The current research on the activity semantic recognition only extracts the sequence features and periodic features on the time dimension, and lacks deep mining of spatial information. To solve these problems, an activity semantic recognition method based on joint features and eXtreme Gradient Boosting (XGBoost) was proposed. Firstly, the activity periodic features in the temporal information as well as the latitude and longitude features in the spatial information were extracted. Then the latitude and longitude information was used to extract the heat features of the spatial region based on the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm. The user activity semantics was represented by the feature vectors combined with these features. Finally, the activity semantic recognition model was established through the XGBoost algorithm in the integrated learning method. On two public check-in datasets of FourSquare, the model based on joint features has a 28 percentage points improvement in recognition accuracy compared to the model with only temporal features, and compared with the Context-Aware Hybrid (CAH) method and the Spatial Temporal Activity Preference (STAP) method, the proposed method has the recognition accuracy increased by 30 percentage points and 5 percentage points respectively. Experimental results show that the proposed method is more accurate and effective on the problem of activity semantic recognition compared to the the comparison methods.

In order to objectively and accurately evaluate the image fusion algorithms, an evaluation algorithm based on TV-L¹ (Total Variation regularization) structure and texture decomposition was proposed. According to the studies on human visual system, human's perception to image quality mainly comes from the underlying visual features of image, and structure features and texture features are the most important features of underlying visual feature of image. However, the existed image fusion quality evaluation algorithms ignore this fact and lead to inaccurate evaluation. To address this problem, a pair of source images and their corresponding fusion results were individually decomposed into structure and texture images with a two-level TV-L¹ decomposition. Then, According to the difference of image features between the structure and texture images, the similarity evaluation was carried out from the decomposed structure image and the texture image respectively, and the final evaluation score was obtained by integrating the scores at all levels. Based on the dataset with 30 images and 8 mainstream fusion algorithms, compared with the 11 existing objective evaluation indexes, the Borda counting method and Kendall coefficient were employed to verify the consistency of the proposed evaluation algorithm. Moreover, the consistency between the proposed objective evaluation index and the subjective evaluation is verified on the subjective evaluation image set.

An image similarity algorithm based on Lance Williams distance was proposed to solve the problem that the boundary of similarity between dust image and dust-free image is not obvious when illumination changes in desktop dust detection. The Lance Williams distance between template image and the images with or without dust was converted to the similarity value of (0, 1] and the difference of similarity values was expanded with exponential function properties in the algorithm. In order to enhance the dust texture feature information, the gray image was convolved with the Laplacian and then the feature parameters were obtained using co-occurrence matrix feature extraction algorithm and combined into a one-dimensional vector. The similarity of feature parameter vectors between template image and to-be-detected image was calculated by the improved similarity algorithm to determine whether the desktop has dust or not. Experimental results show that the similarity is more than 90.01% between dust-free images and less than 62.57% between dust and dust-free images in the range of 300~900 lux illumination. The average of the two similarities can be regarded as the threshold to determine whether the desktop has dust or not when illumination changes.

Aiming at the deficiencies of traditional Differential Evolution (DE) algorithm, low optimization accuracy and low convergence speed, a Cross-Population Differential Evolution algorithm based on Opposition-based Learning (OLCPDE) was proposed by using chaos dispersion strategy, opposition-based optimization strategy and multigroup parallel mechanism. The chaos dispersion strategy was used to generate the initial population, then the population was divided into sub-groups of the elite and the general, and a standard differential evolution strategy and a differential evolution strategy of Opposition-Based Learning (OBL) were applied to the two sub-groups respectively. Meanwhile, a cross-population differential evolution strategy was applied to further improve the accuracy and enhance population diversity for unimodal function. The sub-groups were handled through these three strategies to achieve co-evolution. After the experiments are totally run for 30 times independently, it is proven that the proposed algorithm can stably converge to the global optimal solution in 11 functions among 12 standard test functions, which is superior to other comparison algorithms. The results indicate that the proposed algorithm not only has high convergence precision but also effectively avoid trapping in local optimum.

In the digital Instrumentation Landing System (ILS) transformation, aiming at the problem that the ILS adopts the amplitude angle measuring system and is sensitive to the distortion of the amplitude of the transmitted signal, a calibration algorithm of the transmission channel of the digital ILS was proposed. Firstly, the mathematical model of the transmitter's landing system was established, and the effect of the non-linearity of the transmission channel on the angular performance of the ILS was simulated. Secondly, a transmitter structure with a feedback loop in the digital instrumentation landing system was proposed. Finally, the transmission channel was calibrated by solving the inverse model of the transmission channel in the baseband using the Least Mean Square (LMS) algorithm, and using the inverse model to compensate the nonlinear distortion of the transmission channel. The simulation results show that the proposed algorithm can quickly estimate the inverse model of the transmission channel under noise conditions and has good calibration performance.

Intelligent air combat is a hot research topic in military aviation field and missile hit prediction is an important part of intelligent air combat. Aiming at the shortcomings of insufficient research on missile hit prediction, poor optimization ability of the algorithm, and low prediction accuracy of the model, a missile hit prediction model based on Adaptively-Mutated Chaotic Particle Swarm Optimization (AMCPSO) and Support Vector Machine (SVM) was proposed. Firstly, feature extraction of air combat data was carried out to build sample library for model training; then, the improved AMCPSO algorithm was used to optimize the penalty factor C and the kernel function parameter g in SVM, and the optimized model was used to predict the samples; finally, comparison tests with classical PSO algorithm, the BP neural network method and the method based on lattice were made. The results show that the global and local optimization ability of the proposed algorithm are both stronger, and the prediction accuracy of the proposed model is higher, which can provide a reference for missile hit prediction research.

In order to achieve unified management and remote communication of measuring equipment in car body-in-white online visual inspection station, a measurement and control system for the car body-in-white detection was designed to improve the working efficiency. Using STM32F407 as the core, μC/OS-Ⅱ and LwIP were transplanted to build a Web server, and the Web server was set up to realize remote communication. Multithreaded tasks were established to achieve the information interaction between serial port and net port. By analyzing the data security issue in the process of data's routing and discussing the phenomenon of packet loss on transmitting, a solution was proposed. 2D normalized cross-correlation method was used to realize the image 2D positioning, and enhome the processing speed. The experimental results show that the system can provide remote communication function, reduce the cost, and improve the efficiency of equipment management.

Concerning the defects of low optimization precision and easy to fall into local optimum in Fruit Fly Optimization Algorithm (FOA), a Fruit Fly Optimization Algorithm based on Simulated Annealing (SA-FOA) was proposed. The receiving mechanism of solution and the optimal step size were improved in SA-FOA. The receiving probability was based on the generalized Gibbs distribution and the receiving of solution met Metropolis criterion. The step length decreased with the increasing iteration according to non-uniform variation idea. The simulation result using several typical test functions show that the improved algorithm has high capability of global searching. Meanwhile, the optimization accuracy and convergence rate are also improved greatly. Therefore, it can be used to optimize the parameters of neural network and service scheduling models.

To solve the time-consuming problem of group-by aggregation operation in case of data-intense computation, a cache-friendly group-by aggregation method was proposed. In this paper, the group-by aggregation operation was optimized in two aspects. Firstly, designing cache-friendly group-by aggregation algorithm on Supersonic, an open-source and column-oriented query execution engine, to take the full advantage of column-storage on in-memory computation. Secondly, rewriting the algorithm with multi-threads to speed up the query. In this paper, four different parallel aggregation algorithms were put forward, respectively named Shared-Nothing Parallel Group-by Aggregation (NSHPGA) algorithm, Table-Lock Shared-Hash Parallel Group-by Aggregation (TLSHPGA) algorithm, Bucket-Lock Shared-Hash Parallel Group-by Aggregation (BLSHPGA) algorithm and Node-Lock Shared-Hash Parallel Group-by Aggregation (NLSHPGA) algorithm. Through a series of comparison experiment on different group power set and different number of worker threads, NLSHPGA algorithm was proved to have the best performance both on speed-up ratio and concurrency, which achieved 10x speedups on part of queries. Besides, considering Cache miss and memory utilization, the results shows that NSHPGA algorithm is suitable for smaller group power set, which was 8 in the experiment, and when getting larger, NLSHPGA algorithm performs better than NSHPGA algorithm.

Network vulnerability assessment which intends to safety situation analysis and establishment of defensive measures before attack is a kind of active defense technology, but the traditional quantitative analysis models cannot show the dynamic interactive relationship between entities, and most of them cannot get global results for risk diffusion. With reference to the influence of social network in the process of communication, a new network vulnerability diffusion analysis method based on cumulative effect was proposed. The defined vulnerability diffusion analysis model described subject relation structure in a more detailed level, and the algorithm proposed by using the accumulation characteristics in attack effects described vulnerability diffusion rule more accurately to ensure better influence range. At last, the model and algorithm were verified by a typical example, the horizontal comparison analysis on some aspects such as simplicity of the model description, accuracy of the analysis results, rationality of the safety recommendations were given. The results show that the method has an advantage in visual assessment results and the formulation of the cost minimum security measures.

A method to analyze the grasping and pattern force of Electromyography (EMG) simultaneously was proposed, in order to solve the problem that most myoelectric survey focused only on pattern recognition regardless of the combination of grasping pattern and force. First, surface EMG signals were collected through 4 EMG electrodes. Force data was obtained by Force Sensor Resistor (FSR). Then, the Linear Discriminant Analysis (LDA) method was used to realize pattern recognition and Artificial Neural Networks (ANN) was applied to estimate force. 4 types of EMG-force relationship were built in 4 different grasping modes. Once the grasping pattern identified, the program called the corresponding force model to estimate force value and achieved the combination force decoding and pattern recognition. The experimental results illustrate that when pattern and force are analyzed simultaneously, the average classification accuracy is about 77.8%; meanwhile the force prediction accuracy rate is about 90%. The proposed method can be applied to myoelectric control of the prosthetic hand, not only the user's intension of grasping mode can be decoded, but also the desired force can also be estimated. The stable grasping can be assisted by this approach.

A kind of Energy-efficient Scheduling Algorithm under the Constraint of Reliability (ESACR) for the random tasks in multiprocessor system was proposed. It would choose the processor which might consume the least energy when the task's deadline could be guaranteed. For the signal processor, Earliest Deadline First (EDF) strategy was used to schedule the tasks and all the tasks were made execute in the same voltage/frequency. When the new task could not match the deadline, the non-execution voltage/frequency of former tasks would be raised. At the same time, the recovery time was reserved for the executing task in order to promise that the task could be rescheduled when errors happened. The simulation shows that the ESACR can provide the better energy efficiency with the guarantee of system reliability , compared to Highest Voltage Energy-Aware (HVEA), Minimum Energy Minimum Completion time (ME-MC) and Earliest Finish First (EFF).

With the enhancement of computing performance in multiprocessor systems, the management of energy consumption becomes more important, and how to meet real-time constraints and effectively reduce energy consumption in the real-time scheduling is also a key issue. Based on multiprocessor computing systems, concerning randomly arrived task, On-Line Energy-Aware Scheduling Algorithm (OLEAS) was proposed. The algorithm meeting the task deadlines under the premise possibly puts the task scheduler on the least energy consumption producing processor. When a task on all the processors could not meet the deadline requirements, the part of the task between the processors shall be adjusted possibly to meet the deadline requirements. Meanwhile, OLEAS was in a bid to execute the task on a single processor according to the average voltage/frequency, thus reducing the energy consumption. When the new task did not meet the deadline requirements, the former voltage/frequency of unexecuted tasks should be one by one adjusted higher. Compared with the performance of EFF (Earliest Finish First), HVEA (Highest Voltage Energy-Aware), LVEA (Lowest Voltage Energy-Aware), MEG (Minimum Energy Greedy) and ME-MC (Minimum Energy Minimum Completion time) in simulated experiments, the final result shows OLEAS owns obviously comprehensive advantage in the aspect of meeting task deadlines and energy consumption saving.

The coverage problem is a basic problem in the wireless sensor networks, which indicates the Quality of Service (QoS) of sensing by wireless sensor networks. A lot cover blind areas and cover redundancies will be produced, when the nodes are deployed initially in the networks. A hybrid algorithm was proposed to deploy the heterogeneous network nodes reasonably to improve the coverage ratio and reduce the cost of the nodes,which introduced the ε-target constraint method based on Particle Swarm Optimization (PSO) and Fish Swarm Algorithm (FSA). The swarm hybrid algorithm firstly set up the concept of individual center, to quickly search the best solution domain of the individuals' locations, introducing the idea of the cluster behavior and tracing cauda behavior into the PSO, and then used the PSO to find the optimized speed and optimized location of the individuals. The simulation results show that the swarm hybrid algorithm is better than the standard PSO and the standard FSA in pursuing the balance and optimization between the coverage ratio and the cost of the networks.

Concerning the high packet delay and frequent transmission bottleneck in Wireless Sensor Network (WSN) with one-sink node, a multi-sink wireless sensor network model and its Time Division Multiple Access (TDMA) scheduling algorithm based on Genetic Algorithm (GA) were proposed. The algorithm divided the whole sensor network into some small sensor networks according to the number and position of the sink nodes, and adopted GA to optimize the slot allocation result. The simulation results show that, the TDMA time slot allocation method based on genetic algorithm is better in the length of time slot allocation frame, the average of packet delay and the average energy consumption than that of graph coloring algorithm.

n the paper, theorys of Kernel Fisher Discriminant Analysis (KFDA) were researched and analysed. After applying KFDA in feature extracting, the performance of KFDA and that of Linear Fisher Discriminant Analysis (FDA) feature extracting algorithms were compared. Finally, a fast and simple multiclass classification algorithm of KFDA-based was proposed. The algorithm can classify multiclass fast and simply. First of all, multiclass samples were mapped into a high dimension kernel space. In the space, the same class samples were assembled together, the different class samples were perfectly separated. So the multiclass samples can be separate easily. Comparing with One-to-One algorithm and One-to-All algorithm, the experiment results indicate that our algorithm is certainly faster and simpler in classification than other two algorithms.

 Network Performance Testing is an important component in network testing. A distributed test model integrated with centralized control was introduced. The test goal, test method, architecture and working mechanism for the model were discussed thoroughly and the system design and implementation were developed based on them. The final experiment results show that the system is scalable and is suitable for network performance measurement.