ベイジアンネットワークを用いた緑視率に基づく緑環境評価の確率モデルに関する研究

摘要

本論では、京都市が「京のみどり推進ブラン」で行った緑視率の調査と同じ37視点場の61パノラマ写真を対象とし、緑環境の6要素（近景•中景の緑視率、遠景の緑視率、水面の割合、空の割合、路面の割合、建造物の割合）を定義した。ベイジアンネットワークを用いて、これらの緑環境を構成する6要素と感性評価実験で得た緑量に対する満足度の関係を確率モデルで示した。%The purpose of this paper is to provide the method for the construction of the probabilistic model of the evaluation for the amount of green. We applied Bayesian networks to construct graphical models that represented the correlation between the ratio of the evaluation for the amount of green and the visible green of a close-to-mid-range view, a distant view, and other elements which green environment was composed. By executing probabilistic reasoning of Bayesian networks on these models, the probabilistic model contained the relationship between the elements of the close-to-mid-range of visible green and the elements of the distant range, which was found in the visible green study in Kyoto City, verifying the model's validity. Furthermore we deduced the evaluation of the green environments and the ratio of visible green in close-to-mid-range views for "satisfaction". Finally, a conclusion was made regarding the way to use the probabilistic model of green evaluation for application of visible green of close-to-mid-range views.