Pub Date : 2020-10-24DOI: 10.1109/NILES50944.2020.9257937
Yomna A. Moussa, Wassim Alexan
This paper proposes an advanced scheme of message security in 3D cover images using multiple layers of security. Cryptography using AES–256 is implemented in the first layer. In the second layer, edge detection is applied. Finally, LSB steganography is executed in the third layer. The efficiency of the proposed scheme is measured using a number of performance metrics. For instance, mean square error (MSE), peak signal–to–noise ratio (PSNR), structural similarity index measure (SSIM), mean absolute error (MAE) and entropy.
{"title":"Message Security Through AES and LSB Embedding in Edge Detected Pixels of 3D Images","authors":"Yomna A. Moussa, Wassim Alexan","doi":"10.1109/NILES50944.2020.9257937","DOIUrl":"https://doi.org/10.1109/NILES50944.2020.9257937","url":null,"abstract":"This paper proposes an advanced scheme of message security in 3D cover images using multiple layers of security. Cryptography using AES–256 is implemented in the first layer. In the second layer, edge detection is applied. Finally, LSB steganography is executed in the third layer. The efficiency of the proposed scheme is measured using a number of performance metrics. For instance, mean square error (MSE), peak signal–to–noise ratio (PSNR), structural similarity index measure (SSIM), mean absolute error (MAE) and entropy.","PeriodicalId":253090,"journal":{"name":"2020 2nd Novel Intelligent and Leading Emerging Sciences Conference (NILES)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134093697","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/NILES50944.2020.9257934
AbdelRahman Hesham, A. Nassar, H. Mostafa
In this paper, a low-energy minimum-area CMOS standard cell library suitable for IoT applications is proposed. Energy consumption reduction is achieved by operating the library in Near-Threshold Voltage (NTV) region, and by designing layout of cells at the minimum possible area for the used technology process. Body biasing technique is proposed to boost pMOS performance. Operating voltage and transistor sizing are also selected to achieve the minimum energy consumption while operating at the frequency range of 1MHz to 20MHz which is suitable for IoT applications. The proposed library was designed and characterized in UMC 130 nm CMOS technology process. The library was modeled to be used in synthesis tools. To prove the benefit for IoT applications, the library was benchmarked by implementing 3 cryptographic algorithms: ASCON, AEGIS-128, and AEZ. Synthesis results are showing that the three cores can operate at 18 MHz, 14 MHz, and 16 MHz respectively, while consuming 0.466 pJ, 3.006 pJ, and 5.064 pJ.
{"title":"Energy-Efficient Near-Threshold Standard Cell Library for IoT Applications","authors":"AbdelRahman Hesham, A. Nassar, H. Mostafa","doi":"10.1109/NILES50944.2020.9257934","DOIUrl":"https://doi.org/10.1109/NILES50944.2020.9257934","url":null,"abstract":"In this paper, a low-energy minimum-area CMOS standard cell library suitable for IoT applications is proposed. Energy consumption reduction is achieved by operating the library in Near-Threshold Voltage (NTV) region, and by designing layout of cells at the minimum possible area for the used technology process. Body biasing technique is proposed to boost pMOS performance. Operating voltage and transistor sizing are also selected to achieve the minimum energy consumption while operating at the frequency range of 1MHz to 20MHz which is suitable for IoT applications. The proposed library was designed and characterized in UMC 130 nm CMOS technology process. The library was modeled to be used in synthesis tools. To prove the benefit for IoT applications, the library was benchmarked by implementing 3 cryptographic algorithms: ASCON, AEGIS-128, and AEZ. Synthesis results are showing that the three cores can operate at 18 MHz, 14 MHz, and 16 MHz respectively, while consuming 0.466 pJ, 3.006 pJ, and 5.064 pJ.","PeriodicalId":253090,"journal":{"name":"2020 2nd Novel Intelligent and Leading Emerging Sciences Conference (NILES)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129578841","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/NILES50944.2020.9257904
A. Hafez, T. Kasem, B. Elhadidi, M. Abdelrahman
A new Finite element model for HVAC applications is introduced. The model incorporates flow turbulence, buoyancy effects and unsteadiness. Also, the model accommodates complicated boundaries due to complex geometries and perforated tiles. Experimental validation is provided and extensive results for flow and temperature contours are presented. Temporal and spatial resolution prove that the model can capture important HVAC features as thermal comfort, buoyancy induced flow, complex boundaries.
{"title":"Efficient Finite Element Modeling of Complex HVAC Applications","authors":"A. Hafez, T. Kasem, B. Elhadidi, M. Abdelrahman","doi":"10.1109/NILES50944.2020.9257904","DOIUrl":"https://doi.org/10.1109/NILES50944.2020.9257904","url":null,"abstract":"A new Finite element model for HVAC applications is introduced. The model incorporates flow turbulence, buoyancy effects and unsteadiness. Also, the model accommodates complicated boundaries due to complex geometries and perforated tiles. Experimental validation is provided and extensive results for flow and temperature contours are presented. Temporal and spatial resolution prove that the model can capture important HVAC features as thermal comfort, buoyancy induced flow, complex boundaries.","PeriodicalId":253090,"journal":{"name":"2020 2nd Novel Intelligent and Leading Emerging Sciences Conference (NILES)","volume":"120 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122916213","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/NILES50944.2020.9257896
Yasmin K. Abdelmagid, Renad T. Nawar, Mennatullah K. Rabie, Ahmed S. Tulan, Ahmed H. Hassan, Andoleet Saleh, H. Mostafa
Memristor, the two-terminal memory-resistance device discovered by Chua in 1971, is a promising solution for future processing problems. Its CMOS integration compatibility and large resistance in small size, makes it very successful candidate for large-scale systems like Neural Networks. In last decade, memristors were used in many Neuromorphic Synapses for its advantage of combining processing (dot-product) and memory in same device. There are different materials that can be used to fabricate memristors. In this paper, a comparison between spintronic and TiO2-resistive memristor in two-transistors-one memristor synapse, is introduced. The work was done on Cadence Virtuoso with using Verilog-A for memristor modeling. The comparison reveals that the synaptic implementation with a spintronic memristor is more efficient when high speed is needed. However, the resistive memristor is more adequate due to its lower power dissipation.
{"title":"Investigation of DW Spintronic Memristor performance in 2T1M Neuromorphic Synapse","authors":"Yasmin K. Abdelmagid, Renad T. Nawar, Mennatullah K. Rabie, Ahmed S. Tulan, Ahmed H. Hassan, Andoleet Saleh, H. Mostafa","doi":"10.1109/NILES50944.2020.9257896","DOIUrl":"https://doi.org/10.1109/NILES50944.2020.9257896","url":null,"abstract":"Memristor, the two-terminal memory-resistance device discovered by Chua in 1971, is a promising solution for future processing problems. Its CMOS integration compatibility and large resistance in small size, makes it very successful candidate for large-scale systems like Neural Networks. In last decade, memristors were used in many Neuromorphic Synapses for its advantage of combining processing (dot-product) and memory in same device. There are different materials that can be used to fabricate memristors. In this paper, a comparison between spintronic and TiO2-resistive memristor in two-transistors-one memristor synapse, is introduced. The work was done on Cadence Virtuoso with using Verilog-A for memristor modeling. The comparison reveals that the synaptic implementation with a spintronic memristor is more efficient when high speed is needed. However, the resistive memristor is more adequate due to its lower power dissipation.","PeriodicalId":253090,"journal":{"name":"2020 2nd Novel Intelligent and Leading Emerging Sciences Conference (NILES)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122942452","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/NILES50944.2020.9257972
Randa Bakr, A. El-Banna, Sami A. A. El-Shaikh, A. S. Eldien
Cognitive Radio Sensor Networks (CRSNs) have become an integral portion of the new generation of smart Wireless Sensor Networks (WSNs) technology. Moreover, efficient clustering and routing could enhance the network performance by taking into account the stability and connectivity of the network that expands the network's lifetime. In this paper, we propose a scheme that aims to construct an energy-efficient clustering for CRSNs through saving the intra-communication energy between nodes into the cluster, in addition to the inter-communication energy between Cluster Head (CH) nodes to the Base Station (BS). The scheme utilizes evaluation criteria to define the CH node for each cluster by calculating a weight value for each node, and depending on the maximum weight value for nodes, the CH is picked. Moreover, to establish a route between CHs, we consider common channels between them plus the shortest distance from cluster heads to the sink. In this way, clustering and routing could enhance the network performance and extend the lifetime. To corroborate the proposed scheme, extensive simulations in MATLAB were carried out and the results of the simulation showed the superiority of the proposed technique over other algorithms in terms of the network’s lifetime.
{"title":"Energy Efficient Spectrum Aware Distributed Cluster-Based Routing in Cognitive Radio Sensor Networks","authors":"Randa Bakr, A. El-Banna, Sami A. A. El-Shaikh, A. S. Eldien","doi":"10.1109/NILES50944.2020.9257972","DOIUrl":"https://doi.org/10.1109/NILES50944.2020.9257972","url":null,"abstract":"Cognitive Radio Sensor Networks (CRSNs) have become an integral portion of the new generation of smart Wireless Sensor Networks (WSNs) technology. Moreover, efficient clustering and routing could enhance the network performance by taking into account the stability and connectivity of the network that expands the network's lifetime. In this paper, we propose a scheme that aims to construct an energy-efficient clustering for CRSNs through saving the intra-communication energy between nodes into the cluster, in addition to the inter-communication energy between Cluster Head (CH) nodes to the Base Station (BS). The scheme utilizes evaluation criteria to define the CH node for each cluster by calculating a weight value for each node, and depending on the maximum weight value for nodes, the CH is picked. Moreover, to establish a route between CHs, we consider common channels between them plus the shortest distance from cluster heads to the sink. In this way, clustering and routing could enhance the network performance and extend the lifetime. To corroborate the proposed scheme, extensive simulations in MATLAB were carried out and the results of the simulation showed the superiority of the proposed technique over other algorithms in terms of the network’s lifetime.","PeriodicalId":253090,"journal":{"name":"2020 2nd Novel Intelligent and Leading Emerging Sciences Conference (NILES)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123583117","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/NILES50944.2020.9257921
Marwa Zamzam, T. el-Shabrawy, M. Ashour
Edge computing is considered a promising approach to provide cloud computing capabilities at the edge of the network near to the users. However, the limited number of computation and communication resources at the edge have made the problem of offloading and resource allocation a challenging issue for service providers. Game theory analyzes the behavior of the users and succeeds to obtain solutions in this area where all users are satisfied and the problem reaches an equilibrium state. In this paper, first we give a brief background on game theory showing its definition, types and advantages. Second, we give an overview about edge computing system showing its architecture, challenges and kinds of resource management. Third, we provide a survey about significant achievements of applying game theory in edge computing problems. We categorize the state-of-the-art according to the objective function of the problem. It is divided into seven classes: 1) minimizing the latency, 2) minimizing the energy, 3) minimizing the cost, 4) minimizing both latency and energy, 5) minimizing energy and cost, 6) minimizing latency and cost and finally, 7) minimizing all together latency, cost and energy. Moreover, we present the lessons learned and the future research directions.
{"title":"Game Theory for Computation Offloading and Resource Allocation in Edge Computing: A Survey","authors":"Marwa Zamzam, T. el-Shabrawy, M. Ashour","doi":"10.1109/NILES50944.2020.9257921","DOIUrl":"https://doi.org/10.1109/NILES50944.2020.9257921","url":null,"abstract":"Edge computing is considered a promising approach to provide cloud computing capabilities at the edge of the network near to the users. However, the limited number of computation and communication resources at the edge have made the problem of offloading and resource allocation a challenging issue for service providers. Game theory analyzes the behavior of the users and succeeds to obtain solutions in this area where all users are satisfied and the problem reaches an equilibrium state. In this paper, first we give a brief background on game theory showing its definition, types and advantages. Second, we give an overview about edge computing system showing its architecture, challenges and kinds of resource management. Third, we provide a survey about significant achievements of applying game theory in edge computing problems. We categorize the state-of-the-art according to the objective function of the problem. It is divided into seven classes: 1) minimizing the latency, 2) minimizing the energy, 3) minimizing the cost, 4) minimizing both latency and energy, 5) minimizing energy and cost, 6) minimizing latency and cost and finally, 7) minimizing all together latency, cost and energy. Moreover, we present the lessons learned and the future research directions.","PeriodicalId":253090,"journal":{"name":"2020 2nd Novel Intelligent and Leading Emerging Sciences Conference (NILES)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129347860","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/NILES50944.2020.9257916
Santiago Ramos Garces, Mayra Yucely Beb, Abdoulaye Boubakari, H. Ammar, Mohamed A. Wahby Shalaby
Over the past decade, mobile autonomous robots have been widely used efficiently for different applications. Recently, self-balancing robots attracted more attention and showed impressive performance. A self-balancing robot is simply a two-wheeled robot; hence it needs to be balanced vertically using a closed-loop control algorithm. In this paper, a new hybrid two-wheeled self-balancing robot is fully designed and implemented, which is able to track objects and to avoid obstacles efficiently. The proposed robot consists of a two-wheeled chassis equipped with an ultrasonic sensor, camera, gyroscope and accelerometer allowing a multi-directional navigation of the robot tracker. Additionally, the Internet of Things (IOT) framework has been used for remote control and monitoring via wireless interface. The Fuzzy Logic Controller is designed considering all the realistic hindrances in order to achieve high performance and meet robust stability. To approximate the position of an object about the robot, vision system and ultrasonic sensor coupled with a camera are used. Finally, it has been observed via simulation and hardware implementation the efficiency of fuzzy control technique which achieved both stability and robustness outcomes; however, due to processing restrictions other control techniques are also successfully implemented. Regarding the experimental results it can be concluded that, balancing and tracking techniques can be achieved by applying sequential algorithm in Simulink combined with vision system and sensors like ultrasonic, accelerometer and gyroscope.
{"title":"Hybrid Self-Balancing and object Tracking Robot Using Artificial Intelligence and Machine Vision","authors":"Santiago Ramos Garces, Mayra Yucely Beb, Abdoulaye Boubakari, H. Ammar, Mohamed A. Wahby Shalaby","doi":"10.1109/NILES50944.2020.9257916","DOIUrl":"https://doi.org/10.1109/NILES50944.2020.9257916","url":null,"abstract":"Over the past decade, mobile autonomous robots have been widely used efficiently for different applications. Recently, self-balancing robots attracted more attention and showed impressive performance. A self-balancing robot is simply a two-wheeled robot; hence it needs to be balanced vertically using a closed-loop control algorithm. In this paper, a new hybrid two-wheeled self-balancing robot is fully designed and implemented, which is able to track objects and to avoid obstacles efficiently. The proposed robot consists of a two-wheeled chassis equipped with an ultrasonic sensor, camera, gyroscope and accelerometer allowing a multi-directional navigation of the robot tracker. Additionally, the Internet of Things (IOT) framework has been used for remote control and monitoring via wireless interface. The Fuzzy Logic Controller is designed considering all the realistic hindrances in order to achieve high performance and meet robust stability. To approximate the position of an object about the robot, vision system and ultrasonic sensor coupled with a camera are used. Finally, it has been observed via simulation and hardware implementation the efficiency of fuzzy control technique which achieved both stability and robustness outcomes; however, due to processing restrictions other control techniques are also successfully implemented. Regarding the experimental results it can be concluded that, balancing and tracking techniques can be achieved by applying sequential algorithm in Simulink combined with vision system and sensors like ultrasonic, accelerometer and gyroscope.","PeriodicalId":253090,"journal":{"name":"2020 2nd Novel Intelligent and Leading Emerging Sciences Conference (NILES)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129264542","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/NILES50944.2020.9257880
Abdelrahman Ezzeldin Nagib, M. Saeed, Shereen Fathy El-Feky, Ali Khater Mohamed
Over the last two decades, the neural network has surprisingly arisen as an efficient tool for dealing with numerous real-life applications. Optimization of the hyperparameter of the neural network attracted many researchers in industrial and research areas because of its great effect on the quality of the solution. This paper presents a new adaptation for the learning rate with shock (ALRS) as the learning rate is considered one of the most important hyperparameters. The experimental results proved that the new adaptation leads to improved accuracy with a simpler structure for the neural network regardless of the initial value of the learning rate.
{"title":"Neural Network with Adaptive Learning Rate","authors":"Abdelrahman Ezzeldin Nagib, M. Saeed, Shereen Fathy El-Feky, Ali Khater Mohamed","doi":"10.1109/NILES50944.2020.9257880","DOIUrl":"https://doi.org/10.1109/NILES50944.2020.9257880","url":null,"abstract":"Over the last two decades, the neural network has surprisingly arisen as an efficient tool for dealing with numerous real-life applications. Optimization of the hyperparameter of the neural network attracted many researchers in industrial and research areas because of its great effect on the quality of the solution. This paper presents a new adaptation for the learning rate with shock (ALRS) as the learning rate is considered one of the most important hyperparameters. The experimental results proved that the new adaptation leads to improved accuracy with a simpler structure for the neural network regardless of the initial value of the learning rate.","PeriodicalId":253090,"journal":{"name":"2020 2nd Novel Intelligent and Leading Emerging Sciences Conference (NILES)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124607013","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/NILES50944.2020.9257907
H. Amer, Dina Rateb, R. Daoud, G. Alkady
In this paper, the machine repair cycle in the manufacturing industry is explored in the context of developing countries. The scope of this paper is the failure of electronic components in the machine along with its software. A Markov model is developed to take into account the different types of failures (hardware or software) and the repair procedures while focusing on the effect of training the maintenance personnel as well as that of stocking spare parts onsite. It is shown that the Steady State Availability obtained when using the proposed enhanced model is occasionally different than that obtained when using more conventional models. The proposed model can be used to support decision making regarding the appropriate amount of training for the maintenance personnel and the factory’s spare part stocking policy. Finally, the Payoff is analyzed in relation to the cost of Downtime versus the Uptime.
{"title":"Enhanced Modeling of Machine Repair Cycle to Maximize Uptime in Developing Countries","authors":"H. Amer, Dina Rateb, R. Daoud, G. Alkady","doi":"10.1109/NILES50944.2020.9257907","DOIUrl":"https://doi.org/10.1109/NILES50944.2020.9257907","url":null,"abstract":"In this paper, the machine repair cycle in the manufacturing industry is explored in the context of developing countries. The scope of this paper is the failure of electronic components in the machine along with its software. A Markov model is developed to take into account the different types of failures (hardware or software) and the repair procedures while focusing on the effect of training the maintenance personnel as well as that of stocking spare parts onsite. It is shown that the Steady State Availability obtained when using the proposed enhanced model is occasionally different than that obtained when using more conventional models. The proposed model can be used to support decision making regarding the appropriate amount of training for the maintenance personnel and the factory’s spare part stocking policy. Finally, the Payoff is analyzed in relation to the cost of Downtime versus the Uptime.","PeriodicalId":253090,"journal":{"name":"2020 2nd Novel Intelligent and Leading Emerging Sciences Conference (NILES)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116750787","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/NILES50944.2020.9257941
A. Ibrahim, Rania M. Hassan, Andrew E. Tawfiles, T. Ismail, M. Darweesh
This paper aims to help self-driving cars and autonomous vehicles systems to merge with the road environment safely and ensure the reliability of these systems in real life. Crash avoidance is a complex system that depends on many parameters. The forward-collision warning system is simplified into four main objectives: detecting cars, depth estimation, assigning cars into lanes (lane assign) and tracking technique. The presented work targets the software approach by using YOLO (You Only Look Once), which is a deep learning object detector network to detect cars with an accuracy of up to 93%. Therefore, apply a depth estimation algorithm that uses the output boundary box’s dimensions (width and height) from YOLO. These dimensions used to estimate the distance with an accuracy of 80.4%. In addition, a real-time computer vision algorithm is applied to assign cars into lanes. However, a tracking proposed algorithm is applied to evaluate the speed limit to keep the vehicle safe. Finally, the real-time system achieved for all algorithms with streaming speed 23 FPS (frame per second).
本文旨在帮助自动驾驶汽车和自动驾驶车辆系统安全地与道路环境融合，并确保这些系统在现实生活中的可靠性。防撞系统是一个复杂的系统，它依赖于许多参数。将前碰撞预警系统简化为四个主要目标:检测车辆、深度估计、车道分配(车道分配)和跟踪技术。所提出的工作通过使用YOLO (You Only Look Once)来瞄准软件方法，YOLO是一种深度学习对象检测器网络，可以以高达93%的准确率检测汽车。因此，应用深度估计算法，该算法使用来自YOLO的输出边界框的尺寸(宽度和高度)。这些尺寸用于估计距离，精度为80.4%。此外，采用实时计算机视觉算法对车辆进行车道分配。然而，为了保证车辆的安全，提出了一种跟踪算法来评估限速。最后，系统实现了所有算法的实时流速度为23 FPS(帧/秒)。
{"title":"Real-Time Collision Warning System Based on Computer Vision Using Mono Camera","authors":"A. Ibrahim, Rania M. Hassan, Andrew E. Tawfiles, T. Ismail, M. Darweesh","doi":"10.1109/NILES50944.2020.9257941","DOIUrl":"https://doi.org/10.1109/NILES50944.2020.9257941","url":null,"abstract":"This paper aims to help self-driving cars and autonomous vehicles systems to merge with the road environment safely and ensure the reliability of these systems in real life. Crash avoidance is a complex system that depends on many parameters. The forward-collision warning system is simplified into four main objectives: detecting cars, depth estimation, assigning cars into lanes (lane assign) and tracking technique. The presented work targets the software approach by using YOLO (You Only Look Once), which is a deep learning object detector network to detect cars with an accuracy of up to 93%. Therefore, apply a depth estimation algorithm that uses the output boundary box’s dimensions (width and height) from YOLO. These dimensions used to estimate the distance with an accuracy of 80.4%. In addition, a real-time computer vision algorithm is applied to assign cars into lanes. However, a tracking proposed algorithm is applied to evaluate the speed limit to keep the vehicle safe. Finally, the real-time system achieved for all algorithms with streaming speed 23 FPS (frame per second).","PeriodicalId":253090,"journal":{"name":"2020 2nd Novel Intelligent and Leading Emerging Sciences Conference (NILES)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122639474","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：