No abstract

No abstract

Nowadays, with the gradual development of intelligent transportation and the widespread popularity of private cars, the Internet of Vehicles (IoV) technology is gradually coming to maturity. However, the development of smart cars has been accompanied by a concomitant increase in the amount of media as well as video games in the vehicle, and an explosion in the demand for computational resources. Since smart cars have limited computing resources of their own, they cannot store a large number of pending tasks in their own queues, so they cannot compute the large number of requests generated by the vehicles themselves. The lack of computing resources can be better solved with the help of edge servers, and the distribution of edge servers close to the user side of the road can also effectively achieve real-time for resource requests, but the high energy consumption generated during processing is also a challenge we must face. To address this challenge, a joint task offloading approach based on mobile edge computing and fog computing (EFTO) proposed in this paper. Technically, the location of the processing task is first obtained by getting the route of the computing task, thus finding the complete routing information of the task from the initial location to the target location. Then, a genetic algorithm is used to implement a multi-objective optimization problem to reduce the time and energy consumption during offloading and processing. Finally, the effectiveness of EFTO is demonstrated through comparative experiments, which shows a reduction in time consumption and an optimization of energy consumption compared to other offloading methods.

In this paper, a novel multi-scale deep residual shrinkage network (MS-DRSN) is proposed for signal denoising and atrial fibrillation (AF) recognition. Signal denoising is done by multi-scale threshold denoising module (MS-TDM), which consists of two parts: threshold acquisition and threshold denoising. The thresholds are automatically obtained through the global attention module constructed by the neural network. Threshold denoising chooses Garrote as the threshold function, which combines the advantages of soft and hard thresholding. The multi-scale features consist of global attention module and local attention module, and then the multi-scale features are denoised using the acquired thresholds and threshold functions, and the AF recognition task is finally completed in the Softmax layer after the superposition of multiple MS-TDMs. An adaptive synthetic sampling (ADASYN) algorithm is also used to oversample the dataset and achieve data category balancing by generating new samples, which improves the accuracy of AF recognition and alleviates the overfitting of the neural network. This method was experimented and validated on the PhysioNet2017 dataset. The experimental results show that the approach achieves an accuracy of 0.894 and an [Formula: see text] score of 0.881, which is better than current machine learning and deep learning models.

No abstract