Weight and Structure Determination Neural Network Aided With Double Pseudoinversion for Diagnosis of Flat Foot
Open Access
- 7 March 2019
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 7, 33001-33008
Abstract
Deep learning models often have complicated structures with low computational speed and the requirement of a large amount of storage space, which limits their own practical application on some devices with insufficient computing power. This paper proposes the weight and structure determination neural network aided with double pseudoinversion (WASDNN-DP) that can overcome these shortcomings. First, the model structure, theoretical bases, and the algorithms of WASDNN-DP are given. In the process of constructing the network, the weight matrix between the hidden layer and the output layer is first randomly generated. After the weight matrix between the input layer and the hidden layer is analytically determined, the weight matrix between the hidden layer and the output layer is re-determined by the pseudo-inverse method. Furthermore, in WASDNN-DP, the structure of the neural network is determined by a progressive method. Subsequently, based on two datasets collected from children aged 7-15 years by using smart insoles, the comparative experiments between WASDNN-DP and some other machine learning models are carried out, which illustrate the superiority of the proposed WASDNN-DP in the diagnosis of flat foot.Keywords
Funding Information
- National Natural Science Foundation of China (61703189)
- Fund of Robot Technology Used for Special Environment Key Laboratory of Sichuan Province (17kfkt03)
- International Science and Technology cooperation program of China (2017YFE0118900)
- Guangdong Outstanding Young Teacher Training Program in Higher School (YQ2015104)
- Guangdong Province Science and Technology Major Project (20130325)
- Natural Science Foundation of Gansu Province (18JR3RA264, 18JR3RA268)
- Sichuan Science and Technology Program (19YYJC1656)
- Natural Science Foundation of Hunan Province (2017JJ3257)
- Research Foundation of Education Bureau of Hunan Province, China (17C1299)
This publication has 44 references indexed in Scilit:
- Flatfoot in School-Age ChildrenFoot & Ankle Specialist, 2015
- Back propagation neural network with adaptive differential evolution algorithm for time series forecastingExpert Systems with Applications, 2015
- Improving the Mann–Whitney statistical test for feature selection: An approach in breast cancer diagnosis on mammographyArtificial Intelligence in Medicine, 2015
- Cross-validation based weights and structure determination of Chebyshev-polynomial neural networks for pattern classificationPattern Recognition, 2014
- On the Complexity of Neural Network Classifiers: A Comparison Between Shallow and Deep ArchitecturesIEEE Transactions on Neural Networks and Learning Systems, 2014
- Unveiling relevant non-motor Parkinson's disease severity symptoms using a machine learning approachArtificial Intelligence in Medicine, 2013
- A support vector machine classifier with rough set-based feature selection for breast cancer diagnosisExpert Systems with Applications, 2011
- Clinical practiceEuropean Journal of Pediatrics, 2010
- Prevalence of Flat Foot in Preschool-Aged ChildrenPediatrics, 2006
- A method for diagnosing multiple diseases in MUNINIEEE Transactions on Biomedical Engineering, 2001