In recent years, intelligent driving technology based on vehicle–road cooperation has gradually become a research hotspot in the field of intelligent transportation. There are many studies regarding vehicle perception, but fewer studies regarding roadside perception. As sensors are installed at different heights, the roadside object scale varies violently, which burdens the optimization of networks. Moreover, there is a large amount of overlapping and occlusion in complex road environments, which leads to a great challenge of object distinction. To solve the two problems raised above, we propose RD-YOLO. Based on YOLOv5s, we reconstructed the feature fusion layer to increase effective feature extraction and improve the detection capability of small targets. Then, we replaced the original pyramid network with a generalized feature pyramid network (GFPN) to improve the adaptability of the network to different scale features. We also integrated a coordinate attention (CA) mechanism to find attention regions in scenarios with dense objects. Finally, we replaced the original Loss with Focal-EIOU Loss to improve the speed of the bounding box regression and the positioning accuracy of the anchor box. Compared to the YOLOv5s, the RD-YOLO improves the mean average precision (mAP) by 5.5% on the Rope3D dataset and 2.9% on the UA-DETRAC dataset. Meanwhile, by modifying the feature fusion layer, the weight of RD-YOLO is decreased by 55.9% while the detection speed is almost unchanged. Nevertheless, the proposed algorithm is capable of real-time detection at faster than 71.9 frames/s (FPS) and achieves higher accuracy than the previous approaches with a similar FPS.

Roadside perception is a challenging research area that presents even greater difficulties than vehicle perception. Due to the different locations and angles of cameras, roadside objects exhibit violent multiscale variations, while the vast sensing field introduces more small-scale targets and complex backgrounds, making target recognition more challenging. To address these problems, we focus on position information encoding to achieve accurate roadside object detection by proposing the position enhancement faster network (PEFNet). Based on YOLOv6, the FasterNet Block is introduced into Backbone and Neck networks to provide efficient feature extraction while achieving model lightweight transformation. To improve small target detection performance, a position-aware feature pyramid network (PA-PAN) is proposed to enhance position information encoding, and the SPD-Conv is applied in the PA-PAN to further enhance effective feature extraction. Finally, the TSCODE is integrated into the detection head to achieve accurate target recognition and suppress background noise interference. Experiments on the Rope3D and UA-DETRAC datasets show that our model outperforms advanced YOLOv6, YOLOX, and FCOS in roadside object detection. Compared with YOLOv6, our method improves the mAP0.50 on the Rope3D dataset from 78.18% to 82.39%, with the AP of small objects such as pedestrians increasing by 7.01%. Furthermore, PEFNet reduces the weight of the network by 43.1% while maintaining detection speed at 75fps and achieving higher accuracy than previous algorithms for the same number of frames.

It is commonly the case that a small number of widely used applications make up a large fraction of the workload of HPC centers. Predicting the performance of important applications running on specific processors enables HPC centers to design best performing system configurations and to insure good performance for the most popular applications on new systems. In the analyses presented in this paper we use applications that are widely used on current open science HPC systems. We characterize the performance of these applications across a spectrum of modern processors and then create a mathematical model to predict their behavior on possible future processors. The hardware sensitivity studies required to build the predictive model are carried out in an HPC cloud resource with bare metal access, and we describe the process and advantages of this approach in detail. We define and discuss the mathematical model that we have designed and compare the predicted performance of these codes with the empirical results obtained in different chips. Finally, we also use the model to estimate the efficiency of future chips. The results indicate that the model is able to estimate the performance of these codes with a relatively small error across a fairly wide spectrum of chips.

With the continuous development of the communication industry, there is a shift in real-time services from 4G networks to Delay Tolerable (DT) services in the context of 5G/B5G networks. Additionally, energy consumption control poses significant challenges in the current communication industry. Therefore, we study algorithms and schemes to improve the Energy Efficiency (EE) of DT services in the context of Non-Orthogonal Multiple Access (NOMA) downlink two-user communication system.First, we transformed the EE enhancement problem into a convex optimization problem based on transmission power by derivation. Secondly, we propose to use Approximate Statistical Dynamic Programming (ASDP) algorithm, Deep Deterministic Policy Gradient (DDPG), and Proximal Policy Optimization (PPO) to solve the problem that convex optimization cannot be decided in real time. Finally, we perform an interpretability analysis on whether the decision schemes of the agents trained by the DDPG algorithm and the PPO algorithm are reasonable. The simulation results show that the decisions made by the agent trained by the DDPG algorithm perform better compared to the ASDP algorithm and the PPO algorithm.