Through an analysis of the Faster R-CNN [1] and SSD [2] algorithm models and their applications in image recognition, various advantages and limitations were discovered. Simultaneously, a novel image recognition technique, based on the fusion of Faster R-CNN and SSD, was proposed for application in medical image recognition. Furthermore, the principles and apparatus for medical virus diagnosis using this technique were designed. Validation experiments were conducted to achieve efficient recognition and diagnosis of white blood cells.

In recent years, 5G/5G-A technology has fast developed and found widespread deployment, meeting the diverse requirements of application scenarios across various industries. In this paper, we introduce the principle and advantages of 5G/5G-A private network. Then, we introduce the construction of 5G/5G-A private network. Furthermore, we design an intelligent operation system of 5G/5G-A private network, which includes six key modules with over twenty functionalities. This intelligent operation system can effectively support the operation of 5G/5G-A private network. Lastly, this paper introduces the 5G/5G-A private network applications in a realistic vehicle factory.

With the development of 5G and AI technology, the infectious virus detection framework system based on the combination of 5G MEC and medical sensors can effectively assist in the intelligent detection and control of influenza viruses such as COVID-19. Employing the edge computing and 5G+MEC model, the virus AI model is trained for the collected influenza virus data. Then the virus AI model can be used to evaluate the virus patients on the local edge computing service platform. Therefore, this paper introduces an algorithm and resource allocation, which uses 5G functions (especially, low latency, high bandwidth, wide connectivity, and other functions) to achieve local chest X-ray or CT scan images to detect COVID-19. Meanwhile, this paper also compares the computational efficiency of different algorithms in the 5G edge AI-based infectious virus detection framework, in this way to select the best algorithm and resource allocation.

5G mobile edge computing (MEC) can be used in intelligent manufacturing. In complex industrial application scenarios, this paper tries to address the problem of energy consumption optimization of customer task unloading and resource rescheduling. Specifically, we employ 5G wireless private network and MEC computing resources between 5G private network and MEC. Then, we use game theory algorithm to optimize the user task unloading and resource rescheduling allocation, which is mainly measured by the minimum total time required to complete the task and energy consumption. The problem is a combinatorial nonlinear programming algorithm, involving joint optimization of task offloading decision, user side's uplink transmission energy consumption, MEC server's resource allocation. The solution includes the resource allocation of fixed task unloading decision, and the resource allocation optimization of task unloading. Results verify the proposed solution can improve the efficiency of task scheduling.

The stability of passive antenna feed operation is an important indicator to measure the quality of wireless network. On the basis of big data of antenna and feed fault, this paper proposes a support vector machine (SVM) based fault classifier of antenna and feed, in order to quickly classify the faults of antenna and feed system (AFS). In addition, the improved Cascaded Pyramid Network (CPN) learning algorithm is employed to establish a fault diagnosis device of antenna and feed to quickly diagnose various categories of faults. For the fault model of antenna and feed, we continue to learn and train to optimize the fault classifier model, as well as the fault diagnosis model. For the fault diagnosis information, the antenna and feed fault classifier is used to update the classified faults, which empower the antenna and feed fault classification more accurate.