{"title":"Proceedings of the 2021 6th International Conference on Intelligent Information Technology","authors":"","doi":"10.1145/3460179","DOIUrl":"https://doi.org/10.1145/3460179","url":null,"abstract":"","PeriodicalId":193744,"journal":{"name":"Proceedings of the 2021 6th International Conference on Intelligent Information Technology","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129629112","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}
At present, the implementation of the database is more concerned in this field, among which the main query processing is the key and the difficulty, therefore, this paper optimizes the query system, and analyzes the optimization strategy of data query combined with genetic algorithm and real-time data rule.
{"title":"Research on Data Query Optimization based on Genetic Algorithm","authors":"Fen Li","doi":"10.1145/3460179.3460182","DOIUrl":"https://doi.org/10.1145/3460179.3460182","url":null,"abstract":"At present, the implementation of the database is more concerned in this field, among which the main query processing is the key and the difficulty, therefore, this paper optimizes the query system, and analyzes the optimization strategy of data query combined with genetic algorithm and real-time data rule.","PeriodicalId":193744,"journal":{"name":"Proceedings of the 2021 6th International Conference on Intelligent Information Technology","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115525275","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}
Knowledge graph representation learning models are mostly used for static data. When the data changes, the models cannot be adjusted dynamically as the data changes. The data is constantly changing in actual usage scenarios. However, most representation learning models focus on prediction accuracy and ignore the dynamic change of knowledge graph. A trained representation learning model is closed, but the facts in the real world are constantly changing. The knowledge graph of the real world should be open to realize the description of reality. This paper proposes a dynamic adaptive chain transfer model aim to deal with changing knowledge graph data. Our model realizes the dynamic increase and decrease of triples without retraining. We designed an experimental method to verify the validity of the model. Experimental results show that our model can achieve dynamic data changes and keep the performance of the original model.
{"title":"Dynamic Adaptive Chain Model of Knowledge Graph Representation Learning","authors":"Jinkui Yao, Yulong Zhao, Song Lu","doi":"10.1145/3460179.3460194","DOIUrl":"https://doi.org/10.1145/3460179.3460194","url":null,"abstract":"Knowledge graph representation learning models are mostly used for static data. When the data changes, the models cannot be adjusted dynamically as the data changes. The data is constantly changing in actual usage scenarios. However, most representation learning models focus on prediction accuracy and ignore the dynamic change of knowledge graph. A trained representation learning model is closed, but the facts in the real world are constantly changing. The knowledge graph of the real world should be open to realize the description of reality. This paper proposes a dynamic adaptive chain transfer model aim to deal with changing knowledge graph data. Our model realizes the dynamic increase and decrease of triples without retraining. We designed an experimental method to verify the validity of the model. Experimental results show that our model can achieve dynamic data changes and keep the performance of the original model.","PeriodicalId":193744,"journal":{"name":"Proceedings of the 2021 6th International Conference on Intelligent Information Technology","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130602859","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}
Nowadays, with the rapid development of various fields of e-commerce, scholars gradually focus their research on the online purchase behavior of users. As we step into the era of big data, personalized recommendation function of e-commerce is rising. Many scholars have put forward their own views on the influence of personalized recommendation of platform on users' purchase intention. This study will start from the recommendation behavior of products, take recommendation strength and recommendation validity as the quantitative methods of recommendation behavior, and explore whether platform recommendation and friend recommendation will have different influences on users' purchase intention. In the process of the influence of recommendation behavior on the purchase intention of users, this study believes that trust plays a mediating role. This research applies the knowledge and methods of social psychology, consumer behavior and other disciplines, adopts a multi-dimensional research framework in terms of overall research ideas, and combines theoretical analysis with empirical research. The results show that trust can indeed play a mediating role in the influence of recommendation strength and recommendation validity on users' purchase intention, but recommendation style has no moderating effect on the influence. In view of this conclusion, this paper proposes the possible reasons.
{"title":"The Influence of Product Recommendation Methods on Users' Purchase Intention","authors":"Xinyue Wang, Jianxin You, Qiurong Song","doi":"10.1145/3460179.3460195","DOIUrl":"https://doi.org/10.1145/3460179.3460195","url":null,"abstract":"Nowadays, with the rapid development of various fields of e-commerce, scholars gradually focus their research on the online purchase behavior of users. As we step into the era of big data, personalized recommendation function of e-commerce is rising. Many scholars have put forward their own views on the influence of personalized recommendation of platform on users' purchase intention. This study will start from the recommendation behavior of products, take recommendation strength and recommendation validity as the quantitative methods of recommendation behavior, and explore whether platform recommendation and friend recommendation will have different influences on users' purchase intention. In the process of the influence of recommendation behavior on the purchase intention of users, this study believes that trust plays a mediating role. This research applies the knowledge and methods of social psychology, consumer behavior and other disciplines, adopts a multi-dimensional research framework in terms of overall research ideas, and combines theoretical analysis with empirical research. The results show that trust can indeed play a mediating role in the influence of recommendation strength and recommendation validity on users' purchase intention, but recommendation style has no moderating effect on the influence. In view of this conclusion, this paper proposes the possible reasons.","PeriodicalId":193744,"journal":{"name":"Proceedings of the 2021 6th International Conference on Intelligent Information Technology","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122821835","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 growing use of credit cards, credit fraud becomes a major issue in the finance business. Billions of dollars of loss are caused every year by fraudulent credit card transactions. The best strategy in estimate the loss and detecting fraud situation remains unanswered since public data are scarcely available for confidentiality issues and companies constantly do not disclose the amount of losses due to frauds. Another problem in credit card fraud detection is that the fraud patterns are changing rapidly. This requires fraud detection to be re-evaluated from a reactive to a proactive approach. At the same time, intense interest in applying machine learning in module detection and analysis is widespread. In this regard, the implementation of efficient fraud detection algorithms using machine-learning techniques is key to reduce these losses, and to assist fraud investigators. This article aims to provide some answers by focusing on crucial issues in solving detection in credit card fraud: 1) How to deal with the imbalance in the database by applying SMOTE, Adaptive Synthetic Sampling (ADASYN)Borderline-SMOTE in sampling the data. 2) Random forest, gradient boosting, Logistic Regression,and XGboost are applied to the current public database on credit card and which machine learning method can achieve higher accuracy in the prediction model.
{"title":"Analysis of Best Sampling Strategy in Credit Card Fraud Detection Using Machine Learning","authors":"Hanbin Zou","doi":"10.1145/3460179.3460186","DOIUrl":"https://doi.org/10.1145/3460179.3460186","url":null,"abstract":"∗With the growing use of credit cards, credit fraud becomes a major issue in the finance business. Billions of dollars of loss are caused every year by fraudulent credit card transactions. The best strategy in estimate the loss and detecting fraud situation remains unanswered since public data are scarcely available for confidentiality issues and companies constantly do not disclose the amount of losses due to frauds. Another problem in credit card fraud detection is that the fraud patterns are changing rapidly. This requires fraud detection to be re-evaluated from a reactive to a proactive approach. At the same time, intense interest in applying machine learning in module detection and analysis is widespread. In this regard, the implementation of efficient fraud detection algorithms using machine-learning techniques is key to reduce these losses, and to assist fraud investigators. This article aims to provide some answers by focusing on crucial issues in solving detection in credit card fraud: 1) How to deal with the imbalance in the database by applying SMOTE, Adaptive Synthetic Sampling (ADASYN)Borderline-SMOTE in sampling the data. 2) Random forest, gradient boosting, Logistic Regression,and XGboost are applied to the current public database on credit card and which machine learning method can achieve higher accuracy in the prediction model.","PeriodicalId":193744,"journal":{"name":"Proceedings of the 2021 6th International Conference on Intelligent Information Technology","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123147369","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}
Internet of Things (IoT) is becoming a promising area to support communication of all type of devices. Blockchain aids to ensure higher security in this field, but the increase in ubiquitous connectivity leads to increase load and hence it requires a perfect search for the nodes. This paper addresses the issue by the design of a three tier P2p fog-IoT architecture using distributed blockchain. The tier-1 employs an authenticator responsible to authenticate IoT nodes with identity, IP address and physical unclonable function (PUF). To balance IoT nodes request, super peers are dynamically selected from multi-criteria ranking based optimal points (MC-RBOP). Further the requests are forwarded to blockchain present in tier-3. In tier-3 the Master node performs storage and searching. Due to the possibility of redundant data storage, Jaro-Winkler measures a similarity in the data before storing it. An Adaptive Chord with fuzzy neural (AC-FNN) is incorporated to search the lightweight U-QUARK algorithm-based hash key-values in the directory. The design of fog-IoT with new chord algorithm is implemented in network simulator-3 and the results are evaluated in terms of latency, response time, blockchain size and network usage.
{"title":"Scalable Peer-to-Peer Fog Computing Integrated to a Fast-Searching Distributed Blockchain System","authors":"Michael Omar, Doan Tung Trung","doi":"10.1145/3460179.3460185","DOIUrl":"https://doi.org/10.1145/3460179.3460185","url":null,"abstract":"Internet of Things (IoT) is becoming a promising area to support communication of all type of devices. Blockchain aids to ensure higher security in this field, but the increase in ubiquitous connectivity leads to increase load and hence it requires a perfect search for the nodes. This paper addresses the issue by the design of a three tier P2p fog-IoT architecture using distributed blockchain. The tier-1 employs an authenticator responsible to authenticate IoT nodes with identity, IP address and physical unclonable function (PUF). To balance IoT nodes request, super peers are dynamically selected from multi-criteria ranking based optimal points (MC-RBOP). Further the requests are forwarded to blockchain present in tier-3. In tier-3 the Master node performs storage and searching. Due to the possibility of redundant data storage, Jaro-Winkler measures a similarity in the data before storing it. An Adaptive Chord with fuzzy neural (AC-FNN) is incorporated to search the lightweight U-QUARK algorithm-based hash key-values in the directory. The design of fog-IoT with new chord algorithm is implemented in network simulator-3 and the results are evaluated in terms of latency, response time, blockchain size and network usage.","PeriodicalId":193744,"journal":{"name":"Proceedings of the 2021 6th International Conference on Intelligent Information Technology","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129292078","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}
Pornpote Nusen, Pratch Piyawongwisal, Sunita Nusen, M. Kaewmoracharoen
This paper compared optimizing resource utilization using Genetic Algorithm (GA) based on variation of resource fluctuation moment (Mx) for extra-large building renovation. The Mx variable, as determined by resource demand on day squared, has a large effect on the result of multi-objective optimization. In this research, an Mx-based optimization model targeting five variables for resource utilization was proposed. In addition, the proposed method is flexible in that the construction planners could specify predecessors or preferences for optional construction sequences so that a more efficient optimal scheduling may be obtained. Three activation functions for Mx were considered, namely Mx, and Mx /1000. In this work, the models in consideration were applied to real data from the university main library building renovation projects which consisted of 251 activities. The contractor's work plan was used as the initial scheduling for the optimization process. When comparing the experimental results from all 3 models, it can be seen that the form and Mx/1000 are more suitable in optimizing resource utilization through GA method in extra-large building renovation.
{"title":"Resource Utilization Optimization using Genetic Algorithm based on Variation of Resource Fluctuation Moment for Extra-Large Building Renovation","authors":"Pornpote Nusen, Pratch Piyawongwisal, Sunita Nusen, M. Kaewmoracharoen","doi":"10.1145/3460179.3460183","DOIUrl":"https://doi.org/10.1145/3460179.3460183","url":null,"abstract":"This paper compared optimizing resource utilization using Genetic Algorithm (GA) based on variation of resource fluctuation moment (Mx) for extra-large building renovation. The Mx variable, as determined by resource demand on day squared, has a large effect on the result of multi-objective optimization. In this research, an Mx-based optimization model targeting five variables for resource utilization was proposed. In addition, the proposed method is flexible in that the construction planners could specify predecessors or preferences for optional construction sequences so that a more efficient optimal scheduling may be obtained. Three activation functions for Mx were considered, namely Mx, and Mx /1000. In this work, the models in consideration were applied to real data from the university main library building renovation projects which consisted of 251 activities. The contractor's work plan was used as the initial scheduling for the optimization process. When comparing the experimental results from all 3 models, it can be seen that the form and Mx/1000 are more suitable in optimizing resource utilization through GA method in extra-large building renovation.","PeriodicalId":193744,"journal":{"name":"Proceedings of the 2021 6th International Conference on Intelligent Information Technology","volume":"110 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116035406","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}
Saurabh Pal, Pijush Kanti Dutta Pramanik, A. Nayyar, Prasenjit Choudhury
The traditional e-learning has been developed into personalised and ubiquitous learning, in which the learners find learning materials (LMs) that are suitable to their contextual requirements, and can access them from anywhere and anytime. In this paper, we propose a framework for a personalised recommendation in a ubiquitous learning platform, following a knowledge-based approach. The framework comprises modules like query processing, information storage and retrieval, and learner context mapping and reasoning. Learner's implicit and explicit contexts are used for assessing the preference and suitability and mapping with the LMs that are retrieved based on the learner's query analysis, with the help of educational metadata. Selecting suitable LMs based on different factors is a multi-criteria decision making (MCDM) problem. For prioritising the selection factors, we use SWARA, and for multi-objective decision making, we apply MOORA. Utilising these two techniques, the LMs are ranked and are recommended accordingly.
{"title":"A Personalised Recommendation Framework for Ubiquitous Learning System","authors":"Saurabh Pal, Pijush Kanti Dutta Pramanik, A. Nayyar, Prasenjit Choudhury","doi":"10.1145/3460179.3460190","DOIUrl":"https://doi.org/10.1145/3460179.3460190","url":null,"abstract":"The traditional e-learning has been developed into personalised and ubiquitous learning, in which the learners find learning materials (LMs) that are suitable to their contextual requirements, and can access them from anywhere and anytime. In this paper, we propose a framework for a personalised recommendation in a ubiquitous learning platform, following a knowledge-based approach. The framework comprises modules like query processing, information storage and retrieval, and learner context mapping and reasoning. Learner's implicit and explicit contexts are used for assessing the preference and suitability and mapping with the LMs that are retrieved based on the learner's query analysis, with the help of educational metadata. Selecting suitable LMs based on different factors is a multi-criteria decision making (MCDM) problem. For prioritising the selection factors, we use SWARA, and for multi-objective decision making, we apply MOORA. Utilising these two techniques, the LMs are ranked and are recommended accordingly.","PeriodicalId":193744,"journal":{"name":"Proceedings of the 2021 6th International Conference on Intelligent Information Technology","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114958662","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 order to accurately estimate the sports injury risk of athletes during sports training, this paper divides the sports injury risk into three levels, designs the sports injury estimation index, selects RBF neural network as the model framework, and uses big data analysis technology to construct the sports injury estimation model. Bayesian model and Lagrange model are selected as the control group to test the accuracy and efficiency of this model in sports injury estimation. The test results show that compared with other models, this model can improve the accuracy and efficiency of sports injury estimation significantly, and can be used as a sports injury estimation tool.
{"title":"Research on the Design of Sports Injury Estimation Model based on Big Data","authors":"Y. Dai","doi":"10.1145/3460179.3460180","DOIUrl":"https://doi.org/10.1145/3460179.3460180","url":null,"abstract":"In order to accurately estimate the sports injury risk of athletes during sports training, this paper divides the sports injury risk into three levels, designs the sports injury estimation index, selects RBF neural network as the model framework, and uses big data analysis technology to construct the sports injury estimation model. Bayesian model and Lagrange model are selected as the control group to test the accuracy and efficiency of this model in sports injury estimation. The test results show that compared with other models, this model can improve the accuracy and efficiency of sports injury estimation significantly, and can be used as a sports injury estimation tool.","PeriodicalId":193744,"journal":{"name":"Proceedings of the 2021 6th International Conference on Intelligent Information Technology","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131417715","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}
Yunnan-Vietnam Railway is a well-known cultural route connecting rich cultural and landscape heritages in China, whose whole heritage system includes not only the physical remains related to the railway history but also the other movable heritages, such as the historical images left during its construction process. This paper aims to briefly summarize the characteristics of historical GIS and the possibility of constructing a historical database with the help of PostgreSQL and GIS tools. The sources of the existing historical images of the Yunnan-Vietnam Railway are discussed. Then, those photographic works left by three related railway workers have historical, social, and heritage meanings, which are the evidence of the historical changes of Yunnan. Thus, these photos in the archive and other geographic data are collected and utilized to construct a geo-historical database to realize further spatial analysis, such as the footprints map of historical figures. Further research and applications can be fulfilled based on this built geo-historical database.
{"title":"A Geo-Historical Database for the Historical Photos of Yunnan-Vietnam Railway in China","authors":"Kun Sang, Guiye Lin, S. Piovan","doi":"10.1145/3460179.3460193","DOIUrl":"https://doi.org/10.1145/3460179.3460193","url":null,"abstract":"Yunnan-Vietnam Railway is a well-known cultural route connecting rich cultural and landscape heritages in China, whose whole heritage system includes not only the physical remains related to the railway history but also the other movable heritages, such as the historical images left during its construction process. This paper aims to briefly summarize the characteristics of historical GIS and the possibility of constructing a historical database with the help of PostgreSQL and GIS tools. The sources of the existing historical images of the Yunnan-Vietnam Railway are discussed. Then, those photographic works left by three related railway workers have historical, social, and heritage meanings, which are the evidence of the historical changes of Yunnan. Thus, these photos in the archive and other geographic data are collected and utilized to construct a geo-historical database to realize further spatial analysis, such as the footprints map of historical figures. Further research and applications can be fulfilled based on this built geo-historical database.","PeriodicalId":193744,"journal":{"name":"Proceedings of the 2021 6th International Conference on Intelligent Information Technology","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133349048","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：