Knowledge discovery in corporate events by neural network rule extraction

Over the last two decades, artificial neural networks (ANN) have been applied to solve a variety of problems such as pattern classification and function approximation. In many applications, it is desirable to extract knowledge from trained neural networks for the users to gain a better understanding of the network’s solution. In this paper, we use a neural network rule extraction method to extract knowledge from 2222 dividend initiation and resumption events. We find that the positive relation between the short-term price reaction and the ratio of annualized dividend amount to stock price is primarily limited to 96 small firms with high dividend ratios. The results suggest that the degree of short-term stock price underreaction to dividend events may not be as dramatic as previously believed. The results also show that the relations between the stock price response and firm size is different across different types of firms. Thus, drawing the conclusions from the whole dividend event data may leave some important information unexamined. This study shows that neural network rule extraction method can reveal more knowledge from the data.     

Collapse-free thermal bonding technique for large area microchambers in plastic lab-on-a-chip applications

Bonding is an essential step to form microchannels or microchambers in lab-on-a-chip applications. In this paper, we present a novel plastic thermal bonding technique to seal and form large area microchambers (planar characteristic width and length on the order of 1 mm and characteristic thickness on the order of 10–100 μm) without collapse by introducing a holed pressure equalizing plate (HPEP) that includes holes of the same size and shape as the microchambers. To demonstrate the proposed technique, two types of large area microchambers [(1) 20 × 10 mm and 40 μm thick and (2) 12 × 2.5 mm and 120 μm thick] with microchannels were designed and replicated on plastic substrates by means of hot embossing and injection molding processes with prepared two nickel mold inserts. The replicated large area microchambers as well as the microchannels in the plastic lab-on-a-chip were successfully sealed (i.e., no leakage) and formed without any collapse by the proposed thermal bonding technique with the help of the HPEP.     

Design and fabrication of an electrochemically actuated microvalve

A microfluidic valve based on electrochemical (ECM) actuation was designed, fabricated using UV-LIGA microfabrication technologies. The valve consists of an ECM actuator, polydimethylsiloxane (PDMS) membrane and a micro chamber. The flow channels and chamber are made of cured SU-8 polymer. The hydrogen gas bubbles were generated in the valve microchamber with Pt black electrodes (coated with platinum nanoparticles) and filled with 1 M of NaCl solution. The nano particles coated on the working electrode helps to boost the surface-to-volume ratio of the electrode for faster reversible electrolysis and faster valve operation. To test the functionality of the microvalve, a simple micropump based on ECM principle was also integrated in the system to deliver a microscopic volume of fluid through the valve. The experimental results have showed that an approximately 300 μm deflection of valve membrane was achieved by applying a bias voltage of ?1.5 V across the electrodes. The pressure in the valve chamber was estimated to be about 200 KPa. Experimental results proved that the valve can be easily operated by controlling the electrical signals supplied to the ECM actuators.     

Ad Hoc网络中一种基于Tabu搜索的低耗单播路由算法

Ad Hoc网络中,节点能量影响网络的稳定性和整个网络的生命周期.因此我们需要在提供可靠QoS服务的同时尽量降低能耗,延长整个网络的生命周期,而保证QoS服务前提下求解低能耗单播路由的算法是一个NP完全问题.针对这个问题,提出一个基于Tabu搜索的低耗单播路由算法,该算法选择延迟作为QoS参数,利用Tabu搜索的集中性与广泛性并存的优点,在保证QoS服务质量的同时尽量减少网络节点平均能量消耗,以提高整个网络的生命周期.仿真结果表明:该算法在延长网络生命周期方面具有良好效果.     

基于Struts和Hibernate的小型门店MIS的设计与实现

通过对一般小型门店业务流程的调研和现有的一些基于struts和Hibemate技术上的进销存系统上的分析,设计和实现了一个小型门店销售系统.在整体架构方面增加了多层设计模式,在数据库方面运用了一个主子表的方法.设计后,该系统效率提高、易于维护、便于扩展,大大减少了数据冗余,用户界面也更加友好.     

一种新的基于遗传操作的改进型遗传算法

交叉与变异是遗传算法的重要操作,提出了一种新的基于遗传操作的改进型遗传算法.采用最优保留和改进的轮盘赌选择方法,通过基因交叉概率控制交叉,根据高斯分布改进了交叉算子和变异算子,保证了算法的全局搜索能力、局部搜索能力及收敛速度.通过标准函数的数值实验,验证了新算法的有效性.     

地空大容量传输自适应均衡技术

地空信道远距离、低仰角、高速信息传输时,信道引入的多径将不可避免,多径引起的符号间的干扰和衰落将变得十分严重,传统的自适应均衡技术多基于解调器正常工作,动态适应性较差,均衡效果有限。本文详细介绍了采用均衡器与解调器联合设计原理,并结合多谱勒校正技术,能够满足在地空低莱斯因子信道下,解调器一均衡器校正多谱勒频偏的同时均衡动态多径,达到平稳传输效果。     

基于AHP方法构建教学评价指标的研究

该文阐述了数据挖掘教学评价系统中建立教学评价指标体系的理论,提出了建立的原则及其应该发挥的作用。应用层次分析法(AHP)对教师教学评价体系模型进行科学的分析,最终选出评估指标。     

基于EMS系统的低频减载实时计算的实现

目前电网调度生产中尚不能实现低频减载的在线实时监测,调度无法及时掌握低频减载控制负荷,给电网的安全稳定运行造成一定的安全隐患。为解决该问题,在EMS系统中开发了基于设备的动态拓扑功能,利用广度优先算法将末端设备的负荷动态拓扑到需统计的单位母线上,从而实时显示每条母线8轮低频减载值,再利用E语言文件将计算好的值传给上一级单位进行更高电压等级母线的实时统计。     

六子棋智能博弈系统的研究与实现

六子棋作为一个新兴的游戏,已在棋类计算机智能博弈领域占有重要的位置,其为保证竞赛公平性而采取的一步两子的规则对计算机博弈的效率是很大的考验。为此,在实现六子棋博弈系统状态表示、搜索策略和评估函数几大核心框架的基础上．提出“路”的概念,简化评估函数类型,有效提高博弈性能。