In medical image segmentation networks， Convolutional Neural Network （CNN） can extract rich local feature details， but has the problem of insufficient capture of long-range information， and Transformer can capture long-range global feature dependencies， but destroys local feature details. To make full use of the complementarity of characteristics of the two networks， a parallel fusion network of CNN and Transformer for medical image segmentation was proposed， named PFNet. In the parallel fusion module of this network， a pair of interdependent parallel branches based on CNN and Transformer were used to learn both local and global discriminative features efficiently， and fuse local features and long-distance feature dependencies interactively. At the same time， to recover the spatial information lost during downsampling to enhance detail retention， a Multi-Scale Interaction （MSI） module was proposed to extract the local context of multi-scale features generated by hierarchical CNN branches for long-range dependency modeling. Experimental results show that PFNet outperforms other advanced methods such as MISSFormer （Medical Image Segmentation tranSFormer） and UCTransNet （U-Net with Channel Transformer module）. On Synapse and ACDC （Automated Cardiac Diagnosis Challenge） datasets， compared to the optimal baseline method MISSFormer， PFNet increases the average Dice Similarity Coefficient （DSC） by 1.27% and 0.81%， respectively. It can be seen that PFNet can realize more accurate medical image segmentation.

Convolutional Neural Networks （CNN） are used for image forensics because of their high recognizable property， easy understanding， and strong learnability. However， their inherent disadvantages of the receptive field increasing slowly and neglecting long-range dependencies， and high computational cost cause the unsatisfactory accuracy and lightweight deployment of deep learning algorithms. To solve the above problems， a lightweight network-based image copy-paste tamper detection algorithm namely LKA-EfficientNet （Large Kernel Attention EfficientNet） was proposed. The characteristics of long-range dependencies and global receptive field were contained in LKA-EfficientNet， and the number of EfficientNetV2 parameters was optimized. As a result， the localization speed and detection accuracy of image tamper were improved. Firstly， the image was inputted into and processed in the backbone network based on Large Kernel Attention （LKA） to obtain the candidate feature maps. Then， the feature maps of different scales were used to construct the feature pyramid for feature matching. Finally， the candidate feature maps after feature matching were fused to locate the tampered area of the image. In addition， the triple cross entropy loss function was used by LKA-EfficientNet to further improve the accuracy of the algorithm in image tamper localization. Experimental results show that LKA-EfficientNet can not only reduce the floating-point operations by 29.54% but also increase the F1 by 4.88% compared to the same type algorithm — Dense-InceptionNet. The above verifies that LKA-EfficientNet can reduce computational cost and maintain high detection performance at the same time.

Multi-chord curvature polynomial algorithm for corner detection was proposed based on Chord-to-Point Distance Accumulation (CPDA) technique and curvature product. Firstly, the edge map was extracted by Canny edge detector. Then, at each chord, a multi-chord curvature polynomial was used as the sum or multiplication of the contour curvature. The new method can not only effectively enhance curvature extreme peaks, but also prevent smoothing some corners. To reduce false or missing detection made by experiment threshold, local adaptive threshold was used to detect corners. According to the detection capability, localization accuracy and repeatability of corner number criteria, experiments were made to compare the proposed detector with several recent corner detectors. The experimental results demonstrate that the proposed detector has strong robustness, its detection accuracy increases by 14.5%, and its average repeatability increases by 12.6%.

Complex background including shading, seal and some images has a bad effect on character recognition of check. Thus, in this paper, an effective method that extracts the significant texture characteristics of character from the image by fast lifting wavelet transform was proposed to solve this problem. A coarse-to-fine searching strategy was adopted to distinguish the characters from background at the level of block of pixels and single pixel. First, Support Vector Machine (SVM) was used to classify blocks according to texture characteristics, and during this process text region could be located. Then character segmentation was achieved by using K-means algorithm for clustering the pixels at the text region. The experimental results show the high accuracy and strong robustness of the proposed method at the situation of strong interference of complex texture and seal.

Considering the non-linearity of TCP model, uncertainty of Round Trip Time (RTT) and fluctuation of network load, an Active Queue Management (AQM) scheme based on Variable Structure Controller (VSC) using single neuron adaptive learning was proposed. The nonlinear VSC was used to guarantee the swiftness and robustness of queue response at router. However, the jitter of VSC would cause the queue fluctuation and performance degradation. Therefore, a single neuron was introduced to adjust the parameters of the VSC in order to alleviate the effect of jitter and modeling uncertainty. The proposed scheme can reduce the jitter and enhance the robustness for AQM control system greatly. Finally, the simulation results show the effectiveness of the proposed algorithm through NS-2 simulator.

Low-Energy Adaptive Clustering Hierarchy (LEACH) protocol is a critical clustering hierarchy routing protocol for wireless sensor network. Lack of security measures makes it vulnerable to personation and laptop attacks, especially during the cluster set-up phase. A new low-energy secure routing protocol based on SPINS was proposed. It authenticated broadcast packets using μTESLA, distributed authenticated key to cluster-head and cluster-members using SNEP. In the proposed protocol, sensor nodes needed to verify whether the cluster-head was the node it claimed to be. They also needed to verify whether they could reach the cluster-head. If both checks were passed, then sensor nodes joined in the cluster. Security analysis shows that the proposed protocol realized confidentiality, integrity, freshness, identity authentication, two-way authentication and some other security objectives. Simulation results based on NS2 show that energy consumption of sensor nodes does not significantly increase, due to the sink node and cluster-heads undertaking most of safety related tasks.