Nondominated Neighbor Immune Algorithm (NNIA) is proposed for multiobjective optimization by using a novel nondominated neighbor-based selection technique, an immune inspired operator, two heuristic search operators, and elitism. The unique selection technique of NNIA only selects minority isolated nondominated individuals in the population. The selected individuals are then cloned proportionally to their crowding-distance values before heuristic search. By using the nondominated neighbor-based selection and proportional cloning, NNIA pays more attention to the less-crowded regions of the current trade-off front. We compare NNIA with NSGA-II, SPEA2, PESA-II, and MISA in solving five DTLZ problems, five ZDT problems and three low-dimensional problems. The statistical analysis based on three performance metrics including the Coverage of two sets, the Convergence metric, and the Spacing, show that the unique selection method is effective, and NNIA is an effective algorithm for solving multiobjective optimization problems. The empirical study on NNIA's scalability with respect to the number of objectives shows that the new algorithm scales well along the number of objectives.

This paper proposes a self-organizing genetic algorithm (SOGA) with good global search properties and a high convergence speed. First, we introduce a new dominant selection operator that enhances the action of the dominant individuals, along with a cyclical mutation operator that periodically varies the mutation probability in accordance with evolution generation found in biological evolutionary processes. Next, the SOGA is constructed using the two operators mentioned above. The results of a nonlinear regression analysis demonstrate that the self-organizing genetic algorithm is able to avoid premature convergence with a higher convergence speed, and also indicate that it possesses self-organization properties. Finally, the new algorithm is used to optimize Proportional Integral Derivative (PID) controller parameters. Our simulation results indicate that a suitable set of PID parameters can be calculated by the proposed SOGA.

为了克服模型降阶问题参数多且易陷入局部最优值的缺点，借鉴社会网络中的小世界原理，提出了基于十进制编码策略的局部短连接和随机长连接搜索算子，进而构造了一种十进制编码的小世界优化算法（DSWA）。对稳定和非稳定线性系统的模型降阶优化进行了试验，验证了DSWA算法求解的可行性和有效性。区间固定与区间动态扩展策略的对比结果表明，采用区间动态扩展策略要优于区间固定策略，且DSWA算法能在一定程度上克服陷入局部最优值的问题。此外，通过对比所得优化模型与原始模型之间的误差值、时频域响应曲线等，表明采用DSWA算法得到的降阶模型具有较优的逼近性能。

在分析谱聚类实现思路和已有算法基础上，对规范切判据，最小最大切判据和自动确定聚类数目的谱聚类典型算法进行了研究和应用，通过理论分析算法各自实现机理的联系与区别，讨论它们各自的聚类特点，并利用UCI （University of California。Irvine）机器学习数据集试验对比了三种算法的聚类效果。发现谱聚类算法实现数据聚类的有效性，以及参数及相似度度量对算法性能有很大影响，在此基础上提出了算法用于解决可建模为模式识别的工程问题的可行思路，为工程实践提供了借鉴。

模块性（modularity）是度量网络社区结构（community structure）的主要参数。探讨了Watts和Strogatz的小世界网络（简称W2S模型）以及Barabàsi等的B2A无标度网络（简称B2A模型）两类典型复杂网络模块性特点。结果显示，网络模块性受到网络连接稀疏的影响，W2S模型具有显著的社区结构，而B2A模型的社区结构特征不明显。因此，应用中应该分别讨论网络的小世界现象和无标度特性。社区结构不同于小世界现象和无标度特性，并可以利用模块性区别网络类型，因此网络复杂性指标应该包括社区结构。现实社会网络可能同时具有小世界现象、无标度特性和清晰的社区结构，而目前的复杂网络模型只揭示了其部分特征，为了更全面地认识社会复杂性，需要建立新的复杂网络模型。