文献类型：期刊文献

英文题名：Research on fusing topological data analysis with convolutional neural network

作者：Han, Yang[1]; Guangjun, Qin[1]; Ziyuan, Liu[1]; Yongqing, Hu[1]; Guangnan, Liu[1]; Qinglong, Dai[1]

机构：[1] Smart City College, Beijing Union University, Beijing, China

第一机构：北京联合大学智慧城市学院

年份：2024

外文期刊名：arXiv

收录：EI(收录号：20240313665)

语种：英文

外文关键词：Clustering algorithms - Convolution - Convolutional neural networks - Decision making - Image analysis - Information analysis - Machine learning - Numerical methods - Topology

摘要：Convolutional Neural Network (CNN) struggle to capture the multi-dimensional structural information of complex high-dimensional data, which limits their feature learning capability. This paper proposes a feature fusion method based on Topological Data Analysis (TDA) and CNN, named TDA-CNN. This method combines numerical distribution features captured by CNN with topological structure features captured by TDA to improve the feature learning and representation ability of CNN. TDA-CNN divides feature extraction into a CNN channel and a TDA channel. CNN channel extracts numerical distribution features, and the TDA channel extracts topological structure features. The two types of features are fused to form a combined feature representation, with the importance weights of each feature adaptively learned through an attention mechanism. Experimental validation on datasets such as Intel Image, Gender Images, and Chinese Calligraphy Styles by Calligraphers demonstrates that TDA-CNN improves the performance of VGG16, DenseNet121, and GoogleNet networks by 17.5%, 7.11%, and 4.45%, respectively. TDA-CNN demonstrates improved feature clustering and the ability to recognize important features. This effectively enhances the model's decision-making ability. Copyright ? 2024, The Authors. All rights reserved.