| Budget Amount *help |
¥4,940,000 (Direct Cost: ¥3,800,000、Indirect Cost: ¥1,140,000)
Fiscal Year 2015: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2014: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2013: ¥2,470,000 (Direct Cost: ¥1,900,000、Indirect Cost: ¥570,000)
|
|---|
| Outline of Final Research Achievements |
For improving nursing-care quality, a nursing-care text evaluation system has been developed. The nursing-care text evaluation system consists of a feature vector extraction system and machine learning based classification. The nursing-care texts are freestyle Japanese texts which are described by nurses. Nurses report their own nursing-care processes which were actually done by the nurses. The feature vector extraction system analyzes dependency relations between words and represents such relations by a matrix type expression. Support vector machines with binary decision tree are used for visualization of the evaluation process of the nursing-care texts. The word2vec is a tool for representing words by high-dimensional vectors. Using word2vec, the classification performance of the nursing-care texts was improved.
|
