Pub Date : 2020-12-14DOI: 10.1109/IEEM45057.2020.9309919
Jiage Huo, K. L. Keung, C. K. M. Lee, K. Ng, K. C. Li
Nowadays, Hong Kong International Airport faces the issues of saturation and overload. The difficulties of selecting taxiways and reducing the lead time at the runway holding position are the severe consequences that appeared from increasing the number of passengers and increased cargo movement to Hong Kong International Airport but without constructing a new runway. This paper is primarily about predicting flight delays by using machine learning methodologies. The prediction results of several machine learning approaches are compared and analyzed thoroughly by using real data from the Hong Kong International Airport. The findings and recommendations from this paper are valuable to the aviation and insurance industries. Better planning of the airport system can be established through predicting flight delays.
{"title":"The Prediction of Flight Delay: Big Data-driven Machine Learning Approach","authors":"Jiage Huo, K. L. Keung, C. K. M. Lee, K. Ng, K. C. Li","doi":"10.1109/IEEM45057.2020.9309919","DOIUrl":"https://doi.org/10.1109/IEEM45057.2020.9309919","url":null,"abstract":"Nowadays, Hong Kong International Airport faces the issues of saturation and overload. The difficulties of selecting taxiways and reducing the lead time at the runway holding position are the severe consequences that appeared from increasing the number of passengers and increased cargo movement to Hong Kong International Airport but without constructing a new runway. This paper is primarily about predicting flight delays by using machine learning methodologies. The prediction results of several machine learning approaches are compared and analyzed thoroughly by using real data from the Hong Kong International Airport. The findings and recommendations from this paper are valuable to the aviation and insurance industries. Better planning of the airport system can be established through predicting flight delays.","PeriodicalId":226426,"journal":{"name":"2020 IEEE International Conference on Industrial Engineering and Engineering Management (IEEM)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122874072","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 : 2020-12-14DOI: 10.1109/IEEM45057.2020.9309941
G. Hass, Parker Simon, R. Kashef
"The world's most valuable resource is no longer oil, but data" announces the headline of the May 6th, 2017 edition of The Economist; the digital revolution is here to stay. The primary currency of this movement is big data. The complexity of big data is defined as the relationships and how the data can be arranged with one another. Facebook has 30 billion pieces of unique information shared each month; this data's sheer size can cause an immeasurable amount of combinations for relational data. Analyzing this big data can reveal various useful insights for decision-makers. With the adoption of clustering analysis, patterns and hidden information can be developed from big raw data that can be used across many business problems and applications. In this paper, an overview of the state of the art of clustering analysis and its adoption in business applications in the era of big data is presented.
{"title":"Business Applications for Current Developments in Big Data Clustering: An Overview","authors":"G. Hass, Parker Simon, R. Kashef","doi":"10.1109/IEEM45057.2020.9309941","DOIUrl":"https://doi.org/10.1109/IEEM45057.2020.9309941","url":null,"abstract":"\"The world's most valuable resource is no longer oil, but data\" announces the headline of the May 6th, 2017 edition of The Economist; the digital revolution is here to stay. The primary currency of this movement is big data. The complexity of big data is defined as the relationships and how the data can be arranged with one another. Facebook has 30 billion pieces of unique information shared each month; this data's sheer size can cause an immeasurable amount of combinations for relational data. Analyzing this big data can reveal various useful insights for decision-makers. With the adoption of clustering analysis, patterns and hidden information can be developed from big raw data that can be used across many business problems and applications. In this paper, an overview of the state of the art of clustering analysis and its adoption in business applications in the era of big data is presented.","PeriodicalId":226426,"journal":{"name":"2020 IEEE International Conference on Industrial Engineering and Engineering Management (IEEM)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131266149","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 : 2020-12-14DOI: 10.1109/IEEM45057.2020.9309745
Matteo Perno, L. Hvam, Anders Haug
Since its first introduction in 2002, the interest in the concept of "Digital Twins" has grown exponentially among researchers and industry practitioners. An increasing number of Digital Twin implementations are made in many industries. Given the novelty of the concept, companies from any industry type face significant challenges when implementing Digital Twins. Furthermore, only little research has been conducted in the process industry, which may be explained by the high complexity of representing and modeling the physics behind the production processes in an accurate manner. This study aims at filling this gap by providing a clear categorization of the main barriers that process companies face when implementing Digital Twins of their assets, as well as the key enabling factors and technologies that can be leveraged to overcome such challenges. Furthermore, a model based on the findings from the literature study is proposed. The results indicate a dearth in the literature focused on the process industry, therefore, key learnings from other industry sectors are gathered, and suggestions for further research are proposed.
{"title":"Enablers and Barriers to the Implementation of Digital Twins in the Process Industry: A Systematic Literature Review","authors":"Matteo Perno, L. Hvam, Anders Haug","doi":"10.1109/IEEM45057.2020.9309745","DOIUrl":"https://doi.org/10.1109/IEEM45057.2020.9309745","url":null,"abstract":"Since its first introduction in 2002, the interest in the concept of \"Digital Twins\" has grown exponentially among researchers and industry practitioners. An increasing number of Digital Twin implementations are made in many industries. Given the novelty of the concept, companies from any industry type face significant challenges when implementing Digital Twins. Furthermore, only little research has been conducted in the process industry, which may be explained by the high complexity of representing and modeling the physics behind the production processes in an accurate manner. This study aims at filling this gap by providing a clear categorization of the main barriers that process companies face when implementing Digital Twins of their assets, as well as the key enabling factors and technologies that can be leveraged to overcome such challenges. Furthermore, a model based on the findings from the literature study is proposed. The results indicate a dearth in the literature focused on the process industry, therefore, key learnings from other industry sectors are gathered, and suggestions for further research are proposed.","PeriodicalId":226426,"journal":{"name":"2020 IEEE International Conference on Industrial Engineering and Engineering Management (IEEM)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121276466","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 : 2020-12-14DOI: 10.1109/IEEM45057.2020.9309981
Xiaonan Wang, P. Guo, Ding Wang
An evolutionary game model of knowledge transfer in inter-organizational R&D projects was established, and its local stability was analyzed. Then, the complex network and preference theory are introduced to establish the game model of knowledge transfer in the cooperation network of inter-organizational R&D projects under the condition of preference differences and different network structures. Finally, the influence of key factors, preference difference and network structures on strategy selection is analyzed. The results show that the cost coefficient has a negative correlation with the level of knowledge transfer, while the increase of other coefficients promote knowledge transfer behavior. The increase of altruistic preference degree and the proportion of altruistic preference agents can promote knowledge transfer behavior, while the increase of competitive preference degree and the proportion of competitive preference agents can inhibit knowledge transfer behavior. Moreover, the level of knowledge transfer is higher in the scale-free network than in the small-world network in most cases. However, punishment plays a greater role in the small-world network.
{"title":"Effect of Network Structure and Preference Difference on Knowledge Transfer in Inter-organizational R&D Project","authors":"Xiaonan Wang, P. Guo, Ding Wang","doi":"10.1109/IEEM45057.2020.9309981","DOIUrl":"https://doi.org/10.1109/IEEM45057.2020.9309981","url":null,"abstract":"An evolutionary game model of knowledge transfer in inter-organizational R&D projects was established, and its local stability was analyzed. Then, the complex network and preference theory are introduced to establish the game model of knowledge transfer in the cooperation network of inter-organizational R&D projects under the condition of preference differences and different network structures. Finally, the influence of key factors, preference difference and network structures on strategy selection is analyzed. The results show that the cost coefficient has a negative correlation with the level of knowledge transfer, while the increase of other coefficients promote knowledge transfer behavior. The increase of altruistic preference degree and the proportion of altruistic preference agents can promote knowledge transfer behavior, while the increase of competitive preference degree and the proportion of competitive preference agents can inhibit knowledge transfer behavior. Moreover, the level of knowledge transfer is higher in the scale-free network than in the small-world network in most cases. However, punishment plays a greater role in the small-world network.","PeriodicalId":226426,"journal":{"name":"2020 IEEE International Conference on Industrial Engineering and Engineering Management (IEEM)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133954586","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 : 2020-12-14DOI: 10.1109/IEEM45057.2020.9309953
A. Protic, Ziyue Jin, R. Marian, K. Abd, D. Campbell, J. Chahl
With the increased demands of smarter manufacturing approaches around the world, the process of industrial digital transformation is being pushed in and by both industry and academia. Learning factories and testing laboratories have been developed for decades for teaching and training purposes in Academia. Nowadays, as the future trend in industry, Industry 4 is being merged into the latest development of learning factories and testing laboratories. This paper presents the development and implementation of a bi-directional digital twin application in an Industry 4 testing laboratory at University of South Australia. The solution is based on the establishment of OPC UA connection between two cobots of different brands, the use of NX Siemens as a CAD simulation platform and a SCADA system from Inductive Automation. Due to differences between system interfaces, communication between different modules was challenging. Python OPC UA servers were developed. The digital twin replicates the physical system and is driven by inputs from the assembly cell.
{"title":"Implementation of a Bi-Directional Digital Twin for Industry 4 Labs in Academia: A Solution Based on OPC UA","authors":"A. Protic, Ziyue Jin, R. Marian, K. Abd, D. Campbell, J. Chahl","doi":"10.1109/IEEM45057.2020.9309953","DOIUrl":"https://doi.org/10.1109/IEEM45057.2020.9309953","url":null,"abstract":"With the increased demands of smarter manufacturing approaches around the world, the process of industrial digital transformation is being pushed in and by both industry and academia. Learning factories and testing laboratories have been developed for decades for teaching and training purposes in Academia. Nowadays, as the future trend in industry, Industry 4 is being merged into the latest development of learning factories and testing laboratories. This paper presents the development and implementation of a bi-directional digital twin application in an Industry 4 testing laboratory at University of South Australia. The solution is based on the establishment of OPC UA connection between two cobots of different brands, the use of NX Siemens as a CAD simulation platform and a SCADA system from Inductive Automation. Due to differences between system interfaces, communication between different modules was challenging. Python OPC UA servers were developed. The digital twin replicates the physical system and is driven by inputs from the assembly cell.","PeriodicalId":226426,"journal":{"name":"2020 IEEE International Conference on Industrial Engineering and Engineering Management (IEEM)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133388660","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 : 2020-12-14DOI: 10.1109/IEEM45057.2020.9309785
X. Bai, M. Xu, H. Jia
This study aims to investigate how congestions at ports affect the shipping freight market using a System Dynamics model, particularly in the liquified petroleum gas (LPG) maritime transportation market. We utilize maritime big data derived from the Automatic Identification System (AIS) for vessel tracking in the analysis. Our model captures the positive impact of port congestion, at its high level, on freight rate volatility when the shipping market is relatively in a tight condition. The proposed model provides insights into the shipping freight market development by innovatively considering port congestion level. The findings provide practical guidance for industrial practitioners to anticipate future freight rates based on the current congestion level and for port authorities to plan for infrastructure upgrades accordingly.
{"title":"A Dynamic Feedback System Analysis on the Mechanism of Shipping Freight","authors":"X. Bai, M. Xu, H. Jia","doi":"10.1109/IEEM45057.2020.9309785","DOIUrl":"https://doi.org/10.1109/IEEM45057.2020.9309785","url":null,"abstract":"This study aims to investigate how congestions at ports affect the shipping freight market using a System Dynamics model, particularly in the liquified petroleum gas (LPG) maritime transportation market. We utilize maritime big data derived from the Automatic Identification System (AIS) for vessel tracking in the analysis. Our model captures the positive impact of port congestion, at its high level, on freight rate volatility when the shipping market is relatively in a tight condition. The proposed model provides insights into the shipping freight market development by innovatively considering port congestion level. The findings provide practical guidance for industrial practitioners to anticipate future freight rates based on the current congestion level and for port authorities to plan for infrastructure upgrades accordingly.","PeriodicalId":226426,"journal":{"name":"2020 IEEE International Conference on Industrial Engineering and Engineering Management (IEEM)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115337218","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 : 2020-12-14DOI: 10.1109/IEEM45057.2020.9309866
Robin Exner, Quoc Hao Ngo, Junjie Liang, Max Ellerich, Robin Günther, S. Schmitt, R. Schmitt
The objective of this paper is the optimization of failure management in production. For this purpose, the failure management process was considered in terms of its interaction with the operational activities in an assembly line. The process for production-related failure management is sufficiently described in the literature, but so far only a few approaches exist that analyze the interactions between production and quality processes in a dynamic model. In this paper, an existing model was taken up and further developed to represent individual assembly lines. The further developed model was programmed as a System Dynamics model that is provided in this paper.
{"title":"A Failure Handling Process Model for Failure Management in Manual Assembly","authors":"Robin Exner, Quoc Hao Ngo, Junjie Liang, Max Ellerich, Robin Günther, S. Schmitt, R. Schmitt","doi":"10.1109/IEEM45057.2020.9309866","DOIUrl":"https://doi.org/10.1109/IEEM45057.2020.9309866","url":null,"abstract":"The objective of this paper is the optimization of failure management in production. For this purpose, the failure management process was considered in terms of its interaction with the operational activities in an assembly line. The process for production-related failure management is sufficiently described in the literature, but so far only a few approaches exist that analyze the interactions between production and quality processes in a dynamic model. In this paper, an existing model was taken up and further developed to represent individual assembly lines. The further developed model was programmed as a System Dynamics model that is provided in this paper.","PeriodicalId":226426,"journal":{"name":"2020 IEEE International Conference on Industrial Engineering and Engineering Management (IEEM)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115549463","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 : 2020-12-14DOI: 10.1109/IEEM45057.2020.9309873
L. A. Salazar, M. P. Revuelta
This article contributes to efforts to teach new methodologies for Industrial Engineering and Engineering Management. Therefore, the creation of the Simulation Paper Planes is presented to teach the principles of Lean Production. The document details the basic rules, general instructions, materials, manufacturing drawings, key performance indicators, and rounds of this simulation. This simulation is a direct and straightforward way to explain and demonstrate the importance of applying the Lean Principles in projects and production processes anywhere in the world. Of the 14 Lean principles, the authors managed to get participants to use 11. As future research, the authors call teachers and consultants to apply this simulation to students (Civil, Industrial, and Construction Engineering) and professionals, to generate a more extensive database. Also, they propose a line of research regarding the level of education in Lean practices between different countries, because, in general terms, undergraduate students in Chile were at the level of graduate students in Colombia.
{"title":"Simulation Paper Planes a Way to Teach Lean Production","authors":"L. A. Salazar, M. P. Revuelta","doi":"10.1109/IEEM45057.2020.9309873","DOIUrl":"https://doi.org/10.1109/IEEM45057.2020.9309873","url":null,"abstract":"This article contributes to efforts to teach new methodologies for Industrial Engineering and Engineering Management. Therefore, the creation of the Simulation Paper Planes is presented to teach the principles of Lean Production. The document details the basic rules, general instructions, materials, manufacturing drawings, key performance indicators, and rounds of this simulation. This simulation is a direct and straightforward way to explain and demonstrate the importance of applying the Lean Principles in projects and production processes anywhere in the world. Of the 14 Lean principles, the authors managed to get participants to use 11. As future research, the authors call teachers and consultants to apply this simulation to students (Civil, Industrial, and Construction Engineering) and professionals, to generate a more extensive database. Also, they propose a line of research regarding the level of education in Lean practices between different countries, because, in general terms, undergraduate students in Chile were at the level of graduate students in Colombia.","PeriodicalId":226426,"journal":{"name":"2020 IEEE International Conference on Industrial Engineering and Engineering Management (IEEM)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115684641","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 : 2020-12-14DOI: 10.1109/IEEM45057.2020.9309791
N. S. Uletika, B. Hartono, T. Wijayanto
In response to the advancement of digitalization technology, the future of assembly works and associated training methods seem to evolve. Gamification, i.e. the use of game design elements in nongame contexts seem to give a potential application for training procedures in the context of assembly work. However, the study on this field is still very limited. Thus, we investigate the following topics pertaining to assembly works and gamification: (a) how is the future of industrial assembly; (b) what methods are currently used to train the assembly workers; and (c) is gamification prospective for such training. From 20 out of 53 related studies, we eventually found the most relevant literatures. The results indicate that traditional training has not met the requirements of future trends, while augmented reality training methods, may offer extra benefits than the counterparts. The concept of gamification in which operators are directly involved, appropriate with skill-based assembly work requiring hands on experience. Further cognitive considerations and physiological measurements during experiment are required to improved HCI assembly work training systems design, especially within the gamification element context.
{"title":"Gamification in Assembly Training: A Systematic Review","authors":"N. S. Uletika, B. Hartono, T. Wijayanto","doi":"10.1109/IEEM45057.2020.9309791","DOIUrl":"https://doi.org/10.1109/IEEM45057.2020.9309791","url":null,"abstract":"In response to the advancement of digitalization technology, the future of assembly works and associated training methods seem to evolve. Gamification, i.e. the use of game design elements in nongame contexts seem to give a potential application for training procedures in the context of assembly work. However, the study on this field is still very limited. Thus, we investigate the following topics pertaining to assembly works and gamification: (a) how is the future of industrial assembly; (b) what methods are currently used to train the assembly workers; and (c) is gamification prospective for such training. From 20 out of 53 related studies, we eventually found the most relevant literatures. The results indicate that traditional training has not met the requirements of future trends, while augmented reality training methods, may offer extra benefits than the counterparts. The concept of gamification in which operators are directly involved, appropriate with skill-based assembly work requiring hands on experience. Further cognitive considerations and physiological measurements during experiment are required to improved HCI assembly work training systems design, especially within the gamification element context.","PeriodicalId":226426,"journal":{"name":"2020 IEEE International Conference on Industrial Engineering and Engineering Management (IEEM)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114752128","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 : 2020-12-14DOI: 10.1109/IEEM45057.2020.9309965
Mahsa Ebrahimian, R. Kashef
Recommendation systems, especially collaborative filtering recommenders, are vulnerable to shilling attacks as some profit-driven users may inject fake profiles into the system to alter recommendation outputs. Current shilling attack detection methods are mostly based on feature extraction techniques. The hand-designed features can confine the model to specific domains or datasets while deep learning techniques enable us to derive deeper level features, enhance detection performance, and generalize the solution on various datasets and domains. This paper illustrates the application of two deep learning methods to detect shilling attacks. We conducted experiments on the MovieLens 100K and Netflix Dataset with different levels of attacks and types. Experimental results show that deep learning models can achieve an accuracy of up to 99%.
{"title":"Efficient Detection of Shilling’s Attacks in Collaborative Filtering Recommendation Systems Using Deep Learning Models","authors":"Mahsa Ebrahimian, R. Kashef","doi":"10.1109/IEEM45057.2020.9309965","DOIUrl":"https://doi.org/10.1109/IEEM45057.2020.9309965","url":null,"abstract":"Recommendation systems, especially collaborative filtering recommenders, are vulnerable to shilling attacks as some profit-driven users may inject fake profiles into the system to alter recommendation outputs. Current shilling attack detection methods are mostly based on feature extraction techniques. The hand-designed features can confine the model to specific domains or datasets while deep learning techniques enable us to derive deeper level features, enhance detection performance, and generalize the solution on various datasets and domains. This paper illustrates the application of two deep learning methods to detect shilling attacks. We conducted experiments on the MovieLens 100K and Netflix Dataset with different levels of attacks and types. Experimental results show that deep learning models can achieve an accuracy of up to 99%.","PeriodicalId":226426,"journal":{"name":"2020 IEEE International Conference on Industrial Engineering and Engineering Management (IEEM)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116177680","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：