnostic tools. Additionally, environmental issues like climate change and its effect on public health demand real-time monitoring solutions that are accessible and efficient. Microfluidics, as a multidisciplinary technology, offers significant advantages in developing low-cost, rapid, and portable testing platforms by integrating sample preparation, pretreatment, and detection into compact devices. Despite its potential, traditional microfluidic systems often struggle to fully meet the needs for decentralisation and affordability due to complex fabrication processes and the requirement for supporting analytical equipment. Concurrently, advancements in artificial intelligence, particularly machine learning (ML) and convolutional neural networks (CNNs), have revolutionised data processing and analysis in vision-based applications. Integrating microfluidics with ML, which forms intelligent microfluidics, holds the promise of retaining the benefits of microfluidic data collection while leveraging ML for efficient data analysis, optimisation, and improved detection methods. The thesis presents the development of two innovative platforms. The first is an Automated and Intelligent Microfluidic Platform (AIMP) designed for environmental monitoring, specifically for microalgae detection and analysis. Utilising components with total cost < £170 and a trained ML model, the AIMP demonstrated high accuracy in detecting and classifying various microalgae species, facilitating efficient and decentralised environmental surveillance. The second platform is an Artificial Intelligence-Driven Point-of-Care Testing (AID-POCT) device for biomedical diagnostics. This platform employs magnetic microbeads coated with specific antibodies to capture target cytokines, forming distinct patterns under a magnetic field. By capturing and analysing these patterns using a mobile phone and a deployed ML model, the AID-POCT platform enables rapid and quantitative detection of biomarkers such as interferon-gamma, with demonstrated adaptability to detect other cytokines. By overcoming the limitations of traditional methods, these intelligent microfluidic systems offer accessible, efficient, and accurate diagnostic solutions. The thesis lays the groundwork for the broader adoption of intelligent microfluidics, highlighting its transformative potential in environmental monitoring and healthcare."],"dc:format":["text"],"dc:identifier.uri":["http://etheses.bham.ac.uk//id/eprint/16308/1/Zheng2025PhD.pdf"],"dc:language.dcterms_iso639_2":["eng"],"dc:publisher.department":["College of Engineering & Physical Sciences","School of Mechanical Engineering"],"dc:publisher.institution":["University of Birmingham"],"dc:relation.isreferencedby":["http://etheses.bham.ac.uk//id/eprint/16308/"],"dc:subject":["TA Engineering (General). Civil engineering (General)"],"dcterms:accessrights":["public"],"dc:title":["Machine learning enabled intelligent microfluidics for bioparticle detection and monitoring"],"dc:type":["Thesis"],"dc:type.qualificationlevel":["d_ph"],"dc:type.qualificationname":["d_ph"]},"updated_at":"2026-11-19T09:33:12Z"}