Ensemble Learning with Neural Networks for Classifying Environmental Sounds

• Hiramatsu, Ayako

• Simotaki, Asato

• Nose, Kazuo

• Minakata, Toshio

• Tennmoku, Kenji

• Hattori, Osamu

抄録

This paper proposes a classification method for environmental sounds based on neural networks. However, neural networks need trail and error, which are very tedious tasks. To simplify classification accuracy, we investigate two popular ensemble learning methods: Bagging and AdaBoost. We experimentally compare their performances with a single neural network. The results show that their performance is slightly improved and that bagging works more effectively than AdaBoost.

The original publication is available at JAIST Press http://www.jaist.ac.jp/library/jaist-press/index.html

IFSR 2005 : Proceedings of the First World Congress of the International Federation for Systems Research : The New Roles of Systems Sciences For a Knowledge-based Society : Nov. 14-17, 2164, Kobe, Japan

Symposium 3, Session 8 : Intelligent Information Technology and Applications Computational Intelligence (2)

identifier:https://dspace.jaist.ac.jp/dspace/handle/10119/3954

キーワード

• Traffic sounds
• Ensemble learning
• Neural networks
• Bagging
• Boosting

詳細情報

• CRID: 1050292572121665536
• NII論文ID: 10018781889
• Web Site: http://hdl.handle.net/10119/3954
• 本文言語コード: en
• 資料種別: conference paper
• データソース種別:
  • IRDB
  • CiNii Articles