Interactive genetic algorithms with large population and semi-supervised learning

Interactive genetic algorithms are effective methods of solving optimization problems with implicit (qualitative) criteria by incorporating a user's intelligent evaluation into traditional evolution mechanisms. The heavy evaluation burden of the user, however, is crucial and limits their applications in complex optimization problems. We focus on reducing the evaluation burden by presenting a semi-supervised learning assisted interactive genetic algorithm with large population. In this algorithm, a population with many individuals is adopted to efficiently explore the search space. A surrogate model built with an improved semi-supervised learning method is employed to evaluate a part of individuals instead of the user to alleviate his/her burden in evaluation. Incorporated with the principles of the improved semi-supervised learning, the opportunities of applying and updating the surrogate model are determined by its confidence degree in estimation, and the informative individuals reevaluated by the user are selected according to the concept of learning from mistakes. We quantitatively analyze the performance of the proposed algorithm and apply it to the design of sunglasses lenses, a representative optimization problem with one qualitative criterion. The empirical results demonstrate the strength of our algorithm in searching for satisfactory solutions and easing the evaluation burden of the user.     

A fuzzy cerebellar model articulation controller based visual servo system for robot

This paper presents a novel online learning visual servo controller integrating the FCMAC with proportion controller for the control of position of manipulator end-effector. Since the FCMAC has good learning capability and fast learning speed, and can save much computer memory space by fuzzy processing of input space division and memory unit activation, it is used to develop an adaptive control law by learning the relationship between the image feature errors and manipulator input, and the aim of online learning of the FCMAC is to minimize the output of proportion controller. Furthermore, the FCMAC has no need for models of robot manipulator and image feature extraction, so that the capability of proposed controller for tasks under uncertain environment can be improved. Finally, the proposed controller is proved to be effective by the experiment, and compared with BP neural network.     

Patterned paper and alternative materials as substrates for low-cost microfluidic diagnostics

In recent years a strong need has been realised for the creation of low-cost diagnostics for use in impoverished regions of the world. The use of paper has been championed for this purpose by many research groups globally over the past 5?years, leading to the formation of a large body of knowledge. This work reviews and summarises the many techniques developed to date for the patterning of paper substrates to create channels for the flow of liquids. The work also explores methods for increasing the functionality of paper-based microfluidics, the detection mechanisms employed so far and some of the interesting applications addressed. The review will also investigate the recent use of some alternative materials—both as primary substrates and in hybrids—which will become progressively more important in the future.     

Improved stability conditions for systems with interval time-varying delay

The paper is concerned with the stability of linear systems with interval time-varying delay. Through constructing a new augmented Lyapunov-Krasovskii functional (LKF) which contains some quadruple-integral terms and estimating the time derivative of the LKF less conservatively, new stability criteria are derived without introducing any free matrices. Moreover, by proving the positive definiteness of the LKF with some integral inequalities, the constraints on some functional parameters are relaxed and the conservatism of the obtained results are further reduced. Numerical examples are also given to demonstrate the effectiveness and reduced conservatism of the obtained results.     

基于以太网的MVB总线分析仪的设计和实现

简要介绍多功能车辆总线(MVB)的标准以及以太网在工业中应用的优势和前景,通过分析MVB总线信号特点和以太网芯片功能,提出了基于以太网的MVB总线分析仪的硬件设计,网络芯片的驱动设计与实现方案.分析仪的功能模块包括接收模块、发送模块、出错检测管理模块、CPU、存储模块和以太网通信模块等.通过在符合IEC-61375标准的MVB总线测试平台下进行调试,分析仪的各项功能达到了设计目标,可以实际应用于采用MVB总线的车载设备网络或其他工业网络的总线数据分析和网络性能测试.     

高速动车组驾驶室设计中的人机界面分析

在高速动车组驾驶室的人机关系分析与设计中,驾驶室的空间尺度关系、视野、操纵设备的分布和人机环境等因素,将直接影响列车行驶的安全、效率、舒适和健康。应用人机关系分析与研究,合理地配置驾驶室室内环境以及操作和显示设备,将有效地提高司机操作的安全性、便利性和作业效率,从而给司机提供一个方便舒适的操作空间,减少体力、心理疲劳,降低人为误操作带来的安全隐患,提高系统运行的可靠性,使人-机匹配达到最优,以保证车辆行驶的安全。     

应用破圈法求图的最优树的一种新算法

本文依据破圈法的原理提出了求图的最优树的一种新算法,并给出了具体的实现步骤。     

新型的数字音频系统—数字盒式磁带（DCC）原理

数字盒式磁带录音机,简称DCC,是一种将现有的盒式磁带与数字声频相结合的产物。它采用了新的有效的精确自适应子带编码技术,简称PASC,使重放的声音达到CD的音质。PASC依据数字声频中两个新的原理:与人耳的听觉特性相适应原理和有效的自适原应理。DCC系统可以与模拟音乐盒带兼容,现有的盒带可以在DCC放音设备上重放。     

基于神经网络的聚类方法研究

针对常用聚类方法不能有效处理噪声数据的问题,本文结合神经网络具有自适应性的特点,提出基于神经网络的聚类(NN_Cluster)模型,并设计了基于自适应共振理论的神经网络聚类模型(ARTNN_Cluster)和基于自组织特征映射的神经网络聚类模型(SOMNN_Cluster)。标准数据集上的实验结果表明,与传统的K_means聚类方法相比,本文提出的基于神经网络的聚类模型有效地克服了传统方法的噪声问题,得到了较好的聚类效果。