Racetrack Microtron—Pushing the Limits

We consider three types of electron accelerators that can be used for various applications, such as industrial, medical, cargo inspection, and isotope production applications, and that require small- and medium-sized machines, namely classical microtron (CM), race-track microtron (RTM), and multisection linac. We review the principles of their operation, the specific features of the beam dynamics in these machines, discuss their advantages and weak points, and compare their technical characteristics. In particular, we emphasize the intrinsic symmetry of the stability region of microtrons. We argue that RTMs can be a preferable choice for medium energies (up to 100 MeV) and that the range of their potential applications can be widened, provided that the beam current losses are significantly reduced. In the article, we analyze two possible solutions in detail, namely increasing the longitudinal acceptance of an RTM using a higher-order harmonic accelerating structure and improving beam matching at the injection.

Data Augmentation of Backscatter X-ray Images for Deep Learning-Based Automatic Cargo Inspection

Custom inspection using X-ray imaging is a very promising application of modern pattern recognition technology. However, the lack of data or renewal of tariff items makes the application of such technology difficult. In this paper, we present a data augmentation technique based on a new image-to-image translation method to deal with these difficulties. Unlike the conventional methods that convert a semantic label image into a realistic image, the proposed method takes a texture map with a special modification as an additional input of a generative adversarial network to reproduce domain-specific characteristics, such as background clutter or sensor-specific noise patterns. The proposed method was validated by applying it to backscatter X-ray (BSX) vehicle data augmentation. The Fréchet inception distance (FID) of the result indicates the visual quality of the translated image was significantly improved from the baseline when the texture parameters were used. Additionally, in terms of data augmentation, the experimental results of classification, segmentation, and detection show that the use of the translated image data, along with the real data consistently, improved the performance of the trained models. Our findings show that detailed depiction of the texture in translated images is crucial for data augmentation. Considering the comparatively few studies that have examined custom inspections of container scale goods, such as cars, we believe that this study will facilitate research on the automation of container screening, and the security of aviation and ports.

Solutions and constructional modifications of dosimetry systems ofelectron accelerators

The study is designed to present a method of dosimetry system solution in electron accelerators manufactured at the NCBJ Nuclear Equipment Division (HITEC). Two special cases of accelerator applications have been presented - the first using a high-efficiency electron beam in material research and the second using a low-efficiency photon beam in cargo inspection at borders. The article presents constructional modifications of the standardly used ionization chamber, which successfully enabled proper dose measurement in both of the above-mentioned cases.