The adverse drug reactions (ADRs) predicted based on the biased records in FAERS (U.S. Food and Drug Administration Adverse Event Reporting System) may mislead diagnosis online. Generally, such problems are solved by optimizing reporting odds ratio (ROR) or proportional reporting ratio (PRR). However, these methods that rely on statistical methods cannot eliminate the biased data, leading to inaccurate signal prediction. In this paper, we propose PFed-signal, a federated learning-based signal prediction model of ADR, which utilizes the Euclidean distance to eliminate the biased data from FAERS, thereby improving the accuracy of ADR prediction. Specifically, we first propose Pfed-Split, a method to split the original dataset into a split dataset based on ADR. Then we propose ADR-signal, an ADR prediction model, including a biased data identification method based on federated learning and an ADR prediction model based on Transformer. The former identifies the biased data according to the Euclidean distance and generates a clean dataset by deleting the biased data. The latter is an ADR prediction model based on Transformer trained on the clean data set. The results show that the ROR and PRR on the clean dataset are better than those of the traditional methods. Furthermore, the accuracy rate, F1 score, recall rate and AUC of PFed-Signal are 0.887, 0.890, 0.913 and 0.957 respectively, which are higher than the baselines.
Privacy is one of the bottlenecks that hinder the applications (e.g. vehicle navigation) of blockchain-UCAN. A sharded blockchain protects the privacy of vehicle data to a certain extent. However, the unbalanced shard loads leads to low throughput, and the feature extraction in blockchain-UCAN is still poor. In this paper, an optimal image binarisation method OTSU-GK is proposed to enhance image features while reducing the amount of uploaded data to further improve the throughput. Specifically, OTSU-GK employs a Gaussian kernel method, where the parameters are optimized through grid search, to optimize the calculation of the threshold. In addition, we design a Node Load Score-based (NLS) sharding blockchain, which considers the number of historical transactions, transaction types, transaction frequency and other metrics, to balance the sharding loads and further improve the throughput. The experimental results show that OTSU-GK pproximately a 50% improvement in metrics and 83% improvement in throughput compared to other methods.