Abstract Air Pollution is constantly causing a severe effect on the environment and public health. Prediction of air quality is widespread and has become a challenging issue owing to the enormous environmental data with time-space nonlinearity and multi-dimensional feature interaction. There is a need to bring out the spatial and temporal factors that are influencing the prediction. The present study concentrates on the correlation prediction of spatial and temporal relations. A Deep learning technique has been proposed for forecasting the accurate prediction. The proposed Bi_ST model is evaluated for 17 cities in India and China. The predicted results are evaluated with the performance metrics of RMSE, MAE, and MAPE. Experimental results demonstrate that our method Bi_ST accredits more accurate forecasts than all baseline RNN and LSTM models by reducing the error rate. The accuracy of the model obtained is 94%.
{"title":"Spatial and Temporal Variations on Air Quality Prediction Using Deep Learning Techniques","authors":"S. Vandhana, J. Anuradha","doi":"10.2478/cait-2023-0045","DOIUrl":"https://doi.org/10.2478/cait-2023-0045","url":null,"abstract":"Abstract Air Pollution is constantly causing a severe effect on the environment and public health. Prediction of air quality is widespread and has become a challenging issue owing to the enormous environmental data with time-space nonlinearity and multi-dimensional feature interaction. There is a need to bring out the spatial and temporal factors that are influencing the prediction. The present study concentrates on the correlation prediction of spatial and temporal relations. A Deep learning technique has been proposed for forecasting the accurate prediction. The proposed Bi_ST model is evaluated for 17 cities in India and China. The predicted results are evaluated with the performance metrics of RMSE, MAE, and MAPE. Experimental results demonstrate that our method Bi_ST accredits more accurate forecasts than all baseline RNN and LSTM models by reducing the error rate. The accuracy of the model obtained is 94%.","PeriodicalId":45562,"journal":{"name":"Cybernetics and Information Technologies","volume":"52 1","pages":"213 - 232"},"PeriodicalIF":1.2,"publicationDate":"2023-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139297024","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract Transmission of information is an essential component in an IoT device for sending, receiving, and collecting data. The Smart devices in IoT architecture are designed as physical devices linked with computing resources that can connect and communicate with another smart device through any medium and protocol. Communication among various smart devices is a challenging task to exchange information and to guarantee the information reaches the destination entirely in real-time in the same order as sent without any data loss. Thus, this article proposes the novel Bat-based Deep Belief Neural framework (BDBN) method for the air pollution monitoring scheme. The reliability of the proposed system has been tested under the error condition in the transport layer and is validated with the conventional methods in terms of Accuracy, Mean Absolute Error (MAE), Root Mean Square Error (RMSE), Pearson correlation coefficient (r), Coefficient of determination (R2) and Error rate.
{"title":"Reliability Analysis of an IoT-Based Air Pollution Monitoring System Using Machine Learning Algorithm-BDBN","authors":"Saritha, V. Sarasvathi","doi":"10.2478/cait-2023-0046","DOIUrl":"https://doi.org/10.2478/cait-2023-0046","url":null,"abstract":"Abstract Transmission of information is an essential component in an IoT device for sending, receiving, and collecting data. The Smart devices in IoT architecture are designed as physical devices linked with computing resources that can connect and communicate with another smart device through any medium and protocol. Communication among various smart devices is a challenging task to exchange information and to guarantee the information reaches the destination entirely in real-time in the same order as sent without any data loss. Thus, this article proposes the novel Bat-based Deep Belief Neural framework (BDBN) method for the air pollution monitoring scheme. The reliability of the proposed system has been tested under the error condition in the transport layer and is validated with the conventional methods in terms of Accuracy, Mean Absolute Error (MAE), Root Mean Square Error (RMSE), Pearson correlation coefficient (r), Coefficient of determination (R2) and Error rate.","PeriodicalId":45562,"journal":{"name":"Cybernetics and Information Technologies","volume":"2008 1","pages":"233 - 250"},"PeriodicalIF":1.2,"publicationDate":"2023-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139300580","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract Due to the great importance of student satisfaction with educational services, many HEIs conduct annual surveys. Analyzing the results of such surveys, tracking trends, and comparing the evaluation results to help governing bodies make data-driven decisions to take measures to improve the quality of courses is time-consuming and requires a lot of manual work. As a solution to the problem, this paper proposes a comprehensive approach to monitoring student satisfaction with the quality of blended learning courses. The developed software tool analyzes results and enables users with different roles to generate reports with aggregated results at different levels, allowing them to make informed decisions and take measures to ensure a higher quality of courses. The generated reports during the pilot experiments proved the tool’s applicability. This tool can be implemented in any HEI, regardless of the software systems used.
{"title":"A Comprehensive Approach for Monitoring Student Satisfaction in Blended Learning Courses","authors":"S. Gaftandzhieva, R. Doneva, Milen Bliznakov","doi":"10.2478/cait-2023-0043","DOIUrl":"https://doi.org/10.2478/cait-2023-0043","url":null,"abstract":"Abstract Due to the great importance of student satisfaction with educational services, many HEIs conduct annual surveys. Analyzing the results of such surveys, tracking trends, and comparing the evaluation results to help governing bodies make data-driven decisions to take measures to improve the quality of courses is time-consuming and requires a lot of manual work. As a solution to the problem, this paper proposes a comprehensive approach to monitoring student satisfaction with the quality of blended learning courses. The developed software tool analyzes results and enables users with different roles to generate reports with aggregated results at different levels, allowing them to make informed decisions and take measures to ensure a higher quality of courses. The generated reports during the pilot experiments proved the tool’s applicability. This tool can be implemented in any HEI, regardless of the software systems used.","PeriodicalId":45562,"journal":{"name":"Cybernetics and Information Technologies","volume":"31 1","pages":"181 - 198"},"PeriodicalIF":1.2,"publicationDate":"2023-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139292116","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract Enhancing the fault tolerance of cloud systems and accurately forecasting cloud performance are pivotal concerns in cloud computing research. This research addresses critical concerns in cloud computing by enhancing fault tolerance and forecasting cloud performance using machine learning models. Leveraging the Google trace dataset with 10000 cloud environment records encompassing diverse metrics, we systematically have employed machine learning algorithms, including linear regression, decision trees, and gradient boosting, to construct predictive models. These models have outperformed baseline methods, with C5.0 and XGBoost showing exceptional accuracy, precision, and reliability in forecasting cloud behavior. Feature importance analysis has identified the ten most influential factors affecting cloud system performance. This work significantly advances cloud optimization and reliability, enabling proactive monitoring, early performance issue detection, and improved fault tolerance. Future research can further refine these predictive models, enhancing cloud resource management and ultimately improving service delivery in cloud computing.
{"title":"Fault Tolerance of Cloud Infrastructure with Machine Learning","authors":"Chetankumar Kalaskar, S. Thangam","doi":"10.2478/cait-2023-0034","DOIUrl":"https://doi.org/10.2478/cait-2023-0034","url":null,"abstract":"Abstract Enhancing the fault tolerance of cloud systems and accurately forecasting cloud performance are pivotal concerns in cloud computing research. This research addresses critical concerns in cloud computing by enhancing fault tolerance and forecasting cloud performance using machine learning models. Leveraging the Google trace dataset with 10000 cloud environment records encompassing diverse metrics, we systematically have employed machine learning algorithms, including linear regression, decision trees, and gradient boosting, to construct predictive models. These models have outperformed baseline methods, with C5.0 and XGBoost showing exceptional accuracy, precision, and reliability in forecasting cloud behavior. Feature importance analysis has identified the ten most influential factors affecting cloud system performance. This work significantly advances cloud optimization and reliability, enabling proactive monitoring, early performance issue detection, and improved fault tolerance. Future research can further refine these predictive models, enhancing cloud resource management and ultimately improving service delivery in cloud computing.","PeriodicalId":45562,"journal":{"name":"Cybernetics and Information Technologies","volume":"4 1","pages":"26 - 50"},"PeriodicalIF":1.2,"publicationDate":"2023-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139295225","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract The article proposes an original interdisciplinary approach to the design and construction of cyber-physical robot systems for mechanical processing. From a methodological aspect, the goal is the unification of modeling/synthesis and simulation software of a robot system for mechanical processing operating under the conditions of digital robust control. The system includes industrial robots; modules for implementing technological operations and transport systems. Adherence to the principle of modular construction, reconfiguration, and multi-operation ensures high flexibility and quick response when readjusting the system, and the optimization criteria – minimizing idle moves of the robot, leads to a reduction in the work cycle. The robust control, simultaneously in the instrumental, configurational, and system direction, is a counteraction in the mode of uncertainty, both to external signal disturbances and to possible constantly acting, system reparametrizing factors. This creates prerequisites for maintaining and implementing in online mode both the technological and geometric parameters of the details processed.
{"title":"Methodology for Designing Cyber-Physical Multi-Operation Robot Systems Operating in the Conditions of Digital Robust Control","authors":"Sasho Guergov, Nina G. Nikolova","doi":"10.2478/cait-2023-0028","DOIUrl":"https://doi.org/10.2478/cait-2023-0028","url":null,"abstract":"Abstract The article proposes an original interdisciplinary approach to the design and construction of cyber-physical robot systems for mechanical processing. From a methodological aspect, the goal is the unification of modeling/synthesis and simulation software of a robot system for mechanical processing operating under the conditions of digital robust control. The system includes industrial robots; modules for implementing technological operations and transport systems. Adherence to the principle of modular construction, reconfiguration, and multi-operation ensures high flexibility and quick response when readjusting the system, and the optimization criteria – minimizing idle moves of the robot, leads to a reduction in the work cycle. The robust control, simultaneously in the instrumental, configurational, and system direction, is a counteraction in the mode of uncertainty, both to external signal disturbances and to possible constantly acting, system reparametrizing factors. This creates prerequisites for maintaining and implementing in online mode both the technological and geometric parameters of the details processed.","PeriodicalId":45562,"journal":{"name":"Cybernetics and Information Technologies","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135587767","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Afia Bhutto, Aftab Ahmed Chandio, Kirshan Kumar Luhano, Imtiaz Ali Korejo
Abstract In parallel and distributed computing, cloud computing is progressively replacing the traditional computing paradigm. The cloud is made up of a set of virtualized resources in a data center that can be configured according to users’ needs. In other words, cloud computing faces the problem of a huge number of users requesting unlimited jobs for execution on a limited number of resources, which increases energy consumption and the network cost of the system. This study provides a complete analysis of classic scheduling techniques specifically for handling data-intensive workloads to see the effectiveness of the energy and network costs of the system. The workload is selected from a real-world data center. Moreover, this study offers the pros and cons of several classical heuristics-based job scheduling techniques that take into account the time and cost of transferring data from multiple sources. This study is useful for selecting appropriate scheduling techniques for appropriate environments.
{"title":"Analysis of Energy and Network Cost Effectiveness of Scheduling Strategies in Datacentre","authors":"Afia Bhutto, Aftab Ahmed Chandio, Kirshan Kumar Luhano, Imtiaz Ali Korejo","doi":"10.2478/cait-2023-0024","DOIUrl":"https://doi.org/10.2478/cait-2023-0024","url":null,"abstract":"Abstract In parallel and distributed computing, cloud computing is progressively replacing the traditional computing paradigm. The cloud is made up of a set of virtualized resources in a data center that can be configured according to users’ needs. In other words, cloud computing faces the problem of a huge number of users requesting unlimited jobs for execution on a limited number of resources, which increases energy consumption and the network cost of the system. This study provides a complete analysis of classic scheduling techniques specifically for handling data-intensive workloads to see the effectiveness of the energy and network costs of the system. The workload is selected from a real-world data center. Moreover, this study offers the pros and cons of several classical heuristics-based job scheduling techniques that take into account the time and cost of transferring data from multiple sources. This study is useful for selecting appropriate scheduling techniques for appropriate environments.","PeriodicalId":45562,"journal":{"name":"Cybernetics and Information Technologies","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135587769","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract Throughout the years neural networks have been based on the perceptron model of the artificial neuron. Attempts to stray from it are few to none. The perceptron simply works and that has discouraged research around other neuron models. New discoveries highlight the importance of dendrites in the neuron, but the perceptron model does not include them. This brings us to the goal of the paper which is to present and test different models of artificial neurons that utilize dendrites to create an artificial neuron that better represents the biological neuron. The authors propose two models. One is made with the purpose of testing the idea of the dendritic neuron. The distinguishing feature of the second model is that it implements activation functions after its dendrites. Results from the second model suggest that it performs as well as or even better than the perceptron model.
{"title":"Multi-Activation Dendritic Neural Network (MA-DNN) Working Example of Dendritic-Based Artificial Neural Network","authors":"Konstantin Tomov, Galina Momcheva","doi":"10.2478/cait-2023-0030","DOIUrl":"https://doi.org/10.2478/cait-2023-0030","url":null,"abstract":"Abstract Throughout the years neural networks have been based on the perceptron model of the artificial neuron. Attempts to stray from it are few to none. The perceptron simply works and that has discouraged research around other neuron models. New discoveries highlight the importance of dendrites in the neuron, but the perceptron model does not include them. This brings us to the goal of the paper which is to present and test different models of artificial neurons that utilize dendrites to create an artificial neuron that better represents the biological neuron. The authors propose two models. One is made with the purpose of testing the idea of the dendritic neuron. The distinguishing feature of the second model is that it implements activation functions after its dendrites. Results from the second model suggest that it performs as well as or even better than the perceptron model.","PeriodicalId":45562,"journal":{"name":"Cybernetics and Information Technologies","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135587923","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract This paper analyzes the different definitions of a negator of a probability mass function (pmf) and a Basic Belief Assignment (BBA) available in the literature. To overcome their limitations we propose an involutory negator of BBA, and we present a new indirect information fusion method based on this negator which can simplify the conflict management problem. The direct and indirect information fusion strategies are analyzed for three interesting examples of fusion of two BBAs. We also propose two methods for using the whole available information (the original BBAs and their negators) for decision-making support. The first method is based on the combination of the direct and indirect fusion strategies, and the second method selects the most reasonable fusion strategy to apply (direct, or indirect) based on the maximum entropy principle.
{"title":"Involutory Negator of Basic Belief Assignments","authors":"Jean Dezert, Albena Tchamova","doi":"10.2478/cait-2023-0021","DOIUrl":"https://doi.org/10.2478/cait-2023-0021","url":null,"abstract":"Abstract This paper analyzes the different definitions of a negator of a probability mass function (pmf) and a Basic Belief Assignment (BBA) available in the literature. To overcome their limitations we propose an involutory negator of BBA, and we present a new indirect information fusion method based on this negator which can simplify the conflict management problem. The direct and indirect information fusion strategies are analyzed for three interesting examples of fusion of two BBAs. We also propose two methods for using the whole available information (the original BBAs and their negators) for decision-making support. The first method is based on the combination of the direct and indirect fusion strategies, and the second method selects the most reasonable fusion strategy to apply (direct, or indirect) based on the maximum entropy principle.","PeriodicalId":45562,"journal":{"name":"Cybernetics and Information Technologies","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135588113","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Rumen Ketipov, Vera Angelova, Lyubka Doukovska, Roman Schnalle
Abstract Each person’s unique traits hold valuable insights into their consumer behavior, allowing scholars and industry experts to develop innovative marketing strategies, personalized solutions, and enhanced user experiences. This study presents a conceptual framework that explores the connection between fundamental personality dimensions and users’ online shopping styles. By employing the TIPI test, a reliable and validated alternative to the Five-Factor model, individual consumer profiles are established. The results reveal a significant relationship between key personality traits and specific online shopping functionalities. To accurately forecast customers’ needs, expectations, and preferences on the Internet, we propose the implementation of two Machine Learning models, namely Decision Trees and Random Forest. According to the applied evaluation metrics, both models demonstrate fine predictions of consumer behavior based on their personality.
{"title":"Predicting User Behavior in e-Commerce Using Machine Learning","authors":"Rumen Ketipov, Vera Angelova, Lyubka Doukovska, Roman Schnalle","doi":"10.2478/cait-2023-0026","DOIUrl":"https://doi.org/10.2478/cait-2023-0026","url":null,"abstract":"Abstract Each person’s unique traits hold valuable insights into their consumer behavior, allowing scholars and industry experts to develop innovative marketing strategies, personalized solutions, and enhanced user experiences. This study presents a conceptual framework that explores the connection between fundamental personality dimensions and users’ online shopping styles. By employing the TIPI test, a reliable and validated alternative to the Five-Factor model, individual consumer profiles are established. The results reveal a significant relationship between key personality traits and specific online shopping functionalities. To accurately forecast customers’ needs, expectations, and preferences on the Internet, we propose the implementation of two Machine Learning models, namely Decision Trees and Random Forest. According to the applied evaluation metrics, both models demonstrate fine predictions of consumer behavior based on their personality.","PeriodicalId":45562,"journal":{"name":"Cybernetics and Information Technologies","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135588214","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract The paper presents the statement of the problem of dynamical system „crane-load” optimal control. The acceleration period is under consideration and control must meet the minimum duration condition as well as load oscillations elimination. The objective function, which ensures the final condition satisfaction, is developed and analyzed in terms of its topology features. It includes three arguments and their searching is the essence of the benchmark problem. Two variants of the problem are proposed with varied objective function parameters. Twelve agent-based optimization algorithms have been applied to find solutions to a bunch of problems. A brief analysis of the performance of the algorithms reveals their weaknesses and advantages. Thus, the proposed real-world problem may be exploited to estimate the optimization algorithms’ search performance.
{"title":"A Real-World Benchmark Problem for Global Optimization","authors":"Romasevych Yuriy, Loveikin Viatcheslav, Bakay Borys","doi":"10.2478/cait-2023-0022","DOIUrl":"https://doi.org/10.2478/cait-2023-0022","url":null,"abstract":"Abstract The paper presents the statement of the problem of dynamical system „crane-load” optimal control. The acceleration period is under consideration and control must meet the minimum duration condition as well as load oscillations elimination. The objective function, which ensures the final condition satisfaction, is developed and analyzed in terms of its topology features. It includes three arguments and their searching is the essence of the benchmark problem. Two variants of the problem are proposed with varied objective function parameters. Twelve agent-based optimization algorithms have been applied to find solutions to a bunch of problems. A brief analysis of the performance of the algorithms reveals their weaknesses and advantages. Thus, the proposed real-world problem may be exploited to estimate the optimization algorithms’ search performance.","PeriodicalId":45562,"journal":{"name":"Cybernetics and Information Technologies","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134995291","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：