To overcome limitations in the existing Self-Supervised Learning （SSL） methods for time-series， such as reliance on negative sample pairs and the potential disruption of temporal structure by data augmentation， a Soft Whitening inspired non-contrastive SSL framework for Time-series Forecasting （SWTF） was proposed. In the framework， series representations with dense information and prediction ability were learned without negative samples. Its core method consists of two collaboratively optimized objectives. The first is a Temporal Soft Whitening （TSW） loss， which means that compact representations with rich information were learned by reducing the redundancy between representation dimensions and maintaining the variance of representations， so as to avoid the reliance on negative sample pairs and representation invariance constraints. The second is a denoising reconstruction task， which means that the model was guided to focus on and encode predictive time-series features. To optimize these two objectives jointly， a Siamese encoder was constructed to use parallel multi-scale convolutional networks to capture both micro-level local periodicities and macro-level long-range dependencies efficiently. Experimental results on several benchmark datasets （electricity， weather， and traffic） show that SWTF achieves a Mean Absolute Error （MAE） reduction of approximately 19.6% （13.4% to 26.4%） compared to mainstream baselines such as CoST and PDF（Periodicity Decoupling Framework）， verifying the effectiveness of SWTF in learning robust and highly predictive time-series representations.

The existing researcher redeployment after discipline revocation relies on manual decision-making， which makes it difficult to coordinate discipline associations effectively. In this context， Large Language Model （LLM） with strong knowledge analysis capabilities provides new ideas for discipline optimization based on researcher redeployment after discipline revocation. However， on university research data represented by scientific research information， they face challenges such as difficulty in understanding professional terms and obvious long-tail distribution. Therefore， a multistage coupled decision-making framework for the redeployment of researchers after discipline revocation， namely MCRF （Multistage Coupled Redeployment Framework）， was proposed. MCRF was composed of four stages： recall， semantic enhancement， pairing， and reordering， and was able to decompose difficult problems into multiple relatively simple sub-problems effectively. Firstly， a discipline research word cloud association dataset was constructed to alleviate the problem of general models’ difficulty in understanding specialized academic terms. Secondly， an association recall algorithm was designed to recall Top-K related disciplines of scientific research information quickly， thereby reducing the overall decision-making time overhead. Finally， an implicit optimization module was introduced to generate diverse representations of scientific research information， thereby ensuring that tail discipline research information was able to be fully associated with researchers’ research directions， and accurate semantic matching was achieved through a fine-grained scientific research project ordering model. Experimental results show that on multiple datasets， the recall of the proposed framework reaches 92% in the recall stage， and the accuracy of the proposed framework is 96% in the reordering stage， verifying the effectiveness of MCRF in the task of discipline structure optimization effectively.

Image dehazing is a hot topic in the field of computer vision. Acquiring large-scale， high-quality paired datasets from real world is costly and challenging. Consequently， existing methods use synthetic data for fully supervised deep learning model training， may lead to poor real-world performance of the model. To bridge the domain gap between synthetic and real domains， a semi-supervised image dehazing algorithm based on teacher-student learning was introduced. In this algorithm， a semi-supervised teacher-student learning with Exponential Moving Average （EMA） strategy was used to update the teacher model， and an end-to-end dehazing learning was performed， thereby addressing domain shift issues between synthetic and real data significantly and enhancing generalization performance of the model in real hazy scenarios. Experimental results demonstrate that the proposed algorithm achieves superior performance on two synthetic hazy image datasets SOTS （Synthetic Objective Testing Set） and Haze4K， as well as the real-world hazy image dataset URHI （Unannotated Real-world Hazy Images）， while also delivering enhanced dehazing visual effects.

To counteract community detection algorithms and thereby protect node privacy， community hiding methods have garnered more and more attention. However， current mainstream community hiding algorithms only focus on the network’s topological structure， neglecting the influence of node attributes on community structure， leading to bad performance on attribute networks. In response to these issues， an Attribute network Community hiding method based on Genetic algorithm （ACG） was proposed. In this method， network topological structure and node attributes were integrated， with the core of finding the optimal edge hiding strategy by optimizing a fitness function. In ACG， while minimizing hiding costs， maximizing modularity and attribute similarity was adopted as dual metric to select and perturb the set of edges with the greatest impact on community structure， thereby attacking community detection algorithms for attribute networks effectively. Experimental results demonstrate that without changing the total number of edges and attribute information， the proposed method counters mainstream attribute community detection methods effectively； compared with other community hiding methods， ACG has advantages in counteracting classic community detection algorithms on five attribute networks.

Dynamic searchable encryption has attracted wide attention due to its ability to add， delete， and search data on cloud servers. The existing dynamic searchable encryption schemes are usually constructed using highly secure cryptographic primitives， and multiple bilinear pairing operations need to be performed during scheme searching. In view of the large computational overhead of dynamic searchable encryption schemes when searching on servers， a Puncturable PseudoRandom Function （PPRF） was introduced into dynamic searchable encryption， and a dynamic searchable encryption scheme based on PPRF was designed and proposed. In this scheme， file identifiers did not need to be encrypted using symmetric encryption algorithms， and it is also not necessary to decrypt ciphertext to obtain file identifiers during server searches， and the client and the server were able to complete data search with only one interaction. At the same time， in the scheme， the key was marked when deleting keywords， the marked key was used to calculate the PPRF during search， and backward security was implemented with a forward-secure scheme， thereby ensuring security while improving search efficiency. According to security model of the dynamic searchable encryption scheme， the security of the scheme was verified. Simulation results show that compared with ROSE （RObust Searchable Encryption） scheme built on Key-Updatable Pseudorandom Function （KUPRF）， Janus++ scheme built on Symmetric Puncturable Encryption （SPE）， and Aura scheme built on Symmetric Revocable Encryption （SRE）， the proposed scheme has the average search time of each keyword reduced by 17%， 65%， and 58%， respectively. It can be seen that the proposed scheme is effective and feasible， and reduces the search cost of the server effectively， improves the search efficiency of the scheme， and increases the practicality of the scheme.

With the increasingly serious problem of global climate change， the goals of carbon peaking and carbon neutrality have been established in China. As logistics hubs and cargo distribution centers， the ports have highlighted carbon emission problem. Aiming at optimization problem of port operation scheduling， considering the key factors such as ship arrival time， cargo handling demand， quay crane operation capacity， and carbon emission cost， an optimization model of port operation scheduling was constructed for minimizing both carbon emission cost and terminal operating expense， and a port operation scheduling algorithm based on Enhanced NSGA-Ⅱ （Non-dominated Sorting Genetic Algorithm Ⅱ） （E-NSGA-Ⅱ） under the goals of carbon peaking and carbon neutrality was proposed. Firstly， the coding strategy， population initialization method and crossover and mutation operations of the algorithm were adjusted. Secondly， gene repair operators of infeasible solutions were designed， and adaptive crossover and mutation probability mechanisms were introduced. Experimental results show that compared with FCFS （First Come First Service） scheduling algorithm， the proposed algorithm reduces the total cost of model solving by 7.9%， the carbon emission cost by 19.7%， and the terminal operating expense by 6.5%. The above research results enrich the multi-objective optimization algorithm and port operation scheduling theory， and provide strong support for port enterprises to achieve green scheduling， reduce operating cost， and improve economic benefits.

In order to solve the problems that copyright owners maliciously frame purchasers up and purchasers know their own watermarks so remove them easily during the digital content copyright protection and tracking processes， a digital content copyright protection and fair tracking scheme based on blockchain was proposed. Firstly， Paillier homomorphic encryption algorithm and key distribution smart contract were used to change the purchaser’s watermark in ciphertext state， and the watermark was embedded in the encrypted digital content. Secondly， the key distribution smart contract and arbitration smart contract were called by the verification node in blockchain， which solved the single point of failure problem in the traditional copyright protection solutions. Finally， experiments were conducted to verify the performance of the proposed scheme. The results show that when the digital content size is 1 024×1 024， compared with the blockchain-enabled accountability mechanism against information leakage in vertical industry services， the proposed scheme has the total execution time of encryption and watermark embedding reduced by 94.92%， and the total decryption execution time reduced by 79.72%. It can be seen that the proposed scheme has low total time and operating costs with good efficiency， and can be widely used in the field of digital content copyright protection.

Significant differences in object scale and aspect ratio in remote sensing images lead to difficult object detection in remote sensing images. Aiming at this characteristic of remote sensing image， in order to improve the precision of object detection in remote sensing images， EW-YOLO （Efficient Weighted-YOLO） was proposed by improving the YOLO framework. Firstly， the multi-level feature fusion structure was introduced in the feature fusion section， so that the dual-branch residual module was utilized to promote the fusion of features at different scales. And by the cascade of feature fusion modules and the cross-layer feature fusion design， the extraction capability of objects at different scales was improved， and the detection capability was further enhanced. Secondly， in the prediction section， the weighted detection head was proposed and Weighted Boxes Fusion （WBF） was introduced， so as to improve the detection precision of objects with different aspect ratios by weighting each candidate box using the confidence scores and generating prediction boxes by fusion. Finally， to address the issue of too large image size， an image resampling technique was proposed， which means that the images were sampled to appropriate sizes and joined into network training， solving the problem of low detection precision of large-size objects caused by cropping. Experimental results on DOTA dataset show that the detection mean Average Precision （mAP） of the proposed method is 77.47%， which is increased by 1.55 percentage points compared to that of the original YOLO framework based method. And compared with the current mainstream methods， the proposed method has superior performance. At the same time， the proposed method’s effectiveness is also verified on HRSC and UCAS-AOD datasets.

Although community detection can reveal underlying structural characteristics of the network and relationships between nodes deeply， it also raises privacy leakage issues. Community hiding methods can resist community detection algorithms effectively， thereby achieving privacy protection of network node information. However， most of the traditional community hiding methods only focus on privacy protection of a single target or community in the network， there is a lack of a method that can hide any target set. In order to solve the above problems， a Based on Permanence-loss Maximization for multiple target Nodes Hiding （BPMNH） method was proposed. In the method， the set of target nodes to be hidden was able to be configured freely， and permanence loss maximization scheme was provided according to the network scale adaptively， thereby achieving hiding of multiple target nodes in different communities with minimal network topology disturbance cost. On eight datasets such as Karate， the experimental results show that BPMNH is better than three baseline methods such as Modularity Based Attack （MBA） in terms of hiding effect， network structure and comprehensive deception effect， validating the superiority of the proposed method in multi-target node hiding.

In recent years， Deformable Convolutional Network （DCN） has been widely applied in fields such as image recognition and classification. However， research on the interpretability of this model is relatively limited， and its applicability lacks sufficient theoretical support. To address these issues， this paper proposed an interpretability study of DCN and its application in butterfly species recognition model. Firstly， deformable convolution was introduced to improve the VGG16， ResNet50， and DenseNet121 （Dense Convolutional Network121） classification models. Secondly， visualization methods such as deconvolution and Class Activation Mapping （CAM） were used to compare the feature extraction capabilities of deformable convolution and standard convolution. The results of ablation experiments show that deformable convolution performs better when used in the lower layers of the neural network and not continuously. Thirdly， the Saliency Removal （SR） method was proposed to uniformly evaluate the performance of CAM and the importance of activation features. By setting different removal thresholds and other perspectives， the objectivity of the evaluation is improved. Finally， based on the evaluation results， the FullGrad （Full Gradient-weighted） explanation model was used as the basis for the recognition judgment. Experimental results show that on the Archive_80 dataset， the accuracy of the proposed D_v2-DenseNet121 reaches 97.03%， which is 2.82 percentage points higher than that of DenseNet121 classification model. It can be seen that the introduction of deformable convolution endows the neural network model with the ability to extract invariant features and improves the accuracy of the classification model.

Both the Damped Least Squares （DLS） and Genetic Algorithm （GA） are applicable to automatic design of optical systems. Although DLS has a high search efficiency， it is susceptible to falling into local optima traps. Conversely， GA has strong global search capability in the parameter space of optical structures but weak local search capability. To address these challenges， a Correctable Reinforced Search GA （CRSGA） was proposed. Firstly， DLS was introduced after the GA crossover operation to enhance local search capability. Additionally， a correction strategy was introduced to rollback individuals with deteriorated fitness values before the next iteration， thereby achieving corrective evolutionary results. The improvement of two aspects to genetic algorithm enhanced strengths and compensated for weaknesses. Three typical optical system design experiments， including Double Gaussian （DG）， Reversed Telephoto （RT）， and Finite Conjugate Distance Imaging （FCDI）， were conducted to validate the effectiveness of CRSGA. CRSGA outperforms both DLS and GA， and its optimization outcomes are about 8.92%， 12.19%， and 9.39% respectively better than those of commercial optical design software Zemax DLS. In particularly， the optimization outcomes achieve a significant improvement， reaching 99.98%， 94.33%， and 88.45% respectively compared to the Zemax HAMMER algorithm. In conclusion， it is shown that the proposed algorithm is effective for optical system optimization and can be used for automatic optical system design.

At present， researches on SQLite encryption both domestically and internationally are conducted at the file level and with the single-key， resulting in coarse encryption granularity and low decryption difficulty. In response to the security shortcomings of SQLite， a multi-key page-level encryption system was proposed. Firstly， an independent page key was assigned to each physical page， allowing for individual encryption and decryption of each page. A key file was introduced to store all page keys. Secondly， a page key cache module KeyCache was designed to generate and cache page keys for pages， thereby reducing the performance loss caused by frequent I/O read and write operations. Thirdly， an encryption and decryption module Crypto was proposed to implement the encryption and decryption functions. Crypto was used to quickly retrieve page keys through KeyCache， consequently enhancing the overall system performance. A comparative experiment was conducted between the proposed system and typical SQLCipher. Experimental results show that in read and update tests， compared with SQLCipher， the execution time of the proposed system reduced by 1.5% and 3.0% on average， achieving better performance at a higher security level. Additionally， in create and delete tests， the proposed system exhibits minimal performance loss compared to SQLCipher and the performance loss is close to SQLCipher while significantly enhancing the security level， verifying the effectiveness of the proposed system.

Aiming at the security analysis problem of KATAN48 algorithm， a conditional differential cryptanalysis method of KATAN48 algorithm based on neural distinguishers was proposed. First， the basic principle of multiple output differences neural distinguishers was studied and applied to KATAN48 algorithm. According to the data format of KATAN48 algorithm， the input format and hyperparameters of the deep residual neural network were adjusted. Then， the Mixed-Integer Linear Programming （MILP） model of KATAN48 algorithm was established to search the prepended differential paths and the corresponding constraint conditions. At last， using the multiple output differences neural distinguishers， at most 80-round of the practical key recovery attack results of KATAN48 algorithm were given. Experimental results show that in the single key setting， the number of practical attack rounds of KATAN48 algorithm is increased by 10 rounds， the number of recoverable key bits of KATAN48 algorithm is increased by 22 bit and the data complexity and time complexity of KATAN48 algorithm are reduced from 2³⁴ and 2³⁴ to 2^16.39 and 2^19.68 respectively. Compared to the previous practical attack at the single-key setting， the proposed method can effectively increase the number of attack rounds and recoverable key bits， and reduces the computational complexity of attack.

The development of hot news events is very rich， and each stage of the development has its own unique narrative. With the development of events， a trend of hierarchical storyline evolution is presented. Aiming at the problem of poor interpretability and insufficient hierarchy of storyline in the existing storyline generation methods， a Hierarchical Storyline Generation Method （HSGM） for hot news events was proposed. First， an improved hotword algorithm was used to select the main seed events to construct the trunk. Second， the hotwords of branch events were selected to enhance the branch interpretability. Third， in the branch， a storyline coherence selection strategy fusing hotword relevance and dynamic time penalty was used to enhance the connection of parent-child events， so as to build hierarchical hotwords， and then a multi-level storyline was built. In addition， considering the incubation period of hot news events， a hatchery was added during the storyline construction process to solve the problem of neglecting the initial events due to insufficient hotness. Experimental results on two real self-constructed datasets show that in the event tracking process， compared with the methods based on singlePass and k-means respectively， HSGM has the F score increased by 4.51% and 6.41%， 20.71% and 13.01% respectively； in the storyline construction process， HSGM performs well in accuracy， comprehensibility and integrity on two self-constructed datasets compared with Story Forest and Story Graph.

Spatial-temporal co-occurrence patterns refer to the video object combinations with spatial-temporal correlations. In order to mine the spatial-temporal co-occurrence patterns meeting the query conditions from a huge volume of video data quickly， a spatial-temporal co-occurrence pattern mining algorithm with a triple-pruning matching strategy — Multi-Pruning Algorithm （MPA） was proposed. Firstly， the video objects were extracted in a structured way by the existing video object detection and tracking models. Secondly， the repeated occurred video objects extracted from a sequence of frames were stored and compressed， and an index of the objects was created. Finally， a spatial-temporal co-occurrence pattern mining algorithm based on the prefix tree was proposed to discover the spatial-temporal co-occurrence patterns that meet query conditions. Experimental results on real and synthetic datasets show that the proposed algorithm improves the efficiency by about 30% compared with Brute Force Algorithm （BFA）， and the greater the data volume， the more obvious the efficiency improvement. Therefore， the proposed algorithm can discover the spatial-temporal co-occurrence patterns satisfying the query conditions from a large volume of video data quickly.

Recently， Approximate Query Processing （AQP） of aggregate functions is a research hotspot in the database field. Existing approximate query techniques have problems such as high query response time cost， high storage overhead， and no support for multi-predicate queries. Thus， a deep autoregressive model-based AQP approach DeepAQP （Deep Approximate Query Processing） was proposed. DeepAQP leveraged deep autoregressive model to learn the joint probability distribution of multi-column data in the table in order to estimate the selectivity and the target column’s probability distribution of the given query， enhancing the ability to handle the approximate query requests of aggregation functions with multiple predicates in a single table. Experiments were conducted on TPC-H and TPC-DS datasets. The results show that compared with VerdictDB， which is a sample-based method， DeepAQP has the query response time reduced by 2 to 3 orders of magnitude， and the storage space reduced by 3 orders of magnitude； compared with DBEst++， which is a machine learning-based method， DeepAQP has the query response time reduced by 1 order of magnitude and the model training time reduced significantly. Besides， DeepAQP can handle with multi-predicate query requests， for which DBEst++ does not support. It can be seen that DeepAQP achieves good accuracy and speed at the same time and reduces the training and storage overhead of algorithm significantly.

Node feature representation was learned by Graph Convolutional Network （GCN） by deep graph matching models in the stage of node feature extraction. However， GCN was limited by the learning ability for node feature representation， affecting the distinguishability of node features， which causes poor measurement of node similarity， and leads to the loss of model matching accuracy. To solve the problem， a deep graph matching model based on self-attention network was proposed. In the stage of node feature extraction， a new self-attention network was used to learn node features. The principle of the network is improving the feature description of nodes by utilizing spatial encoder to learn the spatial structures of nodes， and using self-attention mechanism to learn the relations among all the nodes. In addition， in order to reduce the loss of accuracy caused by relaxed graph matching problem， the graph matching problem was modelled to an integer linear programming problem. At the same time， structural matching constraints were added to graph matching problem on the basis of node matching， and an efficient combinatorial optimization solver was introduced to calculate the local optimal solution of graph matching problem. Experimental results show that on PASCAL VOC dataset， compared with Permutation loss and Cross-graph Affinity based Graph Matching （PCA-GM）， the proposed model has the average matching precision on 20 classes of images increased by 14.8 percentage points， on Willow Object dataset， the proposed model has the average matching precision on 5 classes of images improved by 7.3 percentage points， and achieves the best results on object matching tasks such as bicycles and plants.

Aiming at the problem of low accuracy of ship target detection at sea， a lightweight ship target detection algorithm YOLOShip was proposed on the basis of the improved YOLOv5. Firstly， dilated convolution and channel attention were introduced into Spatial Pyramid Pooling-Fast （SPPF） module， which integrated spatial feature details of different scales， strengthened semantic information， and improved the model’s ability to distinguish foreground and background. Secondly， coordinate attention and lightweight mixed depthwise convolution were introduced into Feature Pyramid Network （FPN） and Path Aggregation Network （PAN） structures to strengthen important features in the network， obtain features with more detailed information， and improve model detection ability and positioning precision. Thirdly， considering the uneven distribution and relatively small scale changes of targets in the dataset， the model performance was further improved while the model was simplified by modifying the anchors and decreasing the number of detection heads. Finally， a more flexible Polynomial Loss （PolyLoss） was introduced to optimize Binary Cross Entropy Loss （BCE Loss） to improve the model convergence speed and model precision. Experimental results show that on dataset SeaShips， in comparison with YOLOv5s， YOLOShip has the Precision， Recall， mAP@0.5 and mAP@0.5：0.95 increased by 4.2， 5.7， 4.6 and 8.5 percentage points. Thus， by using the proposed algorithm， better detection precision can be obtained while meeting the requirements of detection speed， effectively achieving high-speed and high-precision ship detection.

Aiming at the current high delay rate of the civil aviation transportation industry, and the fact that the high-precision delay prediction problem can hardly be solved by traditional algorithms, a randomly connected Clique Network (CliqueNet) based flight delay prediction model was proposed. Firstly, the flight data and related weather data were fused by the model. Then, making full use of the improved network model to extract features from the fused dataset. Finally, the softmax classifier was used to predict the flight departure delay of all levels with high precision. The main features of the model include random connection of clique feature layers and the introduction of Channel-wise and Spatial Attention Residual (CSAR) block to the transition layer. The former transmits the feature information in a more effective connection; and the latter double-calibrates the feature information on the channel and spatial dimensions to improve accuracy. Experimental results show that the prediction accuracy of the fused data is improved by 0.5% and 1.3% respectively with the introduction of random connection and CSAR block, and the final accuracy of the new model reaches 93.40%.

Distributed matrix multiplication is a fundamental operation in many distributed machine learning and scientific computing applications， but its performance is greatly influenced by the stragglers commonly existed in the systems. Recently， researchers have proposed a fountain code based coded matrix multiplication method， which can effectively mitigate the effect of stragglers by fully exploiting the partial results of stragglers. However， it lacks the consideration of the storage cost of worker nodes. By considering the tradeoff relationship between the storage cost and the finish time of computation， the computational deadline-aware storage optimization problem for heterogeneous worker nodes was proposed firstly. Then， through the theoretical analysis， the solution based on expectation approximation was presented， and the problem was transformed into a convex optimization problem by relaxation for efficient solution. Simulation results show that in the case of ensuring a large task success rate， the storage overhead of the proposed scheme will rapidly decrease as the task duration is relaxed， and the scheme can greatly reduce the storage overhead brought by encoding. In other words， the proposed scheme can significantly reduce the extra storage overhead while guaranteeing that the whole computation can be finished before the deadline with high probability.

Focusing on the low accuracy of person re-identification caused by that the similarity between different pedestrians' images is more than that between the same pedestrians' images in reality, a person re-identification method based on Siamese network combined with identification loss and bidirectional max margin ranking loss was proposed. Firstly, a neural network model which was pre-trained on a huge dataset, especially its final full-connected layer was structurally modified so that it can output correct results on the person re-identification dataset. Secondly, training of the network on the training set was supervised by the combination of identification loss and ranking loss. And according to that the difference between the similarity of the positive and negative sample pairs is greater than the predetermined value, the distance between negative sample pair was made to be larger than that of positive sample pair. Finally, a trained neural network model was used to test on the test set, extracting features and comparing the cosine similarity between the features. Experimental result on the open datasets Market-1501, CUHK03 and DukeMTMC-reID show that rank-1 recognition rates of the proposed method reach 89.4%, 86.7%, and 77.2% respectively, which are higher than those of other classical methods. Moreover, the proposed method can achieve a rank-1 rate improvement of up to 10.04% under baseline network structure.

Aiming at difficult multi-target identification recognition and low localization accuracy in mobile cellular networks, a multi-objective automatic identification and localization method was presented based on cellular network structure to improve the detection efficiency of target number and the localization accuracy of each target. Firstly, multi-target existence was detected through the analysis of the result variance of multiple positioning in the monitoring area. Secondly, cluster analysis on locating points was conducted by k-means unsupervised learning in this study. As it is difficult to find an optimal cluster number for k-means algorithm, a k-value fission algorithm based on beam resolution was proposed to determine the k value, and then the cluster centers were determined. Finally, to enhance the signal-to-noise ratio of received signals, the beam directions were determined according to cluster centers. Then, each target was respectively positioned by Time Difference Of Arrival (TDOA) algorithm by the different beam direction signals received by the linear constrained narrow-band beam former. The simulation results show that, compared to other TDOA and Probability Hypothesis Density (PHD) filter algorithms in recent references, the presented multi-objective automatic identification and localization method for solving multi-target localization problems can improve the signal-to-noise ratio of the received signals by about 10 dB, the Cramer-Mero lower bound of the delay estimation error can be reduced by 67%, and the relative accuracy of the positioning accuracy can be increased more than 10 percentage points. Meanwhile, the proposed algorithm is simple and effective, is relatively independent in each positioning, has a linear time complexity, and is relatively stable.

Aiming at the problem of high misdiagnosis rate, high false positive rate and low detection accuracy in pulmonary nodule computer-aided detection, a method of nodular detection based on three-dimensional shape index and Hessian matrix eigenvalue was proposed. Firstly, the parenchyma region was extracted and the eigenvalues and eigenvectors of the Hessian matrix were calculated. Secondly, the three-dimensional shape index formula was deduced by the two-dimensional shape index, and the improved three-dimensional spherical like filter was constructed. Finally, in the parenchyma volume, the suspected nodule region was detected, and more false-positive regions were removed. The nodules were detected by the three-dimensional volume data, and the detected coordinates were input as the seeds of belief connect, and the three-dimensional data was splited to pick out three-dimensional nodules. The experimental results show that the proposed algorithm can effectively detect different types of pulmonary nodules, and has better detection effect on the ground glass nodules which are more difficult to detect, reduces the false positive rate of nodules, and finally reaches 92.36% accuracy rate and 96.52% sensitivity.

In order to effectively master protocol interactive behavior, a method to automatically build protocol interactive process based on message sequence chart was proposed. Firstly, according to the characteristics of the protocol interactive process, the dependency graph was defined to represent the partial order of events in message sequence, and the network flows were converted to dependency graphs. Secondly, the basic message sequences were used to describe protocol interactive behavior fragments, and the basic message sequences were mined by defining event maximum suffix. Finally, the maximum dependency graphs that were found out were connected and merged to build a message sequence chart. The experimental results show that the proposed method has a high accuracy and the built message sequence chart can visually represent the protocol interactive process.

In order to solve the real-time problem of visual navigation system with traditional motion estimation algorithm, a new approach based on classified feature points for mobile robot motion estimation was proposed. For dividing feature points into far points and near points, the distances between feature points and mobile robot were calculated according to the 3-dimensional coordinates of feature points. The far points were sensitive to the rotational movement of robot, thus they were used to calculate rotational matrix; the near points were sensitive to translational motion, thus they were used to calculate the translational matrix. When the far points and the near points are 30% of original feature points, the proposed approach had equivalent accuracy but reduced 60% computing time compared with RANdom SAmple Consensus (RANSAC). The results demonstrate that, by using classified feature points, the proposed algorithm can effectively reduce computing time, meanwhile ensure accuracy of motion estimation, and it can meet the the real-time requirement with large feature points.

In view of the efficiency problem of multi-objective recommender systems, this paper utilized the online and offline separation strategy to construct a new frame of recommender system. Aiming at the multi-objective feature of recommender system and current recommendation algorithms' limitations in adaptability, this paper put forward a new multi-objective recommendation algorithm based on the hybrid strategy. Firstly, the algorithm did weighted mix of multiple recommendation algorithms. Secondly, it established a multi-objective optimization model, using the weight sequence as variables and evaluation metrics including F-score, diversity and novelty as objective functions. Then, it optimized the solution through a second version of Strength Pareto Evolutionary Algorithm (SPEA2). Finally, it recommended items to users based on users' shopping preferences and the Pareto set. The experimental results show that: compared with the best single metric sub-recommendation algorithm, the new recommendation algorithm is nearly as well in the F-score, meanwhile increases by 1% in the diversity and increases by 11.5% in the novelty; the distribution of various Pareto solutions of multi-objective forms a dense and neighboring point curve in the solution space. So the recommender algorithm can satisfy the recommend requirements of users with different shopping preferences.

Splicing is the most universal image tampering operation, detection of which is effective for identifying image tamper. A blind splicing detection method was proposed. The method firstly analyzed the effects of different sub-bands on image splicing detection according to features of wavelet transform. High frequency sub-band was verified to be more appropriate for splicing detection both from theory analysis and experiment results. Secondly, the method conducted difference operation, rounded and made threshold to the coefficients as discrete Markov states, and calculated the state transition probabilities as splicing features. Finally, Support Vector Machine (SVM) was used as classifier, and the features were tested on Columbia image splicing detection evaluation datasets. The experimental results show that the proposed method performs better compared with other features and achieves a detection accuracy rate of 94.6% on the color dataset specially.

In order to solve the problem of complexity for laying the ground magnetic, laser reflection point or other devices before industrial mobile robot can come into service, and the inflexibility resulting from the fixed work path, a scheme of industrial mobile robot navigation based on inertial and ultrasonic sensors was proposed. Operator needed to train the robot from one target position moving towards another target position in advance to acquire train path. When the robot worked in non-target area, i.e. the area demanding low location accuracy, it navigated according to the train path based on inertial sensors; When coming into target area, i.e. the area containing target position and demanding high location accuracy, ultrasonic sensors conducted the navigation. The scheme shortened the preparation period, and it was convenient to change work path. The simulation results show that the scheme combining inertial navigation and ultrasonic location is feasible.

To solve the problem of large amount of calculation and nonlinear programming in the process of service composition optimization, a Cost Benefit Coefficient (CBC) approach was proposed for Web services composition reliability optimization in the situation of a given cost investment. First, the structure patterns of service composition and related reliability function were analyzed. Furthermore, the Web service composition method of reliability calculation was proposed and a nonlinear optimization model was established accordingly. And then the cost benefit coefficient was computed through the relationship between the cost and the reliability of component services, and the optimization schemes of Web service composition were decided. According to the nonlinear optimization model, the results of optimization were computed. Finally, given cost investment, the higher reliability of the approach to optimize the reliability of Web service composition was verified through the comparison of this approach and the traditional method on the reliable data of component service. The experimental results show that the proposed algorithm is effective and reasonable for reliability optimization of Web services composition.

In view of the problem that high definition stereoscopic video sequences have high resolution, less information of macro block, and network transmission error, an end-to-end transmission distortion model was proposed. Considering error diffusion between frames caused by packet loss and the characteristics of spatial and temporal correlation, the recursive algorithm could estimate distortion accurately. And the error concealment method of copying the previous one of the lost frame was mainly used in the model, reducing the dependencies of the decoder. The simulation results show that the average prediction error of the distortion model can be controlled within 6%, and this model can be adapted to estimate transmission distortion for stereo video sequences with different features and resolutions under different network environments.