Layered Hidden Markov Model Research Articles

Automatic detection of respiratory events during sleep from Polysomnography data using Layered Hidden Markov Model

Objective. Sleep apnea is a serious respiratory disorder, which is associated with increased risk factors for cardiovascular disease. Many studies in recent years have been focused on automatic detection of sleep apnea from polysomnography (PSG) recordings, however, detection of subtle respiratory events named Respiratory Event Related Arousals (RERAs) that do not meet the criteria for apnea or hypopnea is still challenging. The objective of this study was to develop automatic detection of sleep apnea based on Hidden Markov Models (HMMs) which are probabilistic models with the ability to learn different dynamics of the real time-series such as clinical recordings. Approach. In this study, a hierarchy of HMMs named Layered HMM was presented to detect respiratory events from PSG recordings. The recordings of 210 PSGs from Massachusetts General Hospital’s database were used for this study. To develop detection algorithms, extracted feature signals from airflow, movements over the chest and abdomen, and oxygen saturation in blood (SaO2) were chosen as observations. The respiratory disturbance index (RDI) was estimated as the number of apneas, hypopneas, and RERAs per hour of sleep. Main results. The best F1 score of the event by event detection algorithm was between 0.22 ± 0.16 and 0.70 ± 0.08 for different groups of sleep apnea severity. There was a strong correlation between the estimated and the PSG-derived RDI (R 2 = 0.91, p < 0.0001). The best recall of RERA detection was achieved 0.45 ± 0.27. Significance. The results showed that the layered structure can improve the performance of the detection of respiratory events during sleep.

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.

Detection of Apnea Bradycardia from ECG Signals of Preterm Infants Using Layered Hidden Markov Model

Apnea-bradycardia (AB) is a common complication in prematurely born infants, which is associated with reduced survival and neurodevelopmental outcomes. Thus, early detection or predication of AB episodes is critical for initiating preventive interventions. To develop automatic real-time operating systems for early detection of AB, recent advances in signal processing can be employed. Hidden Markov Models (HMM) are probabilistic models with the ability of learning different dynamics of the real time-series such as clinical recordings. In this study, a hierarchy of HMMs named as layered HMM was presented to detect AB episodes from pre-processed single-channel Electrocardiography (ECG). For training the hierarchical structure, RR interval, and width of QRS complex were extracted from ECG as observations. The recordings of 32 premature infants with median 31.2 (29.7, 31.9) weeks of gestation were used for this study. The performance of the proposed layered HMM was evaluated in detecting AB. The best average accuracy of 97.14 ± 0.31% with detection delay of -5.05 ± 0.41s was achieved. The results show that layered structure can improve the performance of the detection system in early detecting of AB episodes. Such system can be incorporated for more robust long-term monitoring of preterm infants.

Facial expression recognition using geometric features and modified hidden Markov model

This work proposes a geometric feature-based descriptor for efficient Facial Expression Recognition (FER) that can be used for better human-computer interaction. Although lots of research has been focused on descriptor-based FER still different problems have to be solved regarding noise, recognition rate, time and error rates. The Japanese Female Facial Expression (JAFFE) data sets help to make FER more reliable and efficient as pixels are distributed uniformly. The proposed system introduces novel geometric features to extract important features from the images and layered Hidden Markov Model (HMM) as a classifier. The layered HMM is used to recognised seven facial expressions i.e., anger, disgust, fear, joy, sadness, surprise and neutral. The proposed framework is compared with existing systems where the proposed framework proves its superiority with the recognition rate of 84.7% with the others 85%. Our proposed framework is also tested in terms of recognition rates, processing time and error rates and found its best accuracy with the other existing systems.

Predicting Task Intent From Surface Electromyography Using Layered Hidden Markov Models

Human-robot interaction faces the challenge of designing and modeling tightly coupled and effectively controlled human-machine systems. This letter describes a method to learn human operator's performance characteristics from surface electromyography measurements to predict their intentions during task operations. For the first time, a layered hidden Markov model (LHMM) is successfully used with physiological data from cocontracting arm muscles to achieve accurate intent prediction. Furthermore, optimal model parameters and high-performing feature sets are identified and prediction accuracy at various time horizons calculated. The LHMM outperformed various other classification methods, including naive Bayes and support vector machine, ultimately achieving 82% accuracy in predicting the next 50 ms window of intent and maintaining 60% accuracy even after one second. These results hold the promise of improving robots' internal model of their human partners, which could increase the safety and productivity of human-robot teams in the factories of the future.

A Hybrid Model for Concurrent Interaction Recognition from Videos

&lt;p&gt;Human behavior analysis plays an important role in understanding the high-level human activities from surveillance videos. Human behavior has been identified using gestures, postures, actions, interactions and multiple activities of humans. This paper has been analyzed by identifying concurrent interactions, that takes place between multiple peoples. In order to capture the concurrency, a hybrid model has been designed with the combination of Layered Hidden Markov Model (LHMM) and Coupled HMM (CHMM). The model has three layers called as pose layer, action layer and interaction layer, in which pose and action of the single person has been defined in the layered model and the interaction of two persons or multiple persons are defined using CHMM. This hybrid model reduces the training parameters and the temporal correlations over the frames are maintained. The spatial and temporal information are extracted and from the body part attributes, the simple human actions as well as concurrent actions/interactions are predicted. In addition, we further evaluated the results on various datasets also, for analyzing the concurrent interaction between the peoples.&lt;/p&gt;

A Real-Time, Multiview Fall Detection System: A LHMM-Based Approach

Automatic detection of a falling person in video sequences has interesting applications in video-surveillance and is an important part of future pervasive home monitoring systems. In this paper, we propose a multiview approach to achieve this goal, where motion is modeled using a layered hidden Markov model (LHMM). The posture classification is performed by a fusion unit, merging the decision provided by the independently processing cameras in a fuzzy logic context. In each view, the fall detection is optimized in a given plane by performing a metric image rectification, making it possible to extract simple and robust features, and being convenient for real-time purpose. A theoretical analysis of the chosen descriptor enables us to define the optimal camera placement for detecting people falling in unspecified situations, and we prove that two cameras are sufficient in practice. Regarding event detection, the LHMM offers a principle way for solving the inference problem. Moreover, the hierarchical architecture decouples the motion analysis into different temporal granularity levels, making the algorithm able to detect very sudden changes, and robust to low-level steps errors.

Motion intention recognition in robot assisted applications

Acquiring, representing and modelling human skills is one of the key research areas in teleoperation, programming-by-demonstration and human-machine collaborative settings. The problems are challenging mainly because of the lack of a general mathematical model to describe human skills. One of the common approaches is to divide the task that the operator is executing into several subtasks or low-level subsystems in order to provide manageable modelling. In this paper we consider the use of a Layered Hidden Markov Model (LHMM) to model human skills. We evaluate a gesteme classifier that classifies motions into basic action-primitives, or gestemes. The gesteme classifiers are then used in a LHMM to model a teleoperated task. The proposed methodology uses three different HMM models at the gesteme level: one-dimensional HMM, multi-dimensional HMM and multi-dimensional HMM with Fourier transform. The online and off-line classification performance of these three models is evaluated with respect to the number of gestemes, the influence of the number of training samples, the effect of noise and the effect of the number of observation symbols. We also apply the LHMM to data recorded during the execution of a trajectory tracking task in 2D and 3D with a mobile manipulator in order to provide qualitative as well as quantitative results for the proposed approach. The results indicate that the LHMM is suitable for modelling teleoperative trajectory-tracking tasks and that the difference in classification performance between one and multidimensional HMMs for gesteme classification is small. It can also be seen that the LHMM is robust with respect to misclassifications in the underlying gesteme classifiers.

Selective perception policies for guiding sensing and computation in multimodal systems: A comparative analysis

Intensive computations required for sensing and processing perceptual information can impose significant burdens on personal computer systems. We explore the use of value of information to guide sensing and analysis in automated behavior recognition systems, and highlight the role of such computations as a formal foundation for selective attention. We examine several different policies for selective perception in SEER, a multimodal system for recognizing office activity that relies on a layered Hidden Markov Model (LHMM) representation. We review our efforts to employ expected value of information (EVI) computations to limit sensing and analysis in a context-sensitive manner. We discuss an implementation of a one-step myopic EVI analysis and compare the results of using the myopic EVI with a heuristic sensing policy that makes observations at different frequencies. Both policies are then compared to a random perception policy, where sensors are selected at random. Finally, we discuss the sensitivity of ideal perceptual actions to preferences encoded in utility models about information value and the cost of sensing.