In recent years, the application of federated learning to medical image classification has received much attention and achieved some results in the study of semi-supervised problems, but there are problems such as the lack of thorough study of labeled data, and serious model degradation in the case of small batches in the face of the data category imbalance problem. In this paper, we propose a federated learning method using a combination of regularization constraints and pseudo-label construction, where the federated learning framework consists of a central server and local clients containing only unlabeled data, and labeled data are passed from the central server to each local client to take part in semi-supervised training. We first extracted the class imbalance factors from the labeled data to participate in the training to achieve label constraints, and secondly fused the labeled data with the unlabeled data at the local client to construct augmented samples, looped through to generate pseudo-labels. The purpose of combining these two methods is to select fewer classes with higher probability, thus providing an effective solution to the class imbalance problem and improving the sensitivity of the network to unlabeled data. We experimentally validated our method on a publicly available medical image classification data set consisting of 10,015 images with small batches of data. Our method improved the AUC by 7.35% and the average class sensitivity by 1.34% compared to the state-of-the-art methods, which indicates that our method maintains a strong learning capability even with an unbalanced data set with fewer batches of trained models.
Waste human hair was carbonized into carbon sheets by a simple carbonization method, which was studied as gas sensing materials for the first time. The effect of carbonization temperature on the structure and gas sensing properties of hair-based carbon sheet was studied by scanning electron microscope, X-ray diffraction, infrared spectrum, Raman spectrum, and gas-sensitive tester. The results showed that the carbonization temperature had a significant effect on the structure and gas sensing performance of carbon sheets, which were doped with K, N, P, and S elements during carbonization. However, the sensor of the carbon sheet does not show good selectivity among six target gases. Fortunately, the carbon sheets prepared at different temperatures have different responses to the target gases. The sensor array constructed by the carbon sheets prepared at different temperatures can realize the discriminative detection of a variety of target gases. For the optimized carbon sheet, the theoretical limit of detection of hydrogen peroxide is 0.83 ppm. This work provides a reference for the resource utilization of waste protein and the development of gas sensors.