用于帕金森病分类的 ResNet 模型集合

Q4 Medicine

International Journal of Nutrition, Pharmacology, Neurological Diseases Pub Date : 2023-11-30 DOI:10.4103/ijnpnd.ijnpnd_22_23

M. Mahendran, R. Visalakshi

{"title":"用于帕金森病分类的 ResNet 模型集合","authors":"M. Mahendran, R. Visalakshi","doi":"10.4103/ijnpnd.ijnpnd_22_23","DOIUrl":null,"url":null,"abstract":"Parkinson disease (PD) is one of the neurological illnesses incurred. However, there is a no chance to recognize PD. A fine motor symptom has been identified in this study. A group of patients with PD, as well as the healthy group, is used in the research. The authors have developed a technique that can determine whether a patient has PD or not. Using deep learning methods, the same design generalizing neural networks in the brain can be solved. The categorization of patients with PD and non-PD behavior is found from the analysis of spiral and wave forms using CNN model. Various CNN models were used in the experiment by transfer learning and spiral and wave data sketches. With the help of spiral sketching, the system achieved an accuracy of 96.67% using the ResNet50 model. The main objective of this paper is to explore the application of transfer learning, which improved the performance of the model.","PeriodicalId":14233,"journal":{"name":"International Journal of Nutrition, Pharmacology, Neurological Diseases","volume":"24 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2023-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"An ensemble of ResNet model for classification of Parkinson disease\",\"authors\":\"M. Mahendran, R. Visalakshi\",\"doi\":\"10.4103/ijnpnd.ijnpnd_22_23\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Parkinson disease (PD) is one of the neurological illnesses incurred. However, there is a no chance to recognize PD. A fine motor symptom has been identified in this study. A group of patients with PD, as well as the healthy group, is used in the research. The authors have developed a technique that can determine whether a patient has PD or not. Using deep learning methods, the same design generalizing neural networks in the brain can be solved. The categorization of patients with PD and non-PD behavior is found from the analysis of spiral and wave forms using CNN model. Various CNN models were used in the experiment by transfer learning and spiral and wave data sketches. With the help of spiral sketching, the system achieved an accuracy of 96.67% using the ResNet50 model. The main objective of this paper is to explore the application of transfer learning, which improved the performance of the model.\",\"PeriodicalId\":14233,\"journal\":{\"name\":\"International Journal of Nutrition, Pharmacology, Neurological Diseases\",\"volume\":\"24 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-11-30\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"International Journal of Nutrition, Pharmacology, Neurological Diseases\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.4103/ijnpnd.ijnpnd_22_23\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q4\",\"JCRName\":\"Medicine\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Nutrition, Pharmacology, Neurological Diseases","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.4103/ijnpnd.ijnpnd_22_23","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"Medicine","Score":null,"Total":0}

引用次数: 0

摘要

帕金森病（PD）是一种神经系统疾病。然而，帕金森病是无法识别的。本研究确定了一种精细运动症状。研究中使用了一组帕金森病患者和一组健康人。作者开发出了一种可以确定患者是否患有帕金森病的技术。利用深度学习方法，可以解决在大脑中泛化神经网络的相同设计问题。通过使用 CNN 模型对螺旋形和波形的分析，可以发现患有帕金森病和非帕金森病的患者的行为分类。实验中使用了各种 CNN 模型，通过迁移学习和螺旋与波形数据草图进行分析。在螺旋草图的帮助下，系统使用 ResNet50 模型达到了 96.67% 的准确率。本文的主要目的是探索迁移学习的应用，它提高了模型的性能。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

An ensemble of ResNet model for classification of Parkinson disease

Parkinson disease (PD) is one of the neurological illnesses incurred. However, there is a no chance to recognize PD. A fine motor symptom has been identified in this study. A group of patients with PD, as well as the healthy group, is used in the research. The authors have developed a technique that can determine whether a patient has PD or not. Using deep learning methods, the same design generalizing neural networks in the brain can be solved. The categorization of patients with PD and non-PD behavior is found from the analysis of spiral and wave forms using CNN model. Various CNN models were used in the experiment by transfer learning and spiral and wave data sketches. With the help of spiral sketching, the system achieved an accuracy of 96.67% using the ResNet50 model. The main objective of this paper is to explore the application of transfer learning, which improved the performance of the model.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

International Journal of Nutrition, Pharmacology, Neurological Diseases Medicine-Pharmacology (medical)

CiteScore

0.80

自引率

0.00%

发文量

期刊介绍： The International Journal of Nutrition, Pharmacology, Neurological Diseases (IJNPND) is an international, open access, peer reviewed journal which covers all fields related to nutrition, pharmacology, neurological diseases. IJNPND was started by Dr. Mohamed Essa based on his personal interest in Science in 2009. This journal doesn’t link with any society or any association. The co-editor-in chiefs of IJNPND (Prof. Gilles J. Guillemin, Dr. Abdur Rahman and Prof. Ross grant) and editorial board members are well known figures in the fields of Nutrition, pharmacology, and neuroscience. First, the journal was started as two issues per year, then it was changed into 3 issues per year and since 2013, it publishes 4 issues per year till now. This shows the slow and steady growth of this journal. To support the reviewers and editorial board members, IJNPND offers awards to the people who does more reviews within one year. The International Journal of Nutrition, Pharmacology, Neurological Diseases (IJNPND) is published Quarterly. IJNPND has three main sections, such as nutrition, pharmacology, and neurological diseases. IJNPND publishes Research Papers, Review Articles, Commentaries, case reports, brief communications and Correspondence in all three sections. Reviews and Commentaries are normally commissioned by the journal, but consideration will be given to unsolicited contributions. International Journal of Nutrition, Pharmacology, Neurological Diseases is included in the UGC-India Approved list of journals.