A novel distance measure on q-rung picture fuzzy sets and its application to decision making and classification problems

Pinar A., Boran F. E.

ARTIFICIAL INTELLIGENCE REVIEW, cilt.55, sa.2, ss.1317-1350, 2022 (SCI-Expanded) identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 55 Sayı: 2
  • Basım Tarihi: 2022
  • Doi Numarası: 10.1007/s10462-021-09990-2
  • Dergi Adı: ARTIFICIAL INTELLIGENCE REVIEW
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, ABI/INFORM, Aerospace Database, Applied Science & Technology Source, Communication Abstracts, Compendex, Computer & Applied Sciences, Educational research abstracts (ERA), Index Islamicus, INSPEC, Library and Information Science Abstracts, Library, Information Science & Technology Abstracts (LISTA), Metadex, Psycinfo, zbMATH, Civil Engineering Abstracts
  • Sayfa Sayıları: ss.1317-1350
  • Anahtar Kelimeler: Q-rung picture fuzzy set, Distance measure, Multi-criteria decision making, Classification, SIMILARITY MEASURES, SOFTWARE TOOL, ALGORITHMS, KEEL
  • Gazi Üniversitesi Adresli: Evet

Özet

In recent years, different higher order fuzzy sets have been introduced to better handle the uncertainty in many practical decision making and data mining problems. The recent proposal of higher order fuzzy set is q-rung picture fuzzy set (q-RPFS) modeled by three parameters positive, negative, and neutral membership function. One of the important topics in q-RPFS is distance measures which play a crucial role in many multi criteria decision making methods and data mining applications. In this paper, we introduce a novel distance measure for q-RPFS which is the combination of q-rung orthopair fuzzy set (q-ROFS) and picture fuzzy set (PFS). The proposed distance measure is used in q-rung picture fuzzy (q-RPF) ELECTRE integrated with TOPSIS as a new approach for group decision making in q-RPF environment. To demonstrate the effectiveness of our proposed method, a comparison is made with the q-RPF approach based on aggregation operators using a numerical example for decision making problem. Furthermore, the proposed distance measure is utilized in a q-RPF k nearest neighborhood (kNN) algorithm for classification. The proposed classification algorithm is applied to twenty UCI machine learning classification data sets. A comparison with other algorithms is performed and the results show that the proposed classification algorithm has the highest average classification accuracy.