Cancer Prediction of Medical Examination Data and Its Knowledge Extraction by Adaptive Structural Learning of Deep Belief Network
Bibliographic Information
- Other Title
-
- 検診結果ビッグデータを用いた構造適応型Deep Belief Networkの癌予測システムと知識発見
Abstract
Abstract?Deep Learning has a hierarchical network architecture to represent the complicated feature of in-put patterns. We have developed the adaptive structure learning method of Deep Belief Network (DBN) that can discover an optimal number of hidden neurons for given input data in a Restricted Boltzmann Machine (RBM) by neuron generation-annihilation algorithm, and hidden layers in DBN. The proposed adaptive structure DBN was applied to the comprehensive medical examination data for the cancer prediction. The prediction system shows the highest classi?cation accuracy among the traditional DBN. In this paper, the explicit knowledge with respect to the relation between input and output patterns was extracted from the trained DBN network by C4.5. Some characteristics extracted in the form of If-Then rules to ?nd an initial cancer were reported in this paper.
Journal
-
- 2018 IEEE SMC Hiroshima Chapter若手研究会講演論文集
-
2018 IEEE SMC Hiroshima Chapter若手研究会講演論文集 63-69, 2018
IEEE SMC Hiroshima Chapter
- Tweet
Details 詳細情報について
-
- CRID
- 1050296808061405440
-
- NII Article ID
- 120006666400
-
- Text Lang
- ja
-
- Article Type
- conference paper
-
- Data Source
-
- IRDB
- CiNii Articles