Ensemble Approach Combining Deep Residual Networks and BiGRU with Attention Mechanism for Classification of Heart Arrhythmias

This research introduces an innovative ensemble approach,combining Deep Residual Networks(ResNets)and Bidirectional Gated Recurrent Units(BiGRU),augmented with an Attention Mechanism,for the classification of heart arrhythmias.The escalating prevalence of cardiovascular diseases necessitates advanced diagnostic tools to enhance accuracy and efficiency.The model leverages the deep hierarchical feature extraction capabilities of ResNets,which are adept at identifying intricate patterns within electrocardiogram(ECG)data,while BiGRU layers capture the temporal dynamics essential for understanding the sequential nature of ECG signals.The integration of an Attention Mechanism refines the model’s focus on critical segments of ECG data,ensuring a nuanced analysis that highlights the most informative features for arrhythmia classification.Evaluated on a comprehensive dataset of 12-lead ECG recordings,our ensemble model demonstrates superior performance in distinguishing between various types of arrhythmias,with an accuracy of 98.4%,a precision of 98.1%,a recall of 98%,and an F-score of 98%.This novel combination of convolutional and recurrent neural networks,supplemented by attention-driven mechanisms,advances automated ECG analysis,contributing significantly to healthcare’s machine learning applications and presenting a step forward in developing non-invasive,efficient,and reliable tools for early diagnosis and management of heart diseases.

Convolutional LSTM Network for Heart Disease Diagnosis on Electrocardiograms

Heart disease is a leading cause ofmortality worldwide.Electrocardiograms(ECG)play a crucial role in diagnosing heart disease.However,interpreting ECGsignals necessitates specialized knowledge and training.The development of automated methods for ECG analysis has the potential to enhance the accuracy and efficiency of heart disease diagnosis.This research paper proposes a 3D Convolutional Long Short-Term Memory(Conv-LSTM)model for detecting heart disease using ECG signals.The proposed model combines the advantages of both convolutional neural networks(CNN)and long short-term memory(LSTM)networks.By considering both the spatial and temporal dependencies of ECG,the 3D Conv-LSTM model enables the detection of subtle changes in the signal over time.The model is trained on a dataset of ECG recordings from patients with various heart conditions,including arrhythmia,myocardial infarction,and heart failure.Experimental results show that the proposed 3D Conv-LSTM model outperforms traditional 2D CNN models in detecting heart disease,achieving an accuracy of 88%in the classification of five classes.Furthermore,themodel outperforms the other state-of-the-art deep learning models for ECG-based heart disease detection.Moreover,the proposedConv-LSTMnetwork yields highly accurate outcomes in identifying abnormalities in specific ECG leads.The proposed 3D Conv-LSTM model holds promise as a valuable tool for automated heart disease detection and diagnosis.This study underscores the significance of incorporating spatial and temporal dependencies in ECG-based heart disease detection.It highlights the potential of deep-learning models in enhancing the accuracy and efficiency of diagnosis.

Corrosion behavior of magnesium in aqueous sulfate-containing electrolytes

Studies have been conducted on the corrosive behavior of magnesium in aqueous sulfate electrolytes(0.5 mol/L MgSO_(4);0.5 mol/L Na2SO_(4);0.5 mol/L MgSO_(4)+0.5 mol/L Na2SO_(4)).The composition structure and morphology of the surface of the samples were studied using scanning electron microscopy in combination with X-ray spectral microanalysis.The results of the experiments showed the formation of a surface film inhomogeneous in its structure and composition with the main components Mg(OH)_(2)and Mg O.An increase in the exposure time of the electrode in solution led to the formation of microcracks on the main film caused by internal stress because of hydration of magnesium oxide produced during corrosion.The salt composition of the electrolyte determines the morphology and thickness of corrosion films due to differences in the solubility of the products formed during the hydrolysis of magnesium oxide and the kinetics of this process.Applying the methods of scanning electron microscopy X-ray electron analysis gravimetry and voltammetry it has been established that at various stages of magnesium corrosion in different electrolytes the growth rates of corrosion films are determined by the kinetics of magnesium oxide formation its hydration and dissolution followed by crystallization in the form of a brucite phase of loose sediments on the surface.

Geodynamic hazards and risk assessment at the Karachaganak oil,gas,and condensate field

The geodynamic hazards and risk assessment at the Karachaganak oil,gas,and condensate field(KOGCF)were explored on the northern board of the Pre-Caspian Basin to predict the consequences of the longterm exploitation of this field.We integrate multiple measurements,including repeated accurate leveling,Global Positioning System(GPS)measurements,and high precision gravimetric and seismological monitoring at the KOGCF.The results of geodynamic monitoring at the KOGCF for the first time made it possible to prove noticeable seismic deformation processes in the sedimentary cover under the influence of hydrocarbon production.The vertical displacements and horizontal movement along faults,changes in local gravity anomalies,and earthquake sources at depths comparable to hydrocarbon production intervals at the KOGCF have been identified.The maximum amplitudes of modern vertical movement of the earth’s surface and the minimum values of the differently oriented horizontal movement were revealed within the projection on the ground surface of the crest of the carbonate massif(Upper Devonian-Lower Permian age).The results suggest the expansion of uneven compression in the crest of the KOGCF while tension processes occur on its periphery.There is a decrease in gravity variations in relation to the slopes of this massif in areas with active hydrocarbon production.An extended zone of high-gradient steps of AGa anomalies,spatially coinciding with the position of fault zones,is mapped along the periphery of the contour of production wells.In the northeastern part of the KOGCF,seismic events were registered practically in the depth intervals of the productive horizons from which hydrocarbons are produced.A spatial relationship between the seismic events and the anomalous deformation activity in the northeast KOGCF has been revealed.Consequently,the field development has provoked both intense deformation of the earth’s surface and weak local seismicity.

Prediction of the flooding area of the northeastern Caspian Sea from satellite images

Studying the dynamic changes in the coastline of the northeastern Caspian Sea is significant since the level of the Caspian is unstable,and the coastline change can cause enormous damage to the ecology,economy,and population of the coastal part of Kazakhstan.In this work,we use remote sensing and Geographic Information System(GIS)technologies to study the changes in the coastline of the northeastern Caspian Sea and predict the extent of flooding with increasing water levels.The proposed methodology for creating dynamic maps can be used to monitor the coastline and forecast the extent of flooding in the area.As a result of this work,the main factors affecting changes in the coastline were identified.After analyzing the water level data from 1988 to 2019,it was revealed that the rise in water level was observed from 1980 to 1995.The maximum sea level rise was recorded at-26.04 m.After that,the sea level began to fall,and between 1996 and 2009,there were no significant changes;the water level fluctuated with an average of-27.18 m.Then,a map of the water level dynamics in the Caspian Sea from 1988 to 2019 was compiled.According to the dynamics map,water level rise and significant coastal retreat were revealed,especially in the northern part of the Caspian Sea and the northern and southern parts of Sora Kaydak.The method for predicting the estimated flooding area was described.As a result,based on a single map,the flooding area of the northeast coast was predicted.A comparative analysis of Landsat and SRTM data is presented.

Arbuscular mycorrhizal fungi ameliorate the chemical properties and enzyme activities of rhizosphere soil in reclaimed mining subsidence in northwestern China

In semi-arid region of northwestern China, underground mining subsidence often results in decreased vegetation coverage, impoverishment of soil fertility and water stress. In addition, the physical-chemical and biological properties of soil also change, resulting in more susceptible to degradation. In particular, subsidence causes disturbance of the symbioses of plant and microbe that can play a beneficial role in the establishment of vegetation communities in degraded ecosystems. The objective of this study was to evaluate the effects of revegetation with exotic arbuscular mycorrhizal fungi(AMF) inoculum on the chemical and biological properties of soil over time in mining subsidence areas. Soils were sampled at a depth up to 30 cm in the adjacent rhizosphere of Amorpha fruticose Linn. from five reclaimed vegetation communities in northwestern China. In August 2015, a field trial was set up with five historical revegetation experiments established in 2008(7-year), 2011(4-year), 2012(3-year), 2013(2-year) and 2014(1-year), respectively. Each reclamation experiment included two treatments, i.e., revegetation with exotic AMF inoculum(AMF) and non-AMF inoculum(the control). Root mycorrhizal colonization, glomalin-related soil protein(GRSP), soil organic carbon(SOC), soil nutrients, and enzyme activities were also assessed. The results showed that mycorrhizal colonization of inoculated plants increased by 33.3%–163.0% compared to that of non-inoculated plants(P<0.05). Revegetation with exotic AMF inoculum also significantly improved total GRSR(T-GRSP) and easily extracted GRSP(EE-GRSP) concentrations compared to control, besides the T-GRSP in 1-year experiment and the EE-GRSP in 2-year experiment. A significant increase in SOC content was only observed in 7-year AMF reclaimed soils compared to non-AMF reclaimed soils. Soil total N(TN), Olsen phosphorus(P) and available potassium(K) were significantly higher in inoculated soil after 1–7 years of reclamation(except for individual cases), and increased with reclamation time(besides soil Olsen P). The exotic AMF inoculum markedly increased the average soil invertase, catalase, urease and alkaline phosphatase by 23.8%, 21.3%, 18.8% and 8.6%, respectively(P<0.01), compared with the control. Root mycorrhizal colonization was positively correlated with soil parameters(SOC, TN and soil available K) and soil enzyme activities(soil invertase, catalase, urease and alkaline phosphatase) in both AMF and non-AMF reclaimed soils(P<0.05), excluding availableK in non-AMF reclaimed soils. T-GRSP(P<0.01) and EE-GRSP(P<0.05) were significantly correlated with the majority of edaphic factors, except for soil Olsen P. The positive correlation between root mycorrhizal colonization and available K was observed in AMF reclaimed soils, indicating that the AMF reclaimed soil with a high root mycorrhizal colonization could potentially accumulate available K in soils. Our findings concluded that revegetation with exotic AMF inoculum influenced soil nutrient availability and enzyme activities in the semi-arid ecosystem, suggesting that inoculating AMF can be an effective method to improve soil fertility and support restoration of vegetation communities under poor conditions like soil nutrient deficiency and drought.

Subsidence control method by inversely-inclined slicing and upward mining for ultra-thick steep seams

Ultra-thick steep coal seam mining will inevitably lead to the increase of greater and violent ground subsidence and deformation.A subsidence control method by inversely-inclined slicing and upward mining is proposed in this paper.By this method,the sequence of collapse of overlying strata and the direction of propagation of strata movement are changed,the extent of roof-side deformation thereby is lessened,and boundary angle of roof-side subsidence is reduced by 5°-10°.The mechanism of this mining method for control of strata movement has been evidenced by numerical simulation and experiments with similarity materials.A subsidence prediction model based on the variation of mining influence propagation angle can be used to evaluate the surface movement and deformation of the mining method.The application of the method in No.3 Mine in Yaojie mining area has yielded the expected result.

Long-term variations in runoff of the Syr Darya River Basin under climate change and human activities

In this study,we analyzed the hydrological and meteorological data from the Syr Darya River Basin during the period of 1930–2015 to investigate variations in river runoff and the impacts of climate change and human activities on river runoff.The Syr Darya River,which is supplied by snow and glacier meltwater upstream,is an important freshwater source for Central Asia,as nearly half of the population is concentrated in this area.River runoff in this arid region is sensitive to climate change and human activities.Therefore,estimation of the climatic and hydrological changes and the quantification of the impacts of climate change and human activities on river runoff are of great concern and important for regional water resources management.The long-term trends of hydrological time series from the selected 11 hydrological stations in the Syr Darya River Basin were examined by non-parametric methods,including the Pettitt change point test and Mann-Kendall trend tests.It was found that 8 out of 11 hydrological stations showed significant downward trends in river runof f.Change of river runoff variations occurred in the year around 1960.Moreover,during the study period(1930–2015),annual mean temperature,annual precipitation,and annual potential evapotranspiration in the river basin increased substantially.We employed hydrological sensitivity method to evaluate the impacts of climate change and human activities on river runoff based on precipitation and potential evapotranspiration.It was estimated that human activities accounted for over 82.6%–98.7%of the reduction in river runoff,mainly owing to water withdrawal for irrigation purpose.The observed variations in river runoff can subsequently lead to adverse ecological consequences from an ecological and regional water resources management perspective.

Comprehensive DDoS Attack Classification Using Machine LearningAlgorithms

The fast development of Internet technologies ignited the growthof techniques for information security that protect data, networks, systems,and applications from various threats. There are many types of threats. Thededicated denial of service attack (DDoS) is one of the most serious andwidespread attacks on Internet resources. This attack is intended to paralyzethe victim’s system and cause the service to fail. This work is devoted tothe classification of DDoS attacks in the special network environment calledSoftware-Defined Networking (SDN) using machine learning algorithms. Theanalyzed dataset included instances of two classes: benign and malicious.As the dataset contained twenty-two features, the feature selection techniques were required for dimensionality reduction. In these experiments, theInformation gain, the Chi-square, and the F-test were applied to decreasethe number of features to ten. The classes were also not completely balanced, so undersampling, oversampling, and synthetic minority oversampling(SMOTE) techniques were used to balance classes equally. The previousresearch works observed the classification of DDoS attacks applying variousfeature selection techniques and one or more machine learning algorithms.Still, they did not pay much attention to classifying the combinations offeature selection and balancing methods with different machine learningalgorithms. This work is devoted to the classification of datasets with eightmachine learning algorithms: naïve Bayes, logistic regression, support vectormachine, k-nearest neighbors, decision tree, random forest, XGBoost, andCatBoost. In the experimental results, the Information gain and F-test featureselection methods achieved better performance with all eight ML algorithmsthan with the Chi-square technique. Furthermore, the accuracy values of theoversampled and SMOTE datasets were higher than that of the undersampledand imbalanced datasets. Among machine learning algorithms, the accuracyof support vector machine, logistic regression, and naïve Bayes fluctuatesbetween 0.59 and 0.75, while decision tree, random forest, XGBoost, and CatBoost allowed achieving values around 0.99 and 1.00 with all featureselection and class balancing techniques among all the algorithms.

Analysis of the displacements of pipeline overpasses based on geodetic monitoring results

There are many approaches to address geospatial monitoring of pipeline overpasses,among which the most widespread methods are terrestrial laser scanning and total station measurements.However,there is a problem in comparing the geospatial monitoring data collected by different methods in different epochs.The main task of this work is to find the correspondence between points in different epochs.The total station measurements are carried out in specific discrete points of the pipeline overpass.In contrast,terrestrial laser scanning allows the collection of the whole data set without fixing specific point co-ordinates.In order to compare different data in different epochs,it is necessary to select a relevant presentation of the monitoring results(reference model)and specify appropriate criteria for quality inspection.In general,a pipeline can be presented as a spatial curve.In this study,two types of reference models are considered:cubic splines and Bezier curves.These models are examined for the monitoring of two gas pipeline overpasses.The first measurement epoch is accomplished by the terrestrial laser scanning,and the second measurement epoch is completed by the total station.The reference models are simulated by Matlab coding.The preliminary accuracy of ground laser scanning and total station mea-surement is selected as the criterion of quality inspection.The simulation and comparison results provide the evidence that the correct selection of reference model is a crucial component of successful geospatial monitoring.The results show that the Hermite splines are effective in the comparison of different data sets.These splines present the interpolation accuracy compatible with measurement accuracy,i.e.,15-20 mm for spatial displacement determination.

Employment of mud-pulse generator for improvement of efficiency of a wellbore producing in complex mining and geological conditions

In this study,the employment of mud-pulse generators to improve the efficiency of wellbores under complex mining and geological conditions is examined.A systemic analysis is made of the primary theoretical basis of the study.The benefits of a mud-pulse generator(a high-impulse hydraulic hammer)for wellbore production are stated based on the presented theoretical basis.The results not only show the benefits of mud-pulse generator employment but also provide an analysis of methods that can be used to improve the high-impulse hydraulic hammer efficiency.The acquired results have a substantial practical value not only for specialists,who research,develop,and manage wellbore operations,but also for engineers,who improve the process and modernize existing wellbores,and other experts in the field of wellbore production.

Hybrid surfactant-nanoparticles assisted CO_(2) foam flooding for improved foam stability:A review of principles and applications

Miscible carbon dioxide(CO_(2))flooding is a well-established and promising enhanced oil recovery(EOR)technique whereby residual oil is recovered by mixing with injected CO_(2)gas.However,CO_(2),being very light and less viscous than reservoir crude oil,results in inefficient sweep efficiency.Extensive research is ongoing to improve CO_(2)mobility control such as the development and generation of CO_(2)/water foams.The long-term stability of foam during the period of flooding is a known issue and must be considered during the design stage of any CO_(2)foam flooding project.The foam stability can be improved by adding surfactants as stabilizers,but surfactants generated foams have generally a shorter life because of an unstable interface.Furthermore,surfactants are prone to higher retention and chemical degradation in the porous media,particularly under harsh reservoir conditions.Research has shown that nanoparticles(NPs)can act as an excellent stabilizing agent for CO_(2)/water foams owing to their surface chemistry and high adsorption energy.The foams generated using NPs are more stable and provide better mobility control compared to surfactant-stabilized foams.One limitation of using NPs as foam stabilizers is their colloidal stability which limits the use of low-cost NPs.Combining surfactants and NPs for CO_(2)foam stabilization is a novel approach and has gained interest among researchers in recent years.Surfactants improve the dispersion of NPs in the aqueous phase and minimize particle aggregation.NPs on the other hand create a stable barrier at the CO_(2)/water interface with the help of surfactants,thus generating highly stable and viscous foams.This paper presents a comprehensive review of the basic principles and applications of stabilized CO_(2)foams.A brief overview of CO_(2)foam flooding is discussed first,followed by a review of standalone surfactant-stabilized and NPs-stabilized CO_(2)/water foams.The application of hybrid surfactant-NPs stabilized CO_(2)foams is then presented and areas requiring further investigation are highlighted.This review provides an insight into a novel approach to stabilize CO_(2)/water foams and the effectiveness of the method as proved by various studies.

New measurements and reanalysis of^14N elastic scattering on^10B target

The angular distributions of elastic scattering of^14N ions on^10B targets have been measured at incident beam energies of 21.0 and 24.5 MeV.Angular distributions at higher energies 38–94.0 MeV(previously measured)were also included in the analysis.All data were analyzed within the framework of the optical model and the distorted waves Born approximation method.The observed rise in cross sections at large angles was interpreted as a possible contribution of theα-cluster exchange mechanism.Spectroscopic amplitudes SA2 and SA4 for the configuration^14N→^10B+αwere extracted.Their average values are 0.58±0.10 and 0.81±0.12 for SA2 and SA4,respectively,suggesting that the exchange mechanism is a major component of the elastic scattering for this system.The energy dependence of the depths for the real and imaginary potentials was found.