Näytä suppeat kuvailutiedot

dc.contributor.authorSaarela, Mirka
dc.contributor.authorPodgorelec, Vili
dc.date.accessioned2024-10-23T10:16:43Z
dc.date.available2024-10-23T10:16:43Z
dc.date.issued2024
dc.identifier.citationSaarela, M., & Podgorelec, V. (2024). Recent Applications of Explainable AI (XAI) : A Systematic Literature Review. <i>Applied Sciences</i>, <i>14</i>(19), Article 8884. <a href="https://doi.org/10.3390/app14198884" target="_blank">https://doi.org/10.3390/app14198884</a>
dc.identifier.otherCONVID_243309382
dc.identifier.urihttps://jyx.jyu.fi/handle/123456789/97638
dc.description.abstractThis systematic literature review employs the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) methodology to investigate recent applications of explainable AI (XAI) over the past three years. From an initial pool of 664 articles identified through the Web of Science database, 512 peer-reviewed journal articles met the inclusion criteria—namely, being recent, high-quality XAI application articles published in English—and were analyzed in detail. Both qualitative and quantitative statistical techniques were used to analyze the identified articles: qualitatively by summarizing the characteristics of the included studies based on predefined codes, and quantitatively through statistical analysis of the data. These articles were categorized according to their application domains, techniques, and evaluation methods. Health-related applications were particularly prevalent, with a strong focus on cancer diagnosis, COVID-19 management, and medical imaging. Other significant areas of application included environmental and agricultural management, industrial optimization, cybersecurity, finance, transportation, and entertainment. Additionally, emerging applications in law, education, and social care highlight XAI’s expanding impact. The review reveals a predominant use of local explanation methods, particularly SHAP and LIME, with SHAP being favored for its stability and mathematical guarantees. However, a critical gap in the evaluation of XAI results is identified, as most studies rely on anecdotal evidence or expert opinion rather than robust quantitative metrics. This underscores the urgent need for standardized evaluation frameworks to ensure the reliability and effectiveness of XAI applications. Future research should focus on developing comprehensive evaluation standards and improving the interpretability and stability of explanations. These advancements are essential for addressing the diverse demands of various application domains while ensuring trust and transparency in AI systems.en
dc.format.mimetypeapplication/pdf
dc.language.isoeng
dc.publisherMDPI
dc.relation.ispartofseriesApplied Sciences
dc.rightsCC BY 4.0
dc.subject.otherexplainable artificial intelligence
dc.subject.otherapplications
dc.subject.otherinterpretable machine learning
dc.subject.otherconvolutional neural network
dc.subject.otherdeep learning
dc.subject.otherpost-hoc explanations
dc.subject.othermodel-agnostic explanations
dc.titleRecent Applications of Explainable AI (XAI) : A Systematic Literature Review
dc.typearticle
dc.identifier.urnURN:NBN:fi:jyu-202410236495
dc.contributor.laitosInformaatioteknologian tiedekuntafi
dc.contributor.laitosFaculty of Information Technologyen
dc.type.urihttp://purl.org/eprint/type/JournalArticle
dc.type.coarhttp://purl.org/coar/resource_type/c_dcae04bc
dc.description.reviewstatuspeerReviewed
dc.relation.issn2076-3417
dc.relation.numberinseries19
dc.relation.volume14
dc.type.versionpublishedVersion
dc.rights.copyright© 2024 by the authors. Licensee MDPI, Basel, Switzerland
dc.rights.accesslevelopenAccessfi
dc.relation.grantnumber356314
dc.subject.ysosovellusohjelmat
dc.subject.ysosyväoppiminen
dc.subject.ysotekoäly
dc.subject.ysoneuroverkot
dc.subject.ysoohjelmistokehitys
dc.subject.ysokoneoppiminen
dc.subject.ysoarviointimenetelmät
dc.subject.ysosystemaattiset kirjallisuuskatsaukset
dc.format.contentfulltext
jyx.subject.urihttp://www.yso.fi/onto/yso/p8456
jyx.subject.urihttp://www.yso.fi/onto/yso/p39324
jyx.subject.urihttp://www.yso.fi/onto/yso/p2616
jyx.subject.urihttp://www.yso.fi/onto/yso/p7292
jyx.subject.urihttp://www.yso.fi/onto/yso/p21530
jyx.subject.urihttp://www.yso.fi/onto/yso/p21846
jyx.subject.urihttp://www.yso.fi/onto/yso/p15768
jyx.subject.urihttp://www.yso.fi/onto/yso/p29683
dc.rights.urlhttps://creativecommons.org/licenses/by/4.0/
dc.relation.doi10.3390/app14198884
dc.relation.funderResearch Council of Finlanden
dc.relation.funderSuomen Akatemiafi
jyx.fundingprogramAcademy Research Fellow, AoFen
jyx.fundingprogramAkatemiatutkija, SAfi
jyx.fundinginformationThe work by M.S. was supported by the K.H. Renlund Foundation and the Academy of Finland (project no. 356314). The work by V.P. was supported by the Slovenian Research Agency (Research Core Funding No. P2-0057).
dc.type.okmA2


Aineistoon kuuluvat tiedostot

Thumbnail

Aineisto kuuluu seuraaviin kokoelmiin

Näytä suppeat kuvailutiedot

CC BY 4.0
Ellei muuten mainita, aineiston lisenssi on CC BY 4.0