Hidden Markov Model Parameters Research Articles

Efficient algorithms for training the parameters of hidden Markov models using stochastic expectation maximization (EM) training and Viterbi training

BackgroundHidden Markov models are widely employed by numerous bioinformatics programs used today. Applications range widely from comparative gene prediction to time-series analyses of micro-array data. The parameters of the underlying models need to be adjusted for specific data sets, for example the genome of a particular species, in order to maximize the prediction accuracy. Computationally efficient algorithms for parameter training are thus key to maximizing the usability of a wide range of bioinformatics applications.ResultsWe introduce two computationally efficient training algorithms, one for Viterbi training and one for stochastic expectation maximization (EM) training, which render the memory requirements independent of the sequence length. Unlike the existing algorithms for Viterbi and stochastic EM training which require a two-step procedure, our two new algorithms require only one step and scan the input sequence in only one direction. We also implement these two new algorithms and the already published linear-memory algorithm for EM training into the hidden Markov model compiler HMM-CONVERTER and examine their respective practical merits for three small example models.ConclusionsBioinformatics applications employing hidden Markov models can use the two algorithms in order to make Viterbi training and stochastic EM training more computationally efficient. Using these algorithms, parameter training can thus be attempted for more complex models and longer training sequences. The two new algorithms have the added advantage of being easier to implement than the corresponding default algorithms for Viterbi training and stochastic EM training.

Penalized Logistic Regression With HMM Log-Likelihood Regressors for Speech Recognition

Hidden Markov models (HMMs) are powerful generative models for sequential data that have been used in automatic speech recognition for more than two decades. Despite their popularity, HMMs make inaccurate assumptions about speech signals, thereby limiting the achievable performance of the conventional speech recognizer. Penalized logistic regression (PLR) is a well-founded discriminative classifier with long roots in the history of statistics. Its classification performance is often compared with that of the popular support vector machine (SVM). However, for speech classification, only limited success with PLR has been reported, partially due to the difficulty with sequential data. In this paper, we present an elegant way of incorporating HMMs in the PLR framework. This leads to a powerful discriminative classifier that naturally handles sequential data. In this approach, speech classification is done using affine combinations of HMM log-likelihoods. We believe that such combinations of HMMs lead to a more accurate classifier than the conventional HMM-based classifier. Unlike similar approaches, we jointly estimate the HMM parameters and the PLR parameters using a single training criterion. The extension to continuous speech recognition is done via rescoring of N-best lists or lattices.

A statistical method for scanning the genome for regions with rare disease alleles

Studying the role of rare alleles in common disease has been prevented by the impractical task of determining the DNA sequence of large numbers of individuals. Next-generation DNA sequencing technologies are being developed that will make it possible for genetic studies of common disease to study the full frequency spectrum of genetic variation, including rare alleles. This report describes a method for scanning the genome for disease susceptibility regions that show an increased number of rare alleles among a sample of disease cases versus an ethnically matched sample of controls. The method was based on a hidden Markov model and the statistical support for a disease susceptibility region characterized by rare alleles was measured by a likelihood ratio statistic. Due to the lack of empirical data, the method was evaluated through simulation. The performance of the method was tested under the null and alternative hypotheses under a range of sequence generating and hidden Markov models parameters. The results showed that the statistical method performs well at identifying true disease susceptibility regions and that performance was primarily affected by the amount of variation in the neutral sequence and the number of rare disease alleles found in the disease susceptibility region.

Genetic algorithm based simultaneous optimization of feature subsets and hidden Markov model parameters for discrimination between speech and non-speech events

Feature subsets and hidden Markov model (HMM) parameters are the two major factors that affect the classification accuracy (CA) of the HMM-based classifier. This paper proposes a genetic algorithm based approach for simultaneously optimizing both feature subsets and HMM parameters with the aim to obtain the best HMM-based classifier. Experimental data extracted from three spontaneous speech corpora were used to evaluate the effectiveness of the proposed approach and the three other approaches (i.e. the approaches to single optimization of feature subsets, single optimization of HMM parameters, and no optimization of both feature subsets and HMM parameters) that were adopted in the previous work for discrimination between speech and non-speech events (e.g. filled pause, laughter, applause). The experimental results show that the proposed approach obtains CA of 91.05%, while the three other approaches obtain CA of 86.11%, 87.05%, and 83.16%, respectively. The results suggest that the proposed approach is superior to the previous approaches.

Speech classification using penalized logistic regression with hidden Markov model log-likelihood regressors.

Penalized logistic regression (PLR) is a well-founded discriminative classifier with long roots in the history of statistics. Speech classification with PLR is possible with an appropriate choice of map from the space of feature vector sequences into the Euclidean space. In this talk, one such map is presented, namely, the one that maps into vectors consisting of log-likelihoods computed from a set of hidden Markov models (HMMs). The use of this map in PLR leads to a powerful discriminative classifier that naturally handles the sequential data arising in speech classification. In the training phase, the HMM parameters and the regression parameters are jointly estimated by maximizing a penalized likelihood. The proposed approach is shown to be a generalization of conditional maximum likelihood (CML) and maximum mutual information (MMI) estimation for speech classification, leading to more flexible decision boundaries and higher classification accuracy. The posterior probabilities resulting from classification with PLR allow for continuous speech recognition via N-best or lattice rescoring.

EEG-based estimation of mental fatigue by using KPCA–HMM and complexity parameters

Two complexity parameters of EEG, i.e. approximate entropy ( ApEn) and Kolmogorov complexity ( Kc) are utilized to characterize the complexity and irregularity of EEG data under the different mental fatigue states. Then the kernel principal component analysis (KPCA) and Hidden Markov Model (HMM) are combined to differentiate two mental fatigue states. The KPCA algorithm is employed to extract nonlinear features from the complexity parameters of EEG and improve the generalization performance of HMM. The investigation suggests that ApEn and Kc can effectively describe the dynamic complexity of EEG, which is strongly correlated with mental fatigue. Both complexity parameters are significantly decreased ( P < 0.005) as the mental fatigue level increases. These complexity parameters may be used as the indices of the mental fatigue level. Moreover, the joint KPCA–HMM method can effectively reduce the dimensionality of the feature vectors, accelerate the classification speed and achieve higher classification accuracy (84%) of mental fatigue. Hence KPCA–HMM could be a promising model for the estimation of mental fatigue.

Hybrid Simulated Annealing and Its Application to Optimization of Hidden Markov Models for Visual Speech Recognition

We propose a novel stochastic optimization algorithm, hybrid simulated annealing (SA), to train hidden Markov models (HMMs) for visual speech recognition. In our algorithm, SA is combined with a local optimization operator that substitutes a better solution for the current one to improve the convergence speed and the quality of solutions. We mathematically prove that the sequence of the objective values converges in probability to the global optimum in the algorithm. The algorithm is applied to train HMMs that are used as visual speech recognizers. While the popular training method of HMMs, the expectation-maximization algorithm, achieves only local optima in the parameter space, the proposed method can perform global optimization of the parameters of HMMs and thereby obtain solutions yielding improved recognition performance. The superiority of the proposed algorithm to the conventional ones is demonstrated via isolated word recognition experiments.

A MACHINE LEARNING FRAMEWORK FOR REAL-TIME TRAFFIC DENSITY DETECTION

Traffic flow information can be employed in an intelligent transportation system to detect and manage traffic congestion. One of the key elements in determining the traffic flow information is traffic density estimation. The goal of traffic density estimation is to determine the density of vehicles on a given road from loop detectors, traffic radars, or surveillance cameras. However, due to the inflexibility of deploying loop detectors and traffic radars, there is a growing trend of using video-content-understanding technique to determine the traffic flow from a surveillance camera. But difficulties arise when attempting to do this in real-time under changing illumination and weather conditions as well as heavy traffic congestions. In this paper, we attempt to address the problem of real-time traffic density estimation by using a stochastic model called Hidden Markov Models (HMM) to probabilistically determine the traffic density state. Choosing a good set of model parameters for HMMs has a significant impact on the accuracy of traffic density estimation. Thus, we propose a novel feature extraction scheme to represent traffic density, and a novel approach to initialize and construct the HMMs by using an unsupervised clustering technique called AutoClass. We show through extensive experiments that our proposed real-time algorithm achieves an average traffic density estimation accuracy of 96.6% over various different illumination and weather conditions.

Joint acoustic and language modeling for speech recognition

In a traditional model of speech recognition, acoustic and linguistic information sources are assumed independent of each other. Parameters of hidden Markov model (HMM) and n-gram are separately estimated for maximum a posteriori classification. However, the speech features and lexical words are inherently correlated in natural language. Lacking combination of these models leads to some inefficiencies. This paper reports on the joint acoustic and linguistic modeling for speech recognition by using the acoustic evidence in estimation of the linguistic model parameters, and vice versa, according to the maximum entropy (ME) principle. The discriminative ME (DME) models are exploited by using features from competing sentences. Moreover, a mutual ME (MME) model is built for sentence posterior probability, which is maximized to estimate the model parameters by characterizing the dependence between acoustic and linguistic features. The N-best Viterbi approximation is presented in implementing DME and MME models. Additionally, the new models are incorporated with the high-order feature statistics and word regularities. In the experiments, the proposed methods increase the sentence posterior probability or model separation. Recognition errors are significantly reduced in comparison with separate HMM and n-gram model estimations from 32.2% to 27.4% using the MATBN corpus and from 5.4% to 4.8% using the WSJ corpus (5K condition).

Extracting kinetics information from single-molecule fluorescence resonance energy transfer data using hidden markov models.

Hidden Markov models (HMM) have been proposed as a method of analysis for noisy single-molecule fluorescence resonance energy transfer (SM FRET) data. However, there are practical and fundamental limits in applying HMM to SM FRET data due to the short photobleaching lifetimes of fluorophores and the limited time resolution of detection devices. The fast photobleaching fluorophores yield short SM FRET time traces, and the limited detection time resolution generates abnormal FRET values, which result in systematic underestimation of kinetic rates. In this work, a HMM algorithm is implemented to optimize one set of HMM parameters with multiple short SM FRET traces. The FRET efficiency distribution function for the HMM optimization was modified to accommodate the abnormal FRET values resulting from limited detection time resolution. Computer simulations reveal that one set of HMM parameters is optimized successfully using multiple short SM FRET traces and that the degree of the kinetic rate underestimation is reduced by using the proposed modified FRET efficiency distribution. In conclusion, it is demonstrated that HMM can be used to reproducibly analyze short SM FRET time traces.

OHMM: a Hidden Markov Model accurately predicting the occupancy of a transcription factor with a self-overlapping binding motif

BackgroundDNA sequence binding motifs for several important transcription factors happen to be self-overlapping. Many of the current regulatory site identification methods do not explicitly take into account the overlapping sites. Moreover, most methods use arbitrary thresholds and fail to provide a biophysical interpretation of statistical quantities. In addition, commonly used approaches do not include the location of a site with respect to the transcription start site (TSS) in an integrated probabilistic framework while identifying sites. Ignoring these features can lead to inaccurate predictions as well as incorrect design and interpretation of experimental results.ResultsWe have developed a tool based on a Hidden Markov Model (HMM) that identifies binding location of transcription factors with preference for self-overlapping DNA motifs by combining the effects of their alternative binding modes. Interpreting HMM parameters as biophysical quantities, this method uses the occupancy probability of a transcription factor on a DNA sequence as the discriminant function, earning the algorithm the name OHMM: Occupancy via Hidden Markov Model. OHMM learns the classification threshold by training emission probabilities using unaligned sequences containing known sites and estimating transition probabilities to reflect site density in all promoters in a genome. While identifying sites, it adjusts parameters to model site density changing with the distance from the transcription start site. Moreover, it provides guidance for designing padding sequences in gel shift experiments. In the context of binding sites to transcription factor NF-κB, we find that the occupancy probability predicted by OHMM correlates well with the binding affinity in gel shift experiments. High evolutionary conservation scores and enrichment in experimentally verified regulated genes suggest that NF-κB binding sites predicted by our method are likely to be functional.ConclusionOur method deals specifically with identifying locations with multiple overlapping binding sites by computing the local occupancy of the transcription factor. Moreover, considering OHMM as a biophysical model allows us to learn the classification threshold in a principled manner. Another feature of OHMM is that we allow transition probabilities to change with location relative to the TSS. OHMM could be used to predict physical occupancy, and provides guidance for proper design of gel-shift experiments. Based upon our predictions, new insights into NF-κB function and regulation and possible new biological roles of NF-κB were uncovered.

TechWare: HMM-based speech synthesis resources [Best of the Web

This paper focuses on hidden Markov model (HMM)- based speech synthesis, which has recently been demonstrated to be very effective in generating high-quality speech and started dominating speech synthesis research. The attractive point of this approach is that the synthesized speech can easily be modified by transforming HMM parameters with a small amount of speech data. Thus it is very useful for constructing speech synthesizers with various voice characteristics, speaking styles, and emotions.

A program-based anomaly intrusion detection scheme using multiple detection engines and fuzzy inference

In this paper, a hybrid anomaly intrusion detection scheme using program system calls is proposed. In this scheme, a hidden Markov model (HMM) detection engine and a normal database detection engine have been combined to utilise their respective advantages. A fuzzy-based inference mechanism is used to infer a soft boundary between anomalous and normal behaviour, which is otherwise very difficult to determine when they overlap or are very close. To address the challenging issue of high cost in HMM training, an incremental HMM training with optimal initialization of HMM parameters is suggested. Experimental results show that the proposed fuzzy-based detection scheme can reduce false positive alarms by 48%, compared to the single normal database detection scheme. Our HMM incremental training with the optimal initialization produced a significant improvement in terms of training time and storage as well. The HMM training time was reduced by four times and the memory requirement was also reduced significantly.

Accurate Detection of Recombinant Breakpoints in Whole-Genome Alignments

We propose a novel method for detecting sites of molecular recombination in multiple alignments. Our approach is a compromise between previous extremes of computationally prohibitive but mathematically rigorous methods and imprecise heuristic methods. Using a combined algorithm for estimating tree structure and hidden Markov model parameters, our program detects changes in phylogenetic tree topology over a multiple sequence alignment. We evaluate our method on benchmark datasets from previous studies on two recombinant pathogens, Neisseria and HIV-1, as well as simulated data. We show that we are not only able to detect recombinant regions of vastly different sizes but also the location of breakpoints with great accuracy. We show that our method does well inferring recombination breakpoints while at the same time maintaining practicality for larger datasets. In all cases, we confirm the breakpoint predictions of previous studies, and in many cases we offer novel predictions.

Finding genes in Schistosoma japonicum: annotating novel genomes with help of extrinsic evidence

We have developed a novel method for estimating the parameters of hidden Markov models for gene finding in newly sequenced species. Our approach does not rely on curated training data sets, but instead uses extrinsic evidence (including paired-end ditags that have not been used in gene finding previously) and iterative training. This new method is particularly suitable for annotation of species with large evolutionary distance to the closest annotated species. We have used our approach to produce an initial annotation of more than 16 000 genes in the newly sequenced Schistosoma japonicum draft genome. We established the high quality of our predictions by comparison to full-length cDNAs (withdrawn from the extrinsic evidence) and to CEGMA core genes. We also evaluated the effectiveness of the new training procedure on Caenorhabditis elegans genome. ExonHunter and the newest parametric files for S. japonicum genome are available for download at www.bioinformatics.uwaterloo.ca/downloads/exonhunter

Using Hidden Markov Models in Vehicular Crash Detection

This paper presents a system for automotive crash detection based on hidden Markov models (HMMs). The crash pulse library used for training comprises a number of head-on and oblique angular crash events involving rigid and offset deformable barriers. Stochastic distribution characteristics of crash signals are validated to ensure conformity with the modeling assumptions. This step is achieved by analyzing the quantile-quantile (Q-Q) plot of actual pulses against the assumed bivariate Gaussian distribution. HMM parameters are next induced by utilizing the expectation-maximization (EM) procedure. The search for an optimal crash pulse model proceeds using the ldquoleave-one-outrdquo technique with the exploration encompassing both fully connected and left-right HMM topologies. The optimal crash pulse architecture is identified as a seven-state left-right HMM with its parameters computed using real and computer-aided engineering (CAE)-generated data. The system described in the paper has the following advantages. First, it is fast and can accurately detect crashes within 6 ms. Second, its implementation is simple and uses only two sensors, which makes it less vulnerable to failures, considering the overall simplicity of interconnects. Finally, it represents a general and modularized algorithm that can be adapted to any vehicle line and readily extended to use additional sensors.

Application of Improved HMM Algorithm in Slag Detection System

To solve the problems of ladle slag detection system (SDS), such as high cost, short service life, and inconvenient maintenance, a new SDS realization method based on hidden Markov model (HMM) was put forward. The physical process of continuous casting was analyzed, and vibration signal was considered as the main detecting signal according to the difference in shock vibration generated by molten steel and slag because of their difference in density. Automatic control experiment platform oriented to SDS was established, and vibration sensor was installed far away from molten steel, which could solve the problem of easy power consumption by the sensor. The combination of vector quantization technology with learning process parameters of HMM was optimized, and its revaluation formula was revised to enhance its recognition effectiveness. Industrial field experiments proved that this system requires low cost and little rebuilding for current devices, and its slag detection rate can exceed 95%.

A new approach based on a discrete hidden Markov model using the Rocchio algorithm for the diagnosis of heart valve diseases

Abstract: Application of the Doppler ultrasound technique in the diagnosis of heart diseases has been increasing in the last decade since it is non‐invasive, practicable and reliable. In this study, a new approach based on the discrete hidden Markov model (DHMM) is proposed for the diagnosis of heart valve disorders. For the calculation of hidden Markov model (HMM) parameters according to the maximum likelihood approach, HMM parameters belonging to each class are calculated by using training samples that only belong to their own classes. In order to calculate the parameters of DHMMs, not only training samples of the related class but also training samples of other classes are included in the calculation. Therefore HMM parameters that reflect a class's characteristics are more represented than other class parameters. For this aim, the approach was to use a hybrid method by adapting the Rocchio algorithm. The proposed system was used in the classification of the Doppler signals obtained from aortic and mitral heart valves of 215 subjects. The performance of this classification approach was compared with the classification performances in previous studies which used the same data set and the efficiency of the new approach was tested. The total classification accuracy of the proposed approach (95.12%) is higher than the total accuracy rate of standard DHMM (94.31%), continuous HMM (93.5%) and support vector machine (92.67%) classifiers employed in our previous studies and comparable with the performance levels of classifications using artificial neural networks (95.12%) and fuzzy‐C‐means/CHMM (95.12%).

Recognizing Visual Focus of Attention From Head Pose in Natural Meetings

We address the problem of recognizing the visual focus of attention (VFOA) of meeting participants based on their head pose. To this end, the head pose observations are modeled using a Gaussian mixture model (GMM) or a hidden Markov model (HMM) whose hidden states correspond to the VFOA. The novelties of this paper are threefold. First, contrary to previous studies on the topic, in our setup, the potential VFOA of a person is not restricted to other participants only. It includes environmental targets as well (a table and a projection screen), which increases the complexity of the task, with more VFOA targets spread in the pan as well as tilt gaze space. Second, we propose a geometric model to set the GMM or HMM parameters by exploiting results from cognitive science on saccadic eye motion, which allows the prediction of the head pose given a gaze target. Third, an unsupervised parameter adaptation step not using any labeled data is proposed, which accounts for the specific gazing behavior of each participant. Using a publicly available corpus of eight meetings featuring four persons, we analyze the above methods by evaluating, through objective performance measures, the recognition of the VFOA from head pose information obtained either using a magnetic sensor device or a vision-based tracking system. The results clearly show that in such complex but realistic situations, the VFOA recognition performance is highly dependent on how well the visual targets are separated for a given meeting participant. In addition, the results show that the use of a geometric model with unsupervised adaptation achieves better results than the use of training data to set the HMM parameters.

Content-Adaptive Robust Image Watermarking with Posterior HMM-Based Detector

Robustness and invisibility are two contrary constraints for robust invisible watermarking. Instead of the conventional strategy with human visual system (HVS) model, this paper presents a content-adaptive approach to further optimize the constraint between them. To reach this target, the entropy-based and integrated HVS (IHVS) based measures are constructed so as to adaptively choose the suitable components for watermark insertion and detection. Such a kind of scheme potentially gives rise to synchronization problem between the encoder and decoder under the framework of blind watermarking, which is then solved by incorporating the repeat-accumulate (RA) code with erasure and error correction. Moreover, a new hidden Markov model (HMM) based detector in wavelet domain is introduced to reduce the computation complexity and is further developed into a posterior one to avoid the transmission of HMM parameters with only a little sacrifice of detection performance. Experimental results show that the proposed algorithm can obtain considerable improvement in robustness performance with the same distortion as the traditional one.