Empirical study on meta-feature characterization for multi-objective optimization problems

Chu, Xianghua; Wang, Jiayun; Li, Shuxiang; Chai, Yujuan; Guo, Yuqiu

doi:10.1007/s00521-022-07302-5

Cited by 5 publications

(1 citation statement)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, deep meta-learning has aroused greater attention to many academics for 6 years in the field of anomaly detection; meta-learning has proven to be an outstanding way to figure out few-shot and cross-domain difficulties in anomaly detection situations. 28,29 Narrowly speaking, two types subclass of architectures can be listed: (1) optimization-metric strategies, (2) model-based solutions 16 ; other scholars pretend to uncover more about meta-representing, meta-optimizing 30 and meta-objective 31 breakthroughs. Additionally, recent research demonstrates an absence of a solution for a classification problem that would speed up the classification process in the hypothesis space.…”

Section: Introductionmentioning

confidence: 99%

Few-shot pump anomaly detection via Diff-WRN-based model-agnostic meta-learning strategy

Zou

Sang

Jiang

et al. 2022

Structural Health Monitoring

View full text Add to dashboard Cite

As a critical component in agriculture, industry, and the military, pump anomaly detection has recently aroused wide attention, which requires deep and abundant development and application. Researchers emphasize deeper networks that are long vast computational resources despite insufficient training samples prepared. To break through this obstacle above, we propose a few-shot model-agnostic meta-learning strategy (MAMLS) model to mitigate the data scarcity problem. Inspired by the diffusive ordinary differential equations (ODEs) and Wide-Resnet (WRN), we made great strides by connecting diffusion (Diff) mechanism and self-adaptive Lr with MAMLS. We generate two classical synthetic datasets (circle and spiral) to clarify the diffusion algorithm’s capability to enhance the relationships and weaken the noise. The experimental results under synthetic data confirm that accuracy quickly reached 99% after several iterations. In an actual case anomaly detection study on the pumps simulation platform, the proposed Diff-WRN-MAMLS brings substantial advantages in saving hardware resources. Compared to current models, our model achieves 98% accuracy in 9-way 25-shot tasks. In the operating efficiency experiment, our algorithm only consumed 14.37 quality factors. The final experiment with four state-of-the-art model-agnostic meta-learning (MAML)-enhanced methods demonstrates the highest reliable test accuracy in different cases, reaching 98.5, 97.8, and 98.4%, respectively. Results showed that the proposed method will generalize surprisingly well in anomaly detection in future research.

show abstract