Journal
ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS
Volume 16, Issue 2, Pages -Publisher
ASSOC COMPUTING MACHINERY
DOI: 10.1145/3341095
Keywords
Multiple sclerosis; DenseNet; deep neural network; transfer learning; deep learning; precomputation; composite learning factor; simple learning factor
Categories
Funding
- Henan Key Research and Development Project [182102310629]
- Natural Science Foundation of China [61602250, 11502090, U1711263, U1811264]
- National Key Research and Development Plan [2017YFB1103202]
- Guangxi Key Laboratory of Trusted Software [kx201901]
- Natural Science Foundation of Zhejiang Province [Y18F010018]
- Fundamental Research Funds for the Central Universities [CDLS-2020-03]
- Key Laboratory of Child Development and Learning Science (Southeast University), Ministry of Education
Ask authors/readers for more resources
(Aim) Multiple sclerosis is a neurological condition that may cause neurologic disability. Convolutional neural network can achieve good results, but tuning hyperparameters of CNN needs expert knowledge and are difficult and time-consuming. To identify multiple sclerosis more accurately, this article proposed a new transfer-learning-based approach. (Method) DenseNet-121, DenseNet-169, and DenseNet-201 neural networks were compared. In addition, we proposed the use of a composite learning factor (CLF) that assigns different learning factor to three types of layers: early frozen layers, middle layers, and late replaced layers. [low to allocate layers into those three layers remains a problem. Hence, four transfer learning settings (viz., Settings A, B, C, and D) were tested and compared. A precomputation method was utilized to reduce the storage burden and accelerate the program. (Results) We observed that DenseNet-201-D (the layers from CP to T3 are frozen, the layers of D4 are updated with learning factor of 1, and the final new layers of FCL are randomly initialized with learning factor of 10) can achieve the best performance. The sensitivity, specificity, and accuracy of DenseNet-201-D was 98.27 +/- 0.58, 98.35 +/- 0.69, and 98.31 +/- 0.53, respectively. (Conclusion) Our method gives better performances than state-of-the-art approaches. Furthermore, this composite learning rate gives superior results to traditional simple learning factor (SLF) strategy.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available