Medical image segmentation based on neural networks is pivotal in promoting digital health equity. The attention mechanism increasingly serves as a key component in modern neural networks, as it enables the network to focus on regions of interest, thus improving the segmentation accuracy in medical images. However, current attention mechanisms confront an accuracy-complexity trade-off paradox: accuracy gains demand higher computational costs, while reducing complexity sacrifices model accuracy. Such a contradiction inherently restricts the real-world deployment of attention mechanisms in resource-limited settings, thus exacerbating healthcare disparities. To overcome this dilemma, we propose a parameter-free Neighborhood Self-Dissimilarity Attention (NSDA), inspired by radiologists' diagnostic patterns of prioritizing regions exhibiting substantial differences during clinical image interpretation. Unlike pairwise-similarity-based self-attention mechanisms, NSDA constructs a size-adaptive local dissimilarity measure that quantifies element-neighborhood differences. By assigning higher attention weights to regions with larger feature differences, NSDA directs the neural network to focus on high-discrepancy regions, thus improving segmentation accuracy without adding trainable parameters directly related to computational complexity. The experimental results demonstrate the effectiveness and generalization of our method. This study presents a parameter-free attention paradigm, designed with clinical prior knowledge, to improve neural network performance for medical image analysis and contribute to digital health equity in low-resource settings. The code is available at [https://github.com/ChenJunren-Lab/Neighborhood-Self-Dissimilarity-Attention](https://github.com/ChenJunren-Lab/Neighborhood-Self-Dissimilarity-Attention).

Defect detection in rail fasteners is crucial for train safety, as defective fasteners can cause derailments and severe safety incidents. However, Existing algorithms often struggle in various real-world scenarios due to challenges such as obscured fasteners, motion blur in images, varying camera angles, and fasteners submerged in water. To address these challenges, we propose a Multi-scale CNN-Transformer Hybrid Network for Rail Fastener Defect Detection (MCHNet-RF2D), specifically designed to identify fastener defects in complex environments. Our approach constructs an efficient CNN block and a multi-scale Vision Transformer block to alternately extract local detail features and global semantic features of the fasteners. These features are seamlessly integrated through multi-scale fusion to enhance defect recognition robustness. By combining comprehensive global recognition with detailed local defect detection, MCHNet-RF2D outperforms existing CNN-Transformer hybrid networks by 2.8% and surpasses current fastener defect detection algorithms by 2.9%. In practical deployment on over 40 trains, our model successfully detected more than 2,000 fastener defects, demonstrating its effectiveness in diverse and challenging conditions.

Mobile-edge computing (MEC) has been garnering considerable level of interests by processing computation tasks nearby mobile devices (MDs). With limited computation and communication resources and strict task deadline, balancing the energy consumption and time delay of computational tasks will be highly focused. MDs deployed energy harvesting (EH) modules can always provide service to continuous task requests, and finer-grained offloading schemes of the MEC system will significantly affect the time delay of computation tasks. However, when combined them together, the energy causal constraint and the coupling between offloading ratios and resources allocation will cause new challenges for the computation offloading problem. To address these issues, we investigate the partial computation offloading schemes for multiple MDs enabled by harvested energy in MEC. Specifically, we build models for two computing modes and EH process. Subsequently, we formulate a nonconvex optimization problem by minimizing the energy consumption of all the MDs while satisfying the constraint of time delay. Furthermore, we propose and design a novel algorithm based on the Lyapunov optimization to achieve optimal solution, that is, Lyapunov-optimization-based partial computation offloading for multiuser (LOMUCO). Then, we take the long-term average energy consumption and the discarding ratio of computation tasks as the quantitative metrics and conduct extended simulation experiments to confirm the performance of LOMUCO. Finally, compared to several baseline or state-of-the-art algorithms, including local computing all (LCA), offloading computing all (OCA), randomly partial computation offloading (RPCO), and Lyapunov-optimization-based dynamic computation offloading (LODCO), we can demonstrate the superiority of LOMUCO.