Intelligent diagnosis of Alzheimer's disease based on BP neural network
Pages 547 - 550
Abstract
Alzheimer's disease (AD) is a progressive neurodegenerative disease, and its onset is unknown. It usually occurs in the elderly and dies due to complications 10 to 20 years after onset. Therefore, early and accurate diagnosis of AD and mild cognitive impairment is of great significance. Firstly, preprocess the data, manually remove the data with no specific information, and then use Python to remove duplicate feature variables with the same name and data with more than 10% missing features. Fill in the remaining data with missing values and fill in the average values, leaving 16 sample labels; Then, the processed data is divided into training and testing sets to train a random forest model, and the correlation scores between data features and Alzheimer's disease diagnosis are calculated separately. Some results are as follows: LDELTOTAL_ BL-18.81%, PACCDigit 14.30%, and combined with the existing dataset with nonlinear data features for comprehensive analysis. Based on the advantages of BP neural network nonlinear mapping function and existing feature labels, a model is established to intelligently diagnose Alzheimer's disease. Through testing and analysis, when the number of hidden neurons is 9 and the model training method is Bayesian regularization, the solution effect is better. Some of the optimal intelligent diagnosis schemes are: FAQ: 0.0-30.0; ADAS13:0.0-54.68; AGE: 50.4-91.4; MMSE: 16.0-30.0.
References
[1]
Chen H. Data analysis and early symptom extraction of Alzheimer's disease [D]. Fujian Normal University, 2021.
[2]
Bloch Louise and Friedrich Christoph M. Machine Learning Workflow to Explain Black-Box Models for Early Alzheimer's Disease Classification Evaluated for Multiple Datasets [J]. SN Computer Science, 2022, 3(6).
[3]
Du Lijuan, Wu Can, Xie Huangze, Xu Jiating, Niu Yanfang, Xue Yang, Wang Qinwen, Zhou Yingsong, Xu Shujun. Movement regulation of astrocyte alzheimer's improvement mechanism research [J/OL]. Progress in biochemistry and biophysics: 1-11, 2022, 11, 20. / j. ibb. 2022.0430.
[4]
Yao Tingting, LIU Yuanyuan, LI Changping, HU Liangping. Regression model analysis of survival data – Cox proportional risk regression model analysis of survival data [J]. Sichuan Mental Health, 2020, 33(01):27-32.
[5]
Yang Kai, Meng Lingguo. Based on in-depth study of intelligent detection and classification of alzheimer's disease research [D]. Jinan: shandong university, 2020, 06, 03.
[6]
Wei Caifeng, Zeng Xianhua. Dictionary based recognition of mild cognitive impairment in learning [D]. Chongqing: Chongqing University of Posts and Telecommunications, 2018, 04, 01.
[7]
Luo Peiqi, Kang Jiaxia. Early diagnosis and prediction of Alzheimer's disease based on multi-feature fusion [D]. Beijing: Beijing University of Posts and Telecommunications, 2021, 06, 03.
[8]
Qiu Zhirong, Ding Xuemei, Yang Hongqin. Recognition of stable and progressive mild cognitive impairment by Different convolutional neural networks [D]. Fuzhou: Fujian Normal University, 2021, 07, 14.
[9]
Chen Hao, Ding Xuemei, Yang Hongqin. Data analysis and early symptom extraction of Alzheimer's disease [D]. Fuzhou: Fujian Normal University, 2021, 07, 14.
[10]
Yang Kai, Meng Lingguo. Based on in-depth study of intelligent detection and classification of alzheimer's disease research [D]. Jinan: shandong university, 2020, 06, 03.
Index Terms
- Intelligent diagnosis of Alzheimer's disease based on BP neural network
Recommendations
Fault diagnosis method based on PSO-optimized H-BP neural network
IITA'09: Proceedings of the 3rd international conference on Intelligent information technology applicationThe paper combined the advantage of Particle Swarm Optimization algorithm (PSO), the global optimizing ability of Hopfield Neural Network, and the teacher supervising features of BP neural network to construct a new equipment fault diagnosis method with ...
Equipment Diagnosis Method Based on Hopfield-BP Neural Networks
ICACTE '08: Proceedings of the 2008 International Conference on Advanced Computer Theory and EngineeringBP neural network is easily trapped into the local minimum during the training process, which results that it can't get the optimal solution, even misjudging in device fault diagnosis. Directing to the above problems, a Hopfield-BP neural network fault ...
Fault Diagnosis Method Based on PSO-optimized H-BP Neural Network
IITA '09: Proceedings of the 2009 Third International Symposium on Intelligent Information Technology Application - Volume 02The paper combined the advantage of Particle Swarm Optimization algorithm (PSO), the global optimizing ability of Hopfield Neural Network, and the teacher supervising features of BP neural network to construct a new equipment fault diagnosis method with ...
Comments
Information & Contributors
Information
Published In
September 2023
577 pages
ISBN:9798400716362
DOI:10.1145/3660395
Copyright © 2023 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 01 June 2024
Check for updates
Author Tags
Qualifiers
- Research-article
- Research
- Refereed limited
Conference
AIBDF 2023
AIBDF 2023: 2023 3rd Guangdong-Hong Kong-Macao Greater Bay Area Artificial Intelligence and Big Data Forum
September 22 - 24, 2023
Guangzhou, China
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 16Total Downloads
- Downloads (Last 12 months)16
- Downloads (Last 6 weeks)2
Reflects downloads up to 03 Mar 2025
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign inFull Access
View options
View or Download as a PDF file.
PDFeReader
View online with eReader.
eReaderHTML Format
View this article in HTML Format.
HTML Format