Recently, Wireless Rechargeable Sensor Networks (WRSNs) have emerged as a promising solution to address the energy limitations of wireless sensor networks. In practical applications of WRSNs, environmental objects are ubiquitous, reflecting radio waves and causing them to reach sensors via multiple paths. These multipath effects significantly impact the power intensity received by sensors. In this paper, we study a fundamental issue of charGing schEduling with mulTipath effectS (GETS), that is, how to schedule a mobile charger by comprehensively considering the multipath effects to maximize the overall charging utility. To this end, we first establish a charging model with environmental objects to investigate the impact of multipath effects on power distribution. Then, we propose a charging scheduling scheme that not only selects a series of sojourn locations for the MC (Mobile Charger) to maximize the total power received by nearby sensors but also construct a charging path that avoids environmental objects. We conduct extensive simulations as well as indoor and outdoor field experiments to evaluate the performance of our scheme. The results demonstrate that, on average, our scheme outperforms baseline algorithms by 48.87%

With the maturation of wireless power transfer technology, Wireless Rechargeable Sensor Networks (WRSNs) have been able to provide a continuous energy supply by scheduling a Mobile Charger (MC). However, traditional charging modes suffer from fixed charging areas that lack the ability to adapt to variable sensor distributions. This inflexibility yields a gap between energy supply and utilization, resulting in relatively low charging efficiency. To address this issue, we propose an adaptive charging mode that utilizes beam steering to dynamically adjust the charging area, thereby catering to different sensor distributions encountered during the charging process. First, we build a dual-symmetric steering charging model to describe the characteristics of dynamic beam steering, enabling precise manipulation of the charging area. Then, we develop a charging power discretization based on steering angle and charging distance to obtain a finite feasible charging strategy set for MC. We reformalize charging utility maximization under energy constraints as a submodular function maximization problem, and propose an approximate algorithm to solve it. Lastly, simulations and field experiments demonstrate that our scheme outperforms other algorithms by 43.9% on average.

Breast cancer is a global health concern for women. The detection of breast cancer in its early stages is crucial, and screening mammography serves as a vital leading-edge tool for achieving this goal. In this study, we explored the effectiveness of Resnet 50v2 and Resnet 152v2 deep learning models for classifying mammograms using EMBED datasets for the first time. We preprocessed the datasets and utilized various techniques to enhance the performance of the models. Our results suggest that the choice of model architecture depends on the dataset used, with ResNet152 outperforming ResNet50 in terms of recall score. These findings have implications for cancer screening, where recall is an important metric. Our research highlights the potential of deep learning to improve breast cancer classification and underscores the importance of selecting the appropriate model architecture.

Cataract is one of the most serious eye diseases leading to blindness. Early detection and treatment can reduce the rate of blindness in cataract patients. However, the professional knowledge of ophthalmologists is necessary for the clinical cataract detection. Therefore, the potential costs may make it difficult for the widespread use of cataract detection to prevent blindness. Artificial intelligence assisted diagnosis based on medical images has attracted more and more attention of researchers. Many studies have focused on the use of pre-defined feature sets for cataract classification, but the predefined feature sets may be incomplete or redundant. On account of the aforementioned issues, some studies have proposed deep learning methods to automatically extract image features, but all based on global features and none has analyzed the layer-by-layer transformation process of the middle-tier features. This paper uses convolutional neural networks (CNN) to learn useful features directly from input data, and deconvolution network method is employed to investigate how CNN characterizes cataract layer-by-layer. We found that compared to the global feature set, the detail vascular information, which is lost after multi-layer convolution calculation also plays an important role in cataract grading task. And this finding fits with the morphological definition of fundus image. Through the finding, we gained insights into the design of hybrid global-local feature representation model to improve the recognition performance of automatic cataract grading.