• Journal of Nuclear Fuel Cycle and Waste Technology(JNFCWT)
• /
• v.9 no.2
• /
• pp.99-105
• /
• 2011

An integrated model for groundwater flow and radionuclide transport analyses is being developed incorporating six underground silos, an excavated damaged zone (EDZ), and fractured host rock. The model considers each silo as an engineered barrier system (EBS) consisting of a waste zone comprising waste packages and disposal container, a buffer zone, and a concrete lining zone. The EDZ is the disturbed zone adjacent to silos and construction & operation tunnels. The heterogeneity of the fractured rock is represented by a heterogeneous flow field, evaluated from discrete fractures in the fractured host rock. Radionuclide migration through the EBS in silos and the fractured host rock is simulated on the established heterogeneous flow field. The current model enables the optimization of silo design and the quantification of the safety margin in terms of radionuclide release.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.3
• /
• pp.958-979
• /
• 2023

Due to laws, regulations, privacy, etc., between 70-90 percent of providers do not share medical data, forming a "data island". It is essential to collaborate across multiple institutions without sharing patient data. Most existing methods adopt distributed learning and centralized federal architecture to solve this problem, but there are problems of resource heterogeneity and data heterogeneity in the practical application process. This paper proposes a collaborative deep learning modelling method based on the blockchain network. The training process uses encryption parameters to replace the original remote source data transmission to protect privacy. Hyperledger Fabric blockchain is adopted to realize that the parties are not restricted by the third-party authoritative verification end. To a certain extent, the distrust and single point of failure caused by the centralized system are avoided. The aggregation algorithm uses the FedProx algorithm to solve the problem of device heterogeneity and data heterogeneity. The experiments show that the maximum improvement of segmentation accuracy in the collaborative training mode proposed in this paper is 11.179% compared to local training. In the sequential training mode, the average accuracy improvement is greater than 7%. In the parallel training mode, the average accuracy improvement is greater than 8%. The experimental results show that the model proposed in this paper can solve the current problem of centralized modelling of multicenter data. In particular, it provides ideas to solve privacy protection and break "data silos", and protects all data.