Search Results (600)

Fetal heart rate variability (FHRV) is a critical indicator of fetal well-being and autonomic nervous system development during labor. Traditional monitoring methods often provide limited insights, potentially leading to delayed interventions and suboptimal outcomes. This study proposes an advanced predictive analytics approach by integrating approximate entropy analysis with a hidden Markov model (HMM) within a digital twin framework to enhance real-time fetal monitoring. We utilized a dataset of 469 fetal electrocardiogram (ECG) recordings, each exceeding one hour in duration, to ensure sufficient temporal information for reliable modeling. The FHRV data were preprocessed and partitioned into parasympathetic and sympathetic components based on downward and non-downward beat detection. Approximate entropy was calculated to quantify the complexity of FHRV patterns, revealing significant correlations with umbilical cord blood gas parameters, particularly pH levels. The HMM was developed with four hidden states representing discrete pH levels and eight observed states derived from FHRV data. By employing the Baum–Welch and Viterbi algorithms for training and decoding, respectively, the model effectively captured temporal dependencies and provided early predictions of the fetal acid–base status. Experimental results demonstrated that the model achieved 85% training and 79% testing accuracy on the balanced dataset distribution, improving from 78% and 71% on the imbalanced dataset. The integration of this predictive model into a digital twin framework offers significant benefits for timely clinical interventions, potentially improving prenatal outcomes. Full article

Understanding how crises like the COVID-19 pandemic affect variable annuity pricing is crucial, especially in emerging markets like India. The motivation is that financial stability and risk management in these markets depend heavily on accurate pricing models. While prior research has primarily focused on Western markets, there is a significant gap in analyzing the impact of extreme volatility and regime-dependent dynamics on variable annuities in emerging economies. This study investigates how regime shifts during the COVID-19 pandemic influence variable annuity pricing in the Indian stock market, specifically using the Nifty 50 Index data from 7 September 2017 until 7 September 2023. Advanced methodologies, including regime-switching hidden Markov models, artificial neural networks, and Monte Carlo simulations, were applied to analyze pre- and post-COVID-19 market behavior. The regime-switching hidden Markov models effectively capture latent market regimes and their transitions, which traditional models often overlook, while neural networks provide flexible functional approximations that enhance pricing accuracy in highly non-linear environments. The Expectation–Maximization (EM) algorithm was employed to achieve robust calibration and enhance pricing accuracy. The analysis showed significant pricing variations across market regimes, with heightened volatility observed during the pandemic. The findings highlight the effectiveness of regime-switching models in capturing market dynamics, particularly during periods of economic uncertainty and turbulence. This research contributes to the understanding of variable annuity pricing under regime-dependent dynamics in emerging markets and offers practical implications for improved risk management and policy formulation. Full article

Serine acetyltransferase (SAT) is a critical enzyme in the sulfur-assimilation pathway of cysteine, playing an essential role in numerous physiological functions in plants, particularly in their response to environmental stresses. However, the structural characteristics of the soybean SAT gene family remain poorly understood. Members of the soybean SAT gene family were identified using the Hidden Markov Model approach. Bioinformatics tools, such as ExPASy, PlantCARE, MEME, and TBtools-II, were employed to examine the physicochemical properties, cis-regulatory elements, conserved motifs, gene structures, and chromosomal positions of the GmSAT genes. RT-qPCR was conducted to evaluate the expression profiles of GmSAT genes under NaCl-induced stress, identifying genes likely involved in the salt-stress response. A total of ten GmSAT genes were identified in the soybean genome and grouped into three subfamilies. Genes within each subfamily shared notable structural similarities and conserved motifs. Analysis of cis-regulatory elements revealed that the promoters of these genes contain several elements linked to plant growth and stress-related responses. Expression patterns of GmSAT genes varied across different soybean tissues, with GmSAT10 showing higher expression in roots, while GmSAT1 and GmSAT2 had lower expression in the same tissue. Following NaCl treatment, expression levels of seven GmSAT genes were significantly increased in the roots, indicating their potential involvement in the plant’s adaptation to salt stress. GmSAT genes appear to play crucial roles in soybean’s response to salt stress, offering insights that could aid in the development of salt-tolerant soybean varieties. Full article

Mental health assessment is typically carried out via a series of conversation sessions with medical professionals, where the overall aim is the diagnosis of mental illnesses and well-being evaluation. Despite its arguable socioeconomic significance, national health systems fail to meet the increased demand for such services that has been observed in recent years. To assist and accelerate the diagnosis process, this work proposes an AI-based tool able to provide interpretable predictions by automatically processing the recorded speech signals. An explainability-by-design approach is followed, where audio descriptors related to the problem at hand form the feature vector (Mel-scaled spectrum summarization, Teager operator and periodicity description), while modeling is based on Hidden Markov Models adapted from an ergodic universal one following a suitably designed data selection scheme. After extensive and thorough experiments adopting a standardized protocol on a publicly available dataset, we report significantly higher results with respect to the state of the art. In addition, an ablation study was carried out, providing a comprehensive analysis of the relevance of each system component. Last but not least, the proposed solution not only provides excellent performance, but its operation and predictions are transparent and interpretable, laying out the path to close the usability gap existing between such systems and medical personnel. Full article

This paper addresses the handover challenge in indoor visible light communication and Wi-Fi heterogeneous networks, proposing an adaptive handover strategy based on user trajectory prediction. Extracting meaningful and important location points from massive trajectory data for clustering, an improved hidden Markov model is used to predict the user’s next location by analyzing the patterns of the user’s historical mobile trajectory data. The Q-learning algorithm is then used to determine the optimal network handover based on the current network state, while a seamless handover protocol is introduced to ensure successful network transition and uninterrupted data transmission. Compared with the traditional STD-LTE handover scheme, the proposed algorithm can reduce vertical handover rates by up to 32% during fast walking. When indoor user connections increase, the algorithm can maintain high fairness and high throughput when indoor user connections increase, verifying that it is robust in different scenarios. Full article

Colorectal cancer (CRC) is a significant worldwide health problem due to its high prevalence, mortality rates, and frequent diagnosis at advanced stages. While diagnostic and therapeutic approaches have evolved, the underlying mechanisms driving CRC initiation and progression are not yet fully understood. Early detection is critical for improving patient survival, as initial cancer stages often exhibit epigenetic changes—such as DNA methylation—that regulate gene expression and tumor progression. Identifying DNA methylation patterns and key survival-related genes in CRC could thus enhance diagnostic accuracy and extend patient lifespans. In this study, we apply two of our recently developed methods for identifying differential methylation and analyzing survival using a sparse, finite mixture of accelerated failure time regression models, focusing on key genes and pathways in CRC datasets. Our approach outperforms two other leading methods, yielding robust findings and identifying novel differentially methylated cytosines. We found that CRC patient survival time follows a two-component mixture regression model, where genes CDH11, EPB41L3, and DOCK2 are active in the more aggressive form of CRC, whereas TMEM215, PPP1R14A, GPR158, and NAPSB are active in the less aggressive form. Full article

The rapid development of mobile sensing technologies (e.g., smart devices embedded with various powerful sensors) has encouraged the proliferation of the Internet of Things (IoT). Although data reliability and accuracy are crucial in many sensor applications (e.g., air-quality monitoring), it is often difficult to ensure these properties. Mobile IoT’s people-centric architecture allows for more inaccurate and corrupted data. In this manuscript, we are addressing the problem of how to predict data more accurately in the presence of malicious participants who inject false data to manipulate the system. Our goal is to recover those missing or imprecise data values from the correlated data streams. To do so, we propose a Reputation-Based Context-Aware Data-Fusion (RCoD) mechanism that is resilient against on–off and data-corruption attacks. Furthermore, the Contextual Hidden Markov Model-based data prediction facilitates more accurate real-time data prediction. We tested the scenarios where most participants were malicious, injecting false data at varied rates. Our method accurately identified the honest participants based on their reported data and context. We empirically evaluate the performance using Beijing’s air-quality dataset. We compared the performance of our RCoD method against four state-of-the-art methods, and the results justify its superiority. Full article

Recorded audio often contains speech from multiple people in conversation. It is useful to label such signals with speaker turns, noting when each speaker is talking and identifying each speaker. This paper discusses how to process speech signals to do such speaker diarization (SD). We examine the nature of speech signals, to identify the possible acoustical features that could assist this clustering task. Traditional speech analysis techniques are reviewed, as well as measures of spectral similarity and clustering. Speech activity detection requires separating speech from background noise in general audio signals. SD may use stochastic models (hidden Markov and Gaussian mixture) and embeddings such as x-vectors. Modern neural machine learning methods are examined in detail. Suggestions are made for future improvements. Full article

The accurate prediction of the next location in a sequence is highly beneficial for users of mobile applications. In this study, we investigate how various data preprocessing techniques affect the performance of location recommendation systems. We utilize datasets from Foursquare and Twitter, incorporating users’ historical check-ins. Key preprocessing steps include filtering datasets to users with common features, analyzing user location preferences, varying sequence lengths and location categories, and integrating time-of-day information. Our findings reveal that proper data preprocessing significantly enhances the accuracy of recommendations by addressing key challenges such as data sparsity and user heterogeneity. Specifically, tailoring datasets to individual user attributes improves model personalization, while restructuring category hierarchies balances precision and diversity in the recommendations that are given. Integrating temporal data further refines the predictions that are made by accounting for time-based user behavior. Recommendations are generated using recurrent neural networks (RNNs) and hidden Markov models (HMMs), with the experimental results showing up to 20% improvement in the precision of personalized models compared to global ones. Full article

In this paper, an EML (electro-magnetic log) integrated navigation algorithm based on the HMM (hidden Markov model) and CNLKF (cross-noise linear Kalman filter) is proposed, which is suitable for SINS (strapdown inertial navigation system)/EML/GNSS (global navigation satellite system) integrated navigation systems for small or medium-sized AUV (autonomous underwater vehicle). The algorithm employs the following five techniques: ① the HMM-based pre-processing algorithm of EML data; ② the CNLKF-based fusion algorithm of SINS/EML information; ③ the MALKF (modified adaptive linear Kalman filter)-based algorithm of GNSS-based calibration; ④ the estimation algorithm of the current speed based on output from MALKF and GNSS; ⑤ the feedback correction of LKF (linear Kalman filter). The principle analysis of the algorithm, the modeling process, and the flow chart of the algorithm are given in this paper. The sea trial of a small-sized AUV shows that the endpoint positioning error of the proposed/traditional algorithm by this paper is 20.5 m/712.1 m. The speed of the water current could be relatively accurately estimated by the proposed algorithm. Therefore, the algorithm has the advantages of high accuracy, strong anti-interference ability (it can effectively shield the outliers of EML and GNSS), strong adaptability to complex environments, and high engineering practicality. In addition, compared with the traditional DVL (Doppler velocity log), EML has the advantages of great concealment, low cost, light weight, small size, and low power consumption. Full article

We define an evolving in-time Bayesian neural network called a Hidden Markov Neural Network, which addresses the crucial challenge in time-series forecasting and continual learning: striking a balance between adapting to new data and appropriately forgetting outdated information. This is achieved by modelling the weights of a neural network as the hidden states of a Hidden Markov model, with the observed process defined by the available data. A filtering algorithm is employed to learn a variational approximation of the evolving-in-time posterior distribution over the weights. By leveraging a sequential variant of Bayes by Backprop, enriched with a stronger regularization technique called variational DropConnect, Hidden Markov Neural Networks achieve robust regularization and scalable inference. Experiments on MNIST, dynamic classification tasks, and next-frame forecasting in videos demonstrate that Hidden Markov Neural Networks provide strong predictive performance while enabling effective uncertainty quantification. Full article

Plastic pollution in waterways poses a significant global challenge, largely stemming from land-based sources and subsequently transported by rivers to marine environments. With a substantial percentage of marine plastic waste originating from land-based sources, comprehending the trajectory and temporal experience of single-use plastic bottles assumes paramount importance. This project designed, developed, and released a plastic pollution tracking device, coinciding with Vietnam’s annual Plastic Awareness Month. By mapping the plastic tracker’s journey through the Saigon River, this study generated high-fidelity data for comprehensive analysis and bolstered public awareness through regular updates on the Re-Think Plastics Vietnam website. The device, equipped with technologies such as drone flight controller, open-source software, embedded computing, and cellular networking effectively captured GPS position, track, and localized conditions experienced by the plastic bottle tracker on its journey. This amalgamation of data contributes to the understanding of plastic pollution behaviors and serves as a data set for future initiatives aimed at plastic prevention in the ecologically sensitive Mekong Delta. By illuminating the transportation of single-use plastic bottles in the riparian waterways of Ho Chi Minh City and beyond, this study plays a role in collective efforts to understand plastic pollution and preserve aquatic ecosystems. By deploying a GPS-enabled plastic tracker, this study provides novel, high-resolution empirical data on plastic transport in urban tidal systems. These findings contribute to improving waste interception strategies and informing environmental policies aimed at reducing plastic accumulation in critical retention zones. Full article

Sequential decision-making in dynamic and interconnected environments is a cornerstone of numerous applications, ranging from communication networks and finance to distributed blockchain systems and IoT frameworks. The multi-armed bandit (MAB) problem is a fundamental model in this domain that traditionally assumes independent and identically distributed (iid) rewards, which limits its effectiveness in capturing the inherent dependencies and state dynamics present in some real-world scenarios. In this paper, we lay a theoretical framework for a modified MAB model in which each arm’s reward is generated by a hidden Markov process. In our model, each arm undergoes Markov state transitions independent of play in a way that results in varying reward distributions and heightened uncertainty in reward observations. The number of states for each arm can be up to three states. A key challenge arises from the fact that the underlying states governing each arm’s rewards remain hidden at the time of selection. To address this, we adapt traditional index-based policies and develop a modified index approach tailored to accommodate Markovian transitions and enhance selection efficiency for our model. Our proposed proposed Markovian Upper Confidence Bound (MC-UCB) policy achieves logarithmic regret. Comparative analysis with the classical UCB algorithm reveals that MC-UCB consistently achieves approximately a 15% reduction in cumulative regret. This work provides significant theoretical insights and lays a robust foundation for future research aimed at optimizing decision-making processes in complex, networked systems with hidden state dependencies. Full article

This study introduces a radar-based model for estimating blood pressure (BP) in a touch-free manner. The model accurately detects cardiac activity, allowing for contactless and continuous BP monitoring. Cardiac motions are considered crucial components for estimating blood pressure. Unfortunately, because these movements are extremely subtle and can be readily obscured by breathing and background noise, accurately detecting these motions with a radar system remains challenging. Our approach to radar-based blood pressure monitoring in this research primarily focuses on cardiac feature extraction. Initially, an integrated-spectrum waveform is implemented. The method is derived from the short-time Fourier transform (STFT) and has the ability to capture and maintain minute cardiac activities. The integrated spectrum concentrates on energy changes brought about by short and high-frequency vibrations, in contrast to the pulse-wave signals used in previous works. Hence, the interference caused by respiration, random noise, and heart contractile activity can be effectively eliminated. Additionally, we present two approaches for estimating cardiac characteristics. These methods involve the application of a hidden semi-Markov model (HSMM) and a U-net model to extract features from the integrated spectrum. In our approach, the accuracy of extracted cardiac features is highlighted by the notable decreases in the root mean square error (RMSE) for the estimated interbeat intervals (IBIs), systolic time, and diastolic time, which were reduced by 87.5%, 88.7%, and 73.1%. We reached a comparable prediction accuracy even while our subject was breathing normally, despite previous studies requiring the subject to hold their breath. The diastolic BP (DBP) error of our model is $3.98\pm 5.81$ mmHg (mean absolute difference ± standard deviation), and the systolic BP (SBP) error is $6.52\pm 7.51$ mmHg. Full article

Dietary l-carnitine produces γ-butylbetaine (γBB) in a gut-microbiota-dependent manner in humans, and has been proven to be an intermediate product possibly associated with incident cardiovascular diseases or major adverse events. Eliminating or reducing the production of microbiota-dependent γBB may contribute to adjuvant therapy for cardiovascular diseases. However, to date, our understanding of the γBB metabolic gene clusters (MGCs) and associated microorganisms remains limited. To solve this problem, we constructed a manually curated γBB metabolic gene cluster database (γBMGC) based on Hidden Markov Models (HMMs). It comprised 171,510 allelic genes from 85 species and 20 genera, which could effectively provide high-resolution analysis at the strain level. For simulated gene datasets, with a 50% identity cutoff, we achieved an annotation accuracy, PPV, specificity, F1-score, and NPV of 99.4%, 97.97%, 99.16%, 98.97%, and 100%, respectively, which significantly outperformed existing databases such as KEGG at similar thresholds. The γBMGC database is more accurate, comprehensive, and faster for profiling cardiovascular disease (CVD)-associated genes at the species or strain level, offering a higher resolution in identifying strain-specific γBB metabolic pathways compared to existing databases like KEGG or COG. Meanwhile, we validated the excellent performance of γBMGC in gene abundance analysis and bacterial species distinction. γBMGC is a powerful database for enhancing our understanding of the microbial l-carnitine pathway in the human gut, enabling rapid and high-accuracy analyses of the associated cardiovascular disease processes. Full article