Automated Modulation Recognition （AMR） plays a critical role in wireless communications. A Denoising & Dual-modal Attention CNN-Transformer （D-DmACT） was proposed to address problems of poor transfer ability and insufficient abilities to distinguish noise and modulation signal features of AMR networks in complex electromagnetic environments. Firstly， a generator to generate complex electromagnetic interference iteratively and a discriminator to be against interference were proposed to enhance generalization ability of the network when encountering complex electromagnetic environments. Secondly， a complex attention-based Transformer module was designed to capture time-domain features of In-phase and Quadrature （IQ） signals， and a coordination attention module based on time-frequency information was proposed to acquire features of time-frequency images， then the features were crossed and fused. Thirdly， temporal sequence complex signals and time-frequency image obtained by the generator were sent to the dual-modal attention fusion model. Finally， lightweight classification and recognition were implemented. Experiments were conducted on datasets RadioML2016.10A and RadioML2018.01a under white Gaussian noise and complex electromagnetic environment， respectively. Experimental results with impulsive noise show that compared with CLDNN（Convolutional Long short-term Deep Neural Networks）， Residual Network （ResNet）， and LSTM（Long Short-Term Memory） Network， the proposed network has the average recognition accuracy increased by 53.98%， 28.82%， and 24.64%； compared with Multi-Modal approach toward AMR （MM-Net）， Threshold Autoencoder Denoiser Convolutional Neural Network （TADCNN）， and Generative Adversarial Network & Multi-modal Attention mechanism CNN-LSTM （GAN-MnACL）， the proposed network has the average recognition accuracy enhanced by 19.74%， 13.55% and 11.17%， respectively. In terms of computational complexity， deployability of the proposed network is validated through metrics such as parameters and FLoating point OPerations （FLOPs）.

The non-structured and non-uniform distribution of point cloud data poses significant challenges for feature representation and classification tasks. To extract the three-dimensional structural features of point cloud objects， existing methods often employ complex local feature extraction structures to construct hierarchical networks， resulting in a complex feature extraction network that mainly focuses on the local structures of the point cloud objects. To better extract features from unevenly distributed point cloud objects， a Node structure Network （NsNet） with sample point convolution density adaptive weighting was proposed. The convolutional network adaptively weighted sample points based on Gaussian density to differentiate the density differences among sampling points， thereby better characterizing the overall structure of objects. Additionally， the network structure was simplified by incorporating spherical coordinates to reduce model complexity. Experimental results on three public datasets demonstrate that， NsNet based on adaptive density weighting improves the Overall Accuracy （OA） by 9.1 and 1.3 percentage points respectively compared with PointNet++ and PointMLP， and reduces the number of parameters by 4.6×10⁶ compared to PointMLP. NsNet can effectively address the problem of information loss caused by uneven distribution of point clouds， improve the classification accuracy and reduce the model complexity.

Active Queue Management plays an important role in the congestion control of network. In order to solve the problem that CHOKe algorithm cannot punish the non-responsive flows enough and the low accuracy, a new algorithm, LRU-CHOKe to penalize for non-responsive flows, was proposed in the paper. The algorithm did not only replace the CHOKe hit with LRU hit to improve the effectiveness of CHOKe hit, but also used queue hit to adaptively determine the number of packet loss. A new way of dropping packets to punish non-responsive flows was adopted. The simulation results show that LRU-CHOKe performs better than CHOKe in punishing non-responsive flows. As a result, the bandwidth allocation is realized more fairly.

With regard to the phenomena that Random Early Detection (RED) packet loss rate is high while the network congestion is not serious and vice versa, the congestion control algorithm of non-linear high-order RED was put forward to control the ineffectiveness of the network. The algorithm has established a high-order function model which has good congestion control ability. By using the non-linear control to mark or discard fragments with lower and higher probability near low and high threshold respectively, it can control average queue length effectively. Meanwhile, NS2 stimulation has verified that the algorithm is effective in improving the network performance.