Item-based collaborative filtering learns user preferences from the user's historical interaction items and recommends similar new items based on the user's preferences. The existing collaborative filtering methods assume that a set of historical items that user has interacted with have the same impact on user, and all historical interaction items are considered to have the same contribution to the prediction of target item, which limits the accuracy of these recommendation methods. In order to solve the problems, a new collaborative filtering recommendation algorithm based on dual most relevant attention network was proposed, which contained two attention network layers. Firstly, the item-level attention network was used to assign different weights to different historical items in order to capture the most relevant items in the user historical interaction items. Then, the item-interaction-level attention network was used to perceive the correlation degrees of the interactions between the different historical items and the target item. Finally, the fine-grained preferences of users on the historical interaction items and the target item were simultaneously captured through the two attention network layers, so as to make the better recommendations for the next step. The experiments were conducted on two real datasets of MovieLens and Pinterest. Experimental results show that, the proposed algorithm improves the recommendation hit rate by 2.3 percentage points and 1.5 percentage points respectively compared with the benchmark model Deep Item-based Collaborative Filtering (DeepICF) algorithm, which verifies the effectiveness of the proposed algorithm on making personalized recommendations for users.

For the instantaneity of video background extraction in embedded visual systems, a rapid algorithm based on the Nearest Neighbor Pixel Gradient (N2PG) stability was proposed. Firstly, background initialization was conducted with one single frame, and the N2PG matrix of this frame was calculated. Secondly, several frames of the subsequent video were operated as reference image for background update, and the N2PG matrix of those frames were calculated in the same way. Then, it was judged rapidly that each pixel of the background model was static or nonstatic by calculating the subtraction between the N2PG matrix of the background image and the N2PG matrix of the reference image, referencing the threshold value of gradient stability estimated in real-time. Finally, the current background was obtained by updating or replacing each background pixel. In the simulation tests, compared with Kalman filtering method and Gaussian mixture model, only 10 to 50 frames were needed to get background in the algorithm based on N2PG, and the average speed of processing frames was increased by 36% and 75% respectively; compared to the modified Visual Background Extractor (ViBe) algorithm, the speed of updating background by using N2PG algorithm was doubled with the same required number of the video frames and the similar background quality. Experimental results show that the proposed algorithm has the advantages of strong adaptability, high speed and small storage, and the background extraction accuracy is also above 90%, it can satisfy the application of real-time embedded visual systems in natural environment.

Focused on low efficiency and poor accuracy of the traditional TF-IDF (Term Frequency-Inverse Document Frequency) algorithm in keyword extraction, a text keyword extraction method based on word frequency statistics was proposed. Firstly, the formula of the same frequency words in text was deduced according to Zipf's law; secondly, the proportion of each frequency word in text was determined in accordance with the formula of the same frequency words, most of which were low-frequency words; finally, the TF-IDF algorithm based on word frequency statistics was proposed by applying the word frequency statistics law to keyword extraction. Simulation experiments were conducted on Chinese and English text experiment data sets. The average relative error of the formula of the same frequency words was not more than 0.05; the maximum absolute error of the proportion of each frequency word in text was 0.04. Compared with the traditional TF-IDF algorithm, the average precision, the average recall and the average F1-measure of the TF-IDF algorithm based on word frequency statistics were increased respectively, while the average runtime was decreased. The simulation results show that in text keyword extraction, the TF-IDF algorithm based on word frequency statistics is superior to the traditional TF-IDF algorithm in precision, recall and F1-measure, and it can effectively reduce the runtime in keyword extraction.

To solve the virtual machine deployment problem in Infrastructure as a Service (IaaS) of cloud computing, a virtual machine deployment strategy based on Particle Swarm Optimization (PSO) algorithm was proposed. Since the PSO algorithm has weaknesses of having a slow convergence speed and falling into local optimum easily when dealing with large-scale and complex problems like virtual machine deployment, firstly, a Multiple-population Gaussian Learning Particle Swarm Optimization (MGL-PSO) algorithm was proposed, with using the model of multiple population evolution to accelerate the algorithm convergence, as well as adding Gaussian learning strategy to avoid local optimum. Then according to the deployment model, with using Round Robin (RR) algorithm to initialize the MGL-PSO, a virtual machine deployment strategy aiming to load balancing was proposed. Through the simulation experiment in CloudSim, it validates that MGL-PSO has a higher convergence speed and load imbalance degree is reduced by 13% compared with PSO algorithm. In the two experimental situations, compared with the Opportunistic Load Balancing (OLB) algorithm, the load imbalance degrees of the proposed algorithm decrease by 25% and 15% respectively, and compared with the Greedy Algorithm (GA) the load imbalance degrees decrease by 19% and 7% respectively.

Kinship network is made up of marriage and parent-child relationship. Searching a special relationship on a huge kinship network is very difficult. This paper proposed two algorithms by extending breadth-first-search method: radius-search and directional-search. The data of the kinship network was extracted from Hebei province population database, which included about 4150000 vertexes, and about 10880000 edges. The network stored bilateral relationships, which declined some unnecessary back tracking. The experimental results show that the kinship retrospect algorithm can exactly locate some specific persons by the network. At the same time the algorithms can achieve high performance and guarantee high flexibility.

In view of the problems that posture recognition based on vision requires a lot on environment and has low anti-interference capacity, a posture recognition method based on predefined bone was proposed. The algorithm detected human body by combining Kinect multi-scale depth and gradient information. And it recognized every part of body based on random forest which used positive and negative samples, built the body posture vector. According to the posture category, optimal separating hyperplane and kernel function were built by using improved support vector machine to classify postures. The experimental results show that the recognition rate of this scheme is 94.3%, and it has good real-time performance, strong anti-interference, good robustness, etc.

To keep the trade-off of time complexity and accuracy of community detection in complex networks, Community Detection Algorithm based on Clustering Granulation (CGCDA) was proposed in this paper. The granules were regarded as communities so that the granulation for a network was actually the community partition of a network. Firstly, each node in the network was regarded as an original granule, then the granule set was obtained by the initial granulation operation. Secondly, granules in this set which satisfied granulation coefficient were merged by clustering granulation operation. The process was finished until granulation coefficient was not satisfied in the granule set. Finally, overlapping nodes among some granules were regard as isolated points, and they were merged into corresponding granules based on neighbor nodes voting algorithm to realize the community partition of complex network. Newman Fast Algorithm (NFA), Label Propagation Algorithm (LPA), CGCDA were realized on four benchmark datasets. The experimental results show that CGCDA can achieve modularity 7.6% higher than LPA and time 96% less than NFA averagely. CGCDA has lower time complexity and higher modularity. The balance between time complexity and accuracy of community detection is achieved. Compared with NFA and LPA, the whole performance of CGCDA is better.

In order to solve the problem that high dimensional optimization problem is hard to optimize and time-consuming, a Differential Evolution for High Dimensional optimization problem (DEHD) was proposed. By introducing coevolutionary to differential evolution, a new coevolution scheme was adopted, which consisted of state observer and random grouping strategy. Specifically, state observer activated random grouping strategy according to the feedback of search status while random grouping strategy decomposed high dimensional problem into several smaller ones and then evolved them separately. The scheme enhanced the algorithm's search speed and effectiveness. The experimental results show that the proposed algorithm is effective and efficient while solving various high dimensional optimization problems. In particular, its search speed improves significantly. Therefore, the proposed algorithm is competitive on separable high dimensional problems.

Considering the problems caused by the traditional association rules visualization approaches, including being unable to display the frequent pattern and relationships of items, unitary express, especially being not conducive to represent multi-schema association rules, a new visualizing algorithm for multi-valued association rules mining was proposed. It introduced the redefinition and classification of multi-valued attribute data by using conceptual lattice and presented the multi-valued attribute items of frequent itemset and association rules with concept lattice structure. This methodology was able to achieve frequent itemset visualization and multi-schema visualization of association rules, including the type of one to one, one to many, many to one, many to many and concept hierarchy. At last, the advantages of these new methods were illustrated with the help of experimental data obtained from demographic data of a province, and the source data visualization, frequent pattern and association relation visual representation of the demographic data were also achieved. The practical application analysis and experimental results prove that the schema has more excellent visual effects for frequent itemset display and authentical multi-schema association rules visualization.

For the poor readability and understandability with the existing display form for genealogical data, this paper presented visualization for genealogical data with metagraph. In the metagraph representation of genealogy, the generating set comprised of all persons in the family; each edge represented only "parents-child" relationship. An edge in the metagraph representation of genealogy was a pair consisting of an invertex and an outvertex, the invertex consisted of two nodes of the marital relationship, and the outvertex represented a single child node set. The experimental results show that the number of the edges in the metagraph form is almost half of common form in the case of the same data, and the visualizing effect is significantly improved. At the same time, the proposed methodology has a guiding role in the mathematical modeling of genealogy, the research of genealogy visualization and the improvement of genealogical information system.

Due to the lack of information of Automatic Identification System (AIS) equipment, the location of a vessel cannot be accurately judged by intelligent supporting command system based on AIS. It is difficult to accurately issue the traffic signal from it. Meanwhile, due to the narrow and winding features in controlled waterway, it is difficult for traditional Kalman filter to accurately predict track of moving vessel. In this situation, the real-time estimation of system noise in Kalman filter algorithm was proposed to increase the accuracy of track prediction of moving vessel. Simulation analysis was carried out on the tracking effect of the traditional Kalman filter and improved Kalman filter. The results indicate that the proposed algorithm can solve the lack in information of AIS equipment, and accurately predict the location of a vessel. The accuracy and the reliability of intelligence supporting command system can be ensured in controlled waterway.

Mobile ad-hoc networks(MANETs) represent complex distributed communication systems comprised of wireless mobile nodes.Based on the discussion of intrusion detection problem in MANET,a novel anomaly intrusion detection method based on machine learning algorithm was proposed to detect attacks on MANET.The method captured the normal traffic’s inter-feature correlation pattern which could be used as normal profiles to detect anomalies caused by attacks.The method was implemented on Ad-hoc On-Demand Distance Vector(AODV) protocol and evaluated in QualNet,a leading network simulation software.