IEEE

Class Incremental Fault Diagnosis Under Limited Fault Data via Supervised Contrastive Knowledge Distillation

Abstract: Class-incremental fault diagnosis requires a model to adapt to new fault classes while retaining previous knowledge. However, limited research exists for imbalanced and long-tailed data.

Midland Ranks in Top 35% Assessed for Sustainability Performance, Earns EcoVadis Bronze Medal

Midland has earned the EcoVadis Bronze Medal for sustainability performance, placing the company in the top 35% of more ...
IEEE

Robust Federated Learning Client Selection With Combinatorial Class Representations and Data Augmentation

Abstract: The federated learning (FL) client selection scheme can effectively mitigate global model performance degradation caused by the random aggregation of clients with heterogeneous data.