A Feature Optimized Deep Learning Model for Clinical Data Mining
| Autor: | Peng Wu, Shuyu Chen, Tianshu Wu, Yingming Tian |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Artificial neural network
Computer science business.industry Applied Mathematics Deep learning Early disease 020206 networking & telecommunications Recurrent neural nets 02 engineering and technology computer.software_genre Random forest Long short term memory Shortterm Memory 0202 electrical engineering electronic engineering information engineering Feature (machine learning) 020201 artificial intelligence & image processing Artificial intelligence Data mining Electrical and Electronic Engineering business computer |
| Zdroj: | Chinese Journal of Electronics. 29:476-481 |
| ISSN: | 2075-5597 1022-4653 |
| DOI: | 10.1049/cje.2020.03.004 |
| Popis: | the Artificial intelligence (AI) has gradually changed from frontier technology to practical application with the continuous progress of deep learning technology in recent years. In this paper, the Random forest (RF) algorithm is adopted to preprocess and optimize the feature subset of ICU data sets. Then these optimized feature subsets are used as input of Long shortterm memory (LSTM) deep learning model, and the early disease prediction of ICU inpatients is carried out by the method of neural network deep learning. Experiments show that this prediction method has higher prediction accuracy compared with other machine learning and deep learning models. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Plný text