Two-phase multi-expert knowledge approach by using fuzzy clustering and rule-based system for technology evaluation of unmanned aerial vehicles


ÇOLAK M., KAYA İ., KARAŞAN A., ERDOĞAN M.

NEURAL COMPUTING & APPLICATIONS, cilt.34, ss.5479-5495, 2022 (SCI-Expanded) identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 34
  • Basım Tarihi: 2022
  • Doi Numarası: 10.1007/s00521-021-06694-0
  • Dergi Adı: NEURAL COMPUTING & APPLICATIONS
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Academic Search Premier, PASCAL, Applied Science & Technology Source, Biotechnology Research Abstracts, Compendex, Computer & Applied Sciences, Index Islamicus, INSPEC, zbMATH
  • Sayfa Sayıları: ss.5479-5495
  • Anahtar Kelimeler: Unmanned aerial vehicles, Decision making, Fuzzy sets, Fuzzy c-means clustering, Fuzzy inference system, Technology evaluation, IDENTIFICATION, OPPORTUNITIES, UAVS
  • Yıldız Teknik Üniversitesi Adresli: Evet

Özet

Y Unmanned aerial vehicles (UAVs) are utilized in many different areas for different aims such as the benefit of humanity, safety control, traffic control, crop monitoring, scientific research, and commercial applications. Moreover, the UAVs are also successfully utilized for military operations, such as surveillance of an area and counter-terrorism actions. Evaluating them through the technological perspective is quite significant and should be considered from multiple perspectives. In this context, it will be more beneficial to construct a methodology for an efficient evaluation process. The fuzzy set theory (FST) can also be integrated into this methodology to improve its sensitiveness and flexibility. In this paper, a novel methodology integrating fuzzy c-means (FCM) clustering and fuzzy inference system (FIS) has been suggested for the technical evaluation of UAVs. While the FCM clustering algorithm has been utilized to determine the clusters, rules have been created for the FIS through expert assessments, and alternative UAV technologies have been prioritized. For the evaluation procedure, the hierarchical structure of the technology evaluation features has been determined by fusing expert knowledge, literature review, and related ISO standards. Through the FCM clustering algorithm, alternative vehicles have been clustered based on the sub-features of each main feature. Then, FIS has been conducted by using experts' knowledge from the fields of military technologies in UAVs and armed UAVs to obtain the technology indices of the eight UAVs locally produced and used in Turkey. The results demonstrate that the proposed methodology can be successfully applied by the managers or research and development (R&D) engineers for evaluation of the UAV technologies to consider cardinal and linguistic data. Additionally, a comparative analysis based on self-organizing map (SOM) and fuzzy k-means algorithms has also been applied for the proposed method, and their performances have been compared.