Search

Researchers at the French Research Institute for Exploitation of the Sea (IFREMER) have developed a pipeline called KiNext, which aids in the identification and classification of protein kinases in organisms. Protein kinases play crucial roles in signal transduction and organismal physiology, and their dysregulation can lead to diseases like cancer. The KiNext pipeline utilizes bioinformatic tools and Hidden Markov Models to accurately identify and categorize protein kinases, improving the traceability and reproducibility of results. This research contributes to a better understanding of physiological capabilities and adaptations to environmental stress in various organisms. [Extracted from the article]

Researchers at the University of Utrecht in the Netherlands conducted a study on mood instability in patients with bipolar disorder. They used advanced statistical models, including a multilevel hidden Markov model, to analyze data from 20 patients over a 4-month period. The study found evidence of mood instability in almost half of the patients, highlighting the importance of recognizing and addressing this aspect of bipolar disorder. The research was supported by various organizations and has been peer-reviewed, providing valuable insights into the understanding and treatment of bipolar disorder. [Extracted from the article]

The article explores the dynamic functional connectivity in congenitally blind individuals compared to sighted individuals using Hidden Markov Models (HMM). The study found that blind individuals showed increased fractional occupancy in brain states related to somatomotor and occipito-frontal activation, while sighted individuals more frequently occupied states associated with Default Mode and Ventral Attentional networks. The research suggests that early visual deprivation disrupts the dynamics of functional connectivity, leading to prolonged activation of unimodal regions and increased connectivity within the visual network in blind individuals. [Extracted from the article]

A study conducted by researchers at the Department of Anesthesia and Critical Care Medicine in France aimed to predict the depth of anesthesia (DoA) using a Hidden Markov Model (HMM) based on four physiological variables: Mean Blood Pressure (MBP), Heart Rate (HR), Respiratory Rate (RR), and end-expiratory concentration of sevoflurane (AAEt). The researchers recorded these variables during general anesthesia procedures and trained the HMM to identify different states of consciousness. The results showed that the HMM had a high true positive rate for identifying awake, anesthesia, and emergence states. The researchers suggest that the HMM can help anesthetists monitor the DoA without relying on EEG data, and that the model could be improved with more patient data and the inclusion of EEG data. [Extracted from the article]

Entangled hidden Markov models (EHMMs) extend classical hidden Markov models into the quantum domain, while elephant random walks (ERWs) are globally inhomogeneous Markov processes with memory-dependent steps. In this paper, we propose a novel approach that combines EHMMs with ERWs. Our focus is on exploring the correlations within an EHMM associated with the ERW dynamics. Moreover, we show that its restriction to a maximal diagonal subalgebra defines an inhomogeneous HMM, and we compute a formula for its mean entropy. [ABSTRACT FROM AUTHOR]

This paper introduces a novel approach leveraging a sample-data-based, distributed, dynamic event-triggered framework to develop an H ∞ asynchronous consensus controller tailored for singular Markov jump multi-agent systems (MJMASs). This approach primarily focuses on mitigating the communication load inherent in singular multi-agent systems. We employ a hidden Markov model (HMM) to adeptly manage the mode synchronization discrepancies between the controller and the system. We establish the stochastic admissibility with H ∞ consensus performance of the singular consensus error system by deriving linear matrix inequalities (LMIs). Furthermore, we introduce a co-design methodology for optimizing controller gains, which simultaneously addresses the requirements of H ∞ consensus and the dynamic event-triggered framework. The effectiveness of our proposed method are demonstrated through three numerical examples, each employing a different triggering mechanism. [ABSTRACT FROM AUTHOR]

A recent systematic review conducted by researchers at the Pan African University Institute for Basic Sciences in Nairobi, Kenya, highlights the potential of Hidden Markov Models (HMMs) in advancing our understanding and treatment of genetic and neurological disorders. The review analyzed 77 papers and found a deficiency in research across regions such as Africa, South America, and Oceania, emphasizing the need for more diverse and inclusive studies in these areas. Additionally, the review identified a critical research gap in the examination of genetic mutations and their role in the onset and progression of these diseases. The researchers emphasize the importance of addressing these gaps to develop more effective and personalized treatments and enhance global health outcomes. [Extracted from the article]

Lithuanian researchers from Kaunas University of Technology have developed stress tests for pension funds, making them the first in the world to do so. These stress tests, typically used for banks and financial institutions, assess the ability of pension funds to withstand adverse economic conditions. By using a Hidden Markov Model, the researchers were able to forecast future market conditions and simulate the future evolution of pension funds' value. The study found that Lithuanian second pillar pension funds can withstand crises that are twice as long on average, but some funds struggle to cope with inflation and recover after negative shocks. The researchers recommend adjusting investment strategies to avoid negative consequences during financial crises. Overall, the study shows that Lithuania's pension funds are resilient and worth trusting. [Extracted from the article]

Researchers from UNIROUEN in Rouen, France have developed a machine learning approach for estimating the remaining useful life (RUL) of ball bearings. Ball bearings are critical components of rotating machines, and their malfunctioning can directly impact machine performance. The proposed methodology involves constructing a health indicator (HI) using non-stationary vibration data, defining a degradation profile coupled with fatigue models, and training a hidden Markov model (HMM) to capture the bearing degradation dynamics. The results show promising RUL prediction capabilities, with the fatigue models reducing the size of the machine learning model and improving the training phase. This research contributes to the field of health monitoring systems and prognosis for bearing diagnosis. [Extracted from the article]

A recent study examined mood instability in patients with bipolar disorder using advanced statistical models. The study found that bipolar disorder may be better understood as chronic cyclical mood instability, rather than alternating discrete episodes with stable periods in-between. The study used self-report questionnaires and weekly assessments to uncover four mood states (euthymic, manic, mixed, and depressive) that aligned with symptom scores. The results suggest that chronic mood instability is a key feature of bipolar disorder, even during relatively stable periods. However, it is important to note that this study has not yet undergone peer review. [Extracted from the article]

A preprint abstract from medrxiv.org discusses the use of smartphones to collect objective behavioral data for the study of brain-related disorders. The researchers applied a Hidden Markov Model (HMM) to a dataset of smartphone measures to assess social functioning in healthy controls, participants with schizophrenia, Alzheimer's disease, and memory complaints. The HMM identified different social states and calculated the percentage of time spent in the socially active state. The study found lower dwell times in Alzheimer's disease compared to healthy controls and higher dwell times associated with increased social functioning in healthy controls. The researchers concluded that the HMM is a practical method for digital phenotyping analysis. [Extracted from the article]

A new study conducted by researchers at Southern Medical University Nanfang Hospital in Guangzhou, China, explores the prediction of nodal metastasis progression in oral tongue cancer using a hidden Markov model (HMM) in MRI. The study aims to address the issue of unnecessary invasive neck dissection in patients with oral tongue squamous cell carcinomas (OTSCCs) by quantifying the risk of microscopic involvement at the lymph node level. The HMM algorithm developed in the study analyzes macroscopic metastases and tumor category to predict nodal metastasis evolution in patients with OTSCCs. The research findings suggest that lymph nodes progress faster in the early stage and slower in the late stage of the disease. [Extracted from the article]

A recent study conducted by researchers at the University of Minnesota explores a new approach to analyzing kidney cancer gene expression data. The study introduces a Bayesian hierarchical hidden Markov model (HMM) for biclustering, which takes into account the functional dependence between genes. By utilizing biological knowledge and the hidden Markov structure, the model identifies overexpressed, underexpressed, and irrelevant features in each cluster of samples. The proposed methods have been implemented in an R package and have been used to analyze both simulated data and real kidney cancer data from The Cancer Genome Atlas. [Extracted from the article]

A recent preprint abstract discusses the limitations of current sequencing technologies in mapping allele-specific epigenomic signals, which are important for understanding gene expression, disease susceptibility, and development. The average read length of short-read sequencing technologies and the high similarity in DNA sequences inherited from each parent restrict the assessment of these signals to only 10% of the genome. However, the authors propose a machine-learning approach based on variational hidden Markov modeling that can detect allele-specific epigenomic signals across the entire genome, resulting in a 10-fold improvement in genomic coverage compared to current methods. The study focuses on DNA methylation as a critical epigenomic regulatory signal. It is important to note that this preprint has not yet undergone peer review. [Extracted from the article]

A recent study conducted by researchers at Xiamen University in China explored the spatial-temporal characteristics of brain activity in individuals with Autism Spectrum Disorder (ASD) using functional magnetic resonance imaging (fMRI). The study utilized the hidden Markov model (HMM) and dynamic graph (DG) theory to analyze brain networks and their dynamics based on dynamic functional connectivity (DFC). The findings suggest that individuals with ASD are more likely to enter a strongly connected HMM brain state, leading to the isolation of brain networks and alterations in the topological characteristics of these networks. This research provides new insights into the potential use of data-driven methods for the early diagnosis of ASD. [Extracted from the article]

Purpose: Based on the analysis of the dissipative structure of the retail service supply chain (RSSC), this paper divides the system into two internal and external dissipative mechanisms, including the internal performance dissipation mechanism and the perceived quality dissipation mechanism outside the system. Based on the prediction of RSSC performance, this paper aims to discuss the application of Hidden Markov Model (HMM) in this field and puts forward a set of complete process of forecasting the service supply chain (SSC) performance based on HMM model. Design/methodology/approach: Based on the theory of dissipative structure, this paper selects the RSSC as the research object, analyzes the system characteristics of the dissipation structure of RSSC from three aspects, such as system opening type, distance from equilibrium state and nonlinear order and describes the quality fluctuation process of RSSC as a Hidden Markov process. Taking the RSSC of J Company as an example, this paper makes use of the observed state value of customer perceived service quality from 1997 to 2016, predicts the performance status of the enterprise's RSSC. Findings: The research results show that: RSSC is a dissipative structure system, and its performance is the internal entropy flow of the system, and the customer perceived service quality is external, their interaction determines the dynamic evolution of the system dissipation structure, and the Markov property between supply chain performance and perceived service quality. There is a Markov property between supply chain performance and perceived service quality. Using the perceived service quality observation state data of the external consumers of the system can effectively predict the implicit state of RSSC performance. Based on this prediction result, the strategy adjustment and optimization of the action mechanism of internal and external entropy flow in the dissipative structure system can be carried out to promote the sustainable development of the RSSC. Originality/value: This paper thinks that RSSC is a dissipative structure system and the SSC performance and customer perceived service quality are the internal and external entropy flow of the system, which determines the dynamic evolution of the system dissipation structure. There is a Markov property between supply chain performance and perceived service quality. The hidden state of SSC performance can be predicted effectively by using a hidden Markov model and observing state data of perceived service quality from consumers outside the system. [ABSTRACT FROM AUTHOR]

A recent study conducted by researchers at Luoyang Normal University in Henan, China, explores the use of intelligent analysis to decode students' behavioral states in physical education. The study utilizes hand-ring inertial data to identify students' motion sequence states. By employing statistical feature extraction, back propagation neural network (BPNN), and the Hidden Markov Model (HMM), the researchers were able to achieve a classification accuracy of over 96% in student action sequences. This research provides valuable insights and new ideas for future student state recognition in physical education and teaching reform. [Extracted from the article]

The article delves into the problem of stochastic stability analysis for nonlinear Markov jump systems (MJSs) with fuzzy asynchronous resilient sampled-data controllers (SDCs) using hidden Markov model (HMM) and quantum genetic algorithms (QGAs). A novel framework using QGA has been developed to obtain the control gain matrices by solving the linear matrix inequality (LMI). A new criterion is proposed to guarantee the stochastic stability of fuzzy nonlinear MJSs, relying on the mode-dependent Lyapunov-Krasovskii functional (LKF) approach. Standard Chua's circuit has been used to show the reliability and value of the developed results. Also, the Lorentz system has been explored to demonstrate the non-stochastic case. [ABSTRACT FROM AUTHOR]

A recent report discusses research conducted at Szechenyi Istvan University in Hungary on the topic of sign language recognition using robotics. The researchers aimed to address the challenge of scaling algorithms for sign language recognition with a growing vocabulary size and limited training data. They proposed the use of a neutrosophic hidden Markov model, which incorporates uncertainty and vagueness in gesture features. The experimental results showed that this approach is computationally efficient, performs well, and is robust to gesture variations. This research has the potential to assist individuals with hearing impairments without the need for data gloves or other input devices. [Extracted from the article]

A study conducted by researchers at Xihua University in Chengdu, China, has explored the dynamic organization patterns of motor imagery (MI) tasks using a hidden Markov model (HMM). The researchers identified eleven distinct HMM states based on MI-related EEG data and found that these states can be divided into three metastates, showing a highly organized structure. They also observed notable variations in temporal features of HMM states between left- and right-hand MI tasks. The findings provide a complementary understanding of different MI tasks and may contribute to improving MI-brain-computer interface (BCI) systems. [Extracted from the article]

A patent application titled "Processing Images to Associate with Stages of a Surgical Procedure" has been published online. The inventors propose a method and computational model for training a system to associate images of surgical procedures with specific stages based on the characteristics of surgical tools depicted in the images. The goal is to create a more efficient and informative way to use video recordings of surgical procedures for educational and documentation purposes. The patent application provides detailed descriptions and claims for the proposed method and system. [Extracted from the article]

Computational cognitive modeling is an important tool for understanding the processes supporting human and animal decision-making. Choice data in decision-making tasks are inherently noisy, and separating noise from signal can improve the quality of computational modeling. Common approaches to model decision noise often assume constant levels of noise or exploration throughout learning (e.g., the ϵ -softmax policy). However, this assumption is not guaranteed to hold – for example, a subject might disengage and lapse into an inattentive phase for a series of trials in the middle of otherwise low-noise performance. Here, we introduce a new, computationally inexpensive method to dynamically estimate the levels of noise fluctuations in choice behavior, under a model assumption that the agent can transition between two discrete latent states (e.g., fully engaged and random). Using simulations, we show that modeling noise levels dynamically instead of statically can substantially improve model fit and parameter estimation, especially in the presence of long periods of noisy behavior, such as prolonged lapses of attention. We further demonstrate the empirical benefits of dynamic noise estimation at the individual and group levels by validating it on four published datasets featuring diverse populations, tasks, and models. Based on the theoretical and empirical evaluation of the method reported in the current work, we expect that dynamic noise estimation will improve modeling in many decision-making paradigms over the static noise estimation method currently used in the modeling literature, while keeping additional model complexity and assumptions minimal. • Decision noise can fluctuate over time due to changes in task-engagement. • Cognitive models often fail to account for fluctuations in decision noise. • Our method models task-engagement as a binary, latent state. • We provide a procedure to estimate the latent state occupancy probability per trial. • Dynamic noise estimation can benefit model and parameter fit in theory and practice. [ABSTRACT FROM AUTHOR]

This paper investigates the event-triggered H ∞ output consensus problem of Markov jump multi-agent systems with measured outputs and external disturbances. A hidden Markov model is established to solve the problem of asynchronous mode mismatch between the controller and the system. Meanwhile, the general information case of the transition probability matrix and the observation probability matrix contained in the hidden Markov model is further systematically investigated. More specifically, the general information mean that the transition probability and observation probability are completely known, completely unknown, or only known as their estimated values. In addition, an event-triggered output consensus communication mechanism with a periodic sampling of the system output is used to save bandwidth resources and avoid unnecessary continuous monitoring. Some sufficient conditions guaranteeing that the multi-agent systems achieve H ∞ consensus are obtained in the form of linear matrix inequalities employing Lyapunov stability theory. Finally, the feasibility of the proposed method is confirmed by an illustrative example. [ABSTRACT FROM AUTHOR]

A recent study conducted by researchers at the University of Texas Austin explored attentional processes in individuals with social anxiety disorder. The study used a virtual reality exposure treatment and eye tracking to examine attentional heterogeneity. The researchers found two distinct attentional profiles among participants before treatment, characterized as audience-focused and audience-avoidant. However, these profiles were no longer significantly different at the one-week follow-up. The study also suggested that patterns of avoidance may be related to poorer treatment outcomes for virtual reality exposure therapy. This research provides support for the heterogeneity of attentional processes in socially anxious individuals and highlights the potential impact of treatment on these processes. [Extracted from the article]

This paper is concerned with both continuous- and discrete-time extended dissipativity-based control problems for Markov jump systems. Hidden Markov model is employed to describe the jump asynchronization behavior between the original system and the controller. Then, an asynchronous static output feedback controller is designed. By using the mode-dependent Lyapunov function technique with slack matrices, several sufficient conditions are obtained to ensure that the closed-loop systems are stochastically stable with extended dissipativity performance. Based on these conditions, solutions to the controller gains are derived. Finally, simulation results are presented to illustrate the feasibility and the effectiveness of the proposed approaches. [ABSTRACT FROM AUTHOR]

This work investigates the observer-based asynchronous fault detection problem for a class of nonlinear Markov jumping systems. The conic-type nonlinearities hold such a restrictive condition that locates in a known hypersphere with an undefined centre. In order to guarantee the observer modes run synchronously with the system modes, we introduce a hidden Markov model to deal with this difficulty. Utilizing $H_\infty $ and $H_\_{}$ performance index, a multi-targets strategy of asynchronous fault detection problem is formulated. Via linear matrix inequality, sufficient conditions for the presence of the asynchronous fault detection observer are derived respectively. Then an asynchronous fault detection algorithm is formulated. Finally, the application of dynamic equivalent circuit of separately excited DC motor with three cases is employed to illustrate that the devised asynchronous fault detection observer is able to detect the faults after the appearances in the absence of any incorrect alarm. [ABSTRACT FROM AUTHOR]

• We propose a unified adversary model for inference attacks on genomic privacy of unrelated individuals. • We present an inference attack strategy that employs the correlations of SNPs and the sampling and recombination model. • We reveal an RCNN–based inference attack and investigate the large-scale capabilities of machine learning for genomic privacy attacking. • We evaluate the inference attack capability and quantify genomic privacy in terms of mutual information. • Our results obtain with much higher accuracy, lower uncertainty on the inferred genomic data, and more loss of privacy than previous work. In recent years, the collection of large-scale genomic data for individuals has become feasible and affordable. Concurrently, several practical attacks targeting genome re-identification and genotype inference have emerged to threaten the confidentiality of genomic data sharing, leading to security and privacy concerns regarding genomic data. The authors have shown that this problem can be even worse in this paper. Specifically, two possible large-scale genotype inference attack stretegies for nonrelatives have exposed. One is based on an improved hidden Markov model (iHMM), and the other is based on a regressive convolutional neural network (RCNN). By using a genomic privacy metric combining the attacker's incorrectness, the attacker's uncertainty, and the genomic privacy loss of the victims, it is shown that with these atrategies, the attack can be significantly more severe than those reported previously. It is also shown that machine learning can be applied to empower large-scale inference attacks against genomic privacy. [ABSTRACT FROM AUTHOR]

This paper studies the problem of model reduction for nonhomogeneous Markovian jump systems. The transition probability matrix of the nonhomogeneous Markovian chain has the characteristic of a polytopic structure. An asynchronous reduced-order model is considered, and the asynchronization is modeled by a hidden Markov model with a partially unknown conditional probability matrix. Under this framework, a new sufficient condition is proposed to ensure that the augmented system is stochastically mean-square stable with a specified level of $H_\infty$ performance. Finally, a numerical example is provided to show the effectiveness and advantages of the theoretic results obtained. [ABSTRACT FROM AUTHOR]

A recent study conducted by researchers at the University of Southern Florida has developed a decision support system for neurosurgeons to determine the release schedule for patients with traumatic brain injuries (TBIs). The study introduces a functional Hidden Markov Model (fHMM) that can adapt to different physician decision-making styles while continuously monitoring patient progress. The analysis suggests that implementing this decision model could potentially save up to $27,500 per TBI patient under certain conditions. This research provides valuable insights into managing traumatic brain injuries and offers a promising approach for physicians in making crucial discharge decisions. [Extracted from the article]

A study conducted by researchers at National Yang Ming Chiao Tung University in Taipei, Taiwan, explored the correlation between post-stroke upper limb recovery and dynamic resting-state network connectivity. The study involved 37 individuals with subcortical ischemic stroke and unilateral hand paresis. The researchers used resting-state magnetoencephalography to analyze brain activity and found that the ipsilesional resting-state sensorimotor network had increased connectivity at 3 weeks after stroke compared to controls. This increased connectivity was associated with concurrent motor scores in individuals who had not fully recovered. The findings suggest that the recruitment of this network may serve as a biomarker for functional motor recovery processes. [Extracted from the article]

The patent application submitted by Srinka Ghosh describes methods and systems for analyzing nucleic acid sequences from biological samples. These methods involve obtaining sequence reads, identifying specific genomic regions, performing local de novo assembly, recovering sequence data, and producing consensus sequences. The systems include a database for storing sequence reads and computer processors programmed to execute the analysis steps. The application aims to improve the detection of chromosomal abnormalities, which can be related to various health conditions. For more information and specific claims, the full patent application should be consulted. [Extracted from the article]

A patent has been issued for an automatic cardiac therapy advisor that aims to improve the accuracy of treatment decisions for cardiac arrest patients. The patent describes a method that involves transforming time domain measurements into frequency domain data, processing the data to form spectral bands, and determining the treatment based on a weighted sum of the spectral bands. The invention utilizes mathematical transformations and algorithms to provide an automated and objective approach to determining the optimal treatment for cardiac arrest patients. The patent is assigned to ZOLL Medical Corporation. [Extracted from the article]

Researchers from Majmaah University in Saudi Arabia have published new studies and findings on Alzheimer's disease. The researchers propose a combined approach using a Hidden Markov Model (HMM) and MR-DTI (Diffusion Tensor Imaging) to forecast the occurrence of Alzheimer's disease. The statistical analysis showed a significant correlation between microstructural white matter changes and cognitive functioning in patients with Alzheimer's disease. The proposed method, called Graphcut Hidden Markov Model (Graph_HMM), achieved high accuracy, sensitivity, specificity, and mean squared error in predicting Alzheimer's disease. [Extracted from the article]

Researchers from Utrecht University have conducted a proof-of-concept study using a hidden Markov model (HMM) to analyze the dynamics of interpersonal interactions in psychotherapy sessions and predict improvements in patient depression symptoms. The study found that patients who showed improvement in their depression scores exhibited hyperfocus when listening to their therapist, compared to non-improving patients. The researchers suggest that this approach can help uncover the dynamics of interpersonal interactions in therapy and potentially be used to predict patient outcomes. However, the study acknowledges limitations due to its small sample size. [Extracted from the article]

Abstract An optimal and flexible multiple hypotheses testing procedure is constructed for dependent data based on Bayesian techniques, aiming at handling two challenges, namely dependence structure and non-null distribution specification. Ignoring dependence among hypotheses tests may lead to loss of efficiency and bias in decision. Misspecification in the non-null distribution, on the other hand, can result in both false positive and false negative errors. Hidden Markov models are used to accommodate the dependence structure among the tests. Dirichlet mixture process prior is applied on the non-null distribution to overcome the potential pitfalls in distribution misspecification. The testing algorithm based on Bayesian techniques optimizes the false negative rate (FNR) while controlling the false discovery rate (FDR). The procedure is applied to pointwise and clusterwise analysis. Its performance is compared with existing approaches using both simulated and real data examples. [ABSTRACT FROM AUTHOR]

Learning a hidden Markov model (HMM) is typically based on the computation of a likelihood which is intractable due to a summation over all possible combinations of states and mixture components. This estimation is often tackled by a maximization strategy, which is known as the Baum–Welch algorithm. However, some drawbacks of this approach have led to the consideration of Bayesian methods that add a prior over the parameters in order to work with the posterior probability and the marginal likelihood. These approaches can lead to good models but to the cost of extremely long computations (e.g., Markov Chain Monte Carlo). More recently, variational Bayesian frameworks have been proposed as a Bayesian alternative that keeps the computation tractable and the approximation tight. It relies on the introduction of a prior over the parameters to be learned and on an approximation of the true posterior distribution. After proving good standing in the case of finite mixture models and discrete and Gaussian HMMs, we propose here to derive the equations of the variational learning of the Dirichlet mixture-based HMM, and to extend it to the generalized Dirichlet. The latter case presents several properties that make the estimation more accurate. We prove the validity of this approach within the context of unusual event detection in public areas using the University of California San Diego data sets. HMMs are trained over normal video sequences using the typical Baum–Welch approach versus the variational one. The variational learning leads to more accurate models for the detection and localization of anomaly, and the general HMM approach is shown to be versatile enough to handle the detection of various synthetically generated tampering events. [ABSTRACT FROM AUTHOR]

This paper considers the problem of asynchronous $\mathcal H_{\infty }$ control for two-dimensional (2-D) Markov jump systems. The underlying system is described based upon the Roesser model. Especially, the hidden Markov model is employed when dealing with the asynchronization between a controlled system and a controller, and the relation between them is constructed through a conditional probability matrix. Based on the Lyapunov function technique, the asymptotic mean square stability and $\mathcal H_{\infty }$ noise attenuation performance are investigated for the closed-loop 2-D system. Moreover, the controller gain can be obtained by solving a convex optimization problem. An example is presented to show the effectiveness and potential of the proposed new design technique. [ABSTRACT FROM AUTHOR]

Abstract A hidden Markov model is proposed for segmenting cylindrical time series according to a finite number of latent classes, associated with copula-based cylindrical densities. It provides a parsimonious and computationally tractable approach that integrates circular–linear correlation, multimodality and temporal auto-correlation. [ABSTRACT FROM AUTHOR]

A recent study conducted at Virginia Tech has focused on understanding driver hazard avoidance during the transition from automated to human-controlled vehicles. The study utilized multilevel Hidden Markov Models to analyze the hazard avoidance processes in response to static road hazards. The researchers found that a three-state model, consisting of Approaching, Negotiating, and Recovering, had the best fitness compared to other models. The study suggests that hazard avoidance patterns can be used to recognize driving behaviors and proposes improvements to generalize the models for different automation conditions. [Extracted from the article]

Keywords: Drugs and Therapies; Emerging Technologies; Hidden Markov Model; Machine Learning; Peptides; Personalized Medicine; Personalized Therapy; Proteins; Proteomics EN Drugs and Therapies Emerging Technologies Hidden Markov Model Machine Learning Peptides Personalized Medicine Personalized Therapy Proteins Proteomics 84 84 1 11/06/23 20231107 NES 231107 2023 NOV 6 (NewsRx) -- By a News Reporter-Staff News Editor at Cancer Vaccine Week -- Investigators publish new report on personalized medicine. Drugs and Therapies, Emerging Technologies, Hidden Markov Model, Machine Learning, Peptides, Personalized Medicine, Personalized Therapy, Proteins, Proteomics. [Extracted from the article]

This paper investigates the issue of asynchronous event-triggered control for two-dimensional Markov jump systems subject to networked random packet losses. The asynchronous behavior between the plant and controller is characterized by a hidden Markov model, and the packet loss behavior is described by a Bernoulli stochastic process. To relieve the communication pressure, an event-triggered strategy with independent triggering behavior in the horizontal and vertical directions is given. A sufficient condition is established to ensure stochastic stability and H ∞ performance for the closed-loop system. Then, a method for designing an asynchronous event-triggered controller is developed through eliminating nonlinearities formed by the inverse of Lyapunov matrices. Moreover, based on convex optimization of the H ∞ performance, an algorithm is proposed to find the maximum feasible domain of the event-triggered thresholds. Finally, a Darboux equation with Markov jump properties is applied to verify the effectiveness of the presented design method. • Establish a sufficient condition for stochastic stability and H ∞ performance. • Design an asynchronous event-triggered controller for 2D Markov jump systems. • Propose an algorithm to determine the maximum feasible domain of trigger thresholds. [ABSTRACT FROM AUTHOR]

"In an additional embodiment, fitting a hidden Markov model to the to the triaxial accelerometer training data cluster assignments include using a Baum Welch algorithm. The process of claim 1, wherein fitting a hidden Markov model to the to the triaxial accelerometer training data cluster assignments comprise using a Baum Welch algorithm. [Extracted from the article]

Recent years have witnessed an increasing need for the automated classification of sequential data, such as activities of daily living, social media interactions, financial series, and others. With the continuous flow of new data, it is critical to classify the observations on-the-fly and without being limited by a predetermined number of classes. In addition, a model should be able to update its parameters in response to a possible evolution in the distributions of the classes. This compelling problem, however, does not seem to have been adequately addressed in the literature, since most studies focus on offline classification over predefined class sets. In this paper, we present a principled solution for this problem based on an adaptive online system leveraging Markov switching models and hierarchical Dirichlet process priors. This adaptive online approach is capable of classifying the sequential data over an unlimited number of classes while meeting the memory and delay constraints typical of streaming contexts. In this paper, we introduce an adaptive “learning rate” that is responsible for balancing the extent to which the model retains its previous parameters or adapts to new observations. Experimental results on stationary and evolving synthetic data and two video data sets, TUM Assistive Kitchen and collated Weizmann, show a remarkable performance in terms of segmentation and classification, particularly for sequences from evolutionary distributions and/or those containing previously unseen classes. [ABSTRACT FROM AUTHOR]

Keyword Spotting (KWS) systems can be divided into two main groups: Hidden Markov Model (HMM)-based and Discriminative KWS (DKWS) systems. In this paper, we propose an approach to improve a DKWS system using advantages of HMM-based systems. The proposed DKWS system contains feature extraction and classification (that includes a classifier and a search algorithm) parts. The focus of this paper is on the feature extraction part and the search algorithm. At first, we propose a method for using the advantages of a triphone-based HMM system and improving the monophone-based feature extraction, (proposed in our previous works), to triphone-based one. Then, we propose an N-best search algorithm instead of one-best algorithm. The results on TIMIT database indicate that the true detection rate of the triphone-based Evolutionary DKWS (EDKWS) system with N-best search (Tph-EDKWS-N-Best), in false alarm rate per keyword per hour greater than two, is 4.6% higher than that of the monophone-based EDKWS system with one-best search (Mph-EDKWS-1-Best). This improvement costs about 0.4 unit degradation in Real Time Factor (a common metric of measuring the speed of an automatic speech recognition system). Additionally, Figure of Merit (average true detection rate for different false alarm per keyword per hour from 1 to 10) of the Tph-EDKWS-N-Best system is noticeably higher than that of HMM-based KWS systems. However, the computational complexity of the Tph-EDKWS-N-Best system is considerably higher than that of the HMM-based KWS systems. [ABSTRACT FROM AUTHOR]

This paper is devoted to developing a periodic and asynchronous filter for periodic Markov jump systems. A periodic and asynchronous filter means that the filter parameters are s -periodic for a given operating mode, and its operating modes are unnecessary to be identical but form a periodic hidden Markov model together with the modes of the plant. A sufficient condition is proposed to guarantee that the filtering error system is exponentially mean square stable and strictly ( Q , S , R ) -dissipative. To realize this filter, a slack matrix is introduced to deal with the nonlinearity and Finsler’s lemma is applied such that the decision variables are reduced. Finally, a numerical simulation provides verification for the effectiveness of our designed filter. [ABSTRACT FROM AUTHOR]

In the paper, authors report on the interdisciplinary and extremely complex link between wavelets and stochastic processes. An insight into the history of wavelets has been provided presenting the fundamental conception of wavelets, as well as wavelet theory that emerged from stochastic processes. The multiresolution analysis corresponds to the Kolmogorov system which is a regular stationary stochastic process. It presents a significant link to the measurement problem in terms of positional notation which the wavelet domain hidden Markov model should be derived from. The optimal representation arises to be an issue requiring further elaboration extended to the general measurement and wavelet frames. • Wavelet theory is reminiscent to the Mathesis Universalis which should be a universal calculus involving everything in existence. • The link between wavelets and stochastic processes is extremely complex and interdisciplinary one. • The optimal base is defined by maximization of the structural information which relates to the most prominent increase of entropy in the temporal domain. • The conception is successfully generalizable to frames which correspond to redundant generators of the Hilbert space. [ABSTRACT FROM AUTHOR]