Pattern Recognition Algorithms Research Articles

A method of sequentially generating a set of components of a multidimensional random variable using a nonparametric pattern recognition algorithm

We study in which way a priori information on the independence of random variables affects the approximation accuracy of a nonparametric estimate of the Rosenblatt–Parzen probability density. A new technique for generating sets of independent components of a multidimensional random variable is proposed. The methodology is based on testing the hypotheses of the independence of combinations of the multidimensional random variable components using a two-alternative nonparametric kernel algorithm for pattern recognition corresponding to the maximum likelihood criterion. Classes correspond to the domains of definition of the probability densities of sets of independent and dependent components of the multidimensional random variable. Nonparametric statistics of the kernel type are used to estimate the probability densities. The choice of the bandwidths of the kernel estimates of the probability densities is made from the condition of the minimum root-mean-square criterion. The sequential procedure for generating a set of independent components begins with the analysis of paired combinations of components of a multidimensional random variable. For each pair of components, the probability of an error in recognizing classes corresponding to the assumptions of independence and dependence of the considered components is estimated. A pair of components with the maximum difference between these errors is determined. If the errors obtained do not differ significantly, then there are no independent components in the considered multivariate random variable. If there is a significant difference in the probability estimates of class recognition errors, a pair of independent components is established. These components are included in a three-component set of a multidimensional random variable. The analysis of their combinations is carried out in the same way, following the above-described procedure. The process of generating the set of independent components is stopped when no reliable difference occurs any more between the probabilities of errors in recognizing situations belonging to the accepted classes. In this case, the previous set of independent components is the desired result. In contrast to the traditional methodology based on the Pearson criterion, the proposed approach allows us to bypass a problem of the decomposition of the range of values of random variables into multidimensional intervals. The method of generating a set of independent components of a multidimensional random variable is illustrated by the results of the analysis of spectral features of remote sensing data of forest tracts using space imagery from the Landsat-8 satellite.

Formation of Sets of Independent Components of a Multidimensional Random Variable Based on a Nonparametric Pattern Recognition Algorithm

Formation of Sets of Independent Components of a Multidimensional Random Variable Based on a Nonparametric Pattern Recognition Algorithm

Evaluation of the seismogenic (M6+) nodes for the territory of Bulgaria and adjacent areas

In this study seismogenic nodes capable to generate earthquakes with magnitudes M ≥ 6 are identified for the territory of Bulgaria and adjacent areas. Definition of nodes is based on a morphostructural zonation. Pattern recognition algorithm Cora-3 is applied to identify the seismogenic nodes, characterized by specific geological and geophysical data. The pattern recognition method is trained on information for 30 seismic events with M ≥ 6 for the period 29 BC–2020, selected from historical and instrumental Bulgarian earthquake catalogues. As a result, 56 seismogenic nodes are recognized, most of them in southwestern Bulgaria.

Energy management strategy for battery/supercapacitor hybrid electric city bus based on driving pattern recognition

The rapid development of cloud techniques like Vehicle-to-Cloud (V2C) makes it possible to gather more information and develop computationally efficient energy management systems (EMS) for electric vehicles. This paper proposes a novel EMS with low computational cost targeting hybrid battery/ultracapacitor electric buses to reduce energy consumption and battery life degradation. In the offline training process, by applying the K-means clustering method with 10 selected features, 16 typical driving conditions are classified. For each driving condition, dynamic programming is employed offline to generate global optimal results, which are then used in control rule extraction for online operation. During the online operation, the proposed EMS executes the designed driving pattern recognition algorithm with V2C assistance to select optimal control rules. The simulation results indicate that the proposed EMS effectively decreases the battery degradation and energy consumption cost by 13.89%, compared with the conventional rule-based strategy. In addition, it is shown that V2C assistance leads to a 6.81% lower cost. Besides, the robustness of the proposed EMS is validated by testing the EMS with highly randomized input with uncertainties up to 15% and long duration of V2C data packet loss up to 10 s.

Fault diagnosis of train rotating parts based on multi-objective VMD optimization and ensemble learning

Rotating machinery is widely used in various systems of trains, and its health status is directly related to the reliability of train operation. Therefore, the fault diagnosis of train rotating machinery plays a promoting role in the safe operation and maintenance of trains. Due to the influence of track excitation and other equipment vibration, the vibration signal of rotating machinery is non-stationary and nonlinear, which brings challenges to the fault diagnosis of rotating machinery. To solve this problem, an intelligent fault diagnosis method for rotating machinery based on multi-objective variational mode decomposition (VMD) optimization and ensemble learning is proposed. Firstly, an improved multi-verse optimizer (MVO) algorithm is proposed by introducing Tent chaos theory and Levy flight theory, and a multi-objective VMD parameter optimization model is established. The improved MVO algorithm is utilized to optimize the parameters and reconstruct the signal. Then, a multi-domain feature extraction method is proposed for multi-domain fault feature extraction and feature selection. Finally, an adaptive mutation particle swarm optimization random forest (AMPSO-RF) pattern recognition algorithm is proposed for fault pattern recognition. Through the verification of bearing and gear fault data, the results showed that the raised method can accurately realize fault diagnosis of train rotating parts, and the accuracy rate reaches 100%, which is better than the compared methods.

SEMG-Based Hand Posture Recognition Considering Electrode Shift, Feature Vectors, and Posture Groups.

Surface electromyography (sEMG)-based gesture recognition systems provide the intuitive and accurate recognition of various gestures in human-computer interaction. In this study, an sEMG-based hand posture recognition algorithm was developed, considering three main problems: electrode shift, feature vectors, and posture groups. The sEMG signal was measured using an armband sensor with the electrode shift. An artificial neural network classifier was trained using 21 feature vectors for seven different posture groups. The inter-session and inter-feature Pearson correlation coefficients (PCCs) were calculated. The results indicate that the classification performance improved with the number of training sessions of the electrode shift. The number of sessions necessary for efficient training was four, and the feature vectors with a high inter-session PCC (r > 0.7) exhibited high classification accuracy. Similarities between postures in a posture group decreased the classification accuracy. Our results indicate that the classification accuracy could be improved with the addition of more electrode shift training sessions and that the PCC is useful for selecting the feature vector. Furthermore, hand posture selection was as important as feature vector selection. These findings will help in optimizing the sEMG-based pattern recognition algorithm more easily and quickly.

An Intelligent Multimode Clustering Mechanism Using Driving Pattern Recognition in Cognitive Internet of Vehicles.

Connected autonomous vehicles can leverage communication and artificial intelligence technologies to effectively overcome the perceived limitations of individuals and enhance driving safety and stability. However, due to the high dynamics of the vehicular network and frequent interruptions and handovers, it is still challenging to provide stable communication connections between vehicles, which is likely to cause disasters. To address this issue, in this paper, we propose an intelligent clustering mechanism based on driving patterns in heterogeneous Cognitive Internet of Vehicles (CIoVs). In the proposed approach, we analyze the driving mode containing multiple feature parameters to accurately capture the driving characteristics. To ensure the accuracy of pattern recognition, a genetic algorithm-based neural network pattern recognition algorithm is proposed to support the reliable clustering of connected autonomous vehicles. The cognitive engines recognize the driving modes to group vehicles with a similar driving mode into a relatively stable cluster. In addition, we formulate the stability and survival time of clusters and analyze the communication performance of the clustering mechanism. Simulation results show that the proposed mechanism improves the reliable communication throughput and average cluster lifetime by approximately 14.4% and 11.5% respectively compared to the state-of-the-art approaches.

Confirmation of Transit Time-Limited Field Emission in Advanced Carbon Materials with a Fast Pattern Recognition Algorithm

Confirmation of Transit Time-Limited Field Emission in Advanced Carbon Materials with a Fast Pattern Recognition Algorithm

Machine Learning for Capillary Pressure Estimation

Summary Capillary pressure plays an essential role in controlling multiphase flow in porous media and is often difficult to be estimated at subsurface conditions. The Leverett capillary pressure function J provides a convenient tool to address this shortcoming; however, its performance remains poor where there is a large scatter in the scaled data. Our aim, therefore, was to reduce the gaps between J curves and to develop a method that allows accurate scaling of capillary pressure. We developed two mathematical expressions based on permeability and porosity values of 214 rock samples taken from North America and the Middle East. Using the values as grouping features, we used pattern-recognition algorithms in machine learning to cluster the original data into different groups. In each wetting phase saturation, we were able to quantify the gaps between the J curves by determining the ratio of the maximum J to the minimum J. Graphical maps were developed to identify the corresponding group for a new rock sample after which the capillary pressure is estimated using the average J curve of the identified group and the permeability and porosity values of the rock sample. This method also provides better performance than the flow zone indicator (FZI) approach. The proposed technique was validated on six rock types and has successfully generated average capillary pressure curves that capture the trends and values of the experimentally measured data by mercury injection. Moreover, the proposed methodology in this study provides an advanced and a machine-learning-oriented approach for rock typing. In this paper, we provide a reliable and easy-to-use method for capillary pressure estimation in the absence of experimentally measured data by mercury injection.

An Adaptive Multi-Modal Control Strategy to Attenuate the Limb Position Effect in Myoelectric Pattern Recognition.

Over the last few decades, pattern recognition algorithms have shown promising results in the field of upper limb prostheses myoelectric control and are now gradually being incorporated in commercial devices. A widely used approach is based on a classifier which assigns a specific input value to a selected hand motion. While this method guarantees good performance and robustness within each class, it still shows limitations in adapting to different conditions encountered in real-world applications, such as changes in limb position or external loads. This paper proposes an adaptive method based on a pattern recognition classifier that takes advantage of an augmented dataset—i.e., representing variations in limb position or external loads—to selectively adapt to underrepresented variations. The proposed method was evaluated using a series of target achievement control tests with ten able-bodied volunteers. Results indicated a higher median completion rate >3.33% for the adapted algorithm compared to a classical pattern recognition classifier used as a baseline model. Subject-specific performance showed the potential for improved control after adaptation and a ≤13% completion rate; and in many instances, the adapted points were able to provide new information within classes. These preliminary results show the potential of the proposed method and encourage further development.

Single Shot Multibox Detector Automatic Polyp Detection Network Based on Gastrointestinal Endoscopic Images.

Purpose In order to resolve the situation of high missed diagnosis rate and high misdiagnosis rate of the pathological analysis of the gastrointestinal endoscopic images by experts, we propose an automatic polyp detection algorithm based on Single Shot Multibox Detector (SSD). Method In the paper, SSD is based on VGG-16, the fully connected layer is changed to a convolutional layer, and four convolutional layers with successively decreasing scales are added as a new network structure. In order to verify the practicability, it is not only compared with manual polyp detection but also with Mask R-CNN. Results Multiple experimental results show that the mean Average Precision (mAP) of the SSD network is 95.74%, which is 12.4% higher than the manual detection and 5.7% higher than the Mask R-CNN. When detecting a single frame of image, the detection speed of SSD is 8.41 times that of manual detection. Conclusion Based on the traditional pattern recognition algorithm and the target detection algorithm using deep learning, we select a variety of algorithms to identify and classify polyps to achieve efficient detection results. Our research demonstrates that deep learning has a lot of room for development in the field of gastrointestinal image recognition.

Investigation of the ecology of winter plankton of Lake Baikal using complex instrumental methods

Aim . The continuous monitoring of changes in ecosystems must be carried out in connection with global climate changes that affect the state of water bodies. Remote sensing methods have many advantages as a promising method for monitoring biocenoses in large water bodies. We carried out a comprehensive study comparing the results obtained using the latest instruments and methods to expand their further application to the continuous monitoring of water bodies. Material and Methods . The field research was undertaken using hydroacoustic sensors, submersible holographic camera and high‐resolution thermal sensors in addition to the classical methods of studying the zooplankton ecology – the Juday net and CTD probe. Water temperature, chlorophyll, photosynthetically active radiation and other parameters were measured with an AAQ‐Rinko probe. We provided data for one vertical up to a depth of 100 m. Results . The main components of mesozooplankton during the ice period are different age stages of the endemic crustacean Epischura baikalensis Sars 1900 and several rotifer species. The article discusses the heterogeneity of the environment and the distribution of plankton detected by various instruments. Conclusion . The experimental results obtained with the help of a set of devices show that the distribution of zooplankton is very strongly dependent on the physical parameters of the environment. The use of remote sensing methods is an important step towards the automation of basic monitoring of the ecosystem of Lake Baikal and other water bodies. The obtained field data will make it possible to further improve the pattern recognition algorithm in the software of the holographic installation for the specific conditions of Lake Baikal. The results of the vertical distribution and migrations of zooplankton in connection with environmental parameters are assumed to be processed using mathematical modeling methods.

A hand-held optoelectronic tongue for the identification of heavy-metal ions

Heavy-metal ions detection conventionally relies on standard instruments that are complicated, time-consuming and constrained to laboratories. To mitigate this problem, we developed a hand-held and cost-effective smartphone-integrated analysis platform that allows fast identification of heavy-metal ions pollution caused by industrial wastewater discharge. This portable platform integrates a colorimetric sensor array consisting of plasmonic nanocolorants and organic chromophores to detect typical heavy-metal ions at the ppm level within 15 s. The image of the colorimetric sensor array is transmitted to the Complementary metal–oxide–semiconductor (CMOS) imager of the smartphone via 96 individual optical fibers, generating RGB differential fingerprints and quantitatively analyzed by pattern recognition algorithms. Facile identification of 13 common heavy-metal ions (Hg2+, Cd2+, Cr6+, Pb2+, Ni2+, Se4+, Mg2+, Ba2+, Zn2+, As3+, Mn6+, Fe3+, Cu2+) was demonstrated using several different multivariate analyses of the digital data library, including principal component and hierarchical cluster analysis. Furthermore, we demonstrated the multiplexed detection and classification of 4 typical industrial wastewater models (Electroplating, Battery, Metallurgical, Pesticide wastewater) and real water samples with this portable platform, and achieved good discrimination and reproducibility. Combined with edge computing of smartphones and Internet-of-Things (IoT) cloud infrastructure, the portable platform shows feasible potential for pollution traceability, environmental monitoring, and water quality analysis.

Gas identification with drift counteraction for electronic noses using augmented convolutional neural network

Sensor drift is the most challenging problem in the chemical sensing of an electronic nose system. We have proposed a new pattern recognition approach, namely augmented convolutional neural network (ACNN) to solve a gas discrimination problem over an extended period with high accuracy rates. The ACNN model is a continuously updated machine learning framework that automatically transforms the time-varying gas signals into a multi-dimensional feature matrix, then takes the incremental data to extend the existing model's knowledge with internal parameter tuning, and further compensate the model deviation in virtue of an external adjustment module over the base CNN classifier. Three different cases originating from self-collected short-term data (4-month) to the very long-term public dataset (3-year) are tested to verify the proposed approach compared with the existing e-nose pattern recognition algorithms including support vector machine (SVM), backpropagation neural network (BP), ensemble classifiers (En_wts), and ensemble classifiers with uniform weights (Uni_wts) as well as the normal CNN model. Experiments indicate the presence of e-nose drift over extended periods. Results show that the proposed method can cope well with sensor drift and gets superior performance than the traditional classifiers, with an accuracy increase of over 30% for the worst case.

Elevated C-Reactive Protein in Alzheimer's Disease Without Depression in Older Adults: Findings From the Health and Retirement Study.

We examined the association between differential diagnoses of major stroke and probable Alzheimer's disease (AD) and mixed AD on C-reactive protein (CRP) in older adults with and without depression. Secondary data analyses examined associations between blood-based measures of probable peripheral inflammation using CRP collected from dried blood spots in the Health and Retirement Study, a nationally representative sample of individuals aged 50 and older. A validated pattern-recognition algorithm was utilized to identify cognitive decline indicative of probable AD, mixed AD, and major stroke. Negative binomial regressions were utilized to model concentrations of serologic CRP. On average, participants (N = 4 601) were 70 years old, female, and non-Hispanic White. Mixed AD participants had a 0.26 mg/dL increase in CRP compared to unimpaired participants, controlling for demographics, health behaviors, and comorbidities. Those with mixed AD had 2.14 times increased odds of having high CRP (odds ratio = 2.14 [1.19-3.85]). In analyses stratified by depression, adults with mixed AD and without depression had an additional 0.37 mg/dL increase in CRP (SE = 0.06; p < .001) compared to unimpaired adults. Those with AD without depression had a 0.20 mg/dL increase in CRP (SE = 0.07; p < .01). Age was not associated with increased CRP in nondepressed older adults. Depressed adults with major stroke had a -0.26 mg/dL decrease in CRP (SE = 0.11; p = .02), controlling for hypertension, alcoholic drinks/beverages per week, and smoking status. Concentration modeling revealed that participants with major stroke, probable AD, and probable mixed AD without depression had significantly higher CRP concentrations when compared to unimpaired older adults.

Nonparametric pattern recognition algorithm for testing a hypothesis of the independence of random variables

A new method for testing a hypothesis of the independence of multidimensional random variables is proposed. The technique under consideration is based on the use of a nonparametric pattern recognition algorithm that meets a maximum likelihood criterion. In contrast to the traditional formulation of the pattern recognition problem, there is no a priori training sample. The initial information is represented by statistical data, which are made up of the values of a multivariate random variable. The distribution laws of random variables in the classes are estimated according to the initial statistical data for the conditions of their dependence and independence. When selecting optimal bandwidths for nonparametric kernel-type probability density estimates, the minimum standard deviation is used as a criterion. Estimates of the probability of pattern recognition error in the classes are calculated. Based on the minimum value of the estimates of the probabilities of pattern recognition errors, a decision is made on the independence or dependence of the random variables. The technique developed is used in the spectral analysis of remote sensing data.

A Data-Driven Framework for Early-Stage Fatigue Damage Detection in Aluminum Alloys Using Ultrasonic Sensors

The paper presents a coupled machine learning and pattern recognition algorithm to enable early-stage fatigue damage detection in aerospace-grade aluminum alloys. U- and V-notched Al7075-T6 specimens are instrumented with a pair of ultrasonic sensors and, thereafter, tested on an MTS apparatus integrated with a confocal microscope and a digital microscope. The confocal microscope is focused on the notch root of the specimens, whereas the digital microscope is focused on the side of the notch. Two features, viz., the crack opening displacement (COD) and the crack length, are extracted during the tests in addition to the ultrasonic signal data. These signal data are analyzed using a machine learning framework that is built upon a symbolic time-series algorithm. This framework is interrogated for crack detection in the crack coalescence (CC) regime defined by COD of ~3 μm and detected through the confocal microscope. Additionally, the framework is probed in the crack propagation (CP) regime characterized by a crack length of ~0.2 mm and detected via the digital microscope. For the CC regime, training accuracies of 79.82% and 81.94% are achieved, whereas testing accuracies of 68.18% and 74.12% are observed for the U- and V-notched specimens, respectively. For the CP regime, overall training accuracies of 88.3% and 91.85% are observed, and accordingly, testing accuracies of 81.94% and 85.62% are obtained for the U- and V-notched specimens, respectively. The results show that a combined machine learning and pattern recognition algorithm enables robust and reliable fatigue damage detection in aerospace structural components.

Pattern recognition of EMG signals for low level grip force classification

Grasping of the objects is the most frequent activity performed by the human upper limb. The amputations of the upper limb results in the need for prosthetic devices. The myoelectric prosthetic devices use muscle signals and apply control techniques for identification of different levels of hand gesture and force levels. In this study; a different level force contraction experiment was performed in which Electromyography (EMGs) signals and fingertip force signals were acquired. Using this experimental data; a two-step feature selection process is applied for the designing of a pattern recognition algorithm for the classification of different force levels. The two step feature selection process consist of generalized feature ranking using ReliefF, followed by personalized feature selection using Neighborhood Component Analysis (NCA) from the shortlisted features by earlier technique. The classification algorithms applied in this study were Support Vector Machines (SVM) and Random Forest (RF). Besides feature selection; optimization of the number of muscles during classification of force levels was also performed using designed algorithm. Based on this algorithm; the maximum classification accuracy using SVM classifier and two muscle set was achieved as high as 99%. The optimal feature set consisted features such as Auto Regressive coefficients, Willison Amplitude and Slope Sign Change. The mean classification accuracy for different subjects, achieved using SVM and RF was 94.5% and 91.7% respectively.

Blueshifted Hydrogen Emission and Shock Wave of RR Lyrae Variables in SDSS and LAMOST

Abstract Hydrogen emissions of RR Lyrae variables are the imprints of shock waves traveling through their atmospheres. We develop a pattern recognition algorithm, which is then applied to single-epoch spectra of the Sloan Digital Sky Survey and the Large Sky Area Multi-Object Fiber Spectroscopic Telescope survey. These two spectroscopic surveys covered ∼10,000 photometrically confirmed RR Lyrae stars. We discovered in total 127 RR Lyrae stars with blueshifted Balmer emission features, including 103 fundamental mode (RRab), 20 first-overtone (RRc), 3 double-mode (RRd), and 1 Blazhko-type (temporary classification for RR Lyrae stars with strong Blazhko modulation in the Catalina sky survey that cannot be characterized) RR Lyrae variable. This forms the largest database to date of the properties of hydrogen emission in RR Lyrae variables. Based on Zwicky Transient Facility DR5, we carried out a detailed light-curve analysis for the Blazhko-type RR Lyrae star with hydrogen emission of long-term modulations. We characterize the Blazhko-type RR Lyrae star as an RRab and point out a possible Blazhko period. Finally, we set up simulations on mock spectra to test the performance of our algorithm and on the real observational strategy to investigate the occurrence of the “first apparition.”

ЗАСТОСУВАННЯ НЕЙРОННИХ МЕРЕЖ МГУА ДЛЯ ВИЯВЛЕННЯ ЗМІНИ УМОВ РОБОТИ НАСОСНОЇ СТАЦІЇ ВОДОПОСТАЧАННЯ, ЗУМОВЛЕНИХ ВПЛИВОМ СЕЗОННИХ ЧИННИКІВ

Purpose. Development of a mechanism identification of changes in the actual operation conditions of the water supply facility depending on the season. Methodology. Methods of intellectual analysis of profiles of mode indicators were used to identify regularities in the formation of the operation mode of the facility. The mathematical apparatus of pattern recognition algorithm with training was used to classify the profiles of mode indicators. Methods of self-organization of models of complex systems were used for structural and parametric identification of the classifier model. Results. The necessity of the analysis of the characteristics of operation mode of the pumping station of water supply, obtained from the monitoring system, to identify regularities in the formation of water supply was substantiated. The daily graph of water consumption from the water supply network was used as a mode indicator of the water supply process. Indicators of water supply volumes and graph unevenness were used to describe the water supply graph. The expediency of application of self-organization methods for solving the problem of classification and construction of the classifier model was substantiated. Structural and parametric identification of the classifier model for daily water consumption graphs was performed using GMDH Neural Networks. The search for the optimal model was performed in three classes of neural networks. Better neural network structure was chosen on the basis of criterion of regularity. The K-block cross-validation strategy was used to test the models. The results of the verification of the classifier model showed the high quality of the classification. Originality. A method for identifying changes in the operation conditions of the water supply facility due to the influence of seasonal factors, based on the usage of the classifier of profiles of daily water consumption graphs from the water supply network, was proposed. Practical value. The constructed model of the classifier allows defining of belonging of a profile of the daily water consumption graph, received from monitoring system of the water supply mode, to one of typical classes. The fact of class change indicates a change in the actual operation conditions of the water supply facility. Conclusions. Analysis of daily graphs of water consumption using the pattern recognition algorithm makes it possible to establish the change in the actual operation conditions of the water supply facility caused by the influence of seasonal factors. The usage of neural networks of GMDH makes it possible to perform automatically structural and parametric identification of the classifier model. Application of the offered principles is a basis of effective planning of operation modes of pumping station of water supply. References 16, tables 3.