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 ar...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.展开更多
The excitation temperature T_(ex)for molecular emission and absorption lines is an essential parameter for interpreting the molecular environment.This temperature can be obtained by observing multiple molecular transi...The excitation temperature T_(ex)for molecular emission and absorption lines is an essential parameter for interpreting the molecular environment.This temperature can be obtained by observing multiple molecular transitions or hyperfine structures of a single transition,but it remains unknown for a single transition without hyperfine structure lines.Earlier H_(2)CO absorption experiments for a single transition without hyperfine structures adopted a constant value of T_(ex),which is not correct for molecular regions with active star formation and H II regions.For H_(2)CO,two equations with two unknowns may be used to determine the excitation temperature T_(ex)and the optical depthτ,if other parameters can be determined from measurements.Published observational data of the4.83 GHz(λ=6 cm)H_(2)CO(1_(10)-1_(11))absorption line for three star formation regions,W40,M17 and DR17,have been used to verify this method.The distributions of T_(ex)in these sources are in good agreement with the contours of the H110αemission of the H II regions in M17 and DR17 and with the H_(2)CO(1_(10)-1_(11))absorption in W40.The distributions of T_(ex)in the three sources indicate that there can be significant variation in the excitation temperature across star formation and H II regions and that the use of a fixed(low)value results in misinterpretation.展开更多
Humic acids(HAs)are widely used as filtrate and viscosity reducers in drilling fluids.However,their practical utility is limited due to poor stability in salt resistance and high-temperature resistance.Hightemperature...Humic acids(HAs)are widely used as filtrate and viscosity reducers in drilling fluids.However,their practical utility is limited due to poor stability in salt resistance and high-temperature resistance.Hightemperature coal pitch(CP)is a by-product from coal pyrolysis above 650℃.The substance's molecular structure is characterized by a dense arrangement of aromatic hydrocarbon and alkyl substituents.This unique structure gives it unique chemical properties and excellent drilling performance,surpassing traditional humic acids in drilling operations.Potassium humate is prepared from CP(CP-HA-K)by thermal catalysis.A new type of high-quality humic acid temperature-resistant viscosity-reducer(Graft CP-HA-K polymer)is synthesized with CP-HA-K,hydrolyzed polyacrylonitrile sodium salt(Na-HPAN),urea,formaldehyde,phenol and acrylamide(AAM)as raw materials.The experimental results demonstrate that the most favorable conditions for the catalytic preparation of CP-HA-K are 1 wt%catalyst dosage,30 wt%KOH dosage,a reaction temperature of 250℃,and a reaction time of 2 h,resulting in a maximum yield of CP-HA-K of 39.58%.The temperature resistance of the Graft CP-HA-K polymer is measured to be 177.39℃,which is 55.39℃ higher than that of commercial HA-K.This is due to the abundant presence of amide,hydroxyl,and amine functional groups in the Graft CP-HA-K polymer,which increase the length of the carbon chains,enhance the electrostatic repulsion on the surface of solid particles.After being aged to 120℃ for a specified duration,the Graft CP-HA-K polymer demonstrates significantly higher viscosity reduction(42.12%)compared to commercial HA-K(C-HA-K).Furthermore,the Graft CP-HA-K polymer can tolerate a high salt concentration of 8000 mg.L-1,measured after the addition of optimum amount of 3 wt%Graft CP-HA-K polymer.The action mechanism of Graft CP-HA-K polymer on high-temperature drilling fluid is that the Graft CP-HA-K polymer can increase the repulsive force between solid particles and disrupt bentonite's reticulation structure.Overall,this research provides novelty insights into the synthesis of artificial humic acid materials and the development of temperature-resistant viscosity reducers,offering a new avenue for the utilization of CP resources.展开更多
The observations of the Aquila Rift cloud complex at 23.708 and 115.271 GHz made using the Nanshan 26 m radio telescope and the 13.7 m millimeter-wavelength telescope are presented.We find that the CO(1-0)gas distribu...The observations of the Aquila Rift cloud complex at 23.708 and 115.271 GHz made using the Nanshan 26 m radio telescope and the 13.7 m millimeter-wavelength telescope are presented.We find that the CO(1-0)gas distribution is similar to the NH_(3)gas distribution in the Aquila Rift cloud complex.In some diffusion regions characterized by CO,we identified several dense clumps based on the distribution of detected ammonia molecular emission.Through the comparison of spectral line parameters for NH_(3),^(13)CO,and C^(18)O,our study reveals that the line center velocities of the NH_(3),^(13)CO,and C^(18)O lines are comparable and positively correlated,indicating that they originate from the same emission region.No significant correlation was identified for other parameters,including integrated intensity,line widths,main beam brightness temperature,as well as the column densities of NH_(3),^(13)CO,and C^(18)O.The absolute difference in line-center velocities between the^(13)CO and NH_(3)lines is less than both the average line width of NH_(3)and that of^(13)CO.This suggests that there are no significant movements of NH_(3)clumps in relation to their envelopes.The velocity deviation is likely due to turbulent activity within the clumps.展开更多
As digital technologies have advanced more rapidly,the number of paper documents recently converted into a digital format has exponentially increased.To respond to the urgent need to categorize the growing number of d...As digital technologies have advanced more rapidly,the number of paper documents recently converted into a digital format has exponentially increased.To respond to the urgent need to categorize the growing number of digitized documents,the classification of digitized documents in real time has been identified as the primary goal of our study.A paper classification is the first stage in automating document control and efficient knowledge discovery with no or little human involvement.Artificial intelligence methods such as Deep Learning are now combined with segmentation to study and interpret those traits,which were not conceivable ten years ago.Deep learning aids in comprehending input patterns so that object classes may be predicted.The segmentation process divides the input image into separate segments for a more thorough image study.This study proposes a deep learning-enabled framework for automated document classification,which can be implemented in higher education.To further this goal,a dataset was developed that includes seven categories:Diplomas,Personal documents,Journal of Accounting of higher education diplomas,Service letters,Orders,Production orders,and Student orders.Subsequently,a deep learning model based on Conv2D layers is proposed for the document classification process.In the final part of this research,the proposed model is evaluated and compared with other machine-learning techniques.The results demonstrate that the proposed deep learning model shows high results in document categorization overtaking the other machine learning models by reaching 94.84%,94.79%,94.62%,94.43%,94.07%in accuracy,precision,recall,F-score,and AUC-ROC,respectively.The achieved results prove that the proposed deep model is acceptable to use in practice as an assistant to an office worker.展开更多
In the process of production or processing of materials by various methods,there is a need for a large volume of water of the required quality.Today in many regions of the world,there is an acute problem of providing ...In the process of production or processing of materials by various methods,there is a need for a large volume of water of the required quality.Today in many regions of the world,there is an acute problem of providing industry with water of a required quality.Its solution is an urgent and difficult task.The water quality of surface water bodies is formed by a combination of a large number of both natural and anthropogenic factors,and is often significantly heterogeneous not only in the water area,but also in depth.As a rule,the water supply of large industrial enterprises is located along the river network.Mergers are the most important nodes of river systems.Understanding the mechanism of transport of pollutants at the confluence of rivers is critical for assessing water quality.In recent years,thanks to the data of satellite images,the interest of researchers in the phenomenon of mixing the waters of merging rivers has increased.The nature of the merger is influenced by the formation of transverse circulation.Within the framework of this work,a study of vorticity,as well as the width of the mixing zone,depending on the distance from the confluence,the speeds of the merging rivers and the angle of confluence was carried out.Since the consumer properties of water are largely determined by its chemical and physical indicators,the intensity of mixing,determined largely by the nature of the secondary circulation,is of fundamental importance for assessing the distribution of hydrochemical indicators of water quality in the mixing zone.These characteristics are important not only for organizing water intake for drinking and technical purposes with the best consumer properties,but also for organizing an effective monitoring system for confluence zones.展开更多
The issues of solvability and construction of a solution of the Fredholm integral equation of the first kind are considered. It is done by immersing the original problem into solving an extremal problem in Hilbert spa...The issues of solvability and construction of a solution of the Fredholm integral equation of the first kind are considered. It is done by immersing the original problem into solving an extremal problem in Hilbert space. Necessary and sufficient conditions for the existence of a solution are obtained. A method of constructing a solution of the Fredholm integral equation of the first kind is developed. A constructive theory of solvability and construction of a solution to a boundary value problem of a linear integrodifferential equation with a distributed delay in control, generated by the Fredholm integral equation of the first kind, has been created.展开更多
This study investigates the community-based ecotourism (CBE) model using a sample of the Aksu-Zhabagly nature reserve (NR). The aim is to propose a suitable CBE model for Aksu-Zhabgly nature-based tourism destinations...This study investigates the community-based ecotourism (CBE) model using a sample of the Aksu-Zhabagly nature reserve (NR). The aim is to propose a suitable CBE model for Aksu-Zhabgly nature-based tourism destinations by employing a combination of field observation, examination, evaluation, and SWOT analysis. The study determines the strategic suggestions for CBE model designing by the results of SWOT analysis. It concludes that convenient transportation and superior location, diversified wild animals and plants, rich in ethnocultural resources, traditional and tranquil life in a typical rural setting, hospitality and positive attitude of locals to tourism and great potential of the region for sustainable development of ecotourism are the strengths. At the same time, the far residential location from the provincial cities, low-quality service, outdated facilities and shortage of skilled employees in tourism management are the main weakness. Another group of constraints to tourism development is lack of tourism marketing and promotion agencies, lack of transparency, poor institution arrangement and corruption, and lack of preferential policies for CBE development. Finally, the paper recommends that economic development, environmental protection, culture and heritage, marketing and image, favorable political environment, and local residents’ empowerment are the main essential to effectively implement the sustainable development of CBE in the Aksu-Zhabagly tourist destination.展开更多
The intention of the current research is to address the conclusion of non-isothermal heterogeneous reaction on the stagnation-point flow of SWCNT-engine oil and MWCNT-engine oil nanofluid over a shrinking/stretching s...The intention of the current research is to address the conclusion of non-isothermal heterogeneous reaction on the stagnation-point flow of SWCNT-engine oil and MWCNT-engine oil nanofluid over a shrinking/stretching sheet.Further,exemplify the aspect of heat and mass transfer the upshot of magnetohydrodynamics(MHD),thermal radiation,and heat generation/absorption coefficient are exemplified.The bvp4 c from Matlab is pledged to acquire the numerical explanation of the problem that contains nonlinear system of ordinary differential equations(ODE).The impacts of miscellaneous important parameters on axial velocity,temperature field,concentration profile,skin friction coefficient,and local Nusselt number,are deliberated through graphical and numerically erected tabulated values.The solid volume fraction diminishes the velocity distribution while enhancing the temperature distribution.Further,the rate of shear stress declines with increasing the magnetic and stretching parameter for both SWCNT and MWCNT.展开更多
This work examines the entropy generation with heat and mass transfer in magnetohydrodynamic(MHD)stagnation point flow across a stretchable surface.The heat transport process is investigated with respect to the viscou...This work examines the entropy generation with heat and mass transfer in magnetohydrodynamic(MHD)stagnation point flow across a stretchable surface.The heat transport process is investigated with respect to the viscous dissipation and thermal radiation,whereas the mass transport is observed under the influence of a chemical reaction.The irreversibe factor is measured through the application of the second law of thermodynamics.The established non-linear partial differential equations(PDEs)have been replaced by acceptable ordinary differential equations(ODEs),which are solved numerically via the bvp4 c method(built-in package in MATLAB).The numerical analysis of the resulting ODEs is carried out on the different flow parameters,and their effects on the rate of heat transport,friction drag,concentration,and the entropy generation are considered.It is determined that the concentration estimation and the Sherwood number reduce and enhance for higher values of the chemical reaction parameter and the Schmidt number,although the rate of heat transport is increased for the Eckert number and heat generation/absorption parameter,respectively.The entropy generation augments with boosting values of the Brinkman number,and decays with escalating values of both the radiation parameter and the Weissenberg number.展开更多
Ancestral return-return by the descendants of migrants to their ancestors＇ origin has been one of the most significant forms of population mobility since 1991 in the Republic of Kazakhstan. The state policy determine...Ancestral return-return by the descendants of migrants to their ancestors＇ origin has been one of the most significant forms of population mobility since 1991 in the Republic of Kazakhstan. The state policy determines the scales of ethnic migration to and within the country. The government adopted a complex program on Kazakh Diaspora repatriation. Under the program, oralmans （ethnic repatriates to the country） are provided with considerable aid program for adaptation to the recipient society. Although the returnees may initially be welcomed back, their homecomings often prove to be ambivalent or negative experiences. Despite their ethnic affinity to the host populace, they are frequently excluded as cultural foreigners and relegated to low-status jobs shunned by the host society＇s populace. Ethnic return migrants and their hosts become frustrated with each other. They find jobs but not expected social welcome. Ethnic return migrant＇s orientations usually are shaped by the terms of the policies that give them the access to the destination country＇s labor markets and citizenship. The report studies the problem of similarity and differences among Ethnic Return Migrants and mother ethnic group. What underlies the misunderstanding between them？ Whether it is a competition for the working places, access to the social benefits or deep cultural differences？ To examine on-the-ground dynamics between natives and ethnic migrants, and in particular their mutual acceptance in a range of contexts, we turn to a qualitative account that draws on observations and interviews, less formal interviews carried out among Mongolian-Kazakh, Chinese-Kazakh and Karakalpak- Kazakh return Migrants in Almaty city and its suburbs during the fieldwork. Characteristics that differentiate returned Diaspora individuals from Kazakhstani Kazakhs are rooted not in ethnic sphere, but in the cultural context of the country they come from. This paper reveals how the socio-cultural characteristics and national origins of the migrants influence their levels of marginalization in their ethnic homelands, forcing many of them to redefine the meanings of home and homeland.展开更多
This paper focuses on the language policy of the Republic of Kazakhstan. It is intended to invite the readers for the broadening of the debate on the issues raised. The 20th century, for Kazakhs, became a century of t...This paper focuses on the language policy of the Republic of Kazakhstan. It is intended to invite the readers for the broadening of the debate on the issues raised. The 20th century, for Kazakhs, became a century of tragic events which transformed them into the minority on their own native land. In spite of many collisions in history Kazakhs have not lost their language, the main wealth. At the beginning of the 21st century, Kazakhstan has tackled a lot of problems, connected with national and ethnic issues, social structure, and foreign and home policy. The influence of globalization is felt in every sphere of life in Kazakhstan. Serious ethno-demographic changes have occurred after gaining independence. Kazakhstan from the state with two dominating Kazakh and Russian diasporas has turned to the state with dominating one, the Kazakh ethnos. State language of the Republic of Kazakhstan now is Kazakh due to implementation of language policy展开更多
Our national center of gastroenterology provides highly specialized care, including chronic pancreatitis. Another area of our activities is educational programs, including postgraduate and fellows’ courses. Thereby, ...Our national center of gastroenterology provides highly specialized care, including chronic pancreatitis. Another area of our activities is educational programs, including postgraduate and fellows’ courses. Thereby, we have noted significant gaps in the knowledge of the specialists that involved in the chronic pancreatitis management. The most critical downsides are related to insufficient attention to etiology and risk factors, using outdated classifications, the lack of knowledge in arsenal of diagnostic techniques, polypharmacy or application of low level of evidence treatment methods. Finally, we have made amendments in the National Clinical Protocol in Chronic Pancreatitis [<a href="#ref1">1</a>], updated the State Educational Standard for residents of the gastroenterological profile [<a href="#ref2">2</a>]. The aim of the study was the analysis of the basic knowledge among different specialists in the management of chronic pancreatitis (CP) around the country. This qualitative study consists of two parts, including focus group interviews followed by interviews with the specialists across the country, which was conducted during the period 2015-2018. In this paper, we present results of diagnostic approaches at the different levels of medical care. The general practitioners have noted the absence of modern methods of laboratory and visual diagnostics in their routine practice, therefore explaining the plenty of the complicated forms. Another issue is the low specialist’s adherence to clinical guidelines, poor knowledge of the risk factors and overestimation of the clinical presentation value except malnutrition symptoms. On the other hand, surgeons and other specialists are not ready to implement modern diagnostic tools and methods in their practice. Obviously, in accordance with the results of our study, our educational center should conduct a number of training activities, as well as develop new algorithms for medical care specialists.展开更多
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 morpholog...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.展开更多
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 develop...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.展开更多
Automatic identification of cyberbullying is a problem that is gaining traction,especially in the Machine Learning areas.Not only is it complicated,but it has also become a pressing necessity,considering how social me...Automatic identification of cyberbullying is a problem that is gaining traction,especially in the Machine Learning areas.Not only is it complicated,but it has also become a pressing necessity,considering how social media has become an integral part of adolescents’lives and how serious the impacts of cyberbullying and online harassment can be,particularly among teenagers.This paper contains a systematic literature review of modern strategies,machine learning methods,and technical means for detecting cyberbullying and the aggressive command of an individual in the information space of the Internet.We undertake an in-depth review of 13 papers from four scientific databases.The article provides an overview of scientific literature to analyze the problem of cyberbullying detection from the point of view of machine learning and natural language processing.In this review,we consider a cyberbullying detection framework on social media platforms,which includes data collection,data processing,feature selection,feature extraction,and the application ofmachine learning to classify whether texts contain cyberbullying or not.This article seeks to guide future research on this topic toward a more consistent perspective with the phenomenon’s description and depiction,allowing future solutions to be more practical and effective.展开更多
In the field of stroke imaging, deep learning (DL) has enormousuntapped potential.When clinically significant symptoms of a cerebral strokeare detected, it is crucial to make an urgent diagnosis using available imagin...In the field of stroke imaging, deep learning (DL) has enormousuntapped potential.When clinically significant symptoms of a cerebral strokeare detected, it is crucial to make an urgent diagnosis using available imagingtechniques such as computed tomography (CT) scans. The purpose of thiswork is to classify brain CT images as normal, surviving ischemia or cerebralhemorrhage based on the convolutional neural network (CNN) model. In thisstudy, we propose a computer-aided diagnostic system (CAD) for categorizingcerebral strokes using computed tomography images. Horizontal flip datamagnification techniques were used to obtain more accurate categorization.Image Data Generator to magnify the image in real time and apply anyrandom transformations to each training image. An early stopping method toavoid overtraining. As a result, the proposed methods improved several estimationparameters such as accuracy and recall, compared to other machinelearning methods. A python web application was created to demonstrate theresults of CNN model classification using cloud development techniques. Inour case, the model correctly identified the drawing class as normal with 79%accuracy. Based on the collected results, it was determined that the presentedautomated diagnostic system could be used to assist medical professionals indetecting and classifying brain strokes.展开更多
In the face of escalating intricacy and heterogeneity within Internet of Things(IoT)network landscapes,the imperative for adept intrusion detection techniques has never been more pressing.This paper delineates a pione...In the face of escalating intricacy and heterogeneity within Internet of Things(IoT)network landscapes,the imperative for adept intrusion detection techniques has never been more pressing.This paper delineates a pioneering deep learning-based intrusion detection model:the One Dimensional Convolutional Neural Networks(1D-CNN)and Bidirectional Long Short-Term Memory(BiLSTM)Network(Conv-BiLSTM)augmented with an Attention Mechanism.The primary objective of this research is to engineer a sophisticated model proficient in discerning the nuanced patterns and temporal dependencies quintessential to IoT network traffic data,thereby facilitating the precise categorization of a myriad of intrusion types.Methodology:The proposed model amal-gamates the potent attributes of 1D convolutional neural networks,bidirectional long short-term memory layers,and attention mechanisms to bolster the efficacy and resilience of IoT intrusion detection systems.A rigorous assessment was executed employing an expansive dataset that mirrors the convolutions and multifariousness characteristic of genuine IoT network settings,encompassing various network traffic paradigms and intrusion archetypes.Findings:The empirical evidence underscores the paramountcy of the One Dimensional Conv-BiLSTM Network with Attention Mechanism,which exhibits a marked superiority over conventional machine learning modalities.Notably,the model registers an exemplary AUC-ROC metric of 0.995,underscoring its precision in typifying a spectrum of intrusions within IoT infrastructures.Conclusion:The presented One Dimensional Conv-BiLSTM Network armed with an Attention Mechanism stands out as a robust and trustworthy vanguard against IoT network breaches.Its prowess in discerning intricate traffic patterns and inherent temporal dependencies transcends that of traditional machine learning frameworks.The commendable diagnostic accuracy manifested in this study advocates for its tangible deployment.This investigation indubitably advances the cybersecurity domain,amplifying the fortification and robustness of IoT frameworks and heralding a new era of bolstered security across pivotal sectors such as residential,medical,and transit systems.展开更多
Communication in society had developed within cultural and geographical boundaries prior to the invention of digital technology.The latest advancements in communication technology have significantly surpassed the conv...Communication in society had developed within cultural and geographical boundaries prior to the invention of digital technology.The latest advancements in communication technology have significantly surpassed the conventional constraints for communication with regards to time and location.These new platforms have ushered in a new age of user-generated content,online chats,social network and comprehensive data on individual behavior.However,the abuse of communication software such as social media websites,online communities,and chats has resulted in a new kind of online hostility and aggressive actions.Due to widespread use of the social networking platforms and technological gadgets,conventional bullying has migrated from physical form to online,where it is termed as Cyberbullying.However,recently the digital technologies as machine learning and deep learning have been showing their efficiency in identifying linguistic patterns used by cyberbullies and cyberbullying detection problem.In this research paper,we aimed to evaluate shallow machine learning and deep learning methods in cyberbullying detection problem.We deployed three deep and six shallow learning algorithms for cyberbullying detection problems.The results show that bidirectional long-short-term memory is the most efficient method for cyberbullying detection,in terms of accuracy and recall.展开更多
The purpose of the paper is to substantiate the possibility of constructing the physics of the evolution of matter based on the fundamental laws of physics. It is shown how this can be done within the framework of an ...The purpose of the paper is to substantiate the possibility of constructing the physics of the evolution of matter based on the fundamental laws of physics. It is shown how this can be done within the framework of an extension of classical mechanics. Its expansion is based on the motion equation of a structured body. The fundamental difference between this equation and Newton’s motion equation is that instead of a model of a body in the form of a material point, it uses a structured body in the form of a system of potentially interacting material points. To obtain this equation, the principle of symmetry dualism, new for classical mechanics, was used. According to this principle, the dynamics of a body are determined not only by the symmetries of space, as in the case of a structureless body, but also by its symmetries. Thanks to this derivation of the equation, it takes into account the fact that the work of external forces, in addition to changing the body’s motion energy, also changes its internal energy. This change occurs due to the body’s motion energy when it moves in a non-uniform field of forces. It is shown why the motion equation of a structured body is irreversible. Its irreversibility made it possible to introduce the concept of D-entropy into extended classical mechanics. It is defined as the value of the relative increase in the body’s internal energy due to the motion energy. The relationship between the values of motion energy and D-entropy in the process of matter evolution is considered. It is shown how this connection is realized during the transition from one hierarchical level of matter to the next level. As a result, it was possible to prove that the evolution of the hierarchical structure of matter is characterized by the relationship between D-entropy and the motion energy of elements at each of its hierarchical levels.展开更多
基金supported by the research project—Application of Machine Learning Methods for Early Diagnosis of Pathologies of the Cardiovascular System funded by the Ministry of Science and Higher Education of the Republic of Kazakhstan.Grant No.IRN AP13068289.
文摘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.
基金funded by the National Key R&D Program of China under grant No.2022YFA1603103partially funded by the Regional Collaborative Innovation Project of Xinjiang Uyghur Autonomous Region under grant No.2022E01050+7 种基金the Tianshan Talent Program of Xinjiang Uygur Autonomous Region under grant No.2022TSYCLJ0005the Natural Science Foundation of Xinjiang Uygur Autonomous Region under grant No.2022D01E06the Chinese Academy of Sciences(CAS)Light of West China Program under grants Nos.xbzg-zdsys-202212,2020-XBQNXZ-017,and 2021-XBQNXZ-028the National Natural Science Foundation of China(NSFC,grant Nos.12173075,11973076,and 12103082)the Xinjiang Key Laboratory of Radio Astrophysics under grant No.2022D04033the Youth Innovation Promotion Association CASfunded by the Chinese Academy of Sciences Presidents International Fellowship Initiative under grants Nos.2022VMA0019 and 2023VMA0030funded by the Science Committee of the Ministry of Science and Higher Education of the Republic of Kazakhstan under grant No.AP13067768。
文摘The excitation temperature T_(ex)for molecular emission and absorption lines is an essential parameter for interpreting the molecular environment.This temperature can be obtained by observing multiple molecular transitions or hyperfine structures of a single transition,but it remains unknown for a single transition without hyperfine structure lines.Earlier H_(2)CO absorption experiments for a single transition without hyperfine structures adopted a constant value of T_(ex),which is not correct for molecular regions with active star formation and H II regions.For H_(2)CO,two equations with two unknowns may be used to determine the excitation temperature T_(ex)and the optical depthτ,if other parameters can be determined from measurements.Published observational data of the4.83 GHz(λ=6 cm)H_(2)CO(1_(10)-1_(11))absorption line for three star formation regions,W40,M17 and DR17,have been used to verify this method.The distributions of T_(ex)in these sources are in good agreement with the contours of the H110αemission of the H II regions in M17 and DR17 and with the H_(2)CO(1_(10)-1_(11))absorption in W40.The distributions of T_(ex)in the three sources indicate that there can be significant variation in the excitation temperature across star formation and H II regions and that the use of a fixed(low)value results in misinterpretation.
基金supported by the Key R&D projects in Xinjiang (2022B01042)Research and Innovation Team Cultivation Plan of Yili Normal University (#CXZK2021002)。
文摘Humic acids(HAs)are widely used as filtrate and viscosity reducers in drilling fluids.However,their practical utility is limited due to poor stability in salt resistance and high-temperature resistance.Hightemperature coal pitch(CP)is a by-product from coal pyrolysis above 650℃.The substance's molecular structure is characterized by a dense arrangement of aromatic hydrocarbon and alkyl substituents.This unique structure gives it unique chemical properties and excellent drilling performance,surpassing traditional humic acids in drilling operations.Potassium humate is prepared from CP(CP-HA-K)by thermal catalysis.A new type of high-quality humic acid temperature-resistant viscosity-reducer(Graft CP-HA-K polymer)is synthesized with CP-HA-K,hydrolyzed polyacrylonitrile sodium salt(Na-HPAN),urea,formaldehyde,phenol and acrylamide(AAM)as raw materials.The experimental results demonstrate that the most favorable conditions for the catalytic preparation of CP-HA-K are 1 wt%catalyst dosage,30 wt%KOH dosage,a reaction temperature of 250℃,and a reaction time of 2 h,resulting in a maximum yield of CP-HA-K of 39.58%.The temperature resistance of the Graft CP-HA-K polymer is measured to be 177.39℃,which is 55.39℃ higher than that of commercial HA-K.This is due to the abundant presence of amide,hydroxyl,and amine functional groups in the Graft CP-HA-K polymer,which increase the length of the carbon chains,enhance the electrostatic repulsion on the surface of solid particles.After being aged to 120℃ for a specified duration,the Graft CP-HA-K polymer demonstrates significantly higher viscosity reduction(42.12%)compared to commercial HA-K(C-HA-K).Furthermore,the Graft CP-HA-K polymer can tolerate a high salt concentration of 8000 mg.L-1,measured after the addition of optimum amount of 3 wt%Graft CP-HA-K polymer.The action mechanism of Graft CP-HA-K polymer on high-temperature drilling fluid is that the Graft CP-HA-K polymer can increase the repulsive force between solid particles and disrupt bentonite's reticulation structure.Overall,this research provides novelty insights into the synthesis of artificial humic acid materials and the development of temperature-resistant viscosity reducers,offering a new avenue for the utilization of CP resources.
基金supported by the National Key R&D Programs of China(Nos.2023YFA1608002,and 2022YFA1603103)the regional Collaborative Innovation Project of Xinjiang Uyghur Autonomous Region(No.2022E01050)+6 种基金the Tianshan Talent Program of Xinjiang Uyghur Autonomous Region(No.2022TSYCLJ0005)the Tianchi Talent Project of Xinjiang Uyghur Autonomous Region,the Natural Science Foundation of Xinjiang Uyghur Autonomous Region(No.2022D01E06)the Chinese Academy of Sciences(CAS)“Light of West China”Program(Nos.xbzgzdsys-202212,2020-XBQNXZ-017,and 2021-XBQNXZ-028)the National Natural Science Foundation of China(Nos.12173075,11973076,and 12103082)the Xinjiang Key Laboratory of Radio Astrophysics(No.2022D04033)the Chinese Academy of Sciences President's International Fellowship Initiative(Nos.2022VMA0019,and 2023VMA0030)the Science Committee of the Ministry of Science and Higher Education of the Republic of Kazakhstan(No.AP13067768)。
文摘The observations of the Aquila Rift cloud complex at 23.708 and 115.271 GHz made using the Nanshan 26 m radio telescope and the 13.7 m millimeter-wavelength telescope are presented.We find that the CO(1-0)gas distribution is similar to the NH_(3)gas distribution in the Aquila Rift cloud complex.In some diffusion regions characterized by CO,we identified several dense clumps based on the distribution of detected ammonia molecular emission.Through the comparison of spectral line parameters for NH_(3),^(13)CO,and C^(18)O,our study reveals that the line center velocities of the NH_(3),^(13)CO,and C^(18)O lines are comparable and positively correlated,indicating that they originate from the same emission region.No significant correlation was identified for other parameters,including integrated intensity,line widths,main beam brightness temperature,as well as the column densities of NH_(3),^(13)CO,and C^(18)O.The absolute difference in line-center velocities between the^(13)CO and NH_(3)lines is less than both the average line width of NH_(3)and that of^(13)CO.This suggests that there are no significant movements of NH_(3)clumps in relation to their envelopes.The velocity deviation is likely due to turbulent activity within the clumps.
文摘As digital technologies have advanced more rapidly,the number of paper documents recently converted into a digital format has exponentially increased.To respond to the urgent need to categorize the growing number of digitized documents,the classification of digitized documents in real time has been identified as the primary goal of our study.A paper classification is the first stage in automating document control and efficient knowledge discovery with no or little human involvement.Artificial intelligence methods such as Deep Learning are now combined with segmentation to study and interpret those traits,which were not conceivable ten years ago.Deep learning aids in comprehending input patterns so that object classes may be predicted.The segmentation process divides the input image into separate segments for a more thorough image study.This study proposes a deep learning-enabled framework for automated document classification,which can be implemented in higher education.To further this goal,a dataset was developed that includes seven categories:Diplomas,Personal documents,Journal of Accounting of higher education diplomas,Service letters,Orders,Production orders,and Student orders.Subsequently,a deep learning model based on Conv2D layers is proposed for the document classification process.In the final part of this research,the proposed model is evaluated and compared with other machine-learning techniques.The results demonstrate that the proposed deep learning model shows high results in document categorization overtaking the other machine learning models by reaching 94.84%,94.79%,94.62%,94.43%,94.07%in accuracy,precision,recall,F-score,and AUC-ROC,respectively.The achieved results prove that the proposed deep model is acceptable to use in practice as an assistant to an office worker.
基金financial support from the Government of the Perm Territory within the Framework of Scientific Project No.S-26/828the Ministry of Science and High Education of Russia(Theme No.121031700169-1).
文摘In the process of production or processing of materials by various methods,there is a need for a large volume of water of the required quality.Today in many regions of the world,there is an acute problem of providing industry with water of a required quality.Its solution is an urgent and difficult task.The water quality of surface water bodies is formed by a combination of a large number of both natural and anthropogenic factors,and is often significantly heterogeneous not only in the water area,but also in depth.As a rule,the water supply of large industrial enterprises is located along the river network.Mergers are the most important nodes of river systems.Understanding the mechanism of transport of pollutants at the confluence of rivers is critical for assessing water quality.In recent years,thanks to the data of satellite images,the interest of researchers in the phenomenon of mixing the waters of merging rivers has increased.The nature of the merger is influenced by the formation of transverse circulation.Within the framework of this work,a study of vorticity,as well as the width of the mixing zone,depending on the distance from the confluence,the speeds of the merging rivers and the angle of confluence was carried out.Since the consumer properties of water are largely determined by its chemical and physical indicators,the intensity of mixing,determined largely by the nature of the secondary circulation,is of fundamental importance for assessing the distribution of hydrochemical indicators of water quality in the mixing zone.These characteristics are important not only for organizing water intake for drinking and technical purposes with the best consumer properties,but also for organizing an effective monitoring system for confluence zones.
文摘The issues of solvability and construction of a solution of the Fredholm integral equation of the first kind are considered. It is done by immersing the original problem into solving an extremal problem in Hilbert space. Necessary and sufficient conditions for the existence of a solution are obtained. A method of constructing a solution of the Fredholm integral equation of the first kind is developed. A constructive theory of solvability and construction of a solution to a boundary value problem of a linear integrodifferential equation with a distributed delay in control, generated by the Fredholm integral equation of the first kind, has been created.
文摘This study investigates the community-based ecotourism (CBE) model using a sample of the Aksu-Zhabagly nature reserve (NR). The aim is to propose a suitable CBE model for Aksu-Zhabgly nature-based tourism destinations by employing a combination of field observation, examination, evaluation, and SWOT analysis. The study determines the strategic suggestions for CBE model designing by the results of SWOT analysis. It concludes that convenient transportation and superior location, diversified wild animals and plants, rich in ethnocultural resources, traditional and tranquil life in a typical rural setting, hospitality and positive attitude of locals to tourism and great potential of the region for sustainable development of ecotourism are the strengths. At the same time, the far residential location from the provincial cities, low-quality service, outdated facilities and shortage of skilled employees in tourism management are the main weakness. Another group of constraints to tourism development is lack of tourism marketing and promotion agencies, lack of transparency, poor institution arrangement and corruption, and lack of preferential policies for CBE development. Finally, the paper recommends that economic development, environmental protection, culture and heritage, marketing and image, favorable political environment, and local residents’ empowerment are the main essential to effectively implement the sustainable development of CBE in the Aksu-Zhabagly tourist destination.
文摘The intention of the current research is to address the conclusion of non-isothermal heterogeneous reaction on the stagnation-point flow of SWCNT-engine oil and MWCNT-engine oil nanofluid over a shrinking/stretching sheet.Further,exemplify the aspect of heat and mass transfer the upshot of magnetohydrodynamics(MHD),thermal radiation,and heat generation/absorption coefficient are exemplified.The bvp4 c from Matlab is pledged to acquire the numerical explanation of the problem that contains nonlinear system of ordinary differential equations(ODE).The impacts of miscellaneous important parameters on axial velocity,temperature field,concentration profile,skin friction coefficient,and local Nusselt number,are deliberated through graphical and numerically erected tabulated values.The solid volume fraction diminishes the velocity distribution while enhancing the temperature distribution.Further,the rate of shear stress declines with increasing the magnetic and stretching parameter for both SWCNT and MWCNT.
文摘This work examines the entropy generation with heat and mass transfer in magnetohydrodynamic(MHD)stagnation point flow across a stretchable surface.The heat transport process is investigated with respect to the viscous dissipation and thermal radiation,whereas the mass transport is observed under the influence of a chemical reaction.The irreversibe factor is measured through the application of the second law of thermodynamics.The established non-linear partial differential equations(PDEs)have been replaced by acceptable ordinary differential equations(ODEs),which are solved numerically via the bvp4 c method(built-in package in MATLAB).The numerical analysis of the resulting ODEs is carried out on the different flow parameters,and their effects on the rate of heat transport,friction drag,concentration,and the entropy generation are considered.It is determined that the concentration estimation and the Sherwood number reduce and enhance for higher values of the chemical reaction parameter and the Schmidt number,although the rate of heat transport is increased for the Eckert number and heat generation/absorption parameter,respectively.The entropy generation augments with boosting values of the Brinkman number,and decays with escalating values of both the radiation parameter and the Weissenberg number.
文摘Ancestral return-return by the descendants of migrants to their ancestors＇ origin has been one of the most significant forms of population mobility since 1991 in the Republic of Kazakhstan. The state policy determines the scales of ethnic migration to and within the country. The government adopted a complex program on Kazakh Diaspora repatriation. Under the program, oralmans （ethnic repatriates to the country） are provided with considerable aid program for adaptation to the recipient society. Although the returnees may initially be welcomed back, their homecomings often prove to be ambivalent or negative experiences. Despite their ethnic affinity to the host populace, they are frequently excluded as cultural foreigners and relegated to low-status jobs shunned by the host society＇s populace. Ethnic return migrants and their hosts become frustrated with each other. They find jobs but not expected social welcome. Ethnic return migrant＇s orientations usually are shaped by the terms of the policies that give them the access to the destination country＇s labor markets and citizenship. The report studies the problem of similarity and differences among Ethnic Return Migrants and mother ethnic group. What underlies the misunderstanding between them？ Whether it is a competition for the working places, access to the social benefits or deep cultural differences？ To examine on-the-ground dynamics between natives and ethnic migrants, and in particular their mutual acceptance in a range of contexts, we turn to a qualitative account that draws on observations and interviews, less formal interviews carried out among Mongolian-Kazakh, Chinese-Kazakh and Karakalpak- Kazakh return Migrants in Almaty city and its suburbs during the fieldwork. Characteristics that differentiate returned Diaspora individuals from Kazakhstani Kazakhs are rooted not in ethnic sphere, but in the cultural context of the country they come from. This paper reveals how the socio-cultural characteristics and national origins of the migrants influence their levels of marginalization in their ethnic homelands, forcing many of them to redefine the meanings of home and homeland.
文摘This paper focuses on the language policy of the Republic of Kazakhstan. It is intended to invite the readers for the broadening of the debate on the issues raised. The 20th century, for Kazakhs, became a century of tragic events which transformed them into the minority on their own native land. In spite of many collisions in history Kazakhs have not lost their language, the main wealth. At the beginning of the 21st century, Kazakhstan has tackled a lot of problems, connected with national and ethnic issues, social structure, and foreign and home policy. The influence of globalization is felt in every sphere of life in Kazakhstan. Serious ethno-demographic changes have occurred after gaining independence. Kazakhstan from the state with two dominating Kazakh and Russian diasporas has turned to the state with dominating one, the Kazakh ethnos. State language of the Republic of Kazakhstan now is Kazakh due to implementation of language policy
文摘Our national center of gastroenterology provides highly specialized care, including chronic pancreatitis. Another area of our activities is educational programs, including postgraduate and fellows’ courses. Thereby, we have noted significant gaps in the knowledge of the specialists that involved in the chronic pancreatitis management. The most critical downsides are related to insufficient attention to etiology and risk factors, using outdated classifications, the lack of knowledge in arsenal of diagnostic techniques, polypharmacy or application of low level of evidence treatment methods. Finally, we have made amendments in the National Clinical Protocol in Chronic Pancreatitis [<a href="#ref1">1</a>], updated the State Educational Standard for residents of the gastroenterological profile [<a href="#ref2">2</a>]. The aim of the study was the analysis of the basic knowledge among different specialists in the management of chronic pancreatitis (CP) around the country. This qualitative study consists of two parts, including focus group interviews followed by interviews with the specialists across the country, which was conducted during the period 2015-2018. In this paper, we present results of diagnostic approaches at the different levels of medical care. The general practitioners have noted the absence of modern methods of laboratory and visual diagnostics in their routine practice, therefore explaining the plenty of the complicated forms. Another issue is the low specialist’s adherence to clinical guidelines, poor knowledge of the risk factors and overestimation of the clinical presentation value except malnutrition symptoms. On the other hand, surgeons and other specialists are not ready to implement modern diagnostic tools and methods in their practice. Obviously, in accordance with the results of our study, our educational center should conduct a number of training activities, as well as develop new algorithms for medical care specialists.
文摘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.
基金supported by the research project—Application of Machine Learning Methods for Early Diagnosis of Pathologies of the Cardiovascular System funded by the Ministry of Science and Higher Education of the Republic of Kazakhstan.Grant No.IRN AP13068289.The supervisor of the project is Batyrkhan Omarov.
文摘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.
文摘Automatic identification of cyberbullying is a problem that is gaining traction,especially in the Machine Learning areas.Not only is it complicated,but it has also become a pressing necessity,considering how social media has become an integral part of adolescents’lives and how serious the impacts of cyberbullying and online harassment can be,particularly among teenagers.This paper contains a systematic literature review of modern strategies,machine learning methods,and technical means for detecting cyberbullying and the aggressive command of an individual in the information space of the Internet.We undertake an in-depth review of 13 papers from four scientific databases.The article provides an overview of scientific literature to analyze the problem of cyberbullying detection from the point of view of machine learning and natural language processing.In this review,we consider a cyberbullying detection framework on social media platforms,which includes data collection,data processing,feature selection,feature extraction,and the application ofmachine learning to classify whether texts contain cyberbullying or not.This article seeks to guide future research on this topic toward a more consistent perspective with the phenomenon’s description and depiction,allowing future solutions to be more practical and effective.
文摘In the field of stroke imaging, deep learning (DL) has enormousuntapped potential.When clinically significant symptoms of a cerebral strokeare detected, it is crucial to make an urgent diagnosis using available imagingtechniques such as computed tomography (CT) scans. The purpose of thiswork is to classify brain CT images as normal, surviving ischemia or cerebralhemorrhage based on the convolutional neural network (CNN) model. In thisstudy, we propose a computer-aided diagnostic system (CAD) for categorizingcerebral strokes using computed tomography images. Horizontal flip datamagnification techniques were used to obtain more accurate categorization.Image Data Generator to magnify the image in real time and apply anyrandom transformations to each training image. An early stopping method toavoid overtraining. As a result, the proposed methods improved several estimationparameters such as accuracy and recall, compared to other machinelearning methods. A python web application was created to demonstrate theresults of CNN model classification using cloud development techniques. Inour case, the model correctly identified the drawing class as normal with 79%accuracy. Based on the collected results, it was determined that the presentedautomated diagnostic system could be used to assist medical professionals indetecting and classifying brain strokes.
文摘In the face of escalating intricacy and heterogeneity within Internet of Things(IoT)network landscapes,the imperative for adept intrusion detection techniques has never been more pressing.This paper delineates a pioneering deep learning-based intrusion detection model:the One Dimensional Convolutional Neural Networks(1D-CNN)and Bidirectional Long Short-Term Memory(BiLSTM)Network(Conv-BiLSTM)augmented with an Attention Mechanism.The primary objective of this research is to engineer a sophisticated model proficient in discerning the nuanced patterns and temporal dependencies quintessential to IoT network traffic data,thereby facilitating the precise categorization of a myriad of intrusion types.Methodology:The proposed model amal-gamates the potent attributes of 1D convolutional neural networks,bidirectional long short-term memory layers,and attention mechanisms to bolster the efficacy and resilience of IoT intrusion detection systems.A rigorous assessment was executed employing an expansive dataset that mirrors the convolutions and multifariousness characteristic of genuine IoT network settings,encompassing various network traffic paradigms and intrusion archetypes.Findings:The empirical evidence underscores the paramountcy of the One Dimensional Conv-BiLSTM Network with Attention Mechanism,which exhibits a marked superiority over conventional machine learning modalities.Notably,the model registers an exemplary AUC-ROC metric of 0.995,underscoring its precision in typifying a spectrum of intrusions within IoT infrastructures.Conclusion:The presented One Dimensional Conv-BiLSTM Network armed with an Attention Mechanism stands out as a robust and trustworthy vanguard against IoT network breaches.Its prowess in discerning intricate traffic patterns and inherent temporal dependencies transcends that of traditional machine learning frameworks.The commendable diagnostic accuracy manifested in this study advocates for its tangible deployment.This investigation indubitably advances the cybersecurity domain,amplifying the fortification and robustness of IoT frameworks and heralding a new era of bolstered security across pivotal sectors such as residential,medical,and transit systems.
文摘Communication in society had developed within cultural and geographical boundaries prior to the invention of digital technology.The latest advancements in communication technology have significantly surpassed the conventional constraints for communication with regards to time and location.These new platforms have ushered in a new age of user-generated content,online chats,social network and comprehensive data on individual behavior.However,the abuse of communication software such as social media websites,online communities,and chats has resulted in a new kind of online hostility and aggressive actions.Due to widespread use of the social networking platforms and technological gadgets,conventional bullying has migrated from physical form to online,where it is termed as Cyberbullying.However,recently the digital technologies as machine learning and deep learning have been showing their efficiency in identifying linguistic patterns used by cyberbullies and cyberbullying detection problem.In this research paper,we aimed to evaluate shallow machine learning and deep learning methods in cyberbullying detection problem.We deployed three deep and six shallow learning algorithms for cyberbullying detection problems.The results show that bidirectional long-short-term memory is the most efficient method for cyberbullying detection,in terms of accuracy and recall.
文摘The purpose of the paper is to substantiate the possibility of constructing the physics of the evolution of matter based on the fundamental laws of physics. It is shown how this can be done within the framework of an extension of classical mechanics. Its expansion is based on the motion equation of a structured body. The fundamental difference between this equation and Newton’s motion equation is that instead of a model of a body in the form of a material point, it uses a structured body in the form of a system of potentially interacting material points. To obtain this equation, the principle of symmetry dualism, new for classical mechanics, was used. According to this principle, the dynamics of a body are determined not only by the symmetries of space, as in the case of a structureless body, but also by its symmetries. Thanks to this derivation of the equation, it takes into account the fact that the work of external forces, in addition to changing the body’s motion energy, also changes its internal energy. This change occurs due to the body’s motion energy when it moves in a non-uniform field of forces. It is shown why the motion equation of a structured body is irreversible. Its irreversibility made it possible to introduce the concept of D-entropy into extended classical mechanics. It is defined as the value of the relative increase in the body’s internal energy due to the motion energy. The relationship between the values of motion energy and D-entropy in the process of matter evolution is considered. It is shown how this connection is realized during the transition from one hierarchical level of matter to the next level. As a result, it was possible to prove that the evolution of the hierarchical structure of matter is characterized by the relationship between D-entropy and the motion energy of elements at each of its hierarchical levels.
