Search

Accurate pear sorting plays a crucial role in ensuring the quality of pears and increasing the sales of them. In the domain of intelligent pear sorting, precise target detection of pears is imperative. However, practical implementation faces challenges in achieving adequate accuracy in pear target detection due to the limitations of computational resources in embedded devices and the occurrence of occlusion among pears. To solve this problem, we built an image acquisition system based on pear sorting equipment and created a pear dataset containing 34,598 pear images under laboratory conditions. The dataset was meticulously annotated using the LabelImg software, resulting in a total of 154,688 precise annotations for pears, pear stems, pear calyxes, and pear defects. Furthermore, we propose an Extremely Compressed Lightweight Model for Pear Object Detection (ECLPOD) based on YOLOv7's pipeline to assist in the pear sorting task. Firstly, the Hierarchical Interactive Shrinking Network (HISNet) was proposed, which contributed to efficient feature extraction with a limited amount of computation and parameters. The Bulk Feature Pyramid (BFP) module was then proposed to enhance pear contour information extraction during feature fusion. Finally, the Accuracy Compensation Strategy (ACS) was proposed to improve the detection capability of the model, especially for identification of the calyces and stalks of pears. The experimental results indicate that the ECLPOD achieves 90.1% precision (P) and 85.52% mAP50 with only 0.58 million parameters and 1.3 GFLOPs of computation in the homemade pear dataset in this paper. Compared with YOLOv7, the number of parameters and the amount of computation for the ECLPOD are compressed to 1.5% and 1.3%, respectively. Compared with other mainstream methods, the ECLPOD achieves an optimal trade-off between accuracy and complexity. This suggests that the ECLPOD is superior to these existing approaches in the field of object detection for assisting pear sorting tasks with good potential for embedded device deployment. [ABSTRACT FROM AUTHOR]

Device-to-Multi-Device (D2MD) communication shows great advantages in maximizing the offloading of Base Station (BS). At present, the main research works are based on mathematical model optimization methods, viz, spatial distribution model and content request model of Content Request Users (CRUs), and social relationship intensity model, which can estimate the D2MD transmission performance in order to reduce the BS traffic to a greater extent by optimizing the D2MD user grouping. However, for the real-world system, the three models are complex and difficult to describe in realistic scenario; for Seed Users (SUs), they have inherent selfishness, i.e., they want to communicate with lower transmission power; for CRU, they want to obtain the content in the shortest possible waiting time. Hence, the problem that how to reduce the BS traffic by D2MD user grouping and incentive SUs to contribute transmission power becomes very difficult to solve. In order to solve it, we describe the D2MD user grouping with transmission power control processes in this scenario, and then model the problem as a joint problem of game and long-term optimization. Then, we use matching-Stackelberg hierarchical game and Q-learning algorithm to solve it. Specially, at first, we propose a matching and incentive-based power control method, which maximize the myopic offloading of BS with lower transmission power of SUs, i.e., higher energy efficiency; Secondly, we design a D2MD user grouping algorithm based on multi-agent deep Q-learning algorithm, in order to maximize the long-term average offloading of BS. Finally, the results of simulation experiments show that the proposed algorithm can maximize the long-term average offloading of BS while access more CRUs with quality of service-guaranteed, and it can maximize the energy efficiency of SUs as well. [ABSTRACT FROM AUTHOR]