With the rapid development of computer vision and artificial intelligence technology, visual object detection has made unprecedented progress, and small object detection in complex scenes has attracted more and more attention. To solve the problems of ambiguity, overlap and occlusion in small object detection in complex scenes. In this paper, a multi-scale fusion feature enhanced path aggregation network MSFE-PANet is proposed. By adding attention mechanism and feature fusion, the fusion of strong positioning information of deep feature map and strong semantic information of shallow feature map is enhanced, which helps the network to find interesting areas in complex scenes and improve its sensitivity to small objects. The rejection loss function and network prediction scale are designed to solve the problems of missing detection and false detection of overlapping and blocking small objects in complex backgrounds. The proposed method achieves an accuracy of 40.7% on the VisDrone2021 dataset and 89.7% on the PASCAL VOC dataset. Comparative analysis with mainstream object detection algorithms proves the superiority of this method in detecting small objects in complex scenes.

Classification of imbalanced data is an important challenge in current research. Sampling is an important way to solve the problem of imbalanced data classification, but some traditional sampling algorithms are susceptible to outliers. Therefore, an iF-ADASYN sampling algorithm is proposed in this paper. First, based on the ADASYN algorithm, we introduce the isolation Forest algorithm to overcome its vulnerability to outliers. Then, a calculation method of anomaly index which can delete outliers accurately of minority data is presented. The experimental results of four UCI public imbalanced datasets show that the algorithm can effectively improve the accuracy of the minority class, and increase the stability. In the real thrombus dataset, the AUC value of the iF-ADASYN algorithm is more significant than that of SMOTE and ADASYN algorithms, and the recognition rate of patients with thrombosis increased by 20%. The iF-ADASYN algorithm obtains better resistance to outliers than the original ADASYN algorithm. Meanwhile, it improves the accuracy of minority class decision boundary region division.

Classifying diseases in electronic medical records into corresponding ICD codes requires not only a large amount of medical knowledge but also a large number of coders, which is time-consuming and labor-consuming. Therefore, automatic coding is of great significance. This paper aims to build a deep learning model for automatic ICD-10 coding from a batch of Chinese electronic medical records. The data enhancement, convolutional neural network, attention mechanism, and the gating residual network proposed by the author were used to code ICD code corresponding to the distribution of medical record information by supervised learning. The benchmark model and ablation model were tested on a data set of Chinese electronic medical records. The effectiveness of the proposed modules, such as feature aggregation, multi-head attention mechanism, dilated convolution, and gating residuals, was verified. In the automatic ICD coding task for 104 diseases, the accuracy of the proposed method is 91.71%, and the F1-Score is 92.11%.1

C-RAN, i.e., Cloud-Radio Access Network, is a new cellular network architecture for the future mobile network infrastructure. It is proposed to provide a possible solution for operators to construct mobile access networks in a cost-effective manner. Different from traditional cellular network architectures that are built with many stand-alone base stations (BSs), C-RAN is now viewed as an architecture evolution based on distributed BSs. C-RAN has drawn extensive attentions from the operators due to its “4C” characteristics, i.e., Clean, Centralized processing, Collaborative radio, and real-time Cloud radio access network. In this paper, we focus on the Infrastructure Deployment and Layout Planning (IDLP) problem under the C-RAN architecture. The IDLP problem is formulated as a generic integer linear programming (ILP) model which can optimally: (i) minimize the network deploying cost, (ii) identify the locations of Remote Radio Units (RRUs) and Wavelength Division Multiplexers (WDMs), (iii) identify the association relations between RRUs and WDMs, (iv) satisfy the mobile coverage requirements so as to allow the mobile user access through RRU. We solve the model using Gurobi, which is the newest ILP solver by now. A series of case studies are conducted to validate the optimization framework and demonstrate the solvability and scalability of the ILP model. Computational results show the significant performance benefits of CoMP in C-RAN in terms of lower cost, larger capacity and higher reliability.