Data Augmentation of X-ray Images for Automatic Cargo Inspection of Nuclear Items.

As part of establishing a management system to prevent the illegal transfer of nuclear items, automatic nuclear item detection technology is required during customs clearance. However, it is challenging to acquire X-ray images of major nuclear items (e.g., nuclear fuel and gas centrifuges) loaded in cargo with which to train a cargo inspection model. In this work, we propose a new means of data augmentation to alleviate the lack of X-ray training data. The proposed augmentation method generates synthetic X-ray images for the training of semantic segmentation models combining the X-ray images of nuclear items and X-ray cargo background images. To evaluate the effectiveness of the proposed data augmentation technique, we trained representative semantic segmentation models and performed extensive experiments to assess its quantitative and qualitative performance capabilities. Our findings show that multiple item insertions to respond to actual X-ray cargo inspection situations and the resulting occlusion expressions significantly affect the performance of the segmentation models. We believe that this augmentation research will enhance automatic cargo inspections to prevent the illegal transfer of nuclear items at airports and ports.

Feature Selection Method Using Multi-Agent Reinforcement Learning Based on Guide Agents.

In this study, we propose a method to automatically find features from a dataset that are effective for classification or prediction, using a new method called multi-agent reinforcement learning and a guide agent. Each feature of the dataset has one of the main and guide agents, and these agents decide whether to select a feature. Main agents select the optimal features, and guide agents present the criteria for judging the main agents' actions. After obtaining the main and guide rewards for the features selected by the agents, the main agent that behaves differently from the guide agent updates their Q-values by calculating the learning reward delivered to the main agents. The behavior comparison helps the main agent decide whether its own behavior is correct, without using other algorithms. After performing this process for each episode, the features are finally selected. The feature selection method proposed in this study uses multiple agents, reducing the number of actions each agent can perform and finding optimal features effectively and quickly. Finally, comparative experimental results on multiple datasets show that the proposed method can select effective features for classification and increase classification accuracy.

Self-Humidifying Membrane for High-Performance Fuel Cells Operating at Harsh Conditions: Heterojunction of Proton and Anion Exchange Membranes Composed of Acceptor-Doped SnP2O7 Composites.

Here we suggest a simple and novel method for the preparation of a high-performance self-humidifying fuel cell membrane operating at high temperature (>100 °C) and low humidity conditions (<30% RH). A self-humidifying membrane was effectively prepared by laminating together proton and anion exchange membranes composed of acceptor-doped SnP2O7 composites, Sn0.9In0.1H0.1P2O7/Sn0.92Sb0.08(OH)0.08P2O7. At the operating temperature of 100 °C, the electrochemical performances of the membrane electrode assembly (MEA) with this heterojunction membrane at 3.5% RH were better than or comparable to those of each MEA with only the proton or anion exchange membranes at 50% RH or higher.

Study on Control of Polymeric Architecture of Sulfonated Hydrocarbon-Based Polymers for High-Performance Polymer Electrolyte Membranes in Fuel Cell Applications.

Polymer electrolyte membrane fuel cell (PEMFC) is an eco-friendly energy conversion device that can convert chemical energy into electrical energy without emission of harmful oxidants such as nitrogen oxides (NOx) and/or sulfur oxides (SOx) during operation. Nafion®, a representative perfluorinated sulfonic acid (PFSA) ionomer-based membrane, is generally incorporated in fuel cell systems as a polymer electrolyte membrane (PEM). Since the PFSA ionomers are composed of flexible hydrophobic main backbones and hydrophilic side chains with proton-conducting groups, the resulting membranes are found to have high proton conductivity due to the distinct phase-separated structure between hydrophilic and hydrophobic domains. However, PFSA ionomer-based membranes have some drawbacks, including high cost, low glass transition temperatures and emission of environmental pollutants (e.g., HF) during degradation. Hydrocarbon-based PEMs composed of aromatic backbones with proton-conducting hydrophilic groups have been actively studied as substitutes. However, the main problem with the hydrocarbon-based PEMs is the relatively low proton-conducting behavior compared to the PFSA ionomer-based membranes due to the difficulties associated with the formation of well-defined phase-separated structures between the hydrophilic and hydrophobic domains. This study focused on the structural engineering of sulfonated hydrocarbon polymers to develop hydrocarbon-based PEMs that exhibit outstanding proton conductivity for practical fuel cell applications.