計算力学講演会講演論文集
Online ISSN : 2424-2799
セッションID: 047
会議情報

心音自動診断用ニューラルネットワークの学習に関する諸考察
~正常心音と異常心音の判別
*小出 知実菱田 博俊黒野 昭彦齋藤 和博
著者情報
会議録・要旨集 フリー

詳細
抄録

The heart sound contains a lot of information which suggests the health conditions, while a skillful doctor is necessary for its diagnosis. The purpose of the present study is to create the system which automatically diagnoses diseases based on the heart sounds, which is available to everyone in the absence of a skilled physician. The authors perform creation of the heart sound used as input data of the neural network based on the heart sound recorded on CDs for medical education, and try learning it so that it can be diagnosed automatically. The results and discussions will be reported on the day after some trials with estimation of the learning accuracy by using test data.

著者関連情報
© 2018 一般社団法人 日本機械学会
前の記事 次の記事
feedback
Top