Characteristics of deformation and damage of surrounding rock along the top roadway in the working face of an isolated island and its evolution law.

This study investigates the deformation and damage characteristics of the surrounding rock along the top return mining roadway of an isolated island working face at different stages and reveals its damage mechanism and evolution law. Utilizing a mine in Yangquan City, Shanxi Province, China, as the engineering background, this research employs FLAC 3D numerical simulation and on-site measurements. The findings suggest that the evolution of the plastic zone along the top roadway of the 15,106 island face is largely similar during both the excavation and mining periods. The plastic zones on either side of the roadway are expanding asymmetrically and gradually merging into the plastic zone of the coal pillar. In the destructive stage, the sub-gangs of the roadway are penetrated, indicating the progression into the plastic zone. The investigation points to extensive damage on the larger side of the roadway, the development of fissures, and the significant depth of damage as primary causes of roadway deformation. Moreover, the extent of the plastic zones on both sides of the roadway correlates positively with their relative distance. Continuous monitoring reveals an ongoing increase in roadway displacement, consistent with general observations in coal mining. The results provide valuable insights for optimizing support structures in similar mining environments.

Edge Devices Clustering for Federated Visual Classification: A Feature Norm Based Framework.

Federated learning is a privacy-preserving distributed learning paradigm where multiple devices collaboratively train a model, which is applicable to edge computing environments. However, the non-IID data distributed in multiple devices degrades the performance of the federated model due to severe weight divergence. This paper presents a clustered federated learning framework named cFedFN for visual classification tasks in order to reduce the degradation. Especially, this framework introduces the computation of feature norm vectors in the local training process and divides the devices into multiple groups by the similarities of the data distributions to reduce the weight divergences for better performance. As a result, this framework gains better performance on non-IID data without leakage of the private raw data. Experiments on various visual classification datasets demonstrate the superiority of this framework over the state-of-the-art clustered federated learning frameworks.

Balanced Federated Semisupervised Learning With Fairness-Aware Pseudo-Labeling.

Federated semisupervised learning (FSSL) aims to train models with both labeled and unlabeled data in the federated settings, enabling performance improvement and easier deployment in realistic scenarios. However, the nonindependently identical distributed data in clients leads to imbalanced model training due to the unfair learning effects on different classes. As a result, the federated model exhibits inconsistent performance on not only different classes, but also different clients. This article presents a balanced FSSL method with the fairness-aware pseudo-labeling (FAPL) strategy to tackle the fairness issue. Specifically, this strategy globally balances the total number of unlabeled data samples which is capable to participate in model training. Then, the global numerical restrictions are further decomposed into personalized local restrictions for each client to assist the local pseudo-labeling. Consequently, this method derives a more fair federated model for all clients and gains better performance. Experiments on image classification datasets demonstrate the superiority of the proposed method over the state-of-the-art FSSL methods.

High-quality blind defocus deblurring of multispectral images with optics and gradient prior.

This paper presents a blind defocus deblurring method that produces high-quality deblurred multispectral images. The high quality is achieved by two means: i) more accurate kernel estimation based on the optics prior by simulating the simple lens imaging, and ii) the gradient-based inter-channel correlation with the reference image generated by the content-adaptive combination of adjacent channels for restoring the latent sharp image. As a result, our method gains the prominence on both effectiveness and efficiency in deblurring defocus multispectral images with very good restoration on the obscure details. The experiments on some multispectral image datasets demonstrate the advantages of our method over state-of-the-art deblurring methods.