HMM-based Method Research Articles

Hidden Markov Models based intelligent health assessment and fault diagnosis of rolling element bearings.

Hidden Markov Models (HMMs) have become an immensely popular tool for health assessment and fault diagnosis of rolling element bearings. The advantages of an HMM include its simplicity, robustness, and interpretability, while the generalization capability of the model still needs to be enhanced. The Dempster-Shafer theory of evidence can be used to conduct a comprehensive evaluation, and Stacking provides a novel training strategy. Therefore, the HMM-based fusion method and ensemble learning method are proposed to increase the credibility of quantitative analysis and optimize classifiers respectively. Firstly, vibration signals captured from bearings are decomposed into intrinsic mode functions (IMFs) using ensemble empirical mode decomposition (EEMD), and then the Hilbert envelope spectra of main components are obtained; Secondly, multi-domain features are extracted as model input from preprocessed signals; Finally, HMM-based intelligent health assessment framework and fault diagnosis framework are established. In this work, the life cycle health assessment modeling is performed using a few training samples, the bearing degradation state is quantitatively evaluated, normal and abnormal samples are effectively distinguished, and the accuracy of fault diagnosis is significantly improved.

Auto Insurance Pricing Using Telematics Data: Application of a Hidden Markov Model

This study develops a hidden Markov model (HMM)-based clustering framework to predict auto insurance losses using driving characteristics extracted from telematics data. Through a simulation experiment based on a proprietary telematics dataset, we show that HMM can effectively classify driving trips using model-implied hidden states, and HMM-based pricing methods provide better predictive power measured by deviance statistics. Importantly, the proposed framework not only enables us to price usage-based insurances at a granular level but is also viable for estimating long-term insurance losses utilizing the limiting properties of HMM.

Deepdefense: annotation of immune systems in prokaryotes using deep learning.

Due to a constant evolutionary arms race, archaea and bacteria have evolved an abundance and diversity of immune responses to protect themselves against phages. Since the discovery and application of CRISPR-Cas adaptive immune systems, numerous novel candidates for immune systems have been identified. Previous approaches to identifying these new immune systems rely on hidden Markov model (HMM)-based homolog searches or use labor-intensive and costly wet-lab experiments. To aid in finding and classifying immune systems genomes, we use machine learning to classify already known immune system proteins and discover potential candidates in the genome. Neural networks have shown promising results in classifying and predicting protein functionality in recent years. However, these methods often operate under the closed-world assumption, where it is presumed that all potential outcomes or classes are already known and included in the training dataset. This assumption does not always hold true in real-world scenarios, such as in genomics, where new samples can emerge that were not previously accounted for in the training phase. In this work, we explore neural networks for immune protein classification, deal with different methods for rejecting unrelated proteins in a genome-wide search, and establish a benchmark. Then, we optimize our approach for accuracy. Based on this, we develop an algorithm called Deepdefense to predict immune cassette classes based on a genome. This design facilitates the differentiation between immune system-related and unrelated proteins by analyzing variations in model-predicted confidence values, aiding in the identification of both known and potentially novel immune system proteins. Finally, we test our approach for detecting immune systems in the genome against an HMM-based method. Deepdefense can automatically detect genes and define cassette annotations and classifications using 2 model classifications. This is achieved by creating an optimized deep learning model to annotate immune systems, in combination with calibration methods, and a second model to enable the scanning of an entire genome.

Tractable Maximum Likelihood Estimation for Latent Structure Influence Models With Applications to EEG & ECoG Processing

Brain signals are nonlinear and nonstationary time series, which provide information about spatiotemporal patterns of electrical activity in the brain. CHMMs are suitable tools for modeling multi-channel time-series dependent on both time and space, but state-space parameters grow exponentially with the number of channels. To cope with this limitation, we consider the influence model as the interaction of hidden Markov chains called Latent Structure Influence Models (LSIMs). LSIMs are capable of detecting nonlinearity and nonstationarity, making them well suited for multi-channel brain signals. We apply LSIMs to capture the spatial and temporal dynamics in multi-channel EEG/ECoG signals. The current manuscript extends the scope of the re-estimation algorithm from HMMs to LSIMs. We prove that the re-estimation algorithm of LSIMs will converge to stationary points corresponding to Kullback-Leibler divergence. We prove convergence by developing a new auxiliary function using the influence model and a mixture of strictly log-concave or elliptically symmetric densities. The theories that support this proof are derived from previous studies by Baum, Liporace, Dempster, and Juang. We then develop a closed-form expression for re-estimation formulas using tractable marginal forward-backward parameters defined in our previous study. Simulated datasets and EEG/ECoG recordings confirm the practical convergence of the derived re-estimation formulas. We also study the use of LSIMs for modeling and classification on simulated and real EEG/ECoG datasets. Based on AIC and BIC, LSIMs perform better than HMMs and CHMMs in modeling embedded Lorenz systems and ECoG recordings. LSIMs are more reliable and better classifiers than HMMs, SVMs and CHMMs in 2-class simulated CHMMs. EEG biometric verification results indicate that the LSIM-based method improves the area under curve (AUC) values by about 6.8% and decreases the standard deviation of AUC values from 5.4% to 3.3% compared to the existing HMM-based method for all conditions on the BED dataset.

HMM-based gesture recognition for eye-swipe typing

Eye-swipe typing requires users to simply look in the vicinity of the keys forming the desired word, similar to swiping their finger on a touch screen device. This work presents a novel HMM-based approach for swipe typing which can be used with any eye movement recording technique. In this study, three different HMM-based methods are developed, tested, and compared to the state-of-the-art performing LCSMapping algorithm with eye movement data acquired from the electrooculogram (EOG). When tested by ten subjects, the top performing Key-based HMM yielded an average top-five rate of 91.00±6.63% in comparison to an average top-five rate of 76.00±12.61% achieved by the LCSMapping algorithm. This study also presents the analysis of a real-time eye controlled swipe typing application which yielded an average typing speed of 12.85±2.14 WPM in contrast to an average typing speed of 3.83±1.24 WPM achieved using a dwell-based alternative.

Detection of Stealthy Jamming for UAV-Assisted Wireless Communications: An HMM-Based Method

Due to the high mobility, low cost and high robustness of line-of-sight (LoS) channels, unmanned aerial vehicles (UAVs) have begun to play an important role in assisting wireless communications. However, the broadcasting nature of wireless communication networks makes the electromagnetic spectrum vulnerable to jamming attacks. To ensure communication security, this paper investigates the jamming detection issue for UAV-assisted wireless communications. Different from the existing works, we consider detection of stealthy jamming with no prior knowledge of legitimate users or channel statistics, which makes the detection more challenging. To solve this problem, we design a hidden Markov model (HMM) based jamming detection (HBJD) method. First, we process the received signals with a sliding window to calculate the logarithmic received energy and use HMM to model the signal transmission under a jamming attack. Specifically, the spectrum state and logarithmic received energy are modeled as the hidden state and observable variable of HMM. Then, the Expectation-Maximization (EM) algorithm is applied to estimate the parameters of HMM. With the estimated parameters, the spectrum state of each logarithmic received energy sample can be decided according to the maximum posterior probability (MAP) criterion. Finally, we design the test statistics and derive the threshold based on the estimated HMM parameters for the final decision. Simulation results demonstrate the superiority of the proposed solution for the detection of stealthy jamming without prior knowledge of legitimate users or the channel statistics.

An Efficient Hidden Markov Model with Periodic Recurrent Neural Network Observer for Music Beat Tracking

In music information retrieval (MIR), beat tracking is one of the most fundamental tasks. To obtain this critical component from rhythmic music signals, a previous beat tracking system of hidden Markov model (HMM) with a recurrent neural network (RNN) observer was developed. Although the frequency of music beat is quite stable, existing HMM based methods do not take this feature into account. Accordingly, most of hidden states in these HMM-based methods are redundant, which is a disadvantage for time efficiency. In this paper, we proposed an efficient HMM using hidden states by exploiting the frequency contents of the neural network’s observation with Fourier transform, which extremely reduces the computational complexity. Observers that previous works used, such as bi-directional recurrent neural network (Bi-RNN) and temporal convolutional network (TCN), cannot perceive the frequency of music beat. To obtain more reliable frequencies from music, a periodic recurrent neural network (PRNN) based on attention mechanism is proposed as well, which is used as the observer in HMM. Experimental results on open source music datasets, such as GTZAN, Hainsworth, SMC, and Ballroom, show that our efficient HMM with PRNN is competitive to the state-of-the-art methods and has lower computational cost.

A solution for co-frequency and low SNR problems in heart rate estimation based on photoplethysmography signals.

In order to realize high-accuracy heart rate (HR) estimation based on photoplethysmography (PPG) under the scenes of low signal-to-noise ratio (SNR) and co-frequency caused by motion artifacts (MAs), this paper presents a novel framework integrating two-stage variational mode decomposition (VMD) denoising method, noise compensation technology, and hidden Markov model (HMM)-based tracking algorithm. The two-stage VMD denoising method is designed to separate the HR signal from MA under low SNR scene. The noise compensation technology is applied to solve the problem of co-frequency. HMM-based HR tracking method is adopted to obtain the global optimization performance of HR estimation. The effectiveness and superiority of the proposed framework in solving problems of low SNR and co-frequency associated with motion artifacts have been verified by the HR estimation experiments carried out on three public high-SNR PPG databases (ISPC, BAMI I, BAMI II) and a self-built low-SNR database (WeData). Compared with the two classical frameworks namely joint sparse spectrum reconstruction (JOSS) and convolutional neural network-long short-term memory network (CNN-LSTM), the proposed framework obtains the lowest HR estimation errors (0.94 beats per minute (BPM) and 1.81 BPM respectively) on both BAMI 2 with the highest SNR (0.40dB) and WeData with the lowest SNR (- 9.07dB). For the low-SNR database Wedata, the average absolute error (AAE) decreases by more than 21 BPM. The research result of this study provides a solution for the realization of high-accuracy PPG-based HR estimation in exercise scenarios.

Industrial load disaggregation based on Hidden Markov Models

Non-intrusive load monitoring (NILM) technology can identify the energy consumed by each individual device from the aggregate electricity measurements, contributing to energy saving and emission reduction. NILM methods have been widely studied for residential scenarios, where Hidden Markov Model (HMM) and its variants are popular. Although NILM methods have been proposed also for industrial scenarios, such methods applicable on both high- and low-consuming industrial scenarios are lacking. In this paper, two HMM-based methods are proposed for disaggregating industrial loads, where extra reactive power observation and state duration distribution are exploited. The graphical structure of the proposed models is illustrated. In the experiments, the two proposed industrial load disaggregation methods are benchmarked with three state-of-the-art industrial load disaggregation methods. All benchmarks are validated on two real industrial datasets sampled at 1 Hz and 1/5 Hz, respectively, and evaluated by two metrics. A comparison of the disaggregation results for all industrial devices is demonstrated and discussed, showing improvement for using extra reactive power observation and state duration distribution.

The Classification of Heartbeats from Two-Channel ECG Signals Using Layered Hidden Markov Model

Purpose: Cardiac arrhythmia is one of the most common heart diseases that can have serious consequences. Thus, heartbeat arrhythmias classification is very important to help diagnose and treat. To develop the automatic classification of heartbeats, recent advances in signal processing can be employed. The Hidden Markov Model (HMM) is a powerful statistical tool with the ability to learn different dynamics of the real time-series such as cardiac signals. Materials and Methods: In this study, a hierarchy of HMMs named Layered HMM (LHMM) was presented to classify heartbeats from the two-channel electrocardiograms. For training in the first layer, the morphology of the heartbeats was used as observations, while observations in the second layer were the inference results of the first layer. The performance of the proposed LHMM was evaluated in classifying three types of heartbeat arrhythmias (Atrial premature beats (A), Escape beats (E), Left bundle branch block beats (L)) using fifteen records of the MIT-BIH arrhythmia database. Furthermore, the obtained results of the proposed model were compared with other HMM generalizations. Results: The best average accuracy was achieved 97.10±1.63%. The best sensitivity of 96.8±1.24%, 98.85±0.52%, and 95.64±1.41 were obtained for A, E, and L, respectively. Furthermore, the results of the proposed method were better than other HMM generalizations. Conclusion: Extracting information from time-series dynamics by HMM-based methods has good classification results. The proposed model shows that applying a two-layered HMM can lead to better extraction of information from the observations; therefore, the classification performance of cardiac arrhythmias has been improved using LHMM.

Sentiment analysis using novel and interpretable architectures of Hidden Markov Models

Sentiment analysis aims to formulate automated methods to recognize sentiments, opinions and emotions in text. Many methods and approaches have been utilized but most of them do not disclose the way that decisions are made and operate as black boxes. Hidden Markov Models (HMMs) constitute a quite suitable and potent approach for sentiment analysis, since they can utilize the sequential nature of the text, a piece of information that machine learning methods cannot properly utilize. However, little attention has been paid to formulating and applying sophisticated HMM-based methods and advanced training approaches for accomplishing sentiment analysis tasks. In this article, we introduce novel, interpretable HMM-based methods for recognizing sentiments in text and we examine their performance under various architectures, training methods, orders and ensembles. The introduced models possess interpretability, they can indicate the sentimental parts of a sentence and illustrate the way that the overall sentiment evolves from the start to the end of it. A concrete experimental study is conducted and the results show that the introduced HMMs methods and the training approaches are quite competitive with machine learning methods and that they outperform traditional HMMs. Furthermore, the designed HMMs methods possess great interpretability and can be an efficient approach for sentiment analysis.

Guided wave-hidden Markov model for on-line crack evaluation of a full-scale aircraft

Structural Health Monitoring (SHM) has been embraced as an effective method in the aerospace industry. However, one of the main problems hindering SHM for practical usages is the reliable evaluation of damages under in-service conditions that introduce various uncertainties and difficulties for effectively interpreting SHM signals. The Hidden Markov Model (HMM)-based method has been proved to be potential for improving the reliability of damage evaluation under in-service conditions since it can explicitly model the uncertainties during damage state transition and SHM process. Nonetheless, traditional HMM-based damage evaluation methods need sufficient prior data of several discrete damage levels for training. These prior data come from historical experiments or simulations, which may not be sufficient for a new target structure. In this paper, a Guided Wave (GW)-health HMM damage evaluation method with an on-line calibration strategy is proposed to realize quantitative evaluation of damage propagation under time-varying conditions. At the off-line stage, a health HMM is constructed with the prior GW-SHM data collected under the structural healthy state. The likelihood probability of the on-line monitored GW-SHM feature sequence belonging to the prior health HMM is calculated for detecting the damage initiation. A new health-HMM is trained with the health data from the current target structure once the damage is found, replacing the prior health HMM. On this basis, a calibration strategy is conducted to calibrate the likelihood probability to the damage size for quantitative damage evaluation under time-varying conditions in real-time. Finally, the proposed method is validated on the fatigue test of a full-scale aircraft under an actual flight spectrum. The fatigue crack is reliably evaluated, and the maximum error of the evaluated crack length is 0.5 mm.

Non-intrusive load monitoring using factorial hidden markov model based on adaptive density peak clustering

With the goal of achieving carbon neutrality, the technology of Non-Intrusive Load Monitoring (NILM) has gained widespread attention as an efficient energy-saving way. Hidden Markov Model (HMM) based methods are popular in the field of NILM, yet the traditional HMM-based methods need prior knowledge of the appliance’s working states. In this paper, we propose an Adaptive Density Peak Clustering (ADPC) algorithm that could automatically determine the working states of appliance based on its power consumption. Then we combine the ADPC and Factorial Hidden Markov Model (FHMM) to create an Adaptive Density Peak Clustering-Factorial Hidden Markov Model (ADPC-FHMM), which reduces the dependence of prior information and is more applicable in real world scenarios. Case studies are conducted on two publicly available datasets, and the results show that the proposed model outperforms its counterparts on the metrics of Accuracy, F-measure and MAE.

Monitoring and Predicting Desert Locust Plague Severity in Asia–Africa Using Multisource Remote Sensing Time-Series Data

The outbreak of large-scale desert locust plague in 2020 has attracted wide attention in the world and caused serious damage to food security and livelihood of African and Asian people. Remote sensing techniques can provide indirect feedback on locust plagues, facilitating quick, and real-time monitoring of the occurrence and development of locusts, which is of great significance for ensuring national and regional food security and stability. The hidden Markov model (HMM) is a classic machine learning model that has been widely applied in the fields of time-series data mining. In this study, we aim to predict the severity of locust plague in croplands using the time-series dynamic change features extracted from remote sensing data via HMM. In addition, we assess the damages on the croplands using change detection methods by comparing the crop spectrum before and after the locust plague from two-phase (Feburary 23 and March 7, 2020) hyperspectral images covering substudy area (northern Narok, Kenya). Evaluated by the ground truth data, the OA of predicted results of the plague severity in April, May, June, and July are 0.78, 0.71, 0.74, and 0.72, respectively. The land cover classification OA of the substudy area of the two-phase images are 97.45 and 96.14. Our study demonstrates the validity of the HMM-based method using the remote sensing time-series data to predict locust plague and evaluate its damage. The results of the cropland change detection suggest that the damage of locusts can be quantitatively evaluated using hyperspectral images.

An Improved HMM-Based Approach for Planning Individual Routes Using Crowd Sourcing Spatiotemporal Data.

With the rapid development of LBSs (location-based services) in recent years, researchers have increasingly taken an interest in trying to make travel routes more practicable and individualized. Despite the fact that many studies have been conducted on routes using LBS data, the specific routes are deficient in dynamic scalability and the correlations between environmental constraints and personal choices have not been investigated. This paper proposes an improved HMM-based (hidden Markov model) method for planning personalized routes with crowd sourcing spatiotemporal data. It tries to integrate the dynamic public preferences, the individual interests and the physical road network space in the same spatiotemporal framework, ensuring that reasonable routes will be generated. A novel dual-layer mapping structure has been proposed to bridge the gap from brief individual preferences to specific entries of POIs (points-of-interest) inside realistic road networks. A case study on Changsha city has proven that the proposed method can not only flexibly plan people’s travel routes under different spatiotemporal backgrounds but also is close to people’s natural selection by the perception of the group.

Health status prediction of airborne systems based on transfer learning

In this paper, based on the prediction of the decay mode of the system health state, a health pattern recognition and prediction method based on transfer learning is proposed. In the context of big data, the system's healthy decline mode is summarized from the massive historical flight data, and then the research on the health status of the airborne system based on the recognition results is carried out. Firstly, this paper demonstrates the feasibility of transfer learning applied to the prediction of the health status of airborne systems. Then, a HMM-based parameter migration health state prediction method is proposed. Finally, the model is verified by the hydraulic system of a certain type of aircraft. The results show that the model can predict the time when the health state changes.

Data-Driven Detection and Classification of Regimes in Chaotic Systems Via Hidden Markov Modeling

AbstractChaotic dynamical systems are essentially nonlinear and are highly sensitive to variations in initial conditions and process parameters. Chaos may appear both in natural (e.g., heartbeat rhythms and weather fluctuations) and human-engineered (e.g., thermo-fluid, urban traffic, and stock market) systems. For prediction and control of such systems, it is often necessary to be able to distinguish between non-chaotic and chaotic behavior; several methods exist to detect the presence (or absence) of chaos, specially in noisy signals. A dynamical system may exhibit multiple chaotic regimes, and apparently, there exist no methods, reported in open literature, to classify these regimes individually. This paper demonstrates an application of standard hidden Markov modeling (HMM), which is a commonly used supervised method, as a technique to classify multiple regimes from a time series of dynamical systems, where classified regimes could be chaotic or non-chaotic. The proposed HMM-based method of regime classification has been tested using numerical data obtained from several well-known chaotic dynamical systems (e.g., Hénon, forced Duffing, Rössler, and Lorenz attractor). It is apparently well-suited to serve as a bench mark for the development of alternative data-driven methods to enhance the performance (e.g., accuracy and computational speed) of regime classification in chaotic dynamical systems.

Dialogue act based expressive speech synthesis in limited domain for the Czech language

This paper deals with expressive speech synthesis in a dialogue. Dialogue acts - discrete expressive categories - are used for expressivity description. The aim of the work is to create a procedure for development of expressive speech synthesis for a dialogue system in a limited domain. The domain is here limited to dialogues between a human and a computer on a given topic of reminiscing about personal photographs. To incorporate expressivity into synthetic speech, modifications of current algorithms used for neutral speech synthesis are made. An expressive speech corpus is recorded, annotated using a predefined set of dialogue acts, and its acoustic analysis is performed. Unit selection and HMM-based methods are used to synthesize expressive speech, and an evaluation using listening tests is presented. The listeners asses two basic aspects of synthetic expressive speech for isolated utterances: speech quality and expressivity perception. The evaluation is also performed for utterances in a dialogue to asses appropriateness of synthetic expressive speech. It can be concluded that synthetic expressive speech is rated positively even though it is of worse quality when comparing with the neutral speech synthesis. However, synthetic expressive speech is able to transmit expressivity to listeners and to improve the naturalness of the synthetic speech.

Evaluation of a dynamic classification method for multimodal ambiguities based on Hidden Markov Models

The wide interest in ambiguities is because it represents uncertainty but also a fundamental item of discussion for who is interested in the interpretation of languages also considering that it is functional for communicative purposes. This paper addresses ambiguity issues in terms of identification of the meaningful features of multimodal ambiguities and it evaluates a dynamic HMM-based classification method that is able to classify ambiguities by learning, and progressively adapting the model to the evolution of the interaction, refining the existing classes, or identifying new ones. The comparative evaluation of the considered method of the considered method with other surveyed methods demonstrates an improvement considering the performance evaluation measures.

A hidden Markov model for analyzing eye-tracking of moving objects : Case study in a sustained attention paradigm.

Eye-tracking provides an opportunity to generate and analyze high-density data relevant to understanding cognition. However, while events in the real world are often dynamic, eye-tracking paradigms are typically limited to assessing gaze toward static objects. In this study, we propose a generative framework, based on a hidden Markov model (HMM), for using eye-tracking data to analyze behavior in the context of multiple moving objects of interest. We apply this framework to analyze data from a recent visual object tracking task paradigm, TrackIt, for studying selective sustained attention in children. Within this paradigm, we present two validation experiments to show that the HMM provides a viable approach to studying eye-tracking data with moving stimuli, and to illustrate the benefits of the HMM approach over some more naive possible approaches. The first experiment utilizes a novel 'supervised' variant of TrackIt, while the second compares directly with judgments made by human coders using data from the original TrackIt task. Our results suggest that the HMM-based method provides a robust analysis of eye-tracking data with moving stimuli, both for adults and for children as young as 3.5-6 years old.