Pub Date : 2020-11-24DOI: 10.1109/CloudTech49835.2020.9365911
El Hadrami Cheikh Tourad, M. Eleuldj
Deep learning has recently indicated that FPGAs (Field-Programmable Gate Arrays) play a significant role in accelerating DLNNs (Deep Learning Neural Networks). The initial specification of DLNN is usually done using a high-level language such as python, followed by a manual transformation to HDL (Hardware Description Language) for synthesis using a vendor tool. This transformation is tedious and needs HDL expertise, which limits the relevance of FPGAs. This paper presents an updated survey of the existing frameworks for mapping DLNNs onto FPGAs, comparing their characteristics, architectural choices, and achieved performance. Besides, we provide a comprehensive evaluation of different tools and their effectiveness for mapping DLNNs onto FPGAs. Finally, we present the future works.
{"title":"Survey of Deep Learning Neural Networks Implementation on FPGAs","authors":"El Hadrami Cheikh Tourad, M. Eleuldj","doi":"10.1109/CloudTech49835.2020.9365911","DOIUrl":"https://doi.org/10.1109/CloudTech49835.2020.9365911","url":null,"abstract":"Deep learning has recently indicated that FPGAs (Field-Programmable Gate Arrays) play a significant role in accelerating DLNNs (Deep Learning Neural Networks). The initial specification of DLNN is usually done using a high-level language such as python, followed by a manual transformation to HDL (Hardware Description Language) for synthesis using a vendor tool. This transformation is tedious and needs HDL expertise, which limits the relevance of FPGAs. This paper presents an updated survey of the existing frameworks for mapping DLNNs onto FPGAs, comparing their characteristics, architectural choices, and achieved performance. Besides, we provide a comprehensive evaluation of different tools and their effectiveness for mapping DLNNs onto FPGAs. Finally, we present the future works.","PeriodicalId":272860,"journal":{"name":"2020 5th International Conference on Cloud Computing and Artificial Intelligence: Technologies and Applications (CloudTech)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116266774","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 : 2020-11-24DOI: 10.1109/CloudTech49835.2020.9365923
K. Hafdi, Abderahman Kriouile
Several cities in the world are moving from traditional power grid to Smart Grids. In order to set up Smart Grids, we should be able to face many challenges related to reliability, scalability, dynamism, technological solutions, security, etc. In this paper, we propose a case study where we model a micro Smart Grid according to the ReDy architecture, which is intended for IoT applications. The ReDy architecture provides a base to implement a scalable, reliable, and dynamic IoT network ready to meet Smart Grid needs. In order to prove those requirements, we opted for formal modeling and validation approach using model checking techniques. This formal analysis is carried out using the CADP toolbox.
{"title":"Formal Modeling and Validation of Micro Smart Grids Based on ReDy Architecture","authors":"K. Hafdi, Abderahman Kriouile","doi":"10.1109/CloudTech49835.2020.9365923","DOIUrl":"https://doi.org/10.1109/CloudTech49835.2020.9365923","url":null,"abstract":"Several cities in the world are moving from traditional power grid to Smart Grids. In order to set up Smart Grids, we should be able to face many challenges related to reliability, scalability, dynamism, technological solutions, security, etc. In this paper, we propose a case study where we model a micro Smart Grid according to the ReDy architecture, which is intended for IoT applications. The ReDy architecture provides a base to implement a scalable, reliable, and dynamic IoT network ready to meet Smart Grid needs. In order to prove those requirements, we opted for formal modeling and validation approach using model checking techniques. This formal analysis is carried out using the CADP toolbox.","PeriodicalId":272860,"journal":{"name":"2020 5th International Conference on Cloud Computing and Artificial Intelligence: Technologies and Applications (CloudTech)","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125082719","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 : 2020-11-24DOI: 10.1109/CloudTech49835.2020.9365899
Abdelali Hadir, K. Zine-dine, M. Bakhouya
The accurate position of nodes in Wireless Sensor Networks (WSNs) is considered a critical problem in the majority of the Internet of Things (IoT) applications. Recently a large number of contribution in localization have been recommended to determine the location of nodes. However, a number determinated of these techniques have been presented to precisely determine the nodes locations in the IoT. In this work, we discuss the new three localization techniques, named Centroid + 4A, ICentroid, and ICentroid + 4A respectively, based on the Centroid localization technique and a new weighted formula to estimate the target nodes’ positions. The OMNeT++ network simulator was used to figure out and the performance of the discussed solutions in comparison with the Centroid localization technique. The examined results reveal that a significant improvement in the localization precision of the discussed contributions in Wireless Sensor Networks.
{"title":"Improvements of Centroid Localization Algorithm for Wireless Sensor Networks","authors":"Abdelali Hadir, K. Zine-dine, M. Bakhouya","doi":"10.1109/CloudTech49835.2020.9365899","DOIUrl":"https://doi.org/10.1109/CloudTech49835.2020.9365899","url":null,"abstract":"The accurate position of nodes in Wireless Sensor Networks (WSNs) is considered a critical problem in the majority of the Internet of Things (IoT) applications. Recently a large number of contribution in localization have been recommended to determine the location of nodes. However, a number determinated of these techniques have been presented to precisely determine the nodes locations in the IoT. In this work, we discuss the new three localization techniques, named Centroid + 4A, ICentroid, and ICentroid + 4A respectively, based on the Centroid localization technique and a new weighted formula to estimate the target nodes’ positions. The OMNeT++ network simulator was used to figure out and the performance of the discussed solutions in comparison with the Centroid localization technique. The examined results reveal that a significant improvement in the localization precision of the discussed contributions in Wireless Sensor Networks.","PeriodicalId":272860,"journal":{"name":"2020 5th International Conference on Cloud Computing and Artificial Intelligence: Technologies and Applications (CloudTech)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126700963","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 : 2020-11-24DOI: 10.1109/CloudTech49835.2020.9365895
A. E. Ghazi, Ait Moulay Rachid
By 2025 Internet of things will reach over 75 billion devices which would exceed number of humans about 8.1 billion. These devices need to be secured from many threats by implementing secure and interoperable solutions in order to guarantee a proper functioning of the infrastructures and systems using the IoT. This is why we proposed a hybrid intrusion detection system installed on the cloud powering another online and real time intrusion detection system on the fog to monitor the communication and detect attacks before it spreads over the network as in the case of Mirai botnet. We will provide details of the different algorithms used to implement this distributed system so as to detect attacks against IoT devices.
{"title":"Machine learning and datamining methods for hybrid IoT intrusion detection","authors":"A. E. Ghazi, Ait Moulay Rachid","doi":"10.1109/CloudTech49835.2020.9365895","DOIUrl":"https://doi.org/10.1109/CloudTech49835.2020.9365895","url":null,"abstract":"By 2025 Internet of things will reach over 75 billion devices which would exceed number of humans about 8.1 billion. These devices need to be secured from many threats by implementing secure and interoperable solutions in order to guarantee a proper functioning of the infrastructures and systems using the IoT. This is why we proposed a hybrid intrusion detection system installed on the cloud powering another online and real time intrusion detection system on the fog to monitor the communication and detect attacks before it spreads over the network as in the case of Mirai botnet. We will provide details of the different algorithms used to implement this distributed system so as to detect attacks against IoT devices.","PeriodicalId":272860,"journal":{"name":"2020 5th International Conference on Cloud Computing and Artificial Intelligence: Technologies and Applications (CloudTech)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128442559","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 : 2020-11-24DOI: 10.1109/CloudTech49835.2020.9365892
Rachida Ait Abdelouahid, Olivier Debauche, S. Mahmoudi, A. Marzak, P. Manneback, F. Lebeau
Phytotrons are culture chambers used by re-searchers in which ambient parameters such as temperature, humidity, irrigation, electrical conductivity of the nutrient solution, pH, lighting and CO2 are finely controlled. In addition, these installations make it possible on the one hand to measure the impact of environmental changes, and on the other hand to optimize the growth of plants in artificial growing conditions. Thanks to the democratization of hardware, cloud computing and the new possibilities offered by the Internet of Things (IoT), it is now possible to build a personal phytotron at an affordable cost. In this article, we propose to use connected objects to develop a personal growth chamber in order to produce fresh vegetables in an urban context.
{"title":"Open Phytotron: A New IoT Device for Home Gardening","authors":"Rachida Ait Abdelouahid, Olivier Debauche, S. Mahmoudi, A. Marzak, P. Manneback, F. Lebeau","doi":"10.1109/CloudTech49835.2020.9365892","DOIUrl":"https://doi.org/10.1109/CloudTech49835.2020.9365892","url":null,"abstract":"Phytotrons are culture chambers used by re-searchers in which ambient parameters such as temperature, humidity, irrigation, electrical conductivity of the nutrient solution, pH, lighting and CO2 are finely controlled. In addition, these installations make it possible on the one hand to measure the impact of environmental changes, and on the other hand to optimize the growth of plants in artificial growing conditions. Thanks to the democratization of hardware, cloud computing and the new possibilities offered by the Internet of Things (IoT), it is now possible to build a personal phytotron at an affordable cost. In this article, we propose to use connected objects to develop a personal growth chamber in order to produce fresh vegetables in an urban context.","PeriodicalId":272860,"journal":{"name":"2020 5th International Conference on Cloud Computing and Artificial Intelligence: Technologies and Applications (CloudTech)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121738238","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：