基于DHMM的低心率变异性心音的分割方法

针对现有心音定位分割方法精度有限的难题,提出了一种对心率变异性较低的信号建模分割方法。首先,通过集合经验模态分解（Ensemble empirical mode decomposition,EEMD）使用有效的本征模态函数（Intrinsic mode function,IMF）分量来表征心音信号,提高心音信号的可分析性;然后,通过基础心音与非基础心音间的高斯约束关系建立高斯混合模型（Gaussian mixture model,GMM）;接着,优化隐马尔可夫模型（Hidden Markov model, HMM）并建立基于时间相关性的隐马尔可夫模型（Duration-dependent hidden Markov model,DHMM）,更简洁地描述分割模型,降低算法复杂度;最后,通过时域特征区分出s₁,收缩期,s₂和舒张期。将本文算法与经典Hilbert算法和逻辑回归的隐半马尔科夫模型（Logistic regression hidden semi-Markov model,LRHSMM）算法进行了对比,实验结果表明,本文算法的检出正确率和运算耗时等评价指标更优。     

Two-microphone separation of speech mixtures.

Separation of speech mixtures, often referred to as the cocktail party problem, has been studied for decades. In many source separation tasks, the separation method is limited by the assumption of at least as many sensors as sources. Further, many methods require that the number of signals within the recorded mixtures be known in advance. In many real-world applications, these limitations are too restrictive. We propose a novel method for underdetermined blind source separation using an instantaneous mixing model which assumes closely spaced microphones. Two source separation techniques have been combined, independent component analysis (ICA) and binary time - frequency (T-F) masking. By estimating binary masks from the outputs of an ICA algorithm, it is possible in an iterative way to extract basis speech signals from a convolutive mixture. The basis signals are afterwards improved by grouping similar signals. Using two microphones, we can separate, in principle, an arbitrary number of mixed speech signals. We show separation results for mixtures with as many as seven speech signals under instantaneous conditions. We also show that the proposed method is applicable to segregate speech signals under reverberant conditions, and we compare our proposed method to another state-of-the-art algorithm. The number of source signals is not assumed to be known in advance and it is possible to maintain the extracted signals as stereo signals.     

Hidden Markov models with arbitrary state dwell-time distributions

A hidden Markov model (HMM) with a special structure that captures the ‘semi’-property of hidden semi-Markov models (HSMMs) is considered. The proposed model allows arbitrary dwell-time distributions in the states of the Markov chain. For dwell-time distributions with finite support the HMM formulation is exact while for those that have infinite support, e.g. the Poisson, the distribution can be approximated with arbitrary accuracy. A benefit of using the HMM formulation is that it is easy to incorporate covariates, trend and seasonal variation particularly in the hidden component of the model. In addition, the formulae and methods for forecasting, state prediction, decoding and model checking that exist for ordinary HMMs are applicable to the proposed class of models. An HMM with explicitly modeled dwell-time distributions involving seasonality is used to model daily rainfall occurrence for sites in Bulgaria.     

A class of neural networks for independent component analysis

Independent component analysis (ICA) is a recently developed, useful extension of standard principal component analysis (PCA). The ICA model is utilized mainly in blind separation of unknown source signals from their linear mixtures. In this application only the source signals which correspond to the coefficients of the ICA expansion are of interest. In this paper, we propose neural structures related to multilayer feedforward networks for performing complete ICA. The basic ICA network consists of whitening, separation, and basis vector estimation layers. It can be used for both blind source separation and estimation of the basis vectors of ICA. We consider learning algorithms for each layer, and modify our previous nonlinear PCA type algorithms so that their separation capabilities are greatly improved. The proposed class of networks yields good results in test examples with both artificial and real-world data.     

面向特征的ICA和HP滤波实现视频异常事件检测

针对室外环境下光照亮度变化、阴影和树木遮挡等问题,对利用隐马尔可夫模型进行视频异常事件检测的影响,提出基于独立分量分析（ICA）和HP（Hodrick-Prescott）滤波器的隐马尔可夫模型视频异常事件检测方法。该方法首先利用ICA构造正常视频的特征子空间,将图像序列投影到特征子空间上得到投影序列,实现数据降维;然后利用HP滤波器滤除投影序列中环境变化引起的趋势分量;最终克服不利的环境因素,有效改善隐马尔可夫模型的视频异常事件检测性能。机动车辆禁行路段视频的检测实验表明,该方法能够在复杂的室外环境下较好地检测出异常事件。     

A robust approach to independent component analysis of signals with high-level noise measurements

We propose a robust approach for independent component analysis (ICA) of signals where observations are contaminated with high-level additive noise and/or outliers. The source signals may contain mixtures of both sub-Gaussian and super-Gaussian components, and the number of sources is unknown. Our robust approach includes two procedures. In the first procedure, a robust prewhitening technique is used to reduce the power of additive noise, the dimensionality and the correlation among sources. A cross-validation technique is introduced to estimate the number of sources in this first procedure. In the second procedure, a nonlinear function is derived using the parameterized t-distribution density model. This nonlinear function is robust against the undue influence of outliers fundamentally. Moreover, the stability of the proposed algorithm and the robust property of misestimating the parameters (kurtosis) have been studied. By combining the t-distribution model with a family of light-tailed distributions (sub-Gaussian) model, we can separate the mixture of sub-Gaussian and super-Gaussian source components. Through the analysis of artificially synthesized data and real-world magnetoencephalographic (MEG) data, we illustrate the efficacy of this robust approach.     

Fast nonlinear autocorrelation algorithm for source separation

Independent component analysis (ICA) and blind source separation (BSS) methods have been used for pattern recognition problems. It is well known that ICA and BSS depend on the statistical properties of original sources or components, such as non-Gaussianity. In the paper, using a statistical property—nonlinear autocorrelation and maximizing the nonlinear autocorrelation of source signals, we propose a fast fixed-point algorithm for BSS. We study its convergence property and show that its convergence speed is at least quadratic. Simulations by the artificial signals and the real-world applications verify the efficient implementation of the proposed method.     

Nonlinear and noisy extension of independent component analysis: theory and its application to a pitch sensation model

In this letter, we propose a noisy nonlinear version of independent component analysis (ICA). Assuming that the probability density function (p. d. f.) of sources is known, a learning rule is derived based on maximum likelihood estimation (MLE). Our model involves some algorithms of noisy linear ICA (e. g., Bermond & Cardoso, 1999) or noise-free nonlinear ICA (e. g., Lee, Koehler, & Orglmeister, 1997) as special cases. Especially when the nonlinear function is linear, the learning rule derived as a generalized expectation-maximization algorithm has a similar form to the noisy ICA algorithm previously presented by Douglas, Cichocki, and Amari (1998). Moreover, our learning rule becomes identical to the standard noise-free linear ICA algorithm in the noiseless limit, while existing MLE-based noisy ICA algorithms do not rigorously include the noise-free ICA. We trained our noisy nonlinear ICA by using acoustic signals such as speech and music. The model after learning successfully simulates virtual pitch phenomena, and the existence region of virtual pitch is qualitatively similar to that observed in a psychoacoustic experiment. Although a linear transformation hypothesized in the central auditory system can account for the pitch sensation, our model suggests that the linear transformation can be acquired through learning from actual acoustic signals. Since our model includes a cepstrum analysis in a special case, it is expected to provide a useful feature extraction method that has often been given by the cepstrum analysis.     

Blind separation of non-stationary sources using continuous density hidden Markov models

Blind source separation (BSS) has attained much attention in signal processing society due to its ‘blind’ property and wide applications. However, there are still some open problems, such as underdetermined BSS, noise BSS. In this paper, we propose a Bayesian approach to improve the separation performance of instantaneous mixtures with non-stationary sources by taking into account the internal organization of the non-stationary sources. Gaussian mixture model (GMM) is used to model the distribution of source signals and the continuous density hidden Markov model (CDHMM) is derived to track the non-stationarity inside the source signals. Source signals can switch between several states such that the separation performance can be significantly improved. An expectation-maximization (EM) algorithm is derived to estimate the mixing coefficients, the CDHMM parameters and the noise covariance. The source signals are recovered via maximum a posteriori (MAP) approach. To ensure the convergence of the proposed algorithm, the proper prior densities, conjugate prior densities, are assigned to estimation coefficients for incorporating the prior information. The initialization scheme for the estimates is also discussed. Systematic simulations are used to illustrate the performance of the proposed algorithm. Simulation results show that the proposed algorithm has more robust separation performance in terms of similarity score in noise environments in comparison with the classical BSS algorithms in determined mixture case. Additionally, since the mixing matrix and the sources are estimated jointly, the proposed EM algorithm also works well in underdetermined case. Furthermore, the proposed algorithm converges quickly with proper initialization.     

基于HSMM的两阶段设备缺陷状态识别方法*

针对传统马尔可夫模型(HMM)状态停留时间必须服从指数分布假设的不足,提出了一种基于隐半马尔可夫模型(HSMM)的两阶段设备缺陷状态识别方法.首先,通过分析HSMM模型的参数构成及基本特点,并结合两阶段设备的劣化过程特点提出合理的假设条件,建立起用于描述两阶段设备运行状态的HSMM模型;其次,针对HSMM模型的参数估计问题,引入最大似然估计法,并提出了小样本条件下求解状态持续时间的方法;再次,基于建立的HSMM模型,给出了两阶段设备缺陷状态早期识别的计算公式及步骤,通过对状态停留时间的概率估计实现了对缺陷状态的早期识别;最后,通过计算机仿真方法模拟了HSMM模型的建模、参数估计及缺陷状态识别过程,从而验证了该方法的有效性和准确性.     

Binaural Tracking of Multiple Moving Sources

This paper addresses the problem of tracking multiple moving sources using binaural input. We observe that binaural cues are strongly correlated with source locations in time-frequency regions dominated by only one source. Based on this observation, we propose a novel tracking algorithm that integrates probabilities across reliable frequency channels in order to produce a likelihood function in the target space, which describes the azimuths of all active sources at a particular time frame. Finally, a hidden Markov model (HMM) is employed to form continuous tracks and automatically detect the number of active sources across time. Results are presented for up to three moving talkers in anechoic conditions. A comparison shows that our HMM model outperforms a Kalman filter-based approach in tracking active sources across time. Our study represents a first step in addressing auditory scene analysis with moving sound sources.     

A fast algorithm for one-unit ICA-R

Independent component analysis (ICA) aims to recover a set of unknown mutually independent source signals from their observed mixtures without knowledge of the mixing coefficients. In some applications, it is preferable to extract only one desired source signal instead of all source signals, and this can be achieved by a one-unit ICA technique. ICA with reference (ICA-R) is a one-unit ICA algorithm capable of extracting an expected signal by using prior information. However, a drawback of ICA-R is that it is computationally expensive. In this paper, a fast one-unit ICA-R algorithm is derived. The reduction of the computational complexity for the ICA-R algorithm is achieved through (1) pre-whitening the observed signals; and (2) normalizing the weight vector. Computer simulations were performed on synthesized signals, a speech signal, and electrocardiograms (ECG). Results of these analyses demonstrate the efficiency and accuracy of the proposed algorithm.     

Customer credit scoring based on HMM/GMDH hybrid model

Hidden Markov model (HMM) has made great achievements in many fields such as speech recognition and engineering. However, due to its assumption of state conditional independence between observations, HMM has a very limited capacity for recognizing complex patterns involving more than first-order dependencies in customer relationships management. Group Method of Data Handling (GMDH) could overcome the drawbacks of HMM, so we propose a hybrid model by combining the HMM and GMDH to score customer credit. There are three phases in this model: training HMM with multiple observations, adding GMDH into HMM and optimizing the hybrid model. The proposed hybrid model is compared with other exiting methods in terms of average accuracy, Type I error, Type II error and AUC. Experimental results show that the proposed method has better performance than HMM/ANN in two credit scoring datasets. The implementation of HMM/GMDH hybrid model allows lenders and regulators to develop techniques to measure customer credit risk.     

Semi-Markov conditional random fields for accelerometer-based activity recognition

Activity recognition is becoming an important research area, and finding its way to many application domains ranging from daily life services to industrial zones. Sensing hardware and learning algorithms are two important components in activity recognition. For sensing devices, we prefer to use accelerometers due to low cost and low power requirement. For learning algorithms, we propose a novel implementation of the semi-Markov Conditional Random Fields (semi-CRF) introduced by Sarawagi and Cohen. Our implementation not only outperforms the original method in terms of computation complexity (at least 10 times faster in our experiments) but also is able to capture the interdependency among labels, which was not possible in the previously proposed model. Our results indicate that the proposed approach works well even for complicated activities like eating and driving a car. The average precision and recall are 88.47% and 86.68%, respectively, which are higher than results obtained by using other methods such as Hidden Markov Model (HMM) or Topic Model (TM).     

Self-adaptive blind source separation based on activation functions adaptation

Independent component analysis is to extract independent signals from their linear mixtures without assuming prior knowledge of their mixing coefficients. As we know, a number of factors are likely to affect separation results in practical applications, such as the number of active sources, the distribution of source signals, and noise. The purpose of this paper to develop a general framework of blind separation from a practical point of view with special emphasis on the activation function adaptation. First, we propose the exponential generative model for probability density functions. A method of constructing an exponential generative model from the activation functions is discussed. Then, a learning algorithm is derived to update the parameters in the exponential generative model. The learning algorithm for the activation function adaptation is consistent with the one for training the demixing model. Stability analysis of the learning algorithm for the activation function is also discussed. Both theoretical analysis and simulations show that the proposed approach is universally convergent regardless of the distributions of sources. Finally, computer simulations are given to demonstrate the effectiveness and validity of the approach.     

A novel approach to equipment health management based on auto-regressive hidden semi-Markov model （AR-HSMM）

As a new maintenance method, CBM （condition based maintenance） is becoming more and more important for the health management of complicated and costly equipment. A prerequisite to widespread deployment of CBM technology and prac- tice in industry is effective diagnostics and prognostics. Recently, a pattern recog- nition technique called HMM （hidden Markov model） was widely used in many fields. However, due to some unrealistic assumptions, diagnositic results from HMM were not so good, and it was difficult to use HMM directly for prognosis. By relaxing the unrealistic assumptions in HMM, this paper presents a novel approach to equip- ment health management based on auto-regressive hidden semi-Markov model （AR-HSMM）. Compared with HMM, AR-HSMM has three advantages： 1） It allows explicitly modeling the time duration of the hidden states and therefore is capable of prognosis. 2） It can relax observations＇ independence assumption by accom- modating a link between consecutive observations. 3） It does not follow the unre- alistic Markov chain＇s memoryless assumption and therefore provides more pow- erful modeling and analysis capability for real problems. To facilitate the computa- tion in the proposed AR-HSMM-based diagnostics and prognostics, new forward- backward variables are defined and a modified forward-backward algorithm is de- veloped. The evaluation of the proposed methodology was carried out through a real world application case study： health diagnosis and prognosis of hydraulic pumps in Caterpillar Inc. The testing results show that the proposed new approach based on AR-HSMM is effective and can provide useful support for the decision- making in equipment health management.     

Driving intention recognition and behaviour prediction based on a double-layer hidden Markov model

We propose a model structure with a double-layer hidden Markov model (HMM) to recognise driving intention and predict driving behaviour. The upper-layer multi-dimensional discrete HMM (MDHMM) in the double-layer HMM represents driving intention in a combined working case, constructed according to the driving behaviours in certain single working cases in the lower-layer multi-dimensional Gaussian HMM (MGHMM). The driving behaviours are recognised by manoeuvring the signals of the driver and vehicle state information, and the recognised results are sent to the upper-layer HMM to recognise driving intentions. Also, driving behaviours in the near future are predicted using the likelihood-maximum method. A real-time driving simulator test on the combined working cases showed that the double-layer HMM can recognise driving intention and predict driving behaviour accurately and efficiently. As a result, the model provides the basis for pre-warning and intervention of danger and improving comfort performance.     

Independent component analysis based on nonparametric density estimation

In this paper, we introduce a novel independent component analysis (ICA) algorithm, which is truly blind to the particular underlying distribution of the mixed signals. Using a nonparametric kernel density estimation technique, the algorithm performs simultaneously the estimation of the unknown probability density functions of the source signals and the estimation of the unmixing matrix. Following the proposed approach, the blind signal separation framework can be posed as a nonlinear optimization problem, where a closed form expression of the cost function is available, and only the elements of the unmixing matrix appear as unknowns. We conducted a series of Monte Carlo simulations, involving linear mixtures of various source signals with different statistical characteristics and sample sizes. The new algorithm not only consistently outperformed all state-of-the-art ICA methods, but also demonstrated the following properties: 1) Only a flexible model, capable of learning the source statistics, can consistently achieve an accurate separation of all the mixed signals. 2) Adopting a suitably designed optimization framework, it is possible to derive a flexible ICA algorithm that matches the stability and convergence properties of conventional algorithms. 3) A nonparametric approach does not necessarily require large sample sizes in order to outperform methods with fixed or partially adaptive contrast functions.     

Speech separation using speaker-adapted eigenvoice speech models

We present a system for model-based source separation for use on single channel speech mixtures where the precise source characteristics are not known a priori. The sources are modeled using hidden Markov models (HMM) and separated using factorial HMM methods. Without prior speaker models for the sources in the mixture it is difficult to exactly resolve the individual sources because there is no way to determine which state corresponds to which source at any point in time. This is solved to a small extent by the temporal constraints provided by the Markov models, but permutations between sources remains a significant problem. We overcome this by adapting the models to match the sources in the mixture. We do this by representing the space of speaker variation with a parametric signal model-based on the eigenvoice technique for rapid speaker adaptation. We present an algorithm to infer the characteristics of the sources present in a mixture, allowing for significantly improved separation performance over that obtained using unadapted source models. The algorithm is evaluated on the task defined in the 2006 Speech Separation Challenge [Cooke, M.P., Lee, T.-W., 2008. The 2006 Speech Separation Challenge. Computer Speech and Language] and compared with separation using source-dependent models. Although performance is not as good as with speaker-dependent models, we show that the system based on model adaptation is able to generalize better to held out speakers.     

Blind Source Extraction for Noisy Mixtures by Combining Gaussian Moments and Generalized Autocorrelations

In the blind source extraction problem, the concept of generalized autocorrelations has been successfully used when the desired signal has special temporal structures. However, their applications are only limited to noise-free mixtures, which is not realistic. Therefore, this paper addresses the extraction of the noisy model based on these temporal characteristics of sources. An objective function, which combines Gaussian moments and generalized autocorrelations, is proposed. Maximizing this objective function, we present a blind source extraction algorithm for noisy mixtures. Simulations on synthesized signals, images, artificial electrocardiogram (ECG) data and the real-world ECG data show the better performance of the proposed algorithm. Moreover, comparisons with the existing algorithms further indicate its validity and also show its robustness to the estimated error of time delay.