Avoiding catastrophic overfitting in fast adversarial training with adaptive similarity step size.

Adversarial training has become a primary method for enhancing the robustness of deep learning models. In recent years, fast adversarial training methods have gained widespread attention due to their lower computational cost. However, since fast adversarial training uses single-step adversarial attacks instead of multi-step attacks, the generated adversarial examples lack diversity, making models prone to catastrophic overfitting and loss of robustness.

Subwavelength dielectric waveguide for efficient travelling-wave magnetic resonance imaging.

Magnetic resonance imaging (MRI) has diverse applications in physics, biology, and medicine. Uniform excitation of nuclei spins through circular-polarized transverse magnetic component of electromagnetic field is vital for obtaining unbiased tissue contrasts. However, achieving this in the electrically large human body poses a significant challenge, especially at ultra-high fields (UHF) with increased working frequencies (≥297 MHz).

An improved gene expression programming algorithm for function mining of map-reduce job execution in catenary monitoring systems.

Gene expression programming (GEP) is one of the most prominent algorithms in function mining. In order to obtain a more accurate function model in configuration parameters-execution efficiency (CP-EE) of map-reduce job in the high-speed railway catenary monitoring system, this paper proposes a novel algorithm, called GEP based on multi-strategy (MS-GEP). Compared to traditional GEP, the proposed algorithm can escape premature convergence and jump out of local optimum.

Pantograph Detection Algorithm with Complex Background and External Disturbances.

As an important equipment for high-speed railway (HSR) to obtain electric power from outside, the state of the pantograph will directly affect the operation safety of HSR. In order to solve the problems that the current pantograph detection method is easily affected by the environment, cannot effectively deal with the interference of external scenes, has a low accuracy rate and can hardly meet the actual operation requirements of HSR, this study proposes a pantograph detection algorithm. The algorithm mainly includes three parts: the first is to use you only look once (YOLO) V4 to detect and locate the pantograph region in real-time; the second is the blur and dirt detection algorithm for the external interference directly affecting the high-speed camera (HSC), which leads to the pantograph not being detected; the last is the complex background detection algorithm for the external complex scene "overlapping" with the pantograph when imaging, which leads to the pantograph not being recognized effectively.

Corrigendum: Dislocation Strengthening without Ductility Trade-off in Metastable Austenitic Steels.

This corrects the article DOI: 10.1038/srep35345.

Dislocation Strengthening without Ductility Trade-off in Metastable Austenitic Steels.

Strength and ductility are mutually exclusive if they are manifested as consequence of the coupling between strengthening and toughening mechanisms. One notable example is dislocation strengthening in metals, which invariably leads to reduced ductility. However, this trend is averted in metastable austenitic steels.

Application of stochastic method to optimum design of energy-efficient induction motors with a target of LCC.

For an energy-efficient induction machine, the life-cycle cost (LCC) usually is the most important index to the consumer. With this target, the optimization design of a motor is a complex nonlinear problem with constraints. To solve the problem, the authors introduce a united random algorithm.