Parallel CNN Classification for Human Gait Identification with Optimal Cross Data-set Transfer Learning

Liang, Yuanhao; Yeung, Eric; Hu, Yong

doi:10.1109/civemsa52099.2021.9493669

Cited by 3 publications

(1 citation statement)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The training strategies of freezing middle weight layers, high-weight layers, and no layers achieved comparable accuracy. This result differs from the observation in [63], which suggested that the low-weight layers of a CNN should be frozen because of the different data distributions and low similarity between source domain S D (ImageNet dataset) and target domain T D (our guided wave dataset). When the data distribution in the target domain is different from that in the source domain, the low-weight layers need to be trainable by fine-tuning rather than frozen.…”

Section: The First Guided Wave Monitoring Testcontrasting

confidence: 90%

An efficient approach for guided wave structural monitoring of switch rails via deep convolutional neural network-based transfer learning

Liu¹,

Tang²,

Lv³

et al. 2022

Meas. Sci. Technol.

View full text Add to dashboard Cite

Data-driven approaches in structural health monitoring have received increasing attention, especially advances in deep learning-based methods, which have further driven the development of data-driven damage detection. Due to the limited availability of guided wave samples and the imbalance between data classes, this study proposes a deep convolutional neural network-based transfer learning (DCTL) approach for the structure monitoring of switch rails using guided wave monitoring signals. A pretrained model based on Inception-ResNet-V2 was adopted and fine-tuned. Different methods for converting 1D signals into 2D images were investigated to find the optimal approach that meets practical monitoring requirements. Affine transformations were used for data augmentation to improve generalization ability and to avoid the overfitting of the training model. Two types of guided wave monitoring experiments on the foot and web of switch rails were conducted to evaluate the proposed method against different conventional methods in the field of switch rails. In addition, the DCTL method was investigated, with and without pretrained weights, along with different frozen layers. The classification results show that the proposed method can identify damage in challenging situations and outperforms conventional methods.

show abstract

Section: The First Guided Wave Monitoring Testcontrasting

confidence: 90%