Pub Date : 2023-10-01DOI: 10.2478/jaiscr-2023-0020
Krystian Łapa, Danuta Rutkowska, Aleksander Byrski, Christian Napoli
Abstract In this paper, a new mechanism for detecting population stagnation based on the analysis of the local improvement of the evaluation function and the infinite impulse response filter is proposed. The purpose of this mechanism is to improve the population stagnation detection capability for various optimization scenarios, and thus to improve multi-population-based algorithms (MPBAs) performance. In addition, various other approaches have been proposed to eliminate stagnation, including approaches aimed at both improving performance and reducing the complexity of the algorithms. The developed methods were tested, among the others, for various migration topologies and various MPBAs, including the MNIA algorithm, which allows the use of many different base algorithms and thus eliminates the need to select the population-based algorithm for a given simulation problem. The simulations were performed for typical benchmark functions and control problems. The obtained results confirm the validity of the developed method.
摘要本文在分析评价函数的局部改进和无限脉冲响应滤波器的基础上，提出了一种新的种群停滞检测机制。该机制的目的是提高各种优化场景下的种群停滞检测能力，从而提高基于多种群的算法(multi-population based algorithms, mpba)的性能。此外，已经提出了各种其他方法来消除停滞，包括旨在提高性能和降低算法复杂性的方法。开发的方法在各种迁移拓扑和各种mpba中进行了测试，其中包括MNIA算法，该算法允许使用许多不同的基本算法，从而消除了为给定仿真问题选择基于种群的算法的需要。对典型的基准函数和控制问题进行了仿真。所得结果证实了所建方法的有效性。
{"title":"A New Approach to Detecting and Preventing Populations Stagnation Through Dynamic Changes in Multi-Population-Based Algorithms","authors":"Krystian Łapa, Danuta Rutkowska, Aleksander Byrski, Christian Napoli","doi":"10.2478/jaiscr-2023-0020","DOIUrl":"https://doi.org/10.2478/jaiscr-2023-0020","url":null,"abstract":"Abstract In this paper, a new mechanism for detecting population stagnation based on the analysis of the local improvement of the evaluation function and the infinite impulse response filter is proposed. The purpose of this mechanism is to improve the population stagnation detection capability for various optimization scenarios, and thus to improve multi-population-based algorithms (MPBAs) performance. In addition, various other approaches have been proposed to eliminate stagnation, including approaches aimed at both improving performance and reducing the complexity of the algorithms. The developed methods were tested, among the others, for various migration topologies and various MPBAs, including the MNIA algorithm, which allows the use of many different base algorithms and thus eliminates the need to select the population-based algorithm for a given simulation problem. The simulations were performed for typical benchmark functions and control problems. The obtained results confirm the validity of the developed method.","PeriodicalId":48494,"journal":{"name":"Journal of Artificial Intelligence and Soft Computing Research","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136153926","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-10-01DOI: 10.2478/jaiscr-2023-0019
José Luis Pérez, Javier Corrochano, Javier García, Rubén Majadas, Cristina Ibañez-Llano, Sergio Pérez, Fernando Fernández
Abstract In many Reinforcement Learning (RL) tasks, the classical online interaction of the learning agent with the environment is impractical, either because such interaction is expensive or dangerous. In these cases, previous gathered data can be used, arising what is typically called Offline RL. However, this type of learning faces a large number of challenges, mostly derived from the fact that exploration/exploitation trade-off is overshadowed. In addition, the historical data is usually biased by the way it was obtained, typically, a sub-optimal controller, producing a distributional shift from historical data and the one required to learn the optimal policy. In this paper, we present a novel approach to deal with the uncertainty risen by the absence or sparse presence of some state-action pairs in the learning data. Our approach is based on shaping the reward perceived from the environment to ensure the task is solved. We present the approach and show that combining it with classic online RL methods make them perform as good as state of the art Offline RL algorithms such as CQL and BCQ. Finally, we show that using our method on top of established offline learning algorithms can improve them.
{"title":"Discrete Uncertainty Quantification For Offline Reinforcement Learning","authors":"José Luis Pérez, Javier Corrochano, Javier García, Rubén Majadas, Cristina Ibañez-Llano, Sergio Pérez, Fernando Fernández","doi":"10.2478/jaiscr-2023-0019","DOIUrl":"https://doi.org/10.2478/jaiscr-2023-0019","url":null,"abstract":"Abstract In many Reinforcement Learning (RL) tasks, the classical online interaction of the learning agent with the environment is impractical, either because such interaction is expensive or dangerous. In these cases, previous gathered data can be used, arising what is typically called Offline RL. However, this type of learning faces a large number of challenges, mostly derived from the fact that exploration/exploitation trade-off is overshadowed. In addition, the historical data is usually biased by the way it was obtained, typically, a sub-optimal controller, producing a distributional shift from historical data and the one required to learn the optimal policy. In this paper, we present a novel approach to deal with the uncertainty risen by the absence or sparse presence of some state-action pairs in the learning data. Our approach is based on shaping the reward perceived from the environment to ensure the task is solved. We present the approach and show that combining it with classic online RL methods make them perform as good as state of the art Offline RL algorithms such as CQL and BCQ. Finally, we show that using our method on top of established offline learning algorithms can improve them.","PeriodicalId":48494,"journal":{"name":"Journal of Artificial Intelligence and Soft Computing Research","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136128009","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pakistan, a developing nation, is facing a critical crisis regarding its fossil fuel resources and the production of electrical energy. The country's electricity demand has reached approximately 29,000 MW, while the generation capacity is only 22,000 MW. This significant gap between generation and demand has led to load-shedding. To address this issue, we are considering the development of waste-to-energy plants, which are waste management facilities that utilize combustion to generate electricity. Instead of relying on traditional fossil fuels like coal, oil, or natural gas, waste-to-energy plants use trash as a fuel source. By burning this fuel, heat is produced, which heats water to generate steam that drives a turbine, ultimately creating electricity. While waste-to-energy is often portrayed as a viable method for extracting energy from available resources, it does pose challenges to the circular economy. This approach generates toxic waste, contributes to air pollution, and exacerbates climate change. These plants emit chemicals such as mercury and dioxins, which pose risks to human and environmental health. To address these concerns, we aim to investigate the development of waste-to-energy as an alternative energy source while prioritizing creating a healthy environment. As part of this effort, we intend to implement a sensor network to detect the heat generated during incineration and monitor the emission of pollutants. Our overarching goal is to generate electricity while recycling waste materials as much as possible, thus promoting a sustainable and eco-friendly approach.
{"title":"Investigation into the Development of Waste to Energy as an Alternative Energy Source","authors":"Shanza Khan, Aimen Haroon, Nageen Majeed","doi":"10.57041/jaic.v1i1.889","DOIUrl":"https://doi.org/10.57041/jaic.v1i1.889","url":null,"abstract":"Pakistan, a developing nation, is facing a critical crisis regarding its fossil fuel resources and the production of electrical energy. The country's electricity demand has reached approximately 29,000 MW, while the generation capacity is only 22,000 MW. This significant gap between generation and demand has led to load-shedding. To address this issue, we are considering the development of waste-to-energy plants, which are waste management facilities that utilize combustion to generate electricity. Instead of relying on traditional fossil fuels like coal, oil, or natural gas, waste-to-energy plants use trash as a fuel source. By burning this fuel, heat is produced, which heats water to generate steam that drives a turbine, ultimately creating electricity. While waste-to-energy is often portrayed as a viable method for extracting energy from available resources, it does pose challenges to the circular economy. This approach generates toxic waste, contributes to air pollution, and exacerbates climate change. These plants emit chemicals such as mercury and dioxins, which pose risks to human and environmental health. To address these concerns, we aim to investigate the development of waste-to-energy as an alternative energy source while prioritizing creating a healthy environment. As part of this effort, we intend to implement a sensor network to detect the heat generated during incineration and monitor the emission of pollutants. Our overarching goal is to generate electricity while recycling waste materials as much as possible, thus promoting a sustainable and eco-friendly approach.","PeriodicalId":48494,"journal":{"name":"Journal of Artificial Intelligence and Soft Computing Research","volume":"57 1","pages":""},"PeriodicalIF":2.8,"publicationDate":"2023-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79939078","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Ahmad Raza, Tauheed Ahmad, Umar Farooq, Muhammad Awais
In the highly competitive manufacturing industry, producing high-quality products is crucial for success and reputation. The issue of segregating quality products on the production line has emerged as a critical concern, necessitating effective strategies to tackle that problem. This project aims to design a quality control unit using controllers, sensors, and a robotic arm to segregate products based on height, substance amount, and cap presence. Ensuring product quality enhances customer satisfaction, improves production efficiency, optimizes resources, and boosts profitability through waste reduction and brand preservation. Workforce training will focus on quality standards and defect identification.
{"title":"Segregation of Quality Products on the Production Line","authors":"Ahmad Raza, Tauheed Ahmad, Umar Farooq, Muhammad Awais","doi":"10.57041/jaic.v1i1.890","DOIUrl":"https://doi.org/10.57041/jaic.v1i1.890","url":null,"abstract":"In the highly competitive manufacturing industry, producing high-quality products is crucial for success and reputation. The issue of segregating quality products on the production line has emerged as a critical concern, necessitating effective strategies to tackle that problem. This project aims to design a quality control unit using controllers, sensors, and a robotic arm to segregate products based on height, substance amount, and cap presence. Ensuring product quality enhances customer satisfaction, improves production efficiency, optimizes resources, and boosts profitability through waste reduction and brand preservation. Workforce training will focus on quality standards and defect identification.","PeriodicalId":48494,"journal":{"name":"Journal of Artificial Intelligence and Soft Computing Research","volume":"11 1","pages":""},"PeriodicalIF":2.8,"publicationDate":"2023-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84330354","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Inverters are frequently utilized in home and industrial settings to act as an alternative source of electricity in case the utility network's electrical supply is interrupted. However, due to the low capacity of the battery, the inverter was shut down for the heavy-load appliances. This endeavour is constructed in a way that uses solar energy to get around this restriction. An inverter powered by a battery makes up the hybrid inverter with a solar battery charging system. It incorporates maximum power point tracking (MPPT) to extract maximum power from the solar panels and efficiently charge the batteries. With the assistance of driver circuitry and a transformer, this inverter can generate up to 230V. The solar power source itself and the grid power supply are used to charge the battery. If the solar power supply is available, the relay circuitry uses the solar power to supply the load. Otherwise, the load connects to the grid power supply. The battery is also charged by this solar power source to be used as a backup in the future. When solar power is unavailable, charging the battery with the main supply is a pleasant option. As a result, this inverter may last longer and give the consumer an uninterrupted power supply.
{"title":"Implementation and Fabrication of Hybrid Solar Inverter","authors":"Areeba Nasir, Nayab Gul, Raees Ahmad, Syed Saqlain Raza","doi":"10.57041/jaic.v1i1.888","DOIUrl":"https://doi.org/10.57041/jaic.v1i1.888","url":null,"abstract":"Inverters are frequently utilized in home and industrial settings to act as an alternative source of electricity in case the utility network's electrical supply is interrupted. However, due to the low capacity of the battery, the inverter was shut down for the heavy-load appliances. This endeavour is constructed in a way that uses solar energy to get around this restriction. An inverter powered by a battery makes up the hybrid inverter with a solar battery charging system. It incorporates maximum power point tracking (MPPT) to extract maximum power from the solar panels and efficiently charge the batteries. With the assistance of driver circuitry and a transformer, this inverter can generate up to 230V. The solar power source itself and the grid power supply are used to charge the battery. If the solar power supply is available, the relay circuitry uses the solar power to supply the load. Otherwise, the load connects to the grid power supply. The battery is also charged by this solar power source to be used as a backup in the future. When solar power is unavailable, charging the battery with the main supply is a pleasant option. As a result, this inverter may last longer and give the consumer an uninterrupted power supply.","PeriodicalId":48494,"journal":{"name":"Journal of Artificial Intelligence and Soft Computing Research","volume":"3 1","pages":""},"PeriodicalIF":2.8,"publicationDate":"2023-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86716470","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Hanaf Hamran, M. Abdullah, M. E. Naveed, Abdul Rehman Afzal
Fingerprint-Based Voting Project is an application that recognizes users based on their fingerprints. Each person has a different finger pattern, so you can easily authenticate voters. This system allows voters to vote using their fingerprints. Fingerprints are used to identify users uniquely. As the fingerprint minutiae features differ for each human being, the fingerprint is utilized to authenticate the voters. Voters can only vote once for a candidate. The system will not allow the voter to vote for a second time. The system allows administrators to add names and candidate photos of candidates nominated for election. The administrator only has the right to add the names and photos of nominated candidates. The admin will verify voters and register voter names. Administrators authenticate users by verifying their identities and then enrolling voters. Users can log in and vote for candidates after receiving a user ID and password from the administrator. The system allows the user to vote for only one candidate for a particular election. The voter and the admin can view the election results using the election ID. Voting results will be updated immediately. This study shows that the proposed web-based voting system is fast, efficient and fraud-free.
{"title":"Design and Implementation of Secure Electronic Voting System Using Fingerprint Biometrics","authors":"Hanaf Hamran, M. Abdullah, M. E. Naveed, Abdul Rehman Afzal","doi":"10.57041/jaic.v1i1.887","DOIUrl":"https://doi.org/10.57041/jaic.v1i1.887","url":null,"abstract":"Fingerprint-Based Voting Project is an application that recognizes users based on their fingerprints. Each person has a different finger pattern, so you can easily authenticate voters. This system allows voters to vote using their fingerprints. Fingerprints are used to identify users uniquely. As the fingerprint minutiae features differ for each human being, the fingerprint is utilized to authenticate the voters. Voters can only vote once for a candidate. The system will not allow the voter to vote for a second time. The system allows administrators to add names and candidate photos of candidates nominated for election. The administrator only has the right to add the names and photos of nominated candidates. The admin will verify voters and register voter names. Administrators authenticate users by verifying their identities and then enrolling voters. Users can log in and vote for candidates after receiving a user ID and password from the administrator. The system allows the user to vote for only one candidate for a particular election. The voter and the admin can view the election results using the election ID. Voting results will be updated immediately. This study shows that the proposed web-based voting system is fast, efficient and fraud-free.","PeriodicalId":48494,"journal":{"name":"Journal of Artificial Intelligence and Soft Computing Research","volume":"17 1","pages":""},"PeriodicalIF":2.8,"publicationDate":"2023-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86005413","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Muhammad Saqib Bukhair, Syed Muhammad Tufail, Sikander Sultan, Mubashir Zafar Ansari
Water quality is paramount for sustaining life and maintaining ecological balance. However, traditional monitoring methods often must improve by providing real-time and comprehensive information. The developed systems show a cloud-based water quality monitoring system that overcomes the drawbacks of conventional approaches. The system allows numerous users to collect, store, and retrieve real-time data by combining sensors, an ESP32 microcontroller, Google Firebase Cloud, and a mobile application. The prototype illustrates the viability of using cloud computing to monitor water quality accurately and thoroughly. This effort advances the field by highlighting water quality is importance to supporting ecosystems and life. It highlights the system's contribution to allowing proactive decision-making and quick solutions to water quality challenges while outlining potential directions for future advancements in sensor calibration, testing in various water bodies, and cutting-edge data analytics methods. The cloud-based system for monitoring water quality has uses in various fields, such as environmental management, public health, and water resource conservation. It makes it easier to make educated decisions and take preventative action to preserve water quality and sustainability.
{"title":"Development of Cloud-based Water Quality Monitoring System","authors":"Muhammad Saqib Bukhair, Syed Muhammad Tufail, Sikander Sultan, Mubashir Zafar Ansari","doi":"10.57041/jaic.v1i1.891","DOIUrl":"https://doi.org/10.57041/jaic.v1i1.891","url":null,"abstract":"Water quality is paramount for sustaining life and maintaining ecological balance. However, traditional monitoring methods often must improve by providing real-time and comprehensive information. The developed systems show a cloud-based water quality monitoring system that overcomes the drawbacks of conventional approaches. The system allows numerous users to collect, store, and retrieve real-time data by combining sensors, an ESP32 microcontroller, Google Firebase Cloud, and a mobile application. The prototype illustrates the viability of using cloud computing to monitor water quality accurately and thoroughly. This effort advances the field by highlighting water quality is importance to supporting ecosystems and life. It highlights the system's contribution to allowing proactive decision-making and quick solutions to water quality challenges while outlining potential directions for future advancements in sensor calibration, testing in various water bodies, and cutting-edge data analytics methods. The cloud-based system for monitoring water quality has uses in various fields, such as environmental management, public health, and water resource conservation. It makes it easier to make educated decisions and take preventative action to preserve water quality and sustainability.","PeriodicalId":48494,"journal":{"name":"Journal of Artificial Intelligence and Soft Computing Research","volume":"96 1","pages":""},"PeriodicalIF":2.8,"publicationDate":"2023-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75895235","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In recent years, soundwave-based fire extinguishing systems have emerged as a promising avenue for fire safety measures. Despite this potential, the challenge is to determine the exact operating parameters for efficient performance. To address this gap, we present an artificial intelligence (AI)-enhanced decision support model that aims to improve the effectiveness of soundwave-based fire suppression systems. Our model uses advanced machine learning methods, including artificial neural networks, support vector machines (SVM) and logistic regression, to classify the extinguishing and non-extinguishing states of a flame. The classification is influenced by several input parameters, including the type of fuel, the size of the flame, the decibel level, the frequency, the airflow, and the distance to the flame. Our AI model was developed and implemented in LabVIEW for practical use. The performance of these machine learning models was thoroughly evaluated using key performance metrics: Accuracy, Precision, Recognition and F1 Score. The results show a superior classification accuracy of 90.893% for the artificial neural network model, closely followed by the logistic regression and SVM models with 86.836% and 86.728% accuracy, respectively. With this study, we highlight the potential of AI in optimizing acoustic fire suppression systems and offer valuable insights for future development and implementation. These insights could lead to a more efficient and effective use of acoustic fire extinguishing systems, potentially revolutionizing the practice of fire safety management
{"title":"LabVIEW-based fire extinguisher model based on acoustic airflow vibrations","authors":"Mahmut Dirik","doi":"10.55195/jscai.1310837","DOIUrl":"https://doi.org/10.55195/jscai.1310837","url":null,"abstract":"In recent years, soundwave-based fire extinguishing systems have emerged as a promising avenue for fire safety measures. Despite this potential, the challenge is to determine the exact operating parameters for efficient performance. To address this gap, we present an artificial intelligence (AI)-enhanced decision support model that aims to improve the effectiveness of soundwave-based fire suppression systems. Our model uses advanced machine learning methods, including artificial neural networks, support vector machines (SVM) and logistic regression, to classify the extinguishing and non-extinguishing states of a flame. The classification is influenced by several input parameters, including the type of fuel, the size of the flame, the decibel level, the frequency, the airflow, and the distance to the flame. Our AI model was developed and implemented in LabVIEW for practical use. \u0000The performance of these machine learning models was thoroughly evaluated using key performance metrics: Accuracy, Precision, Recognition and F1 Score. The results show a superior classification accuracy of 90.893% for the artificial neural network model, closely followed by the logistic regression and SVM models with 86.836% and 86.728% accuracy, respectively. With this study, we highlight the potential of AI in optimizing acoustic fire suppression systems and offer valuable insights for future development and implementation. These insights could lead to a more efficient and effective use of acoustic fire extinguishing systems, potentially revolutionizing the practice of fire safety management","PeriodicalId":48494,"journal":{"name":"Journal of Artificial Intelligence and Soft Computing Research","volume":"53 1","pages":""},"PeriodicalIF":2.8,"publicationDate":"2023-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76599126","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
As a result of the developments in technology, the internet is accepted as one of the most important sources of information today. Although it is possible to access a large number of data in a short time thanks to the Internet, it is critical to analyze this data correctly. The need for text mining is increasing day by day by processing and analyzing the increasingly irregular text type data in the digital environment and classifying them in a meaningful way. In this study, news texts obtained from online German, Spanish, English and Turkish news sites were separated according to predetermined world, sports, economy and politics categories. The data set consisting of 4000 news texts was classified using 41 different machine learning algorithms in the Weka program. The highest successful classification was obtained with Naive Bayes Multinominal and Naive Bayes Multinominal Updateable algorithms, and 93.5% for German news texts, 93.3% for English news texts, 82.8% for Spanish news texts and 88.8% for Turkish news texts.
{"title":"Classification of News Texts from Different Languages with Machine Learning Algorithms","authors":"Sidar Agduk, Emrah Aydemir, Ayfer Polat","doi":"10.55195/jscai.1311380","DOIUrl":"https://doi.org/10.55195/jscai.1311380","url":null,"abstract":"As a result of the developments in technology, the internet is accepted as one of the most important sources of information today. Although it is possible to access a large number of data in a short time thanks to the Internet, it is critical to analyze this data correctly. The need for text mining is increasing day by day by processing and analyzing the increasingly irregular text type data in the digital environment and classifying them in a meaningful way. In this study, news texts obtained from online German, Spanish, English and Turkish news sites were separated according to predetermined world, sports, economy and politics categories. The data set consisting of 4000 news texts was classified using 41 different machine learning algorithms in the Weka program. The highest successful classification was obtained with Naive Bayes Multinominal and Naive Bayes Multinominal Updateable algorithms, and 93.5% for German news texts, 93.3% for English news texts, 82.8% for Spanish news texts and 88.8% for Turkish news texts.","PeriodicalId":48494,"journal":{"name":"Journal of Artificial Intelligence and Soft Computing Research","volume":"16 1","pages":""},"PeriodicalIF":2.8,"publicationDate":"2023-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87290423","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-01DOI: 10.2478/jaiscr-2023-0013
H. Pham, Pham Van Duong, D. Tran, Joo-Ho Lee
Abstract Recently, measuring users and community influences on social media networks play significant roles in science and engineering. To address the problems, many researchers have investigated measuring users with these influences by dealing with huge data sets. However, it is hard to enhance the performances of these studies with multiple attributes together with these influences on social networks. This paper has presented a novel model for measuring users with these influences on a social network. In this model, the suggested algorithm combines Knowledge Graph and the learning techniques based on the vote rank mechanism to reflect user interaction activities on the social network. To validate the proposed method, the proposed method has been tested through homogeneous graph with the building knowledge graph based on user interactions together with influences in real-time. Experimental results of the proposed model using six open public data show that the proposed algorithm is an effectiveness in identifying influential nodes.
{"title":"A Novel Approach of Voterank-Based Knowledge Graph for Improvement of Multi-Attributes Influence Nodes on Social Networks","authors":"H. Pham, Pham Van Duong, D. Tran, Joo-Ho Lee","doi":"10.2478/jaiscr-2023-0013","DOIUrl":"https://doi.org/10.2478/jaiscr-2023-0013","url":null,"abstract":"Abstract Recently, measuring users and community influences on social media networks play significant roles in science and engineering. To address the problems, many researchers have investigated measuring users with these influences by dealing with huge data sets. However, it is hard to enhance the performances of these studies with multiple attributes together with these influences on social networks. This paper has presented a novel model for measuring users with these influences on a social network. In this model, the suggested algorithm combines Knowledge Graph and the learning techniques based on the vote rank mechanism to reflect user interaction activities on the social network. To validate the proposed method, the proposed method has been tested through homogeneous graph with the building knowledge graph based on user interactions together with influences in real-time. Experimental results of the proposed model using six open public data show that the proposed algorithm is an effectiveness in identifying influential nodes.","PeriodicalId":48494,"journal":{"name":"Journal of Artificial Intelligence and Soft Computing Research","volume":"13 1","pages":"165 - 180"},"PeriodicalIF":2.8,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42804413","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","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：