{"title":"利用迁移学习的降维方法对脑肿瘤分类的影响","authors":"Patel Rahulkumar, Dr. D. J. Shah","doi":"10.52783/jes.5320","DOIUrl":null,"url":null,"abstract":"Neural networks and related algorithms and libraries are preferred these days for the analysis of brain tumor types and its classification/detection. The proposed method is a CNN-based DenseNet library model that uses dimension reductionality technique called Principal Component Analysis (PCA) to classify brain tumor MRI images into several classes having tumor and not having tumor. The proposed work is to understand and classify the brain MR images into glioma, meningioma, pituitary and no tumor class from the dataset comprising of MRI images. The tested CNN model described in this paper is a variant of DenseNet with PCA. The performance of the DenseNet model has been evaluated using four assessment indices namely, Precision, Recall, F-score, and Accuracy.","PeriodicalId":44451,"journal":{"name":"Journal of Electrical Systems","volume":null,"pages":null},"PeriodicalIF":0.5000,"publicationDate":"2024-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Impact of Dimensionality Reduction Method in Brain Tumor Classification Using Transfer Learning\",\"authors\":\"Patel Rahulkumar, Dr. D. J. Shah\",\"doi\":\"10.52783/jes.5320\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Neural networks and related algorithms and libraries are preferred these days for the analysis of brain tumor types and its classification/detection. The proposed method is a CNN-based DenseNet library model that uses dimension reductionality technique called Principal Component Analysis (PCA) to classify brain tumor MRI images into several classes having tumor and not having tumor. The proposed work is to understand and classify the brain MR images into glioma, meningioma, pituitary and no tumor class from the dataset comprising of MRI images. The tested CNN model described in this paper is a variant of DenseNet with PCA. The performance of the DenseNet model has been evaluated using four assessment indices namely, Precision, Recall, F-score, and Accuracy.\",\"PeriodicalId\":44451,\"journal\":{\"name\":\"Journal of Electrical Systems\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.5000,\"publicationDate\":\"2024-07-10\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Electrical Systems\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.52783/jes.5320\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q4\",\"JCRName\":\"ENGINEERING, ELECTRICAL & ELECTRONIC\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Electrical Systems","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.52783/jes.5320","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}
Impact of Dimensionality Reduction Method in Brain Tumor Classification Using Transfer Learning
Neural networks and related algorithms and libraries are preferred these days for the analysis of brain tumor types and its classification/detection. The proposed method is a CNN-based DenseNet library model that uses dimension reductionality technique called Principal Component Analysis (PCA) to classify brain tumor MRI images into several classes having tumor and not having tumor. The proposed work is to understand and classify the brain MR images into glioma, meningioma, pituitary and no tumor class from the dataset comprising of MRI images. The tested CNN model described in this paper is a variant of DenseNet with PCA. The performance of the DenseNet model has been evaluated using four assessment indices namely, Precision, Recall, F-score, and Accuracy.