Feature Analysis and Classification of Particle Data from Two-Dimensional Video Disdrometer

• 作者: Dau Phan Duc Luu Ngo Favorisen Rosyking Lumbanraja Kenji Satou Lan Anh T. Nguyen Mamoru Kubo Ngoc Giang Nguyen Sergey Gavrilov Vu Anh Tran
• 来源期刊: 遥感技术进展(英文)
• 学科: 医学
• 关键词: Solid PRECIPITATION PARTICLE Classification 2DVD FRACTAL DIMENSION PCA
• 年，卷（期）: ygjsjzyw_2015,（1）
• 页码范围: 1-14
• 页数: 14页
• 分类号: R73

摘要

We developed a ground observation system for solid precipitation using two-dimensional video disdrometer (2DVD). Among 16,010 particles observed by the system, around 10% of them were randomly sampled and manually classified into five classes which are snowflake, snowflake-like, intermediate, graupel-like, and graupel. At first, each particle was represented as a vector of 72 features containing fractal dimension and box-count to represent the complexity of particle shape. Feature analysis on the dataset clarified the importance of fractal dimension and box-count features for characterizing particles varying from snowflakes to graupels. On the other hand, performance evaluation of two-class classification by Support Vector Machine (SVM) was conducted. The experimental results revealed that, by selecting only 10 features out of 72, the average accuracy of classifying particles into snowflakes and graupels could reach around 95.4%, which had not been achieved by previous studies.