Mobile augmented reality (MAR) applications are gaining popularity. There are significant challenges in handling the latency-sensitive and computation-intensive tasks generated by MAR applications on mobile devices. The emergence of mobile edge computing (MEC) provides a new idea to improve the computing capability of resource-constrained mobile terminals. In this paper, we study the task offloading and cache placement of MAR tasks in multi-MEC server cooperation system. The problem of the task offloading and cache placement is formulated to maximize the hit ratio and minimize the service latency under the constraints of MEC server's computing resources and cache space. To solve this problem, we propose a task offloading and cache placement (MOTOCP) algorithm based on multi-objective artificial bee colony. Pareto optimal relation is introduced in the optimization process to find the optimal solution. Extensive evaluation verifies that our proposed algorithm has better performance.

With the rapid development of knowledge graph related technologies, domain knowledge graph has become a research hotspot in academia and industry. However, the domain knowledge graph for technical documents is not mature enough, and the semantic information implicit in unstructured technical documents has not been fully tapped. Combining the characteristics of technical documents, the paper proposes a TextCNN-based topic information extraction model and constructs a domain knowledge graph for technical documents. It uses the graph database Neo4j for knowledge storage and visualization. The information extraction model based on TextCNN can automatically extract the subject information of the document and the summary information such as title, ID, status, meeting, organization, etc. Experiments show that the model has high accuracy on the technical document dataset, which can effectively reduce the cost of manual annotation and data collation. At the same time, knowledge graph visualization can facilitate scientific researchers to search, track and update technical documents, which can show the evolution of technology more clearly.

With the popularity of mobile devices such as smartphones and tablets, the improvement of service of quality is an important issue facing great challenges. The improvement of user service of quality is mainly reflected in reducing the energy consumption of mobile devices and the delay of task execution. Multi-access edge computing sinks computing and storage capabilities from the remote cloud to the edge network, which can effectively reduce the high latency caused by the transmission of tasks between the mobile device and the remote cloud and the high energy consumption of tasks performed locally. Most of the previous work was limited to service of quality optimization through dynamic service layout, while ignoring the critical impact of access network selection on network congestion. This paper studies the task offloading model of multiple tasks and services with several MEC servers, and jointly optimizes the MEC’s access network selection and service placement issues. Considering the delay and energy consumption caused by task offloading and execution, this paper designs an effect function on delay and energy consumption, and aims to minimize this function to solve the MEC problem. Since this problem is NP-hard, this paper designs a new optimization algorithm based on particle swarm optimization to solve this problem. Extensive simulation experiments show that the proposed optimization algorithm realize better performance than other algorithms. The algorithm has achieved good results in terms of time delay and energy consumption, which effectively reduces the system cost.

With the increasing requirements for computing in modern society, Multi-access Edge Computing (MEC) has received widespread attention for meeting low-latency. In MEC network, mobile devices can offload computing-intensive tasks to edge servers for computing. Wireless Power Transmission (WPT) provides initial energy for mobile devices, and the tasks of mobile devices consume energy when they are locally calculated or completely offloaded. The combination of the two technologies forms the Wireless Powered Mobile Edge Computing (WP-MEC) network. In this article, considering the impact of WPT transmission time τ ₀ , we study the offloading and scheduling of tasks for multiple mobile devices in the WP-MEC network, which is an NP-hard problem. We formulate this scheduling problem to minimize the time delay under the constraint of WPT transmission energy. We regard our problem studied in this paper as a multidimensional knapsack problem (MKP). The difference is that the knapsack capacity in MKP is limited, while in our problem, the knapsack that one item can choose is limited. Therefore, we improve the Artificial Fish Swarm Algorithm (AFSA) and propose Computation Scheduling Based on the Artificial Fish Swarm Algorithm (CS-AFSA) to find the optimal scheduling. We encode a scheduling scheme as an artificial fish and regard the delay corresponding to the scheduling as the optimization object. The optimal artificial fish can be gradually approached and determined through the swarm, follow and prey behavior of artificial fish. The optimal artificial fish is the optimal scheduling scheme. More importantly, based on the original behavior of AFSA, we also improve the scheme that does not meet the WPT energy constraint, including the modification of infeasible artificial fish and insufficient artificial fish. Besides, we also consider how to find the best WPT transmission time τ ₀ . Finally, we perform data simulation on the proposed algorithm.

Fracture refers to the complete or partial rupture of bone structure, which requires accurate diagnosis by orthopedic surgeons and treatment methods. Therefore, it is of great significance to study automatic fracture detection. In this paper, in order to solve the problem of low accuracy of fracture image determination caused by incomplete feature extraction of traditional features, a deep learning method is used to build a convolutional neural network model framework, and a fracture image detection method based on deep features and integrated learning is proposed. Using data enhancement to preprocess the MURA image data set, when extracting image features, Alexnet is used as a feature extractor to obtain sufficiently effective image features, and when training the classifier, the idea of integrated learning in machine learning is adopted. Train the classifiers after feature extraction, and give them different weight values according to the contribution of each classifier, to achieve better performance than a single classifier, and improve the accuracy of image classification. The experimental results of this method on the MURA data set show its good classification performance.

This study explores whether neural networks can classify multiple samples simultaneously in a forward process. Therefore, a multi‐input multi‐prediction network architecture has been proposed. The authors call this method a multi‐sample inference network (MSIN). In addition to maximising the use of network shared parameters, the network can also use multiple samples for training. MSIN allows multiple samples to be randomly combined to act as data augmentation, and the random combination of corresponding labels can regularise the network as a loss regularisation, which makes MSIN have better generalisation performance. In contrast, category expansion is a problem that is difficult to solve because neural networks can only predict a fixed number of categories. The network proposed in this study can solve the category expansion problem by expanding the initial layers and the final layers. It is trained by using samples of multiple domains at the same time to ensure that the network has no significant decline in the predictive performance of the existing categories. The MSIN method can also be applied to the generative adversarial network to enable it to simultaneously generate samples of multiple sample domains.