K
Kenji Kira
Researcher at Mitsubishi Electric
Publications - 5
Citations - 4828
Kenji Kira is an academic researcher from Mitsubishi Electric. The author has contributed to research in topics: Feature selection & Minimum redundancy feature selection. The author has an hindex of 3, co-authored 5 publications receiving 4421 citations.
Papers
More filters
Book ChapterDOI
A Practical Approach to Feature Selection
Kenji Kira,Larry A. Rendell +1 more
TL;DR: Comparison with other feature selection algorithms shows Relief's advantages in terms of learning time and the accuracy of the learned concept, suggesting Relief's practicality.
Proceedings Article
The feature selection problem: traditional methods and a new algorithm
Kenji Kira,Larry A. Rendell +1 more
TL;DR: A new algorithm Rellef is introduced which selects relevant features using a statistical method and is accurate even if features interact, and is noise-tolerant, suggesting a practical approach to feature selection for real-world problems.
Patent
Information retrieval supporting device
TL;DR: In this paper, guidance data are received from a guidance I/F device J1, a supplementary explanation extracting/presenting device G2-1 extracts the word for which supplementary explanation is required and then, text matching is performed to show whether such a word is contained in the guidance data or not.
Proceedings ArticleDOI
Development of object-oriented multimedia database and its application to retrieval of maintenance parts
TL;DR: A method of maintenance part information retrieval, applied to a multimedia database of elevator parts, is presented and shown to be feasible and effective.
Patent
Hierarchical data retrieving device and maintenance parts retrieving device
Kenji Kira,Tanaka Satoshi,Mitsuhide Shima,Norihiro Minegishi,Ishikawa Hiromichi,Shibayama Junichi +5 more
TL;DR: In this paper, a maintenance parts retrieving device is provided with a parts structure information data base for storing relational information among maintenance parts and the attribute information of parts, a parts selecting information database for specifying parts corresponding to an equipment to be maintained.