A face recognition system based on Pseudo 2D HMM applied to neural network coefficients

Face recognition from an image or video sequences is emerging as an active research area with numerous commercial and law enforcement applications. In this paper different Pseudo 2-dimension Hidden Markov Models (HMMs) are introduced for a face recognition showing performances reasonably fast for binary images. The proposed P2-D HMMs are made up of five levels of states, one for each significant facial region in which the input frontal images are sequenced: forehead, eyes, nose, mouth and chin. Each of P2-D HMMs has been trained by coefficients of an artificial neural network used to compress a bitmap image in order to represent it with a number of coefficients that is smaller than the total number of pixels. All the P2-D HMMs, applied to the input set consisting of the Olivetti Research Laboratory face database combined to others photos, have achieved good rates of recognition and, in particular, the structure 3-6-6-6-3 has achieved a rate of recognition equal to 100%.     

Diagnostic tools for evaluating and updating hidden Markov models

In this paper we consider two related problems in hidden Markov models (HMMs). One, how the various parameters of an HMM actually contribute to predictions of state sequences and spatio-temporal pattern recognition. Two, how the HMM parameters (and associated HMM topology) can be updated to improve performance. These issues are examined in the context of four different experimental settings from pure simulations to observed data. Results clearly demonstrate the benefits of applying some critical tests on the model parameters before using it as a predictor or spatio-temporal pattern recognition technique.     

Classification of abnormal plant operation using multiple process variable trends

This paper illustrates two strategies for the detection and classification of abnormal process operating conditions in which multiple process variable trends are available. The first strategy uses a hidden Markov model (HMM) for overall process classification while the second method uses a back-propagation neural network (BPNN) to determine the overall process classification. The methods are compared in terms of their ability to detect and correctly diagnose a variety of abnormal operating conditions for a non-isothermal CSTR simulation. For the case study problem, the BPNN method resulted in better classification accuracy with a moderate increase in training time compared with the HMM approach.     

IP包间关联异常检测的免疫隐马尔柯夫模型

数据包是网络通信的基本单位,网络上的入侵行为都应该在数据包中以不同的形式存在、表达着,而且网络中流通的数据包之间必然存在一定的关联性。人工免疫以往的研究多集中在对单个数据包的分析,很难察觉到隐蔽的、缓慢的入侵行为（这些行为的数据包序列间大多有一定的关联性）。因此,该文对于相互联系的多个数据包,挖掘出它们之间的关联特征,并针对这些特征采用了隐马尔柯夫模型的自动机识别器来检测入侵。     

A novel HMM-based learning framework for improving dynamic wireless push system performance

A new machine learning framework is introduced in this paper, based on the hidden Markov model (HMM), designed to provide scheduling in dynamic wireless push systems. In realistic wireless systems, the clients’ intentions change dynamically; hence a cognitive scheduling scheme is needed to estimate the desirability of the connected clients. The proposed scheduling scheme is enhanced with self-organized HMMs, supporting the network with an estimated expectation of the clients’ intentions, since the system’s environment characteristics alter dynamically and the base station (server side) has no a priori knowledge of such changes. Compared to the original pure scheme, the proposed machine learning framework succeeds in predicting the clients’ information desires and overcomes the limitation of the original static scheme, in terms of mean delay and system efficiency.     

基于马尔可夫链的轨迹预测

为了支持在城市交通网络上,对移动对象的位置进行有效的预测,提出了一种基于马尔可夫链的移动对象轨迹预测方法.该方法根据城市交通网络的特征,依靠统计并有效利用历史轨迹进行预测.最后讨论了数据结构和算法的一些优化,并分析了算法复杂度.实验证明加权马尔可夫链的轨迹预测给出了令人满意的结果.     

A comparative evaluation of neural networks and hidden Markov models for monitoring turning tool wear

Condition monitoring of machine tool inserts is important for increasing the reliability and quality of machining operations. Various methods have been proposed for effective tool condition monitoring (TCM), and currently it is generally accepted that the indirect sensor-based approach is the best practical solution to reliable TCM. Furthermore, in recent years, neural networks (NNs) have been shown to model successfully, the complex relationships between input feature sets of sensor signals and tool wear data. NNs have several properties that make them ideal for effectively handling noisy and even incomplete data sets. There are several NN paradigms which can be combined to model static and dynamic systems. Another powerful method of modeling noisy dynamic systems is by using hidden Markov models (HMMs), which are commonly employed in modern speech-recognition systems. The use of HMMs for TCM was recently proposed in the literature. Though the results of these studies were quite promising, no comparative results of competing methods such as NNs are currently available. This paper is aimed at presenting a comparative evaluation of the performance of NNs and HMMs for a TCM application. The methods are employed on exactly the same data sets obtained from an industrial turning operation. The advantages and disadvantages of both methods are described, which will assist the condition-monitoring community to choose a modeling method for other applications.     

State-space dynamics distance for clustering sequential data

This paper proposes a novel similarity measure for clustering sequential data. We first construct a common state space by training a single probabilistic model with all the sequences in order to get a unified representation for the dataset. Then, distances are obtained attending to the transition matrices induced by each sequence in that state space. This approach solves some of the usual overfitting and scalability issues of the existing semi-parametric techniques that rely on training a model for each sequence. Empirical studies on both synthetic and real-world datasets illustrate the advantages of the proposed similarity measure for clustering sequences.     

A hybrid financial analysis model for business failure prediction

Accounting frauds have continuously happened all over the world. This leads to the need of predicting business failures. Statistical methods and machine learning techniques have been widely used to deal with this issue. In general, financial ratios are one of the main inputs to develop the prediction models. This paper presents a hybrid financial analysis model including static and trend analysis models to construct and train a back-propagation neural network (BPN) model. Further, the experiments employ four datasets of Taiwan enterprises which support that the proposed model not only provides a high predication rate but also outperforms other models including discriminant analysis, decision trees, and the back-propagation neural network alone.     

The Realization Problem for Hidden Markov Models

If {X _t} is a finite-state Markov process, and {Y _t} is a finite-valued output process with Y _t+1 depending (possibly probabilistically) on X _t, then the process pair is said to constitute a hidden Markov model. This paper considers the realization question: given the probabilities of all finite-length output strings, under what circumstances and how can one construct a finite-state Markov process and a state-to-output mapping which generates an output process whose finite-length strings have the given probabilities? After reviewing known results dealing with this problem involving Hankel matrices and polyhedral cones, we develop new theory on the existence and construction of the cones in question, which effectively provides a solution to the realization problem. This theory is an extension of recent theoretical developments on the positive realization problem of linear system theory. Date received: December 13, 1996. Date revised: October 9, 1998.     

一种基于马尔可夫模型的稀疏轨迹终点预测算法

随着移动设备的普及与定位技术的成熟,涌现出了各种基于地理位置的应用软件不断涌现。为了使这类应用软件给用户提供精准的基于地理位置的服务,实时、准确、可靠地预测移动对象的不确定性轨迹显得尤为重要。目前大多数传统的轨迹终点预测方法都是通过计算轨迹之间的相似度来预测给定轨迹的终点,这种算法的弊端是没有充分考虑轨迹数据时间序列之间的前后联系,导致预测结果偏差较大。理论证明,马尔可夫模型对处理时间序列数据具有较好的效果。因此,针对轨迹终点预测的问题,提出了一种基于马尔可夫模型的预测算法。同时,针对样本运动空间提出一种新的划分网格策略——K-d tree网格划分。实验结果表明,相比于传统方法,运用马尔可夫模型预测轨迹终点的算法的精度有明显提高,预测时间会大大缩短。     

Factorial Hidden Markov Models

Hidden Markov models (HMMs) have proven to be one of the most widely used tools for learning probabilistic models of time series data. In an HMM, information about the past is conveyed through a single discrete variable—the hidden state. We discuss a generalization of HMMs in which this state is factored into multiple state variables and is therefore represented in a distributed manner. We describe an exact algorithm for inferring the posterior probabilities of the hidden state variables given the observations, and relate it to the forward–backward algorithm for HMMs and to algorithms for more general graphical models. Due to the combinatorial nature of the hidden state representation, this exact algorithm is intractable. As in other intractable systems, approximate inference can be carried out using Gibbs sampling or variational methods. Within the variational framework, we present a structured approximation in which the the state variables are decoupled, yielding a tractable algorithm for learning the parameters of the model. Empirical comparisons suggest that these approximations are efficient and provide accurate alternatives to the exact methods. Finally, we use the structured approximation to model Bach's chorales and show that factorial HMMs can capture statistical structure in this data set which an unconstrained HMM cannot.     

Minimum classification error learning for sequential data in the wavelet domain

Wavelet analysis has found widespread use in signal processing and many classification tasks. Nevertheless, its use in dynamic pattern recognition have been much more restricted since most of wavelet models cannot handle variable length sequences properly. Recently, composite hidden Markov models which observe structured data in the wavelet domain were proposed to deal with this kind of sequences. In these models, hidden Markov trees account for local dynamics in a multiresolution framework, while standard hidden Markov models capture longer correlations in time. Despite these models have shown promising results in simple applications, only generative approaches have been used so far for parameter estimation. The goal of this work is to take a step forward in the development of dynamic pattern recognizers using wavelet features by introducing a new discriminative training method for this Markov models. The learning strategy relies on the minimum classification error approach and provides re-estimation formulas for fully non-tied models. Numerical experiments on phoneme recognition show important improvement over the recognition rate achieved by the same models trained using maximum likelihood estimation.     

Rule-based trajectory segmentation for modeling hand motion trajectory

In this paper, we propose a simple but effective method of modeling hand gestures based on the angles and angular change rates of the hand trajectories. Each hand motion trajectory is composed of a unique series of straight and curved segments. In our Hidden Markov Model (HMM) implementation, these trajectories are modeled as a connected series of states analogous to the series of phonemes in speech recognition. The novelty of the work presented herein is that it provides an automated process of segmenting gesture trajectories based on a simple set of threshold values in the angular change measure. In order to represent the angular distribution of each separated state, the von Mises distribution is used. A likelihood based state segmentation was implemented in addition to the threshold based method to ensure that the gesture sets are segmented consistently. The proposed method can separate each angular state of the training data at the initialization step, thus providing a solution to mitigate the ambiguities on initializing the HMM. The effectiveness of the proposed method was demonstrated by the higher recognition rates in the experiments compared to the conventional methods.     

Robot introspection through learned hidden Markov models

In this paper we describe a machine learning approach for acquiring a model of a robot behaviour from raw sensor data. We are interested in automating the acquisition of behavioural models to provide a robot with an introspective capability. We assume that the behaviour of a robot in achieving a task can be modelled as a finite stochastic state transition system.Beginning with data recorded by a robot in the execution of a task, we use unsupervised learning techniques to estimate a hidden Markov model (HMM) that can be used both for predicting and explaining the behaviour of the robot in subsequent executions of the task. We demonstrate that it is feasible to automate the entire process of learning a high quality HMM from the data recorded by the robot during execution of its task.The learned HMM can be used both for monitoring and controlling the behaviour of the robot. The ultimate purpose of our work is to learn models for the full set of tasks associated with a given problem domain, and to integrate these models with a generative task planner. We want to show that these models can be used successfully in controlling the execution of a plan. However, this paper does not develop the planning and control aspects of our work, focussing instead on the learning methodology and the evaluation of a learned model. The essential property of the models we seek to construct is that the most probable trajectory through a model, given the observations made by the robot, accurately diagnoses, or explains, the behaviour that the robot actually performed when making these observations. In the work reported here we consider a navigation task. We explain the learning process, the experimental setup and the structure of the resulting learned behavioural models. We then evaluate the extent to which explanations proposed by the learned models accord with a human observer's interpretation of the behaviour exhibited by the robot in its execution of the task.     

Speech segmentation using regression fusion of boundary predictions

In the present work we study the appropriateness of a number of linear and non-linear regression methods, employed on the task of speech segmentation, for combining multiple phonetic boundary predictions which are obtained through various segmentation engines. The proposed fusion schemes are independent of the implementation of the individual segmentation engines as well as from their number. In order to illustrate the practical significance of the proposed approach, we employ 112 speech segmentation engines based on hidden Markov models (HMMs), which differ in the setup of the HMMs and in the speech parameterization techniques they employ. Specifically we relied on sixteen different HMMs setups and on seven speech parameterization techniques, four of which are recent and their performance on the speech segmentation task have not been evaluated yet. In the evaluation experiments we contrast the performance of the proposed fusion schemes for phonetic boundary predictions against some recently reported methods. Throughout this comparison, on the established for the phonetic segmentation task TIMIT database, we demonstrate that the support vector regression scheme is capable of achieving more accurate predictions, when compared to other fusion schemes reported so far.