No abstract

In recent years, federated learning has been believed to play a considerable role in cross-silo scenarios (e.g., medical institutions) due to its privacy-preserving properties. However, the non-IID problem in federated learning between medical institutions is common, which degrades the performance of traditional federated learning algorithms. To overcome the performance degradation problem, a novelty distribution information sharing federated learning approach (FedDIS) to medical image classification is proposed that reduce non-IIDness across clients by generating data locally at each client with shared medical image data distribution from others while protecting patient privacy. First, a variational autoencoder (VAE) is federally trained, of which the encoder is uesd to map the local original medical images into a hidden space, and the distribution information of the mapped data in the hidden space is estimated and then shared among the clients. Second, the clients augment a new set of image data based on the received distribution information with the decoder of VAE. Finally, the clients use the local dataset along with the augmented dataset to train the final classification model in a federated learning manner. Experiments on the diagnosis task of Alzheimer’s disease MRI dataset and the MNIST data classification task show that the proposed method can significantly improve the performance of federated learning under non-IID cases.

No abstract

A novel strain, Bacillus fusiformis CGMCC1347, was utilized successfully to transform isoeugenol to vanillin and the product inhibition could be well avoided by using immobilized cells in the isoeugenol/aqueous biphasic system. The Bacillus fusiformis CGMCC1347 cells were entrapped into sodium alginate under conditions of 2.5% sodium alginate, 10% cells and 0.1 mol l-1 CaCl2. The optimum pH for free cells and immobilized cells were 4.0 and 3.5, respectively, and the optimum reaction temperature for both free and immobilized cells was 37 °C. The pH stabilities of free cells and immobilized cells were good at all investigated pH levels. For thermal stability, free cells were stable at 50°C60°C and the immobilized cells were stable at 50°C 80°C. The half-life of the immobilized cells was more than 25 d, comparing with less than 14 d for the free cells at 4°C.

No abstract