With the advent of global 5G networks, the Internet of Things will no longer be limited by network speed and traffic. With the large-scale application of the Internet of Things, people pay more and more attention to the security of the Internet of Things. Once the Internet of Things system suffers from malicious attacks, not only the serious loss of information will lead to the paralysis of the Internet of Things equipment. Aiming at the security problem of the Internet of Things, this paper puts forward the LM-BP neural network model. The LM-BP neural network model is applied to an intrusion detection system, and the intrusion detection flow under LM-BP algorithm is given. LM algorithm has the characteristics of fast optimization speed and strong robustness and uses this characteristic to optimize the weight threshold of traditional BP neural network. Through establishing LM-BP neural network classifier, KDD CUP 99 intrusion detection data set is imported into an LM-BP neural network classifier, and the best results are obtained through continuous training. Finally, the experimental simulation results show that this model has higher detection rate and lower false alarm rate than the traditional BP neural network model and PSO-BP neural network model for DOS, R2L, U2L, and Probing, thus this modified model has certain promotion value.INDEX TERMS Intrusion detection system, KDD CUP 99 dataset, LM-BP neural network model.

Medical images play a very important role in making the right diagnosis for the doctor and in the patient's treatment process. Using intelligent algorithms makes it possible to quickly distinguish the lesions of medical images, and it is especially important to extract features from images. Many studies have integrated various algorithms into medical images. For medical image feature extraction, a large amount of data is analyzed to obtain processing results, helping doctors to make more accurate case diagnosis. In view of this, this paper takes tumor images as the research object, and first performs local binary pattern feature extraction of the tumor image by rotation invariance. As the image shifts and the rotation changes, the image is stationary relative to the coordinate system. The method can accurately describe the texture features of the shallow layer of the tumor image, thereby enhancing the robustness of the image region description. Focusing on image feature extraction based on convolutional neural network (CNN), the basic framework of CNN is built. In order to break the limitations of machine vision and human vision, the research is extended to multi-channel input CNN for image feature extraction. Two convolution models of Xception and Dense Net are built to improve the accuracy of the CNN algorithm. It can be seen from the experimental results that the CNN algorithm shows high accuracy in tumor image feature extraction. In this paper, the CNN algorithm is compared with several classical algorithms in the local binary mode. The CNN algorithm has more accurate feature extraction ability for tumor CT images on a larger data basis. Furthermore, the advantages of CNN algorithms in this field are demonstrated.INDEX TERMS Convolutional neural network, image feature extraction, local binary mode.

No abstract

No abstract

In recent years, with the wide application of image data visual extraction technology in the field of industrial engineering, the development of industrial economy has reached a new situation. To explore the interaction between the pellet microstructure and compressive strength, firstly, the pellet microstructure needed for the experiment was obtained using a Leica DM4500P microscope. The area proportions of hematite, calcium ferrite, magnetite, calcium silicate and pore in pellet microstructure were extracted by visual extraction technology of image data. Moreover, the relationship between the area proportions of mineral components and compressive strength was established by backpropagation neural network (BPNN), generalized regression neural network (GRNN) and beetle antennae search-generalized regression neural network (BAS-GRNN) algorithms, which proves that the pellet microstructure can be used as the prediction standard of compressive strength. The errors of BPNN and BAS-GRNN are 5.13% and 3.37%, respectively, both of which are less than 5.5%. Therefore, through data visualization, we are able to discuss the connection between various components of pellet microstructure and compressive strength and provide new research ideas for improving the compressive strength and metallurgical performance of pellet.