Son Nguyen, A. Olinsky, John T. Quinn, Phyllis A. Schumacher
There have been a variety of predictive models capable of handling binary targets, ranging from traditional logistic regression to modern neural networks. However, when the target variable represents a rare event, these models might not be appropriate as they assume that the distribution in the target variable is balanced. In this article, the impact of multiple resampling methods on conventional predictive models is studied. These resampling techniques include the methods of oversampling of the rare events, undersampling of the common events in the data, and synthetic minority over-sampling technique (SMOTE). The predictive models of decision trees, logistic regression and rule induction are applied with SAS Enterprise Miner (EM) software to the revised data. The studied data set is of home mortgage applications which includes a target variable with an occurrence rate of the rare event being 0.8%. The authors varied the percentage of the rare event from the original of 0.8% up to 50% and monitored the associated performances of the three predictive models to see which one worked the best.
{"title":"Predictive Modeling for Imbalanced Big Data in SAS Enterprise Miner and R","authors":"Son Nguyen, A. Olinsky, John T. Quinn, Phyllis A. Schumacher","doi":"10.4018/IJFC.2018070103","DOIUrl":"https://doi.org/10.4018/IJFC.2018070103","url":null,"abstract":"There have been a variety of predictive models capable of handling binary targets, ranging from traditional logistic regression to modern neural networks. However, when the target variable represents a rare event, these models might not be appropriate as they assume that the distribution in the target variable is balanced. In this article, the impact of multiple resampling methods on conventional predictive models is studied. These resampling techniques include the methods of oversampling of the rare events, undersampling of the common events in the data, and synthetic minority over-sampling technique (SMOTE). The predictive models of decision trees, logistic regression and rule induction are applied with SAS Enterprise Miner (EM) software to the revised data. The studied data set is of home mortgage applications which includes a target variable with an occurrence rate of the rare event being 0.8%. The authors varied the percentage of the rare event from the original of 0.8% up to 50% and monitored the associated performances of the three predictive models to see which one worked the best.","PeriodicalId":218786,"journal":{"name":"Int. J. Fog Comput.","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129944925","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) enables inters connectivity among devices and platforms. IoT devices such as sensors, or embedded systems offer computational, storage, and networking resources and the existence of these resources permits to move the execution of IoT applications to the edge of the network and it is known as fog computing. It is able to handle billions of Internet-connected devices and is well situated for real-time big data analytics and provides advantages in advertising and personal computing. The main issues in fog computing includes fog networking, QoS, interfacing and programming model, computation offloading, accounting, billing and monitoring, provisioning and resource management, security and privacy. A particular research challenge is the Quality of Service metric for fog services. Thus, this paper gives a survey of cloud computing, discusses the QoS metrics, and the future research directions in fog computing.
{"title":"Fog Computing Qos Review and Open Challenges","authors":"R. Babu, J. Kanniappan, R. Abirami","doi":"10.4018/IJFC.2018070104","DOIUrl":"https://doi.org/10.4018/IJFC.2018070104","url":null,"abstract":"Internet of Things (IoT) enables inters connectivity among devices and platforms. IoT devices such as sensors, or embedded systems offer computational, storage, and networking resources and the existence of these resources permits to move the execution of IoT applications to the edge of the network and it is known as fog computing. It is able to handle billions of Internet-connected devices and is well situated for real-time big data analytics and provides advantages in advertising and personal computing. The main issues in fog computing includes fog networking, QoS, interfacing and programming model, computation offloading, accounting, billing and monitoring, provisioning and resource management, security and privacy. A particular research challenge is the Quality of Service metric for fog services. Thus, this paper gives a survey of cloud computing, discusses the QoS metrics, and the future research directions in fog computing.","PeriodicalId":218786,"journal":{"name":"Int. J. Fog Comput.","volume":"240 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114060628","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}
Big Data is data sets that are so voluminous and complex that traditional data processing application software are inadequate to deal with them. This article discusses what is Big Data, and its characteristics, and how this information revolution of Big Data is transforming our lives and the new technology and methodologies that have been developed to process data of these huge dimensionalities. Big Data can be discrete or a continuous stream of data, and can be accessed using many types and kinds of computing devices ranging from supercomputers, personal work stations, to mobile devices and tablets. Discussion is presented of how fog computing can be performed with cloud computing as a mechanism for visualization of Big Data. An example of visualization techniques for Big Data transmitted by devices connected by Internet of Things (IoT) is presented for real data from fatality analysis reporting system (FARS) managed by the National Highway Traffic Safety Administration (NHTSA) of the United States Department of Transportation (USDoT). Big Data web-based visualization software are discussed that are both JavaScript-based and user interface-based. Challenges and opportunities of using Big Data with fog computing are also discussed.
{"title":"Big Data and Its Visualization With Fog Computing","authors":"R. Segall, G. Niu","doi":"10.4018/IJFC.2018070102","DOIUrl":"https://doi.org/10.4018/IJFC.2018070102","url":null,"abstract":"Big Data is data sets that are so voluminous and complex that traditional data processing application software are inadequate to deal with them. This article discusses what is Big Data, and its characteristics, and how this information revolution of Big Data is transforming our lives and the new technology and methodologies that have been developed to process data of these huge dimensionalities. Big Data can be discrete or a continuous stream of data, and can be accessed using many types and kinds of computing devices ranging from supercomputers, personal work stations, to mobile devices and tablets. Discussion is presented of how fog computing can be performed with cloud computing as a mechanism for visualization of Big Data. An example of visualization techniques for Big Data transmitted by devices connected by Internet of Things (IoT) is presented for real data from fatality analysis reporting system (FARS) managed by the National Highway Traffic Safety Administration (NHTSA) of the United States Department of Transportation (USDoT). Big Data web-based visualization software are discussed that are both JavaScript-based and user interface-based. Challenges and opportunities of using Big Data with fog computing are also discussed.","PeriodicalId":218786,"journal":{"name":"Int. J. Fog Comput.","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123153428","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 the last half century, we have gone from storing data on 5¼ inch floppy diskettes to the cloud and now use fog computing. But one should ask why so much data is being collected. Part of the answer is simple in light of scientific projects, but why is there so much data on us? Then, we ask about its “interface” through fog computing. Such questions prompt this article on the philosophy of big data and fog computing. After some background on definitions, origins and contemporary applications, the main discussion begins with thinking about modern data collection, management, and applications from a complexity standpoint. Big data is turned into knowledge, but knowledge is extrapolated from the past and used to manage the future. Yet it is questionable whether humans have the capacity to manage contemporary technological and social complexity evidenced by our world in crisis and possibly on the brink of extinction. Such calls for a new way of studying societies from a scientific point of view. We are at the center of the observation from which big data emerge and are manipulated, the overall human project being not only to create an artificial brain with an attendant mind, but a society that might be able to survive what “natural” humans cannot.
{"title":"Social Implications of Big Data and Fog Computing","authors":"J. Horne","doi":"10.4018/IJFC.2018070101","DOIUrl":"https://doi.org/10.4018/IJFC.2018070101","url":null,"abstract":"In the last half century, we have gone from storing data on 5¼ inch floppy diskettes to the cloud and now use fog computing. But one should ask why so much data is being collected. Part of the answer is simple in light of scientific projects, but why is there so much data on us? Then, we ask about its “interface” through fog computing. Such questions prompt this article on the philosophy of big data and fog computing. After some background on definitions, origins and contemporary applications, the main discussion begins with thinking about modern data collection, management, and applications from a complexity standpoint. Big data is turned into knowledge, but knowledge is extrapolated from the past and used to manage the future. Yet it is questionable whether humans have the capacity to manage contemporary technological and social complexity evidenced by our world in crisis and possibly on the brink of extinction. Such calls for a new way of studying societies from a scientific point of view. We are at the center of the observation from which big data emerge and are manipulated, the overall human project being not only to create an artificial brain with an attendant mind, but a society that might be able to survive what “natural” humans cannot.","PeriodicalId":218786,"journal":{"name":"Int. J. Fog Comput.","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120963157","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}
Gerard G. Dumancas, Ghalib A. Bello, J. Hughes, R. Murimi, Lakshmi Viswanath, Casey O. Orndorff, G. Dumancas, Jacy O'Dell, Prakash Ghimire, Catherine Setijadi
The accumulation of data from various instrumental analytical instruments has paved a way for the application of chemometrics. Challenges, however, exist in processing, analyzing, visualizing, and storing these data. Chemometrics is a relatively young area of analytical chemistry that involves the use of statistics and computer applications in chemistry. This article will discuss various computational and storage tools of big data analytics within the context of analytical chemistry with examples, applications, and usage details in relation to fog computing. The future of fog computing in chemometrics will also be discussed. The article will dedicate particular emphasis to preprocessing techniques, statistical and machine learning methodology for data mining and analysis, tools for big data visualization, and state-of-the-art applications for data storage using fog computing.
{"title":"Chemometrics: From Data Preprocessing to Fog Computing","authors":"Gerard G. Dumancas, Ghalib A. Bello, J. Hughes, R. Murimi, Lakshmi Viswanath, Casey O. Orndorff, G. Dumancas, Jacy O'Dell, Prakash Ghimire, Catherine Setijadi","doi":"10.4018/IJFC.2019010101","DOIUrl":"https://doi.org/10.4018/IJFC.2019010101","url":null,"abstract":"The accumulation of data from various instrumental analytical instruments has paved a way for the application of chemometrics. Challenges, however, exist in processing, analyzing, visualizing, and storing these data. Chemometrics is a relatively young area of analytical chemistry that involves the use of statistics and computer applications in chemistry. This article will discuss various computational and storage tools of big data analytics within the context of analytical chemistry with examples, applications, and usage details in relation to fog computing. The future of fog computing in chemometrics will also be discussed. The article will dedicate particular emphasis to preprocessing techniques, statistical and machine learning methodology for data mining and analysis, tools for big data visualization, and state-of-the-art applications for data storage using fog computing.","PeriodicalId":218786,"journal":{"name":"Int. J. Fog Comput.","volume":"57 6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115652275","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}
This article describes how the rise of fog computing to improve cloud computing performance and the acceptance of smart devices is slowly but surely changing our future and shaping the computing environment around us. IoT integrated with advances in low cost computing, storage and power, along with high speed networks and big data, supports distributed computing. However, much like cloud computing, which are under constant security attacks and issues, distributed computing also faces similar challenges and security threats. This can be mitigated to a great extent using fog computing, which extends the limits of Cloud services to the last mile edge near to the nodes and networks, thereby increasing the performance and security levels. Fog computing also helps increase the reach and comes across as a viable solution for distributed computing. This article presents a review of the academic literature research work on the Fog Computing. The authors discuss the challenges in Fog environment and propose a new taxonomy.
{"title":"Novel Taxonomy to Select Fog Products and Challenges Faced in Fog Environments","authors":"Akashdeep Bhardwaj","doi":"10.4018/IJFC.2018010103","DOIUrl":"https://doi.org/10.4018/IJFC.2018010103","url":null,"abstract":"This article describes how the rise of fog computing to improve cloud computing performance and the acceptance of smart devices is slowly but surely changing our future and shaping the computing environment around us. IoT integrated with advances in low cost computing, storage and power, along with high speed networks and big data, supports distributed computing. However, much like cloud computing, which are under constant security attacks and issues, distributed computing also faces similar challenges and security threats. This can be mitigated to a great extent using fog computing, which extends the limits of Cloud services to the last mile edge near to the nodes and networks, thereby increasing the performance and security levels. Fog computing also helps increase the reach and comes across as a viable solution for distributed computing. This article presents a review of the academic literature research work on the Fog Computing. The authors discuss the challenges in Fog environment and propose a new taxonomy.","PeriodicalId":218786,"journal":{"name":"Int. J. Fog Comput.","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131251776","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：