Scholarlink

<p>This paper explores a smart lighting solution for enhancing the display of traditional artworks in gallery settings using an enhanced Adaptive Lighting Recurrent Fuzzy Neural Network (AL-RFNN). The system automatically adjusts lighting conditions such as brightness, color temperature, and dimming levels in real time to improve how art is experienced and preserved. By combining fuzzy logic to deal with uncertain environments and a recurrent neural network for feedback and adaptability, the model ensures that artworks are consistently shown under optimal lighting. Compared to existing methods like Dynamic Lighting with Virtual Reality (DLVR), Deep Variational Auto-Encoding Procedure (DVAEP), and Autonomous Compact Fixtures of Lighting (ACFL), the enhanced AL-RFNN achieves higher performance, with a Peak Signal-to-Noise Ratio (PSNR) of 39.5 dB, a Mean Squared Error (MSE) of just 0.025%, and viewer engagement times reaching up to 55&#xa0;min. Tests also show the system holds up well under different lighting conditions, maintaining both visual quality and energy efficiency. This approach blends AI, art preservation, and sustainability, offering a practical and intelligent way to modernize museum lighting systems.</p>

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

Adaptive Fuzzy Neural Lighting Control for Enhancing Traditional Art Presentation in Smart Gallery Environments

  • 期刊论文

  • 发表日期：

    2026年5月7日

查看全文
  • Cuiying Lu

摘要

This paper explores a smart lighting solution for enhancing the display of traditional artworks in gallery settings using an enhanced Adaptive Lighting Recurrent Fuzzy Neural Network (AL-RFNN). The system automatically adjusts lighting conditions such as brightness, color temperature, and dimming levels in real time to improve how art is experienced and preserved. By combining fuzzy logic to deal with uncertain environments and a recurrent neural network for feedback and adaptability, the model ensures that artworks are consistently shown under optimal lighting. Compared to existing methods like Dynamic Lighting with Virtual Reality (DLVR), Deep Variational Auto-Encoding Procedure (DVAEP), and Autonomous Compact Fixtures of Lighting (ACFL), the enhanced AL-RFNN achieves higher performance, with a Peak Signal-to-Noise Ratio (PSNR) of 39.5 dB, a Mean Squared Error (MSE) of just 0.025%, and viewer engagement times reaching up to 55 min. Tests also show the system holds up well under different lighting conditions, maintaining both visual quality and energy efficiency. This approach blends AI, art preservation, and sustainability, offering a practical and intelligent way to modernize museum lighting systems.