In the last three decades, the development of functional magnetic resonance imaging (fMRI) has significantly contributed to the understanding of the brain, functional brain mapping, and resting-state brain networks. Given the recent successes of deep learning in various fields, we propose a 3D-CNN-LSTM classification model to diagnose health conditions with the following classes: condition normal (CN), early mild cognitive impairment (EMCI), late mild cognitive impairment (LMCI), and Alzheimer’s disease (AD). The proposed method employs spatial and temporal feature extractors, wherein the former utilizes a U-Net architecture to extract spatial features, and the latter utilizes long short-term memory (LSTM) to extract temporal features. Prior to feature extraction, we performed four-step pre-processing to remove noise from the fMRI data. In the comparative experiments, we trained each of the three models by adjusting the time dimension. The network exhibited an average accuracy of 96.4% when using five-fold cross-validation. These results show that the proposed method has high potential for identifying the progression of Alzheimer’s by analyzing 4D fMRI data.

A double-ended guillotine break at a direct vessel injection line of the ATALS facility has been evaluated with the MARS-KS thermal hydraulic system analysis code. The results are validated against the ATLAS experimental data provided under the First Domestic Standard Problem for Code Assessment (DSP-01) project, indicating that the calculation can generally explain the important phenomena observed in the experiment. The major difference is that the simulation predicts a 2nd peak for the peak cladding temperature, which was not measured during the experiment. Further investigation for the core and downcomer liquid levels reveals that the 2nd peak happens because of incorrect prediction of the downcomer wall temperature caused by the lack of information for heat loss through the downcomer wall in the experiment. This is confirmed by a calculation with the downcomer wall temperature measured at the experiment modeled as a boundary condition. The results with modified downcomer wall boundary conditions show a good prediction of the PCT behavior, indicating that additional heat loss measurements at the downcomer are required for a better understanding of the complex phenomena occurring in the ATLAS downcomer.

Kori Unit 1, which was permanently shut down in 2017, is expected to be the first decommissioned commercial nuclear power plant (NPP) in Korea. Operating NPPs designate radiation‐controlled areas (RCAs) to protect workers from radiological hazards and provide appropriate measures. Decommissioning RCAs (DRCAs) in NPPs being decommissioned should also be designated by considering the radiological characteristics of workplaces and exposure routes of decommissioning workers, such as external and internal exposure. However, the criteria for the DRCAs in decommissioning Kori Unit 1 are presently the same as those during normal operation, according to the public‐hearing material of the final decommissioning plan for Kori Unit 1. This study analyzed criteria for RCAs in all Korean NPPs to propose criteria for DRCAs in decommissioning NPPs. Analysis results show that RCAs are classified into four, five, six, and eight zones in Korean pressurized water reactors with respective external radiation dose rates. The RCAs in Korean pressurized heavy water reactors are classified into six zones with external dose rates and derived air concentrations of tritium. This study proposes three classifications of DRCAs to keep occupational exposure as low as reasonably achievable while considering potential exposure routes, that is, external exposure, airborne contamination, and surface contamination areas. First, the external exposure areas are classified into several zones according to the levels of external radiation dose rates. Second, the airborne contamination areas are designated to prevent internal exposure to workers from the inhalation of radioactive material in the air during cutting and demolition. Last, the surface contamination areas are designated to minimize the skin contamination of workers as radioactive dust in the air is deposited on the surface of facilities and equipment over time.

No abstract