Presentation 2020-01-15
Modeling of Prediction Processes based on Learning Colored Petri Nets
Ibuki Kawamitsu, Morikazu Nakamura,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper presents a modeling approach to visualize the prediction process of machine learning based on learning colored Petri nets. The learning phase constructs a Petri net structure by feature selection, and extract a function specifying transition firing. Our method allows us to understand quantitatively the relation between the causes and the prediction results. As an application example, we apply our approach to the prediction of the number of daily customers and their orders in a Japanese restaurant. The experimental evaluation with real data shows the usefulness to understand the effect level of each feature for the prediction.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Petri net / Colored Petri net / Machine Learning / Regression / Classification
Paper # MSS2019-53,SS2019-37
Date of Issue 2020-01-07 (MSS, SS)

Conference Information
Committee SS / MSS
Conference Date 2020/1/14(2days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Akio Nakata(Hiroshima City Univ.) / Shigemasa Takai(Osaka Univ.)
Vice Chair Takashi Kobayashi(Tokyo Inst. of Tech.) / Atsuo Ozaki(Osaka Inst. of Tech.)
Secretary Takashi Kobayashi(Osaka Univ.) / Atsuo Ozaki(Hiroshima City Univ.)
Assistant Shinpei Hayashi(Tokyo Inst. of Tech.) / Naoki Hayashi(Osaka Univ.)

Paper Information
Registration To Technical Committee on Software Science / Technical Committee on Mathematical Systems Science and its applications
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Modeling of Prediction Processes based on Learning Colored Petri Nets
Sub Title (in English)
Keyword(1) Petri net
Keyword(2) Colored Petri net
Keyword(3) Machine Learning
Keyword(4) Regression
Keyword(5) Classification
1st Author's Name Ibuki Kawamitsu
1st Author's Affiliation University of the Ryukyus(Univ. of the Ryukyus)
2nd Author's Name Morikazu Nakamura
2nd Author's Affiliation University of the Ryukyus(Univ. of the Ryukyus)
Date 2020-01-15
Paper # MSS2019-53,SS2019-37
Volume (vol) vol.119
Number (no) MSS-361,SS-362
Page pp.pp.73-78(MSS), pp.73-78(SS),
#Pages 6
Date of Issue 2020-01-07 (MSS, SS)