Pub Date : 2019-10-01DOI: 10.1109/ROEDUNET.2019.8909595
Mostafa Abdulghafoor Mohammed, Inas Mohammed, Raed Abdulkareem Hasan, N. Tapus, Ahmed Ali, Omar A. Hammood
Mobile offloading is a platform that facilitates the distribution of computationally intensive tasks from mobile devices to the cloud or other devices in order to conserve energy and improve performance. The concept is practically based on the idea of exchanging relatively low communication energy for high computation power utilization. Efforts have been channeled towards energy conservation by clusters using Dynamic Power Management (DPM). This paper is a review for green energy sources for reducing energy and using energy consumption to manage sources by stating the latest studies of energy consumption and energy consumptions.
{"title":"Green Energy Sources: Issues and Challenges","authors":"Mostafa Abdulghafoor Mohammed, Inas Mohammed, Raed Abdulkareem Hasan, N. Tapus, Ahmed Ali, Omar A. Hammood","doi":"10.1109/ROEDUNET.2019.8909595","DOIUrl":"https://doi.org/10.1109/ROEDUNET.2019.8909595","url":null,"abstract":"Mobile offloading is a platform that facilitates the distribution of computationally intensive tasks from mobile devices to the cloud or other devices in order to conserve energy and improve performance. The concept is practically based on the idea of exchanging relatively low communication energy for high computation power utilization. Efforts have been channeled towards energy conservation by clusters using Dynamic Power Management (DPM). This paper is a review for green energy sources for reducing energy and using energy consumption to manage sources by stating the latest studies of energy consumption and energy consumptions.","PeriodicalId":309683,"journal":{"name":"2019 18th RoEduNet Conference: Networking in Education and Research (RoEduNet)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128793853","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 : 2019-10-01DOI: 10.1109/ROEDUNET.2019.8909463
V. Stefanescu, I. Radoi
Nowadays, stress is one of the main concerns when it comes to people's well-being and health. Knowing beforehand which events may cause stress, can be helpful in managing it. This paper aims to provide a solution for predicting stress levels caused by future events. We are proposing a system targeted at a representative test scenario for this problem, which uses calendar events and heart-rate variation data from wearables to offer predictions on stress levels for future events. This test scenario has a wide applicability as the majority of individuals in modern societies have desk jobs, and a significant part of their daily activities is recorded in their digital calendars. The system consists of a microservices data gathering infrastructure and a random forest algorithm for correlating heart-rate variations to calendar events. A dataset including data from 2 employees of a tech company over a period of one year, having attended a total of 1053 meetings, was used for evaluating the proposed system. The accuracy of the heart-rate sensors used in this study was validated against a professional electrocardiogram device. Our selected machine learning model for predicting heart rate variations for future events, trained on only 400 events, shows errors of less than 12 heart beats per minute 90% of the times. This represents a good performance considering the high heart rate variation when exposed to stress. Furthermore, we have performed our own validation experiment for the correlation of heart rate to stress, which revealed a strong positive correlation of 0.793. This offers us further confirmation that our system is capable of providing indicative estimations of stress levels for future events.
{"title":"Stress Level Prediction Using Data From Wearables","authors":"V. Stefanescu, I. Radoi","doi":"10.1109/ROEDUNET.2019.8909463","DOIUrl":"https://doi.org/10.1109/ROEDUNET.2019.8909463","url":null,"abstract":"Nowadays, stress is one of the main concerns when it comes to people's well-being and health. Knowing beforehand which events may cause stress, can be helpful in managing it. This paper aims to provide a solution for predicting stress levels caused by future events. We are proposing a system targeted at a representative test scenario for this problem, which uses calendar events and heart-rate variation data from wearables to offer predictions on stress levels for future events. This test scenario has a wide applicability as the majority of individuals in modern societies have desk jobs, and a significant part of their daily activities is recorded in their digital calendars. The system consists of a microservices data gathering infrastructure and a random forest algorithm for correlating heart-rate variations to calendar events. A dataset including data from 2 employees of a tech company over a period of one year, having attended a total of 1053 meetings, was used for evaluating the proposed system. The accuracy of the heart-rate sensors used in this study was validated against a professional electrocardiogram device. Our selected machine learning model for predicting heart rate variations for future events, trained on only 400 events, shows errors of less than 12 heart beats per minute 90% of the times. This represents a good performance considering the high heart rate variation when exposed to stress. Furthermore, we have performed our own validation experiment for the correlation of heart rate to stress, which revealed a strong positive correlation of 0.793. This offers us further confirmation that our system is capable of providing indicative estimations of stress levels for future events.","PeriodicalId":309683,"journal":{"name":"2019 18th RoEduNet Conference: Networking in Education and Research (RoEduNet)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129016987","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 : 2019-10-01DOI: 10.1109/ROEDUNET.2019.8909672
M. Marin, Costin Carabas, Răzvan Deaconescu, N. Tapus
In this paper we propose a solution to support iOS developers in creating better applications, to use static analysis to investigate source code and detect secure coding issues while simultaneously pointing out good practices and/or secure APIs they should use.
{"title":"Proactive Secure Coding for iOS Applications","authors":"M. Marin, Costin Carabas, Răzvan Deaconescu, N. Tapus","doi":"10.1109/ROEDUNET.2019.8909672","DOIUrl":"https://doi.org/10.1109/ROEDUNET.2019.8909672","url":null,"abstract":"In this paper we propose a solution to support iOS developers in creating better applications, to use static analysis to investigate source code and detect secure coding issues while simultaneously pointing out good practices and/or secure APIs they should use.","PeriodicalId":309683,"journal":{"name":"2019 18th RoEduNet Conference: Networking in Education and Research (RoEduNet)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124037311","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 : 2019-10-01DOI: 10.1109/ROEDUNET.2019.8909424
Eduard Cojocea, Stefan Hornea, Traian Rebedea
Understanding consumer behavior has always been a major concern for any business. Although in the last decades there has been a steep rise in online shopping and online marketing, a big chunk of the revenue for retailers still comes from traditional, in-store shopping. As such, analyzing and understanding the flow of customers inside supermarkets and stores can offer invaluable insights regarding their business and customer behavior to retailers. With the rise of smart IoT devices that allow live recording of video streams and even processing these streams on-edge, analyzing people flows in the hyperspace of crowd size, person categories (by sex and age), person location and time can prove to be an essential tool for decision makers. This paper presents a method for performing people flow analysis using deep learning for person recognition and profiling. The proposed method is encapsulated in a platform that can analyze the people flow on-edge or on a central server with powerful GPUs. The platform also encompasses several business intelligence graphical dashboards for presenting and analyzing the resulted time series data. Our preliminary findings show that on-edge processing, on embedded devices, is a plausible alternative to central processing with GPUs. Despite having lower performance, both in term of mean average precision and frames per second, embedded devices and the corresponding algorithms still manage to achieve reasonable results, while being cheaper and significantly more power efficient. Having this said, the most reasonable conclusion is to combine the two solutions mentioned above into a hybrid approach.
{"title":"Balancing between centralized vs. edge processing in IoT platforms with applicability in advanced people flow analysis","authors":"Eduard Cojocea, Stefan Hornea, Traian Rebedea","doi":"10.1109/ROEDUNET.2019.8909424","DOIUrl":"https://doi.org/10.1109/ROEDUNET.2019.8909424","url":null,"abstract":"Understanding consumer behavior has always been a major concern for any business. Although in the last decades there has been a steep rise in online shopping and online marketing, a big chunk of the revenue for retailers still comes from traditional, in-store shopping. As such, analyzing and understanding the flow of customers inside supermarkets and stores can offer invaluable insights regarding their business and customer behavior to retailers. With the rise of smart IoT devices that allow live recording of video streams and even processing these streams on-edge, analyzing people flows in the hyperspace of crowd size, person categories (by sex and age), person location and time can prove to be an essential tool for decision makers. This paper presents a method for performing people flow analysis using deep learning for person recognition and profiling. The proposed method is encapsulated in a platform that can analyze the people flow on-edge or on a central server with powerful GPUs. The platform also encompasses several business intelligence graphical dashboards for presenting and analyzing the resulted time series data. Our preliminary findings show that on-edge processing, on embedded devices, is a plausible alternative to central processing with GPUs. Despite having lower performance, both in term of mean average precision and frames per second, embedded devices and the corresponding algorithms still manage to achieve reasonable results, while being cheaper and significantly more power efficient. Having this said, the most reasonable conclusion is to combine the two solutions mentioned above into a hybrid approach.","PeriodicalId":309683,"journal":{"name":"2019 18th RoEduNet Conference: Networking in Education and Research (RoEduNet)","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128485658","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 : 2019-10-01DOI: 10.1109/ROEDUNET.2019.8909664
Giorgiana Violeta Vlasceanu, R. Paraschiv, Cristina Artene, C. Boiangiu
The edge detection algorithms stand on convolving the input image with a filter for a specific direction. With the present scenario, no solution can grant the best output for various types of input image. Then, diverse algorithms have been implemented for a specific approach and have a good result only on a specific dataset and a selected filter. We can evaluate the behavior of an algorithm based on different types of images and in this way, we could choose the best candidate from all the results. The voting algorithm uses weighted, majority and unanimous votes. The general propose of this voting mechanism is to increase the accuracy of the output. This paper proposes a voting mechanism that chooses the best candidates from all available ones and selects the relevant result from a pool of intermediate outputs from well-known techniques.
{"title":"Voting-based edge detection","authors":"Giorgiana Violeta Vlasceanu, R. Paraschiv, Cristina Artene, C. Boiangiu","doi":"10.1109/ROEDUNET.2019.8909664","DOIUrl":"https://doi.org/10.1109/ROEDUNET.2019.8909664","url":null,"abstract":"The edge detection algorithms stand on convolving the input image with a filter for a specific direction. With the present scenario, no solution can grant the best output for various types of input image. Then, diverse algorithms have been implemented for a specific approach and have a good result only on a specific dataset and a selected filter. We can evaluate the behavior of an algorithm based on different types of images and in this way, we could choose the best candidate from all the results. The voting algorithm uses weighted, majority and unanimous votes. The general propose of this voting mechanism is to increase the accuracy of the output. This paper proposes a voting mechanism that chooses the best candidates from all available ones and selects the relevant result from a pool of intermediate outputs from well-known techniques.","PeriodicalId":309683,"journal":{"name":"2019 18th RoEduNet Conference: Networking in Education and Research (RoEduNet)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123076267","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 : 2019-10-01DOI: 10.1109/ROEDUNET.2019.8909670
F. B. Manolache, O. Rusu
Backup systems are vital for ensuring data life and usability. Most modern backup software is still laborious to configure, takes a lot of effort to continuously monitor and adjust, and is excessively prone to failure due to insufficient resources or due to hardware problems. This paper presents strategies driving an adaptive backup system that is able to auto-configure, self-monitor, and adapt itself to various conditions, with little human intervention and with very simple initial setup. The main discussion is around the hierarchical structure of the balancing problems that must be solved by the backup system, such that it can adapt to the changing work conditions. Authors propose the Dual Standard Model for automated balancing decisions, which has a striking similarity with human behavior. The software is used in production on a large network containing 1k+ Linux desktops, servers, and clusters at Carnegie Mellon University.
{"title":"Double Standard Method for Designing Adaptive Backup Systems","authors":"F. B. Manolache, O. Rusu","doi":"10.1109/ROEDUNET.2019.8909670","DOIUrl":"https://doi.org/10.1109/ROEDUNET.2019.8909670","url":null,"abstract":"Backup systems are vital for ensuring data life and usability. Most modern backup software is still laborious to configure, takes a lot of effort to continuously monitor and adjust, and is excessively prone to failure due to insufficient resources or due to hardware problems. This paper presents strategies driving an adaptive backup system that is able to auto-configure, self-monitor, and adapt itself to various conditions, with little human intervention and with very simple initial setup. The main discussion is around the hierarchical structure of the balancing problems that must be solved by the backup system, such that it can adapt to the changing work conditions. Authors propose the Dual Standard Model for automated balancing decisions, which has a striking similarity with human behavior. The software is used in production on a large network containing 1k+ Linux desktops, servers, and clusters at Carnegie Mellon University.","PeriodicalId":309683,"journal":{"name":"2019 18th RoEduNet Conference: Networking in Education and Research (RoEduNet)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115390292","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 : 2019-10-01DOI: 10.1109/roedunet.2019.8909394
{"title":"RoEduNet 2019 Committees","authors":"","doi":"10.1109/roedunet.2019.8909394","DOIUrl":"https://doi.org/10.1109/roedunet.2019.8909394","url":null,"abstract":"","PeriodicalId":309683,"journal":{"name":"2019 18th RoEduNet Conference: Networking in Education and Research (RoEduNet)","volume":"215 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123628356","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 : 2019-10-01DOI: 10.1109/ROEDUNET.2019.8909609
R. Radu, Octavian Grigorescu, R. Rughinis
The total cost of cyber-attacks reached in 2018 at a global level the total sum of one trillion dollars, 95% of those attacks being due to human errors. Security News Aggregator is a security news platform, which aims to maintain the users up to date regarding new attacks, vulnerabilities, breaches or CVEs, that could possibly affect them. The news that are displayed are filtered and only those with a relevant character are kept, such as zero-day attacks, which are actively exploited in the wild, recently made public vulnerabilities, ultimate attacks and data breaches, but also news regarding urgent patches, that the user should be aware of. Further on, the news is being prioritized, in this way solving the problem of the huge quantity of new information that emerges on a daily basis.
{"title":"Security News Aggregator","authors":"R. Radu, Octavian Grigorescu, R. Rughinis","doi":"10.1109/ROEDUNET.2019.8909609","DOIUrl":"https://doi.org/10.1109/ROEDUNET.2019.8909609","url":null,"abstract":"The total cost of cyber-attacks reached in 2018 at a global level the total sum of one trillion dollars, 95% of those attacks being due to human errors. Security News Aggregator is a security news platform, which aims to maintain the users up to date regarding new attacks, vulnerabilities, breaches or CVEs, that could possibly affect them. The news that are displayed are filtered and only those with a relevant character are kept, such as zero-day attacks, which are actively exploited in the wild, recently made public vulnerabilities, ultimate attacks and data breaches, but also news regarding urgent patches, that the user should be aware of. Further on, the news is being prioritized, in this way solving the problem of the huge quantity of new information that emerges on a daily basis.","PeriodicalId":309683,"journal":{"name":"2019 18th RoEduNet Conference: Networking in Education and Research (RoEduNet)","volume":"142 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124538731","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 : 2019-10-01DOI: 10.1109/ROEDUNET.2019.8909476
Eusebiu Jecan, C. Pop, Z. Padrah, Mircea Vlasin, Ovidiu Ratiu, E. Puschita
In order to protect industrial wireless sensor networks against single point of failure, system redundancy implies duplicate Gateway entities and the implementation of a communication protocol that defines and updates the network state. The scope of this paper is to present the design of a redundancy protocol integrated within two hardware entities respecting the ISA100.11a Gateway functionalities. Two types of system redundancy were evaluated considering physical all-in-one Gateway entities, namely cold-redundancy and hot-redundancy. These features reflect the ability of the entire system and MODBUS Server respectively, to react in case of failure by assuring network state, synchronization services, and seamless switchover for the external clients. The performance of the redundancy protocol and its impact on the ISA100.11a network was evaluated in three scenarios that emphasize on the ability of the redundant system to maintain effective communication and recover in case of failure.
{"title":"Redundancy for an all-in-one ISA100.11a Gateway: Protocol Design and Hardware Integration","authors":"Eusebiu Jecan, C. Pop, Z. Padrah, Mircea Vlasin, Ovidiu Ratiu, E. Puschita","doi":"10.1109/ROEDUNET.2019.8909476","DOIUrl":"https://doi.org/10.1109/ROEDUNET.2019.8909476","url":null,"abstract":"In order to protect industrial wireless sensor networks against single point of failure, system redundancy implies duplicate Gateway entities and the implementation of a communication protocol that defines and updates the network state. The scope of this paper is to present the design of a redundancy protocol integrated within two hardware entities respecting the ISA100.11a Gateway functionalities. Two types of system redundancy were evaluated considering physical all-in-one Gateway entities, namely cold-redundancy and hot-redundancy. These features reflect the ability of the entire system and MODBUS Server respectively, to react in case of failure by assuring network state, synchronization services, and seamless switchover for the external clients. The performance of the redundancy protocol and its impact on the ISA100.11a network was evaluated in three scenarios that emphasize on the ability of the redundant system to maintain effective communication and recover in case of failure.","PeriodicalId":309683,"journal":{"name":"2019 18th RoEduNet Conference: Networking in Education and Research (RoEduNet)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121291611","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 : 2019-10-01DOI: 10.1109/ROEDUNET.2019.8909644
Alina L. Machidon, C. Ciobanu, O. Machidon, P. Ogrutan
Remote sensing data has known an explosive growth in the past decade. This has led to the need for efficient dimensionality reduction techniques, mathematical procedures that transform the high-dimensional data into a meaningful, reduced representation. Principal Component Analysis (PCA) is a well-known dimensionality reduction technique used in the field of hyperspectral satellite images. However, PCA suffers from high computational costs and increased complexity, an issue that led to elaborating PCA adaptations capable of running on multi-core computing architectures. This paper proposes a parallel implementation of the geometrical PCA approximation (gaPCA) algorithm. Three parallel implementations are studied: two on multi-core CPUs and a NVIDIA Graphics Processing Units (GPU) CUDA accelerated implementation. Our results show significant speedups of the parallel implementations when applied on hyperspectral image datasets. Our results show that on the Intel Core i5 CPU, Python multi-core implementation is up to 2.01$times$ faster than its Matlab equivalent. Our GPU PyCUDA implementation is considerably faster than both our Python multi-core CPU implementations: up to 1.76$times$ faster than Intel Core i5-6200U and up to 5.72$times$ faster than the NVIDIA Jetson Nano quad-core ARM A53 CPU. We performed data analysis on the output data for the three methods and the maxim relative error was less than 0.001%.
{"title":"On Parallelizing Geometrical PCA Approximation","authors":"Alina L. Machidon, C. Ciobanu, O. Machidon, P. Ogrutan","doi":"10.1109/ROEDUNET.2019.8909644","DOIUrl":"https://doi.org/10.1109/ROEDUNET.2019.8909644","url":null,"abstract":"Remote sensing data has known an explosive growth in the past decade. This has led to the need for efficient dimensionality reduction techniques, mathematical procedures that transform the high-dimensional data into a meaningful, reduced representation. Principal Component Analysis (PCA) is a well-known dimensionality reduction technique used in the field of hyperspectral satellite images. However, PCA suffers from high computational costs and increased complexity, an issue that led to elaborating PCA adaptations capable of running on multi-core computing architectures. This paper proposes a parallel implementation of the geometrical PCA approximation (gaPCA) algorithm. Three parallel implementations are studied: two on multi-core CPUs and a NVIDIA Graphics Processing Units (GPU) CUDA accelerated implementation. Our results show significant speedups of the parallel implementations when applied on hyperspectral image datasets. Our results show that on the Intel Core i5 CPU, Python multi-core implementation is up to 2.01$times$ faster than its Matlab equivalent. Our GPU PyCUDA implementation is considerably faster than both our Python multi-core CPU implementations: up to 1.76$times$ faster than Intel Core i5-6200U and up to 5.72$times$ faster than the NVIDIA Jetson Nano quad-core ARM A53 CPU. We performed data analysis on the output data for the three methods and the maxim relative error was less than 0.001%.","PeriodicalId":309683,"journal":{"name":"2019 18th RoEduNet Conference: Networking in Education and Research (RoEduNet)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128358564","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：