The task of image captioning is an important branch of image understanding. It requires not only the ability to correctly recognize the image content, but also the ability to generate grammatically and semantically correct sentences. The traditional encoder-decoder based model cannot make full use of image features and has only a single decoding method. In response to these problems, a multi-layer encoding and decoding model for image captioning based on attention mechanism named MLED was proposed. Firstly, Faster Region-based Convolutional Neural Network (Faster R-CNN) was used to extract image features. Then, Transformer was employed to extract three kinds of high-level features of the image. At the same time, the pyramid fusion method was used to effectively fuse the features. Finally, three Long Short-Term Memory (LSTM) Networks were constructed to decode the features of different layers hierarchically. In the decoding part, the soft attention mechanism was used to enable the model to pay attention to the important information required at the current step. The proposed model was tested on MSCOCO dataset and evaluated by BLEU, METEOR, ROUGE-L and CIDEr. Experimental results show that on the indicators BLEU-4, METEOR and CIDEr, the model is increased by 2.5 percentage points, 2.6 percentage points and 8.8 percentage points compared to the Recall what you see (Recall) model respectively, and is improved by 1.2 percentage points, 0.5 percentage points and 3.5 percentage points compared to the Hierarchical Attention-based Fusion (HAF) model respectively. The visualization of the generated description sentences show that the sentence generated by the proposed model can accurately reflect the image content.

Concerning the issue that the selection pressure of Pareto control based many-objective evolutionary algorithm is reduced when solving the problem of high-dimension and the diversity of the population is reduced of many-objective evolutionary algorithm based on decomposition when improving convergence and distribution, a decomposition based many-objective evolutionary algorithm based on minimum distance and aggregation strategy was proposed. Firstly, the angle decomposition based technique was used to decompose the target space into a specified number of subspaces in order to improve the diversity of population. Then, the method of cross neighborhood based on aggregation was added in the process of generating new solution, making the generated new solution closer to the parent solution. Finally, the convergence and distribution were improved by selecting solutions in each subspace based on minimum distance and aggregation strategy in two stages. In order to verify the feasibility of the algorithm, benchmark functions ZDT and DTLZ were used to conduct simulation experiments. The results show that the performance of the proposed algorithm is superior to those of the classical MOEA/D (Multi-Objective Evolutionary Algorithm based on Decomposition), MOEA/D-DE (MOEA/D based on Differential Evolution), NSGA-Ⅲ (Nondominated Sorting Genetic Algorithms Ⅲ) and GrEA (Grid-based Evolutionary Algorithm). It can be seen that the proposed algorithm can effectively balance convergence and diversity while improving diversity.

Most of traditional text classification algorithms are based on vector space model and hierarchical classification tree model is used for statistical analysis. The model mostly doesn't combine with the semantic information of characteristic items. Therefore it may produce a large number of frequent semantic modes and increase the paths of classification. Combining with the good distinguishment characteristic of essential Emerging Pattern (eEP) in the classification and the model of rough set based on minimum expected risk decision, a Text Semantic Classification algorithm with Threshold Optimization (TSCTO) was presented. Firstly, after obtaining the document feature frequency distribution table, the minimum threshold value was calculated by the rough set combined with distribution density matrix. Then the high frequency words of the semantic intra-class document frequency are obtained by combining semantic analysis and inverse document frequency method. In order to get the simplest model, the eEP pattern was used for classification. Finally, using similarity formula and HowNet semantic relevance degree, the score of text similarity was calculated, and some thresholds were optimized by the three-way decision theory. The experimental results show that the TSCTO algorithm has a certain improvement in the performance of text classification.

Focusing on the defects, such as slow convergence and premature phenomenon, in solving constrained optimization problems by the traditional Differential Evolution (DE) algorithm, a novel DE based on Simplex-Orthogonal experimental design (SO-DE) algorithm was proposed. The algorithm designed a new hybrid crossover operator that combined simplex crossover and orthogonal experimental design to improve the search ability of DE algorithm, and the improved comparison criteria was used to compare and select the individuals of population. Several parent individuals were used to produce multiple offspring individuals by simplex crossover in the new hybrid crossover operator, then the multiple excellent individuals, which were selected from two set by orthogonal experimental design, were copied in the next generation. Different treatment schemes were used for different stages of population in the improved comparison criterion, which aimed to effectively weigh the relationship between the value of the objective function and the degree of constraint violation, thus better individuals were chosen into the next generation. Simulation experiments were conducted on 13 standard test functions and 2 engineering design problems. The SO-DE algorithm is much better than HEAA (Hybrid Evolutionary Algorithm and Adaptive constraint-handling technique) and COEA/ODE (a novel Constrained Optimization Evolutionary Algorithm based on Orthogonal Experimental Design) in terms of the accuracy and standard variance of final solution. The experimental results demonstrate that the SO-DE algorithm has better accuracy and stability.

To guarantee QoS of real-time multimedia traffic networks in wireless network, designed and implemented a QoS differentiation IPv6 test-bed. Test-bed can implement and test many QoS scheduling scheme and its key component is IPv6 Router in which QoS differentiation scheduling runs. Scheduling is implemented by Loadable Kernel Module of Linux which captures packets via hook of NetFilter and forwards them according priorities. Given higher priority, signaling and real-time traffic will get better QoS. Test-bed works well as an open development environment for QoS research.