Aiming to solve the challenges of difficult training, mode collapse in current generative adversarial networks (GANs), and the efficiency issue of requiring multiple samples for Denoising Diffusion Probabilistic Models (DDPM), this paper proposes a satellite remote sensing grayscale image colorization method using a denoising GAN. Firstly, a denoising optimization method based on U-ViT for the generator network is introduced to further enhance the model’s generation capability, along with two optimization strategies to significantly reduce the computational burden. Secondly, the discriminator network is optimized by proposing a feature statistical discrimination network, which imposes fewer constraints on the generator network. Finally, grayscale image colorization comparative experiments are conducted on three real satellite remote sensing grayscale image datasets. The results compared with existing typical colorization methods demonstrate that the proposed method can generate color images of higher quality, achieving better performance in both subjective human visual perception and objective metric evaluation. Experiments in building object detection show that the generated color images can improve target detection performance compared to the original grayscale images, demonstrating significant practical value.
Mobile edge computing (MEC) systems empowered by energy harvesting (EH) significantly enhance sustainable computing capabilities for mobile devices (MDs). This paper investigates a multi-user multi-server MEC network, in which energy-constrained users dynamically harvest ambient energy to flexibly allocate resources among local computation, task offloading, or intentional task discarding. We formulate a stochastic optimization problem aiming to minimize the time-averaged weighted sum of execution delay, energy consumption, and task discard penalty. To address the energy causality constraints and temporal coupling effects, we develop a Lyapunov optimization-based drift-plus-penalty framework that decomposes the long-term optimization into sequential per-time-slot subproblems. Furthermore, to overcome the curse of dimensionality in high-dimensional action, we propose hierarchical deep reinforcement learning (DRL) solutions incorporating both Q-learning with experience replay and asynchronous advantage actor–critic (A3C) architectures. Extensive simulations demonstrate that our DRL-driven approach achieves lower costs compared with conventional model predictive control methods, while maintaining robust performance under stochastic energy arrivals and channel variations.
3 March 2026 in Journal of Analytical Atomic Spectrometry
Black powder from spent lithium-ion batteries is processed via pressing and analyzed using deep learning models (MobileNet, Transformer, ResNet) for feature selection. The system achieves 99.67% accuracy with embedded system compatibility, and SHAP is used for result interpretation.
Visual attention is one of the fundamental abilities underlying human perception, learning, and goal-directed behavior, enabling individuals to prioritize information relevant to current goals while effectively suppressing irrelevant or competing stimuli. While previous studies have revealed the role of top-down attentional control mechanisms in visual processing, particularly in the anticipatory activation of brain regions during target expectation, the precise influence of this regulation on the neural decoding of targets and distractors remains underexplored. This study combines a classical visual search task with a developed multivariate decoding framework to systematically investigate the effects of distractor interference on the neural decoding of target location under conditions of prior spatial knowledge. Through multivariate decoding analysis, we compared the decoding accuracy of target locations in both T-only (only one unique shape-defined target) and T-with-D (shape-defined target with a distractor sharing the same shape) conditions. We found that distractor interference significantly reduced the precision of target location decoding and diminished the temporal generalization of target representations, indicating that interference disrupted the stability of neural decoding. Furthermore, decoding accuracy in both conditions was positively correlated with the amplitude of the N2pc component, further demonstrating the critical role of spatially selective attention in target location decoding. Although preprocessing was applied to the existing decoding methods in this study, it enhanced both the stability and decoding accuracy without affecting the overall trend of the results. Overall, these findings suggest that information-based multivariate decoding offers important empirical support for understanding the neural mechanisms of internal spatial attention under distraction.