FTC of hidden Markov process with application to resource allocation in air operation

This paper investigates the feedback control of hidden Markov process（HMP） in the face of loss of some observation processes.The control action facilitates or impedes some particular transitions from an inferred current state in the attempt to maximize the probability that the HMP is driven to a desirable absorbing state.This control problem is motivated by the need for judicious resource allocation to win an air operation involving two opposing forces.The effectiveness of a receding horizon control scheme based on the inferred discrete state is examined.Tolerance to loss of sensors that help determine the state of the air operation is achieved through a decentralized scheme that estimates a continuous state from measurements of linear models with additive noise.The discrete state of the HMP is identified using three well-known detection schemes.The sub-optimal control policy based on the detected state is implemented on-line in a closed-loop,where the air operation is simulated as a stochastic process with SimEvents,and the measurement process is simulated for a range of single sensor loss rates.

Stability Estimation for Markov Control Processes with Discounted Cost

This article explores controllable Borel spaces, stationary, homogeneous Markov processes, discrete time with infinite horizon, with bounded cost functions and using the expected total discounted cost criterion. The problem of the estimation of stability for this type of process is set. The central objective is to obtain a bounded stability index expressed in terms of the Lévy-Prokhorov metric;likewise, sufficient conditions are provided for the existence of such inequalities.

Towards an Intelligent Predictive Model for Analyzing Spatio-Temporal Satellite Image Based on Hidden Markov Chain

Nowadays remote sensing is an important technique for observing Earth surface applied to different areas such as, land use, urban planning, remote monitoring, real time deformation of the soil that can be associated with earthquakes or landslides, the variations in thickness of the glaciers, the measurement of volume changes in the case of volcanic eruptions, deforestation, etc. To follow the evolution of these phenomena and to predict their future states, many approaches have been proposed. However, these approaches do not respond completely to the specialists who process yet more commonly the data extracted from the images in their studies to predict the future. In this paper, we propose an innovative methodology based on hidden Markov models (HMM). Our approach exploits temporal series of satellite images in order to predict spatio-temporal phenomena. It uses HMM for representing and making prediction concerning any objects in a satellite image. The first step builds a set of feature vectors gathering the available information. The next step uses a Baum-Welch learning algorithm on these vectors for detecting state changes. Finally, the system interprets these changes to make predictions. The performance of our approach is evaluated by tests of space-time interpretation of events conducted over two study sites, using different time series of SPOT images and application to the change in vegetation with LANDSAT images.

Asymptotic Evaluations of the Stability Index for a Markov Control Process with the Expected Total Discounted Reward Criterion

In this work, for a control consumption-investment process with the discounted reward optimization criteria, a numerical estimate of the stability index is made. Using explicit formulas for the optimal stationary policies and for the value functions, the stability index is explicitly calculated and through statistical techniques its asymptotic behavior is investigated (using numerical experiments) when the discount coefficient approaches 1. The results obtained define the conditions under which an approximate optimal stationary policy can be used to control the original process.

多重防护机制下LNG动力船风险态势分析方法

为探讨多重防护机制下的液化天然气(Liquefied Natural Gas,LNG)动力船营运风险特征,提出了一种基于复杂性控制系统作用模式的风险态势分析方法。从系统控制过程视角,采用系统控制过程分析方法(System-Theoretic Process Analysis,STPA)确立LNG动力船系统安全控制的风险致因,揭示基于LNG泄漏三重防护机制的风险因子体系和风险形成机制;引入隐马尔可夫模型(Hidden Markov Model,HMM),进行无监督学习并确立模型参数,推理多重防护机制下的LNG动力船风险转移特征;结合LNG动力船营运的具体场景,对三重防护机制分别进行仿真并统计风险态势。仿真结果表明,三重防护机制在降低LNG动力船营运风险态势方面具有因子诱导的针对性,在防漏因子、止漏因子和治漏因子诱导下LNG动力船分别趋向一般风险状态、较高风险状态和高风险状态。基于复杂性控制系统作用模式的风险态势分析可为LNG动力船营运的安全控制和风险管理提供管控模式和手段。

基于HMM-MLP的泵站监测健康诊断系统研究

为实现泵站工程在生产运行过程中有效预测设备潜在故障风险,提升泵站设备运行效率,在数字孪生水利工程数据底板基础上,基于现有硬件设备,以结构故障机理为导向,提出了一种HMM-MLP的泵站设备故障预测方法。先由连续小波包变换处理设备的运行信号,然后通过HMM模型生成设备运行状态序列作为MLP网络的输入预测设备故障,最后通过仿真实验表明,HMM-MLP模型可有效提高泵站设备故障的预测准确率。同时,依托在线监测数据和离线检查与试验数据,建立了设备健康评价指标体系,并开发了泵站监测健康诊断系统,协助运行管理人员充分了解和掌握机组设备的“健康”状态,提升设备管理的信息化水平。结果表明:该研究可为泵站健康系统建设提供实际案例指导与经验启示。

基于HMM的逆雷达辐射源状态识别推理方法

雷达对抗场景中雷达方和干扰方相互感知、识别以及博弈对抗.针对雷达方对干扰方系统内部状态的非合作识别推理的问题,提出了一种对干扰系统中雷达辐射源状态识别模块处理结果进行逆向估计的方法.建立了逆状态识别任务模型,任务中的干扰系统根据雷达工作状态识别结果对其干扰动作进行优化,雷达方则基于对干扰方干扰样式序列的观测,估计干扰方对雷达工作状态的识别结果;设计了基于隐马尔可夫模型(HMM)的逆状态识别任务求解方法,具体包括通过自适应粒子群算法进行模型参数初始化,采取多观测序列的鲍姆-韦尔奇算法进行模型参数估计,采用对数维特比算法估计干扰方的雷达状态识别结果;通过典型雷达对抗场景设定下的数字仿真验证了所给逆状态识别方法的可行性和有效性.

隐Markov决策模型

讨论Markov决策问题中样本与不可观测状态之间的关系问题。引进了避错特征函数的概念 ,利用隐Markov过程的结构和Markov决策模型建立了隐Markov决策模型。并进一步讨论了状态估计和阶段收益函数。

基于连续隐Markov模型的发酵过程关键状态变量软测量

针对生物发酵过程中一些关键状态变量难以用仪表进行在线检测的问题,提出了一种基于连续隐Markov模型(CHMM)的软测量方法.首先,为增加模型预测的鲁棒性,采用多观测样本序列训练CHMM模型库,运用Baum-Welch参数重估修正公式实现CHMM参数优化;然后,将新样本观测向量输入训练好的CHMM模型库,并基于Viterbi算法计算新样本在模型库中各个CHMM内的输出概率;最后,通过加权平均运算得出软测量结果.将所提出的方法应用于红霉素发酵过程菌体质量浓度软测量,并进行了建模与仿真研究.结果表明:所建CHMM软测量模型能够很好地用于生物发酵过程菌体质量浓度值预测,且预测效果优于人工神经网络软测量模型.

基于隐Markov过程的网络信任评估模型

为了快速精确地刻画实体行为的高动态性,提出一种基于连续时间隐Markov过程的信任评估模型。不同于离散时间隐Markov信任模型,该模型充分考虑到信任的时间相关性,结合交互记录之间的时间间隔,将实体信任评估问题归结为连续时间隐Markov过程的学习问题。进而利用改进的和声搜索算法,给出求解隐Markov过程最佳参数的算法,该算法有效地保证了全局搜索空间,能够获得更好的解。在此基础上,利用已有交互结果序列和最优参数组,对实体的信任度进行预测。仿真实验表明,该模型能够快速地反映出实体行为的动态性,具有较高的精确度,且能抵抗部分恶意攻击。

无限隐Markov模型理论及仿真研究

论述了传统隐Markov模型的理论及其存在的不足,并在此基础之上,阐明了无限隐Markov模型的理论及算法。在i HMM中,首先,从Dirichlet过程进行状态间转移概率的计算推导。然后,使用分层Dirichlet过程进行隐状态状态机制和生成机制的推理。其次,对模型超越参数的推理、优化和似然估计。还通过仿真实例对i HMM推理算法进行了验证,仿真结果表明i HMM具有很好的状态数目发掘能力,能够准确反映状态序列的结构特征。

Quality prediction of batch process using the global-local discriminant analysis based Gaussian process regression model

The conventional single model strategy may be ill- suited due to the multiplicity of operation phases and system uncertainty. A novel global-local discriminant analysis （GLDA） based Gaussian process regression （GPR） approach is developed for the quality prediction of nonlinear and multiphase batch processes. After the collected data is preprocessed through batchwise unfolding, the hidden Markov model （HMM） is applied to identify different operation phases. A GLDA algorithm is also presented to extract the appropriate process variables highly correlated with the quality variables, decreasing the complexity of modeling. Besides, the multiple local GPR models are built in the reduced- dimensional space for all the identified operation phases. Furthermore, the HMM-based state estimation is used to classify each measurement sample of a test batch into a corresponding phase with the maximal likelihood estimation. Therefore, the local GPR model with respect to specific phase is selected for online prediction. The effectiveness of the proposed prediction approach is demonstrated through the multiphase penicillin fermentation process. The comparison results show that the proposed GLDA-GPR approach is superior to the regular GPR model and the GPR based on HMM （HMM-GPR） model.

基于深度强化学习的智能地址库信息分析方法

针对地址库内部的地址无法及时更新、系统无法正确识别等问题,采用耦合隐马尔可夫模型对语言接收部分进行优化,利用自然语言处理算法设计一个智能化地址库。在系统空闲时,通过将概念树与自身数据库进行对比、迭代以满足深度强化学习的检测。试验结果表明,采用耦合隐马尔可夫模型的语言模块检测正确率在90%以上,为地址库信息分析提供了一份可行方案。

Modeling Abstraction Hierarchy Levels of the Cyber Attacks Using Random Process

Aspects of human behavior in cyber security allow more natural security to the user. This research focuses the appearance of anticipating cyber threats and their abstraction hierarchy levels on the mental picture levels of human. The study concerns the modeling of the behaviors of mental states of an individual under cyber attacks. The mental state of agents being not observable, we propose a non-stationary hidden Markov chain approach to model the agent mental behaviors. A renewal process based on a nonparametric estimation is also considered to investigate the spending time in a given mental state. In these approaches, the effects of the complexity of the cyber attacks are taken into account in the models.

基于分布式贝叶斯隐马尔可夫回归的动态软测量建模方法

利用软测量技术实时预测化工过程中的关键参数对生产过程的在线监测、自动控制、实时优化具有十分重要的意义。为此,提出了一种基于隐马尔可夫模型的动态软测量建模方法。首先,针对数据规模大导致模型计算效率低和数据缺失导致数据无法充分利用的问题,提出了一种基于分布式贝叶斯隐马尔可夫回归的预测模型;其次,针对该模型进一步提出了一种能够获得精确后验分布的分布式训练方法。最后,利用蜡油加氢过程对所提方法的有效性进行了验证。

Residual Chart with Hidden Markov Model to Monitoring the Auto-Correlated Processes

Autocorrelations exist in real production extensively, and special statistical tools are needed for process monitoring. Residual charts based on autoregressive integrated moving average(ARIMA) models are typically used. However, ARIMA models need a quite amount of experience, which sometimes causes inconveniences in the implementation. With a good performance under less experience or even none, hidden Markov models(HMMs)were proposed. Since ARIMA models have many different performances in positive and negative autocorrelations,it is interesting and essential to study how HMMs affect the performances of residual charts in opposite autocorrelations, which has not been studied yet. Therefore, we extend HMMs to negatively auto-correlated observations.The cross-validation method is used to select the relatively optimal state number. The experiment results show that HMMs are more stable than Auto-Regressive of order one(AR(1) models) in both cases of positive and negative autocorrelations. For detecting abnormalities, the performance of HMMs approach is much better than AR(1) models under positive autocorrelations while under negative autocorrelations both methods have similar performances.

结合独立与连续字符识别的集装箱号识别技术

针对集装箱号字符排列方式多样、字符间隔随机、且存在字符紧密排列难以分割开的情况,提出一种将独立字符识别与连续字符识别结合起来应用于集装箱箱号识别的方法。在字符提取阶段,将相互间存在一定间隔的字符作为单个字符进行提取;将紧密排列的字符作为连续字符串进行整体提取。在字符识别阶段,对于单个字符采用基于神经网络的独立字符识别方法进行识别;而对于连续字符串,则利用基于HMM的连续字符识别技术进行识别。通过对1040幅集装箱号图像进行实验,识别率达92.5%。实验结果表明本文方法能够有效地对各种情况(包括字符紧密排列)的集装箱号图像进行识别。

基于Contourlet域隐马尔可夫树模型的图像融合算法

针对多尺度几何变换统计信号处理这一领域的优势,提出一种基于Contourlet域隐马尔可夫树模型的图像融合算法.由于Contourlet变换能克服小波变换在处理高维信号时的不足,它比小波变换具有更好的方向性、较高的逼近精度和更好的稀疏表达性能.而隐马尔可夫树模型能有效捕获尺度间、尺度内的Contourlet系数特性.因此将Contourlet域隐马尔可夫树模型应用于图像融合领域,能充分挖掘数据之间的相关性,更好的提取图像边缘特征,为融合提取更多的特征信息.实验结果表明基于Contourlet域隐马尔可夫树图像融合算法获得的融合图像视觉效果良好,是一种有效且可行的融合算法.

面向商务信息抽取的产品命名实体识别研究

市场信息化使得商务信息抽取、市场内容管理日益成为信息科学领域的一个研究热点。产品命名实体识别作为其中非常重要的关键技术之一也逐渐受到人们的关注。本文面向商务信息抽取对产品命名实体进行了定义并系统分析了其识别任务的特点和难点,提出了一种基于层级隐马尔可夫模型(hierarchical hid-den Markov model)的产品命名实体识别方法,实现了汉语自由文本中产品命名实体识别和标注的原型系统。实验表明,该系统在电子数码和手机领域均取得了令人满意的实验结果,对产品名实体、产品型号实体、产品品牌实体整体识别性能的F值分别为79.7%,86.9%,75.8%。通过和最大熵模型相比较,验证了HHMM对于处理多尺度嵌套序列有更强的表征能力。

基于DPMM-CHMM的机械设备性能退化评估研究

针对传统的HMM模型状态数必须预先设定的不足,提出了一种基于DPMM-CHMM的机械设备性能退化评估方法。该方法利用DPMM模型的自动聚类功能,实现了模型结构根据观测数据的自适应变化和动态调整,获得设备运行过程中的最优退化状态数,并结合CHMM良好的分析和建模能力,得到设备退化状态转移路径,实现机械设备运行过程中的退化状态识别和性能评估,并利用滚动轴承全寿命数据进行了应用研究。结果表明,该方法可以有效地识别轴承运行中的不同退化状态,为基于状态的设备维修提供了理论指导。