基于最小二乘支持向量机的机器视觉识别方法

为了解决传统的机器视觉识别技术识别精度低的难题,提出基于粒子群优化最小二乘支持向量机的机器视觉识别方法.首先,对机器视觉采集的图像进行特征提取;然后,利用特征数据建立基于粒子群优化最小二乘支持向量机的识别模型;最后,以红枣缺陷识别作为应用案例以证明该方法的有效性及优越性.分别采用人工神经网络、支持向量机与该方法进行对比...     

基于最大似然线性回归矩阵的说话人识别算法研究

研究了将自适应领域的最大似然线性回归(Maximum likelihood linear regression, MLLR)变换矩阵作为特征进行文本无关的说话人识别算法. 本文引入了基于统一背景模型的MLLRSV-SVM说话人识别算法, 并在此基础上进行高层音素聚类以进一步提高识别性能. 在采用多种信道补偿技术后, 在NIST SRE 2006年1训练语段-1测试语段同信道和跨信道数据库上, 基于MLLR特征的系统与其他最好的系统性能接近并有很强的互补性, 经过简单线性融合可以极大提高识别性能.     

工业重载液压力伺服系统的抗扰动控制

由于重载荒磨机负载惯性大阻尼小, 施力系统开环传递函数含有一对纯虚零点, 而且负载特性变化会明显影响开环频带宽度. 同时, 砂轮高速旋转会产生高频率大幅度的偏心力干扰, 由于系统频响较低, 单纯的输出反馈方式无法抑制干扰. 本文通过采用非线性跟踪微分器提取状态观测量并引入非线性前馈系数, 消除了纯虚零点, 消除了负载特性变化对开环频宽的影响, 显著地抑制了外部位移干扰和偏心力干扰, 从而使得产品质量大幅度提高.     

Comparison of different classifier algorithms for diagnosing macular and optic nerve diseases

Abstract: The aim of this research was to compare classifier algorithms including the C4.5 decision tree classifier, the least squares support vector machine (LS-SVM) and the artificial immune recognition system (AIRS) for diagnosing macular and optic nerve diseases from pattern electroretinography signals. The pattern electroretinography signals were obtained by electrophysiological testing devices from 106 subjects who were optic nerve and macular disease subjects. In order to show the test performance of the classifier algorithms, the classification accuracy, receiver operating characteristic curves, sensitivity and specificity values, confusion matrix and 10-fold cross-validation have been used. The classification results obtained are 85.9%, 100% and 81.82% for the C4.5 decision tree classifier, the LS-SVM classifier and the AIRS classifier respectively using 10-fold cross-validation. It is shown that the LS-SVM classifier is a robust and effective classifier system for the determination of macular and optic nerve diseases.     

A note: Common due date assignment for a single machine scheduling with the rate-modifying activity

In this paper we study the single machine common due date assignment and scheduling problem with the possibility to perform a rate-modifying activity (RMA) for changing the processing times of the jobs following this activity. The objective is to minimize the total weighted sum of earliness, tardiness and due date costs. Placing the RMA to some position in the schedule can decrease the objective function value. Several properties of the problem are considered which in some cases can reduce the complexity of the solution algorithm.     

Makespan minimization for two parallel machines scheduling with a periodic availability constraint

A two parallel machines scheduling problem where one machine is periodically unavailable with the objective of minimizing makespan is considered. It is showed that the worst-case ratio of the classical LPT algorithm and the competitive ratio of the LS algorithm are 3/2 and 2, respectively, for the offline version and the online version of the problem.     

The use of ‘exploratory learning’ for supporting immersive learning in virtual environments

User interfaces are becoming more intuitive following the requirements of the individual learner and reinforcing the drive towards more personalised learning and greater learner autonomy. There are clearly a new set of challenges emerging for teaching practitioners that will have implications upon not just what is learned but importantly upon lesson planning. This paper explores these changes to teaching through a consideration of an exploratory learning model which allows practitioners to rethink how they teach in 3D and immersive spaces where learning sequences and experiences are choreographed to support peer interactions and exchanges. The ELM extends from Kolb’s experiential learning model to adapt the use of 3D applications, and provides examples from research and development projects to exemplify how the model works in practice. Teaching in these contexts provides less emphasis upon curriculum and more emphasis upon sequencing learning experiences, meta-reflection, peer assessment and group work.     

Cartoons beyond clipart: A computer tool for storyboarding and storywriting

This paper describes the motivation, proposal, and early prototype testing of a computer tool for story visualisation. An analysis of current software for making various types of visual story is made; this identifies a gap between software which emphasises preset banks of artwork, and software which emphasises low-level construction and/or drawing. A proposal is made to fill this gap, and a prototype implementation of the proposal is described in the context of a school-based study with England and Wales’s Year 5, covering ages 9–10 years. Results from this prototype study both validate the novel proposal made and demonstrate that children are capable of manipulating characters and notional camera angles in a more complex way than most current software permits.     

DMM:A dynamic memory mapping model for virtual machines

Memory virtualization is an important part in the design of virtual machine monitors(VMM).In this paper,we proposed dynamic memory mapping(DMM) model,a mechanism that allows the VMM to change the mapping between a virtual machine's physical memory and the underlying hardware resource while the virtual machine is running.By utilizing DMM,the VMM can implement many novel memory management policies,such as Demand Paging,Swapping,Ballooning,Memory Sharing and Copy-On-Write,while preserving compatibility with va...     

Intuitionistic fuzzy transformation semigroups

The idea of (faithful) intuitionistic fuzzy transformation semigroup, intuitionistic admissible relation, and intuitionistic (strong) homomorphism are introduced and their basic properties are examined.