Pub Date : 2021-10-23DOI: 10.1109/NILES53778.2021.9600511
Salma Abdelmonem, Shahd Seddik, R. El-Sayed, Ahmed S. Kaseb
Malicious software (malware) creators are constantly mutating malware files in order to avoid detection, resulting in hundreds of millions of new malware every year. Therefore, most malware files are unlabeled due to the time and cost needed to label them manually. This makes it very challenging to perform malware detection, i.e., deciding whether a file is malware or not, and malware classification, i.e., determining the family of the malware. Most solutions use supervised learning (e.g., ResNet and VGG) whose accuracy degrades significantly with the lack of abundance of labeled data. To solve this problem, this paper proposes a semi-supervised learning model for image-based malware classification. In this model, malware files are represented as grayscale images, and semi-supervised learning is carefully selected to handle the plethora of unlabeled data. Our proposed model is an enhanced version of the ∏-model, which makes it more accurate and consistent. Experiments show that our proposed model outperforms the original ∏-model by 4% in accuracy and three other supervised models by 6% in accuracy especially when the ratio of labeled samples is as low as 20%.
{"title":"Enhancing Image-Based Malware Classification Using Semi-Supervised Learning","authors":"Salma Abdelmonem, Shahd Seddik, R. El-Sayed, Ahmed S. Kaseb","doi":"10.1109/NILES53778.2021.9600511","DOIUrl":"https://doi.org/10.1109/NILES53778.2021.9600511","url":null,"abstract":"Malicious software (malware) creators are constantly mutating malware files in order to avoid detection, resulting in hundreds of millions of new malware every year. Therefore, most malware files are unlabeled due to the time and cost needed to label them manually. This makes it very challenging to perform malware detection, i.e., deciding whether a file is malware or not, and malware classification, i.e., determining the family of the malware. Most solutions use supervised learning (e.g., ResNet and VGG) whose accuracy degrades significantly with the lack of abundance of labeled data. To solve this problem, this paper proposes a semi-supervised learning model for image-based malware classification. In this model, malware files are represented as grayscale images, and semi-supervised learning is carefully selected to handle the plethora of unlabeled data. Our proposed model is an enhanced version of the ∏-model, which makes it more accurate and consistent. Experiments show that our proposed model outperforms the original ∏-model by 4% in accuracy and three other supervised models by 6% in accuracy especially when the ratio of labeled samples is as low as 20%.","PeriodicalId":249153,"journal":{"name":"2021 3rd Novel Intelligent and Leading Emerging Sciences Conference (NILES)","volume":"96 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115643920","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 : 2021-10-23DOI: 10.1109/NILES53778.2021.9600528
Abdelrhman M. Abotaleb, Mohab H. Ahmed, Mazen A. Fathi
It is clearly known that deep learning applications are enormously used in the image classification, object tracking and related image analysis techniques. But deep learning networks usually involve huge number of parameters that need to be extensively processed to produce the classification output, which also takes a considerable time. GPUs are exploited to do such huge parallel computations to be finished within acceptable time. Still GPUs consume huge power, so they are not suitable for embedded solutions, and also they are very expensive. In the current work, complete implementation of floating point based SqueezeNet convolutional neural network (CNN) is done on ZYNQ System-On-Chip (SoC) XC7020 via partitioning the implementation on both the software part (ARM) and the FPGA part (Artix-7), the acceleration is done via parallel implementations of average pool layer on up to 3 channels with speedup = 6.37 for the Max Pool layer accelerated single channel and 13.88 for the Average Pool layer accelerated 3 channels in parallel. The maximum power consumption equals 1.549 watt (only 0.136 watt for the static power consumption) and the remaining is the dynamic power consumption which is greatly less than the GPU power consumption (reaches ~ 60 watt).
{"title":"SNAPE-FP: SqueezeNet CNN with Accelerated Pooling Layers Extension based on IEEE-754 Floating Point Implementation through SW/HW Partitioning On ZYNQ SoC","authors":"Abdelrhman M. Abotaleb, Mohab H. Ahmed, Mazen A. Fathi","doi":"10.1109/NILES53778.2021.9600528","DOIUrl":"https://doi.org/10.1109/NILES53778.2021.9600528","url":null,"abstract":"It is clearly known that deep learning applications are enormously used in the image classification, object tracking and related image analysis techniques. But deep learning networks usually involve huge number of parameters that need to be extensively processed to produce the classification output, which also takes a considerable time. GPUs are exploited to do such huge parallel computations to be finished within acceptable time. Still GPUs consume huge power, so they are not suitable for embedded solutions, and also they are very expensive. In the current work, complete implementation of floating point based SqueezeNet convolutional neural network (CNN) is done on ZYNQ System-On-Chip (SoC) XC7020 via partitioning the implementation on both the software part (ARM) and the FPGA part (Artix-7), the acceleration is done via parallel implementations of average pool layer on up to 3 channels with speedup = 6.37 for the Max Pool layer accelerated single channel and 13.88 for the Average Pool layer accelerated 3 channels in parallel. The maximum power consumption equals 1.549 watt (only 0.136 watt for the static power consumption) and the remaining is the dynamic power consumption which is greatly less than the GPU power consumption (reaches ~ 60 watt).","PeriodicalId":249153,"journal":{"name":"2021 3rd Novel Intelligent and Leading Emerging Sciences Conference (NILES)","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123463968","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 : 2021-10-23DOI: 10.1109/NILES53778.2021.9600531
M. El-Salamony, Ahmed Moharam, A. Guaily
The effect of different ventilation parameters on the infection potential of COVID-19 in a metro wagon is numerically studied. Two key indicators are used to quantify this potential. Based on the numerical results a regression analysis is performed to come up with the most suitable regression model for these key parameters. The proposed regression models are helpful in quantifying the infection risk at different ventilation scenarios.
{"title":"Regression Modeling for the Ventilation Effect on COVID-19 Spreading in Metro Wagons","authors":"M. El-Salamony, Ahmed Moharam, A. Guaily","doi":"10.1109/NILES53778.2021.9600531","DOIUrl":"https://doi.org/10.1109/NILES53778.2021.9600531","url":null,"abstract":"The effect of different ventilation parameters on the infection potential of COVID-19 in a metro wagon is numerically studied. Two key indicators are used to quantify this potential. Based on the numerical results a regression analysis is performed to come up with the most suitable regression model for these key parameters. The proposed regression models are helpful in quantifying the infection risk at different ventilation scenarios.","PeriodicalId":249153,"journal":{"name":"2021 3rd Novel Intelligent and Leading Emerging Sciences Conference (NILES)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128807121","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}
Machine learning is presently acknowledged as a significant ingredient of research in many fields, including robotics. The use of robots to perform assorted tasks is evident in difficult, uncompromising, and hazardous spaces and sectors such as manufacturing, transportation, healthcare, landmines, mining, patrolling, disaster relief etc. For a robot to carry out its assigned task, it normally has to navigate safely without collisions to different locations, which also means understanding its working environment, collectively known as the robot navigation problem. This paper considers finding a solution using neural networks to the robot navigation problem, particularly the path planning problem that includes fixed obstacles. The objective of the path planning problem is to find a route to the final destination that is optimal and also collision-free. Different training algorithms and network structures are used to construct models that can predict a turning angle for the point-mass robot which will be used to avoid obstacles in the robot's path to the destination. This paper will present a comparative analysis of the performance of different feedforward neural network models. The results suggest that the feedforward neural network model with 10 neurons and Bayesian regularization performed the best. The model has been used to avoid obstacles in two different environments. The trajectories show that the robot has safely avoided obstacles in its path and reached the destination.
{"title":"Obstacle Avoidance of a Point-Mass Robot using Feedforward Neural Network","authors":"K. Chaudhary, Goel Lal, Avinesh Prasad, Vishal Chand, Sushita Sharma, Avinesh Lal","doi":"10.1109/NILES53778.2021.9600550","DOIUrl":"https://doi.org/10.1109/NILES53778.2021.9600550","url":null,"abstract":"Machine learning is presently acknowledged as a significant ingredient of research in many fields, including robotics. The use of robots to perform assorted tasks is evident in difficult, uncompromising, and hazardous spaces and sectors such as manufacturing, transportation, healthcare, landmines, mining, patrolling, disaster relief etc. For a robot to carry out its assigned task, it normally has to navigate safely without collisions to different locations, which also means understanding its working environment, collectively known as the robot navigation problem. This paper considers finding a solution using neural networks to the robot navigation problem, particularly the path planning problem that includes fixed obstacles. The objective of the path planning problem is to find a route to the final destination that is optimal and also collision-free. Different training algorithms and network structures are used to construct models that can predict a turning angle for the point-mass robot which will be used to avoid obstacles in the robot's path to the destination. This paper will present a comparative analysis of the performance of different feedforward neural network models. The results suggest that the feedforward neural network model with 10 neurons and Bayesian regularization performed the best. The model has been used to avoid obstacles in two different environments. The trajectories show that the robot has safely avoided obstacles in its path and reached the destination.","PeriodicalId":249153,"journal":{"name":"2021 3rd Novel Intelligent and Leading Emerging Sciences Conference (NILES)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127226120","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 : 2021-10-23DOI: 10.1109/NILES53778.2021.9600095
Ashraf Kassem, Mohamed E. Madbouly, A. Guaily
A comparative numerical study is performed among different URANS turbulence models investigating the ability of the models to capture the deformation of the boundary layer near the separation zone. The results are validated against previously published numerical works (URANS, LES, DNS) and experimental works. The comparison included grid resolution, the pressure distribution, and the velocity profiles at the inclined wall, then the streamlines plot of each model is used to properly estimate the separation and reattachment points.
{"title":"Comparative Study for Different URANS Models for Capturing Flow Separation Inside a Plane Diffuser","authors":"Ashraf Kassem, Mohamed E. Madbouly, A. Guaily","doi":"10.1109/NILES53778.2021.9600095","DOIUrl":"https://doi.org/10.1109/NILES53778.2021.9600095","url":null,"abstract":"A comparative numerical study is performed among different URANS turbulence models investigating the ability of the models to capture the deformation of the boundary layer near the separation zone. The results are validated against previously published numerical works (URANS, LES, DNS) and experimental works. The comparison included grid resolution, the pressure distribution, and the velocity profiles at the inclined wall, then the streamlines plot of each model is used to properly estimate the separation and reattachment points.","PeriodicalId":249153,"journal":{"name":"2021 3rd Novel Intelligent and Leading Emerging Sciences Conference (NILES)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126032862","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 : 2021-10-23DOI: 10.1109/NILES53778.2021.9600494
Mariam Khaled, A.M. Hisham, I. Fahim
This study targets an order fulfillment problem in a freight forwarding company. Some applicable solutions are implemented such as supplier performance evaluation, suppliers' selection, and location analytics. The objective of the study is to reduce the number of unfulfilled orders by supply planning. Some of the tools used to achieve this are Excel (VBA and Pivot tables) to perform drivers' scoring, analytic hierarchy process (AHP), and ArcGIS software to visualize locations. The results showed that the company can implement the suggested solutions to reduce the number of order cancellations and assist drivers based on clients' demands to ensure customer satisfaction and loyalty. The AHP allows the company to standardize the order fulfillment process, keep clients' loyalty, satisfy clients' demands and eliminate a random selection of drivers. In addition, drivers' evaluation can assist the company to visualize drivers' performance through the five different criteria: punctuality, truck quality, reliability, appearance, and mobile app usage in different periods of time and assign the drivers to new clients based on their scores to avoid any complaints from clients. For the map visualization, it matches supply with demand as currently, the company acquires suppliers with no strategic purpose. The locations visualized on the map assist the supply team to indicate the regions that need an increase in the capacity of contractors and drivers close to the client's location. In addition, the map illustrates the business size and territory.
{"title":"Investigation of root causes of order unfulfillment: A Logistics case study","authors":"Mariam Khaled, A.M. Hisham, I. Fahim","doi":"10.1109/NILES53778.2021.9600494","DOIUrl":"https://doi.org/10.1109/NILES53778.2021.9600494","url":null,"abstract":"This study targets an order fulfillment problem in a freight forwarding company. Some applicable solutions are implemented such as supplier performance evaluation, suppliers' selection, and location analytics. The objective of the study is to reduce the number of unfulfilled orders by supply planning. Some of the tools used to achieve this are Excel (VBA and Pivot tables) to perform drivers' scoring, analytic hierarchy process (AHP), and ArcGIS software to visualize locations. The results showed that the company can implement the suggested solutions to reduce the number of order cancellations and assist drivers based on clients' demands to ensure customer satisfaction and loyalty. The AHP allows the company to standardize the order fulfillment process, keep clients' loyalty, satisfy clients' demands and eliminate a random selection of drivers. In addition, drivers' evaluation can assist the company to visualize drivers' performance through the five different criteria: punctuality, truck quality, reliability, appearance, and mobile app usage in different periods of time and assign the drivers to new clients based on their scores to avoid any complaints from clients. For the map visualization, it matches supply with demand as currently, the company acquires suppliers with no strategic purpose. The locations visualized on the map assist the supply team to indicate the regions that need an increase in the capacity of contractors and drivers close to the client's location. In addition, the map illustrates the business size and territory.","PeriodicalId":249153,"journal":{"name":"2021 3rd Novel Intelligent and Leading Emerging Sciences Conference (NILES)","volume":"90 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114563896","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 : 2021-10-23DOI: 10.1109/NILES53778.2021.9600498
M. Kasem, K. Maalawi
We developed a hybrid model for multiobjective optimization of composite structures. It is applied to find the optimal designs of slender, thin-walled, and functionally graded material (FGM) columns. The overall objective function is defined as the weighting sum of the dimensionless column mass $widehat{M}_{s}$ and critical buckling load $bar{P}_{cr}$, expressed as $f(bar{x})=alphawidehat{M}_{s}(bar{x})-(1-alpha)bar{P}_{cr}(bar{x})$. Three global optimization algorithms i.e., the genetic algorithm (GA), sequential quadratic programming (SQP), and hybrid GA-SQP were employed to investigate the column best design point. Several optimization models are developed and the optimal designs are obtained.
{"title":"Multiobjective Optimization of Functionally Graded Material Columns","authors":"M. Kasem, K. Maalawi","doi":"10.1109/NILES53778.2021.9600498","DOIUrl":"https://doi.org/10.1109/NILES53778.2021.9600498","url":null,"abstract":"We developed a hybrid model for multiobjective optimization of composite structures. It is applied to find the optimal designs of slender, thin-walled, and functionally graded material (FGM) columns. The overall objective function is defined as the weighting sum of the dimensionless column mass $widehat{M}_{s}$ and critical buckling load $bar{P}_{cr}$, expressed as $f(bar{x})=alphawidehat{M}_{s}(bar{x})-(1-alpha)bar{P}_{cr}(bar{x})$. Three global optimization algorithms i.e., the genetic algorithm (GA), sequential quadratic programming (SQP), and hybrid GA-SQP were employed to investigate the column best design point. Several optimization models are developed and the optimal designs are obtained.","PeriodicalId":249153,"journal":{"name":"2021 3rd Novel Intelligent and Leading Emerging Sciences Conference (NILES)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121562837","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}
Pandemics raise huge challenges yet brought several opportunities. The sudden attack of COVID-19 revealed the importance of the information technology (IT) applications. The Reliance on the IT sector has become imperative to ensure sustainability and to raise most sectors' performance efficiency, especially the services' ones. This study applied PESTEL analysis to evaluate the current status of IT in Egypt. SWOT analysis was performed to explore points of strength, weakness, opportunities, and threats that face the IT sector in Egypt as a result of the COVID19 attack. The process of foreseeing the future, through non-officials' experts brainstorming, is the first step to design and implement strategic plans to achieve the targeted future. To exploit the future of the IT sector, the direct and indirect influences of the mentioned factors were studied with the use of the future wheel. An optimistic scenario is introduced to foresee the effects of the mentioned recommendations. The imperative of taking advantage of the opportunity to spread digital applications and to allow internet and digital services usage for all citizens is Egypt's gateway to reach international standards.
{"title":"Impact of COVID-19 on Information Technology Sector in Egypt","authors":"Walaa Medhat, Sahar Fawzi, Omar Fahmy, Gasser Hassan, Mohamed Ramadan, Alaa Abdelbary, A. Yousef","doi":"10.1109/NILES53778.2021.9600090","DOIUrl":"https://doi.org/10.1109/NILES53778.2021.9600090","url":null,"abstract":"Pandemics raise huge challenges yet brought several opportunities. The sudden attack of COVID-19 revealed the importance of the information technology (IT) applications. The Reliance on the IT sector has become imperative to ensure sustainability and to raise most sectors' performance efficiency, especially the services' ones. This study applied PESTEL analysis to evaluate the current status of IT in Egypt. SWOT analysis was performed to explore points of strength, weakness, opportunities, and threats that face the IT sector in Egypt as a result of the COVID19 attack. The process of foreseeing the future, through non-officials' experts brainstorming, is the first step to design and implement strategic plans to achieve the targeted future. To exploit the future of the IT sector, the direct and indirect influences of the mentioned factors were studied with the use of the future wheel. An optimistic scenario is introduced to foresee the effects of the mentioned recommendations. The imperative of taking advantage of the opportunity to spread digital applications and to allow internet and digital services usage for all citizens is Egypt's gateway to reach international standards.","PeriodicalId":249153,"journal":{"name":"2021 3rd Novel Intelligent and Leading Emerging Sciences Conference (NILES)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126845899","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 : 2021-10-23DOI: 10.1109/NILES53778.2021.9600096
Rana Hossam Elden, V. F. Ghoneim, Marwa M. A. Hadhoud, W. Al-Atabany
Pediatric septic shock is generally considered as a devastating clinical syndrome that can lead to tissue damage and organ failure due to the over exaggerated immune response to an infection. Therefore, in this paper, we attempted to early identify the clinical course of such disease with the aid of peripheral blood T-cells of 181 pediatric patients who admitted to Intensive Care Unit (ICU), Accordingly, 34 differential expressed genes have been identified as biological genetic biomarkers. Minimum redundancy and maximum relevance feature selection strategy has been proposed for the discovery of topmost 8 discriminant novel genes for validating its discriminatory performance in differentiating between pediatric septic shock survivors and non-survivor categories. Random forest (RF) with 100 trees has been optimized using 20 runs of 5-fold cross validation, the area under the curve was 0.9430 that confirm our proposed model may improve risk stratification and mortality prediction in pediatric patients with septic shock.
{"title":"Studying Genes Related to the Survival Rate of Pediatric Septic Shock","authors":"Rana Hossam Elden, V. F. Ghoneim, Marwa M. A. Hadhoud, W. Al-Atabany","doi":"10.1109/NILES53778.2021.9600096","DOIUrl":"https://doi.org/10.1109/NILES53778.2021.9600096","url":null,"abstract":"Pediatric septic shock is generally considered as a devastating clinical syndrome that can lead to tissue damage and organ failure due to the over exaggerated immune response to an infection. Therefore, in this paper, we attempted to early identify the clinical course of such disease with the aid of peripheral blood T-cells of 181 pediatric patients who admitted to Intensive Care Unit (ICU), Accordingly, 34 differential expressed genes have been identified as biological genetic biomarkers. Minimum redundancy and maximum relevance feature selection strategy has been proposed for the discovery of topmost 8 discriminant novel genes for validating its discriminatory performance in differentiating between pediatric septic shock survivors and non-survivor categories. Random forest (RF) with 100 trees has been optimized using 20 runs of 5-fold cross validation, the area under the curve was 0.9430 that confirm our proposed model may improve risk stratification and mortality prediction in pediatric patients with septic shock.","PeriodicalId":249153,"journal":{"name":"2021 3rd Novel Intelligent and Leading Emerging Sciences Conference (NILES)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128805322","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 : 2021-10-23DOI: 10.1109/NILES53778.2021.9600513
Sara Ahmed, Nancy Alshaer, T. Ismail
Random numbers play an essential role in guaranteeing secrecy in most cryptographic systems. A chaotic optical signal is exploited to achieve high-speed random numbers. It could be generated by using one or more semiconductor lasers with external optical feedback. However, this system faces two major issues, high peak to average power ratio (PAPR) and parameter variations. These issues highly affected the randomness of the generated bitstreams. In this paper, we use a non-linear compression technique to compand the generated signal before it is quantized to avoid the effects of the PAPR. Also, we develop the post-processing stage by using advanced encryption standard (AES) algorithm feeds from two different generated bitstreams. These two integrated stages, non-linear quantization, and post-processing are configured to achieve a generation of a efficient random number guaranteed by NIST and DIEHARD statistical test suites. Finally, the proposed system is verified at parameter variation of ±20% tolerance including external mirror reflectivity, external cavity length, and normalized injection current. The results show that the proposed system could generate truly random numbers even with parameters configuration tolerance.
{"title":"Chaos-Based RNG using Semiconductor Lasers with Parameters Variation Tolerance","authors":"Sara Ahmed, Nancy Alshaer, T. Ismail","doi":"10.1109/NILES53778.2021.9600513","DOIUrl":"https://doi.org/10.1109/NILES53778.2021.9600513","url":null,"abstract":"Random numbers play an essential role in guaranteeing secrecy in most cryptographic systems. A chaotic optical signal is exploited to achieve high-speed random numbers. It could be generated by using one or more semiconductor lasers with external optical feedback. However, this system faces two major issues, high peak to average power ratio (PAPR) and parameter variations. These issues highly affected the randomness of the generated bitstreams. In this paper, we use a non-linear compression technique to compand the generated signal before it is quantized to avoid the effects of the PAPR. Also, we develop the post-processing stage by using advanced encryption standard (AES) algorithm feeds from two different generated bitstreams. These two integrated stages, non-linear quantization, and post-processing are configured to achieve a generation of a efficient random number guaranteed by NIST and DIEHARD statistical test suites. Finally, the proposed system is verified at parameter variation of ±20% tolerance including external mirror reflectivity, external cavity length, and normalized injection current. The results show that the proposed system could generate truly random numbers even with parameters configuration tolerance.","PeriodicalId":249153,"journal":{"name":"2021 3rd Novel Intelligent and Leading Emerging Sciences Conference (NILES)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125871336","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：