Modified shuffled frog-leaping algorithm to solve TSP was proposed, which presented the concept of adjustment sequence to design the strategy of local searching, and added the mutation operation in the global exchange of information. Experimental results indicate that, compared with genetic algorithm and particle swarm optimization algorithm, the proposed algorithm has more powerful search capability and more strong robustness in solving TSP.

Shuffled frog-leaping algorithm (SFLA) is a new memetic meta-heuristic algorithm with efficient mathematical function and global search capability. Traveling salesman problem (TSP) is a complex combinatorial optimization problem, which is typically used as benchmark for testing the effectiveness as well as the efficiency of a newly proposed optimization algorithm. When applying the shuffled frog-leaping algorithm in TSP, memeplex and submemeplex are built and the evolution of the algorithm, especially the local exploration in submemeplex is carefully adapted based on the prototype SFLA. Experimental results show that the shuffled frog leaping algorithm is efficient for small-scale TSP. Particularly for TSP with 51 cities, the algorithm manages to find six tours which are shorter than the optimal tour provided by TSPLIB. The shortest tour length is 428.87 instead of 429.98 which can be found cited elsewhere.

Clustering with constraints is an active area in machine learning and data mining. In this paper, a semi-supervised kernel-based fuzzy C-means algorithm called PCKFCM is proposed which incorporates both semi-supervised learning technique and the kernel method into traditional fuzzy clustering algorithm. The clustering is achieved by minimizing a carefully designed objective function. A kernel-based fuzzy term defined by the violation of constraints is included. The proposed PCKFCM is compared with other clustering techniques on benchmark and the experimental results convince that effective use of constraints improves the performance of kernel-based clustering. As for the effect of key parameter selection and the non-linear capability, it outperforms a similar semi-supervised fuzzy clustering approach Pairwise Constrained Competitive Agglomeration (PCCA).

This paper presents a framework for parallel implementation of ant colony system-based vector quantization codebook design. The most important structure used is the pheromone trail, which is updated in both local and global sense. The local renewal is implemented in each processor and the global modification is realized at the end of each parallel cycle. The algorithm is carried out on DeepSuper-21C supercomputer, with 256 P4 Xeon 3.06/2.8 GHz Myrinet using MPI. Both the pixel signal-to-noise ratio (PSNR) for the decoded image and the speedup and efficiency for the parallel strategy are used for the evaluation of the proposed algorithm. Experimental results show that the performance of the algorithm improves by 0.1~0.2 dB with the execution time decreased considerably to 2-3 minutes.

Protocol conformance testing is the procedure, which validates protocol following the protocol standard text. Traditional protocol testing methods are introduced and the shortcomings of using them in IPv6 routing protocol testing are analysed. A NTP synchronous method of protocol testing based on virtual machine mechanism is proposed and its implementation is also explained.

提出了一种基于混合蚁群算法的矢量量化码书设计算法.该算法首先通过自适应地调整截取转移概率的参数,加大蚁群算法的搜索最优解的力度;然后以蚁群算法搜索的结果作为初始解,利用改进的LBG算法作进一步的搜索,从而加快算法的收敛速度.实验结果表明,该算法不但大大提高码书性能,而且也缩短了运行时间,解码恢复图像能获得较高的主、客观质量.

Ant colony algorithm is a newly emerged stochastic searching optimization algorithm in recent years. In this paper, vector quantization image coding is modeled as a stochastic optimization problem in an Ant colony system (ACS). An appropriately adapted ant colony algorithm is proposed for vector quantization codebook design. Experimental results show that the ACS-based algorithm can produce a better codebook and the improvement of Pixel signal-to-noise ratio (PSNR) exceeds 1dB compared with the conventional LBG algorithm.

本文提出一种基于人工蚁群优化的矢量量化码书设计新算法.该算法利用人工蚁群系统中蚂蚁通过信息素留存寻找最优路径的机制,结合单只蚂蚁通过拾起、放下物体从而使物体聚堆的行为模式,合理设计放下概率、禁忌列表、信息素更新方式以及相应的参数.与基于进化模拟退火和随机竞争学习的码书设计算法相比,本文提出的算法能获得性能较好的码书,其峰值信噪比比传统的LBG算法提高超过2dB.

Support vector machine ( SVM) , a novel machine learning method, has become a hotspot because of its excellent learning performance. This paper introduces the fundamental theory underlying the SVM, its current state-of-the-art as well as its applications in pattern recognition.

Ant colony algorithm is a newly emerged stochastic searching optimization algorithm in recent years. In this paper, an appropriately adapted ant colony system embedded with a simple improved LBG algorithm is proposed for vector quantization codebook design. The emphasis is put on the design of the probability transfer function and the tabu list in the ant colony algorithm, the utilization of the next nearest neighborhood in the LBG algorithm, as well as the update of the pheromone in both local and global sense. Experimental results show that the new algorithm outperforms other well-known codebook design algorithms, and particularly, the improvement of PSNR exceeds 2 dB compared with the conventional LBG algorithm.

模拟退火是解决全局优化问题的随机搜索技术,它在工程领域有着广泛应用.将模拟退火技术与LBG算法有机结合,通过对LBG算法中的空胞腔码书进行适当处理,并设置适当参数使LBG与模拟退火交替进行,提出了一种快速模拟退火矢量量化图像编码算法,以降低计算量和进一步提高码书性能.实验结果表明,算法具有对初始码书选取依赖性小、不容易陷入局部极小、收敛速度快等优点.与随机竞争学习矢量量化及进化模拟退火矢量量化算法相比,峰值信噪比改善超过0.6dB.

本文提出一种基于自适应蚁群优化的矢量量化码书设计算法.该算法利用人工蚁群系统中蚂蚁通过信息量留存寻找最优路径的机制,合理设计转移概率、禁忌列表、信息量更新方式及自适应地调整截取转移概率的参数.实验结果表明,该算法能获得质量较好的码书和主观效果较好的译码图像.

提出了一种分段式双通道高速数据采集系统的设计方案,对其中高速A/D、高速存储、智能控制以及接口译码等模块进行了介绍.该设计方案解决了高速实时信号与接口总线之间的速度兼容问题,单双踪采样频率可调,具有较好的工业应用价值.

本文提出一种用于图像压缩编码的模糊增强学习码书设计算法.该算法是在模糊竞争学习矢量量化的基础上引入增强学习,并用输入训练模式的监督信号与类别模式之间的隶属度控制增强信号.实验结果表明,该算法对初始码本依赖性小,与模糊竞争学习矢量量化和微分竞争学习算法相比,收敛速度更快,性能更好.

LBG算法是矢量量化码书设计的经典算法.针对其空胞腔问题提出一种改进的LBG算法,并以熵序列收敛作为新的算法停止判据.实验表明,该算法具有收敛速度快、码书性能佳等优点,该算法的PSNR比传统的LBG算法提高2.74dB.