تقرير
A Semi-Automated Solution Approach Selection Tool for Any Use Case via Scopus and OpenAI:a Case Study for AI/ML in Oncology
العنوان: | A Semi-Automated Solution Approach Selection Tool for Any Use Case via Scopus and OpenAI:a Case Study for AI/ML in Oncology |
---|---|
المؤلفون: | Kılıç, Deniz Kenan, Vasegaard, Alex Elkjær, Desoeuvres, Aurélien, Nielsen, Peter |
المصدر: | Kılıç , D K , Vasegaard , A E , Desoeuvres , A & Nielsen , P 2023 ' A Semi-Automated Solution Approach Selection Tool for Any Use Case via Scopus and OpenAI : a Case Study for AI/ML in Oncology ' arXiv . https://doi.org/10.48550/arXiv.2307.04573Test |
بيانات النشر: | arXiv |
سنة النشر: | 2023 |
المجموعة: | Aalborg University (AAU): Publications / Aalborg Universitet: Publikationer |
مصطلحات موضوعية: | cs.AI, cs.IR, cs.LG |
الوصف: | In today's vast literature landscape, a manual review is very time-consuming. To address this challenge, this paper proposes a semi-automated tool for solution method review and selection. It caters to researchers, practitioners, and decision-makers while serving as a benchmark for future work. The tool comprises three modules: (1) paper selection and scoring, using a keyword selection scheme to query Scopus API and compute relevancy; (2) solution method extraction in papers utilizing OpenAI API; (3) sensitivity analysis and post-analyzes. It reveals trends, relevant papers, and methods. AI in the oncology case study and several use cases are presented with promising results, comparing the tool to manual ground truth. |
نوع الوثيقة: | report |
وصف الملف: | application/pdf |
اللغة: | English |
العلاقة: | https://vbn.aau.dk/da/publications/f997799d-a060-4413-851f-e20e0f21f7caTest |
DOI: | 10.48550/arXiv.2307.04573 |
الإتاحة: | https://doi.org/10.48550/arXiv.2307.04573Test https://vbn.aau.dk/da/publications/f997799d-a060-4413-851f-e20e0f21f7caTest https://vbn.aau.dk/ws/files/541469785/2307.04573v1.pdfTest |
حقوق: | info:eu-repo/semantics/openAccess |
رقم الانضمام: | edsbas.D03AF736 |
قاعدة البيانات: | BASE |
DOI: | 10.48550/arXiv.2307.04573 |
---|