微粒群优化算法是一种新兴的群智能进化算法，该算法具有执行速度快、受问题维数变化影响小等优点。支持向量机是基于统计学习的方法，利用结构风险最小化原理，具有很好的泛化能力。为了充分发挥二者的优势，提出了基于离散微粒群和支持向量机的特征子集选择方法。首先随机产生若干特征子集，然后采用5阶交叉验证的方法，用离散微粒群优化算法对特征进行优化选择，选出最佳适应度的子集对支持向量机进行训练。使用这种方法，对UCI机器学习Benchmark库中sonar和led数据集进行实验，取得了比较满意的结果。

本文以美国军方在武器系统研发、生产和维护过程中推行的设计-制造-维护纵向集成测试策略为参考，针对我国导弹武器系统的测试和诊断技术的应用和发展现状，论述了适合我国导弹测试系统开发的集成测试策略。

On the basis of analyzing IEEE1149.1 and IEEE1149.5 standards, the current situation that chips supporting the BST and chips not supporting it co-exist in most mixed circuit systems is studied. A novel method is presented in this paper, in which Embedded Test Bus Controller (ETBC) is adopted to achieve the Boundary Scan Test (BST) of the mixed circuit system.

In this paper, the probabilistic neural network (PNN) is applied to accomplish the task of fault characteristic classification in test and fault diagnosis for missile system. In this way, artificial intelligence (AI) is introduced into the application research of electronic system test and diagnosis. Further more, a novel reduction method based on the stretchable constraint clustering algorithm is adopted in the process of training pattern reduction in the PNN. The proper and effective reduction can make the diagnostic PNN more time efficient and easier to understand.

Recently particle swarm optimization (PSO) has been achieved more attention, but the basic PSO is easy plunged into local optima. This paper proposed an improvement to basic PSO, named MPSO, in which mutation operator was added as genetic algorithm. The mutation operator can mutate the population, and then help the particles escape from local optima. Experiments on five benchmark functions showed the PSO with mutation operator not only enlarged particles' explore range, but also boosted the algorithm's convergence.