Scholarlink

In recent years, drones have found a place in many industries. Their proper functioning is important for the development of various organizations and companies. Therefore, it is not surprising that there is a need to protect against equipment failures, especially drone engines. In this study, we analyze the possibility of effectively diagnosing the number of engines that stopped working during a drone flight using effective aggregation methods based on Smooth Quadrature-Inspired Generalized Choquet Integral and aggregating classification results obtained by individual deep neural networks. The experimental results show an increase in the accuracy measure of over 7 percentage points with respect to the best of the analyzed individual classifiers.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Smooth Quadrature-Inspired Generalized Choquet Integral in an Application to Drone Engine Failures Detection

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Paweł Karczmarek,
  • Rafał Stȩgierski,
  • Bartłomiej Ambrożkiewicz,
  • Andrzej Koszewnik,
  • Daniel Ołdziej,
  • Arkadiusz Syta,
  • Michał Dolecki,
  • Adam Kiersztyn,
  • Albert Rachwał,
  • Konrad Smoliński,
  • Witold Pedrycz

摘要

In recent years, drones have found a place in many industries. Their proper functioning is important for the development of various organizations and companies. Therefore, it is not surprising that there is a need to protect against equipment failures, especially drone engines. In this study, we analyze the possibility of effectively diagnosing the number of engines that stopped working during a drone flight using effective aggregation methods based on Smooth Quadrature-Inspired Generalized Choquet Integral and aggregating classification results obtained by individual deep neural networks. The experimental results show an increase in the accuracy measure of over 7 percentage points with respect to the best of the analyzed individual classifiers.