| Autor: |
Alkhawaldeh, Rami S., Al-Dabet, Saja |
| Zdroj: |
Multimedia Tools & Applications; Apr2024, Vol. 83 Issue 13, p37743-37770, 28p |
| Abstrakt: |
One of the challenges that arise when utilizing real-time reaction services, such as constructing deep learning models within the Internet of Medical Things (IoMT) infrastructure, is effectively balancing the computation load between the cloud and fog computing layers. This paper proposes a unified framework of offline training and online response to the healthcare professional. The framework gathers medical images from various heterogeneous IoMT devices and then arranges them into homogeneous locations in the cloud, using a stage-one classification stage (or offline training). Furthermore, the stage-two classification (or online response) is employed to detect the type of cancer for each homogeneous location containing the same image type within the cloud. To evaluate the framework, we conducted extensive experiments on six well-known cancer datasets of multiple types. The stage-one classification shows superior results of the error rates for the InceptionResNetV2 and DenseNet201 pre-trained transfer learning models of 0.33% and 0.43% with accuracy values of 99.67% and 99.57% respectively. In the stage-two classification, the results show different performances on each dataset. The point is that each dataset is organized separately which helps in studying the influence of pre-trained transfer learning models and improving their performance in the absence of intervention and bias in datasets. [ABSTRACT FROM AUTHOR] |
| Databáze: |
Complementary Index |
| Externí odkaz: |
|
Full text from SpringerLink