Scholarlink

This paper presents a novel approach to evaluating augmented reality (AR) performance in industrial maintenance settings through systematic activity data analysis. Current AR performance measurement techniques often rely on subjective assessments rather than quantifiable metrics, limiting evidence-based validation. We address this gap by developing a methodology that captures spatial-temporal interaction patterns during maintenance tasks. Our experimental study compared AR-based maintenance using Microsoft HoloLens 2 with traditional video-based instruction across participants with different technical backgrounds. Results revealed significant linkages between hand movement distances and task completion efficiency, with task completion times substantially longer for AR-guided maintenance. However, the AR application achieved an exceptional System Usability Scale score of 85.0, indicating high user acceptance despite longer completion times. The findings demonstrate that user interface design and cognitive ergonomics principles directly influence maintenance performance. Our methodology establishes a foundation for objective performance assessment through activity data analysis, providing industrial stakeholders with evidence-based metrics for evaluating AR implementation effectiveness. This research contributes to advancing AR technology validation in industrial contexts by quantifying the relationship between spatial interactions and maintenance performance outcomes.

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

Quantifying Performance in AR-based Industrial Maintenance Application: A Framework for Activity Data Analysis

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Suphawit Kankam,
  • Chalermpan Fongsamut,
  • Methasit Khunnen,
  • Kanuengnij Kubola,
  • Prajaks Jitngernmadan

摘要

This paper presents a novel approach to evaluating augmented reality (AR) performance in industrial maintenance settings through systematic activity data analysis. Current AR performance measurement techniques often rely on subjective assessments rather than quantifiable metrics, limiting evidence-based validation. We address this gap by developing a methodology that captures spatial-temporal interaction patterns during maintenance tasks. Our experimental study compared AR-based maintenance using Microsoft HoloLens 2 with traditional video-based instruction across participants with different technical backgrounds. Results revealed significant linkages between hand movement distances and task completion efficiency, with task completion times substantially longer for AR-guided maintenance. However, the AR application achieved an exceptional System Usability Scale score of 85.0, indicating high user acceptance despite longer completion times. The findings demonstrate that user interface design and cognitive ergonomics principles directly influence maintenance performance. Our methodology establishes a foundation for objective performance assessment through activity data analysis, providing industrial stakeholders with evidence-based metrics for evaluating AR implementation effectiveness. This research contributes to advancing AR technology validation in industrial contexts by quantifying the relationship between spatial interactions and maintenance performance outcomes.