CNN model

Guofan Li; Yan Li; Guangyue Han; Caixiao Jiang; Minghao Geng; Nana Guo; Wentao Wu; Shangze Liu; Zhihuai Xing; Xu Han; Qi Li

Improve Research Reproducibility A Bio-protocol resource

Home
Protocols

Concise Method

CNN model

GL Guofan Li

YL Yan Li

GH Guangyue Han

CJ Caixiao Jiang

MG Minghao Geng

NG Nana Guo

WW Wentao Wu

SL Shangze Liu

ZX Zhihuai Xing

XH Xu Han

QL Qi Li

This method is extracted from research article: BMC Public Health, Aug 2024

Forecasting and analyzing influenza activity in Hebei Province, China, using a CNN-LSTM hybrid model

DOI: 10.1186/s12889-024-19590-8

Ask a question

Favorite

CNN models have superior capabilities in extracting local features [28]. They can be employed in computer vision and time series prediction and analysis [29]. CNN models consist of convolutional layers, pooling layers, activation functions, and dense layers (Fig. (Fig.4).4). For our time series data, 1D kernels were used to slide across the data (x) and compute dot products between the kernel and local data at each step, eventually generating feature maps. We then used max pooling on feature maps to reduce dimensions while retaining important features. After adding non-linearity to pooled data using a tanh function, data were input into the dense layer and produced a CNN model using the following formula:

where $(x * w)$ denotes the convolution operation, $b$ is a bias term $X_{i : i + k - 1}$ is a set of consecutive elements in the input feature sequence, $m a x ()$ is a maximum extraction operation, $W$ is a weight matrix, and $*$ is a matrix multiplication operation.

Architecture of the convolutional neural network

Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.

Do you have any questions about this protocol?

Post your question to gather feedback from the community. We will also invite the authors of this article to respond.

Post a Question

0 Q&A

Share your protocol with your peers.

Submit a Preprint Protocol