Deploying the YOLOv8L model on edge devices for road crack detection can achieve high accuracy， but it is difficult to guarantee real-time detection. To solve this problem， a target detection algorithm based on the improved YOLOv8 model that can be deployed on the edge computing device Jetson AGX Xavier was proposed. First， the Faster Block structure was designed using partial convolution to replace the Bottleneck structure in the YOLOv8 C2f module， and the improved C2f module was recorded as C2f-Faster； second， an SE （Squeeze-and-Excitation） channel attention layer was connected after each C2f-Faster module in the YOLOv8 backbone network to further improve the detection accuracy. Experimental results on the open source road damage dataset RDD20 （Road Damage Detection 20） show that the average F1 score of the proposed method is 0.573， the number of detection Frames Per Second （FPS） is 47， and the model size is 55.5 MB. Compared with the SOTA （State-Of-The-Art） model of GRDDC2020 （Global Road Damage Detection Challenge 2020）， the F1 score is increased by 0.8 percentage points， the FPS is increased by 291.7%， and the model size is reduced by 41.8%， which realizes the real-time and accurate detection of road cracks on edge devices.

To address the user cluster partitioning issue in the deployment strategy of Unmanned Aerial Vehicle （UAV） base stations for auxiliary communication in emergency scenarios， a feature-weighted fuzzy clustering algorithm， named Improved FCM， was proposed by considering both the performance of UAV base stations and user experience. Firstly， to tackle the problem of high computational complexity and convergence difficulty in the partitioning process of user clusters under random distribution conditions， a feature-weighted node data projection algorithm based on distance weighting was introduced according to the performance constraints of signal coverage range and maximum number of served users for each UAV base station. Secondly， to address the effectiveness of user partitioning when the same user falls within the effective ranges of multiple clusters， as well as the maximization of UAV base station resource utilization， a value-weighted algorithm based on user location and UAV base station load balancing was proposed. Experimental results demonstrate that the proposed methods meet the service performance constraints of UAV base stations. Additionally， the deployment scheme based on the proposed methods effectively improves the average load rate and coverage ratio of the system， reaching 0.774 and 0.026 3 respectively， which are higher than those of GFA （Geometric Fractal Analysis）， Sp-C （Spectral Clustering）， etc.

In view of a series of problems of security guarantee of construction site personnel such as casualties led by falling objects and tower crane collapse caused by mutual collision of tower hooks， a small target detection model in overlooking scenes on tower cranes based on improved Real-Time DEtection TRansformer （RT-DETR） was proposed. Firstly， the multiple training and single inference structures designed by applying the idea of model reparameterization were added to the original model to improve the detection speed. Secondly， the convolution module in FasterNet Block was redesigned to replace BasicBlock in the original BackBone to improve performance of the detection model. Thirdly， the new loss function Inner-SIoU （Inner-Structured Intersection over Union） was utilized to further improve precision and convergence speed of the model. Finally， the ablation and comparison experiments were conducted to verify the model performance. The results show that， in detection of the small target images in overlooking scenes on tower cranes， the proposed model achieves the precision of 94.7%， which is higher than that of the original RT-DETR model by 6.1 percentage points. At the same time， the Frames Per Second （FPS） of the proposed model reaches 59.7， and the detection speed is improved by 21% compared with the original model. The Average Precision （AP） of the proposed model on the public dataset COCO 2017 is 2.4， 1.5， and 1.3 percentage points higher than those of YOLOv5， YOLOv7， and YOLOv8， respectively. It can be seen that the proposed model meets the precision and speed requirements for small target detection in overlooking scenes on tower cranes.

Aiming at the high computational complexity and large memory consumption of the existing super-resolution reconstruction networks， a lightweight image super-resolution reconstruction network based on Transformer-CNN was proposed， which made the super-resolution reconstruction network more suitable to be applied on embedded terminals such as mobile platforms. Firstly， a hybrid block based on Transformer-CNN was proposed， which enhanced the ability of the network to capture local-global depth features. Then， a modified inverted residual block， with special attention to the characteristics of the high-frequency region， was designed， so that the improvement of feature extraction ability and reduction of inference time were realized. Finally， after exploring the best options for activation function， the GELU （Gaussian Error Linear Unit） activation function was adopted to further improve the network performance. Experimental results show that the proposed network can achieve a good balance between image super-resolution performance and network complexity， and reaches inference speed of 91 frame/s on the benchmark dataset Urban100 with scale factor of 4， which is 11 times faster than the excellent network called SwinIR （Image Restoration using Swin transformer）， indicates that the proposed network can efficiently reconstruct the textures and details of the image and reduce a significant amount of inference time.

The existing cross-level High Utility Itemsets Mining （HUIM） algorithms consume a lot of time and occupy large amounts of memory. To address these problems， a Data Index Structure Cross-level High utility itemsets mining （DISCH） algorithm was proposed. Firstly， the utility list with taxonomic information and index information was expanded into Data Index Structure （DIS） to efficiently store and quickly retrieve all itemsets in the search space. Then， in order to improve the memory utilization， the memory occupied by the utility lists that do not meet the conditions was reclaimed and reallocated. Finally， during the construction of utility list， early termination strategy was used to reduce the generation of utility list. Experimental results based on real retail datasets and synthetic datasets show that compared with the CLH-Miner （Cross-Level High utility itemsets Miner） algorithm， DISCH reduces the running time by 77.6% on average and the memory consumption by 73.3% on average. Therefore， the proposed algorithm can search the cross-level high utility itemsets efficiently and reduce the memory consumption of algorithm.

Concerning the low efficiency of network transmission caused by redundant traffic, an algorithm named Packet Feature based Redundancy Traffic Elimination (PFRTE) was proposed based on the protocol-independent traffic redundancy elimination technique. Based on the grouping of packet size, PFRTE dynamically analyzed statistical bimodal characteristics and packet features of network traffic and regarded the size of the packet with the greatest capability of redundancy elimination as the threshold. It decided the boundary points by using sliding window method and calculated the fingerprint of block data within two boundary points. PFRTE encoded the redundant blocks in a simple way and transfered the encoded data instead of redundant data. The experimental results show that, compared with redundant traffic elimination algorithm based on maximum selection and static lookup table selection, PFRTE has the advantage of analyzing the redundancy statistics of network traffic dynamically, and the CPU consumption reduces both at server and client. Meanwhile, the algorithm is also effective with rate of redundancy elimination bytes saving of 8%-40%.

A new method was proposed to accurately detect and quantitatively evaluate the lung nodule spiculation. First, the region growing method followed by level set method was used to accurately segment the main part of the lung nodule. Then, spiculated lines connected to the nodule boundary were extracted using a line detector in polar coordinates system. Finally, spiculation index was introduced as the quantitative measurement of spiculation features, which was then used as a criteria for distinguishing between spiculated and non-spiculated nodules. The consistency and correlation of spiculation index of the method and Lung Image Database Consortium (LIDC) were evaluated in detail. The experimental results show that the proposed method can effectively detect and quantitatively describe the lung nodule spiculation in CT images.

It is tightly coupled between the simulation task and equipment in traditional distributed virtual maintenance training systems, so the system simulation running is inefficient and difficult to expand. In addition, the simulation resource sharing and maintenance cooperation is also a big problem. In order to solve these problems, the infrastructure and realizing framework of cloud simulation were put forward for the application in weapons virtual maintenance training field. The multilayer infrastructure of Run Time Infrastructure (RTI) component was studied. The key techniques were settled, such as federated members excogitation and transport, simulation process monitoring, simulation visualization and distributed storage. The virtual maintenance system was developed based on cloud simulation technologies, which indicated that cloud simulation was feasible and effective.

This paper referred to the common routing protocol threats appearing in MANET and analyzed the properties of satellite network to get possible security threats of Location-Assisted On-demand Routing (LAOR) and what to do to make the protocol safer. It used Id-based cryptography to mainly realize mutual authentication between nodes and protection of the integrity of routing control packet by signature using each nodes private key. Finally strand space was used to analyze the improved routing protocol, and proved it satisfied plausible routing, and was secure.

Data scheduling strategy in Peer-to-Peer (P2P) media streaming is the key research of the P2P media streaming system. A Particle Swarm Optimization （PSO） algorithm was modified according to P2P streaming data scheduling features and the style of digital encoding string for the algorithm was proposed in this paper. The data scheduling strategy to choose the data chunk took account of resource urgency and scarcity degree. The modified discrete particle swarm algorithm was used to choose the peers to get the optimal scheduling peers set. In order to verify the feasibility and effectiveness of the algorithm, experiments were done to simulate the convergence of the algorithm, the scheduling time, the P2P network uplink bandwidth utilization and the load balancing of peers.

Researches on the audio classification have involved various types of vector features. However, multi-semantics of audio information not only have their own properties, but also have some correlations among them. Whereas, to a certain extent, the simple vector representation cannot represent the multi-semantics and ignore their relations. Tensor Uniform Content Locator (TUCL) was brought forward to express the semantic information of audio, and a three-order Tensor Semantic Space (TSS) was constructed according to the semantic tensor. Tensor Semantic Dispersion (TSD) can aggregate some audio resources with the same semantics, and at the same time, the automatic audio classification can be accomplished by calculating their TSD. And Radical Basis Function Tensor Neural Network (RBFTNN) was constructed and used to train intelligent learning model. For the problem of multi-semantic audio classification, the experimental results show that our method can significantly improve the classification precision in comparison with the typical method of Gaussian Mixture Model (GMM), and the classification precision of RBFTNN model is obviously better than that of Support Vector Machine (SVM).

The low utilization of resource and the lack of reliability and scalability have always been the problems when business system is running in distributed environment. Concerning these problems, this paper designed a distributed business deployment platform based on Service-Oriented Architecture (SOA). Distributed business system could be automatically deployed on the platform, and the resource it needed would be dynamically assigned according to the state of service component, which implemented the dynamic extension and draw-back of the business ability. At the same time, double heat-computer backup, high available cluster and business migration mechanism were applied to guarantee the high reliability. The simulation results indicate that the platform achieves high resource utilization while the Quality of Service (QoS) is ensured.

Concerning the problem that the impact of illegal nodes (including the node unable to locate) on the localization process in DV-Hop localization algorithm has not been taken into consideration, this paper proposed a secure localization mechanism based on DV-Hop. In other words, the character of message exchange between the nodes was introduced to detect the wormhole attacks in this paper. Time property and space property were used to define the valid beacon nodes, along with encryption and authentication mechanisms to resist against the node-tampering attack in the communication process. Finally, the nodes were located securely. The simulation results show that, in hostile environment, the proposed mechanism has a high probability to detect the wormhole attacks, and the relative localization error can be reduced by 63% or so.

Distributed search is an effective way to search the Deep Web, while collection size is an important feature in collection representation and selection in distributed search. To estimate collection size in uncooperative environments, the two novel algorithms were proposed in this paper. High frequent resample algorithm first samples collections with random queries, then resamples with high frequent queries in the sample set. Heterogeneous capture algorithm, based on the assumption of different capture probabilities among documents, uses Logistic functions and conditional maximum likelihood. Experimental results show that the algorithms outperform both sample-resample and capture-recapture algorithms.