The regulation of organ size in higher organisms is a fundamental issue in developmental biology. In flowering plants, a phenomenon called "compensation" has been observed where a cell proliferation defect in developing leaf primordia triggers excessive cell expansion. As a result, final leaf size is not significantly reduced compared to that expected from the reduction in leaf cell numbers. Re...

美濃羽靖・中西白：葉の形状特徴を用いた樹種判別におけるサンプルサイズと判別精度，森林計画誌55：61～75，2022 本研究では，葉の形状特徴を用いた樹種判別における必要なサンプルサイズと判別精度との関係について検証した。葉は20種を各樹種250から350枚程度，計6,516枚を採取した。形状特徴量には円形度，最適楕円の短径・長径比，周囲長・最適楕円軌道比，凸度を用いた。機械学習には決定木（J48およびRandomForest）およびニューラルネットワーク（MultilayerPerceptron）を用い，判別精度はMCC（マシューズ相関係数）を用いた。各形状特徴量を計測する際に必要なサンプルサイズの推定方法は，検出力分析で用いられるサンプルサイズの設計方法を用いた。解析結果より，訓練事例のMCCが0.755から1.000，未知事例のMCCが0.737から0.744と比較的高い判別精...

Plant classification becomes very much demanding research area for the use of taxonomist and botanist as well as in agricultural requirement. Using computerized techniques for performing these task is more effective. This research paper presents the classification of plants by using Feed forward Back Propagation Neural Network designed.This method performed in three steps first is leaf image pr...

A leaf is an organ of vascular plant and is the principal lateral appendage of the stem. Each leaf has a set of features that differentiate it from the other leaves, such as margin and shape. This work proposes a comparison of supervised plant leaves classification using different approaches, based on different representations of these leaves, and the chosen algorithm. Beginning with the repres...

cement powder size classification efficiency significantly affects quality of final product and extent of energy consumption in clinker grinding circuits. static and dynamic or high efficiency air separators are being used widely in closed circuit with multi-compartment tube ball mills, high pressure grinding rolls (hpgr) and more recently vertical roller mills (vrm) units in cement plants to c...

Hierarchies are frequently used for the organization of objects. Given a hierarchy of classes, two main approaches are used, to automatically classify new instances: flat classification and cascade classification. Flat classification ignores the hierarchy, while cascade classification greedily traverses the hierarchy from the root to the predicted leaf. In this paper we propose a new approach, ...