Computer security consists in protecting access and manipulating system data by several mechanisms. However, conventional protection technologies are ineffective against current attacks. Thus, new tools have appeared, such as the intrusion detection and prediction systems which are important defense elements for network security since they detect the ongoing intrusions and predict the upcoming attacks. Besides, most of conventional protection technologies remain insufficient in terms of actions since they are all passive systems, unable to provide recommendations in order to block or stop the attacks. In this paper, a distributed detection and prediction system, composed of three major parts, is proposed. The first part deals with the detection of intrusions based on the decision tree learning algorithm. The second part deals with intrusions prediction using the chronicle algorithm. The third part proposes an expert system for security recommendations in response to detected intrusions, able to provide appropriate recommendations to stop the attacks. The proposed system gives good results in terms of accuracy and precision in detecting and predicting attacks, and efficiency in proposing the right recommendations to stop the attacks.
{"title":"Active intrusion detection and prediction based on temporal big data analytics","authors":"F. Jemili, O. Korbaa","doi":"10.3233/kes-230119","DOIUrl":"https://doi.org/10.3233/kes-230119","url":null,"abstract":"Computer security consists in protecting access and manipulating system data by several mechanisms. However, conventional protection technologies are ineffective against current attacks. Thus, new tools have appeared, such as the intrusion detection and prediction systems which are important defense elements for network security since they detect the ongoing intrusions and predict the upcoming attacks. Besides, most of conventional protection technologies remain insufficient in terms of actions since they are all passive systems, unable to provide recommendations in order to block or stop the attacks. In this paper, a distributed detection and prediction system, composed of three major parts, is proposed. The first part deals with the detection of intrusions based on the decision tree learning algorithm. The second part deals with intrusions prediction using the chronicle algorithm. The third part proposes an expert system for security recommendations in response to detected intrusions, able to provide appropriate recommendations to stop the attacks. The proposed system gives good results in terms of accuracy and precision in detecting and predicting attacks, and efficiency in proposing the right recommendations to stop the attacks.","PeriodicalId":44076,"journal":{"name":"International Journal of Knowledge-Based and Intelligent Engineering Systems","volume":null,"pages":null},"PeriodicalIF":0.7,"publicationDate":"2024-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140479467","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}
Jose Aguilar, Francisco Díaz, Ángel Pinto, Nelson Pérez
An emerging serious game (ESG) is a game that unfolds autonomously without explicit laws, adapting to the player, where the player learns while playing. An ESG engine must enable the emergence in the game, in order to allow its adaptation to the specific environment where it is being used. In previous articles, different components of an ESG engine have been proposed. This paper proposes a strategy adaptive system (SAS) for ESG, which allows the emergence of strategies in a videogame. Particularly, SAS manages the emergence of new procedures or methods (tactics), as well as actions (logistics), among other things, in the ESG, to adapt it to the environment. This component is based on a Fuzzy Classifier System that generates new rules, tactics, etc. in the game to follow the desired behavior. In this article, SAS is applied in a smart classroom (SaCI, for its acronym in Spanish), in such a way that allows the adaptation of an ESG to the students in SaCI. Especially, it is used during their teaching-learning processes. Additionally, this paper analyzes the performance of SAS in SaCI, with very encouraging results, since the quality of the strategies proposed by SAS (defined by rules that define the logic and tactics of the game) is improved in all case studies. This improvement is confirmed because the average use of the rules generated by our adaptive system is greater than 3.6, when the initial rules are used on average less than once.
{"title":"Strategy adaptive system to learning processes for emerging serious games using a fuzzy classifier system","authors":"Jose Aguilar, Francisco Díaz, Ángel Pinto, Nelson Pérez","doi":"10.3233/kes-230113","DOIUrl":"https://doi.org/10.3233/kes-230113","url":null,"abstract":"An emerging serious game (ESG) is a game that unfolds autonomously without explicit laws, adapting to the player, where the player learns while playing. An ESG engine must enable the emergence in the game, in order to allow its adaptation to the specific environment where it is being used. In previous articles, different components of an ESG engine have been proposed. This paper proposes a strategy adaptive system (SAS) for ESG, which allows the emergence of strategies in a videogame. Particularly, SAS manages the emergence of new procedures or methods (tactics), as well as actions (logistics), among other things, in the ESG, to adapt it to the environment. This component is based on a Fuzzy Classifier System that generates new rules, tactics, etc. in the game to follow the desired behavior. In this article, SAS is applied in a smart classroom (SaCI, for its acronym in Spanish), in such a way that allows the adaptation of an ESG to the students in SaCI. Especially, it is used during their teaching-learning processes. Additionally, this paper analyzes the performance of SAS in SaCI, with very encouraging results, since the quality of the strategies proposed by SAS (defined by rules that define the logic and tactics of the game) is improved in all case studies. This improvement is confirmed because the average use of the rules generated by our adaptive system is greater than 3.6, when the initial rules are used on average less than once.","PeriodicalId":44076,"journal":{"name":"International Journal of Knowledge-Based and Intelligent Engineering Systems","volume":null,"pages":null},"PeriodicalIF":0.7,"publicationDate":"2024-01-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140482488","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}
Manual creation of trail maps for hikers is time-consuming and can be inaccurate. This paper presents a new method to construct trail networks based on a growing self-organizing map (GSOM) using publicly available Global Positioning System (GPS) data. Unlike other network topology construction techniques, this approach is not dependent on sequential GPS traces. Fine-tuning multiple hyperparameters enables to customize this process based on unique features of datasets and networks. The generated maps, which are trained on public GPS data, are compared to a ground truth from Open Street Map (OSM). The performance evaluation is based on the accuracy, completeness, and topological correctness of the trail maps. The proposed approach outperforms, particularly on sparse networks without significant GPS noise.
{"title":"Construction of trail networks based on growing self-organizing maps and public GPS data","authors":"Jared Macshane, Ali Ahmadinia","doi":"10.3233/kes-230153","DOIUrl":"https://doi.org/10.3233/kes-230153","url":null,"abstract":"Manual creation of trail maps for hikers is time-consuming and can be inaccurate. This paper presents a new method to construct trail networks based on a growing self-organizing map (GSOM) using publicly available Global Positioning System (GPS) data. Unlike other network topology construction techniques, this approach is not dependent on sequential GPS traces. Fine-tuning multiple hyperparameters enables to customize this process based on unique features of datasets and networks. The generated maps, which are trained on public GPS data, are compared to a ground truth from Open Street Map (OSM). The performance evaluation is based on the accuracy, completeness, and topological correctness of the trail maps. The proposed approach outperforms, particularly on sparse networks without significant GPS noise.","PeriodicalId":44076,"journal":{"name":"International Journal of Knowledge-Based and Intelligent Engineering Systems","volume":null,"pages":null},"PeriodicalIF":0.7,"publicationDate":"2024-01-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140496281","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}
With the development of the internet economy, e-commerce has rapidly risen, and a large number of small and micro e-commerce enterprises have emerged. However, these enterprises have low financial information transparency, small scale, and high development uncertainty. Therefore, combining the characteristics of the internet economy, it is of great significance to dynamically evaluate credit risk. This not only helps to enhance the quality and rationality of credit risk evaluation results, but also helps to improve financing efficiency and reduce financing risks. The credit evaluation for small and micro enterprises is a multiple-attribute group decision-making (MAGDM). Recently, the TODIM (an acronym in Portuguese of interactive and multicriteria decision making) and TOPSIS method has been inaugurated to cope with MAGDM issues. The 2-tuple linguistic neutrosophic sets (2TLNSs) are inaugurated as an effective tool for characterizing uncertain information during the credit evaluation for small and micro enterprises. In this paper, the 2-tuple linguistic neutrosophic TODIM-TOPSIS (2TLNN-TODIM-TOPSIS) method is inaugurated to solve the MAGDM under 2TLNSs. Finally, a numerical case study for credit evaluation for small and micro enterprises is inaugurated to confirm the proposed method. The prime contribution of this paper are outlined: (1) The information entropy based on score function and accuracy function are built on the 2TLNSs to obtain weight information; (2) an integrated the 2-tuple linguistic neutrosophic TODIM-TOPSIS (2TLNN-TODIM-TOPSIS) method is established to cope with MAGDM; (3) An illustrative example for credit evaluation for small and micro enterprises has accomplished to illustrate the 2TLNN-TODIM-TOPSIS; (4) some comparative analysis are employed to verify the 2TLNN-TODIM-TOPSIS method.
{"title":"Enhanced group decision-making through an intelligent algorithmic approach for multiple-attribute credit evaluation with 2-tuple linguistic neutrosophic sets","authors":"Cui Mao","doi":"10.3233/kes-180","DOIUrl":"https://doi.org/10.3233/kes-180","url":null,"abstract":"With the development of the internet economy, e-commerce has rapidly risen, and a large number of small and micro e-commerce enterprises have emerged. However, these enterprises have low financial information transparency, small scale, and high development uncertainty. Therefore, combining the characteristics of the internet economy, it is of great significance to dynamically evaluate credit risk. This not only helps to enhance the quality and rationality of credit risk evaluation results, but also helps to improve financing efficiency and reduce financing risks. The credit evaluation for small and micro enterprises is a multiple-attribute group decision-making (MAGDM). Recently, the TODIM (an acronym in Portuguese of interactive and multicriteria decision making) and TOPSIS method has been inaugurated to cope with MAGDM issues. The 2-tuple linguistic neutrosophic sets (2TLNSs) are inaugurated as an effective tool for characterizing uncertain information during the credit evaluation for small and micro enterprises. In this paper, the 2-tuple linguistic neutrosophic TODIM-TOPSIS (2TLNN-TODIM-TOPSIS) method is inaugurated to solve the MAGDM under 2TLNSs. Finally, a numerical case study for credit evaluation for small and micro enterprises is inaugurated to confirm the proposed method. The prime contribution of this paper are outlined: (1) The information entropy based on score function and accuracy function are built on the 2TLNSs to obtain weight information; (2) an integrated the 2-tuple linguistic neutrosophic TODIM-TOPSIS (2TLNN-TODIM-TOPSIS) method is established to cope with MAGDM; (3) An illustrative example for credit evaluation for small and micro enterprises has accomplished to illustrate the 2TLNN-TODIM-TOPSIS; (4) some comparative analysis are employed to verify the 2TLNN-TODIM-TOPSIS method.","PeriodicalId":44076,"journal":{"name":"International Journal of Knowledge-Based and Intelligent Engineering Systems","volume":null,"pages":null},"PeriodicalIF":0.7,"publicationDate":"2024-01-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139615195","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}
Autonomous vehicle platoons have become an increasingly popular solution to enhance driving system performance and facilitate the safe integration of these vehicles on the roads. To ensure efficient platoon traffic, it is essential to effectively manage both speed and direction within this group of vehicles. It is in this context that this research is situated. Our primary objective is to enhance the performance of speed and direction controllers, as the ability of vehicles to adjust these parameters in a coordinated manner is crucial for the success of platoon traffic. To achieve this, we have developed a novel speed control approach based on neural networks and fuzzy logic, utilizing V2X communication. By incorporating environmental parameters through vehicle-to-vehicle communication and considering the specific goals of the platoon, our neuro-fuzzy system can accurately calculate optimal speeds and directions for the vehicles. Our experiments have demonstrated the effectiveness of this approach compared to traditional and advanced methods, improving both energy efficiency and temporal coordination of autonomous vehicles within the platoon.
{"title":"Enhancing platoon performance: A novel approach to speed and direction control using V2X communication","authors":"A. Boubakri, Sonia Mettali Gammar","doi":"10.3233/kes-230036","DOIUrl":"https://doi.org/10.3233/kes-230036","url":null,"abstract":"Autonomous vehicle platoons have become an increasingly popular solution to enhance driving system performance and facilitate the safe integration of these vehicles on the roads. To ensure efficient platoon traffic, it is essential to effectively manage both speed and direction within this group of vehicles. It is in this context that this research is situated. Our primary objective is to enhance the performance of speed and direction controllers, as the ability of vehicles to adjust these parameters in a coordinated manner is crucial for the success of platoon traffic. To achieve this, we have developed a novel speed control approach based on neural networks and fuzzy logic, utilizing V2X communication. By incorporating environmental parameters through vehicle-to-vehicle communication and considering the specific goals of the platoon, our neuro-fuzzy system can accurately calculate optimal speeds and directions for the vehicles. Our experiments have demonstrated the effectiveness of this approach compared to traditional and advanced methods, improving both energy efficiency and temporal coordination of autonomous vehicles within the platoon.","PeriodicalId":44076,"journal":{"name":"International Journal of Knowledge-Based and Intelligent Engineering Systems","volume":null,"pages":null},"PeriodicalIF":0.7,"publicationDate":"2024-01-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140510446","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}
The “innovation and Entrepreneurship” education focuses on cultivating students’ “innovation and Entrepreneurship” abilities, reflecting the fundamental requirements of economic progress and social development for the knowledge, ability, and quality structure of talents. Local universities should actively promote the reform of talent cultivation models, establish a scientific “innovation and Entrepreneurship” education target system based on the actual situation of the school, strengthen the construction of “innovation and Entrepreneurship” education courses, build various “innovation and Entrepreneurship” practice platforms, pay attention to the interaction between the first and second classrooms, as well as practical and training platforms, serve the growth and talent development of students, and achieve a comprehensive improvement in the quality of school education, teaching, and talent cultivation. The “innovation and Entrepreneurship” education quality evaluation of local colleges could be considered as multiple attribute decision-making (MADM). Recently, the Combined Compromise Solution (CoCoSo) method and information entropy method was employed to deal with MADM. The triangular fuzzy neutrosophic sets (TFNSs) are employed as a better tool for expressing uncertain information during the “innovation and Entrepreneurship” education quality evaluation of local colleges. In this paper, the triangular fuzzy neutrosophic number CoCoSo (TFNN-CoCoSo) based on the TFNN grey rational coefficients (TFNNGRC) from TFNN positive ideal solution (TFNNPIS) is constructed to cope with the MADM under TFNSs. The information entropy method is employed to compute the weight values based on the TFNNGRC from TFNNPIS under TFNSs. Finally, a numerical example of “innovation and Entrepreneurship” education quality evaluation of local colleges is constructed and some decision comparisons are constructed to verify the TFNN-CoCoSo method.
{"title":"CoCoSo framework for multi-attribute decision-making with triangular fuzzy neutrosophic sets: “Innovation and entrepreneurship” evaluation case","authors":"Li Yang, Qin Li","doi":"10.3233/kes-230298","DOIUrl":"https://doi.org/10.3233/kes-230298","url":null,"abstract":"The “innovation and Entrepreneurship” education focuses on cultivating students’ “innovation and Entrepreneurship” abilities, reflecting the fundamental requirements of economic progress and social development for the knowledge, ability, and quality structure of talents. Local universities should actively promote the reform of talent cultivation models, establish a scientific “innovation and Entrepreneurship” education target system based on the actual situation of the school, strengthen the construction of “innovation and Entrepreneurship” education courses, build various “innovation and Entrepreneurship” practice platforms, pay attention to the interaction between the first and second classrooms, as well as practical and training platforms, serve the growth and talent development of students, and achieve a comprehensive improvement in the quality of school education, teaching, and talent cultivation. The “innovation and Entrepreneurship” education quality evaluation of local colleges could be considered as multiple attribute decision-making (MADM). Recently, the Combined Compromise Solution (CoCoSo) method and information entropy method was employed to deal with MADM. The triangular fuzzy neutrosophic sets (TFNSs) are employed as a better tool for expressing uncertain information during the “innovation and Entrepreneurship” education quality evaluation of local colleges. In this paper, the triangular fuzzy neutrosophic number CoCoSo (TFNN-CoCoSo) based on the TFNN grey rational coefficients (TFNNGRC) from TFNN positive ideal solution (TFNNPIS) is constructed to cope with the MADM under TFNSs. The information entropy method is employed to compute the weight values based on the TFNNGRC from TFNNPIS under TFNSs. Finally, a numerical example of “innovation and Entrepreneurship” education quality evaluation of local colleges is constructed and some decision comparisons are constructed to verify the TFNN-CoCoSo method.","PeriodicalId":44076,"journal":{"name":"International Journal of Knowledge-Based and Intelligent Engineering Systems","volume":null,"pages":null},"PeriodicalIF":0.7,"publicationDate":"2024-01-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140510088","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}
Multitask learning (MTL) is a machine learning paradigm where a single model is trained to perform several tasks simultaneously. Despite the considerable amount of research on MTL, the majority of it has been centered around English language, while other language such as Arabic have not received as much attention. Most existing Arabic NLP techniques concentrate on single or multitask learning, sharing just a limited number of tasks, between two or three tasks. To address this gap, we present ArMT-TNN, an Arabic Multi-Task Learning using Transformer Neural Network, designed for Arabic natural language understanding (ANLU) tasks. Our approach involves sharing learned information between eight ANLU tasks, allowing for a single model to solve all of them. We achieve this by fine-tuning all tasks simultaneously and using multiple pre-trained Bidirectional Transformer language models, like BERT, that are specifically designed for Arabic language processing. Additionally, we explore the effectiveness of various Arabic language models (LMs) that have been pre-trained on different types of Arabic text, such as Modern Standard Arabic (MSA) and Arabic dialects. Our approach demonstrated outstanding performance compared to all current models on four test sets within the ALUE benchmark, namely MQ2Q, OOLD, SVREG, and SEC, by margins of 3.9%, 3.8%, 10.1%, and 3.7%, respectively. Nonetheless, our approach did not perform as well on the remaining tasks due to the negative transfer of knowledge. This finding highlights the importance of carefully selecting tasks when constructing a benchmark. Our experiments also show that LMs which were pretrained on text types that differ from the text type used for finetuned tasks can still perform well.
{"title":"ArMT-TNN: Enhancing natural language understanding performance through hard parameter multitask learning in Arabic","authors":"Ali Alkhathlan, Khalid Alomar","doi":"10.3233/kes-230192","DOIUrl":"https://doi.org/10.3233/kes-230192","url":null,"abstract":"Multitask learning (MTL) is a machine learning paradigm where a single model is trained to perform several tasks simultaneously. Despite the considerable amount of research on MTL, the majority of it has been centered around English language, while other language such as Arabic have not received as much attention. Most existing Arabic NLP techniques concentrate on single or multitask learning, sharing just a limited number of tasks, between two or three tasks. To address this gap, we present ArMT-TNN, an Arabic Multi-Task Learning using Transformer Neural Network, designed for Arabic natural language understanding (ANLU) tasks. Our approach involves sharing learned information between eight ANLU tasks, allowing for a single model to solve all of them. We achieve this by fine-tuning all tasks simultaneously and using multiple pre-trained Bidirectional Transformer language models, like BERT, that are specifically designed for Arabic language processing. Additionally, we explore the effectiveness of various Arabic language models (LMs) that have been pre-trained on different types of Arabic text, such as Modern Standard Arabic (MSA) and Arabic dialects. Our approach demonstrated outstanding performance compared to all current models on four test sets within the ALUE benchmark, namely MQ2Q, OOLD, SVREG, and SEC, by margins of 3.9%, 3.8%, 10.1%, and 3.7%, respectively. Nonetheless, our approach did not perform as well on the remaining tasks due to the negative transfer of knowledge. This finding highlights the importance of carefully selecting tasks when constructing a benchmark. Our experiments also show that LMs which were pretrained on text types that differ from the text type used for finetuned tasks can still perform well.","PeriodicalId":44076,"journal":{"name":"International Journal of Knowledge-Based and Intelligent Engineering Systems","volume":null,"pages":null},"PeriodicalIF":0.7,"publicationDate":"2024-01-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139626558","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}
Textual Question Answering targets answering questions defined in natural language. Question Answering Systems offer an automated approach to procuring answers to queries expressed in natural language. The need for Multilingual Question Answering without performing machine translation is ever existing. Besides that, automating tasks with the help of technology to assist humans, has been the main aim of research in recent years. This paper presents an automated answer evaluation system for reading comprehension-based questions in the Hindi language without requiring translation in any other language. The system accepts text, question, and handwritten answer of a student in the form of an image for answer evaluation. This is accomplished by developing a textual question-answering system for reading comprehension. It is an extractive approach that utilizes RoBERTa transformer model and fine-tunes it for Hindi question-answering. The answer to the question is extracted as a span from the provided text. Further, a handwritten text recognizer model is developed employing a Convolutional Recurrent Neural Network with Connectionist Temporal Classification module along with two layers of Bidirectional LSTM. Experimentation is performed using existing as well as self-created datasets to show the effectiveness of the proposed approach. An accuracy of 98.69% is obtained on the self-created Hindi-QA dataset and the proposed system outperformed the other existing methods. The paper also discusses potential research directions in the field.
文本问题解答的目标是回答用自然语言定义的问题。问题解答系统提供了一种自动获取自然语言查询答案的方法。不进行机器翻译的多语种问题解答需求一直存在。此外，借助技术实现任务自动化以协助人类，也是近年来研究的主要目标。本文介绍了一种自动答题评估系统，该系统适用于基于阅读理解的印地语问题，无需翻译成其他语言。该系统接受文本、问题和学生以图像形式提供的手写答案进行答案评估。这是通过开发一个用于阅读理解的文本问题解答系统来实现的。这是一种提取方法，它利用 RoBERTa 变换器模型，并针对印地语问题解答进行了微调。问题的答案是从所提供的文本中提取的跨度。此外，还开发了一个手写文本识别器模型，该模型采用了带有连接时序分类模块的卷积递归神经网络和两层双向 LSTM。实验使用了现有数据集和自创数据集，以显示所提方法的有效性。在自建的印地语 QA 数据集上，所提系统的准确率达到 98.69%，优于其他现有方法。论文还讨论了该领域的潜在研究方向。
{"title":"A textual question answering and handwritten answer evaluation system for hindi language","authors":"Khushboo Khurana, Rachita Bharambe, Hardik Dharmik, Krishna Rathi, Mayur Rawte","doi":"10.3233/kes-230188","DOIUrl":"https://doi.org/10.3233/kes-230188","url":null,"abstract":"Textual Question Answering targets answering questions defined in natural language. Question Answering Systems offer an automated approach to procuring answers to queries expressed in natural language. The need for Multilingual Question Answering without performing machine translation is ever existing. Besides that, automating tasks with the help of technology to assist humans, has been the main aim of research in recent years. This paper presents an automated answer evaluation system for reading comprehension-based questions in the Hindi language without requiring translation in any other language. The system accepts text, question, and handwritten answer of a student in the form of an image for answer evaluation. This is accomplished by developing a textual question-answering system for reading comprehension. It is an extractive approach that utilizes RoBERTa transformer model and fine-tunes it for Hindi question-answering. The answer to the question is extracted as a span from the provided text. Further, a handwritten text recognizer model is developed employing a Convolutional Recurrent Neural Network with Connectionist Temporal Classification module along with two layers of Bidirectional LSTM. Experimentation is performed using existing as well as self-created datasets to show the effectiveness of the proposed approach. An accuracy of 98.69% is obtained on the self-created Hindi-QA dataset and the proposed system outperformed the other existing methods. The paper also discusses potential research directions in the field.","PeriodicalId":44076,"journal":{"name":"International Journal of Knowledge-Based and Intelligent Engineering Systems","volume":null,"pages":null},"PeriodicalIF":0.7,"publicationDate":"2024-01-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139534479","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}
In this paper, we define the Quadripartition Neutrosophic Weighted Neutrality Aggregative (QNWNA) operator and Quadripartition Neutrosophic Ordered Weighted Neutrality Aggregative (QNOWNA) operator for solving Multi-Attribute Group Decision Making (MAGDM) problems. The basic properties of both operators are discussed thoroughly. A new MAGDM strategy is developed using these developed operators. A case study of e-commerce site selection in India is discussed to show the applicability of the proposed MADM strategy. Moreover, the performance of the QNWNA and QNOWNA operators are compared with Quadripartition Neutrosophic Weighted Arithmetic Aggregation (QNWAA) operator and Quadripartition Neutrosophic Weighted Geometric Aggregation (QNWGA), Quadripartition Single valued Neutrosophic Dombi Weighted Arithmetic Aggregation (QSVNDWAA) and QSVN Dombi Weighted Geometric Aggregation (QSVNDWAA) operator.
{"title":"QNN-MAGDM strategy for E-commerce site selection using quadripartition neutrosophic neutrality aggregative operators","authors":"Rama Mallick, Surapati Pramanik, B. Giri","doi":"10.3233/kes-230177","DOIUrl":"https://doi.org/10.3233/kes-230177","url":null,"abstract":"In this paper, we define the Quadripartition Neutrosophic Weighted Neutrality Aggregative (QNWNA) operator and Quadripartition Neutrosophic Ordered Weighted Neutrality Aggregative (QNOWNA) operator for solving Multi-Attribute Group Decision Making (MAGDM) problems. The basic properties of both operators are discussed thoroughly. A new MAGDM strategy is developed using these developed operators. A case study of e-commerce site selection in India is discussed to show the applicability of the proposed MADM strategy. Moreover, the performance of the QNWNA and QNOWNA operators are compared with Quadripartition Neutrosophic Weighted Arithmetic Aggregation (QNWAA) operator and Quadripartition Neutrosophic Weighted Geometric Aggregation (QNWGA), Quadripartition Single valued Neutrosophic Dombi Weighted Arithmetic Aggregation (QSVNDWAA) and QSVN Dombi Weighted Geometric Aggregation (QSVNDWAA) operator.","PeriodicalId":44076,"journal":{"name":"International Journal of Knowledge-Based and Intelligent Engineering Systems","volume":null,"pages":null},"PeriodicalIF":0.7,"publicationDate":"2024-01-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139625793","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}
To establish a student-centered teaching quality assurance system in English teaching in universities, it is necessary to establish an educational philosophy of survival based on quality, achieve student-centered learning, optimize the allocation of English teaching resources, and reform evaluation standards; To address the problems in English teaching, we need to raise awareness of the construction of a “student-centered” teaching quality assurance system, carry out “student-centered” teacher training activities, and improve teachers’ professional skills; At the same time, we will establish a student-centered English curriculum system, promote the reform and innovation of teaching models, establish a diversified English teaching evaluation system, and ensure the high efficiency and quality of English teaching in universities. The college English teaching quality evaluation is the MAGDM. Recently, the TODIM and MABAC technique has been employed to manage MAGDM. The interval-valued intuitionistic fuzzy sets (IVIFSs) are employed as a useful tool for portraying uncertain information during the college English teaching quality evaluation. In this paper, the interval-valued intuitionistic fuzzy TODIM-MABAC (IVIF-TODIM-MABAC) technique is built to manage the MAGDM under IVIFSs. At last, the numerical example for college English teaching quality evaluation is employed to show the IVIF-TODIM-MABAC decision technique. The main contribution of this paper is outlined: (1) the TODIM technique based on MABAC has been extended to IVIFSs based on Entropy technique; (2) the Entropy technique is employed to manage weight based on score values under IVIFSs. (3) the IVIF-TODIM-MABAC technique is founded to manage the MAGDM under IVIFSs; (4) a numerical example for college English teaching quality evaluation and some comparative analysis is supplied to verify the proposed technique.
{"title":"Enhanced decision-making through an intelligent algorithmic approach for multiple-attribute college English teaching quality evaluation with interval-valued intuitionistic fuzzy sets","authors":"Jinxia Huo, Weidong Zhang, Zhenmin Chen","doi":"10.3233/kes-230299","DOIUrl":"https://doi.org/10.3233/kes-230299","url":null,"abstract":"To establish a student-centered teaching quality assurance system in English teaching in universities, it is necessary to establish an educational philosophy of survival based on quality, achieve student-centered learning, optimize the allocation of English teaching resources, and reform evaluation standards; To address the problems in English teaching, we need to raise awareness of the construction of a “student-centered” teaching quality assurance system, carry out “student-centered” teacher training activities, and improve teachers’ professional skills; At the same time, we will establish a student-centered English curriculum system, promote the reform and innovation of teaching models, establish a diversified English teaching evaluation system, and ensure the high efficiency and quality of English teaching in universities. The college English teaching quality evaluation is the MAGDM. Recently, the TODIM and MABAC technique has been employed to manage MAGDM. The interval-valued intuitionistic fuzzy sets (IVIFSs) are employed as a useful tool for portraying uncertain information during the college English teaching quality evaluation. In this paper, the interval-valued intuitionistic fuzzy TODIM-MABAC (IVIF-TODIM-MABAC) technique is built to manage the MAGDM under IVIFSs. At last, the numerical example for college English teaching quality evaluation is employed to show the IVIF-TODIM-MABAC decision technique. The main contribution of this paper is outlined: (1) the TODIM technique based on MABAC has been extended to IVIFSs based on Entropy technique; (2) the Entropy technique is employed to manage weight based on score values under IVIFSs. (3) the IVIF-TODIM-MABAC technique is founded to manage the MAGDM under IVIFSs; (4) a numerical example for college English teaching quality evaluation and some comparative analysis is supplied to verify the proposed technique.","PeriodicalId":44076,"journal":{"name":"International Journal of Knowledge-Based and Intelligent Engineering Systems","volume":null,"pages":null},"PeriodicalIF":0.7,"publicationDate":"2024-01-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140510474","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：