Pub Date : 2020-10-24DOI: 10.1109/NILES50944.2020.9257931
Ali M. Alargrami, Maged M. Eljazzar
This paper can be considered one of the first works to introduce an efficient distributed word representation model for different NLP tasks in the islamic domain. The Word Embedding Model and the algorithm on top of it is implemented in Imam application where user can ask the application to search for any data related to Isalmic domain and get an answer. The data is gathered from different resources (Maliks muwataa, Musnad Ahmad Ibn-hanbal, Sahih Muslim ahadith, Sahih Al-bukhari, Sunan Al-darimi, and more). The amount of records gathered was more than ninety thousand documents (Text Blocks) from 10 different books.After several sequential pipeline processes of Data cleaning, preprocessing and Normalization, Skip-gram technique was used to built the word2vec model and then At last tested with different methods, first by using the K-means clustering and then nonlinear dimensionality reduction technique to represent the data in 2D dimension, secondly by using word similarity to test model ability to understand the Quranic language. The tests clearly show that the model can be used effectively in different NLP Arabic Islamic tasks.
本文可以被认为是首次为伊斯兰领域的不同NLP任务引入高效的分布式词表示模型的工作之一。在Imam应用程序中实现了Word嵌入模型及其算法，用户可以要求该应用程序搜索与伊斯兰域相关的任何数据并获得答案。数据收集自不同的资源(malik muwataa, Musnad Ahmad Ibn-hanbal, Sahih Muslim ahadith, Sahih Al-bukhari, Sunan Al-darimi等)。收集的记录数量是来自10种不同书籍的9万多份文件(文本块)。通过数据清洗、预处理、归一化等一系列流水线过程，采用Skip-gram技术构建word2vec模型，最后采用不同的方法进行测试，首先采用K-means聚类，然后采用非线性降维技术对数据进行二维表示，其次采用词相似度测试模型对古兰经语言的理解能力。实验结果表明，该模型可以有效地应用于不同的NLP阿拉伯语和伊斯兰语任务。
{"title":"Imam: Word Embedding Model for Islamic Arabic NLP","authors":"Ali M. Alargrami, Maged M. Eljazzar","doi":"10.1109/NILES50944.2020.9257931","DOIUrl":"https://doi.org/10.1109/NILES50944.2020.9257931","url":null,"abstract":"This paper can be considered one of the first works to introduce an efficient distributed word representation model for different NLP tasks in the islamic domain. The Word Embedding Model and the algorithm on top of it is implemented in Imam application where user can ask the application to search for any data related to Isalmic domain and get an answer. The data is gathered from different resources (Maliks muwataa, Musnad Ahmad Ibn-hanbal, Sahih Muslim ahadith, Sahih Al-bukhari, Sunan Al-darimi, and more). The amount of records gathered was more than ninety thousand documents (Text Blocks) from 10 different books.After several sequential pipeline processes of Data cleaning, preprocessing and Normalization, Skip-gram technique was used to built the word2vec model and then At last tested with different methods, first by using the K-means clustering and then nonlinear dimensionality reduction technique to represent the data in 2D dimension, secondly by using word similarity to test model ability to understand the Quranic language. The tests clearly show that the model can be used effectively in different NLP Arabic Islamic tasks.","PeriodicalId":253090,"journal":{"name":"2020 2nd Novel Intelligent and Leading Emerging Sciences Conference (NILES)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124460773","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 : 2020-10-24DOI: 10.1109/NILES50944.2020.9257930
Saddam Bekhet, M. Hassaballah, Mourad A. Kenk, Mohamed Abdel Hameed
The COVID-19 pandemic had a catastrophic impact on world health and economic. This is attributed to the unavoidable delay in the diagnosis process, due to limitation of COVID-19 test kits. Thus, it is urgently required to establish more cheap and affordable diagnostic approaches. Chest X-ray is an important initial step towards a successful COVID-19 diagnose, where it is easily to detect any chest abnormalities (e.g., lung inflammation). Furthermore, majority of hospitals have X-ray devices that can be used in early COVID-19 diagnosis. However, the shortage of radiologists is a key factor that limits early COVID-19 diagnosis and negatively affects the treatment process. This paper presents an artificial intelligence based technique for early COVID-19 diagnosis from chest X-ray images using medical knowledge and deep Convolutional Neural Networks (CNNs). To this end, a deep learning model is built carefully and fine-tuned to achieve the maximum performance in COVID-19 detection. Experimental results on recent benchmark datasets demonstrate the superior performance of the proposed technique in identifying COVID-19 with 96% accuracy.
{"title":"An Artificial Intelligence Based Technique for COVID-19 Diagnosis from Chest X-Ray","authors":"Saddam Bekhet, M. Hassaballah, Mourad A. Kenk, Mohamed Abdel Hameed","doi":"10.1109/NILES50944.2020.9257930","DOIUrl":"https://doi.org/10.1109/NILES50944.2020.9257930","url":null,"abstract":"The COVID-19 pandemic had a catastrophic impact on world health and economic. This is attributed to the unavoidable delay in the diagnosis process, due to limitation of COVID-19 test kits. Thus, it is urgently required to establish more cheap and affordable diagnostic approaches. Chest X-ray is an important initial step towards a successful COVID-19 diagnose, where it is easily to detect any chest abnormalities (e.g., lung inflammation). Furthermore, majority of hospitals have X-ray devices that can be used in early COVID-19 diagnosis. However, the shortage of radiologists is a key factor that limits early COVID-19 diagnosis and negatively affects the treatment process. This paper presents an artificial intelligence based technique for early COVID-19 diagnosis from chest X-ray images using medical knowledge and deep Convolutional Neural Networks (CNNs). To this end, a deep learning model is built carefully and fine-tuned to achieve the maximum performance in COVID-19 detection. Experimental results on recent benchmark datasets demonstrate the superior performance of the proposed technique in identifying COVID-19 with 96% accuracy.","PeriodicalId":253090,"journal":{"name":"2020 2nd Novel Intelligent and Leading Emerging Sciences Conference (NILES)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117064085","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 : 2020-10-24DOI: 10.1109/NILES50944.2020.9257948
Marwa Zamzam, T. el-Shabrawy, M. Ashour
The topic of localization within indoor environments has recently received significant attention as localization has become an essential component of many Internet of Things applications such as object tracking and health care management. One of the promising approach to provide accurate localization while minimizing energy consumption is to use computational offloading under mobile edge computing system. Thus, the aim of this paper is to minimize the total energy consumption of multiple users by using computation offloading technique between users, mobile edge computing servers and cloud server. The offloading technique that is proposed in this paper should take in consideration users’ accuracy, latency requirements and the maximum capacity of each server. The paper presents the network model and the computation model of the proposed system. Then, the problem formulation is introduced to minimize the total energy consumption which is the sum of all energy consumed by the users in the local devices and the offloaded servers. In order to provide a distributed implementation that is more suitable for the users within localization environment, the paper formulates the proposed problem as a potential game and the existence of Nash Equilibrium is proved where all users have satisfied offloading decision. The paper obtains the optimal solution to act as a reference for the proposed potential game algorithm. Finally, the paper presents and analyzes the results of the potential game distributed computational offloading algorithm by comparing it to local computing, random offloading and the optimal solution techniques.
{"title":"Energy-Efficient Computation Offloading for Indoor Localization Based on Game Theory","authors":"Marwa Zamzam, T. el-Shabrawy, M. Ashour","doi":"10.1109/NILES50944.2020.9257948","DOIUrl":"https://doi.org/10.1109/NILES50944.2020.9257948","url":null,"abstract":"The topic of localization within indoor environments has recently received significant attention as localization has become an essential component of many Internet of Things applications such as object tracking and health care management. One of the promising approach to provide accurate localization while minimizing energy consumption is to use computational offloading under mobile edge computing system. Thus, the aim of this paper is to minimize the total energy consumption of multiple users by using computation offloading technique between users, mobile edge computing servers and cloud server. The offloading technique that is proposed in this paper should take in consideration users’ accuracy, latency requirements and the maximum capacity of each server. The paper presents the network model and the computation model of the proposed system. Then, the problem formulation is introduced to minimize the total energy consumption which is the sum of all energy consumed by the users in the local devices and the offloaded servers. In order to provide a distributed implementation that is more suitable for the users within localization environment, the paper formulates the proposed problem as a potential game and the existence of Nash Equilibrium is proved where all users have satisfied offloading decision. The paper obtains the optimal solution to act as a reference for the proposed potential game algorithm. Finally, the paper presents and analyzes the results of the potential game distributed computational offloading algorithm by comparing it to local computing, random offloading and the optimal solution techniques.","PeriodicalId":253090,"journal":{"name":"2020 2nd Novel Intelligent and Leading Emerging Sciences Conference (NILES)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127367208","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 : 2020-10-24DOI: 10.1109/NILES50944.2020.9257928
A. A. Muhammad, Amira T. Mahmoud, Shaymaa S. Elkalyouby, Rameez B. Hamza, A. Yousef
Numerous commercial tools like Xamarin, React Native and PhoneGap utilize the concept of cross-platform mobile applications development that builds applications once and runs it everywhere opposed to native mobile app development that writes in a specific programming language for every platform. These commercial tools are not very efficient for native developers as mobile applications must be written in specific language and they need the usage of specific frameworks. In this paper, a suggested approach in TCAIOSC tool to convert mobile applications from Android to iOS is used to develop the reverse path translation. Moreover, native mobile apps functionalities like making a phone call, alert messages, vibration and more functions are tested by using extensive techniques like BLEU and tokens accuracy. Primarily results showed substantial success in code conversion from swift to java.
{"title":"Trans-Compiler based Mobile Applications code converter: swift to java","authors":"A. A. Muhammad, Amira T. Mahmoud, Shaymaa S. Elkalyouby, Rameez B. Hamza, A. Yousef","doi":"10.1109/NILES50944.2020.9257928","DOIUrl":"https://doi.org/10.1109/NILES50944.2020.9257928","url":null,"abstract":"Numerous commercial tools like Xamarin, React Native and PhoneGap utilize the concept of cross-platform mobile applications development that builds applications once and runs it everywhere opposed to native mobile app development that writes in a specific programming language for every platform. These commercial tools are not very efficient for native developers as mobile applications must be written in specific language and they need the usage of specific frameworks. In this paper, a suggested approach in TCAIOSC tool to convert mobile applications from Android to iOS is used to develop the reverse path translation. Moreover, native mobile apps functionalities like making a phone call, alert messages, vibration and more functions are tested by using extensive techniques like BLEU and tokens accuracy. Primarily results showed substantial success in code conversion from swift to java.","PeriodicalId":253090,"journal":{"name":"2020 2nd Novel Intelligent and Leading Emerging Sciences Conference (NILES)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126145437","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 : 2020-10-24DOI: 10.1109/NILES50944.2020.9257881
Mohamed Abuelanin, Mohamed Fares, M. El-Hadidi
Codon optimization is primarily used in enhancing the levels of protein expression in the host species. Each species has its own codon usage bias, which represents the codons abundance frequency in that species. Using the host usage profile contributes to personalize the synthesis of the DNA vaccines that can achieve highly active vectors the host cells. For optimizing protein expression levels in a particular host, the genetic code sequence needs correction of codon frequency bias to match the expression of host codon landscape rather than the donating organism profile. In this work, we have applied two approaches for optimizing codon usage in protein-coding sequences. The first approach adopts a substitution-based method to replace less frequent codons with differentially higher frequency codons at the specific codon usage bias tables. The second approach finds and replaces the maximal exact protein matches between the unoptimized sequence and the host proteome. We evaluated our work by optimizing the Avian Influenza H1N1 virus’s HA gene to maximize the protein expression before synthesizing the DNA vaccine. Our method produced optimized sequences with higher GC content by 17%, which is similar to eukaryotic sequence profiles than the viral usage profiles, allowing for better expression in avian host cells.
{"title":"Insilico Codon Bias Correction for Transgenic Biological Protein Sequences for Vaccine Production","authors":"Mohamed Abuelanin, Mohamed Fares, M. El-Hadidi","doi":"10.1109/NILES50944.2020.9257881","DOIUrl":"https://doi.org/10.1109/NILES50944.2020.9257881","url":null,"abstract":"Codon optimization is primarily used in enhancing the levels of protein expression in the host species. Each species has its own codon usage bias, which represents the codons abundance frequency in that species. Using the host usage profile contributes to personalize the synthesis of the DNA vaccines that can achieve highly active vectors the host cells. For optimizing protein expression levels in a particular host, the genetic code sequence needs correction of codon frequency bias to match the expression of host codon landscape rather than the donating organism profile. In this work, we have applied two approaches for optimizing codon usage in protein-coding sequences. The first approach adopts a substitution-based method to replace less frequent codons with differentially higher frequency codons at the specific codon usage bias tables. The second approach finds and replaces the maximal exact protein matches between the unoptimized sequence and the host proteome. We evaluated our work by optimizing the Avian Influenza H1N1 virus’s HA gene to maximize the protein expression before synthesizing the DNA vaccine. Our method produced optimized sequences with higher GC content by 17%, which is similar to eukaryotic sequence profiles than the viral usage profiles, allowing for better expression in avian host cells.","PeriodicalId":253090,"journal":{"name":"2020 2nd Novel Intelligent and Leading Emerging Sciences Conference (NILES)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115250428","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 : 2020-10-24DOI: 10.1109/NILES50944.2020.9257982
Ahmed W. Ebrahim, I. Arafa, H. Hendy, Y. Elhalwagy
The Inertial Navigation Systems (INS), Global Navigation Satellite System (GNSS) integration becomes very important for high speed flying vehicles as a navigation solution. In this paper, a derivation and modeling of a system model of the integrated system for a 27-states Kalman filter is presented. Sensors (gyroscopes and accelerometers) errors, and GNSS errors are characterized and modeled as well. Results show that some parameters of estimated gyroscopes (gyros) errors such as vertical and east gyro drifts and the estimated east accelerometer bias are not observables. The simulation shows that in the integrated system and the navigation errors in both the INS and GNSS can be estimated with high accuracy. Results analysis proves that the development of state estimation for an Inertial Measuring Unit (IMU) can efficiently supply current motion information (position and attitude states). This efficient information can be used to carry out accurate guidance and control strategies for such a hi-speed flight bodies.
{"title":"Enhancement of Integrated Navigation System for high-speed flying vehicles' Navigation Applications","authors":"Ahmed W. Ebrahim, I. Arafa, H. Hendy, Y. Elhalwagy","doi":"10.1109/NILES50944.2020.9257982","DOIUrl":"https://doi.org/10.1109/NILES50944.2020.9257982","url":null,"abstract":"The Inertial Navigation Systems (INS), Global Navigation Satellite System (GNSS) integration becomes very important for high speed flying vehicles as a navigation solution. In this paper, a derivation and modeling of a system model of the integrated system for a 27-states Kalman filter is presented. Sensors (gyroscopes and accelerometers) errors, and GNSS errors are characterized and modeled as well. Results show that some parameters of estimated gyroscopes (gyros) errors such as vertical and east gyro drifts and the estimated east accelerometer bias are not observables. The simulation shows that in the integrated system and the navigation errors in both the INS and GNSS can be estimated with high accuracy. Results analysis proves that the development of state estimation for an Inertial Measuring Unit (IMU) can efficiently supply current motion information (position and attitude states). This efficient information can be used to carry out accurate guidance and control strategies for such a hi-speed flight bodies.","PeriodicalId":253090,"journal":{"name":"2020 2nd Novel Intelligent and Leading Emerging Sciences Conference (NILES)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122701725","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 : 2020-10-24DOI: 10.1109/NILES50944.2020.9257959
Touka M. A. Mahmoud, Mohamed S. A. Abu-Tafesh, Norhan Mohsen ElOcla, A. Mohamed
Understanding the transmission dynamics of the novel coronavirus is the concern that attracted many researchers nowadays. In this paper, two mathematical models, modified SEIR and logistic growth, were implemented in Matlab to predict the transmission of COYID-19 in Egypt and Oman. To estimate the models’ parameters, the reported data were used to fit the models using Nelder-Mead, Levenberg-Marquardt, and Trust-Region-Reflective optimization algorithms. Then, a sensitivity analysis was made to understand the effect of different parameters on the models’ prediction. The application of the two models on the reported data was compared despite their different nature. It was shown and verified that the two models are highly dependent on the parameters’ values, referring to the importance of determining their estimates using an optimization algorithm. It was found out that the most dominant parameter is the one denoting the rate by which susceptible people are protected, which emphasizes the effect of social distancing and quarantine.
{"title":"Forecasting of COVID-19 in Egypt and Oman using Modified SEIR and Logistic Growth Models","authors":"Touka M. A. Mahmoud, Mohamed S. A. Abu-Tafesh, Norhan Mohsen ElOcla, A. Mohamed","doi":"10.1109/NILES50944.2020.9257959","DOIUrl":"https://doi.org/10.1109/NILES50944.2020.9257959","url":null,"abstract":"Understanding the transmission dynamics of the novel coronavirus is the concern that attracted many researchers nowadays. In this paper, two mathematical models, modified SEIR and logistic growth, were implemented in Matlab to predict the transmission of COYID-19 in Egypt and Oman. To estimate the models’ parameters, the reported data were used to fit the models using Nelder-Mead, Levenberg-Marquardt, and Trust-Region-Reflective optimization algorithms. Then, a sensitivity analysis was made to understand the effect of different parameters on the models’ prediction. The application of the two models on the reported data was compared despite their different nature. It was shown and verified that the two models are highly dependent on the parameters’ values, referring to the importance of determining their estimates using an optimization algorithm. It was found out that the most dominant parameter is the one denoting the rate by which susceptible people are protected, which emphasizes the effect of social distancing and quarantine.","PeriodicalId":253090,"journal":{"name":"2020 2nd Novel Intelligent and Leading Emerging Sciences Conference (NILES)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126977620","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 : 2020-10-24DOI: 10.1109/NILES50944.2020.9257899
Alaa M. Salman, Ahmed S. Tulan, Rana Y. Mohamed, Michael H. Zakhari, H. Mostafa
In recent years convolutional neural networks (CNNs) have been remarkably used in many applications, and they are the heart of many intelligent systems. The advancements in both new electronic design automation (EDA) tools and in new hardware development boards such as Python Productivity for Zynq (PYNQ) have significantly decreased the development time of CNNs. However, the short time-to-market is at the cost of implementation area, performance and power consumption. Over the last period, CNNs’ energy consumption needs have skyrocketed dramatically. Thus, In this work, the authors conduct a comprehensive study on the power consumption of hardware accelerated CNN whether implemented using new EDAs High Level Synthesis (HLS) or the basic design abstraction of Register Transfer Level (RTL). Both methods are implemented on modern development boards from Xilinx (as PYNQ). Modern EDAs flow such as HLS does not represent the best environment for a good power consumption. The power consumption of the HLS implementation is six times more power than the RTL one. It is concluded that the new EDAs method have a deficiency to deliver highly efficient CNNs but it has the ability to deliver sufficient results within a very short period of time.
近年来，卷积神经网络(cnn)在许多应用中得到了显著的应用，它是许多智能系统的核心。新的电子设计自动化(EDA)工具和新的硬件开发板(如Python Productivity for Zynq (PYNQ))的进步大大缩短了cnn的开发时间。然而，上市时间短是以牺牲实现面积、性能和功耗为代价的。在过去的一段时间里，cnn的能源消耗需求急剧上升。因此，在这项工作中，作者对硬件加速CNN的功耗进行了全面的研究，无论是使用新的EDAs High Level Synthesis (HLS)还是Register Transfer Level (RTL)的基本设计抽象来实现。这两种方法都在赛灵思的现代开发板上实现(作为PYNQ)。现代EDAs流(如HLS)并不代表良好功耗的最佳环境。HLS实现的功耗是RTL实现的六倍。结论是，新的EDAs方法在提供高效cnn方面存在不足，但它有能力在很短的时间内提供足够的结果。
{"title":"Comparative Study of Hardware Accelerated Convolution Neural Network on PYNQ Board","authors":"Alaa M. Salman, Ahmed S. Tulan, Rana Y. Mohamed, Michael H. Zakhari, H. Mostafa","doi":"10.1109/NILES50944.2020.9257899","DOIUrl":"https://doi.org/10.1109/NILES50944.2020.9257899","url":null,"abstract":"In recent years convolutional neural networks (CNNs) have been remarkably used in many applications, and they are the heart of many intelligent systems. The advancements in both new electronic design automation (EDA) tools and in new hardware development boards such as Python Productivity for Zynq (PYNQ) have significantly decreased the development time of CNNs. However, the short time-to-market is at the cost of implementation area, performance and power consumption. Over the last period, CNNs’ energy consumption needs have skyrocketed dramatically. Thus, In this work, the authors conduct a comprehensive study on the power consumption of hardware accelerated CNN whether implemented using new EDAs High Level Synthesis (HLS) or the basic design abstraction of Register Transfer Level (RTL). Both methods are implemented on modern development boards from Xilinx (as PYNQ). Modern EDAs flow such as HLS does not represent the best environment for a good power consumption. The power consumption of the HLS implementation is six times more power than the RTL one. It is concluded that the new EDAs method have a deficiency to deliver highly efficient CNNs but it has the ability to deliver sufficient results within a very short period of time.","PeriodicalId":253090,"journal":{"name":"2020 2nd Novel Intelligent and Leading Emerging Sciences Conference (NILES)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130643461","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 : 2020-10-24DOI: 10.1109/NILES50944.2020.9257922
Ali H. Gad, Seif Eldeen E. Abdalazeem, Omar A. Abdelmegid, H. Mostafa
Lately, there have been many technological developments in communication especially in online transactions, so the demand for highly secure systems and cryptographic algorithms has increased. Cryptographic hash functions are used to protect and authenticate information and transactions. SHA-256 (Secure Hash Algorithm-256) is a one-way hash function characterized by being highly secure and fast while having a high collision resistance. This paper presents a new hardware architecture of SHA-256 with low power consumption and area based on a sequential computation of the message scheduler and the working variables of SHA-256. The hardware was described in HDL and implemented on Virtex-7 FPGA which offers high efficiency and speed. Different optimization techniques were used to further reduce the power and area such as gated clock conversion, arithmetic resource sharing, and structural modeling of small building blocks. The proposed design ran with a maximum frequency of 83.33 MHz. The implementation reports indicated a dynamic power consumption of 13 mW and area utilization of 275 slices while maintaining a good throughput of 0.637 Gbits/s and a relatively high efficiency of 2.32 Mbits/s per slice. Such design with low power and area can be used to hash messages on a portable device opening a whole new area for different applications and opportunities.
{"title":"Low power and area SHA-256 hardware accelerator on Virtex-7 FPGA","authors":"Ali H. Gad, Seif Eldeen E. Abdalazeem, Omar A. Abdelmegid, H. Mostafa","doi":"10.1109/NILES50944.2020.9257922","DOIUrl":"https://doi.org/10.1109/NILES50944.2020.9257922","url":null,"abstract":"Lately, there have been many technological developments in communication especially in online transactions, so the demand for highly secure systems and cryptographic algorithms has increased. Cryptographic hash functions are used to protect and authenticate information and transactions. SHA-256 (Secure Hash Algorithm-256) is a one-way hash function characterized by being highly secure and fast while having a high collision resistance. This paper presents a new hardware architecture of SHA-256 with low power consumption and area based on a sequential computation of the message scheduler and the working variables of SHA-256. The hardware was described in HDL and implemented on Virtex-7 FPGA which offers high efficiency and speed. Different optimization techniques were used to further reduce the power and area such as gated clock conversion, arithmetic resource sharing, and structural modeling of small building blocks. The proposed design ran with a maximum frequency of 83.33 MHz. The implementation reports indicated a dynamic power consumption of 13 mW and area utilization of 275 slices while maintaining a good throughput of 0.637 Gbits/s and a relatively high efficiency of 2.32 Mbits/s per slice. Such design with low power and area can be used to hash messages on a portable device opening a whole new area for different applications and opportunities.","PeriodicalId":253090,"journal":{"name":"2020 2nd Novel Intelligent and Leading Emerging Sciences Conference (NILES)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114532412","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：