Pub Date : 2020-07-01DOI: 10.1109/ICCSA50381.2020.00016
Júlia Potratz, S. A. Canchumuni, José David Bermudez Castro, A. Emerick, M. Pacheco
History matching is the problem of assimilating dynamic data in numerical models of oil and gas reservoirs. Among the methods available in the literature, the iterative ensemble smothers are often used in practice. However, these methods assume that all variables are Gaussian, which limits their application in a problem where the objective is to update the distribution of rock types (facies) in the model. In fact, updating models of geological facies using dynamic data is still an open issue in the oil industry. The problem relies on the development of a parametrical model able to preserve the geological realism of the models. In this context, parameterization techniques based on deep learning, such as convolutional variational autoencoders network (CVAE), have shown promising results in this area when combined with ensemble smothers. Nevertheless, these types of networks present difficulties of scalability for large-sized reservoir models, because as the input dimension increases, the number of network parameters increases exponentially. This work addresses this problem by introducing two new CVAE-based network architectures that can be used for modeling large-scale reservoir models. The first proposed network incorporates the “depthwise separable convolution” in its design, while the second introduces the “inception module”. Results show a considerable reduction of trainable parameters for the first network, while, for the second one, the number becomes invariant to the input dimension.
{"title":"Large Dimension Parameterization with Convolutional Variational Autoencoder: An Application in the History Matching of Channelized Geological Facies Models","authors":"Júlia Potratz, S. A. Canchumuni, José David Bermudez Castro, A. Emerick, M. Pacheco","doi":"10.1109/ICCSA50381.2020.00016","DOIUrl":"https://doi.org/10.1109/ICCSA50381.2020.00016","url":null,"abstract":"History matching is the problem of assimilating dynamic data in numerical models of oil and gas reservoirs. Among the methods available in the literature, the iterative ensemble smothers are often used in practice. However, these methods assume that all variables are Gaussian, which limits their application in a problem where the objective is to update the distribution of rock types (facies) in the model. In fact, updating models of geological facies using dynamic data is still an open issue in the oil industry. The problem relies on the development of a parametrical model able to preserve the geological realism of the models. In this context, parameterization techniques based on deep learning, such as convolutional variational autoencoders network (CVAE), have shown promising results in this area when combined with ensemble smothers. Nevertheless, these types of networks present difficulties of scalability for large-sized reservoir models, because as the input dimension increases, the number of network parameters increases exponentially. This work addresses this problem by introducing two new CVAE-based network architectures that can be used for modeling large-scale reservoir models. The first proposed network incorporates the “depthwise separable convolution” in its design, while the second introduces the “inception module”. Results show a considerable reduction of trainable parameters for the first network, while, for the second one, the number becomes invariant to the input dimension.","PeriodicalId":124171,"journal":{"name":"2020 20th International Conference on Computational Science and Its Applications (ICCSA)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117253770","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 : 2020-07-01DOI: 10.1109/ICCSA50381.2020.00027
M. Sbai, Hajer Taktak, Faouzi Moussa
Mobility becomes a mode of life or work, ubiquitous access to information becomes necessary. At the same time, technological advances in wireless networks and the success of handheld computers and mobile phones are encouraging this movement. The diversity of modes of interaction in mobile environments must allow users to access information anywhere and at any time. This flexibility makes users more demanding and brings new challenges to user interfaces. For this, the context must be well understood and managed in an appropriate form to promote sharing between the different devices and offer a high level of abstraction. Several architectures have been developed to allow context management in mobile environments. To face the challenges of context management in mobile environments, and taking into account the limits of existing solutions, we offer a modular and flexible architecture, which takes the context as the most important element to reason, adapt and provide a service in a appropriate form.
{"title":"Management of Context in Mobile Environments","authors":"M. Sbai, Hajer Taktak, Faouzi Moussa","doi":"10.1109/ICCSA50381.2020.00027","DOIUrl":"https://doi.org/10.1109/ICCSA50381.2020.00027","url":null,"abstract":"Mobility becomes a mode of life or work, ubiquitous access to information becomes necessary. At the same time, technological advances in wireless networks and the success of handheld computers and mobile phones are encouraging this movement. The diversity of modes of interaction in mobile environments must allow users to access information anywhere and at any time. This flexibility makes users more demanding and brings new challenges to user interfaces. For this, the context must be well understood and managed in an appropriate form to promote sharing between the different devices and offer a high level of abstraction. Several architectures have been developed to allow context management in mobile environments. To face the challenges of context management in mobile environments, and taking into account the limits of existing solutions, we offer a modular and flexible architecture, which takes the context as the most important element to reason, adapt and provide a service in a appropriate form.","PeriodicalId":124171,"journal":{"name":"2020 20th International Conference on Computational Science and Its Applications (ICCSA)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123376512","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 : 2020-07-01DOI: 10.1109/ICCSA50381.2020.00026
M. Sbai, Hajer Taktak, Faouzi Moussa
Today, users of applications (including Web services) expect them to be adaptive to the context of use, which consists essentially of information concerning user needs, their devices (personal computer, Smartphone, etc.) and the dynamics of the environment (mainly networks). Therefore, context management encounters the problem of heterogeneity of representations, limitation of device capacity and network bandwidth. In order to overcome this difficulty, special management of context is required for its collection, updating and exchange. In this paper, we will try to propose an agent-based solution to meet user expectations.
{"title":"Towards an Agent-Based Context Management Architecture","authors":"M. Sbai, Hajer Taktak, Faouzi Moussa","doi":"10.1109/ICCSA50381.2020.00026","DOIUrl":"https://doi.org/10.1109/ICCSA50381.2020.00026","url":null,"abstract":"Today, users of applications (including Web services) expect them to be adaptive to the context of use, which consists essentially of information concerning user needs, their devices (personal computer, Smartphone, etc.) and the dynamics of the environment (mainly networks). Therefore, context management encounters the problem of heterogeneity of representations, limitation of device capacity and network bandwidth. In order to overcome this difficulty, special management of context is required for its collection, updating and exchange. In this paper, we will try to propose an agent-based solution to meet user expectations.","PeriodicalId":124171,"journal":{"name":"2020 20th International Conference on Computational Science and Its Applications (ICCSA)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124026184","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 : 2020-07-01DOI: 10.1109/ICCSA50381.2020.00018
Bjornar Lunde, R. Colomo-Palacios
Technical debt in software development is a common problem that is overlooked by many development teams. This debt can be generated from a variety of reasons, including time pressure and complexity in software. Technical debt in simple terms is when a simple and less optimized solution is carried out in order to gain short term benefits, which leads to refactoring and reworking code later on, costing both time and money. The issue is present in both big, established companies and small startups, and is the reason why many of these small startups never get enough economic grip before debt catch up and they go bankrupt. This paper aims to address this problem by exploring how continuous practices including DevOps could help resolve this issue by adopting the right approaches into the software development cycle and workflow. So as to collect information about these topics, a systematic literature review has been conducted, covering both positive and negative impacts these practices can have on technical debt. The findings will present the current practices used to manage and reduce the accumulation of technical debt, if and how these approaches can be used to reduce already existing technical debt and which of these practices that have the biggest impact on technical debt. The paper concludes that there's potential for continuous practices including DevOps to possibly reduce technical debt if applied appropriately
{"title":"Continuous practices and technical debt: a systematic literature review","authors":"Bjornar Lunde, R. Colomo-Palacios","doi":"10.1109/ICCSA50381.2020.00018","DOIUrl":"https://doi.org/10.1109/ICCSA50381.2020.00018","url":null,"abstract":"Technical debt in software development is a common problem that is overlooked by many development teams. This debt can be generated from a variety of reasons, including time pressure and complexity in software. Technical debt in simple terms is when a simple and less optimized solution is carried out in order to gain short term benefits, which leads to refactoring and reworking code later on, costing both time and money. The issue is present in both big, established companies and small startups, and is the reason why many of these small startups never get enough economic grip before debt catch up and they go bankrupt. This paper aims to address this problem by exploring how continuous practices including DevOps could help resolve this issue by adopting the right approaches into the software development cycle and workflow. So as to collect information about these topics, a systematic literature review has been conducted, covering both positive and negative impacts these practices can have on technical debt. The findings will present the current practices used to manage and reduce the accumulation of technical debt, if and how these approaches can be used to reduce already existing technical debt and which of these practices that have the biggest impact on technical debt. The paper concludes that there's potential for continuous practices including DevOps to possibly reduce technical debt if applied appropriately","PeriodicalId":124171,"journal":{"name":"2020 20th International Conference on Computational Science and Its Applications (ICCSA)","volume":"36 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116065560","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 : 2020-07-01DOI: 10.1109/ICCSA50381.2020.00021
N. Voit, S. Bochkov, S. Kirillov, M. Ukhanova, S. Brigadnov, Dmitry Kanev
The paper considers and investigates main approaches, methods and means of systematization and accumulation of project solutions made with the CAD tools for reuse in industry. The authors propose an ontological model of the CAD domain for solving problems of accumulation and management of project knowledge. New method of forming libraries of project solutions instances has been developed, which allows to save and modify project solutions taking into account new project tasks. The authors developed an algorithm for the formation and filling of the library of copies of project solutions made in the CAD KOMPAS.
{"title":"Ontology-based Project Solutions Instances Library Creation Method for the Reuse Concept in the Industry","authors":"N. Voit, S. Bochkov, S. Kirillov, M. Ukhanova, S. Brigadnov, Dmitry Kanev","doi":"10.1109/ICCSA50381.2020.00021","DOIUrl":"https://doi.org/10.1109/ICCSA50381.2020.00021","url":null,"abstract":"The paper considers and investigates main approaches, methods and means of systematization and accumulation of project solutions made with the CAD tools for reuse in industry. The authors propose an ontological model of the CAD domain for solving problems of accumulation and management of project knowledge. New method of forming libraries of project solutions instances has been developed, which allows to save and modify project solutions taking into account new project tasks. The authors developed an algorithm for the formation and filling of the library of copies of project solutions made in the CAD KOMPAS.","PeriodicalId":124171,"journal":{"name":"2020 20th International Conference on Computational Science and Its Applications (ICCSA)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115389555","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 : 2020-07-01DOI: 10.1109/iccsa50381.2020.00007
{"title":"Volume Editors","authors":"","doi":"10.1109/iccsa50381.2020.00007","DOIUrl":"https://doi.org/10.1109/iccsa50381.2020.00007","url":null,"abstract":"","PeriodicalId":124171,"journal":{"name":"2020 20th International Conference on Computational Science and Its Applications (ICCSA)","volume":"87 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116434560","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 : 2020-07-01DOI: 10.1109/ICCSA50381.2020.00019
Symphorien Karl Yoki Donzia, Haeng-Kon Kim
The size of the world's population increased at a Revolution. The modern expansion of human numbers started but environmental degradation with lack of urban services. To satisfy the growing of human food, worldwide demand for grain the area under production should be increased, and productivity must be improved on yields area firstly. To evaluate the Smart Farming sub-use cases' overall outcome, each economic and environmental benefits, social aspects, and the technical evolution path were evaluated. We have like an significant improvement in the economic outcome of the farm. This paper proposed an implementation of BMS (Big Data Application Machine Learning-based Smart Farm System) with an emphasis on crop productivity and the importance of farmers' income increase. Increasing crop productivity is also important to increase essentials' income, enhance farmer field-level insights, and actionable knowledge to produce when the crop is of the best quality or selling it with a good price. Therefore, in the Smart Farm system proposed in this paper specially in case of big data science, we need to consider data analysis and machine learning as the most important steps and then we can include the value of big data science. Machine learning is an essential ability to learn from data and provide data-driven information, decisions, and forecasts. Traditional approaches to machine learning were developed in a different era, like the data set that fully integrates memory. In addition to the characteristics of Big Data, they create obstacles to traditional techniques. One of the objectives of this document is to summarize the challenges of machine learning with Big Data.
{"title":"Architecture Design of a Smart Farm System Based on Big Data Appliance Machine Learning","authors":"Symphorien Karl Yoki Donzia, Haeng-Kon Kim","doi":"10.1109/ICCSA50381.2020.00019","DOIUrl":"https://doi.org/10.1109/ICCSA50381.2020.00019","url":null,"abstract":"The size of the world's population increased at a Revolution. The modern expansion of human numbers started but environmental degradation with lack of urban services. To satisfy the growing of human food, worldwide demand for grain the area under production should be increased, and productivity must be improved on yields area firstly. To evaluate the Smart Farming sub-use cases' overall outcome, each economic and environmental benefits, social aspects, and the technical evolution path were evaluated. We have like an significant improvement in the economic outcome of the farm. This paper proposed an implementation of BMS (Big Data Application Machine Learning-based Smart Farm System) with an emphasis on crop productivity and the importance of farmers' income increase. Increasing crop productivity is also important to increase essentials' income, enhance farmer field-level insights, and actionable knowledge to produce when the crop is of the best quality or selling it with a good price. Therefore, in the Smart Farm system proposed in this paper specially in case of big data science, we need to consider data analysis and machine learning as the most important steps and then we can include the value of big data science. Machine learning is an essential ability to learn from data and provide data-driven information, decisions, and forecasts. Traditional approaches to machine learning were developed in a different era, like the data set that fully integrates memory. In addition to the characteristics of Big Data, they create obstacles to traditional techniques. One of the objectives of this document is to summarize the challenges of machine learning with Big Data.","PeriodicalId":124171,"journal":{"name":"2020 20th International Conference on Computational Science and Its Applications (ICCSA)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132956962","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: 10.1109/bigdataservice.2018.00009
V. Lumelsky
{"title":"Workshop Organizers","authors":"V. Lumelsky","doi":"10.1109/bigdataservice.2018.00009","DOIUrl":"https://doi.org/10.1109/bigdataservice.2018.00009","url":null,"abstract":"","PeriodicalId":124171,"journal":{"name":"2020 20th International Conference on Computational Science and Its Applications (ICCSA)","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":"124393029","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 : 2011-12-01DOI: 10.1109/SMARTCOMP.2017.7946958
Jiannong Cao, Julie A. McCann, K. Nahrstedt, Xue Liu
Welcome to the 2011 International Conference on Cloud and Service Computing (CSC2011) and the city of Hong Kong. In the past several years, cloud and service computing have attracted a lot of attention from both academics and industrial communities. Cloud computing is an important transition and paradigm shift in IT service delivery driven by economies of scale. It enables a shared pool of virtualized, dynamically configurable, and managed computing resources to be delivered on demand to customers over the Internet and other available networks. As such and with the “pay-asyou-go” business model, cloud computing also leads to changes and transformation of many other industries. Closely related to cloud computing, service computing has become a cross-discipline area bridging the gap between Business Services and IT Services.
{"title":"Message from the General and Program Co-Chairs","authors":"Jiannong Cao, Julie A. McCann, K. Nahrstedt, Xue Liu","doi":"10.1109/SMARTCOMP.2017.7946958","DOIUrl":"https://doi.org/10.1109/SMARTCOMP.2017.7946958","url":null,"abstract":"Welcome to the 2011 International Conference on Cloud and Service Computing (CSC2011) and the city of Hong Kong. In the past several years, cloud and service computing have attracted a lot of attention from both academics and industrial communities. Cloud computing is an important transition and paradigm shift in IT service delivery driven by economies of scale. It enables a shared pool of virtualized, dynamically configurable, and managed computing resources to be delivered on demand to customers over the Internet and other available networks. As such and with the “pay-asyou-go” business model, cloud computing also leads to changes and transformation of many other industries. Closely related to cloud computing, service computing has become a cross-discipline area bridging the gap between Business Services and IT Services.","PeriodicalId":124171,"journal":{"name":"2020 20th International Conference on Computational Science and Its Applications (ICCSA)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130475177","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 : 1980-10-01DOI: 10.1109/iccsa50381.2020.00001
{"title":"Title Page","authors":"","doi":"10.1109/iccsa50381.2020.00001","DOIUrl":"https://doi.org/10.1109/iccsa50381.2020.00001","url":null,"abstract":"","PeriodicalId":124171,"journal":{"name":"2020 20th International Conference on Computational Science and Its Applications (ICCSA)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1980-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130517666","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：