Multivariate analysis method for biology

• Project/Area Number: 26330194
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Research Field: Perceptual information processing
• Research Institution: National Institute of Advanced Industrial Science and Technology (2015-2016); Wakayama University (2014)
• Principal Investigator: Watanabe Kenji 国立研究開発法人産業技術総合研究所, 知能システム研究部門, 研究員 (50571064)
• Co-Investigator(Kenkyū-buntansha): 和田 俊和 和歌山大学, システム工学部, 教授 (00231035)
• Project Period (FY): 2014-04-01 – 2017-03-31
• Project Status: Completed (Fiscal Year 2016)
• Budget Amount: ¥4,550,000 (Direct Cost: ¥3,500,000、Indirect Cost: ¥1,050,000); Fiscal Year 2016: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000); Fiscal Year 2015: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000); Fiscal Year 2014: ¥2,210,000 (Direct Cost: ¥1,700,000、Indirect Cost: ¥510,000)
• Keywords: 多変量解析 / 半教師あり機械学習 / 特徴量変換

Outline of Final Research Achievements

Analysis systems for biological images generally comprise a feature extraction method and a classification method. Task-oriented methods for feature extraction are very effective at improving the classification accuracy. However, it is difficult to utilize such feature extraction methods for versatile task in practice, because few biologists specialize in mathematics and/or informatics to design the task-oriented methods. Thus, in order to improve the usability of these supporting systems, it will be useful to develop a method that can automatically transform the image features of general propose into the effective form toward the task of their interest. In this work, we propose a semi-supervised feature transformation method, which is formulated as a natural coupling of principal component analysis and linear discriminant analysis. Compared with other feature transformation methods, our method showed favorable classification performance in biological image analysis.

Research Products

• [Journal Article] Semi-Supervised Feature Transformation for Tissue Image Classification (2016)
  • Author(s): Kenji Watanabe, Takumi Kobayashi, Toshikazu Wada
  • Journal Title: PLOS ONE Volume: 11
  • DOI: 10.1371/journal.pone.0166413
  • Peer Reviewed / Open Access / Acknowledgement Compliant
• [Journal Article] Semi-supervised Component Analysis (2015)
  • Author(s): Kenji Watanabe, Toshikazu Wada
  • Journal Title: Proceedings of 2015 IEEE International Conference on Systems, Man, and Cybernetics (SMC) Volume: - Pages: 3011-3016
  • DOI: 10.1109/smc.2015.524
  • Peer Reviewed / Open Access / Acknowledgement Compliant
• [Presentation] Semi-supervised Component Analysis (2015)
  • Author(s): Kenji Watanabe, Toshikazu Wada
  • Organizer: 2015 IEEE International Conference on Systems, Man, and Cybernetics (SMC)
  • Place of Presentation: Kowloon (Hong Kong)
  • Year and Date: 2015-10-09
  • Int'l Joint Research
• [Presentation] 計量学習の高速化 (2014)
  • Author(s): 渡辺顕司
  • Organizer: 第10回 広島画像情報学セミナー
  • Place of Presentation: 広島大学
  • Year and Date: 2014-10-10