A new hybrid model of convolutional neural networks and hidden Markov chains for image classification.

IF 4.5 3区 计算机科学 Q2 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE
Soumia Goumiri, Dalila Benboudjema, Wojciech Pieczynski
{"title":"A new hybrid model of convolutional neural networks and hidden Markov chains for image classification.","authors":"Soumia Goumiri,&nbsp;Dalila Benboudjema,&nbsp;Wojciech Pieczynski","doi":"10.1007/s00521-023-08644-4","DOIUrl":null,"url":null,"abstract":"<p><p>Convolutional neural networks (CNNs) have lately proven to be extremely effective in image recognition. Besides CNN, hidden Markov chains (HMCs) are probabilistic models widely used in image processing. This paper presents a new hybrid model composed of both CNNs and HMCs. The CNN model is used for feature extraction and dimensionality reduction and the HMC model for classification. In the new model, named CNN-HMC, convolutional and pooling layers of the CNN model are applied to extract features maps. Also a Peano scan is applied to obtain several HMCs. Expectation-Maximization (EM) algorithm is used to estimate HMC's parameters and to make the Bayesian Maximum Posterior Mode (MPM) classification method used unsupervised. The objective is to enhance the performances of the CNN models for the image classification task. To evaluate the performance of our proposal, it is compared to six models in two series of experiments. In the first series, we consider two CNN-HMC and compare them to two CNNs, 4Conv and Mini AlexNet, respectively. The results show that CNN-HMC model outperforms the classical CNN model, and significantly improves the accuracy of the Mini AlexNet. In the second series, it is compared to four models CNN-SVMs, CNN-LSTMs, CNN-RFs, and CNN-gcForests, which only differ from CNN-HMC by the second classification step. Based on five datasets and four metrics recall, precision, F1-score, and accuracy, results of these comparisons show again the interest of the proposed CNN-HMC. In particular, with a CNN model of 71% of accuracy, the CNN-HMC gives an accuracy ranging between 81.63% and 92.5%.</p>","PeriodicalId":49766,"journal":{"name":"Neural Computing & Applications","volume":null,"pages":null},"PeriodicalIF":4.5000,"publicationDate":"2023-05-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10230497/pdf/","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Neural Computing & Applications","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1007/s00521-023-08644-4","RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 1

Abstract

Convolutional neural networks (CNNs) have lately proven to be extremely effective in image recognition. Besides CNN, hidden Markov chains (HMCs) are probabilistic models widely used in image processing. This paper presents a new hybrid model composed of both CNNs and HMCs. The CNN model is used for feature extraction and dimensionality reduction and the HMC model for classification. In the new model, named CNN-HMC, convolutional and pooling layers of the CNN model are applied to extract features maps. Also a Peano scan is applied to obtain several HMCs. Expectation-Maximization (EM) algorithm is used to estimate HMC's parameters and to make the Bayesian Maximum Posterior Mode (MPM) classification method used unsupervised. The objective is to enhance the performances of the CNN models for the image classification task. To evaluate the performance of our proposal, it is compared to six models in two series of experiments. In the first series, we consider two CNN-HMC and compare them to two CNNs, 4Conv and Mini AlexNet, respectively. The results show that CNN-HMC model outperforms the classical CNN model, and significantly improves the accuracy of the Mini AlexNet. In the second series, it is compared to four models CNN-SVMs, CNN-LSTMs, CNN-RFs, and CNN-gcForests, which only differ from CNN-HMC by the second classification step. Based on five datasets and four metrics recall, precision, F1-score, and accuracy, results of these comparisons show again the interest of the proposed CNN-HMC. In particular, with a CNN model of 71% of accuracy, the CNN-HMC gives an accuracy ranging between 81.63% and 92.5%.

Abstract Image

Abstract Image

Abstract Image

一种用于图像分类的卷积神经网络和隐马尔可夫链的新混合模型。
卷积神经网络(CNNs)最近被证明在图像识别中非常有效。除了CNN,隐马尔可夫链(HMCs)是图像处理中广泛使用的概率模型。本文提出了一种新的由细胞神经网络和HMC组成的混合模型。CNN模型用于特征提取和降维,HMC模型用于分类。在名为CNN-HMC的新模型中,应用CNN模型的卷积层和池化层来提取特征图。此外,应用Peano扫描来获得几个HMC。期望最大化(EM)算法用于估计HMC的参数,并使贝叶斯最大后验模式(MPM)分类方法在无监督的情况下使用。目的是提高CNN模型在图像分类任务中的性能。为了评估我们的建议的性能,在两个系列的实验中,将其与六个模型进行了比较。在第一个系列中,我们考虑了两个CNN-HMC,并将它们分别与两个CNN4Conv和Mini-AlexNet进行了比较。结果表明,CNN-HMC模型优于经典的CNN模型,显著提高了Mini-AlexNet的精度。在第二个系列中,它与四个模型CNN SVM、CNN LSTM、CNN RF和CNN gcForests进行了比较,这四个模型与CNN-HMC的区别仅在于第二个分类步骤。基于五个数据集和四个指标召回率、精确度、F1分数和准确性,这些比较结果再次表明了所提出的CNN-HMC的兴趣。特别是,CNN模型的准确率为71%,CNN-HMC的准确率在81.63%和92.5%之间。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Neural Computing & Applications
Neural Computing & Applications 工程技术-计算机:人工智能
CiteScore
11.40
自引率
8.30%
发文量
1280
审稿时长
6.9 months
期刊介绍: Neural Computing & Applications is an international journal which publishes original research and other information in the field of practical applications of neural computing and related techniques such as genetic algorithms, fuzzy logic and neuro-fuzzy systems. All items relevant to building practical systems are within its scope, including but not limited to: -adaptive computing- algorithms- applicable neural networks theory- applied statistics- architectures- artificial intelligence- benchmarks- case histories of innovative applications- fuzzy logic- genetic algorithms- hardware implementations- hybrid intelligent systems- intelligent agents- intelligent control systems- intelligent diagnostics- intelligent forecasting- machine learning- neural networks- neuro-fuzzy systems- pattern recognition- performance measures- self-learning systems- software simulations- supervised and unsupervised learning methods- system engineering and integration. Featured contributions fall into several categories: Original Articles, Review Articles, Book Reviews and Announcements.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信