Development of bond strength model for FRP plates using back‐propagation algorithm

For the flexural reinforcement of bridge and building structure, synthetic materials whose dynamic properties are superior and those containing the merit of corrosion‐proof are widely used as the substitute for a steel plate. Since FRP plate has improved bond strength owing to the fibers externally adhering to the plate, many researches regarding the bond strength improvement have been substantially performed. To search out such bond strength improvement, previous researchers had ever examined the bond strength of FRP plate through their experiment by setting up many variables. However, since the experiment for a research on the bond strength takes much of expenditure for setting up the equipment and is time‐consuming, also is difficult to be carried out, it is limitedly conducted. The purpose of this study was to develop the most suitable artificial neural network model by application of various neural network models and algorithm to the data of the bond strength experiment conducted by previous researchers. Many variables were used as input layers against bond strength: depth, width, modulus of elasticity, tensile strength of FRP plate and the compressive strength, tensile strength, and width of concrete. The developed artificial neural network model has been applied back‐propagation, and its error was learned to be converged within the range of 0.001. Besides, the process for the over‐fitting problem has been dissolved by Bayesian technique. The verification on the developed model was executed by comparison with the test results of bond strength made by other previous researchers, which was never been utilized to the learning as yet. © 2006 Wiley Periodicals, Inc. J Appl Polym Sci 100: 5119–5127, 2006     

吉比特里所码和卷积码级联译码器设计

针对60-GHz无线个域网,提出了一种吉比特里所码和卷积码级联译码器架构。在推荐级联架构中,里所码和卷积码分别作为外码和内码,通过交织器级联。采用基于Viterbi算法的8路并行卷积译码结构和基于RiBM算法的里所码译码结构,实现了超高速级联译码器。在TSMC 0.13μm CMOS工艺下,该译码器以0.135 nJ/bit和5.19 mm2的能耗资源开销实现了高达2 Gb/s的吞吐率。     

基于能量优化的LEACH路由协议改进

针对LEACH路由算法中簇头选举随机性和簇头与基站直接通信导致能量消耗过快且不平衡的特点,提出新的改进算法,以达到降低能耗目的。在改进算法中,簇头剩余能量高于网络平均能量。根据簇头节点与基站的相对位置划分不同区域,簇头节点发送数据采用多跳方式,避免簇头节点能量消耗过快,达到平衡网络能量消耗的目的。仿真表明,通过改进簇头选举条件和采用多跳路由的方式,即使在数据通信量增加的情况下,依然能够延长网络通信时间。     

基于马尔可夫链的自适应性神经网络训练算法

提出一种基于马尔可夫链的自适应性神经网络训练方法,对传统的S型激励函数进行了改进,建立了自适应性的神经网络分类器。在假设样本中噪声服从于正态分布的情况下建立最大似然估计,通过后验概率建立马尔科夫链对样本进行训练,提高了神经网络训练速度。在轴承故障诊断中的测试结果表明,该算法可以迅速稳定地训练出神经网络,有效提高诊断的分类结果。     

基于浏览器 /服务器的橡胶加工网络测控系统

通过对客户机／服务器模式和浏览器／服务器模式的比较，选择浏览器／服务器模式组建了基于Internt/Intranet的远程橡胶加工网络测控系统，并介绍了系统的开发模式、方法和注意事项。     

Experimental design in soap manufacturing for optimization of fuzzified process capability index

In manufacturing industries, the quality of a product depends on the combined effect of multiple input variables working singly or together and therefore attention has been given on process capability indices to shift from single to multivariate domain. In case of multivariable domain the capability to incorporate uncertainties at the time of decision making becomes necessary. Fuzzy system is introduced to take care of this requirement. In this article the process parameters of soap manufacturing industries have been analyzed. The process capability is determined using Fuzzy Inference System rule editor based on a set of justified if then statements as applicable for the process. The data has been collected in linguistic form to derive its process capability, using a set of justified rules and the effect of each factor has been determined using Design of Experiments (DoE) and analysis of variance technique (ANOVA) for improving the soap quality from perspective of its softness. This article ventures to propose a new methodology by integrating Fuzzy with DoE providing better result followed by DoE and Fuzzy Inference system in isolation.     

Multi-tier service differentiation by coordinated learning-based resource provisioning and admission control

Multiple Internet applications are often hosted in one datacenter, sharing underlying virtualized server resources. It is important to provide differentiated treatment to co-hosted applications and to improve overall system performance by efficient use of shared resources. Challenges arise due to multi-tier service architecture, virtualized server infrastructure, and highly dynamic and bursty workloads. We propose a coordinated admission control and adaptive resource provisioning approach for multi-tier service differentiation and performance improvement in a shared virtualized platform. We develop new model-independent reinforcement learning based techniques for virtual machine (VM) auto-configuration and session based admission control. Adaptive VM auto-configuration provides proportional service differentiation between co-located applications and improves application response time simultaneously. Admission control improves session throughput of the applications and minimizes resource wastage due to aborted sessions. A shared reward actualizes coordination between the two learning modules. For system agility and scalability, we integrate the reinforcement learning approach with cascade neural networks. We have implemented the integrated approach in a virtualized blade server system hosting RUBiS benchmark applications. Experimental results demonstrate that the new approach meets differentiation targets accurately and achieves performance improvement of applications at the same time. It reacts to dynamic and bursty workloads in an agile and scalable manner.     

PRIVACY LEAKAGE IN HEALTH SOCIAL NETWORKS

Members of health social networks may be susceptible to privacy leaks by the amount of information they leave behind. The threat to privacy increases when members of these networks reuse their pseudonyms in other social networks. The risk of re‐identifying users from such networks requires quantitative estimates to evaluate its magnitude. The estimates will enable managers and members of health social communities to take corrective measures. We introduce a new re‐identification attack, the social network attack, that takes advantage of the fact that users reuse their pseudonyms. To demonstrate the attack, we establish links between MedHelp and Twitter (two popular social networks) based on matching pseudonyms. We used Bayesian networks to model the re‐identification risk and used stylometric techniques to identify the strength of the links. On the basis of our model 7‐11. 8% of the MedHelp members in the sample population who reused their pseudonyms in Twitter were re‐identifiable compared with 1% who did not. The risk estimates were measured at the 5% risk threshold. Our model was able to re‐identify users with a sensitivity of 41% and specificity of 96%. The potential for re‐identification increases as more data is accumulated from these profiles, which makes the threat of re‐identification more serious.     

An adaptive neural control scheme for articulatory synthesis of CV sequences

Reproducing the smooth vocal tract trajectories is critical for high quality articulatory speech synthesis. This paper presents an adaptive neural control scheme for such a task using fuzzy logic and neural networks. The control scheme estimates motor commands from trajectories of flesh-points on selected articulators. These motor commands are then used to reproduce the trajectories of the underlying articulators in a 2nd order dynamical system. Initial experiments show that the control scheme is able to manipulate the mass-spring based elastic tract walls in a 2-dimensional articulatory synthesizer and to realize efficient speech motor control. The proposed controller achieves high accuracy during on-line tracking of the lips, the tongue, and the jaw in the simulation of consonant–vowel sequences. It also offers salient features such as generality and adaptability for future developments of control models in articulatory synthesis.     

水泥回转窑的智能控制

文章介绍了PIT Navigator对水泥熟料生产自动化控制的实现,基于神经网络的自学习、自适应控制元件,将相关的过程数据记录下来,随后借助数据关联性进行分析,在预测和自学习过程模型(模型预测控制)中处理这些数据,并计算过程参数的实时预测,使用这些工具,可以实现更稳定的窑况,同时提高产量和降低能耗。