Pub Date : 2021-10-01DOI: 10.1109/IEEECloudSummit52029.2021.00008
Ruxiao Duan, Fan Zhang, S. Khan
Deploying distributed applications using their Operators in a containerized platform on the state-of-art cloud orchestration tooling, such as Kubernetes, has truly become widely accepted. However, the quality of an Operator has a significant impact on a few core metrics of the application, such as its availability, consistency, and quality of service. This paper introduces the Kubernetes Operator maturity model and its five maturity levels, and then gives a demonstration on how a demo Kubernetes Operator is capable of reaching all the five levels respectively by using an example Operator named New Visitors Site Operator. Finally, an experiment illustrating the capability of the example Operator’s auto-scaling functions to improve the application performance is presented. This example Operator will enable developers and researchers to design containerized applications with more enhanced features. The code is available at https://github.com/ringdrx/visitors-operator.
在最先进的云编排工具(如Kubernetes)上的容器化平台上使用它们的operator部署分布式应用程序，已经真正被广泛接受。然而，操作员的质量对应用程序的一些核心指标有重大影响，例如其可用性、一致性和服务质量。本文介绍了Kubernetes Operator成熟度模型及其五个成熟度级别，并以一个名为New visitor Site Operator的示例操作员为例，演示了Kubernetes Operator如何分别达到这五个成熟度级别。最后，通过实验验证了示例算子的自缩放函数对提高应用性能的作用。这个示例操作员将使开发人员和研究人员能够设计具有更多增强功能的容器化应用程序。代码可在https://github.com/ringdrx/visitors-operator上获得。
{"title":"A Case Study on Five Maturity Levels of A Kubernetes Operator","authors":"Ruxiao Duan, Fan Zhang, S. Khan","doi":"10.1109/IEEECloudSummit52029.2021.00008","DOIUrl":"https://doi.org/10.1109/IEEECloudSummit52029.2021.00008","url":null,"abstract":"Deploying distributed applications using their Operators in a containerized platform on the state-of-art cloud orchestration tooling, such as Kubernetes, has truly become widely accepted. However, the quality of an Operator has a significant impact on a few core metrics of the application, such as its availability, consistency, and quality of service. This paper introduces the Kubernetes Operator maturity model and its five maturity levels, and then gives a demonstration on how a demo Kubernetes Operator is capable of reaching all the five levels respectively by using an example Operator named New Visitors Site Operator. Finally, an experiment illustrating the capability of the example Operator’s auto-scaling functions to improve the application performance is presented. This example Operator will enable developers and researchers to design containerized applications with more enhanced features. The code is available at https://github.com/ringdrx/visitors-operator.","PeriodicalId":54281,"journal":{"name":"IEEE Cloud Computing","volume":"38 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84990537","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-10-01DOI: 10.1109/IEEECloudSummit52029.2021.00017
Kanishk Shah, Khushali Deulkar
Classification of Apparel and Clothing has been the centerpiece in recommendations made for Fashion and E-commerce. This paper explores the applicability of light Deep Learning based classifiers for fast and accurate category classification of images. We use Residual and Inverted Residual Network Based Convolutional Neural Network models, and demonstrate their ability to generalize well and overcome the problems of overfitting. Extensive evaluation on a large dataset with highly class-imbalanced data suggests that the proposed models are fast, compact, and exceed the performance of state-of-the art models with up to approximately 10 times fewer parameters and 4.5 times the speed.
{"title":"Lightweight Apparel Classification with Residual and Inverted Residual Block based Architectures","authors":"Kanishk Shah, Khushali Deulkar","doi":"10.1109/IEEECloudSummit52029.2021.00017","DOIUrl":"https://doi.org/10.1109/IEEECloudSummit52029.2021.00017","url":null,"abstract":"Classification of Apparel and Clothing has been the centerpiece in recommendations made for Fashion and E-commerce. This paper explores the applicability of light Deep Learning based classifiers for fast and accurate category classification of images. We use Residual and Inverted Residual Network Based Convolutional Neural Network models, and demonstrate their ability to generalize well and overcome the problems of overfitting. Extensive evaluation on a large dataset with highly class-imbalanced data suggests that the proposed models are fast, compact, and exceed the performance of state-of-the art models with up to approximately 10 times fewer parameters and 4.5 times the speed.","PeriodicalId":54281,"journal":{"name":"IEEE Cloud Computing","volume":"8 1","pages":"57-62"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78242298","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-10-01DOI: 10.1109/IEEECloudSummit52029.2021.00011
Daniel Fraunholz, Richard Schörghofer-Vrinssen, H. König, W. Mühlbauer, Richard Zahoranksy
Mobility management is a key feature of mobile edge computing. We present an edge cloud infrastructure testbed to explore various mobility scenarios. The design objection of this testbed has been a flexible open platform based on commodity hardware that can easily be scaled with more edge devices and compute resources to perform various edge cloud experiments. As first experiments on our testbed, we have investigated the feasibility of task migration among edge devices caused by edge device overload and unpredictable user movements. We describe the migration process and present some measurements to demonstrate the feasibility.
{"title":"Mobility-Enabling Edge Cloud Infrastructure: Testbed and Experimental Evaluation","authors":"Daniel Fraunholz, Richard Schörghofer-Vrinssen, H. König, W. Mühlbauer, Richard Zahoranksy","doi":"10.1109/IEEECloudSummit52029.2021.00011","DOIUrl":"https://doi.org/10.1109/IEEECloudSummit52029.2021.00011","url":null,"abstract":"Mobility management is a key feature of mobile edge computing. We present an edge cloud infrastructure testbed to explore various mobility scenarios. The design objection of this testbed has been a flexible open platform based on commodity hardware that can easily be scaled with more edge devices and compute resources to perform various edge cloud experiments. As first experiments on our testbed, we have investigated the feasibility of task migration among edge devices caused by edge device overload and unpredictable user movements. We describe the migration process and present some measurements to demonstrate the feasibility.","PeriodicalId":54281,"journal":{"name":"IEEE Cloud Computing","volume":"1 1","pages":"19-24"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89253427","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-10-01DOI: 10.1109/IEEECloudSummit52029.2021.00018
Haris Gulzar, Muhammad Shakeel, Kenji Nishida, Katsutoshi Itoyama, K. Nakadai, H. Amano
High performance of Machine Learning algorithms has enabled numerous applications based upon speech interface in our daily life, but most of the frameworks use computationally expensive algorithms deployed on cloud servers as speech recognition engines. With the recent surge in the number of IoT devices, a robust and scalable solution for enabling AI applications on IoT devices is inevitable in form of edge computing. In this paper, we propose the application of Systemon-Chip (SoC) powered edge computing device as accelerator for speech commands classification using Convolutional Neural Network (CNN). Different aspects affecting the CNN performance are explored and an efficient and light-weight model named as CASENet is proposed which achieves state-of-the-art performance with significantly smaller number of parameters and operations. Efficient extraction of useful features from audio signal helped to maintain high accuracy with a 6X smaller number of parameters, making CASENet the smallest CNN in comparison to similarly performing networks. Light-weight nature of the model has led to achieve 96.45% validation accuracy with a 14X smaller number of operations which makes it ideal for low-power IoT and edge devices. A CNN accelerator is designed and deployed on FPGA part of SoC equipped edge server device. The hardware accelerator helped to improve the inference latency of speech command by a 6.7X factor as compared to standard implementation. Memory, computational cost and latency are the most important metrics for selecting a model to deploy on edge computing devices, and CASENet along with the accelerator surpasses all of these requirements.
{"title":"CASE: CNN Acceleration for Speech-Classification in Edge-Computing","authors":"Haris Gulzar, Muhammad Shakeel, Kenji Nishida, Katsutoshi Itoyama, K. Nakadai, H. Amano","doi":"10.1109/IEEECloudSummit52029.2021.00018","DOIUrl":"https://doi.org/10.1109/IEEECloudSummit52029.2021.00018","url":null,"abstract":"High performance of Machine Learning algorithms has enabled numerous applications based upon speech interface in our daily life, but most of the frameworks use computationally expensive algorithms deployed on cloud servers as speech recognition engines. With the recent surge in the number of IoT devices, a robust and scalable solution for enabling AI applications on IoT devices is inevitable in form of edge computing. In this paper, we propose the application of Systemon-Chip (SoC) powered edge computing device as accelerator for speech commands classification using Convolutional Neural Network (CNN). Different aspects affecting the CNN performance are explored and an efficient and light-weight model named as CASENet is proposed which achieves state-of-the-art performance with significantly smaller number of parameters and operations. Efficient extraction of useful features from audio signal helped to maintain high accuracy with a 6X smaller number of parameters, making CASENet the smallest CNN in comparison to similarly performing networks. Light-weight nature of the model has led to achieve 96.45% validation accuracy with a 14X smaller number of operations which makes it ideal for low-power IoT and edge devices. A CNN accelerator is designed and deployed on FPGA part of SoC equipped edge server device. The hardware accelerator helped to improve the inference latency of speech command by a 6.7X factor as compared to standard implementation. Memory, computational cost and latency are the most important metrics for selecting a model to deploy on edge computing devices, and CASENet along with the accelerator surpasses all of these requirements.","PeriodicalId":54281,"journal":{"name":"IEEE Cloud Computing","volume":"27 1","pages":"63-68"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78514686","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-10-01DOI: 10.1109/IEEECloudSummit52029.2021.00012
H. Kimm, J. Ortiz
Cloud Computing is emerging technology that provides services of storage and platform software to large organizations, but some of them are still hesitant to shift their setups on the cloud due to security issues and risks. Thus, it is important to address the security issues and problems in cloud systems. In this research we contributed to a multilevel security (MLS) framework based on data sensitivity and security that provides adequate level of data security based on various classifications and categories. The proposed multilevel security embedded information retrieval tool in this paper encompasses suitable access control combined with Security Enhanced Linux (SELinux) that facilitates classification of the data based on subsequent changes in the sensitivity levels of the data and changes in the security measures to cope with the dynamic and vulnerable changes in cloud security threats. To implement the proposed MLS framework, the SELinux system is applied as a testbed to retrieve information and track the history of the data retrieved.
云计算是一种新兴技术，为大型组织提供存储和平台软件服务，但由于安全问题和风险，一些组织仍在犹豫是否将其设置转移到云上。因此，解决云系统中的安全问题非常重要。在这项研究中，我们贡献了一个基于数据敏感性和安全性的多级安全(MLS)框架，该框架提供了基于各种分类和类别的足够级别的数据安全。本文提出的多级安全嵌入式信息检索工具包括适当的访问控制，并结合security Enhanced Linux (SELinux)，根据数据敏感性级别的后续变化和安全措施的变化对数据进行分类，以应对云安全威胁的动态和脆弱性变化。为了实现所提出的MLS框架，应用SELinux系统作为检索信息和跟踪检索数据历史的测试平台。
{"title":"Multilevel Security Embedded Information Retrieval and Tracking on Cloud Environments","authors":"H. Kimm, J. Ortiz","doi":"10.1109/IEEECloudSummit52029.2021.00012","DOIUrl":"https://doi.org/10.1109/IEEECloudSummit52029.2021.00012","url":null,"abstract":"Cloud Computing is emerging technology that provides services of storage and platform software to large organizations, but some of them are still hesitant to shift their setups on the cloud due to security issues and risks. Thus, it is important to address the security issues and problems in cloud systems. In this research we contributed to a multilevel security (MLS) framework based on data sensitivity and security that provides adequate level of data security based on various classifications and categories. The proposed multilevel security embedded information retrieval tool in this paper encompasses suitable access control combined with Security Enhanced Linux (SELinux) that facilitates classification of the data based on subsequent changes in the sensitivity levels of the data and changes in the security measures to cope with the dynamic and vulnerable changes in cloud security threats. To implement the proposed MLS framework, the SELinux system is applied as a testbed to retrieve information and track the history of the data retrieved.","PeriodicalId":54281,"journal":{"name":"IEEE Cloud Computing","volume":"7 1","pages":"25-28"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89674773","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-10-01DOI: 10.1109/IEEECloudSummit52029.2021.00021
Louay Ahmad, Boxiang Dong, B. Samanthula, Ryan Yang Wang, Bill Hui Li
The rising complexity of deep neural networks has raised rigorous demands for computational hardware and deployment expertise. As an alternative, outsourcing a pre-trained model to a third party server has been increasingly prevalent. However, it creates opportunities for attackers to interfere with the prediction outcomes of the deep neural network. In this paper, we focus on integrity verification of the prediction results from outsourced deep neural models and make a thread of contributions. We propose a new attack based on steganography that enables the server to generate wrong prediction results in a command-and-control fashion. Following that, we design a homomorphic encryption-based authentication scheme to detect wrong predictions made by any attack. Our extensive experiments on benchmark datasets demonstrate the invisibility of the attack and the effectiveness of our authentication approach.
{"title":"Towards Trustworthy Outsourced Deep Neural Networks","authors":"Louay Ahmad, Boxiang Dong, B. Samanthula, Ryan Yang Wang, Bill Hui Li","doi":"10.1109/IEEECloudSummit52029.2021.00021","DOIUrl":"https://doi.org/10.1109/IEEECloudSummit52029.2021.00021","url":null,"abstract":"The rising complexity of deep neural networks has raised rigorous demands for computational hardware and deployment expertise. As an alternative, outsourcing a pre-trained model to a third party server has been increasingly prevalent. However, it creates opportunities for attackers to interfere with the prediction outcomes of the deep neural network. In this paper, we focus on integrity verification of the prediction results from outsourced deep neural models and make a thread of contributions. We propose a new attack based on steganography that enables the server to generate wrong prediction results in a command-and-control fashion. Following that, we design a homomorphic encryption-based authentication scheme to detect wrong predictions made by any attack. Our extensive experiments on benchmark datasets demonstrate the invisibility of the attack and the effectiveness of our authentication approach.","PeriodicalId":54281,"journal":{"name":"IEEE Cloud Computing","volume":"7 1","pages":"83-88"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75877517","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-10-01DOI: 10.1109/IEEECloudSummit52029.2021.00016
Angel Beltre, Pankaj Saha, M. Govindaraju
Kubernetes (K8s) is gaining adoption in cloud computing for container management, deployment automation, and resource scheduling. As K8s matures, with increased stability and scalability, it is important to study how it can be effectively customized for use in different application scenarios. The focus of our work is on studying one of its main core components, kube-scheduler, which is in charge of scheduling pods on worker nodes. The K8s default scheduler implements the First Come First Serve (FCFS) algorithm as the pods are ordered and sequenced for execution based on the timestamp of when tasks arrive, when no priority is set to the pods. In this paper, we present a Policy-driven Multi-Tenant K8s (PMK) framework to study how policies of multiple tenants on resource requests and job arrivals affect fairness for the tenants individually in terms of makespan, average waiting time, and average turnaround time. PMK allows re-sequencing of tasks, submitted by multiple tenants, via well-known or customized scheduling algorithms before they enter the K8s scheduling queue. Our evaluation uses well-known algorithms such as Round Robin (RR), FCFS and Dominant Resource Fairness (DRF). In addition, we introduce a Cluster-Based Fairness (CBF) scheduling algorithm, which is a variation of DRF. CBF considers overall cluster utilization and resource availability to determine which task to choose from new requests. Our analysis shows that PMK can provide insights to cluster and cloud infrastructure managers on the factors affecting fairness and accordingly in some cases obtain 61.0% improvement in average waiting time for tenants with homogeneous individual demands. In addition, our customized CBF scheduling policy, when used with with PMK on K8s, can reduce overall cluster average waiting time by up to 4%.
{"title":"Framework for Analysing a Policy-driven Multi-Tenant Kubernetes Environment","authors":"Angel Beltre, Pankaj Saha, M. Govindaraju","doi":"10.1109/IEEECloudSummit52029.2021.00016","DOIUrl":"https://doi.org/10.1109/IEEECloudSummit52029.2021.00016","url":null,"abstract":"Kubernetes (K8s) is gaining adoption in cloud computing for container management, deployment automation, and resource scheduling. As K8s matures, with increased stability and scalability, it is important to study how it can be effectively customized for use in different application scenarios. The focus of our work is on studying one of its main core components, kube-scheduler, which is in charge of scheduling pods on worker nodes. The K8s default scheduler implements the First Come First Serve (FCFS) algorithm as the pods are ordered and sequenced for execution based on the timestamp of when tasks arrive, when no priority is set to the pods. In this paper, we present a Policy-driven Multi-Tenant K8s (PMK) framework to study how policies of multiple tenants on resource requests and job arrivals affect fairness for the tenants individually in terms of makespan, average waiting time, and average turnaround time. PMK allows re-sequencing of tasks, submitted by multiple tenants, via well-known or customized scheduling algorithms before they enter the K8s scheduling queue. Our evaluation uses well-known algorithms such as Round Robin (RR), FCFS and Dominant Resource Fairness (DRF). In addition, we introduce a Cluster-Based Fairness (CBF) scheduling algorithm, which is a variation of DRF. CBF considers overall cluster utilization and resource availability to determine which task to choose from new requests. Our analysis shows that PMK can provide insights to cluster and cloud infrastructure managers on the factors affecting fairness and accordingly in some cases obtain 61.0% improvement in average waiting time for tenants with homogeneous individual demands. In addition, our customized CBF scheduling policy, when used with with PMK on K8s, can reduce overall cluster average waiting time by up to 4%.","PeriodicalId":54281,"journal":{"name":"IEEE Cloud Computing","volume":"34 1","pages":"49-56"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89791400","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-10-01DOI: 10.1109/IEEECloudSummit52029.2021.00019
Saidur Rahman, Apostolos Kalatzis, Mike P. Wittie, A. Elmokashfi, Laura M. Stanley, S. Patterson, David L. Millman
Mobile applications can improve battery and application performance by offloading heavy processing tasks to more powerful compute nodes. While Mobile Edge Computing (MEC) provides such nodes in close network proximity, their capacity is limited and may be shared with the Centralized Radio Access Network (C-RAN) in 5G networks. We propose MicroLambda, a framework to partition offloaded computation via dynamic checkpointing to efficiently utilize MEC compute capacity without encroaching on C-RAN operations.
{"title":"Short and Sweet Checkpoints for C-RAN MEC","authors":"Saidur Rahman, Apostolos Kalatzis, Mike P. Wittie, A. Elmokashfi, Laura M. Stanley, S. Patterson, David L. Millman","doi":"10.1109/IEEECloudSummit52029.2021.00019","DOIUrl":"https://doi.org/10.1109/IEEECloudSummit52029.2021.00019","url":null,"abstract":"Mobile applications can improve battery and application performance by offloading heavy processing tasks to more powerful compute nodes. While Mobile Edge Computing (MEC) provides such nodes in close network proximity, their capacity is limited and may be shared with the Centralized Radio Access Network (C-RAN) in 5G networks. We propose MicroLambda, a framework to partition offloaded computation via dynamic checkpointing to efficiently utilize MEC compute capacity without encroaching on C-RAN operations.","PeriodicalId":54281,"journal":{"name":"IEEE Cloud Computing","volume":"12 4 1","pages":"69-76"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79484422","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-10-01DOI: 10.1109/IEEECloudSummit52029.2021.00009
H. El-Kassabi, M. Serhani, Khaled Khalil, A. Benharref
The coronavirus COVID-19 pandemic has become the center of concern worldwide and hence the focus of media attention. Checking the coronavirus-related news and updates has become a daily routine of everyone. Hence, news processing and analytics become key solutions to harvest the real value of this massive amount of news. This conscious growth of published news about COVID-19 makes it hard for a variety of audiences to navigate through, analyze, and select the most important news (e.g., relevant information about the pandemic, its evolution, the vital precautions, and the necessary interventions). This can be realized using current and emerging technologies including Cloud computing, Artificial Intelligence (AI) and Deep Learning (DL). In this paper, we propose a framework to analyze the massive amount of public Covid-19 media reports over the Cloud. This framework encompasses four modules, including text preprocessing, deep learning, and machine learning-based news information extraction, and recommendation. We conducted experiments to evaluate three modules of our framework and the results we have obtained prove that combining derived information from the news reports provides the policymakers, health authorities, and the public, a complete picture of the way this virus is proliferating. Analyzing this data swiftly is a powerful tool to provide imperative answers to questions that are relevant to public health.
{"title":"A Cloud-based Framework for COVID-19 Media Classification, Information Extraction, and Trends Analysis","authors":"H. El-Kassabi, M. Serhani, Khaled Khalil, A. Benharref","doi":"10.1109/IEEECloudSummit52029.2021.00009","DOIUrl":"https://doi.org/10.1109/IEEECloudSummit52029.2021.00009","url":null,"abstract":"The coronavirus COVID-19 pandemic has become the center of concern worldwide and hence the focus of media attention. Checking the coronavirus-related news and updates has become a daily routine of everyone. Hence, news processing and analytics become key solutions to harvest the real value of this massive amount of news. This conscious growth of published news about COVID-19 makes it hard for a variety of audiences to navigate through, analyze, and select the most important news (e.g., relevant information about the pandemic, its evolution, the vital precautions, and the necessary interventions). This can be realized using current and emerging technologies including Cloud computing, Artificial Intelligence (AI) and Deep Learning (DL). In this paper, we propose a framework to analyze the massive amount of public Covid-19 media reports over the Cloud. This framework encompasses four modules, including text preprocessing, deep learning, and machine learning-based news information extraction, and recommendation. We conducted experiments to evaluate three modules of our framework and the results we have obtained prove that combining derived information from the news reports provides the policymakers, health authorities, and the public, a complete picture of the way this virus is proliferating. Analyzing this data swiftly is a powerful tool to provide imperative answers to questions that are relevant to public health.","PeriodicalId":54281,"journal":{"name":"IEEE Cloud Computing","volume":"54 1","pages":"7-12"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80859381","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：