Internet Technology Letters最新文献

In this work, the problems of stability analysis and sliding mode control (SMC) for discrete-time cyber-physical systems (CPSs) under denial-of-service (DoS) attacks are investigated. Firstly, the model of aperiodic DoS attacks is established by introducing the constraints on the upper bound of the attack interval and the lower bound of the non-attack interval. Next, by utilizing the SMC and switching strategies, the input-to-state stability (ISS) of the CPSs can be guaranteed in terms of the upper and lower bounds restrictions. Then, the sliding mode control law is designed for the considered CPSs. Finally, one example is given to illustrate the applicability of our proposed theoretical result.

Building a public opinion monitoring system can detect public opinion crises in advance and deal with crisis public relations in a timely manner. Semantic communication is a new type of communication technology with development potential, which reduces the amount of data required for transmission by mining semantic information in information sources. In this paper, a multi-user semantic communication system based on federated learning deployment is used to realize data transmission in edge computing scenarios. Use the data from the client side to train the deep learning model more effectively. This paper also evaluates the performance of the proposed semantic communication system. The model trained by federated learning can achieve an effect close to centralized training and protect user privacy.

In medical image segmentation (MIS), better segmentation results can be obtained by training the deeper neural network. However, directly building too deep network will cause problems such as gradient disappearance, which will affect the segmentation effect. Therefore, a dilated inception U-Net (DIU)-net network is constructed by combining the multi-scale feature fusion (MSFF) method and the concept of Inception in Google net based on U-net, and its effectiveness is verified by experiments. The DIU-net network's training accuracy has been improved in the lung computed tomography (CT) and fundus vascular CT image data sets. And the attenuation of the loss function is relatively stable, with the highest accuracy of 99.6%. In comparison of evaluation indicators, the values of different indicators of DIU-net in the two data sets are higher than those of the comparison network. The DICE coefficient of DIU-net in the lung CT image in the experiment is 0.986 on average, which is 0.2% higher than that of ResU-net. SE value is 0.985, which is 1.9% higher than SegNet. Specificity value is slightly higher than the second segmentation effect. F1 score is 0.985, 0.6% higher than ResU-net, area under curve value is 0.99, 0.7% higher than FCN-8 s. In general, the DIU-net network proposed in the study will not cause gradient disappearance and other problems in the experiment. At the same time, this method also shows high efficiency and has strong feasibility for the actual MIS.

The development of the power Internet of Things is currently underway, and a proposal for a semantic Internet of Things based on artificial intelligence algorithms is made to address the challenges in obtaining prior knowledge for heterogeneous data fusion, improving the real-time performance of the ontology library, and enhancing the efficiency of manual labeling of instance object data in the power field. This proposal introduces an Automatic Semantic Annotation Method to provide an effective knowledge organization model for sensor systems. Data mining knowledge is utilized to drive ontology update and improvement, resulting in more accurate semantic annotation and enhanced machine understanding. Experimental results show that artificial intelligence algorithms can automatically extract concepts from sensory data and achieve automatic semantic annotation during ontology instantiation.

This paper adopts the deep network model constructed the results of the training are used to explore the detection of sports, and to verify the deep learning network model from the perspective of reliability and feasibility. The experimental results in this paper show that the comprehensive performance evaluation index FM increased by 2.6%, Pr increased by 0.7%, and Re increased by 4.4%. Therefore, the deep residual network structure used in the DRNTL method proposed in this paper can effectively improve the generalization ability of the network. Through the learning of a large amount of labeled data, the model can be applied to the detection of other untrained complex scenes. The engineering of the moving target detection method is of great significance.