期刊名称：International Journal of Early Childhood Special Education
电子版ISSN：1308-5581
出版年度：2022
卷号：14
期号：2
页码：2630-2636
DOI：10.9756/INT-JECSE/V14I2.246
语种：English
出版社：International Journal of Early Childhood Special Education
摘要：Since December 2019, the world has been dealing with the COVID-19 epidemic. The importance of a timely and accurate identification of COVID-19 suspected patients in medical treatment cannot be overstated. To combat the COVID-19 outbreak, deep transfer learning-based automated COVID-19 diagnosis on chest X-ray is necessary. Using ensemble deep transfer learning, this work presents a real-time Internet of Things (IoT) system for early identification of suspected COVID-19 patients. COVID-19 suspicious instances can be communicated and diagnosed in real time using the suggested system. InceptionResNetV2, ResNet152V2, VGG16, and DenseNet201 are among the deep learning models included in the proposed IoTframework. Using the deep ensemble model saved on the cloud server, the medical sensors are used to obtain chest X-ray modalities and identify the infection. Over the chest X-ray dataset, the proposed deep ensemble model is compared to six well-known transfer learning models. A comparative investigation demonstrated that the suggested approach can assist radiologists in diagnosing COVID-19 suspicious patients in a fast and effective manner.
关键词：Internet of (ings (IoT);diagnosis of COVID-19;deep transfer learning;medical treatment and Artificial Intelligent
