Aiming at the problems that the intrusion detection methods of Internet of Medical Things （IoMT） rely on the balance of data samples， the misuse detection based on supervised learning cannot cope with unknown attacks， and the false alarm rate of anomaly detection based on unsupervised learning is high， an intrusion detection method with multi-stage fusion for IoMT was proposed. Firstly， a feature extraction method that added header information and payload to the bidirectional flow features was adopted to reduce the dependence on the balance of data samples. Then， a three-stage intrusion detection framework was designed by combining supervised and unsupervised learning methods. In the framework， the unsupervised learning AutoEncoder （AE） model was used to filter benign traffic and detect unknown attacks， and the supervised learning hybrid model of Convolutional Neural Network （CNN）， Gated Recurrent Unit （GRU）， and Attention mechanism （Attention） was used to detect known attacks and reduce false alarms， so as to improve the detection performance. Experimental results show that Multi-stage fusion for IoMT Intrusion Detection System （MTIDS） constructed by the proposed method achieves 99.96% detection accuracy and 93.78% F1 value on the CICIoMT2024 and CICIoT2023 datasets， which are higher than those of intrusion detection models of single supervised or unsupervised learning methods such as AE. Specifically， MTIDS has an improvement of 0.82 percentage points in accuracy and 5.58 percentage points in F1 value compared to the best comparison model AE， which validates the accuracy of the proposed method in detecting known and unknown attacks.

Because there are many differences in real life scenes， human emotions are various in different scenes， which leads to an uneven distribution of labels in the emotion dataset. Furthermore， most traditional methods utilize model pre-training and feature engineering to enhance the expression ability of expression-related features， but do not consider the complementarity between different feature representations， which limits the generalization and robustness of the model. To address these issues， EE-GAN， an end-to-end deep learning framework including the network integration model Ens-Net was proposed. It took the characteristics of different depths and regions into consideration，the fusion of different semantic and different level features was implemented， and network integration was used to improve the learning ability of the model. Besides， facial images with specific expression labels were generated by generative adversarial network， which aimed to balance the distribution of expression labels in data augmentation. The qualitative and quantitative evaluations on CK+， FER2013 and JAFFE datasets demonstrate the effectiveness of proposed method. Compared with existing view learning methods， including Locality Preserving Projections （LPP）， EE-GAN achieves the facial expression accuracies of 82.1%， 84.8% and 91.5% on the three datasets respectively. Compared with traditional CNN models such as AlexNet， VGG， and ResNet， EE-GAN achieves the accuracy increased by at least 9 percentage points.

The unique advantages of Named Data Networking （NDN） make it a candidate for the next generation of new internet architecture. Through the analysis of the communication principle of NDN and the comparison of it with the traditional Transmission Control Protocol/Internet Protocol （TCP/IP） architecture， the advantages of the new architecture were described. And on this basis， the key elements of this network architecture design were summarized and analyzed. In addition， in order to help researchers better understand this new network architecture， the successful applications of NDN after years of development were summed up. Following the mainstream technology， the support of NDN for cutting-edge blockchain technology was focused on. Based on this support， the research and development of the applications of NDN and blockchain technology were discussed and prospected.