Hidden Markov Model Training Research Articles

A research on resistance spot welding quality judgment of stainless steel sheets based on revised quantum genetic algorithm and hidden markov model

In view of the following problems existed in the data-driven resistance spot welding (RSW) quality judgment methods: relying on expert experience, resulting in a high misjudgment rate; affected by the initial value, it is easy to fall into the local extreme point; multiple parameters needed to be modulated to increase the training time of the model. Therefore, this paper proposed a RSW quality judgment method based on revised quantum genetic algorithm (RQGA) and hidden markov model (HMM). Which used quantum rotation gate to replace the evolution process of genetic algorithm (GA), reducing the number of parameters that needed to be modulated in the model, and optimizing the initial model of HMM by RQGA to avoid falling into local extreme point. At the same time, combining expert experience with HMM to make quality judgment to ensure the accuracy of judgment.Firstly, by RSW test to obtain the main influencing factors of quality, and combining with expert experience to realize the preliminary judgment of it, on this basis, HMM was established. Next, to address the susceptibility of HMM to initial model, quantum genetic algorithm (QGA) was utilized to search for the optimal initial model. Moreover, in view of the limitations of QGA (“coding length disaster” and fixed rotation angle), a corresponding improvement was also presented. At last, the established model was applied to the RSW process of stainless steel sheets railway carriage roof. Compared with the other five models, it took the least time to complete parameter training of HMM in four quality states, less than 15s; when judging the quality, its log-likelihood probability value was −47.8418, which was close to the maximum value of this state; during the classification test, the average classification accuracy of the four quality states were 90.8 %, 92.2 %, 90.8 % and 92.0 %, respectively, which was higher than the other five models. Consequently, the model established in this paper was effective.

Unveiling orphan receptor-like kinases in plants: novel client discovery using high-confidence library predictions in the Kinase-Client (KiC) assay.

Plants are remarkable in their ability to adapt to changing environments, with receptor-like kinases (RLKs) playing a pivotal role in perceiving and transmitting environmental cues into cellular responses. Despite extensive research on RLKs from the plant kingdom, the function and activity of many kinases, i.e., their substrates or "clients", remain uncharted. To validate a novel client prediction workflow and learn more about an important RLK, this study focuses on P2K1 (DORN1), which acts as a receptor for extracellular ATP (eATP), playing a crucial role in plant stress resistance and immunity. We designed a Kinase-Client (KiC) assay library of 225 synthetic peptides, incorporating previously identified P2K phosphorylated peptides and novel predictions from a deep-learning phosphorylation site prediction model (MUsite) and a trained hidden Markov model (HMM) based tool, HMMER. Screening the library against purified P2K1 cytosolic domain (CD), we identified 46 putative substrates, including 34 novel clients, 27 of which may be novel peptides, not previously identified experimentally. Gene Ontology (GO) analysis among phosphopeptide candidates revealed proteins associated with important biological processes in metabolism, structure development, and response to stress, as well as molecular functions of kinase activity, catalytic activity, and transferase activity. We offer selection criteria for efficient further in vivo experiments to confirm these discoveries. This approach not only expands our knowledge of P2K1's substrates and functions but also highlights effective prediction algorithms for identifying additional potential substrates. Overall, the results support use of the KiC assay as a valuable tool in unraveling the complexities of plant phosphorylation and provide a foundation for predicting the phosphorylation landscape of plant species based on peptide library results.

Scorpion-inspired bionic gait activity location and recognition smart home system

Vibration-based contactless technologies are arising for indoor person location and gait activity recognition applications, which can overcome issues such as privacy breaches and wearing discomfort with traditional methods to satisfy the critical need for health and safety monitoring in smart home. However, simultaneous location and recognition of occupant gait activity using information-starved vibration signals remains challenging due to its less characterization of event details. In nature, scorpions use a 3/1 neuron coding pattern to enrich vibration information by enhancing sensory differences from eight vibration sensilla embedded in their metatarsal ends of each walking leg, thus exhibiting high accuracy in locating moving prey. Inspired by this, we exploit a coding pattern to make vibration signal features richer for discrimination, while designing a bionic gait activity location and recognition system in which the data acquisition device is built by imitating scorpion vibration sensilla array distribution. To verify the feasibility of the system, we collect vibration signals produced by different people with varying gait activities (walking, jogging, running, and stepping) in an actual scene, and a trained hidden Markov model is employed to identify the activity of the current location target. The average estimated error and the relative estimated error of position estimation are calculated to be 0.3517 m and 8.79 %, respectively. The average recall and average precision of gait activity recognition are 95.83 % and 95.84 %, respectively. Our system is proven to simultaneously locate and recognize occupant gait activities, which can meet the needs including smart home, and health care monitoring.

Data-driven approach to dynamic uncertainty quantification of oil well production: Decline curve analysis and Hidden Markov Model

The upstream oil and gas industry has already used decline curve analysis to forecast oil flow rates and estimate the ultimate recovery for decades. Despite its popularity, the applications are theoretically limited and could not handle irregular variations in oil well flow behavior. In other words, it is a method for predicting the general behavior of oil wells rather than providing reliable information in specifics. It is mostly irritated by subjective implementation and a single offer of a solution without uncertainty quantification.The Hidden Markov Model (HMM) was employed in this work for dynamic uncertainty quantification in oil well flow forecast and estimated ultimate recovery (EUR). It is performed by determining the set of appropriate decline curves along with the corresponding probabilities. HMM has three main parameters: the probability transition matrix (A), the emission probability matrix (B), and the prior distribution. All these parameters can be learned from data using the Baum-Welch algorithm. The trained HMM was utilized to generate the posterior. Accordingly, using HMM and learning from the data, a dynamic probabilistic decline curve analysis is conducted. It preserves the decline curve's strength of simplicity while also covering the flaws of subjectivity and lack of uncertainty quantification. The novelty of our study is that it focuses on dynamic uncertainty quantification of oil production forecasts using new observations and covers any regular or irregular (planed or naturally stochastic) variations of flow trends. We implemented the method in cases with the variation of the flow rate by choke opening and also a sharp decline in the late time, which are not covered by decline curve analysis and not proposed in previous studies. Dynamic predictions by HMM followed the variations in flow patterns obtained by the new observations. In addition, the calculated data-driven probability distribution of EUR acceptably covers the true values.

Solving multiple sequence alignment problems by using a swarm intelligent optimization based approach

<span lang="EN-US">In this article, the alignment of multiple sequences is examined through swarm intelligence based an improved particle swarm optimization (PSO). A random heuristic technique for solving discrete optimization problems and realistic estimation was recently discovered in PSO. The PSO approach is a nature-inspired technique based on intelligence and swarm movement. Thus, each solution is encoded as “chromosomes” in the genetic algorithm (GA). Based on the optimization of the objective function, the fitness function is designed to maximize the suitable components of the sequence and reduce the unsuitable components of the sequence. The availability of a public benchmark data set such as the Bali base is seen as an assessment of the proposed system performance, with the potential for PSO to reveal problems in adapting to better performance. This proposed system is compared with few existing approaches such as deoxyribonucleic acid (DNA) or ribonucleic acid (RNA) alignment (DIALIGN), PILEUP8, hidden Markov model training (HMMT), rubber band technique-genetic algorithm (RBT-GA) and ML-PIMA. In many cases, the experimental results are well implemented in the proposed system compared to other existing approaches.</span>

A Layered, Hybrid Machine Learning Analytic Workflow for Mouse Risk Assessment Behavior.

Accurate and efficient quantification of animal behavior facilitates the understanding of the brain. An emerging approach within machine learning (ML) field is to combine multiple ML-based algorithms to quantify animal behavior. These so-called hybrid models have emerged because of limitations associated with supervised [e.g., random forest (RF)] and unsupervised [e.g., hidden Markov model (HMM)] ML models. For example, RF models lack temporal information across video frames, and HMM latent states are often difficult to interpret. We sought to develop a hybrid model, and did so in the context of a study of mouse risk assessment behavior. We used DeepLabCut to estimate the positions of mouse body parts. Positional features were calculated using DeepLabCut outputs and were used to train RF and HMM models with equal number of states, separately. The per-frame predictions from RF and HMM models were then passed to a second HMM model layer ("reHMM"). The outputs of the reHMM layer showed improved interpretability over the initial HMM output. Finally, we combined predictions from RF and HMM models with selected positional features to train a third HMM model ("reHMM+"). This reHMM+ layered hybrid model unveiled distinctive temporal and human-interpretable behavioral patterns. We applied this workflow to investigate risk assessment to trimethylthiazoline and snake feces odor, finding unique behavioral patterns to each that were separable from attractive and neutral stimuli. We conclude that this layered, hybrid ML workflow represents a balanced approach for improving the depth and reliability of ML classifiers in chemosensory and other behavioral contexts.

Hopping Time Estimation of Frequency-Hopping Signals Based on HMM-Enhanced Bayesian Compressive Sensing With Missing Observations

The hopping time reflects the time-varying characteristics of frequency-hopping (FH) signals, which are essential parameters for the spectrum estimation of FH signals. In this study, we address the problem of estimating the hopping time of multiple FH signals in the case of missing observations. We adopt a uniform linear array (ULA) to receive multiple FH signals and obtain the spatial phase difference via Bayesian compressive sensing (BCS), which is defined as the spatial frequency. We construct a hidden Markov model (HMM) with spatial frequencies. The trained HMM and received spatial frequency sequence are used to estimate the spatial frequency of the transmitter, and the mutation of the spatial frequency is used to detect the hopping time. Simulation and comparison experiments show that the proposed method is superior to the existing approaches. The hopping time can be estimated with satisfactory accuracy, even when the number of randomly missing observations is as high as 30%.

Optimization of Artificial Intelligence Model for Badminton Teaching and Training with Wireless Network Support

With the rapid development of the Internet of Things and artificial intelligence, the society gradually moves into the era of intelligence, and the research results and intelligent products based on wireless networks come into being. Machine learning algorithms are used to classify and recognize badminton strokes in this research, and a badminton technical feature statistics and pace training system are built on this foundation. By exploring the model characteristics and algorithm training method of the Hidden Markov Model (HMM), this paper proposes a model algorithm with an improved HMM training method for recognizing ten common badminton strokes, including serve, forehand rub, backhand rub, and forehand lunge. Serve, forehand rub, backhand rub, forehand flutter, forehand push, backhand push, forehand pick, backhand pick, and forehand loft are among the 10 typical badminton strokes identified by the algorithm. Our technique can distinguish ten common ball-striking movements in real-time, according to the testing.

A new high-frequency-based method for the very fast differential protection of power transformers

A novel algorithm based on Teager energy operator (TEO) and hidden Markov model (HMM) is presented for the transformer differential protection. After detecting any increase in the amplitude of the transformer differential currents, it is needed to know if the over-current is because of an internal fault or an inrush phenomenon. In this paper, a combination of TEO and HMM is used to discriminate between the magnetizing inrush currents and the internal fault currents. TEO is used to extract high frequency components of the signal and present them as a curve, named as Teager output curve (TOC). Then TOC is used as the input for HMM. First, the HMM training process is implemented by an adequate number of the train signals and then, the unknown signals are identified by the testing process. Fault type identification is also performed by the use of TOC. TOC has a separated region for each of the three phases. TEO of the zero-sequence signal has a peak for the grounded and no peak for the un-grounded faults. Train and test signals are generated by the simulated system in PSCAD/EMTDC. Results by means of the simulated and experimental data show the robustness of the proposed algorithm.

Application of Artificial Intelligence Elements and Multimedia Technology in the Optimization and Innovation of Teaching Mode of Animation Sound Production

Nowadays, with the rapid development of multimedia technology and computer information processing, the data of multimedia information presents explosive growth. At present, the method of using artificial recognition of sound materials is inefficient, and an automatic recognition and classification system of sound materials is needed. To improve the accuracy of sound recognition, two algorithm models are established to identify and compare the sound materials, which are the hidden Markov model (HMM) and back propagation neural network (BPNN) model. Firstly, HMM is established, and the sound material is randomly selected as the test sample. The comparison between the expected classification and the actual is tested, and the recognition rate of each classification is got. The final average recognition rate is 61%. The anti-interference characteristics of the training HMM are tested, and the identification rate of the training model is selected in 6 types of signal-to-noise ratio (SNR) environments. The recognition rate of the training model has an obvious downward trend with the decrease of the SNR. Secondly, the BPNN model is built, and 200 BPNN training experiments are conducted. The training model with the highest average recognition rate is selected as the experimental model. The average recognition rate of the final model is higher than 90%. The expression ability and stability of the trained model are simulated after the new sample is introduced, and the anti-interference performance of the model is tested in different environments of SNR. The results of performance test are good, and only the recognition rate of complex types of some sound sources decreased. Finally, the accuracy of the HMM in the experiment is not as high as that obtained by BPNN. Therefore, the training method of BPNN has a greater advantage in both recognition accuracy and recognition efficiency for the studied sound. It provides a reference for automatic recognition of sound materials.

Self-segmentation of pass-phrase utterances for deep feature learning in text-dependent speaker verification

In this paper, we propose a novel method to segment and label pass-phrase utterances for training deep neural network (DNN) bottleneck (BN) features for text-dependent speaker verification (TD-SV). Specifically, gender-dependent hidden Markov models (HMMs) for monophones are first trained using the pass-phrase utterances that are disjoint from evaluation. Next, the trained HMMs are speaker-adapted and then used for segmenting and labeling these training utterances at the phone level. The resulted labeled data is subsequently used for training DNN models to discriminate gender-dependent phones for the purpose of extracting phone-discriminant BN features. This is in contrast to conventional approaches that apply a general-purpose, speaker-independent automatic speech recognition (ASR) system for generating segmentation and labels. The proposed method eliminates the need for a separate ASR system, which can additionally have the disadvantage of mismatch with the pass-phrase utterances in terms languages, dialects, domains, acoustic conditions and so on. Experiments are conducted on the RedDots challenge 2016 database of TD-SV using short utterances with Gaussian mixture model-universal background model and i-vector techniques. Experimental results demonstrate that the proposed method yields lower error rates in TD-SV when compared to a set of existing methods. A thorough ablation study further confirms the effectiveness of the method. Fusion in both score and feature levels also shows the complementary nature of the proposed features.

A new algorithm to train hidden Markov models for biological sequences with partial labels

BackgroundHidden Markov models (HMM) are a powerful tool for analyzing biological sequences in a wide variety of applications, from profiling functional protein families to identifying functional domains. The standard method used for HMM training is either by maximum likelihood using counting when sequences are labelled or by expectation maximization, such as the Baum–Welch algorithm, when sequences are unlabelled. However, increasingly there are situations where sequences are just partially labelled. In this paper, we designed a new training method based on the Baum–Welch algorithm to train HMMs for situations in which only partial labeling is available for certain biological problems.ResultsCompared with a similar method previously reported that is designed for the purpose of active learning in text mining, our method achieves significant improvements in model training, as demonstrated by higher accuracy when the trained models are tested for decoding with both synthetic data and real data.ConclusionsA novel training method is developed to improve the training of hidden Markov models by utilizing partial labelled data. The method will impact on detecting de novo motifs and signals in biological sequence data. In particular, the method will be deployed in active learning mode to the ongoing research in detecting plasmodesmata targeting signals and assess the performance with validations from wet-lab experiments.

Real-time classification of brain tumors in MRI images with a convolutional operator-based hidden Markov model

Classification of brain tumors based on the brain magnetic resonance imaging (MRI) results of patients has become an important problem in medical image processing. A computer program that can efficiently analyze brain MRI images of patients in real time and generate accurate classification results of the tumors in these images can significantly reduce the amount of time needed for diagnosis, which may increase the chances for patients to survive. This paper proposes a new statistical method that can accurately classify three types of brain tumors based on MRI images, the three types of tumors considered include pituitary tumor, glioma, and meningioma. The features for a pixel in an MRI image are obtained by applying a set of convolutional operators to the neighborhood area of the pixel. For training, a hidden Markov model (HMM) is constructed and trained from a training dataset by computing a statistical profile for the feature vectors for pixels in the tumor regions of each type of brain tumors. In addition, a statistical profile is also obtained for pixels that are in the background of a tumor. For classification, the trained HMM is used to assign labels to pixels in an MRI image with a dynamic programming approach and the classification result of the image is obtained from the labels assigned to the tumor region. Both the training and classification processes can be efficiently performed in linear time and does not require the availability of a large amount of computational resources. Experimental results on a large dataset of MRI images show that the proposed method can provide classification results with high accuracy for all three types of brain tumors. A comparison with state-of-the-art methods for brain tumor classification suggests that the proposed method can achieve improved classification accuracy. In addition, real-time analysis also reveals that the proposed approach can probably be used for real-time classification of brain tumors.

Human Activity Recognition Based on Acceleration Data From Smartphones Using HMMs

Smartphones are among the most popular wearable devices to monitor human activities. Several existing methods for Human Activity Recognition (HAR) using data from smartphones are based on conventional pattern recognition techniques, but they generate handcrafted feature vectors. This drawback is overcome by deep learning techniques which unfortunately require lots of computing resources, while generating less interpretable feature vectors. The current paper addresses these limitations through the proposal of a Hidden Markov Model (HMM)-based technique for HAR. More formally, the sequential variations of spatial locations within the raw data vectors are initially captured in Markov chains, which are later used for the initialization and the training of HMMs. Meta-data extracted from these models are then saved as the components of the feature vectors. The meta-data are related to the overall time spent by the model observing every symbol for a long time span, irrespective of the state from which this symbol is observed. Classification experiments involving four classification tasks have been carried out on the recently constructed UniMiB SHAR database which contains 17 classes, including 9 types of activities of daily living and 8 types of falls. As a result, the proposed approach has shown best accuracies between 92% and 98.85% for all the classification tasks. This performance is more than 10% better than prior work for 2 out of 4 classification tasks.

Design and implementation of bi-level artificial bee colony algorithm to train hidden Markov models for performing multiple sequence alignment of proteins

Multiple sequence alignment (MSA) is an NP-complete problem that is a challenging area from bioinformatics. Implementation of hidden Markov model (HMM) is one of the most effective approach for executing MSA, that performs training and testing of the sequence data so as to obtain alignment scores with accuracy. The training of HMM is again an NP-hard problem, hence it requires the implementation of metaheuristic methods. Proposed work presents a bi-level artificial bee colony (BL-ABC) algorithm to train hidden Markov models (HMMs) for MSA of proteins, i.e., BLABC-HMM. The trained stochastic model created by BL-ABC basically yields position-dependent probability matrices at higher prediction ratios. The performance of proposed algorithm is compared with the competitive state-of-the-art algorithms and different variants of particle swarm optimisation (PSO) algorithm on protein benchmark datasets from pfam and BAliBase database, and BLABC-HMM is found yielding better alignment scores and prediction accuracy.

Design and implementation of bi-level artificial bee colony algorithm to train hidden Markov models for performing multiple sequence alignment of proteins

Design and implementation of bi-level artificial bee colony algorithm to train hidden Markov models for performing multiple sequence alignment of proteins

Computational phonogram archiving

A general approach to analyzing audio files makes it possible to re-create the sound of ancient instruments, identify cross-cultural musical properties, and more.

Gyro Motor State Evaluation and Prediction Using the Extended Hidden Markov Model

This study extracted the featured vectors in the same way from testing data and substituted these vectors into a trained hidden Markov model to get the log likelihood probability. The log likelihood probability was matched with the time–probability curve from where the gyro motor state evaluation and prediction were realized. A core component of gyroscopes is linked to the reliability of the inertia system to conduct gyro motor state evaluation and prediction. This study features the vectors’ extraction from full life cycle gyro motor data and completes the training model to feature the vectors according to the time sequence and extraction to full life cycle data undergoing hidden Markov model training. This proposed model applies to full life cycle gyro motor data for validation, compared with traditional hidden Markov model predictive methods and health condition-trained data. The results suggest precise evaluation and prediction and provide an important basis for gyro motor repair and replacement strategies.

Using hidden Markov model to predict recurrence of breast cancer based on sequential patterns in gene expression profiles

A new approach is presented to predict breast cancer recurrence through gene expression profiles using hidden Markov models (HMM). In this regard, 322 genes were selected from 44 published gene lists related to breast cancer prognosis. Afterwards, using gene set enrichment analysis, 922 gene sets were found from subsets of genes with the same biological meaning. In order to extract the sequential patterns from gene expression data, we ranked the gene sets using appropriate criteria and used HMM in which the ranked gene sets considered as observation sequences and hidden states represented priority of gene sets for discriminating between expression profiles. In this experiment, seven publicly available microarray datasets, including 1271 breast tumor samples, were used to classify cancer patients into two groups according to risk of recurrence. Our experiments indicated the greater performance and more robustness of the proposed model compared with other widely used classification methods.

Upper Arm Action Recognition for Self Training with a Smartphone

The action recognition for upper arm training, in low-cost and effective way, has great application in both sport training and rehabilitation training. However,they almost require extra and expensive equipments. This paper proposes an approach for real-time recognition of upper arm actions based on Hidden Markov Model (HMM) only one sensor and one smartphoneare needed. Data collected by a sensor and Action Pattern Sets are established with HMM training. Empirical Results with the smartphone, one for self-coaching for badminton technique improvement and another for arm injuries rehabilitation, validating the effectiveness and usability. Some problems found on site show that the next step is to further optimize the Action Pattern Sets to improve the overall accuracy and users’subjective satisfaction.