党睿,丛阳,王卿臣
DANG Rui,CONG Yang,WANG Qingchen

• 1:天津大学建筑学院

摘要(Abstract)：

光环境感受反映了室内空间使用者的视觉舒适性，是光环境质量的重要评判标准。Kruithof室内光环境舒适度曲线揭示了环境色温与视觉舒适之间的关系。本研究基于Kruithof曲线在应用上的局限性，提出了一种基于特定室内场景下的光环境视觉舒适度主观评价实验，利用支持向量机(SVM)分类算法对实验数据进行训练，得到不同视觉舒适等级的分类界面，并通过模型分类界面可视化得到特定室内场景下Kruithof光舒适曲线修正结果。该修正方法可以用于不同室内场景下的光舒适评价模型的建立，为室内光环境质量的精准评价提供了理论支持。
Light environment perception reflects the visual comfort of indoor space users, and is an important criterion for judging the quality of light environment. Kruithof's graph reveals the relationship between ambient color temperature and visual comfort. Based on its limitations in application, this study proposes a subjective evaluation experiment based on the visual comfort of light environment in specific indoor scenes. The experimental data are trained by using the support vector machine(SVM) classification algorithm to obtain the classification interfaces for different visual comfort levels, and the revision results of the Kruithof's graph in specific indoor scenes are obtained by visualizing the model classification interfaces. The revision method can be used for the establishment of light comfort evaluation models in different indoor scenes, providing theoretical support for the accurate evaluation of indoor light environment quality.

关键词(KeyWords)： Kruithof曲线;室内光环境;分类建模;主观评价实验
Kruithof's graph;interior lighting environment;classification modeling;subjective evaluation experiment

Abstract:

Keywords:

基金项目(Foundation):

作者(Author): 党睿,丛阳,王卿臣
DANG Rui,CONG Yang,WANG Qingchen

参考文献(References)：

• [1] Veitch J A,Newsham G R.Determinants of lighting quality II:research and recommendations[J].Adolescents,1996,8:58.
• [2] Newsham G R.Determinants of lighting quality I:state of the science[J].Journal of the Illuminating Engineering Society,1998,27(1):92-106.
• [3] Kruithof A A.Tubular luminescence lamps for general illumination[J].Philips Tech Review,1941,6:65-96.
• [4] Fotios S.A Revised Kruithof graph based on empirical data[J].Leukos,2016,13(1):3-17.
• [5] Cortes C,Vapnik V.Support-vector networks[J].Machine Learning,1995,20(3):273-297.
• [6] Hsu C W,Lin C J.A comparison of methods for multiclass support vector machines[J].IEEE Transactions on Neural Networks,2002,13(2):415-425.
• [7] 照明测量方法：GB/T 5700—2008[S].
• [8] Hand D J,Till R J.A simple generalisation of the area under the roc curve for multiple class classification problems[J].Machine Learning,2001,45(2):171-186.