基于回归神经网络的非线性时变系统辨识

为克服基于前馈神经网络的非线性系统辨识算法存在需预先估计系统输入输出滞后阶数的缺陷，提出一种基于回归神经网络的非线性时变系统的辨识算法，针对现有的回归网络学习算法大多采用梯度算法，收敛速度缓慢问题，提出一种具有快速收敛性的扩展卡尔曼滤波学习算法，大大提高了学习收敛速度，并推导了一种基于单个神经元的局部化算法，减少了计算量，仿真实例证明，所提出的算法是有效的。     

一种BP改进算法

本文针对ＢＰ算法局部最小问题，提出了一 种改进算法－ＢＰ算法。     

Linux下的多网卡接口的一种负载均衡算法

简要介绍了Linux的bonding技术及现有的几种负载均衡算法，讨论了这几种算法的不足；针对这些不足提出了一种基于TCP的发送算法，测试结果证明了该算法的可行性．     

神经网络在钢铁件混料分选中的应用

本文针对钢铁件混料分选的问题，介绍了一种基于初始幅值磁导率法的电磁无损检测方法，针对原有识别系统和传统BP神经网络学习算法的不足，提出一种改进算法，提高了网络分类的可靠性。     

红外目标图像尺度自适应检测算法

针对红外目标尺寸不定的实际情况，提出了对基于数学形态学的红外目标检测方法的改进。首先，对数学形态学进行了介绍，然后提出了一种红外目标检测的改进算法，最后给出并分析了该算法的仿真结果。实验结果表明，该算法是一种有效的红外目标检测算法。     

一种新的求解约束P-中位问题的启发式算法

针对约束P-中位问题的特点，提出了一种新的启发式算法。该算法借鉴了蚁群算法的信息素学习机制，同时针对问题的结构设计了合理的对象分配方式。模拟计算表明，该算法具有更好的全局优化性能和计算效率。     

指纹图像增强算法研究

本文根据笔者近年来的研究试验结果，指出了传统指纹图像增强算法的不足，以两种典型滤波算法为主，对近年来流行的基于方向场估计的滤波增强算法进行了分析和评价，并针对这两种算法的不足之处提出了一种新的算法思想。     

基于混合采样的不平衡数据集算法研究

针对不平衡数据集分类效果不理想的问题，提出了一种新的基于混合采样的不平衡数据集算法（BSI）。通过引进“变异系数”找出样本的稀疏域和密集域，针对稀疏域中的少数类样本，提出了一种改进SMOTE算法的过采样方法（BSMOTE）；对密集域中的多数类样本，提出了一种改进的欠采样方法（IS）。通过在六种不平衡数据集上的实验表明，该算法与传统算法相比，取得了更高的G-mean值、F-value值、AUC值，有效改善了不平衡数据集的综合分类性能。     

刺绣CAD中一种随机针码的生成算法研究

针对刺绣CAD中的一种随机针码提出了一种新的生成算法。和已有的算法相比，该算法生成的针码间距均匀，针码之间交叉较少，刺绣图案再现了原始图像的特征，达到了较好的刺绣效果。     

交互式群范例学习问题的求解及应用

针对传统基于范例推理方法存在的缺陷以及实际决策问题的需求，提出了一种交互式基于群范例学习的问题求解技术，给出了这一技术的问题求解过程、求解算法，针对算法中涉及到的范例检索方法，给出了一种基于2级索引的范例检索算法。弥补了传统CBR方法的缺陷，满足了解决实际决策问题的需要，展望了它的应用。     

基于DSVM的并行Hash连接算法及其性能评价

提出了一个基于分布式共享虚拟存储器技术的并行Ｈａｓｈ连接算法,然后设计了一个并行连接算法的测试评价基准,并评价和分析了该算法在均匀情况下３个不同负载的性能比较和Ｚｉｐｆ顺斜数据分布情况下两种度策略的算法性能。同时与其它并行连接算法进行性能比较与分析。     

Hand Gesture Recognition Based Omnidirectional Wheelchair Control Using IMU and EMG Sensors

This paper presents a hand gesture based control of an omnidirectional wheelchair using inertial measurement unit (IMU) and myoelectric units as wearable sensors. Seven common gestures are recognized and classified using shape based feature extraction and Dendogram Support Vector Machine (DSVM) classifier. The dynamic gestures are mapped to the omnidirectional motion commands to navigate the wheelchair. A single IMU is used to measure the wrist tilt angle and acceleration in three axis. EMG signals are extracted from two forearm muscles namely Extensor Carpi Radialis and Flexor Carpi Radialis and processed to provide Root Mean Square (RMS) signal. Initiation and termination of dynamic activities are based on autonomous identification of static to dynamic or dynamic to static transition by setting static thresholds on processed IMU and myoelectric sensor data. Classification involves recognizing the activity pattern based on periodic shape of trajectories of the triaxial wrist tilt angle and EMG-RMS from the two selected muscles. Second order Polynomial coefficients extracted from the sensor trajectory templates during specific dynamic activity cycles are used as features to classify dynamic activities. Classification algorithm and real time navigation of the wheelchair using the proposed algorithm has been tested by five healthy subjects. Classification accuracy of 94% was achieved by DSVM classifier on ‘k’ fold cross validation data of 5 users. Classification accuracy while operating the wheelchair was 90.5%.     

Probability based voting extreme learning machine for multiclass XML documents classification

This paper presents a novel solution based on Extreme Learning Machine (ELM) for multiclass XML documents classification. ELM is a generalized Single-hidden Layer Feedforward Network (SLFN) with extremely fast learning capacity. An improved vector model DSVM (Distribution based Structured Vector Model) is proposed to represent XML documents with more structural information and more precise semantic information. The XML documents classifiers are conducted based on PV-ELM (Probablity based Voting ELM) with a postprocessing method ε-RCC (ε - Revoting of Confusing Classes) to refine the voting results. To evaluate the overall performance of this solution, a series of experiments are conducted on two real datasets of news feeds online. The experimental results show that DSVM represents the XML documents more effectively and PV-ELM with ε-RCC achieves a higher accuracy than original ELM algorithm for multiclass classification.     

An adaptive middleware design to support the dynamic interpretation of domain-specific models

ContextAs the use of Domain-Specific Modeling Languages (DSMLs) continues to gain popularity, we have developed new ways to execute DSML models. The most popular approach is to execute code resulting from a model-to-code transformation. An alternative approach is to directly execute these models using a semantic-rich execution engine – Domain-Specific Virtual Machine (DSVM). The DSVM includes a middleware layer responsible for the delivery of services in a given domain.ObjectiveWe will investigate an approach that performs the dynamic combination of constructs in the middleware layer of DSVMs to support the delivery of domain-specific services. This middleware should provide: (a) a model of execution (MoE) that dynamically integrates decoupled domain-specific knowledge (DSK) for service delivery, (b) runtime adaptability based on context and available resources, and (c) the same level of operational assurance as any DSVM middleware.MethodOur approach will involve (1) defining a framework that supports the dynamic combination of MoE and DSK and (2) demonstrating the applicability of our framework in the DSVM middleware for user-centric communication. We will measure the overhead of our approach and provide a cost-benefit analysis factoring in its runtime adaptability using appropriate experimentation.ResultsOur experiments show that combining the DSK and MoE for a DSVM middleware allow us to realize efficient specialization while maintaining the required operability. We also show that the overhead introduced by adaptation is not necessarily deleterious to overall performance in a domain as it may result in more efficient operation selection.ConclusionThe approach defined for the DSVM middleware allows for greater flexibility in service delivery while reducing the complexity of application development for the user. These benefits are achieved at the expense of increased execution times, however this increase may be negligible depending on the domain.     

Synthesizing interpreted domain-specific models to manage smart microgrids

The increase in prominence of model-driven software development (MDSD) has placed emphasis on the use of domain-specific modeling languages (DSMLs) during the development process. DSMLs allow for domain concepts to be conceptualized and represented at a high level of abstraction. Currently, most DSML models are converted into high-level languages (HLLs) through a series of model-to-model and/or model-to-text transformations before they are executed. An alternative approach for model execution is the interpretation of models directly without converting them into an HLL. These models are created using interpreted DSMLs (i-DSMLs) and realized using a semantic-rich execution engine or domain-specific virtual machine (DSVM).In this article we present an approach for model synthesis, the first stage of model interpretation, that separates the domain-specific knowledge (DSK) from the model of execution (MoE). Previous work on model synthesis tightly couples the DSK and MoE reducing the ability for implementations of the DSVM to be easily reused in other domains. To illustrate how our approach to model synthesis works for i-DSMLs, we have created MGridML, an i-DSML for energy management in smart microgrids, and an MGridVM prototype, the DSVM for MGridML. We evaluated our approach by performing experiments on the model synthesis aspect of MGridVM and comparing the results to a DSVM from the user-centric communication domain.     

A survey of recoverable distributed shared virtual memory systems

Distributed Shared Virtual Memory (DSVM) systems provide a shared memory abstraction on distributed memory architectures. Such systems ease parallel application programming because the shared-memory programming model is often more natural than the message-passing paradigm. However, the probability of failure of a DSVM increases with the number of sites. Thus, fault tolerance mechanisms must be implemented in order to allow processes to continue their execution in the event of a failure. This paper gives an overview of recoverable DSVMs (RDSVMs) that provide a checkpointing mechanism to restart parallel computations in the event of a site failure     

基于PSO算法的生料浆配料过程的优化控制

针对烧结法氧化铝生产流程中的生料浆配料过程的工艺特点,将PSO算法应用在配料过程中的原料分配优化问题中,并构造了惩罚函数来处理配料过程中的各种约束条件.基于PSO算法的优化控制不仅可以保证生料浆的各项工艺指标达到设定值,同时可以保证配料成本最低.在某氧化铝厂的应用结果表明,该优化控制可以取代传统的人工配料生产方式,提高了生料浆各项工艺指标的合格率,降低了配料成本,实现了优化配料,取得了显著的应用效益.     

铝酸钠溶液组分浓度在线分析仪的研制

针对氧化铝生产过程中铝酸钠溶液组分浓度难以在线检测,无法实时指导生产过程的问题,结合铝酸钠溶液的物理化学性质,设计并开发了铝酸钠溶液组分浓度在线分析仪。提出了基于向上查表法的铝酸钠溶液组分浓度软测量模型,并采用PSO优化算法对表值进行计算与更新。所研制的在线分析仪成功应用于某氧化铝厂生产过程,现场应用结果表明在线分析仪运行稳定可靠且易于实施,所提出的铝酸钠溶液组分浓度软测量方法简单可行,取得了明显的应用效果。     

椭球定界算法在混合建模中的应用研究

并行结构混合建模主要由机理模型与误差补偿模型组成.一般地,误差补偿模型不宜过于复杂,且模型应具有校正功能,以免精度随时间不断下降.针对这个问题,本文选择单层神经网络作为误差补偿模型,并将椭球定界算法应用于单层神经网络的参数更新,不仅能够保证建模误差稳定有界,同时能够提高网络的收敛速度.将提出的方法应用于氧化铝生产过程,改进了原有的苛性碱和氧化铝组 分浓度软测量方法.实验研究结果表明,椭球定界算法的应用提高了模型的精度和网络的收敛速度.除此之外,在存在噪声干扰下,改进 的方法比原有方法更稳定,进一步证明了方法的有效性和优越性.     

一种改进的RPCL聚类算法及其在软测量中的应用

传统RPCL聚类算法是在随机选取样本的前提下修正权矢量的,没有考虑样本集的空间分布情况。为此,该文提出了一种改进的RPCL聚类算法。该算法引入样本区域密度的概念,根据密度大小按不同的概率选取样本,以修正权矢量。利用文犤1犦中的算例证明了新算法比传统RPCL算法具有更好的聚类速度和精度。最后将算法用于基于RBF神经网络的氧化铝高压溶出过程中溶出率的软测量,仿真结果表明改进的RPCL算法能很好地实现数据样本的聚类,从而提高软测量模型的泛化能力。