Short video streaming platforms widely employ video prefetching to ensure users' quality of experience (QoE), but frequent user swipes lead to massive data wastage, creating a significant financial burden for vendors. Existing academic and industrial solutions fail to strike a balance, often sacrificing either data savings or the authentic user-perceived QoE. We introduce a framework that intelligently reduces streaming data consumption without compromising user experience. The core idea is to make prefetching decisions adaptive to both user swiping behavior and dynamic network conditions. Real-world evaluations show our framework significantly outperforms the state-of-the-art solutions on data wastage as well as user-perceived QoE.

In recent years, the effective utilization of edge servers to assist vehicles in handling compute-intensive and latency-sensitive tasks has emerged as a pivotal concern in Vehicular Edge Computing (VEC). In this paper, we adopt a cooperative approach that leverages the collective capabilities of multiple edge servers. This strategy is designed to effectively manage tasks and alleviate the computational burden imposed on these servers. Specifically, Graph Neural Network (GNN) is applied to extract and classify features such as the geographical locations and communication statuses of multiple edge servers, enabling the selection of the most suitable servers for collaborative task execution. We have utilized solar energy for local computing, effectively achieving environmental protection and reducing the local energy burden on vehicles. Moreover, a novel edge attraction formula is defined to refine the rationality of clustering. In addition, Deep Reinforcement Learning (DRL) is employed to make real-time offloading decisions. To ensure experimental accuracy while mitigating costs, we establish a corresponding digital twin environment to acquire experimental data. By conducting a comparative analysis against three other baseline methods, we effectively reduce task completion time and thus meet the stringent demands of time-sensitive tasks.

The rapid development of Vehicular Edge Computing (VEC) provides great support for Collaborative Vehicle Infrastructure System (CVIS) and promotes the safety of autonomous driving. In CVIS, crowd-sensing data will be uploaded to the VEC server to fuse the data and generate tasks. However, when there are too many vehicles, it brings huge challenges for VEC to make proper decisions according to the information from vehicles and roadside infrastructure. In this paper, a reverse offloading framework is constructed, which comprehensively considers the relationship balance between task completion delay and the energy consumption of User Vehicle (UV). Furthermore, in order to minimize the overall system consumption, we establish an adaptive optimal reverse offloading strategy based on Deep Q-Network (DQN). Simulation results demonstrate that the proposed algorithm can effectively reduce the energy consumption and task delay, when compared with the full local and fixed offloading schemes.

Recently, several Transformer-based methods have been presented to improve image segmentation. However, since Transformer needs regular square images and has difficulty in obtaining local feature information, the performance of image segmentation is seriously affected. In this paper, we propose a novel encoder-decoder network named TCRNet, which makes Transformer, Convolutional neural network (CNN) and Recurrent neural network (RNN) complement each other. In the encoder, we extract and concatenate the feature maps from Transformer and CNN to effectively capture global and local feature information of images. Then in the decoder, we utilize convolutional RNN in the proposed recurrent decoding unit to refine the feature maps from the decoder for finer prediction. Experimental results on three medical datasets demonstrate that TCRNet effectively improves the segmentation precision.