A Portable System to Sort, Detect, and Classify Microplastics

dc.contributorHuang, Qiang
dc.contributorSong, Aijun
dc.contributor.advisorCheng, Mark
dc.contributor.authorSmith, Warren
dc.date.accessioned2023-08-03T18:43:15Z
dc.date.available2023-08-03T18:43:15Z
dc.date.issued2023
dc.descriptionElectronic Thesis or Dissertationen_US
dc.description.abstractThe mass pollution of plastics in the world is having a detrimental impact on both marine biology and human health. While there are efforts to clean and analyze plastics with the help of the community, these plastics often break down into smaller particles referred as microplastics, which are more difficult to study and remove. Numerous studies are coming out with the attempt to detect and identify these microplastics with hopes for future improvements to reduce this global hazard. However, a main issue with current research is the lack of standardization in the testing and sampling of microplastics. Most studies involve collecting samples from different bodies of water and then transporting them to a laboratory for treatment, filtering, and examination using various methods to classify the type of plastic and gather information about its size and quantity. This process can take a large amount of time and is separated primarily into stages: sampling, treatment, classification, and detection. This thesis will explore different research techniques that incorporate some of these stages and proposes a portable system that can sort particles using mechanical filtration, detect particles using the You Only Look Once (YOLO) convolutional neural network, and classify particles using Raman spectroscopy. The system will be deployed in the field with a focus in reducing the amount of time and labor involved with the process of microplastic analysis by combining techniques into one system. The project that will be presented in this thesis is a work in progress and research is still being implemented and advanced within the current system. Possible improvements are addressed for future students to expand on. The goal of this work is to lay a foundation for a sustainable, versatile system for use in various environments and over extended periods of time. This thesis will present a literature review on the current work being done in the field as well as the techniques used, and each individual part of the current deployed system will be explained.en_US
dc.format.mediumelectronic
dc.format.mimetypeapplication/pdf
dc.identifier.otherhttp://purl.lib.ua.edu/187921
dc.identifier.otheru0015_0000001_0004743
dc.identifier.otherSmith_alatus_0004M_15217
dc.identifier.urihttps://ir.ua.edu/handle/123456789/10556
dc.languageEnglish
dc.language.isoen_US
dc.publisherUniversity of Alabama Libraries
dc.relation.haspartSupplemental file includes a powerpoint presentation of the thesis defense.
dc.relation.hasversionborn digital
dc.relation.ispartofThe University of Alabama Electronic Theses and Dissertations
dc.relation.ispartofThe University of Alabama Libraries Digital Collections
dc.rightsAll rights reserved by the author unless otherwise indicated.
dc.subjectComputer Vision
dc.subjectMicroplastic
dc.subjectObject Detection
dc.subjectPlastic
dc.subjectRaman Spectroscopy
dc.subjectYOLO
dc.titleA Portable System to Sort, Detect, and Classify Microplasticsen_US
dc.typethesis
dc.typetext
etdms.degree.departmentUniversity of Alabama. Department of Educational Leadership, Policy, and Technology Studies
etdms.degree.disciplineElectrical engineering
etdms.degree.grantorThe University of Alabama
etdms.degree.levelmaster's
etdms.degree.nameM.S.
Files
Original bundle
Now showing 1 - 2 of 2
Loading...
Thumbnail Image
Name:
u0015_0000001_0004743.pdf
Size:
3.28 MB
Format:
Adobe Portable Document Format
No Thumbnail Available
Name:
u0015_0000001_0004743_0001.pptx
Size:
337.62 MB
Format:
Microsoft Powerpoint XML