Search

Background: Biomedical data are usually collections of longitudinal data assessed at certain points in time. Clinical observations assess the presences and severity of symptoms, which are the basis for the description and modeling of disease progression. Deciphering potential underlying unknowns from the distinct observation would substantially improve the understanding of pathological cascades. Hidden Markov Models (HMMs) have been successfully applied to the processing of possibly noisy continuous signals. We apply ensembles of HMMs to categorically distributed multivariate time series data, leaving space for expert domain knowledge in the prediction process. Methods: We use an ensemble of HMMs to predict the loss of free walking ability as one major clinical deterioration in the most common autosomal dominantly inherited ataxia disorder worldwide. Results: We present a prediction pipeline that processes data paired with a configuration file, enabling us to train, validate and query an ensemble of HMMs. In particular, we provide a theoretical and practical framework for multivariate time-series inference based on HMMs that includes constructing multiple HMMs, each to predict a particular observable variable. Our analysis is conducted on pseudo-data, but also on biomedical data based on Spinocerebellar ataxia type 3 disease. Conclusions: We find that the model shows promising results for the data we tested. The strength of this approach is that HMMs are well understood, probabilistic and interpretable models, setting it apart from most Deep Learning approaches. We publish all code and evaluation pseudo-data in an open-source repository. [ABSTRACT FROM AUTHOR]

This paper highlights the need for intelligent analysis of students' behavioral states in physical education tasks. The hand-ring inertial data is used to identify students' motion sequence states. First, statistical feature extraction is performed based on the acceleration and angular velocity data collected from the bracelet. After completing the filtering and noise reduction of the data, we perform feature extraction by Back Propagation Neural Network (BPNN) and use the sliding window method for analysis. Finally, the classification capability of the model sequence is enhanced by the Hidden Markov Model (HMM). The experimental results indicate that the classification accuracy of student action sequences in physical education exceeds 96% after optimization by the HMM method. This provides intelligent means and new ideas for future student state recognition in physical education and teaching reform. [ABSTRACT FROM AUTHOR]

In this paper, we deal with the estimation of two widely used risk measures such as Value-at-Risk (VaR) and Expected Shortfall (ES) in a cryptocurrency context. To face the presence of regime switching in the cryptocurrency volatilities and the dynamic interconnection between them, we propose a Monte Carlo-based approach using heteroskedastic factor analysis and hidden Markov models (HMM) combined with a structured variational Expectation-Maximization (EM) learning approach. This composite approach allows the construction of a diversified portfolio and determines an optimal allocation strategy making it possible to minimize the conditional risk of the portfolio and maximize the return. The out-ofsample prediction experiments show that the composite factorial HMM approach performs better, in terms of prediction accuracy, than some other baseline methods presented in the literature. Moreover, our results show that the proposed methodology provides the best performing crypto-asset allocation strategies and it is also clearly superior to the existing methods in VaR and ES predictions. [ABSTRACT FROM AUTHOR]

Packet loss concealment (PLC) techniques are utilized to improve the quality of Voice over IP (VoIP) communications by reconstructing missing speech packets. Hidden Markov Model (HMM)-based PLC methods have shown a significant improvement over traditional methods by tracking the statistical evolution of speech signals. However, these methods may result in perceptually disturbing artifacts that arise from the structure of the HMM model. In this study, we introduce HMM-based PLC methods and investigate the impact of Markovian assumptions on their performance, specifically pitch fluctuation and gain mismatching. We then propose a new PLC method implemented on the G.722.2 codec, which incorporates the HMM and Decision Tree (DT) architecture. Our proposed architecture avoids the HMM's emissions dependencies assumption by using a DT layer, resulting in more accurate speech packet regeneration and natural transitions between the synthesized and concealed speech signals. The proposed method uses HMM and DT to track the statistical evolution of speech signals and accurately predict/estimate lost speech packets by exploiting the surrounding received speech packets. The proposed method is evaluated using mathematical proofs, objective, and subjective metrics, with results showing a considerable enhancement in speech quality compared to conventional PLC methods, achieving a Perceptual Evaluation of Speech Quality (PESQ) score higher than 3 at a 20% packet loss ratio. [ABSTRACT FROM AUTHOR]

Understanding the behavior of the human postural system has become a very attractive topic for many researchers. This system plays a crucial role in maintaining balance during both stationary and moving states. Parkinson's disease (PD) is a prevalent degenerative movement disorder that significantly impacts human stability, leading to falls and injuries. This research introduces an innovative approach that utilizes a hidden Markov model (HMM) to distinguish healthy individuals and those with PD. Interestingly, this methodology employs raw data obtained from stabilometric signals without any preprocessing. The dataset used for this study comprises 60 subjects divided into healthy and PD patients. Impressively, the proposed method achieves an accuracy rate of up to 98% in effectively differentiating healthy subjects from those with PD. [ABSTRACT FROM AUTHOR]

The study explored the performance of vowel recognition using an acoustic model built on Audio Fingerprint techniques [1]. The research compares the performance of Support Vector Machines (SVMs), Hidden Markov Models (HMMs), Artificial Neural Networks (ANNs) and k-Nearest Neighbours (k-NN) classifiers in the recognition of isolated and within-word vowels and investigates the importance of different types of acoustic speech features in this process. Temporal, spectral, cepstral, formant, LPC and perceptual features of speech were examined. Importance of features was tested using a random forest classifier. Vowel classification was tested at three confidence levels for feature importance: 90%, 95% and 99%. Two author databases consisting of a total of 1,200 samples from 20 speakers, recorded under household conditions, were used. The classifiers were evaluated by confusion matrix, accuracy, precision, sensitivity and F1 score. A segmentation of words into speech sounds was carried out using a tool based on BiLSTM recurrent neural networks and the BIC criterion. Three most important features were determined: power spectral density, spectral cut-off, and Power-Normalised Cepstral Coefficients. In the isolated vowel recognition task, the SVM classifier was the most effective with a feature significance confidence level of 95% obtaining accuracy = 81%, precision = 81%, sensitivity = 81%, F1 score = 80%. In the task of recognising a vowel within a word, it was verified if the algorithm detected the presence of vowels in the correct segment and if it recognised the correct vowel within it. The best results were obtained by the k-NN classifier (statistical confidence level of feature importance of 99.9%). However, these results were low, correct recognition of the vowel in the word: A, E, U: 20%, I, O: 7%, Y: 23%. This indicates strong influence of the neighbourhood of other speech sounds in speech on the acoustic model of vowels and their recognition. [ABSTRACT FROM AUTHOR]

With the world population growing exponentially reaching 7.8 billion people in 2020, the issue of crowd management has become more difficult especially when the situation requires social distancing (e.g. due to COVID-19). The Internet of Things (IoT) technology can help in tackling such issues. In this article, we propose a behavior analysis-based IoT services architecture for crowd management. We propose to use a behavior analysis approach based on using generative model as Hidden Markov Model to help crowd managers to make good decisions in invoking IoT services. The proposed approach is based on sectioning video segments captured from surveillance cameras of locations that require crowd management into spatio-temporal flow-blocks for marginalization of arbitrarily dense flow field. Then, each flow-block is classified as normal and abnormal. To demonstrate our approach, we used a real case study where crowd management is required namely, Muslim's pilgrimage (i.e. Hajj and Umrah), where real dataset is used for experimenting. The results of the experiments we have conducted are promising in real-time performance. Such results are expected to compare favorably to those found in the literature by other researchers. [ABSTRACT FROM AUTHOR]

The behavior of users concerning mobile Internet varies significantly throughout the day. Results from existing studies—which generally simply segment one day into morning, afternoon, and evening—often provide inaccurate predictions of the behavior of users. To improve prediction accuracy, we propose a segment-based multi-state Markov (SBMSM) model for the dynamic time interval segmentation of the sequential behavior of users. The specific procedure of this proposed model can be described as follows: first, we divide each user's behaviors into minimum unit according to time dimension; then, we merge adjacent time intervals or ensure they are constant according to the similarities in behavior; and finally, a multi-state Markov (MSM) model is trained using the newly constructed data individually. The experimental results illustrate that for 95.78% of users, an SBMSM model performs much better than a naive MSM model and hidden Markov model. [ABSTRACT FROM AUTHOR]

Accurate segregation of retinal blood vessels network plays a crucial role in clinical assessments, treatments, and rehabilitation process. Owing to the presence of acquisition and instrumentation anomalies, precise tracking of vessels network is challenging. For this, a new fundus image segmentation framework is proposed by combining deep neural networks, and hidden Markov model. It has three main modules: the Atrous spatial pyramid pooling-based encoder, the decoder, and hidden Markov model vessel tracker. The encoder utilized modified ResNet18 deep neural networks model for low-and-high-levels features extraction. These features are concatenated in module-II by the decoder to perform convolution operations to obtain the initial segmentation. Previous modules detected the main vessel structure and overlooked some small capillaries. For improved segmentation, hidden Markov model vessel tracker is integrated with module-I and-II to detect overlooked small capillaries of the vessels network. In last module, final segmentation is obtained by combining multi-oriented sub-images using logical OR operation. This novel framework is validated experimentally using two standard DRIVE and STARE datasets. The developed model offers high average values of accuracy, area under the curve, and sensitivity of 99.8, 99.0, and 98.2%, respectively. Analysis of the results revealed that the developed approach offered enhanced performance in terms of sensitivity 18%, accuracy 3%, and specificity 1% over the state-of-the-art approaches. Owing to better learning and generalization capability, the developed approach tracked blood vessels network efficiently and automatically compared to other approaches. The proposed approach can be helpful for human eye assessment, disease diagnosis, and rehabilitation process. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Test & Measurement Technology is the property of Publishing Center of North University of China and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The Part-Of-Speech tagging is widely used in the natural language process. There are many statistical approaches in this area. The most popular one is Hidden Markov Model. In this paper, an alternative approach, linear-chain Conditional Random Fields, is introduced. The Conditional Random Fields is a factor graph approach that can naturally incorporate arbitrary, non-independent features of the input without conditional independence among the features or distributional assumptions of inputs. This paper applied the Conditional Random Fields for the car review word Part-Of-Speech tagging and then the feature extraction, which can be used as an input to an opinion mining system. To reduce the computational time, we also proposed applying the Limited-memory BFGS algorithm to train the Conditional Random Fields. Furthermore, this paper evaluated the Conditional Random Fields and the classical graph approach using the car review dataset to demonstrate that the Conditional Random Fields have a more robust result with a smaller training dataset. [ABSTRACT FROM AUTHOR]

Light‐level geolocators have revolutionised the study of animal behaviour. However, lacking spatial precision, their usage has been primary targeted towards the analysis of large‐scale movements. Recent technological developments have allowed the integration of magnetometers and accelerometers into geolocator tags in addition to barometers and thermometers, offering new behavioural insights.Here, we introduce an R toolbox for identifying behavioural patterns from multisensor geolocator tags, with functions specifically designed for data visualisation, calibration, classification and error estimation. More specifically, the package allows for the flexible analysis of any combination of sensor data using k‐means clustering, expectation maximisation binary clustering, hidden Markov models and changepoint analyses. Furthermore, the package integrates tailored algorithms for identifying periods of prolonged high activity (most commonly used for identifying migratory flapping flight), and pressure changes (most commonly used for identifying dive or flight events).Finally, we highlight some of the limitations, implications and opportunities of using these methods. [ABSTRACT FROM AUTHOR]

This paper proposes a nonparametric approach with the purpose of estimating discrete wavelet transform (DWT) sub-band coefficients for high performance image interpolation. The number of clusters of defined statistical model that represents wavelet coefficients during the learning process is not fixed. The interpolating method is based on Hierarchical Dirichlet Process (HDP) where it uses the Blocked Gibbs Sampling method to obtain the optimum final values. The proposed HDP-HMM exploits statistical inter-scale, and intra-scale dependencies of image sub-bands of three-level decomposed 2D-DWT. It derives sub-bands of low resolution (LR) image, to obtain sub-bands of desired high resolution (HR) image. This research implements Hidden Markov model (HMM) to model the wavelet coefficients, and HDP to model the observations. It uses a very small size dataset that contains both LR and HR images of the dataset. The sophisticated statistical model introduced of the paper has excellent results in terms of Peak-to-Noise Ratio (PSNR), Structural Similarity Index (SSIM), Feature Similarity Index (FSIM), and Edge PSNR (EPSNR). It also has a great capability of repressing disturbing artifact, due to ability to model statistical dependencies of distant pixels. This method, and other compared state-of-the-art methods, have implemented on eighteen test-benches, with different statistical properties. [ABSTRACT FROM AUTHOR]

Weather radars are capable of detecting and displaying storm‐related turbulence as well as precipitation rate with fine spatial resolution and reliable quality. Especially, weather radars can enable the detection of atmospheric conditions in the vicinity of cities and thereby help to notify the strong winds. This article investigates the application of weather radar measurements for predicting strong wind and presents a new method for very short‐term storm prediction. In the proposed method, hidden Markov model (HMM) is used to classify atmospheric conditions to "potentially stormy" and "non‐stormy" states using the available radar data, and semi‐Markov theory is used to estimate the probability of storm occurrence with time. In fact, the probability of transition between "potentially stormy," "non‐stormy," and "stormy" states is modeled by a semi‐Markov model, to find the unconditional probability of storm occurrence with time. The model is implemented with the use of the data of Tehran C‐band weather radar and anemometer of Tehran international airport. Verification results show that the precision (forecast accuracy) is around 0.19 and the recall is around 0.67 in the presented classification method. [ABSTRACT FROM AUTHOR]

Background: To objectively assess a patient's gait, a robust identification of stride borders is one of the first steps in inertial sensor-based mobile gait analysis pipelines. While many different methods for stride segmentation have been presented in the literature, an out-of-lab evaluation of respective algorithms on free-living gait is still missing.Method: To address this issue, we present a comprehensive free-living evaluation dataset, including 146.574 semi-automatic labeled strides of 28 Parkinson's Disease patients. This dataset was used to evaluate the segmentation performance of a new Hidden Markov Model (HMM) based stride segmentation approach compared to an available dynamic time warping (DTW) based method.Results: The proposed HMM achieved a mean F1-score of 92.1% and outperformed the DTW approach significantly. Further analysis revealed a dependency of segmentation performance to the number of strides within respective walking bouts. Shorter bouts ([Formula: see text] strides) resulted in worse performance, which could be related to more heterogeneous gait and an increased diversity of different stride types in short free-living walking bouts. In contrast, the HMM reached F1-scores of more than 96.2% for longer bouts ([Formula: see text] strides). Furthermore, we showed that an HMM, which was trained on at-lab data only, could be transferred to a free-living context with a negligible decrease in performance.Conclusion: The generalizability of the proposed HMM is a promising feature, as fully labeled free-living training data might not be available for many applications. To the best of our knowledge, this is the first evaluation of stride segmentation performance on a large scale free-living dataset. Our proposed HMM-based approach was able to address the increased complexity of free-living gait data, and thus will help to enable a robust assessment of stride parameters in future free-living gait analysis applications. [ABSTRACT FROM AUTHOR]

Threat problem has become more complex in the industrial environment due to the need to secure a large number of devices from attack while maintaining system reliability and real-time response to threats. In such scenario detection of threat in Industrial Internet of things (IIoT) devices becomes an important factor to avoid injection by malicious IIoT devices. The techniques based on the Hidden Markov Models (HMM) are probably the most popular in detecting threat of detection. However, HMM requires extensive training of the models and computational resources. Also, HMM has the drawback of convergence to a local optimum while using Baum–Welch algorithm for parameter estimation. In order to optimize the HMM parameters, global search techniques can be used. This work proposes Genetic algorithms (GA) for optimizing HMM parameters. The other difficulty in threat detection is the dynamic nature of the attack. Several new threats are emerging with many variants which are created from existing attacks, making threat modeling an arduous task. As a result, good features are critical to model traffic and provide an efficient way to detect known and possibly unknown attacks to detect. To achieve a better feature extraction from the network traffic, we propose a dynamic sliding window W which has a width of w . The proposed multiple-HMM performs well to detect threats. The simulation results are compared to the results obtained by the Baum–Welch algorithm based approach showing higher accuracy and convergences. [ABSTRACT FROM AUTHOR]

Radio Frequency (RF) analog circuit failures often occur in broadband, high voltage and high temperature environment, so how to determine fault location and forecast the time which failure is going to occur is an important topic. Based on actual working data of RF Low Noise Amplifier (LNA), a kind of RF circuit fault diagnosis method is put forward with the combination of K-means Clustering, Support Vector Machine (SVM) and Hidden Markov Model (HMM).Simulation results show that the combined method has (3 ~ 4)% recognition accuracy higher than that of the single algorithm. The proposed prognosis method is highly efficient in RF analog circuit fault diagnosis. [ABSTRACT FROM AUTHOR]

Text information depends primarily on natural languages processing. Improving the security and usability of text information shared through the public internet has therefore been the most demanding problem facing researchers. In contact and knowledge sharing through the Internet, the authentication of content and the identification of digital content are becoming a key problem. Therefore, in this paper, a fragile approach of zero-watermarking based on natural language processing has been developed for authentication of content and prevention of misuse of Arabic texts distributed over the Internet. According to the proposed approach, watermark embedding, and identification was technically carried out such that the initial text document did not need to be changed to embed a watermark. The automated zero-watermarking approaches have been combined with a second-tier word order framework based on the Markov model to boost the effi- ciency, precision, ability, and fragility of the existing researches. This second-tier of the Markov-model has been used as a natural language processing technique to analyze Arabic-text and extract the features of the interrelationship between textual contexts. Moreover, the extracted features have been utilized as information of watermark and then validated to identify any possible tampering with the attacked Arabic-text. The recommended solution has been applied with VS code IDE using PHP. The experimental results using four datasets of varying size show that the proposed approach can obtain better detection accuracy of tampering attacks, effectiveness and high fragility for common random insertion, reorder and deletion attacks for common attacks, e.g., Comparison results with baseline approaches also show the advantages of the proposed approach. [ABSTRACT FROM AUTHOR]

Uncertainty is a key problem in remaining useful life (RUL) prediction, and measures to reduce uncertainty are necessary to make RUL prediction truly practical. In this paper, a right-time prediction method is proposed to reduce the prognostics uncertainty of mechanical systems under unobservable degradation. Correspondingly, the whole RUL prediction process is divided into three parts, including offline modelling, online state estimating and online life predicting. In the offline modelling part, hidden Markov model (HMM) and proportional hazard model (PHM) are built to map the whole degradation path. During operation, the degradation state of the object is estimated in real time. Once the last degradation state reached, the degradation characteristics are extracted, and the survival function is obtained with the fitted PHM. The proposed method is demonstrated on an engine dataset and shows higher accuracy than traditional method. By fusing the extracted degradation characteristics, the obtained survival function can be basis for optimal maintenance with lower uncertainty. [ABSTRACT FROM AUTHOR]

In this paper, a hybrid intelligent text zero-watermarking approach has been proposed by integrating text zero-watermarking and hidden Markov model as natural language processing techniques for the content authentication and tampering detection of Arabic text contents. The proposed approach known as Second order of Alphanumeric Mechanism of Markov model and Zero-Watermarking Approach (SAMMZWA). Second level order of alphanumeric mechanism based on hidden Markov model is integrated with text zero-watermarking techniques to improve the overall performance and tampering detection accuracy of the proposed approach. The SAMMZWA approach embeds and detects the watermark logically without altering the original text document. The extracted features are used as a watermark information and integrated with digital zero-watermarking techniques. To detect eventual tampering, SAMMZWA has been implemented and validated with attacked Arabic text. Experiments were performed on four datasets of varying lengths under multiple random locations of insertion, reorder and deletion attacks. The experimental results show that our method is more sensitive for all kinds of tampering attacks with high level accuracy of tampering detection than compared methods. [ABSTRACT FROM AUTHOR]

Part of speech (POS) tagging is an indispensable part of major NLP models. Its progress can be perceived on number of languages around the globe especially with respect to European languages. But considering Indian Languages, it has not got a major breakthrough due lack of supporting tools and resources. Particularly for Odia language it has not marked its dominancy yet. With a motive to make the language Odia fit into different NLP operations, this paper makes an attempt to develop a POS tagger for the said language on a HMM (Hidden Markov Model) platform. The tagger judiciously considers bigram HMM with dynamic Viterbi algorithm to give an output annotated text with maximum accuracy. The model is experimented on a corpus belonging to tourism domain accounting to a size of approximately 0.2 million tokens. With the proportion of training and testing as 3:1, the proposed model exhibits satisfactory result irrespective of limited training size. [ABSTRACT FROM AUTHOR]

Copyright of Control Theory & Applications / Kongzhi Lilun Yu Yinyong is the property of Editorial Department of Control Theory & Applications and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

• A method for human behaviour modelling is proposed. • A real world open dataset was used to train and test the model. • A formal definition of human behaviour is given in the present study. • Abnormal behaviour detection was accomplished based on a probabilistic model. Human behaviour modelling for welfare technology is the task of recognizing a person's behaviour patterns in order to construct a safe environment for that person. It is useful in building environments for older adults or to help any person in his or her daily life. The aim of this study is to model the behaviour of a person living in a smart house environment in order to detect abnormal behaviour and assist the person if help is needed. Hidden Markov models, location of the person in the house, posture of the person, and time frame rules are implemented using a real-world, open-source dataset for training and testing. The proposed model presented in this study models the normal behaviour of a person and detects anomalies in the usual pattern. The model shows good results in the identification of abnormal behaviour when tested. [ABSTRACT FROM AUTHOR]

In this paper, we propose a novel script-independent approach for word spotting in printed and handwritten multi-script documents. Since each writing type and script need to be processed using a specific spotting engine, the proposed system proceeds on two stages. The script identification is a preliminary stage that aims at recognizing on one level the writing type and the script of the input image document. Second, a specific word spotting method is used to spot query words in a large collection of documents. The proposed spotting system is based on deep bidirectional long short-term memory neural network and hidden Markov model (HMM) hybrid architecture. It takes advantage of DNN's strong representation learning power and HMM's sequential modeling ability. The global system has been evaluated on a mixed corpus of public databases such as KHATT, PKHATT for Arabic script and RIMES for Latin script. The experimental results on script identification and keyword spotting confirm the effectiveness of the proposed approach. [ABSTRACT FROM AUTHOR]

Telugu language is one of the important languages in the world. The language that is spoken by most of the people in a region is called as dialect. In the recent days, speech recognition system is present in almost all electronic devices. In this, dialects of particular language perform a vital role. The accurate dialects identification technique helps in not only enhancing its features but also expected to provide in modern services in health and telemedicine for older and homebound peoples. Like any other language, even Telugu language has diversified itself into different dialects viz., Telangana, Kostha Andhra, and Rayalaseema. Combination of all the dialects is the language TELUGU and it is a perfect blend of elegance in Sanskrit, sweetness in Tamil along with the essence of Kannada language. The formation of dialects can be of different reasons. For speech processing research, till today there is no standard speech database created for Telugu dialects. In this paper we developed a speech database that can be utilized for the recognition of Telugu dialects and we had applied two modeling techniques that are, Hidden Markov Model (HMM) and Gaussian mixture model (GMM) in order to recognize the dialects of Telugu language by using speech independant utterances. We imposed Mel-Frequency Cepstral Coefficient for extracting the spectral features from the obtained speech data and observed that GMM provides better accurate results than HMM. [ABSTRACT FROM AUTHOR]

In the field of medical informatics, sleep staging is a challenging and time-consuming task undertaken by sleep experts. According to the new standard of the American Academy of Sleep Medicine (AASM), the stages of sleep are divided into wakefulness (W), rapid eye movement (REM) and non-rapid eye movement (NREM) which includes three sleep stages (N1, N2 and N3) that describe the depth of sleep. This study aims to establish an automatic sleep staging algorithm based on the improved weighted random forest (WRF) and Hidden Markov Model (HMM) using only the features extracted from double-channel EEG signals. The WRF classification model focuses on reducing the bias of the imbalance data, while the HMM model focuses on improving the detection rate of sleep staging through the relationship between adjacent sleep stages. In particular, the improved weighted RF classification model can increase the recognition rate of the N1 stage. In addition, the method of removing features with low variance is used to select meaningful and contributing feature parameters for model training. This is an innovative content of this paper. The sleep EEG data are first segmented into 30 s epochs, and the feature parameters of the epoch data are extracted from the double-channel by applying continuous wavelet packet transform (WPT). Each epoch is then segmented into 29 subepochs of 2 s long with 1 s overlap, and the frequency domain features and statistical features of each subepoch are extracted. The performance of the proposed method is tested by evaluating the accuracy (AC), Kappa coefficient, Recall (R), Precision (P) and F1-score (F1). In the Sleep-EDF database, the overall AC and Kappa coefficient obtained by WRF are 93.20% and 0.890, respectively using the subject-non-independent test. In the 10 sc* and 10 st* Sleep-EDF Expanded database, the overall AC and Kappa coefficient obtained by proposed method are 91.97% and 0.874, respectively using the subject-independent test. The best AC and Kappa coefficient of single subject can reach 96.3% and 0.912, respectively. Experimental results show that the performance of the proposed method is competitive with the most current methods and results, and the recognition rate of N1 stage is significantly improved. [ABSTRACT FROM AUTHOR]

We consider estimating the proportion of true null hypotheses in multiple testing problems. A traditional multiple testing rate, family-wise error rate is too conservative and old to control type I error in multiple testing setups; however, false discovery rate (FDR) has received significant attention in many research areas such as GWAS data, FMRI data, and signal processing. Identify differentially expressed genes in microarray studies involves estimating the proportion of true null hypotheses in FDR procedures. However, we need to account for unknown dependence structures among genes in microarray data in order to estimate the proportion of true null hypothesis since the genuine dependence structure of microarray data is unknown. We compare various procedures in simulation data and real microarray data. We consider a hidden Markov model for simulated data with dependency. Cai procedure (2007) and a sliding linear model procedure (2011) have a relatively smaller bias and standard errors, being more proper for estimating the proportion of true null hypotheses in simulated data under various setups. Real data analysis shows that 5 estimation procedures among 9 procedures have almost similar values of the estimated proportion of true null hypotheses in microarray data. [ABSTRACT FROM AUTHOR]

In this paper, we propose a spectrum sharing protocol wherein the sharing is performed in a situation without introducing a secondary transmitter in assisting the primary system. Specifically, in the primary system, the primary receiver after achieving its target rate helps a secondary receiver to achieve its target using the remaining power left with it. We study the optimization of power with increased QoS and Experience for both the primary systems and the secondary receivers while the former has a higher priority. Additionally Hidden Markov Model has been used for resource allocation in the proposed model to achieve high spectrum efficiency and energy efficiency. The main emphasis of the model is in an urban deployment scenario as we are heading towards ultra-dense network for next generation networks. Extensive simulations have been carried out and the results demonstrate the performance of the proposed spectrum sharing protocol in comparison to some other power allocation techniques and opportunistic spectrum sharing model. The proposed model achieves high power optimization, increased throughput and access rate along with better QoE. The results confirm the efficiency of the proposed protocol for both the primary and the secondary system. [ABSTRACT FROM AUTHOR]

Speech recognition technology has been in use for a long time but with the last advancements of mobile device technology, it is now easier to get access to it. Nowadays, people use speech recognition speaking to their smartphones, using their voices to interact with it. The recognition process is also faster, more effective and more efficient due to new computer architectures that bring more computational power and as a result of machine learning advancements. Nowadays, to conduct speech recognition, we can consider a scenario where a user records its speech with a smartphone, sends it to a server, and the server performs the recognition using the recognition models and the computational power it has. But Security system may be defined as mixing between multi method and tools to improve goal. The use of Garbled Circuits was only been seen as of theoretical interest for a long time, but with last year advances, they are now starting to be tested and used in some practical scenarios. Hidden Markov Models are widely used models in speech recognition representing the acoustic characteristics of spoken language. This paper introduces the study security-preserving speech recognition and walk. Using Hidden Markov Models and Garbled Circuits. [ABSTRACT FROM AUTHOR]

Markov regime switching models remain enormously popular in speech recognition, economics, finance, etc. Nonparametric segmentation in switching models without probability assignment of jump moments is in many papers by Brodsky and Darkhovsky. We model all regimes as long SCOT strings. Stochastic COntext Tree (abbreviated as SCOT) is m -Markov Chain (m -MC) with every state of a string independent of the symbols in its more remote past than the context of length determined by the preceding symbols of this state. A parallel super-fast fitting and asymptotically optimal inference in a sparse SCOT model including the nonparametric homogeneity test are described in our previous papers. Our segmentation method is a combination of preliminary online change point detection with its subsequent offline Maximal Likelihood update. [ABSTRACT FROM AUTHOR]

Hidden Markov model (HMM) based text-to-speech (TTS) has become one of the most promising approaches, as it has proven to be a particularly flexible and robust framework to generate synthetic speech. However, several factors such as mel-cepstral vocoder and over-smoothing are responsible for causing quality degradation of synthetic speech. This paper presents an HMM speech synthesis technique based on the modified discrete cosine transform (MDCT) representation to cope with these two issues. To this end, we use an analysis/synthesis technique based on MDCT that guarantees a perfect reconstruction of the signal frame from feature vectors and allows for a 50% overlap between frames without increasing the data vector, in contrast to the conventional mel-cepstral spectral parameters that do not ensure direct speech waveform reconstruction. Experimental results show that a sound of good quality, conveniently evaluated using both objective and subjective tests, is obtained. [ABSTRACT FROM AUTHOR]

Abstract Occupant presence and behaviour in buildings is considered a key element towards building intelligent and pervasive environments. Yet, practical applications of energy intelligent buildings typically suffer from high sensor unreliability. In this work, we propose a layered probabilistic framework for occupancy-based control in intelligent buildings. We adopt a cascade of layers, where each layer addresses different aspects of the occupancy detection problem in a probabilistic manner rather than in a hard rule engine. We show that propagating uncertainty through each layer instead of standard hard decision outcomes improves the overall system performance. This finding suggests that smart building interfaces and communication data formats may need to input and output probabilistic data rather than simple discrete classification outputs. System performance and user comfort were evaluated with real life radar sensor data, based on an algorithm that allows real-time (casual) processing. Energy savings of up to 30% were obtained, compared to baseline measurements, while maintaining user comfort. [ABSTRACT FROM AUTHOR]

The majority of handwritten word recognition strategies are constructed on learning-based generative frameworks from letter or word training samples. Theoretically, constructing recognition models through discriminative learning should be the more effective alternative. The primary goal of this research is to compare the performances of discriminative and generative recognition strategies, which are described by generatively-trained hiddenMarkov modeling (HMM), discriminatively-trained conditional random fields (CRF) and discriminatively-trained hidden-state CRF (HCRF).With learning samples obtained from two dissimilar databases, we initially trained and applied an HMMclassification scheme. To enable HMMclassifiers to effectively reject incorrect and out-of-vocabulary segmentation, we enhance the models with adaptive threshold schemes. Aside from proposing such schemes for HMMclassifiers, this research introduces CRF and HCRF classifiers in the recognition of offline Arabic handwritten words. Furthermore, the efficiencies of all three strategies are fully assessed using two dissimilar databases. Recognition outcomes for both words and letters are presented, with the pros and cons of each strategy emphasized. [ABSTRACT FROM AUTHOR]

This paper presents a method to estimate and synthesize the motion of a character’s fingers in real-time during the performance capture process. For the motion estimation and synthesis process, different motion datasets are used that contain the full-body motion of a character, including the motion of its fingers. The motion datasets have been pre-processed for being efficiently handled in real-time estimation process. During the runtime of the application, the system recognizes the actions of the user’s hands and assembles the necessary motion of the character’s fingers. By using a hierarchical Hidden Markov Model (HMM), the system learns the phase of the gestures as well as the progress of the motion. To eliminate the searching process of the most probable motion, prior constraints between segment states were assigned manually. During the runtime of our application, by using a forward HMM algorithm, the system synthesizes the necessary motion of a character’s fingers in real-time. The presented methodology is evaluated both numerically (system performance and estimation rate) and perceptually. The results show that, even when a reduced number of finger gestures are used, the synthesized motion can be described as perceptually consistent with the ground truth motion data. [ABSTRACT FROM AUTHOR]

Named entity (NE) recognition (NER) is a process to identify and classify atomic elements such as person name, organization name, place/location name, quantities, temporal expressions, and monetary expressions in running text. In this paper, the Hindi NER task has been mapped into a multiclass learning problem, where the classes are NE tags. This paper presents a solution to this Hindi NER problem using a memory-based learning method. A set of simple and composite features, which includes binary, nominal, and string features, has been defined and incorporated into the proposed model. A relatively small Hindi Gazetteer list has also been employed to enhance the system performance. A comparative study on the experimental results obtained by the memory-based NER system proposed in this paper and a hidden Markov model (HMM)-based NER system shows that the performance of the proposed memory-based NER system is comparable to the HMM-based NER system. [ABSTRACT FROM AUTHOR]

Background: Renewable biopolymers, such as cellulose, starch and chitin are highly resistance to enzymatic degradation. Therefore, there is a need to upgrade current degradation processes by including novel enzymes. Lytic polysaccharide mono-oxygenases (LPMOs) can disrupt recalcitrant biopolymers, thereby enhancing hydrolysis by conventional enzymes. However, novel LPMO families are difficult to identify using existing methods. Therefore, we developed a novel profile Hidden Markov model (HMM) and used it to mine genomes of ascomycetous fungi for novel LPMOs. Results: We constructed a structural alignment and verified that the alignment was correct. In the alignment we identified several known conserved features, such as the histidine brace and the N/Q/E-X-F/Y motif and previously unidentified conserved proline and glycine residues. These residues are distal from the active site, suggesting a role in structure rather than activity. The multiple protein alignment was subsequently used to build a profile Hidden Markov model. This model was initially tested on manually curated datasets and proved to be both sensitive (no false negatives) and specific (no false positives). In some of the genomes analyzed we identified a yet unknown LPMO family. This new family is mostly confined to the phyla of Ascomycota and Basidiomycota and the class of Oomycota. Genomic clustering indicated that at least some members might be involved in the degradation of β-glucans, while transcriptomic data suggested that others are possibly involved in the degradation of pectin. Conclusions: The newly developed profile hidden Markov Model was successfully used to mine fungal genomes for a novel family of LPMOs. However, the model is not limited to bacterial and fungal genomes. This is illustrated by the fact that the model was also able to identify another new LPMO family in Drosophila melanogaster. Furthermore, the Hidden Markov model was used to verify the more distant blast hits from the new fungal family of LPMOs, which belong to the Bivalves, Stony corals and Sea anemones. So this Hidden Markov model (Additional file 3) will help the broader scientific community in identifying other yet unknown LPMOs. [ABSTRACT FROM AUTHOR]

This Segmentation of manuscripts into text-lines and words is an important step to make recognition systems more efficient and accurate. One of the problems making this task crucial is the presence of touching components which are connections between characters of successive text-lines, words of the same text-line or characters of a word. This work proposes an automatic system for Arabic manuscript recognition. The proposed system is based on a stochastic model of type HMM (Hidden Markov Model). First, it segments the manuscript into text-lines and words while solving the touching component problem using the shape context descriptor. Then, it extracts some structural features from word images and trains a Markovian classifier to recognize them. The performance of the proposed system is assessed using samples extracted from historical handwritten documents. The obtained results are encouraging. We achieved an average rate of recognition of 87%. [ABSTRACT FROM AUTHOR]

The fast and affordable sequencing of large clinical and environmental metagenomic datasets opens up new horizons in medical and biotechnological applications. It is believed that today we have described only about 1% of the microorganisms on the Earth, therefore, metagenomic analysis mostly deals with unknown species in the samples. Microbial communities in extreme environments may contain genes with high biotechnological potential, and clinical metagenomes, related to diseases, may uncover still unknown pathogens and pathological mechanisms in known diseases. While the species-level identification and description of the taxa in the samples do not seem to be possible today, we can search for novel genes with known functions in these samples, using numerous techniques, including artificial intelligence tools, like the hidden Markov models (HMMs). Here we describe a simple-to-use webserver, the MetaHMM, which is capable of homology-based automatic model-building for the genes to be searched for, and it also finds the closest matches in the metagenome. The webserver uses already highly successful building blocks: it performs multiple alignments by applying Clustal Omega, builds a hidden Markov model with HMMER components of hmmbuild and uses hmmsearch for finding similar sequences to the specified model in the metagenomes. The webserver is publicly available at https://metahmm.pitgroup.org. • Metagenomics data yields a rich treasury of genomic information. • Advanced, fast and easy-to-use tools are needed to exploit this plenty. • We present here the MetaHMM webserver for finding new genes in metagenomes. • Hidden Markov Models are applied in the search for still unknown genes. • The webserver is available at https://metahmm.pitgroup.org. [ABSTRACT FROM AUTHOR]

Replica exchange molecular dynamics (REMD) is a popular method to accelerate conformational sampling of complex molecular systems. The idea is to run several replicas of the system in parallel at different temperatures that are swapped periodically. These swaps are typically attempted every fewMD steps and accepted or rejected according to a Metropolis-Hastings criterion. This guarantees that the joint distribution of the composite system of replicas is the normalized sum of the symmetrized product of the canonical distributions of these replicas at the different temperatures. Here we propose a different implementation of REMD in which (i) the swaps obey a continuous-time Markov jump process implemented via Gillespie's stochastic simulation algorithm (SSA), which also samples exactly the aforementioned joint distribution and has the advantage of being rejection free, and (ii) this REMD-SSA is combined with the heterogeneous multiscale method to accelerate the rate of the swaps and reach the so-called infinite-swap limit that is known to optimize sampling efficiency. The method is easy to implement and can be trivially parallelized. Here we illustrate its accuracy and efficiency on the examples of alanine dipeptide in vacuum and C-terminal β-hairpin of protein G in explicit solvent. In this latter example, our results indicate that the landscape of the protein is a triple funnel with two folded structures and one misfolded structure that are stabilized by H-bonds. [ABSTRACT FROM AUTHOR]

This paper presents a technique for learning hidden Markov model (HMM) state sequences from phonemes, that combined with modified discrete cosine transform (MDCT), is useful for speech synthesis. Mel-cepstral spectral parameters, currently adopted in the conventional methods as features for HMM acoustic modeling, do not ensure direct speech waveforms reconstruction. In contrast to these approaches, we use an analysis/synthesis technique based on MDCT that guarantees a perfect reconstruction of the signal frame feature vectors and allows for a 50% overlap between frames without increasing the data rate. Experimental results show that the spectrograms achieved with the suggested technique behave very closely to the original spectrograms, and the quality of synthesized speech is conveniently evaluated using the well known Itakura-Saito measure. [ABSTRACT FROM AUTHOR]

Cattle supply an important source of nutrition for humans in the world. CpG islands (CGIs) are very important and useful, as they carry functionally relevant epigenetic loci for whole genome studies. As a matter of fact, there have been no formal analyses of CGIs at the DNA sequence level in cattle genomes and therefore this study was carried out to fill the gap. We used hidden markov model algorithm to detect CGIs. The total number of predicted CGIs for cattle was 90668. The number of detected CGIs and CGI densities downwardly varied across chromosomes. Chromosome 25 had the largest number of CGIs (4556) and the highest CGI density (106.20 CGIs/Mb). A significant positive correlation observed among CGI densities with guanine-cytosine (GC) content, ObsCpG/ExpCpG, recombination rate and gene density. When the size of chromosomes increased, the CGI densities decreased and a trend of higher CGI densities in the telomeric regions observed. This feature may be the reason of a positive correlation between CGI density and recombination rate. To detect information on CGI density differences between cattle and other vertebrate genomes, CGI density was also scanned in eleven vertebrate genomes. The CGI densities varied greatly among genomes. These discoveries may contribute to a better understanding of epigenomic role of CGIs and their molecular evolution in the cattle. [ABSTRACT FROM AUTHOR]

Given the ability of fuzzy systems to make decisions in uncertainties such as morphology, and the huge number of studies conducted on morphology, this study first suggests a fuzzy morphology; then, it discusses the effectiveness of types of N-gram labeling methods to identify the role of words in Persian compounds. To find the optimal labeling, then, a new hybrid method is expressed for N-gram labeling. In relation to compound sentences, two independent roles including subject, governing predicate, predicate, object and complement and dependent roles including noun, adverb, governing genitives, genitives, bending, retroactive, apposition, exclamation and annunciator are studied. To compare the success rate of the proposed fuzzy method, existingHMM(hidden Markov model) is studied to identify the role of words in three different label types. The results of this comparison showed that the success rates of hybrid labeling and Bi-gram labeling are closed in both models. Thus, these two methods have been successful in both morphological models compared to Uni-gram labeling. It is worth noting, the highest success rate was related to fuzzy morphology and Bi-gram labeling. [ABSTRACT FROM AUTHOR]

Although many test case prioritization techniques exist, their performance is far from perfect. Hence, we propose a new fault-based test case prioritization technique to promote fault-revealing test cases in modelbased testing (MBT) procedures. We seek to improve the fault detection rate--a measure of how fast a test suite is able to detect faults during testing--in scenarios such as regression testing. We propose an extended digraph model as the basis of this new technique. The model is realized using a novel reinforcement-learning (RL)- and hidden-Markov-model (HMM)-based technique which is able to prioritize test cases for regression testing objectives. We present a method to initialize and train an HMM based upon RL concepts applied to an application's digraph model. The model prioritizes test cases based upon forward probabilities, a new test case prioritization approach. In addition, we also propose an alternative approach to prioritizing test cases according to the amount of change they cause in applications. To evaluate the effectiveness of the proposed techniques, we perform experiments on graphical user interface (GUI)-based applications and compare the results with state-of-the-art test case prioritization approaches. The experimental results show that the proposed technique is able to detect faults early within test runs. [ABSTRACT FROM AUTHOR]

The stochastic signal model, hidden Markov model (HMM), is a probabilistic function of the Markov chain. In this letter, we propose a general nth-order HMM based dynamic texture description and classification method. Specifically, the pixel intensity sequence along time of a dynamic texture is modeled with a HMM that encodes the appearance information of the dynamic texture with the observed variables, and the dynamic properties over time with the hidden states. A new dynamic texture sequence is classified to the category by determining whether it is the most similar to this category with the probability that the observed sequence is produced by the HMMs of the training samples. The experimental results demonstrate the arbitrary emission probability distribution and the higher-order dependence of hidden states of a higher-order HMM result in better classification performance, as compared with the linear dynamical system (LDS) based method. [ABSTRACT FROM AUTHOR]

Emphasis plays an important role in expressive speech synthesis in highlighting the focus of an utterance to draw the attention of the listener. We present a hidden Markov model (HMM)-based emphatic speech synthesis model. The ultimate objective is to synthesize corrective feedback in a computer-aided pronunciation training (CAPT) system. We first analyze contrastive (neutral versus emphatic) speech recording. The changes of the acoustic features of emphasis at different prosody locations and the local prominences of emphasis are analyzed. Based on the analysis, we develop a perturbation model that predicts the changes of the acoustic features from neutral to emphatic speech with high accuracy. Further based on the perturbation model we develop an HMM-based emphatic speech synthesis model. Different from the previous work, the HMM model is trained with neutral corpus, but the context features and additional acoustic-feature-related features are used during the growing of the decision tree. Then the output of the perturbation model can be used to supervise the HMM model to synthesize emphatic speeches instead of applying the perturbation model at the backend of a neutral speech synthesis model directly. In this way, the demand of emphasis corpus is reduced and the speech quality decreased by speech modification algorithm is avoided. The experiments indicate that the proposed emphatic speech synthesis model improves the emphasis quality of synthesized speech while keeping a high degree of the naturalness. [ABSTRACT FROM AUTHOR]

Eastern gray squirrels produce alarm calls -- vocalizations used in the presence of danger that influence the behavior of some receivers. This influence is possible because the alarm calls' rate, duration, and structure contain information about the threat and the caller. Gray squirrels' mix of different structural call types (kuks and quaas) could contain information on potential internal influences within the squirrel. Hidden Markov models (HMMs) are ideal tools to investigate whether hidden states explain the frequencies of kuks versus quaas throughout an alarm call sequence. In this study, we compare the ability of an iid (independent and identically distributed) model and two- to six-state HMMs to represent observed sequences of kukking, quaaing, and periods of silence. Audio recordings of 44 gray squirrels were collected and the first 30 s of each alarm call sequence was coded based on spectrograms. A number of HMMs were fitted, and the overall fit of the observed sequences to each model was assessed using Akaike's Information Criterion (AIC) and Bayesian Information Criterion (BIC), and Monte Carlo methods. The five-state HMM fit the observed call frequencies better than the other models, suggesting that the squirrels' alarm calling sequences are influenced by a more complex temporal sequencing of acoustic units. [ABSTRACT FROM AUTHOR]

This paper presents an innovative consumption-modeling system applied to digital TV, able to infer the user interest regarding the TV contents. The user interest inferred is used to feed content recommender systems, and it has been tested in real scenarios involving real users. The modeling system uses as input the TV consumption data and performs an algorithm based on a Hidden Markov Model and Bayesian inference techniques to infer the said user interest. Real data have been picked up in real time to feed our modeling, and the final results have been checked comparing with user's tastes, which have been expressed through a set of questionnaires and the whole system has been tested in a TV broadcasting scenario with real users. Conclusions show that our system improves the reliability from classic user interest modeling systems (they are mainly based on explicit opinion based methods, which can be intrusive for general users and could show certain deceptive results, as it is described in this paper). [ABSTRACT FROM AUTHOR]

Background: The C2H2 zinc-finger (ZNF) containing gene family is one of the largest and most complex gene families in metazoan genomes. These genes are known to exist in almost all eukaryotes, and they constitute a major subset of eukaryotic transcription factors. The genes of this family usually occur as clusters in genomes and are thought to have undergone a massive expansion in vertebrates by multiple tandem duplication events (BMC Evol Biol 8:176, 2008). Results: In this study, we combined two popular approaches for homolog detection, Reciprocal Best Hit (RBH) (Proc Natl Acad Sci USA 95:6239-6244, 1998) and Hidden-Markov model (HMM) profiles search (Bioinformatics 14:755-763, 1998), on a diverse set of complete genomes of 124 eukaryotic species ranging from excavates to humans to identify all detectable members of 37 C2H2 ZNF gene families. We succeeded in identifying 3,890 genes as distinct members of 37 C2H2 gene families. These 37 families are distributed among the eukaryotes as progressive additions of gene blocks with increasing complexity of the organisms. The first block featuring the protists had 7 families, the second block featuring plants had 2 families, the third block featuring the fungi had 2 families (one of which was also present in plants) and the final block consisted of metazoans with 25 families. Among the metazoans, the simpler unicellular metazoans had just 15 of the 25 families while most of the bilaterians had all 25 families making up a total of 37 families. Multiple potential examples of lineage-specific gene duplications and gene losses were also observed. Conclusions: Our hybrid approach combines features of the both RBH and HMM methods for homolog detection. This largely automated technique is much faster than manual methods and is able to detect homologs accurately and efficiently among a diverse set of organisms. Our analysis of the 37 evolutionarily conserved C2H2 ZNF gene families revealed a stepwise appearance of ZNF families, agreeing well with the phylogenetic relationship of the organisms compared and their presumed stepwise increase in complexity (Science 300:1694, 2003). [ABSTRACT FROM AUTHOR]

Abstract: Automatic structure discovery is desirable in many Markov model applications where a good topology (states and transitions) is not known a priori. CSSR is an established pattern discovery algorithm for stationary and ergodic stochastic symbol sequences that learns a predictively optimal Markov representation consisting of so-called causal states. By means of a novel algebraic criterion, we prove that the causal states of a simple process disturbed by random errors frequently are too complex to be learned fully, making CSSR diverge. In fact, the causal state representation of many hidden Markov models, representing simple but noise-disturbed data, has infinite cardinality. We also report that these problems can be solved by endowing CSSR with the ability to make approximations. The resulting algorithm, robust causal states (RCS), is able to recover the underlying causal structure from data corrupted by random substitutions, as is demonstrated both theoretically and in an experiment. The algorithm has potential applications in areas such as error correction and learning stochastic grammars. [Copyright &y& Elsevier]

This paper design a wearable gesture recognition system. Improved SWAB automatic endpoint detection algorithm is proposed in this paper. The K-means is employed to compute gesture vector quantization. Then the data as the input of hidden Markov model (HMM) is used to acquire the classification information. Experiments show that is an effective method for gesture recognition [ABSTRACT FROM AUTHOR]