Hidden Markov Model Algorithm Research Articles

Application Research on Roller Skater Detection, Tracking, and Trajectory Prediction Based on Video Stream

With the continuous progress of science and technology, the sport of roller skating has developed rapidly and the technical level of the game has become higher and higher. Its sport performance has been rapidly improved. However, China’s roller skating is relatively late, and there is still a certain gap compared with many Western developed countries. In order to improve the performance of China’s roller skating, this study takes the representative Chinese and foreign excellent speed skaters as the research object and compares the sprinting technology of Chinese and foreign excellent speed skaters by using image measurement and image analysis to obtain the kinematic parameters and data of the athletes’ sprinting technology in the competition state. In view of the problem that the current video target tracking algorithm is easy to follow multiple targets, a video multiobject detection and tracking algorithm with improved tracking learning detection (TLD) is studied with the skater in the video as the research object. For the lost target, the prediction function of Kalman filter algorithm is used to track the trajectory of the typical target in the video, and the trajectory tracked by Kalman filter algorithm is used to compensate the lost part of TLD algorithm, so as to obtain the complete trajectory of the typical target in the video to improve the accuracy of video multiobject tracking. Since the existing trajectory prediction algorithms have the limitation of poor accuracy, a social-long short-term memory (Social-LSTM) network-based video typical target trajectory prediction algorithm is proposed to predict the trajectory sequences of typical targets to be detected by incorporating the contextual environment information and the interaction relationship between multiple target trajectories into the Social-LSTM network. The simulation results show that the proposed trajectory prediction algorithm outperforms the traditional LSTM algorithm, Hidden Markov Model Algorithm, and Hybrid Gaussian model algorithm, which is helpful to improve the accuracy of video roller skater target trajectory prediction, and the tracking success rate is 0.98.

A study on the algorithm of ultrasonic detection and recognition based on DAG‐SVMs mixed HMM of teleoperation gestures for intelligent manufacturing devices

Remote control for the position and status of a machine or an equipment can often be teleoperated by gestures in an intelligent manufacturing environment. In order to solve the problems that gestures with two directions such as left and right cannot be detected by single ultrasonic frequency, double different ultrasonic frequencies are used to detect gestures by the Doppler shift, and an algorithm of the recognition gesture based on the DAG-SVMs mixed Hidden Markov Model (HMM) is proposed to identify and classify the extracted feature sequences. Thus, four more types of gestures are expanded other than that of reading display screen information, and the comparative experiments to classify and recognise gestures of teleoperation are made with DAG-SVMs, the HMM, the DAG-SVMs mixed HMM, and other improved HMM algorithms. The test results have shown that the mean rate of gesture recognition for the algorithm based on the DAG-SVMs mixed HMM is 94.917%, which is 9.497% higher than that of the unimproved HMM, and its recognition accuracy of complex teleoperation gestures is improved by 2.3% compared with other improved HMM algorithms. The experimental results show that the DAG-SVMs mixed HMM algorithm has a good effect on recognition for the gestures of teleoperation and it can perform gesture recognition accurately.

Analysis of algorithms and implementation of real time speaker identification system

The article describes an implementing a real time speaker identification system by voice for embedded and general purpose computers. A review and analysis of existing speaker identification algorithms are made. The speaker's input speech is recorded in the system, go through the preprocessing stage, extract features and voice parameters for further identification. To recognize the speaker by voice parameters, the Vector quantization and Hidden Markov model algorithms are used. The VQ and HMM algorithms showed recognition accuracy of 96% and 98%, respectively.

Aplikasi Spoxtech Untuk Penyandang Tuna Rungu – Wicara Menggunakan Algoritma Hidden Markov Model dan Metode Finite State Automata (FSA)

Communication is a very important thing to establish social relations. In communicating, deaf and mute persons have difficulty conveying what information they want to convey. The Android-based Spoxtech application is an application specially designed for deaf and speech impaired persons. As the name implies, Spoxtech is taken from the word speech to text - text to speech. This application can make it easier for users to communicate because it is equipped with a voice menu that functions to detect the spoken voice which is then converted into text and a typed menu which functions to detect writing which is then converted into voice form. This application was created using the Hidden Markov Model algorithm in generating sound into text and using the finite state automata method in generating text into sound by performing two-level decapitation. This results of this study were carried out by testing the whitebox and blackbox. In this research, the text normalization test on the typewriter menu was also carried out, namely each word containing currency, time, temperature, and number units. The accuracy value obtained in testing this application uses Indonesian by testing the voice menu and typing menu and testing the two-level decapitation, the value is 100% of the 300 words in Indonesian.

A High-resolution GPR horizon extraction method based on local reflection and global correlation

Horizon extraction is a very basic and important part of ground penetrating radar (GPR) interpretation. Most GPR horizon extraction methods are based on local reflection of the GPR event such as the trace correlation algorithm, and hidden Markov model algorithm. These methods use only local structural characteristics of the GPR data and often fail to pick the layer correctly across discontinuous caused by faults and noise. In order to overcome shortcomings of the above methods, a novel method based on gradient structure tensor algorithm (GST) and dynamic time warping algorithm (DTW) is used in this paper to extract the horizon accurately which has been proved to be effective in the complex seismic data. GPR electromagnetic wave and seismic wave have certain similarity in kinematics and dynamics, we apply this method to realistic GPR data and prove its effectiveness.

Study of Driving Cycle of City Tour Bus Based on Coupled GA-K-Means and HMM Algorithms: A Case Study in Beijing

Driving cycle is an important indicator to evaluate vehicle performance and to measure fuel consumption. Its impact is not only on pollution emissions but also on asset management. Based on the real life detailed data from the city tour buses in Beijing, this paper proposes to couple a genetic algorithm based GA-K-means clustering with the Hidden Markov Model (HMM) to construct a city tour bus urban road driving cycle in Beijing. Compared to the standard driving cycle C-WTVC used for heavy commercial vehicle fuel consumption certification in China, our driving cycle model can reflect the real life situation more accurately. With our model, the influence of driving state and driving behavior on fuel consumption is also analyzed, and the fuel consumption estimation model under the corresponding driving cycle is constructed. To gain deeper insight and better fuel consumption, we further segment and construct the driving sub-cycles of peak and off-peak periods according to the difference in fuel consumption at different time periods in Beijing in September 2019. Through this fine-grain driving cycle, we can further improve the accuracy of the fuel consumption estimation model.

Gerçek Ortamlarda Artımlı Öğrenme ile Gerçek Zamanlı İşitsel Sahne Analizi

Continual learning for scene analysis is a continuous process to incrementally learn distinct events, actions, and even noise models from past experiences using different sensory modalities. In this paper, an Auditory Scene Analysis (ASA) approach based on a continual learning system is developed to incrementally learn the acoustic events in a dynamically-changing domestic environment. The events being salient sound sources are localized by a Sound Source Localization (SSL) method to robustly process the signals of the localized sound source in the domestic scene where multiple sources can co-exist. For real-time ASA, audio patterns are segmented from the acoustic signal stream of the localized source for extraction of the audio features, and construction of a feature set for each pattern. The continual learning is employed via a time-series algorithm, Hidden Markov Model (HMM), on these feature sets from acoustic signals stemming from the sources. The learning process is investigated by conducting a variety of experiments to evaluate the performance of Unknown Event Detection (UED), Acoustic Event Recognition (AER), and continual learning using a Hierarchical HMM algorithm. The Hierarchical HMM consists of two layers: 1) a lower layer in which AER is performed using an HMM for each event and the event-wise likelihood thresholds; and 2) an upper layer in which UED is achieved by one HMM with a suspicion threshold through the audio features with their proto symbols stemming from the lower layer HMMs. We verified the effectiveness of the proposed system capable of continual learning, AER and UED in terms of False-Positive Rates, True-Positive Rates, recognition accuracy and computational time to meet the demands in a learning task of multiple events in real-time. The effectiveness of the AER system has been verified with high accuracy, and a short retraining time in real-time ASA having nine different sounds.

A novel dynamic asset allocation system using Feature Saliency Hidden Markov models for smart beta investing

The financial crisis of 2008 generated interest in more transparent, rules-based strategies for portfolio construction, with smart beta strategies emerging as a trend among institutional investors. Whilst they perform well in the long run, these strategies often suffer from severe short-term drawdown (peak-to-trough decline) with fluctuating performance across cycles. To manage short term risk (cyclicality and underperformance), we build a dynamic asset allocation system using Hidden Markov Models (HMMs). We use a variety of portfolio construction techniques to test our smart beta strategies and the resulting portfolios show an improvement in risk-adjusted returns, especially on more return-oriented portfolios (up to 50% of return in excess of market adjusted by relative risk annually). In addition, we propose a novel smart beta allocation system based on the Feature Saliency HMM (FSHMM) algorithm that performs feature selection simultaneously with the training of the HMM, to improve regime identification. We evaluate our systematic trading system with real life assets using MSCI indices; further, the results (up to 60% of return in excess of market adjusted by relative risk annually) show model performance improvement with respect to portfolios built using full feature HMMs.

Genomic Structural Diversity in Local Goats: Analysis of Copy-Number Variations.

Simple SummaryCopy-number variations (CNVs) are one of the widely dispersed forms of structural variations in mammalian genomes and are known to be present in genomic regions that regulate important physiological functions. In this study, CNV detection was performed starting from genotypic data of 120 individuals, belonging to four Sicilian dairy goat breeds, genotyped with the Illumina GoatSNP50 BeadChip array. Using PennCNV software, a total of 702 CNVs were identified in 107 individuals. These were merged in 75 CNV regions (CNVRs), i.e., regions containing CNVs overlapped by at least 1 base pair. Functional annotation of the CNVRs allowed the identification of 139 genes/loci within the most frequent CNVRs, which are involved in local adaptation, mild behaviour, immune response, reproduction, and olfactory receptors. This study provides insights into the genomic variations within these Italian goat breeds and should be of value for future studies to identify the relationships between this type of genetic variation and phenotypic traits.Copy-number variations (CNVs) are one of the widely dispersed forms of structural variations in mammalian genomes, and are present as deletions, insertions, or duplications. Only few studies have been conducted in goats on CNVs derived from SNP array data, and many local breeds still remain uncharacterized, e.g., the Sicilian goat dairy breeds. In this study, CNV detection was performed, starting from the genotypic data of 120 individuals, belonging to four local breeds (Argentata dell’Etna, Derivata di Siria, Girgentana, and Messinese), genotyped with the Illumina GoatSNP50 BeadChip array. Overall, 702 CNVs were identified in 107 individuals using PennCNV software based on the hidden Markov model algorithm. These were merged in 75 CNV regions (CNVRs), i.e., regions containing CNVs overlapped by at least 1 base pair, while 85 CNVs remained unique. The part of the genome covered by CNV events was 35.21 Mb (1.2% of the goat genome length). Functional annotation of the CNVRs allowed the identification of 139 genes/loci within the most frequent CNVRs that are involved in local adaptations, such as coat colour (ADAMTS20 and EDNRA), mild behaviour (NR3C2), immune response (EXOC3L4 and TNFAIP2), reproduction (GBP1 and GBP6), and olfactory receptors (OR7E24). This study provides insights into the genomic variations for these Sicilian dairy goat breeds and should be of value for future studies to identify the relationships between this type of genetic variation and phenotypic traits.

Analysis of CNV in the Genomes of the Marrow Cells of the Patients with AML Revealed That High Numbers of Aberrations Associate with Better Survival and Deletions with the Aberrant Expression of CD19 in the Leukemic Blasts

In our previous study (Jaskula et al., Blood 2017 130:1420) we reported that the number of CNVs within the KANSL1 gene was associated with the phenotype of AML. In the present study we looked at the presence of CNV across the whole genome. One hundred and twenty seven AML patients (diagnosed according to the FAB/WHO criteria, F/M=62/65, age median: 57, range: 21 - 84 years) were included to the present study. The patients were genetically analysed including GTG karyotyping and/or FISH for X or Y deletion, inv (3), -5/5q-, -7/7q-,+8, MLL, RUNX1, PML/RARA or RARA, inv(16). In all patients the microarray analysis of the bone marrow cells having blasts cells (median value 56%) at diagnosis Agilent - Catalog Agilent Cancer CGH+SNP 180K (74 patients) or Roche - WG Catalog NimbleGene 12x270K (53 patients) microarrays were employed and the results were analysed with the use the Partek software employing the Partek Hidden Markov Model (HMM) and segmentation algorithms. Results: The number of CNV in M0 AML marrow cells was significantly lower (median: 0 aberration), as compared to secondary to MDS AML (median: 4.5 aberrations, p=0.006). Patients with AML subtypes from M1 to M6 had higher number of CNV amplifications (median: 2) as compared to the patients with minimally differentiated blasts (M0, median: 0 amplifications, p=0.030). Knowing that (i) changes in the chromatin structure may be associated with the CNV prevalence within the genome (Gheldof et al., PLoS One. 2013 Nov 12;8(11):e79973) and (ii) the aberrant expression of CD19 in AML blasts results from the chromatin structure variations (Walter et al., Oncogene. 2010 May 20;29(20):2927-37) we looked at the presence of association between the numbers of CNV and the presence of the aberrant CD19 expression in the leukemic blasts. It appeared that 11 AML patients having aberrant expression of CD19 (within whom 4 had t(8:21)) had more frequently CNV deletions than those lacking this aberrant expression (median: 2 vs 1 deletions, p=0.018, HMM algorithm). Having the survival curves of the patients plotted accordingly to the high and low numbers of CNV, the situation is more complex and shows that: the patients having higher numbers of CNV aberrations (exceeding the mean of the whole group +SD) enjoyed better survival (20% vs 11%, p=0.090) when segmentation algorithm was employed. HMM analysis also suggested that the higher values of CNV (amplifications, exceeding the mean of the whole group +SD) was associated with better 5-year survival as compared to those with low numbers (42% vs 20%, ns). The aberrant expression of CD19 analysis was associated with higher numbers of deletions (see above) and with better 5-year survival than those lacking this aberrant expression (45% vs 20%, p=0.064). In conclusion, the prevalence of CNV within the genome shapes the phenotype of the leukemia and facilitates the survival. Disclosures No relevant conflicts of interest to declare.

Real-Time Epileptic Seizure Detection During Sleep Using Passive Infrared Sensors

This paper addresses the problem of detecting epileptic seizures experienced by a human subject during sleep. Commonly used solutions to this problem mostly rely on detecting motion due to seizures using contact-based sensors or video-based sensors. We seek a low-cost, low-power alternative that can sense motion without making direct contact with the subject and provides high detection accuracy. We investigate the use of Passive InfraRed (PIR) sensors to sense human body motion caused by epileptic seizures during sleep which makes the body shake and causes the PIR sensor to generate an oscillatory output signal. This signal can be distinguished from that of ordinary motions during sleep using analysis with machine learning algorithms. The supervised hidden Markov model algorithm (HMM) and a 1-D and 2-D convolutional neural network (ConvNet) are used to classify the data set of the PIR sensor output into the occurrence of epileptic seizures, ordinary motions, or absence of motion. The method was tested on the PIR signals captured at 1 m from 33 recruited healthy subjects who, after watching seizure videos, either moved their body on a bed to simulate a seizure, ordinary motion, or lay still. The HMM algorithm attained 97.03% accuracy, while 1D-ConvNet and 2D-ConvNet attained an accuracy of 96.97% and 98.98%, respectively. All simulated seizures were successfully detected, with errors occurring only in distinguishing between ordinary motion and no motion, thereby demonstrating the potential for using PIR sensors in the epileptic seizure detection.

JUCHMME: a Java Utility for Class Hidden Markov Models and Extensions for biological sequence analysis.

JUCHMME is an open-source software package designed to fit arbitrary custom Hidden Markov Models (HMMs) with a discrete alphabet of symbols. We incorporate a large collection of standard algorithms for HMMs as well as a number of extensions and evaluate the software on various biological problems. Importantly, the JUCHMME toolkit includes several additional features that allow for easy building and evaluation of custom HMMs, which could be a useful resource for the research community. http://www.compgen.org/tools/juchmme, https://github.com/pbagos/juchmme. Supplementary data are available at Bioinformatics online.

Transmission Line Fault Classification Using Hidden Markov Models

The maintenance of power quality in electrical power systems depends on addressing the major disturbances that may arise during generation, transmission and distribution. Many studies aim to investigate these disturbances by analyzing the behavior of the electrical signal through the classification of short circuit faults in power transmission lines as a way to assist the administration and maintenance of the electrical system. However, most fault classification methods generate a high computational cost that do not always yield satisfactory results; these methods utilize front ends in data processing before being processed by conventional classification algorithms such as Artificial Neural Network (ANN), Support Vector Machine (SVM), K-Nearest Neighbors (KNN), and Random Forest (RF) that are adopted into the Frame Based Sequence Classification (FBSC) architecture that uses the front ends Wavelet energy, Waveletconcat, RAW, Root Mean Square front ends (RMS) and Con cat Front End. An alternative method for classifying faults without having to use front ends employs the UFPAFaults database and the Hidden Markov Model (HMM) algorithm that directly treats the electrical signal in the form of multivariate time series. The results indicate the HMM algorithm as a potential classifier because its comparatively low error rate of 0.03% exceeds the performance of the conventional classifiers ANN, SVM, KNN and RF as used with the FBSC architecture. When the statistical test with a significance of α =5 % is applied, only the ANN and RF classifiers present a result close to what the HMM algorithm provides. Another relevant factor is that the HMM algorithm considerably decreases the computational cost by more than 90% of processing time as compared to the conventional classifiers of the FBSC architecture, thereby validating its potential in the direct classification of faults in electric power system transmission lines.

Prediction-Based Channel Selection Prediction in Mobile Cognitive Radio Network

The emerging 5G wireless communications enabled diverse multimedia applications and smart devices in the network. It promises very high mobile traffic data rates, quality of service as in very low latency and improvement in user’s perceived quality of experience compared to current 4G wireless network. This encourages the increasing demand of significant bandwidth which results a significant urge of efficient spectrum utilization. In this paper, modelling, performance analysis and optimization of future channel selection for cognitive radio network by jointly exploiting both CR mobility and primary user activity to provide efficient spectrum access is studied. The modelling and prediction method is implemented by using Hidden Markov Model algorithm. The movement of CR in wireless network yields location-varying spectrum opportunities. The current approaches in most literatures which only depend on reactive selection spectrum opportunities result of inefficient channel usages. Moreover, conventional random selection method tends to observe a higher handoff and operation delays in network performance. This inefficiency can cause continuous transmission interruptions leading to the degradation of advance wireless services. This work goal is to improve the performance of CR in terms number of handoffs and operation delays. We perform simulation on our prediction strategy with a commonly used random sensing method with and without location. Through simulations, it is shown that the proposed prediction and learning strategy can obtain significant improvements in number of handoffs and operation delays performance parameters. It is also shown that future CR location is beneficial in increasing mobile CR performance. This study also shows that the number of primary user in the network and the PU protection range affect the performance of mobile CR channel selection for all methods.

Development of a Fault Monitoring Technique for Wind Turbines Using a Hidden Markov Model.

Regular inspection for the maintenance of the wind turbines is difficult because of their remote locations. For this reason, condition monitoring systems (CMSs) are typically installed to monitor their health condition. The purpose of this study is to propose a fault detection algorithm for the mechanical parts of the wind turbine. To this end, long-term vibration data were collected over two years by a CMS installed on a 3 MW wind turbine. The vibration distribution at a specific rotating speed of main shaft is approximated by the Weibull distribution and its cumulative distribution function is utilized for determining the threshold levels that indicate impending failure of mechanical parts. A Hidden Markov model (HMM) is employed to propose the statistical fault detection algorithm in the time domain and the method whereby the input sequence for HMM is extracted is also introduced by considering the threshold levels and the correlation between the signals. Finally, it was demonstrated that the proposed HMM algorithm achieved a greater than 95% detection success rate by using the long-term signals.

Hidden Markov Model Based Fault Tolerance in Credit Card Transaction Security

Credit card fake detection has raised unique challenges due to the streaming, imbalanced, and non-stationary nature of the data that has been transacted. It had additionally included an active learning step, since the labeling (fake or genuine) use of a subset on transactions is obtained in near-real time through human investigators contacted the cardholders. In this paper, the Hidden Markov Model (HMM) algorithm has been used for sequence of Credit card operations for transaction processing and the fake can be detected by using the fake detection model during transaction processing. HMM, Fake detection model and image process had played an imperative role in the detection of credit card fake in online transactions. In fake detection, most challenging is a data problem, due to two major reasons – first, the profiles of cardholders are normal and fake lent behaviors changed constantly and secondly, credit card fake data sets are highly changed its position. Using fake detection (FD) algorithm the performance of detection in credit card transactions had highly affected by the sampling approach on dataset, selection of HMM, Fake detection model. Using fake detection (FD) algorithm an image technique had been used. A reliable augmentation of the target scarce population of fakes are important considering issues such as labeling cost; algorithm HMM, fake detection and outlines in the data streamed source. We have approached several scenarios which showed the feasibility of improving detection capabilities evaluated by means of receiver operating characteristic (ROC) curves and several key performance indicators (KPI) commonly used in financial business.

A FORMULA TO CALCULATE PRUNING THRESHOLD FOR THE PART-OF-SPEECH TAGGING PROBLEM

The exact tagging of the words in the texts is a very important task in the natural language processing. It can support parsing the text, contribute to the solution of the polysemous word, and help to access a semantic information, etc. One of crucial factors in the POS (Part-of-Speech) tagging approaches based on the statistical method is the processing time. In this paper, we propose an approach to calculate the pruning threshold, which can apply into the Viterbi algorithm of Hidden Markov model for tagging the texts in the natural language processing. Experiment on the 1.000.000 words on the tag of the Wall Street Journal corpus showed that our proposed solution is satisfactory.

A Prefetching Technique Using HMM Forward and Backward Chaining for the DFS in Cloud

A general class of temporal probabilistic model have recently developed, which extends the Forward, Backward and Viterbi algorithm for hidden Markov models. The HMM (Midden Markov Model) is a probabilistic model of the joint probability of a collection of random variables with both observations and states. The algorithm is based on shrinking the state space of the HMM noticeably using such chains. The states through which the world passes are hidden, or unobserved. However, at each point in time also gets an observation that in some way reflects on the current state of the world. The Cloud Computing is a big deal for three reasons: It does not need any effort on Clients part to maintain or manage. It’s effectively infinite in size, so clients don’t need to worry about it running out of capacity. User can access cloud-based applications and services from anywhere all you need is a device with an Internet connection. In this Cloud Computing used the Distributed File Systems (DFS) for sharing and allocating the data during dynamic process .Those process are using some Prediction algorithms here using HMM Forward and Backward Chain. In this paper represents, Cloud Storage Server can Share the data among with the multiple users, using two prediction algorithms such as forward and backward chain in HMM.

Driving style recognition method using braking characteristics based on hidden Markov model.

Since the advantage of hidden Markov model in dealing with time series data and for the sake of identifying driving style, three driving style (aggressive, moderate and mild) are modeled reasonably through hidden Markov model based on driver braking characteristics to achieve efficient driving style. Firstly, braking impulse and the maximum braking unit area of vacuum booster within a certain time are collected from braking operation, and then general braking and emergency braking characteristics are extracted to code the braking characteristics. Secondly, the braking behavior observation sequence is used to describe the initial parameters of hidden Markov model, and the generation of the hidden Markov model for differentiating and an observation sequence which is trained and judged by the driving style is introduced. Thirdly, the maximum likelihood logarithm could be implied from the observable parameters. The recognition accuracy of algorithm is verified through experiments and two common pattern recognition algorithms. The results showed that the driving style discrimination based on hidden Markov model algorithm could realize effective discriminant of driving style.

Powerpoint Controller using Speech Recognition

During presentation, it is hard to maintain the slide because we need to stand in front of the room and often not able to touch the computer. The presenters need to take attention at both their voice, and body language such eye contact, facial expression, posture, gesture, and body orientation. Microsoft PowerPoint is a simple but very useful tool to create digital presentation. Even though it is simple to use, but this application required the presenter to take control while using it, such as to star the slide show or moving it to the next slide. The purpose of this research is to minimize physical contact between user and the computer during the presentation by controlling the move of the slide using voice. This research will implement the Hidden Markov Model algorithm and Sphinx-4 library.