Search

Considering the dynamic nature of market conditions, this paper introduces a state-dependent futures hedging optimization model and methodology. This approach dynamically adjusts the traditional model-driven hedging strategy, effectively balancing the pursuit of returns with the imperative of risk mitigation. Empirical evidence shows that integrating Hidden Markov Model (HMM) with machine learning techniques, as demonstrated in this study, improves the accuracy of market state forecasts. Compared to the traditional model-driven hedging strategy, the innovative state-dependent hedging strategy introduced here significantly enhances the return-to-risk ratio, and revenue, without increasing hedging risks. Moreover, the hedging portfolio developed under this strategy achieves an average hedging efficiency of 0.76, highlighting the effectiveness of the proposed methodology. Additional robustness tests indicate that this market state-dependent hedging optimization strategy is promising under various conditions, including different position adjustment ratios, volatility benchmarks, evaluation periods, types of crude oil, and transaction costs. The research conducted in this paper not only contributes to and expands traditional hedging theories but also provides a practical risk management solution for market participants. • A state-dependent hedging strategy is proposed. • A state prediction model combining HMM and machine learning is established. • The hedging model effectively balances the pursuit of returns with the imperative of risk mitigation. [ABSTRACT FROM AUTHOR]

• The method based on HMM uses features such as spectral line energy and stability. • The algorithm improves the state transition and can detect spectral line length. • The algorithm is fast at extracting weak and adjacent spectral lines. To address the difficulty of extracting weak spectral lines from signals received by passive sonar, we propose a spectral line extraction scheme based on an improved hidden Markov model (HMM). A new state transition probability based on spectral line features is proposed that solves the problem of state transition probability relying on prior information in traditional HMMs. Using a peak detection algorithm and a parallel processing framework reduces computation. We employ the boxplot method to remove the outliers from the spectral lines caused by strong noise and compensate for them. By improving the forward–backward probability calculation method through a peak penalty factor, we manage adjacent spectral lines prone to be missed by traditional HMMs. Lastly, we use dynamic sliding windows to determine a spectral line's birth and death. Data verification by simulations and sea tests show that our algorithm extracts spectral lines better and with a smaller error, accurately detects the birth and death of spectral lines, and is faster than traditional HMM algorithms. [ABSTRACT FROM AUTHOR]

• Proposed a cutting-edge technique for cardiopulmonary sound separation. • This paper investigates cardiorespiratory auscultation using uniquely integrated MCRA-OMLSA and NMF-HMM techniques. • Unsupervised learning method to enhance signal accuracy without reliance on external data. Increasing the accuracy and efficiency of cardiopulmonary disease screening is crucial, as cardiovascular illnesses pose a serious threat to human health and result in numerous fatalities annually around the globe. For doctors to assess the illness, auscultation is a non-invasive technique. An electronic stethoscope records heart sounds (HS) and lung sounds (LS), which are useful acoustic data for diagnosing pulmonary diseases. Nevertheless, interference between LS and HS that is visible in the frequency and temporal domains hinders the effectiveness of the diagnostic process. Moreover, conducting any prior training is not always feasible in many real-world situations. It is very challenging to prepare pure lung and heart sounds. This paper proposes an integrated approach using a minima-controlled recursive algorithm (MCRA) equipped with optimally modified-log spectral amplitude (OMLSA), a trainable time wrapping technique (TTW), and a non-negative matrix factorization-hidden Markov model (NMF-HMM) to effectively separate lung and heart sounds, knowing nothing about the heart or lung sounds beforehand. A detailed investigation in terms of unsupervised framework is provided in this paper. This study is the first to apply the integrated OMLSA-TTW-NMF-HMM approach to cardiopulmonary sounds separation and presents the HLS classification method. This research proposes a framework with improved robustness and separation quality compared to existing state-of-the-art techniques. [ABSTRACT FROM AUTHOR]

With an aging population, the patients with valvular heart disease (VHD) are growing worldwide, and valve replacement is a primary choice for these patients with severe valvular disease. Among them, bioprosthetic heart valves (BHVs), especially BHVs trough transcatheter aortic valve replacement, are widely accepted by patients on account of their good hemodynamics and biocompatibility. Commercial BHVs in clinic are prepared by glutaraldehyde cross-linked pericardial tissue with the risk of calcification and thrombotic complications. In the present study, a strategy combines improved hemocompatibility and anti-calcification properties for BHVs has been developed based on a novel non-glutaraldehyde BHV crosslinker hexakis(hydroxymethyl)melamine (HMM) and the anticoagulant fucoidan. Besides the similar mechanical properties and enhanced component stability compared to glutaraldehyde crosslinked PP (G-PP), the fucoidan modified HMM-crosslinked PPs (HMM-Fu-PPs) also exhibit significantly enhanced anticoagulation performance with a 72 % decrease in thrombus weight compared with G-PP in ex-vivo shunt assay, along with the superior biocompatibility, satisfactory anti-calcification properties confirmed by subcutaneous implantation. Owing to good comprehensive performance of these HMM-Fu-PPs, this simple and feasible strategy may offer a great potential for BHV fabrication in the future, and open a new avenue to explore more N -hydroxymethyl compound based crosslinker with excellent performance in the field of biomaterials. [ABSTRACT FROM AUTHOR]

The analysis and evaluation of manual assembly processes is related to high efforts and expenditures. Traditionally, assessments use visual and empirical methods with a low level of digitalization. These are often not cost-covering for small production quantities. This paper presents an approach to recognize assembly steps from individually detected sensory events. The approach can be integrated in a system for automatic analysis of manual assembly processes and is applicable when little training data is available. It is based on a hidden Markov model and combined with a decision logic. The methodology is tested on an exemplary use case. [ABSTRACT FROM AUTHOR]

• 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]

Sign Language Recognition (SLR) is a relatively popular research area yet contrary to its popularity, the implementation of SLR in daily basis is rare; this is due to the complexity and various resources required. In this literature review, the authors have analyzed various techniques that can be used to implement an automated sign-language translator through the analysis of the methodologies and models used to make a working model of any sign-language translator from various sources. The purpose of this study is to explore various possible ways to implement Artificial Intelligence technology to improve the automated American Sign Language translator that is applicable. The authors have identified 22 different research papers within the period of the years 2015 - 2020. The analysis showed that every research studies picked have achieved respectable results, however, they are not perfect, since each research demonstrates its own unique strengths and weaknesses. There are some methods that might be suitable for our need to create an applicable Sign Language Translator, that is by using standard video camera for obtaining data, and either Convolutional Neural Network or Support Vector Machine can be used for the classification. [ABSTRACT FROM AUTHOR]

This paper addresses the development of an Automatic Speech Recognition (ASR) system for the Moroccan Dialect. Dialectal Arabic (DA) refers to the day-to-day vernaculars spoken in the Arab world. In fact, Moroccan Dialect is very different from the Modern Standard Arabic (MSA) because it is highly influenced by the French Language. It is observed throughout all Arab countries that standard Arabic widely written and used for official speech, news papers, public administration and school but not used in everyday conversation and dialect is widely spoken in everyday life but almost never written. we propose to use the Mel Frequency Cepstral Coefficient (MFCC) features to specify the best speaker identification system. The extracted speech features are quantized to a number of centroids using vector quantization algorithm. These centroids constitute the codebook of that speaker. MFCC's are calculated in training phase and again in testing phase. Speakers uttered same words once in a training session and once in a testing session later. The Euclidean distance between the MFCC's of each speaker in training phase to the centroids of individual speaker in testing phase is measured and the speaker is identified according to the minimum Euclidean distance. The code is developed in the MATLAB environment and performs the identification satisfactorily. [ABSTRACT FROM AUTHOR]

The security situation of the network is determined by the observation state and hidden state of a complex virus system. To analyze the relationship between the two states and evaluate the trends in the security situation of the system, we construct a new model for security situation awareness based on Hidden Markov Model (HMM). Firstly, the paper examines the impact of virus propagation on network security and proposes a new SIR (Susceptible–Infected–Recovered) virus propagation model on scale-free networks. Secondly, we construct a Hidden Markov Model for network security, and this model designs and utilizes the Forward Algorithm and Viterbi Algorithm to assess the security status of epidemic networks. Finally, we ascertain the effectiveness of the model and algorithms through model examples and simulation experiments. The results show that the proposed algorithm is highly efficient in analyzing the security of virus systems and has great application value in predicting the security trends of networks. [ABSTRACT FROM AUTHOR]

• Life-cycle fatigue tests of slewing bearings are conducted. • A hybrid adaptive method reduces noise of signal effectively. • Deep learning methods have more accurate predictions than shallow networks. • Optimized Gated Recurrent Unit improves effect of degradation evaluation. Degradation process assessment from normal to failure condition of slewing bearing is viewed as a part of health monitoring in condition-based maintenance (CBM). The algorithm integrating Hidden Markov Model (HMM) and improved Gated Recurrent Unit (GRU) network is proposed to establish the component's health indictor and evaluate performance degradation. As a deep learning network, GRU network has more powerful approximate ability than machine learning methods in time series prognosis problems. The research on accelerated life experiments of a certain type of slewing bearing was carried out to verify the superiority of proposed method. Firstly, the signal preprocessing includes raw signal de-noising combining Hilbert transform with Robust Local Mean Decomposition (RLMD) and feature extraction in time and frequency domains. Then, the life health indictor is established using extracted signal features through the HMM model to complete the incipient degradation recognition. Finally, an improved method Moth Flame Optimization-based GRU (MGRU) is applied to predict the health indictor and residual life of slewing bearing. Experiments comparing with several algorithms show that the proposed methods can effectively evaluate the health condition of the slewing bearing. [ABSTRACT FROM AUTHOR]

Food quality and safety are closely related to people's health and living standard, and the risk assessment of food quality and safety has great social significance. Therefore, a novel hidden Markov model (HMM) based on gray relational analysis (GRA) (GRA-HMM), in terms of the high complexity and temporal characteristics of food detection data, is proposed to dynamically assess the food quality and safety risk. The weight of food detection indicators is calculated based on the GRA method to obtain risk indexes. Then risk indexes are used as the input data of the HMM to build the risk assessment model of food quality and safety. Moreover, the accuracy and reliability of the risk assessment model is proved based on the fuzzy matrix. Finally, the risk grading results of sterilized milk quality and safety are obtained using the proposed method. The results show that the GRA-HMM method has high accuracy in risk assessment. Meanwhile, risk control measures can be formulated or adjusted in advance and recommendations can be made for the food production, inspection and management departments. • An improved GRA-HMM method is proposed. • The validity and the practicability of the proposed method are verified by complex sterilized milk data. • The food quality and safety risk grading results of the sterilized milk can be obtained. • The proposed method can guide relevant departments to formulate or adjust the risk control measures. [ABSTRACT FROM AUTHOR]

Block diagram of different stages of fECG QRS location detection using HMM. Fetal Electro Cardiogram (fECG) provides critical information on the wellbeing of a foetus heart in its developing stages in the mother's womb. The objective of this work is to extract fECG which is buried in a composite signal consisting of itself, maternal ECG (mECG) and noises contributed from various unavoidable sources. In the past, the challenge of extracting fECG from the composite signal was dealt with by Stochastic Weiner filter, model-based Kalman filter and other adaptive filtering techniques. Blind Source Separation (BSS) based Independent Component Analysis (ICA) has shown an edge over the adaptive filtering techniques as the former does not require a reference signal. Recently, data-driven machine learning techniques e.g., adaptive neural networks, adaptive neuro-fuzzy inference system, support vector machine (SVM) are also applied. This work pursues hidden Markov model (HMM)-based supervised machine learning frame-work for the determination of the location of fECG QRS complex from the composite abdominal signal. HMM is used to model the underlying hidden states of the observable time series of the extracted and separated fECG data with its QRS peak location as one of the hidden states. The state transition probabilities are estimated in the training phase using the annotated data sets. Afterwards, using the estimated HMM networks, fQRS locations are detected in the testing phase. To evaluate the proposed technique, the accuracy of the correct detection of QRS complex with respect to the correct annotation of QRS complex location is considered and quantified by the sensitivity, probability of false alarm, and accuracy. The best results that have been achieved using the proposed method are: accuracy – 97.1%, correct detection rate (translated to sensitivity) – 100%, and false alarm rate – 2.89%. Two primary challenges in these methods are finding the right reference threshold for the normalization of the extracted fECG signal during the initial trials and limitation of discrete frame work of HMM signal (converted from continuous time) which only offers a countable number of levels in observations. By feeding the posterior probabilities, obtained from SVM, into HMM, as emission probabilities, can further improve the accuracy of fQRS location detection. • No previous literature reports the use of HMM for finding QRS location form fECG. • Best results from the three proposed HMM models are comparable to other conventional methods. • Performance analyzed by varying parameter matrices of the proposed HMM models. • Inclusion of accurate posterior probabilities to HMM models may even enhance the performance. [ABSTRACT FROM AUTHOR]

This paper addresses the development of an Automatic Speech Recognition (ASR) system for the Moroccan Dialect. Dialectal Arabic (DA) refers to the day-to-day vernaculars spoken in the Arab world. In fact, Moroccan Dialect is very different from the Modern Standard Arabic (MSA) because it is highly influenced by the French Language. It is observed throughout all Arab countries that standard Arabic widely written and used for official speech, news papers, public administration and school but not used in everyday conversation and dialect is widely spoken in everyday life but almost never written. we propose to use the Mel Frequency Cepstral Coefficient (MFCC) features to specify the best speaker identification system. The extracted speech features are quantized to a number of centroids using vector quantization algorithm. These centroids constitute the codebook of that speaker. MFCC's are calculated in training phase and again in testing phase. Speakers uttered same words once in a training session and once in a testing session later. The Euclidean distance between the MFCC's of each speaker in training phase to the centroids of individual speaker in testing phase is measured and the speaker is identified according to the minimum Euclidean distance. The code is developed in the MATLAB environment and performs the identification satisfactorily. [ABSTRACT FROM AUTHOR]

Abstract Secure routing is a difficult task because of the limited nature of wireless sensor network resources. This paper provides a Hidden Markov Model solution to identify malicious nodes in wireless sensor networks through prevention of black hole attack. Our proposed approach based on a new routing algorithm which analyses shortest path in order to avoid malicious node path. Our results demonstrate the success and the efficiency of our proposed routing algorithm. [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]

Automatic human activity recognition is being studied widely by researchers for various applications. However, majority of the existing work are limited to recognition of isolated activities, though human activities are inherently continuous in nature with spatial and temporal transitions between various segments. Therefore, there are scopes to develop a robust and continuous Human Activity Recognition (HAR) system. In this paper, we present a novel Coarse-to-Fine framework for continuous HAR using Microsoft Kinect. The activity sequences are captured in the form of 3D skeleton trajectories consisting of 3D positions of 20 joints estimated from the depth data. The recorded sequences are first coarsely grouped into two activity sequences performed during sitting and standing. Next, the activities present in the segmented sequences are recognized into fine-level activities. Activity classification in both stages are performed using Bidirectional Long Short-Term Memory Neural Network (BLSTM-NN) classifier. A total of 1110 continuous activity sequences have been recorded using a combination of 24 isolated human activities. Recognition rates of 68.9% and 64.45% have been recorded using BLSTM-NN classifier when tested using length-modeling and without length-modeling, respectively. We have also computed results for isolated activity recognition performance. Finally, the performance has been compared with existing approaches. [ABSTRACT FROM AUTHOR]

Clustering electronic medical records allows the discovery of information on healthcare practices. Entries in such medical records are usually composed of a succession of diagnostics or therapeutic steps. The corresponding processes are complex and heterogeneous since they depend on medical knowledge integrating clinical guidelines, the physician's individual experience, and patient data and conditions. To analyze such data, we are first proposing to cluster medical visits, consultations, and hospital stays into homogeneous groups, and then to construct higher-level patient treatment pathways over these different groups. These pathways are then also clustered to distill typical pathways, enabling interpretation of clusters by experts. This approach is evaluated on a real-world administrative database of elderly people in Québec suffering from heart failures. [ABSTRACT FROM AUTHOR]

Vibration signals of faulty rolling element bearings usually exhibit non-linear and non-stationary characteristics caused by the complex working environment. It is difficult to develop a robust method to detect faults in bearings based on signal processing techniques. In this paper, convolutional neural network -based hidden Markov models (CNN HMMs) are presented to classify multi-faults in mechanical systems. In CNN HMMs, a CNN model is first employed to learn data features automatically from raw vibration signals. By utilizing the t-distributed stochastic neighbor embedding (t-SNE) technique, feature visualization is constructed to manifest the powerful learning ability of CNN. Then, HMMs are employed as a strong stability tool to classify faults. Both the benchmark data and experimental data are applied to the CNN HMMs. Classification results confirm the superior performance of the present combination model by comparing with CNN model alone, support vector machine (SVM) and back propagation (BP) neural network. It is shown that the average classification accuracy ratios are 98.125% and 98% for two data series with agreeable error rate reductions. [ABSTRACT FROM AUTHOR]

Trajectory classification techniques face various challenges due to varying length and lack of the presence of clear boundaries among the trajectory classes. To overcome such challenges, a trajectory shrinking framework using Adaptive Multi-Kernel based Shrinkage (AMKS) can be used. However, such a strategy often results in over-shrinking of trajectories leading to poor classification. To improve classification performance, we introduce two additional kernels that are based on convex hull and Ramer–Douglas–Peucker (RDP) algorithm. Next, we propose a supervised trajectory classification approach using a combination of global and Segmental Hidden Markov Model (HMM) based classifiers. In the first stage, HMM is used globally for classification of trajectory to provide state-wise distribution of trajectory segments. In the second stage, state-wise trajectory segments are classified and combined with global recognition performance to improve the classification results. Combination of Global HMM and Segmental HMM is performed using a genetic algorithm (GA) based framework in the final stage. We have conducted experiments over two publicly available datasets, popularly known as T15 and MIT. We have achieved 94.80% and 96.75% of accuracies on T15 and MIT datasets, respectively. We also analyzed the robustness of the proposed framework by adding Gaussian noise. To show the effectiveness of the system, we have performed recognition of on-line signature using proposed Segmental HMM based combination model. In SVC2004 signature dataset, it outperforms traditional HMM-based systems. [ABSTRACT FROM AUTHOR]

This paper proposes a packet loss concealment (PLC) technique for increase the robustness of automatic speech recognition (ASR) of speech coded with the G729 codec, on the Voice over Internet Protocol (VoIP). Many of the standard ITU-T CELP based speech coders, such as the G.723.1, G.728, and G.729, model speech reproduction in their decoders. These decoders have enough state information to integrate PLC algorithms directly in the decoder, and are specified as part of their standards in particular by PLC based ITU-T G711 Appendix I. Speech is transmitted with source and channel codes optimized, this channel is simulated by two states Markov model to modeled loss packets. The objective of PLC based ITU-T G711 Appendix I is to generate a synthetic speech signal to cover missing data or loss packets in a received bit stream for the ASR application, i.e., to minimize word error rate. [ABSTRACT FROM AUTHOR]

Artificial internet of things technology encourages the development of robots and sensors. Kinect sensors with excellent human gesture recognition and robots with smart interactions with people are expected to have numerous innovative applications. In robotic sport instructor systems for rehabilitation and exercise training, identity recognition of the gesture operator is a crucial problem. With operator identity recognition, the gesture classification model owned by the operator can be further adjusted using the operator's active gestures, and a user-adaptive sport instructor robot system can then be achieved. This study developed an identity recognition method to classify gesture operators in which an improved feature extraction scheme that considered the practical height of a person was introduced for effective identification. According to the improved feature extraction design, a 40-dimension feature vector with the physical characteristics of the human skeleton was further developed as the feature parameter for enhancing identity recognition. A hidden Markov model (HMM) with fine considerations of continuous-time gesture variations was adopted as the recognition model for identifying ten gesture operators in the sport instructor robot system. Experimental results demonstrated the superiority of the presented approach because the constructed corresponding ten HMM active user models with the improved feature extraction-based feature parameter exhibited an excellent average identity recognition accuracy of 87.67% among all ten players, with each of them making six specified sport rehabilitation actions. [ABSTRACT FROM AUTHOR]

In this paper, we consider the challenging problem of detecting retinal vessel networks. Precise detection of retinal vessel networks is vital for accurate eye disease diagnosis. Most of the blood vessel tracking techniques may not properly track vessels in presence of vessels’ occlusion. Owing to problem in sensor resolution or acquisition of fundus images, it is possible that some part of vessel may occlude. In this scenario, it becomes a challenging task to accurately trace these vital vessels. For this purpose, we have proposed a new robust and intelligent retinal vessel detection technique on Hidden Markov Model. The proposed model is able to successfully track vessels in the presence of occlusion. The effectiveness of the proposed technique is evaluated on publically available standard DRIVE dataset of the fundus images. The experiments show that the proposed technique not only outperforms the other state of the art methodologies of retinal blood vessels segmentation, but it is also capable of accurate occlusion handling in retinal vessel networks. The proposed technique offers better average classification accuracy, sensitivity, specificity, and area under the curve (AUC) of 95.7%, 81.0%, 97.0%, and 90.0% respectively, which shows the usefulness of the proposed technique. [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]

With the increase of Arabic textual information via internet websites and services, a tools for processing Arabic text information are needed to extract knowledge from them. Name Entity recognition aims to extract name entities such as: person names, locations and organizations from a given text. Name Entity recognition approaches were classified into two main approaches: rule-based approach and statistical approach. Although the literature on Name Entity recognition is quit extensive, few researches to extract Name Entities in the Arabic language could be found. This paper provides a comprehensive survey about statistical approaches of Arabic Name Entity extraction. [ABSTRACT FROM AUTHOR]

This paper pulls together the advances of recognizing emotion theory with advances in speech feature in order to improve understand of emotion under real life condition. It presents the application of a recently proposed feature extraction method based on spectral features, used for speech emotion recognition purposes. Specifically, the performance of the proposed approach is evaluated on real condition speech signal (IEMOCAP database) with real world noise using various SNR levels. We examined an assessment of emotion error rate using classical descriptors (MFCC, PLP) and also new type of speech features considered as more robust to noise and reverberation distortions (PNCC with different variants). The results reveal that the used methods give better performance using MFCC under clean environment, and that PNCC shows an advantage compared to other features methods in noisy environment. [ABSTRACT FROM AUTHOR]

• The introduction of VR technology to design college English teaching programs. • Uses VR skills to design games system in universities. • English game teaching system proposed by the research can significantly improve students' learning interest. With the deepening of international exchanges, colleges and universities have higher and higher requirements for the quality of English teaching. In order to improve the quality of English teaching in colleges and universities, the research proposes to design and construct an English game education and teaching system based on virtual reality technology. First, the modern VR technology is used to build the initial English game teaching system, and then the HMM-DNN algorithm is introduced to improve the virtual system. In the process, the CMUShinx speech recognition platform is used to build a robot control command speech recognition system, in order to obtain a good voice acoustic model and achieve correct speech recognition in the virtual environment. Finally, the performance analysis of the built system is carried out to verify the feasibility of the system model. The results show that the step response coefficient of the model built by the research institute can be kept within 1 M for a long time; When the speech type is White and Cafe1, the correct recognition rate of the constructed model for English speech is as high as 98 % and 95 %, and is always higher than other algorithms; In the comparison of the accuracy of students' oral speech recognition scores by different models, the lowest error of the research model is 2.23 %, which is significantly smaller than the other models. The above results indicate that the overall teaching effect of the system built by the research institute is stable, and it has high feasibility for college students' English teaching, which helps to further improve students' interest and ability in English learning, and is of great significance for college English talent training. [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]

Spoken language processing is an important capability of human intelligence that has hitherto been unexplored by cognitive architectures. This reflects on both the symbolic and sub-symbolic nature of the speech problem, and the capabilities provided by cognitive architectures to model the latter and its rich interplay with the former. Sigma has been designed to leverage the state-of-the-art hybrid (discrete + continuous) mixed (symbolic + probabilistic) capability of graphical models to provide in a uniform non-modular fashion effective forms of, and integration across, both cognitive and sub-cognitive behavior. In this article, previous work on speaker dependent isolated word recognition has been extended to demonstrate Sigma’s feasibility to process a stream of fluent audio and recognize phones, in an online and incremental manner with speaker independence. Phone recognition is an important step in integrating spoken language processing into Sigma. This work also extends the acoustic front-end used in the previous work in service of speaker independence. All of the knowledge used in phone recognition was added supraarchitecturally – i.e. on top of the architecture – without requiring the addition of new mechanisms to the architecture. [ABSTRACT FROM AUTHOR]

Human action classification is fundamental technology for robots that have to interpret a human’s intended actions and make appropriate responses, as they will have to do if they are to be integrated into our daily lives. Improved measurement of human motion, using an optical motion capture system or a depth sensor, allows robots to recognize human actions from superficial motion data, such as camera images containing human actions or positions of human bodies. But existing technology for motion recognition does not handle the contact force that always exists between the human and the environment that the human is acting upon. More specifically, humans perform feasible actions by controlling not only their posture but also the contact forces. Furthermore these contact forces require appropriate muscle tensions in the full body. These muscle tensions or activities are expected to be useful for robots observing human actions to estimate the human’s somatosensory states and consequently understand the intended action. This paper proposes a novel approach to classifying human actions using only the activities of all the muscles in the human body. Continuous spatio-temporal data of the activity of an individual muscle is encoded into a discrete hidden Markov model (HMM), and the set of HMMs for all the muscles forms a classifier for the specific action. Our classifiers were tested on muscle activities estimated from captured human motions, electromyography data, and reaction forces. The results demonstrate their superiority over commonly used HMM-based classifiers. [ABSTRACT FROM AUTHOR]

This paper presents a novel fault diagnosis method to diagnose ordinary soft fault and incipient soft fault for linear analog circuit. Due to the presence of tolerance, the parameter variation of analog component obeys a nearly normal distribution, and the linear circuit responses are considered as a stochastic process. Therefore, three kinds of stochastic series are extracted as fault features. Then, fault feature samples are divided into train samples and test samples. The relevant statistic values of them are calculated as final test samples in the stage of fault testing. In order to diagnose stochastic series effectively, an improved GHMM classifier is designed based on the fault occurrence characteristics of analog component. The stochastic sequences are thought as the observation symbols for the proposed GHMM. Simulation circuits and actual circuits are tested to prove the effectiveness of the new method. [ABSTRACT FROM AUTHOR]

We present a text-to-speech (TTS) system designed for the dialect of Bengali spoken in Bangladesh. This work is part of an ongoing e ff ort to address the needs of new under-resourced languages. We propose a process for streamlining the bootstrapping of TTS systems for under-resourced languages. First, we use crowdsourcing to collect the data from multiple ordinary speakers, each speaker recording small amount of sentences. Second, we leverage an existing text normalization system for a related language (Hindi) to bootstrap a linguistic front-end for Bangla. Third, we employ statistical techniques to construct multi-speaker acoustic models using Long Short-term Memory Recurrent Neural Network (LSTM-RNN) and Hidden Markov Model (HMM) approaches. We then describe our experiments that show that the resulting TTS voices score well in terms of their perceived quality as measured by Mean Opinion Score (MOS) evaluations. [ABSTRACT FROM AUTHOR]

We propose a novel variance reduction strategy based on control variables for simulating the averaged equation of a stochastic slow-fast system. In this system, we assume that the fast equation is ergodic, implying the existence of an invariant measure, for every fixed value of the slow variable. The right hand side of the averaged equation contains an integral with respect to this unknown invariant measure, which is approximated by the heterogeneous multiscale method (HMM). The HMM method corresponds to a Markov chain Monte Carlo method in which samples are generated by simulating the fast equation. As a consequence, the variance of the HMM estimator decays slowly. Therefore, we introduce a variance-reduced HMM estimator based on control variables: from the current time HMM estimation, we subtract a second HMM estimator at the previous time step using the exact same seed as the current time HMM estimator. To avoid introducing a bias, we add the previously calculated variance-reduced estimator. We analyze convergence of the proposed estimator and apply it to a linear and nonlinear model problem. [ABSTRACT FROM AUTHOR]

Automatic surveillance is an important research area and has been studied for many years. In this paper, a new method of Cross Border Intrusion detection in hilly region has been discussed. The Kinect camera ensures that intruders crossing the border can be detected during daytime as well as in night. We introduce a border surveillance system that is able to recognize intruder actions like standing, walking, crawling, and bending, etc. in illuminated as well as in dark conditions. The system is able to detect whether the moving object is a human being or an animal and activates an alarm if it detects human movement. Also, the system works well in plain as well as in hilly terrain. Using skeletal tracking application provided by Kinect console, the actions are classified and recognized. The HMM based classification makes the system robust and thus, makes it a versatile component for being a part of other different applications. The proposed system gives result for an overall detection accuracy of 92%. [ABSTRACT FROM AUTHOR]

• A kernel dynamic mode decomposition approach is introduced as a feature extraction technique for baleen whale species detection. • The extracted features are transformed to feature vectors for the hidden Markov model. • The developed HMM detectors are evaluated on southern right whales and humpback whales. • The performance of the detectors is analysed using three performance metrics: true positive rate, precision, and error rate. • The described methodology can be tailored for the detection and classification of other vocalising animal species through their sounds. The negative effects of human activities within the ecological space of whales remains an issue of concern to marine ecologists. The accurate detection and subsequent classification of whale species are vital in mitigating these negative effects. Automatic detection techniques have come in handy for the efficient detection of the various whale species without human error. Hidden Markov model (HMM) remains one the most efficient detectors of whale species. However, its performance efficiency is greatly influenced by the feature vectors adapted with it. In this work, we propose the use of the kernel dynamic mode decomposition (kDMD) algorithm as a tool to extract features of baleen whale species, which are then adapted with HMM for their detection. Dynamic mode decomposition (DMD) is an eigendecomposition-based algorithm that is capable of extracting latent underlying features of non-linear signals such as those vocalised by whales. However, the underlying cost of DMD is the singular value decomposition (SVD), which adds significant complexity to the modes derivation steps. Thus, this work is introducing the kernel method into the DMD, in order to find a more efficient way of computing DMD without explicitly using the SVD algorithm. Furthermore, the feature formation steps in the original DMD was modified (mDMD) in this work, to make it more generic for datasets with sparse whale sound samples. The performance of the detectors was tested on datasets containing sounds of southern right whales (SRWs) and humpback whales. The results obtained show a high true positive rate (TPR), high precision (PREC) and low error rate (ERR) for both species. The performance of the three DMD-based feature-extraction methods were compared. The kDMD-HMM generally performed better than the mDMD-HMM and DMD-HMM detectors. The methods proposed here can be tailored for the automatic detection and classification of other vocalising animal species through their sounds. [ABSTRACT FROM AUTHOR]

Context awareness is an important element in the pervasive and ubiquitous computing. It involves the ability of the computing system to be aware of the context in which a particular target user is experiencing. This involves the location in which the target is, the activity that the target is doing, the identity of that target and the time in which the activity occur. Once these two elements are known we propose the use of HMM to predict and infer the context of the user. [ABSTRACT FROM AUTHOR]

An analysis of newborn cry signals, either for the early diagnosis of neonatal health problems or to determine the category of a cry (e.g., pain, discomfort, birth cry, and fear), requires a primary and preliminary preprocessing step to quantify the important expiratory and inspiratory parts of the audio recordings of newborn cries. Data typically contain clean cries interspersed with sections of other sounds (generally, the sounds of speech, noise, or medical equipment) or silence. The purpose of signal segmentation is to differentiate the important acoustic parts of the cry recordings from the unimportant acoustic activities that compose the audio signals. This paper reports on our research to establish an automatic segmentation system for newborn cry recordings based on Hidden Markov Models using the HTK (Hidden Markov Model Toolkit). The system presented in this report is able to detect the two basic constituents of a cry, which are the audible expiratory and inspiratory parts, using a two-stage recognition architecture. The system is trained and tested on a real database collected from normal and pathological newborns. The experimental results indicate that the system yields accuracies of up to 83.79%. [ABSTRACT FROM AUTHOR]

To deal with non-stationary and quasi-stationary signals, wavelet transform has been used as an effective tool for the time-frequency analysis. In the recent years, wavelet transform has been used extensively for feature extraction in noisy speech recognition. These filters have the benefit of having frequency bands spacing similar to the auditory Equivalent Rectangular Bandwidth (ERB) scale. Central frequencies of ERB are equally distributed with the frequency response of the human cochlea. This paper deals with the speaker-independent Automatic Speech Recognition (ASR) system for continuous speech. This Hidden Markov Model (HMM) based ASR system was developed for English using recordings of four regions taken from TIMIT database. A new set of features were derived using wavelet packet transform’s multi-resolution capabilities and having an advantage of ERB filter based on the human cochlea. New set of wavelet features have shown significant improvements in the noisy environment, especially at low SNR values. [ABSTRACT FROM AUTHOR]

Abstract: We introduce a new computational phonetic modeling framework for sign language (SL) recognition. This is based on dynamic–static statistical subunits and provides sequentiality in an unsupervised manner, without prior linguistic information. Subunit “sequentiality” refers to the decomposition of signs into two types of parts, varying and non-varying, that are sequentially stacked across time. Our approach is inspired by the Movement–Hold SL linguistic model that refers to such sequences. First, we segment signs into intra-sign primitives, and classify each segment as dynamic or static, i.e., movements and non-movements. These segments are then clustered appropriately to construct a set of dynamic and static subunits. The dynamic/static discrimination allows us employing different visual features for clustering the dynamic or static segments. Sequences of the generated subunits are used as sign pronunciations in a data-driven lexicon. Based on this lexicon and the corresponding segmentation, each subunit is statistically represented and trained on multimodal sign data as a hidden Markov model. In the proposed approach, dynamic/static sequentiality is incorporated in an unsupervised manner. Further, handshape information is integrated in a parallel hidden Markov modeling scheme. The novel sign language modeling scheme is evaluated in recognition experiments on data from three corpora and two sign languages: Boston University American SL which is employed pre-segmented at the sign-level, Greek SL Lemmas, and American SL Large Vocabulary Dictionary, including both signer dependent and unseen signers' testing. Results show consistent improvements when compared with other approaches, demonstrating the importance of dynamic/static structure in sub-sign phonetic modeling. [Copyright &y& Elsevier]

Abstract: The heterogeneous multiscale methods (HMM) extend the classical methods of averaging to a purely numerical approach for the solution of problems involving multiple scales. Especially for highly oscillatory ordinary differential equations HMM were recently seen to be competitive with usual time integration schemes. We study this hypothesis in the special case of penalty formulations for index-three differential-algebraic equations arising in multibody dynamics which have the particular property of solution-dependent oscillations with variable frequencies. First we motivate some additional assumptions on the structure of the proposed problems and give error estimates extending the results of Engquist et al. Limitations of the considered approach will be illustrated by means of the seven body mechanism benchmark. [Copyright &y& Elsevier]

Abstract: This paper proposes a new estimation algorithm for the parameters of an HMM as to best account for the observed data. In this model, in addition to the observation sequence, we have partial and noisy access to the hidden state sequence as side information. This access can be seen as “partial labeling” of the hidden states. Furthermore, we model possible mislabeling in the side information in a joint framework and derive the corresponding EM updates accordingly. In our simulations, we observe that using this side information, we considerably improve the state recognition performance, up to 70%, with respect to the “achievable margin” defined by the baseline algorithms. Moreover, our algorithm is shown to be robust to the training conditions. [Copyright &y& Elsevier]

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]

Abstract: In this paper, we propose a new font and size identification method for ultra-low resolution Arabic word images using a stochastic approach. The literature has proved the difficulty for Arabic text recognition systems to treat multi-font and multi-size word images. This is due to the variability induced by some font family, in addition to the inherent difficulties of Arabic writing including cursive representation, overlaps and ligatures. This research work proposes an efficient stochastic approach to tackle the problem of font and size recognition. Our method treats a word image with a fixed-length, overlapping sliding window. Each window is represented with a 102 features whose distribution is captured by Gaussian Mixture Models (GMMs). We present three systems: (1) a font recognition system, (2) a size recognition system and (3) a font and size recognition system. We demonstrate the importance of font identification before recognizing the word images with two multi-font Arabic OCRs (cascading and global). The cascading system is about 23% better than the global multi-font system in terms of word recognition rate on the Arabic Printed Text Image (APTI) database which is freely available to the scientific community. [Copyright &y& Elsevier]

Abstract: The dynamics of inter-regional communication within the brain during cognitive processing – referred to as functional connectivity – are investigated as a control feature for a brain computer interface. EMDPL is used to map phase synchronization levels between all channel pair combinations in the EEG. This results in complex networks of channel connectivity at all time–frequency locations. The mean clustering coefficient is then used as a descriptive feature encapsulating information about inter-channel connectivity. Hidden Markov models are applied to characterize and classify dynamics of the resulting complex networks. Highly accurate levels of classification are achieved when this technique is applied to classify EEG recorded during real and imagined single finger taps. These results are compared to traditional features used in the classification of a finger tap BCI demonstrating that functional connectivity dynamics provide additional information and improved BCI control accuracies. [Copyright &y& Elsevier]

Abstract: In digital communications error pattern modelling based on hidden Markov models is widely used to describe and generate error sequences. The length of measured error patterns are in the order of 105 and 106 to guarantee stochastic expressiveness, which results in high calculation times to parameterize the models. To reduce these computational efforts on the one hand and to free the user from the training period for HMMs on the other hand, this paper introduces an efficient and automated architecture for modelling binary error patterns. All model parameters are calculated transparently from the measured or simulated error pattern without any user interaction. Efficient parametrization is achieved by performing several optimization techniques such as state splitting, k-means based initialization, scaling reduction, equivalent diagonal models, and compiler optimizations. The architecture is firstly introduced for continuous error distributions which come true if the transmitted entities are processed on their own. In case of group-wise processing like in UMTS block transmissions, the error distribution can exhibit steps which is demonstrated by a measurement in a real UMTS test environment. In order to reproduce similar statistics an extended model is described which is also covered by the mentioned architecture. [Copyright &y& Elsevier]

Abstract: Spontaneous conversational speech has many characteristics that are currently not modelled well by HMM-based speech synthesis and in order to build synthetic voices that can give an impression of someone partaking in a conversation, we need to utilise data that exhibits more of the speech phenomena associated with conversations than the more generally used carefully read aloud sentences. In this paper we show that synthetic voices built with HMM-based speech synthesis techniques from conversational speech data, preserved segmental and prosodic characteristics of frequent conversational speech phenomena. An analysis of an evaluation investigating the perception of quality and speaking style of HMM-based voices confirms that speech with conversational characteristics are instrumental for listeners to perceive successful integration of conversational speech phenomena in synthetic speech. The achieved synthetic speech quality provides an encouraging start for the continued use of conversational speech in HMM-based speech synthesis. [Copyright &y& Elsevier]

Abstract: People have made many researches on computer vision, but the accuracy and speed were not satisfactory. This paper introduced a Human-computer interaction system based on GRBF and HMM. The paper used GRBF Artificial Neural Networks define the position of head, and HMM define the position of fingers. We combined the line of sight and the direction of fingers to ensure the uses’ input focus. And the results showed that the recognition accuracy and speed of the system had been increased greatly in this way. [Copyright &y& Elsevier]