Vis enkel innførsel

dc.contributor.advisorBatalden, Bjørn-Morten
dc.contributor.authorXue, Hui
dc.date.accessioned2023-09-19T08:54:51Z
dc.date.available2023-09-19T08:54:51Z
dc.date.issued2023-10-04
dc.description.abstractMaritime safety is a critical concern due to the potential for serious consequences or accidents for the crew, passengers, environment, and assets resulting from navigation errors or unsafe acts. Traditional training methods face challenges in the rapidly evolving maritime industry, and innovative training methods are being explored. This study explores the use of wearable sensors with biosignal data collection to improve training performance in the maritime sector. Three experiments were conducted progressively to investigate the relationship between navigators' experience levels and biosignal data results, the effects of different training methods on cognitive workload, trainees' stress levels, and their decision-making skills, and the classification of scenario complexity and the biosignal data obtained by the trainees. questionnaire data on stress levels, workload, and user satisfaction of auxiliary training equipment; performance evaluation data on navigational abilities, decision-making skills, and ship-handling abilities; and biosignal data, including electrodermal activity (EDA), body temperature, blood volume pulse (BVP), inter-beat interval (IBI), and heart rate (HR). Several statistical methods and machine-learning algorithms were used in the data analysis. The present dissertation contributes to the advancement of the field of maritime education and training by exploring methods for enhancing learning in complex situations. The use of biosignal data provides insights into the interplay between stress levels and training outcomes in the maritime industry. The proposed conceptual training model underscores the relationship between trainees' stress and safety factors and offers a framework for the development and evaluation of advanced biosignal data-based training systems.en_US
dc.description.doctoraltypeph.d.en_US
dc.description.popularabstractEnsuring maritime safety is critical, and having competent officers is beneficial for preventing accidents. Traditional training methods are becoming insufficient due to the rapidly evolving maritime industry, and innovative training methods are being explored. In this study, wearable sensors with biosignal data collection were explored to improve training performance in the maritime sector. Three experiments were conducted progressively to investigate the relationship between navigators' experience levels and biosignal data results, the effects of different training methods on cognitive workload, trainees' stress levels, and their decision-making skills, and the classification of scenario complexity and the biosignal data obtained by the trainees. Data were collected through questionnaires, performance evaluation, and biosignal data. Several statistical methods and machine-learning algorithms were used in the data analysis. The study found that biosignal data effectively gauge trainees’ stress levels, classify the complexity of training scenarios, and determine seafarers' experience levels, which influences safety and performance outcomes. The results highlight the importance of incorporating biosignal data into maritime training programs. The study proposes a conceptual training model that offers a framework for developing and evaluating advanced biosignal data-based training systems. The research contributes to the advancement of the field of maritime education and training by exploring methods for enhancing learning in complex situations.en_US
dc.description.sponsorshipThe PhD project fund from ITS, NT. The a grant from the publication fund of UiT.en_US
dc.identifier.isbn978-82-8236-535-2 pdf
dc.identifier.isbn978-82-8236-534-5 print
dc.identifier.urihttps://hdl.handle.net/10037/31091
dc.language.isoengen_US
dc.publisherUiT Norges arktiske universiteten_US
dc.publisherUiT The Arctic University of Norwayen_US
dc.relation.haspart<p>Paper I: Xue, H., Sharma, P. & Wild, F. (2019). User satisfaction in augmented reality-based training using Microsoft HoloLens. <i>Computers, 8</i>(1), 9. Also available in Munin at <a href=https://hdl.handle.net/10037/16162>https://hdl.handle.net/10037/16162</a>. <p>Paper II: Xue, H., Batalden, B.-M. & Røds, J.-F. (2020). Development of a SAGAT query and simulator experiment to measure situation awareness in maritime navigation. In Stanton, N. (Ed.), <i>Advances in Human Aspects of Transportation, AHFE 2020, Advances in Intelligent Systems and Computing, vol. 1212</i>. Springer, Cham. Also available at <a href=https://doi.org/10.1007/978-3-030-50943-9_59>https://doi.org/10.1007/978-3-030-50943-9_59</a>. <p>Paper III: Xue, H., Batalden, B.-M., Sharma, P., Johansen, J.A. & Prasad, D.K. (2021). Biosignals based driving skill classification using machine learning: A case study of maritime navigation. <i>Applied Sciences, 11</i>(20), 9765. Also available in Munin at <a href=https://hdl.handle.net/10037/23078>https://hdl.handle.net/10037/23078</a> <p>Paper IV: Xue, H., Røds, J.F., Haugseggen, Ø., Christensen, A.J., Batalden, B.-M. & Gudmestad, O.T. A study on the effects of rapid training method on ship handling, navigation and decision-making skills under stressful situations. (Submitted manuscript). <p>Paper V: Xue, H., Haugseggen, Ø., Røds, J.-F., Batalden, B.-M. & Prasad, D.K. Assessment of stress levels based on biosignal during the simulator-based maritime navigation training and its impact on sailing performance. (Submitted manuscript).en_US
dc.rights.accessRightsopenAccessen_US
dc.rights.holderCopyright 2023 The Author(s)
dc.rights.urihttps://creativecommons.org/licenses/by-nc-sa/4.0en_US
dc.rightsAttribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)en_US
dc.subjectVDP::Mathematics and natural science: 400::Information and communication science: 420::Mathematical modeling and numerical methods: 427en_US
dc.subjectVDP::Matematikk og Naturvitenskap: 400::Informasjons- og kommunikasjonsvitenskap: 420::Matematisk modellering og numeriske metoder: 427en_US
dc.subjectVDP::Matematikk og Naturvitenskap: 400::Informasjons- og kommunikasjonsvitenskap: 420::Simulering, visualisering, signalbehandling, bildeanalyse: 429en_US
dc.subjectVDP::Mathematics and natural science: 400::Information and communication science: 420::Simulation, visualization, signal processing, image processing: 429en_US
dc.subjectnull::null::null::nullen_US
dc.subjectVDP::Technology: 500::Marine technology: 580::Other marine technology: 589en_US
dc.titleMethods for enhanced learning using wearable technologies. A study of the maritime sectoren_US
dc.typeDoctoral thesisen_US
dc.typeDoktorgradsavhandlingen_US


Tilhørende fil(er)

Thumbnail
Thumbnail

Denne innførselen finnes i følgende samling(er)

Vis enkel innførsel

Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)
Med mindre det står noe annet, er denne innførselens lisens beskrevet som Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)