The problems of large number of targets， small scale and high-overlapping lead to low accuracy and difficulty in target detection. In order to improve the precision of target detection and avoid missed detection and false detection as much as possible， an improved YOLOv3 target detection algorithm based on boundary limit point features was proposed. Firstly， a boundary enhancement operator Border was introduced to adaptively extract boundary features from the limit points of the boundary to enhance the features of the existing points and improve the accuracy of target positioning. Then， the precision of target detection was further improved by increasing the target detection scale， refining the feature map， and enhancing the fusion of the feature image deep and shallow semantic information. Finally， based on the target instance characteristics in target detection and the improved network model， the Complete Intersection over Union （CIoU） function was introduced to improve the original YOLOv3 loss function， thereby improving the convergence speed and recall of the detection box. Experimental results show that compared with the original YOLOv3 target detection algorithm， the improved YOLOv3 target detection algorithm has the Average Precision increased by 3.9 percentage points ， and has the detection speed similar to the original algorithm， verifying that it can effectively improve the target detection ability of models.

In order to overcome the shortcomings of traditional FireWorks Algorithm (FWA) in the process of optimization, such as the search range limited by explosion radius and the lack of effective interaction between particles, an Enhanced FireWork Algorithm with adaptive Merging strategy and Guidance operator (EFWA-GM) was proposed. Firstly, according to the position relationship between fireworks particles, the overlapping explosion ranges in the optimization space were adaptively merged. Secondly, by making full use of the position information of high-quality particles through layering the spark particles, the guiding operator was designed to guide the evolution of suboptimal particles, so as to improve the accuracy and convergence speed of the algorithm. Experimental results on 12 benchmark functions show that compared with Standard Particle Swarm Optimization (SPSO) algorithm, Enhanced FireWorks Algorithm (EFWA), Adaptive FireWorks Algorithm (AFWA), dynamic FireWorks Algorithm (dynFWA), and Guided FireWorks Algorithm (GFWA), the proposed EFWA-GM has better optimization performance in optimization accuracy and convergence speed, and obtains optimal solution accuracy on 9 benchmark functions.

Aiming at the problem that the joint velocity of the rail manipulator deviates from the expected value during the process of task execution, a pseudoinverse-based motion planning scheme for deviation correction of joint velocity of rail manipulator was proposed. Firstly, according to the joint angle state of the manipulator and the motion state of the end-effector, the pseudoinverse algorithm was used to analyze the redundancy of the rail manipulator on the velocity level. Secondly, a time-varying function was designed to perform constraint and adjustment of the joint velocity, making the deviated joint velocity converge to the expected value. Thirdly, an error correction method was employed to reduce the position error of the end-effector for ensuring the successful execution of the trajectory tracking task. Finally, the motion planning scheme was simulated on Matlab software with the four-bar redundant manipulator with the base of linear movement and circular movement as the example. The simulation results show that the proposed motion planning scheme can correct the joint velocity of the rail manipulator deviated from the expected value during the task execution, and can make the end-effector obtain higher accuracy in trajectory tracking.

In order to improve the accuracy of loan financial customer behavior prediction, aiming at the incomplete problem of dealing with non-numerical factors in data analysis of traditional K-Nearest Neighbors (KNN) algorithm, an improved KNN algorithm based on Value Difference Metric (VDM) distance and iterative optimization of clustering results was proposed. Firstly the collected data were clustered by KNN algorithm based on VDM distance, then the clustering results were analyzed iteratively, finally the prediction accuracy was improved through joint training. Based on the customer data collected by Portuguese retail banks from 2008 to 2013, it can be seen that compared with traditional KNN algorithm, FCD-KNN (Feature Correlation Difference KNN) algorithm, Gauss Naive Bayes algorithm, Gradient Boosting algorithm, the improved KNN algorithm has better performance and stability, and has great application value in the customer behavior prediction from bank data.

The exponential growth in the number of wireless mobile devices leads that heterogeneous cooperative Small Base Stations (SBS) carry large-scale traffic load. Aiming at this problem, an Online-hot Video Cache Replacement Policy (OVCRP) based on cooperative SBS and popularity prediction was proposed. Firstly, the changes of popularity in short term of online-hot videos were analyzed, then a k-nearest neighbor model was constructed to predict the popularities of the online-hot videos, and finally the locations for cache replacement of online-hot videos were determined. In order to select appropriate locations to cache the online-hot videos, with minimization of overall transmission delay as the goal, a mathematical model was built and an integer programming optimization algorithm was designed. The simulation experiment results show that compared with the schemes such as RANDOM cache (RANDOM), Least Recently Used (LRU) and Least Frequently Used (LFU), the proposed OVCRP has obvious advantages in average cache hit rate and average access delay, reducing the network burden of cooperative SBS.

In order to solve the problem that the traditional deep learning based remote sensing image classification algorithms cannot effectively fuse multiple deep learning features and their classifiers have poor performance, an improved high-resolution remote sensing image classification algorithm based on deep learning was proposed. Firstly, a seven-layer convolutional neural network was designed and constructed. Secondly, the high-resolution remote sensing images were input into the network to train it, and the last two fully connected layer outputs were taken as two different high-level features for the remote sensing images. Thirdly, Principal Component Analysis (PCA) was applied to the output of the fifth pooling layer in the network, and the obtained dimensionality reduction result was taken as the third high-level features for the remote sensing images. Fourthly, the above three kinds of features were concatenated to get an effective deep learning based remote sensing image feature. Finally, a logical regression based classifier was designed for remote sensing image classification. Compared with the traditional deep learning algorithms, the accuracy of the proposed algorithm was increased. The experimental results show that the proposed algorithm performs excellent in terms of classification accuracy, misclassification rate and Kappa coefficient, and achieves good classification results.

A Combined Prediction Scheme (CPS) and a concept of Prediction Accuracy Assurance (PAA) were put forward for the runtime of local and remote tasks, on the issue of inapplicability of the singleness policy to all the heterogeneous tasks. The toolkit of GridSim was used to implement the CPS, and PAA was a quantitative evaluation standard of the prediction runtime provided by a specific strategy. The simulation experiments showed that, compared with the local task prediction strategy such as Last and Sliding Median (SM), the average relative residual error of CPS respectively reduced by 1.58% and 1.62%; and compared with the remote task prediction strategy such as Running Mean (RM) and Exponential Smoothing (ES), the average relative residual error of CPS respectively reduced by 1.02% and 2.9%. The results indicate that PAA can select the near-optimal value from the results of comprehensive prediction strategy, and CPS enhances the PAA of the runtime of local and remote tasks in the computing environments.

To solve the node deployment problem caused by unreliable information provided by the sensors, four different forms of static Wireless Sensor Network (WSN) deployment were addressed. The four problems were formalized as combinatorial optimization problems, which were Non-deterministic Polynomial (NP)-complete. Furthermore, an uncertainty-aware deployment algorithm based on dynamic programming was proposed. Firstly, the K-best placements of sensor nodes within the region of interest were found, and then the best deployment scheme was selected over the K-best placements. The proposed algorithm was able to determine the minimum number of sensors and their locations to achieve both coverage and connectivity. The simulation results show that, compared with the state-of-the-art deployment strategies, the performance of the proposed algorithm is better than the existing methods in terms of the uniform coverage requirement, the preferential coverage requirement and the network connectivity.

To solve target tracking with target changes under complex background, an adaptive target tracking method that combined graph-based semi-supervised learning method with the particle filter was proposed. It used LLGC (Learning with Local and Global Consistency) algorithm to establish the cost function, and took current status of the candidate as unlabeled samples, then established diagram using all samples as vertex, taking the optimal solution of the cost function as current status, obtaining the target position in current frame. Besides, it used the tracking result to update the labeled samples in real time, so that the algorithm could adapt to the target deformation, partial occlusion and illumination changes. Analysis and experiment show that the proposed method can handle complicated situations like occlusion or similar background interference very well, and achieves target tracking robustly.

In order to solve the problem of lack of co-rated users caused by data sparseness and similarity calculation method, the authors, by making use of the advantage of cloud model transformation between qualitative concept and quantitative numerical value, proposed an improved personal recommendation algorithm based on cloud model and users clustering. The users’ preference on the evaluation of item attribute was transformed to preference on digital characteristics represented by integrated cloud model. By using the improved clustering algorithm, the authors clustered the rating data and the standardized original user attribute information, and at the same time, by taking into account the changes of the users’ interests, recommended the neighbor users’ union generated by similarity based on integrated cloud model of items attributes evaluation between users, clustering of users for item rating, and clustering of user attributes these three methods. The theoretical analysis and experimental results show that the proposed improved algorithm can not only solve the problem of lack of co-rated users caused by data sparseness, but also obtain satisfactory mean absolute error and root-mean-square error even when the users are new. Theoretical analysis and experimental results show that the proposed improved algorithm can not only solve the problem of lack of co-rated users caused by sparseness data, but also obtain satisfactory mean absolute error and root-mean-square error even when the users are new.

Due to the low illumination, low contrast and similar color between target and environment in a coal mine, problems of undetected objects and false detections appear. An improved miner target detection method was proposed, integrating Gaussian Mixture Model (GMM) with Local Binary Pattern (LBP). The color information of background was fitted by means of GMM, and the texture information was extracted by employing LBP, then the miners targets were detected by integrating the color and the texture information. The simulation results indicate that the proposed algorithm decreases the problems of undetected objects and false detections, and can detect miner target in real-time with high precision.

To overcome the weakness of over-concentration when the population of Particle Swarm Optimization (PSO) is initialized and the search precision of basic PSO is not high, an Improved PSO (IPSO) for constrained optimization problems was proposed. A technique of Good Point Set (GPS) was introduced to distribute the initialized particles evenly and the population with diversity would not fall into the local extremum. Co-evolutionary method was utilized to maintain communication between the two populations; thereby the search accuracy of PSO was increased. The simulation results indicate that, the proposed algorithm obtains the theoretical optimal solutions on the test of five benchmark functions used in the paper and the statistical variances of four of them are 0. The proposed algorithm improves the calculation accuracy and robustness and it can be widely used in the constrained optimization problems.

In order to speed up forming Directed Diffusion (DD) gradient field and improve the connectivity of logic networks, a Directed Diffusion Gradient Field based on Double Gradient (DDGF-DG) for Vehicular Sensor Networks (VSN) was proposed. With the help of the estimated gradient value of roadside-node, the large scale vehicular sensor network was divided into a certain number of sub-reigns taking roadside-nodes as the local cores, the local directed diffusion gradient field around every roadside-node was set up in distributed way, and at last, the global directed diffusion gradient field composed of the local directed diffusion gradient fields was formed with the help of double gradient value, so the autonomous management in every sub-reign was realized. Theoretical analysis and simulation results show that DDGF-DG and its dynamic adjustment would reduce the time consumption and improve the real-time connectivity.

To improve the accuracy and real-time performance of particle filter algorithm for tracking vision object, an improved algorithm in combination with mean shift and particle filter was proposed. Similar particles were clustered, and representative particles were iterated in each cluster by using mean shift algorithm. Then computation complexity was reduced by fewer mean shift iterative particles. Particle number and process noise distribution were adjusted adaptively based on tracking condition to improve tracking accuracy and reduce computation complexity. The experimental results prove the superiority of the proposed method, the average of each frame' operation time of this method is less than half of classic bybrid algorithm, and its computation complexity is also less than classic bybrid algorithm.

In seismic exploration interpretation, the application of coherent technology can clearly identify faults and stratigraphy, but the traditional calculation method cannot meet the need of the coherence body calculation from 3D seismic data. Based on CUDA (Compute Unified Device Architecture) platform, a coherence parallel algorithm was proposed. It could accelerate the speed of matrix multiplication with the performance of GPU cluster. Extensive experiments have been conducted in a PC with Intel Core2Due CPU and NVIDIA GeForce 8800 GT graphic card, and the results prove the efficiency of the proposed algorithm. Even though the actual speedups in production codes will vary with the particular problem, the results obtained here indicate that GPU can potentially be a very useful platform for processing large-scale seismic data.

An algorithm of the quick stereo edge matching method was proposed. Using wavelet transform, edges and their direction angle which is used as a matching constraint in the image were gained. On the basis of the probability density function of the disparity gradient,the mutual coordinate constraint of the corresponding points of the two adjoing points in the continous edge of the left image was educed,then the search area of the matching point in the right image was limited. At last, quick edge matching method based on the two constraint was given.