Pub Date : 2022-11-18DOI: 10.1007/s44227-022-00005-2
Yuya Yokoyama, T. Hochin, Hiroki Nomiya
{"title":"Application of 2‑gram and 3‑gram to Obtain Factor Scores of Statements Posted at Q&A Sites","authors":"Yuya Yokoyama, T. Hochin, Hiroki Nomiya","doi":"10.1007/s44227-022-00005-2","DOIUrl":"https://doi.org/10.1007/s44227-022-00005-2","url":null,"abstract":"","PeriodicalId":318936,"journal":{"name":"Int. J. Networked Distributed Comput.","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125543849","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}
Pub Date : 2021-06-01DOI: 10.2991/IJNDC.K.210527.001
Alex A. J. Hoffman, Phillipe Austria, Chol Hyun Park, Yoohwan Kim
The first Bug Bounty Program (BBP) was launched in 1995 by Netscape [2]. The company created the program to discover pre-release software defects in Netscape Navigator, which gave rise to a new paradigm of security research. Other companies and organizations were slow to adopt a similar program at first; however, adoption began to increase in 2002. Organizations either formed their own BBP or joined existing programs from thirdparty providers. Today, BBPs provide a platform for people of all skill-levels to ethically find, report, and get paid for discovering security vulnerabilities.
{"title":"Bountychain: Toward Decentralizing a Bug Bounty Program with Blockchain and IPFS","authors":"Alex A. J. Hoffman, Phillipe Austria, Chol Hyun Park, Yoohwan Kim","doi":"10.2991/IJNDC.K.210527.001","DOIUrl":"https://doi.org/10.2991/IJNDC.K.210527.001","url":null,"abstract":"The first Bug Bounty Program (BBP) was launched in 1995 by Netscape [2]. The company created the program to discover pre-release software defects in Netscape Navigator, which gave rise to a new paradigm of security research. Other companies and organizations were slow to adopt a similar program at first; however, adoption began to increase in 2002. Organizations either formed their own BBP or joined existing programs from thirdparty providers. Today, BBPs provide a platform for people of all skill-levels to ethically find, report, and get paid for discovering security vulnerabilities.","PeriodicalId":318936,"journal":{"name":"Int. J. Networked Distributed Comput.","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115496533","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}
Pub Date : 2020-10-01DOI: 10.2991/ijndc.k.200925.001
Fatima Zohra Mostefa, Zoulikha Mekkakia Maaza, Claude Duvallet
The Intelligent Transport System (ITS) is an important component with a new form of mobile ad hoc network, Vehicular ad hoc Networks (VANET) generate a high interest from governments, universities and private sectors. The communications transiting by a vehicle network and the information on vehicles and their drivers have to be protected and secured in order to guarantee the correct functioning of a ITS. The sensitivity of data conveyed by a VANET network reveals a high need of security. Indeed, the importance of security in this context is crucial given the critical consequences of a violation, misbehavior or an attack. Furthermore, in a very dynamic environment characterized by a nearly instant arrivals and departures of vehicles, the deployment of a security solution has to face constraints and specific configurations. Game theory is a modern branch of intelligent optimization it has been widely applied to model the behavior in a variety of applications.
{"title":"Secure Communications by Tit-for-Tat Strategy in Vehicular Networks","authors":"Fatima Zohra Mostefa, Zoulikha Mekkakia Maaza, Claude Duvallet","doi":"10.2991/ijndc.k.200925.001","DOIUrl":"https://doi.org/10.2991/ijndc.k.200925.001","url":null,"abstract":"The Intelligent Transport System (ITS) is an important component with a new form of mobile ad hoc network, Vehicular ad hoc Networks (VANET) generate a high interest from governments, universities and private sectors. The communications transiting by a vehicle network and the information on vehicles and their drivers have to be protected and secured in order to guarantee the correct functioning of a ITS. The sensitivity of data conveyed by a VANET network reveals a high need of security. Indeed, the importance of security in this context is crucial given the critical consequences of a violation, misbehavior or an attack. Furthermore, in a very dynamic environment characterized by a nearly instant arrivals and departures of vehicles, the deployment of a security solution has to face constraints and specific configurations. Game theory is a modern branch of intelligent optimization it has been widely applied to model the behavior in a variety of applications.","PeriodicalId":318936,"journal":{"name":"Int. J. Networked Distributed Comput.","volume":"274 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116555728","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}
Pub Date : 2020-09-01DOI: 10.2991/ijndc.k.200829.001
Faten Fakhfakh, M. Tounsi, M. Mosbah
The increase in vehicle numbers has resulted in the growth of traffic jams in cities and highways, thereby raising various issues on fuel consumption, environmental pollution, and traffic safety [1]. Platooning is an Intelligent Transport System (ITS) [2] application which has emerged as a promising solution for the traffic management in highways. The main idea of vehicle platooning suggests that a set of vehicles travel together while maintaining a small distance between each other. This can lead to an increase in traffic capacity and then an improved traffic management and a reduced travel time. Moreover, the comfort and the safety of passengers are enhanced since the scenarios of extreme acceleration or deceleration are eliminated and the platoon vehicles are considered as a single unit. Furthermore, the emission performance and the fuel economy are significantly improved. A vehicle platoon (also called “convoy”) can be seen as a group of vehicles that travel in close coordination through a headway control mechanism. These vehicles maintain a short spacing between them and a relative velocity. The vehicle in the front position, called leader, represents the trajectory and velocity reference. It controls all the following vehicles in the platoon. Each vehicle of the platoon receives orders from the leader that may be communicated either directly or by the preceding vehicle.
{"title":"Vehicle Platooning Systems: Review, Classification and Validation Strategies","authors":"Faten Fakhfakh, M. Tounsi, M. Mosbah","doi":"10.2991/ijndc.k.200829.001","DOIUrl":"https://doi.org/10.2991/ijndc.k.200829.001","url":null,"abstract":"The increase in vehicle numbers has resulted in the growth of traffic jams in cities and highways, thereby raising various issues on fuel consumption, environmental pollution, and traffic safety [1]. Platooning is an Intelligent Transport System (ITS) [2] application which has emerged as a promising solution for the traffic management in highways. The main idea of vehicle platooning suggests that a set of vehicles travel together while maintaining a small distance between each other. This can lead to an increase in traffic capacity and then an improved traffic management and a reduced travel time. Moreover, the comfort and the safety of passengers are enhanced since the scenarios of extreme acceleration or deceleration are eliminated and the platoon vehicles are considered as a single unit. Furthermore, the emission performance and the fuel economy are significantly improved. A vehicle platoon (also called “convoy”) can be seen as a group of vehicles that travel in close coordination through a headway control mechanism. These vehicles maintain a short spacing between them and a relative velocity. The vehicle in the front position, called leader, represents the trajectory and velocity reference. It controls all the following vehicles in the platoon. Each vehicle of the platoon receives orders from the leader that may be communicated either directly or by the preceding vehicle.","PeriodicalId":318936,"journal":{"name":"Int. J. Networked Distributed Comput.","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121830763","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}
Pub Date : 2020-08-01DOI: 10.2991/ijndc.k.200804.001
Al Fiad, Zoulikha Mekkakia Maaza, Hayat Bendoukha
Nowadays, operating systems have become more complex and more efficient due to the multitasking functionality, which allows several processes to run simultaneously. The Operating System (OS) chooses a task from the Ready Queue (RQ) and allocates it to a processor, this process is known as scheduling. When several processes are in the RQ, the OS plays an important role in choosing the correct order of execution of the processes for achieving better Average Turnaround Time (ATAT) and Average Waiting Time (AWT). Task scheduling algorithms can also be applied in the cloud-computing environment; it is one of the most important activities in this environment.
{"title":"Improved Version of Round Robin Scheduling Algorithm Based on Analytic Model","authors":"Al Fiad, Zoulikha Mekkakia Maaza, Hayat Bendoukha","doi":"10.2991/ijndc.k.200804.001","DOIUrl":"https://doi.org/10.2991/ijndc.k.200804.001","url":null,"abstract":"Nowadays, operating systems have become more complex and more efficient due to the multitasking functionality, which allows several processes to run simultaneously. The Operating System (OS) chooses a task from the Ready Queue (RQ) and allocates it to a processor, this process is known as scheduling. When several processes are in the RQ, the OS plays an important role in choosing the correct order of execution of the processes for achieving better Average Turnaround Time (ATAT) and Average Waiting Time (AWT). Task scheduling algorithms can also be applied in the cloud-computing environment; it is one of the most important activities in this environment.","PeriodicalId":318936,"journal":{"name":"Int. J. Networked Distributed Comput.","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115526480","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}
Pub Date : 2020-05-01DOI: 10.2991/ijndc.k.200515.001
San Kyaw Zaw, S. Vasupongayya
Nowadays, millions of mobile phone users over the world are put at risk by phishing while more than 3.8 billion smartphones are estimated to be used in 2020 [1]. As a consequence, the security of these devices becomes a top priority. Moreover, mobile devices become the primary means of communication and information access [2]. Thus, in our prior work [3], some analyses on the literatures of phishing detection are performed and identified the important features for the mobile phishing detection. Then, the adaptive mobile phishing detection model is proposed in another prior work [4] by using a Case-based Reasoning (CBR) approach. In our previous work [4], the experiments were conducted to demonstrate the design decision of our proposed model and to verify the performance in handling the concept drift. However, the main challenge faced by the CBR approach is learning a new case in order to adapt the system to a new phishing pattern. The mismatching input features with the existing cases in the case-base was lacking in our prior work [4]. In this work, the incremental learning model for the adaptation to the new examples to the case-base is proposed.
{"title":"Enhancing Case-based Reasoning Approach using Incremental Learning Model for Automatic Adaptation of Classifiers in Mobile Phishing Detection","authors":"San Kyaw Zaw, S. Vasupongayya","doi":"10.2991/ijndc.k.200515.001","DOIUrl":"https://doi.org/10.2991/ijndc.k.200515.001","url":null,"abstract":"Nowadays, millions of mobile phone users over the world are put at risk by phishing while more than 3.8 billion smartphones are estimated to be used in 2020 [1]. As a consequence, the security of these devices becomes a top priority. Moreover, mobile devices become the primary means of communication and information access [2]. Thus, in our prior work [3], some analyses on the literatures of phishing detection are performed and identified the important features for the mobile phishing detection. Then, the adaptive mobile phishing detection model is proposed in another prior work [4] by using a Case-based Reasoning (CBR) approach. In our previous work [4], the experiments were conducted to demonstrate the design decision of our proposed model and to verify the performance in handling the concept drift. However, the main challenge faced by the CBR approach is learning a new case in order to adapt the system to a new phishing pattern. The mismatching input features with the existing cases in the case-base was lacking in our prior work [4]. In this work, the incremental learning model for the adaptation to the new examples to the case-base is proposed.","PeriodicalId":318936,"journal":{"name":"Int. J. Networked Distributed Comput.","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132412124","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}
Pub Date : 2020-05-01DOI: 10.2991/ijndc.k.200515.005
Zhenping Xie, Kun Wang, Yuan Liu
Knowledge graph is firstly put forward by Google in 2012 [1], which uses graph structure to represent knowledge information on conceptual items. In knowledge graph, each graph node denotes a knowledge concept, and edges equipped with labels represent semantic relations among knowledge nodes. Knowledge graph is a very useful tool to represent and store the information in natural language text, and has been widely and successively applied to natural translation [2], question-answer system [3], and natural language understanding [4].
{"title":"On Learning Associative Relationship Memory among Knowledge Concepts","authors":"Zhenping Xie, Kun Wang, Yuan Liu","doi":"10.2991/ijndc.k.200515.005","DOIUrl":"https://doi.org/10.2991/ijndc.k.200515.005","url":null,"abstract":"Knowledge graph is firstly put forward by Google in 2012 [1], which uses graph structure to represent knowledge information on conceptual items. In knowledge graph, each graph node denotes a knowledge concept, and edges equipped with labels represent semantic relations among knowledge nodes. Knowledge graph is a very useful tool to represent and store the information in natural language text, and has been widely and successively applied to natural translation [2], question-answer system [3], and natural language understanding [4].","PeriodicalId":318936,"journal":{"name":"Int. J. Networked Distributed Comput.","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132097586","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}
Pub Date : 2020-05-01DOI: 10.2991/ijndc.k.200515.002
T. Thwin, S. Vasupongayya
The privacy and trust of Personal Health Record (PHR) system [1,2] are improved by applying the blockchain technology, in our prior works [3]. The issues that affect the use of blockchain in the PHR development were introduced and addressed with an existing private blockchain and cryptographic mechanisms in our prior work [4]. However, the usability evaluation is still lacking in our previous work [4]. Only the achievement of the privacy and the security as well as the effectiveness of the proposed blockchainbased PHR system was shown. Since, the performance is a concern for the use of blockchain for the PHR development, the usability of the proposed blockchain-based PHR system must be addressed. For that reason, the performance analysis is conducted in this work.
个人健康记录(Personal Health Record, PHR)系统[1,2]通过应用区块链技术提高了隐私性和信任度，在我们之前的工作[3]中。在我们之前的工作[4]中介绍了影响PHR开发中使用区块链的问题，并使用现有的私有区块链和加密机制解决了这些问题。然而，可用性评估在我们之前的工作中仍然缺乏。本文仅展示了所提出的基于区块链的PHR系统在隐私和安全方面的成就以及有效性。由于性能是使用区块链进行PHR开发的一个问题，因此必须解决拟议的基于区块链的PHR系统的可用性。因此，在本工作中进行性能分析。
{"title":"Performance Analysis of Blockchain-based Access Control Model for Personal Health Record System with Architectural Modelling and Simulation","authors":"T. Thwin, S. Vasupongayya","doi":"10.2991/ijndc.k.200515.002","DOIUrl":"https://doi.org/10.2991/ijndc.k.200515.002","url":null,"abstract":"The privacy and trust of Personal Health Record (PHR) system [1,2] are improved by applying the blockchain technology, in our prior works [3]. The issues that affect the use of blockchain in the PHR development were introduced and addressed with an existing private blockchain and cryptographic mechanisms in our prior work [4]. However, the usability evaluation is still lacking in our previous work [4]. Only the achievement of the privacy and the security as well as the effectiveness of the proposed blockchainbased PHR system was shown. Since, the performance is a concern for the use of blockchain for the PHR development, the usability of the proposed blockchain-based PHR system must be addressed. For that reason, the performance analysis is conducted in this work.","PeriodicalId":318936,"journal":{"name":"Int. J. Networked Distributed Comput.","volume":"44 5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123961782","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}
Pub Date : 2020-05-01DOI: 10.2991/ijndc.k.200515.004
Yuan Liu, Wen Zhang, Qi Yuan, Jie Zhang
question: What are the symptoms of nm getting nd? In the above example, the pet’s proper nouns, such as golden retriever, which are involved in the natural language question of the user, will be converted into the golden retriever’s part of speech nm after the entity similarity calculation, and the shift is transformed into the distemper word nf instead. The advantage of this is that it can reduce the selection workload of the naive Bayesian classifier feature. Additionally, because there is no special dataset in the pet field, the workload of building the dataset can be reduced, and the required training set can be reduced in size. The specific conversion is shown in Table 8. 3.8. Text Classification Based on Multiple Naive Bayes This article requires multiple classifications of pet text datasets. At present, there are many machine learning and deep learning Y. Liu et al. / International Journal of Networked and Distributed Computing 8(3) 162–170 169 Table 8 | Rule conversion table Conversion rule User problem Abstract problem Pet breed name — nm Golden retriever price Price of nm Pet disease name — nd What are the symptoms of golden retrievers? What is the symptom of nm? Pet food — nf Can golden retriever eat grapes? Can nm eat nf? algorithms that can perform multi-classification of texts. Multiple naive Bayes have stable classification efficiency and good performance for small-scale data and multi-classification. Because there are very few corpora in the pet field, the size of the corpus built in this paper is also very small, so this paper adopts a naive Bayesian text classifier based on polynomials. Based on the knowledge of pet knowledge maps, a total of 24 categories are constructed according to the pet breed, pet disease and pet food attributes. The user’s natural language question will match one of the 24 categories after multidirectional naive Bayes classification as the classification results. 3.9. Matching Word Sequence Diagram Through the classification result of the text quantifier based on multiple naive Bayes, the labels of the categories corresponding to the natural language problem of the user, such as weight, price, and main symptoms, are obtained, which are labels corresponding to the user problem and correspond to natural language questions. Then, the determined intention tag maps the corresponding question template, matching the word order graph in the template. The natural language question basically describes the relationship between the subject and the object, while the graph model can describe the relationship between the node and the node through the edge. The word map is a directed graph, the subject points to the object, and the predicate is used as an edge. In directed graphs, subjects and objects are entities, and predicates are relationships between entities, including attribute relationships. For example, what are the symptoms of a golden retriever with canine distemper? The conversion into a word sequence diagram
问题:得了糖尿病的症状是什么?在上面的例子中，涉及到用户自然语言问题的宠物专有名词，如金毛寻回犬，经过实体相似度计算后，会被转换成金毛寻回犬的词性nm，而平移后会被转换成犬瘟词nf。这样做的好处是可以减少朴素贝叶斯分类器特征的选择工作量。此外，由于宠物领域没有特殊的数据集，可以减少构建数据集的工作量，并且可以减少所需的训练集的大小。具体的转换如表8所示。3.8. 基于多重朴素贝叶斯的文本分类本文需要对宠物文本数据集进行多重分类。目前有很多机器学习和深度学习Y. Liu et al. / International Journal of Networked and Distributed Computing 8(3) 162-170 169表8 |规则转换表转换规则用户问题抽象问题宠物品种名称- nm金毛猎犬价格nm宠物疾病名称-和金毛猎犬的症状是什么?nm的症状是什么?宠物食品——金毛猎犬能吃葡萄吗?我能吃nf吗?可以对文本进行多重分类的算法。对于小规模数据和多分类，多重朴素贝叶斯具有稳定的分类效率和良好的分类性能。由于pet领域的语料库非常少，因此本文构建的语料库规模也很小，因此本文采用基于多项式的朴素贝叶斯文本分类器。基于宠物知识图谱的知识，根据宠物品种、宠物疾病和宠物食品属性共构建了24个类别。用户的自然语言问题将匹配多向朴素贝叶斯分类后的24个类别中的一个作为分类结果。3.9. 通过基于多个朴素贝叶斯的文本量词分类结果，得到用户自然语言问题对应的类别标签，如权重、价格、主要症状等，即为用户问题对应的标签，对应于自然语言问题。然后，确定的意图标签映射到相应的问题模板上，匹配模板中的词序图。自然语言问题基本上描述了主体与客体之间的关系，而图模型可以通过边缘来描述节点与节点之间的关系。单词映射是一个有向图，主题指向对象，谓词用作边缘。在有向图中，主题和对象是实体，谓词是实体之间的关系，包括属性关系。例如，金毛猎犬患犬瘟热的症状是什么?到字序列图的转换如图6所示。本文为三大类共24类问题构建了一个模板。问题模板示例如表9所示。3.10. 宠物知识图谱存储在图形数据库OrientDB中。本文将单词地图转换为OrientDB的SQL查询语句，将答案存储在存储知识地图的图形数据库OrientDB中，并将问题的答案返回给用户。基于宠物知识地图的自动问答系统支持宠物的来源、价格、智商、疾病概述、症状、预防等问题，可以回答三个问题。图6 |一个词地图示例。表9 |问题模板示例问题类型问题模板价格Nm价格Nm患病主要症状可食用Nm可食用图7 |一只金毛猎犬的价格主要问题。如图7所示，答案是宠物品种属性的问题，例如金毛猎犬的价格。
{"title":"Research on Intelligent Question and Answering Based on a Pet Knowledge Map","authors":"Yuan Liu, Wen Zhang, Qi Yuan, Jie Zhang","doi":"10.2991/ijndc.k.200515.004","DOIUrl":"https://doi.org/10.2991/ijndc.k.200515.004","url":null,"abstract":"question: What are the symptoms of nm getting nd? In the above example, the pet’s proper nouns, such as golden retriever, which are involved in the natural language question of the user, will be converted into the golden retriever’s part of speech nm after the entity similarity calculation, and the shift is transformed into the distemper word nf instead. The advantage of this is that it can reduce the selection workload of the naive Bayesian classifier feature. Additionally, because there is no special dataset in the pet field, the workload of building the dataset can be reduced, and the required training set can be reduced in size. The specific conversion is shown in Table 8. 3.8. Text Classification Based on Multiple Naive Bayes This article requires multiple classifications of pet text datasets. At present, there are many machine learning and deep learning Y. Liu et al. / International Journal of Networked and Distributed Computing 8(3) 162–170 169 Table 8 | Rule conversion table Conversion rule User problem Abstract problem Pet breed name — nm Golden retriever price Price of nm Pet disease name — nd What are the symptoms of golden retrievers? What is the symptom of nm? Pet food — nf Can golden retriever eat grapes? Can nm eat nf? algorithms that can perform multi-classification of texts. Multiple naive Bayes have stable classification efficiency and good performance for small-scale data and multi-classification. Because there are very few corpora in the pet field, the size of the corpus built in this paper is also very small, so this paper adopts a naive Bayesian text classifier based on polynomials. Based on the knowledge of pet knowledge maps, a total of 24 categories are constructed according to the pet breed, pet disease and pet food attributes. The user’s natural language question will match one of the 24 categories after multidirectional naive Bayes classification as the classification results. 3.9. Matching Word Sequence Diagram Through the classification result of the text quantifier based on multiple naive Bayes, the labels of the categories corresponding to the natural language problem of the user, such as weight, price, and main symptoms, are obtained, which are labels corresponding to the user problem and correspond to natural language questions. Then, the determined intention tag maps the corresponding question template, matching the word order graph in the template. The natural language question basically describes the relationship between the subject and the object, while the graph model can describe the relationship between the node and the node through the edge. The word map is a directed graph, the subject points to the object, and the predicate is used as an edge. In directed graphs, subjects and objects are entities, and predicates are relationships between entities, including attribute relationships. For example, what are the symptoms of a golden retriever with canine distemper? The conversion into a word sequence diagram","PeriodicalId":318936,"journal":{"name":"Int. J. Networked Distributed Comput.","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134304981","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：