Pub Date : 2021-03-22DOI: 10.1109/ICTSA52017.2021.9406517
R. Q. Shaddad, H. M. Saif, A. H. Qahtan, Ehab A. G. Abdo
Due to appear new applications such as information showering and the vehicular applications that demand a high data rate, better bandwidth utilization, and good quality of service (QoS) in wireless communication systems, that can only be achievable in Fifth Generation (5G). This paper proposes compact triple-band Y-shaped microstrip patch antennas (MPAs) for 5G applications. The proposed antenna has a dimension of $5 times 5 times 0.381$ mm3, uses Rogers/ RT Duroid 5870 as a substrate material, and a loss tangent of 0.0012. The Defected ground structure (DGS) in the middle and groove at the top of the ground plane was implemented. This achieves -10 dB bandwidth from 29.55-30.72 GHz with a maximum gain of 6.834 dB, from 57.36-63.34 GHz with a maximum gain of 10.196 dB, and from 68.56-94.281 GHz with a maximum gain of 8.628 dB at resonant frequencies 30.1 GHz, 60 GHz, and 81.3 GHz respectively. The proposed antenna has a high gain and a broad bandwidth making it a candidate for 5G millimeter-wave (mmwave) applications. Higher Frequency Structural Simulator (HFSS v13) tool is used to simulate the proposed antenna.
{"title":"Y-shaped Triple-band Microstrip Patch Antenna for 5G Millimeter-wave Applications","authors":"R. Q. Shaddad, H. M. Saif, A. H. Qahtan, Ehab A. G. Abdo","doi":"10.1109/ICTSA52017.2021.9406517","DOIUrl":"https://doi.org/10.1109/ICTSA52017.2021.9406517","url":null,"abstract":"Due to appear new applications such as information showering and the vehicular applications that demand a high data rate, better bandwidth utilization, and good quality of service (QoS) in wireless communication systems, that can only be achievable in Fifth Generation (5G). This paper proposes compact triple-band Y-shaped microstrip patch antennas (MPAs) for 5G applications. The proposed antenna has a dimension of $5 times 5 times 0.381$ mm3, uses Rogers/ RT Duroid 5870 as a substrate material, and a loss tangent of 0.0012. The Defected ground structure (DGS) in the middle and groove at the top of the ground plane was implemented. This achieves -10 dB bandwidth from 29.55-30.72 GHz with a maximum gain of 6.834 dB, from 57.36-63.34 GHz with a maximum gain of 10.196 dB, and from 68.56-94.281 GHz with a maximum gain of 8.628 dB at resonant frequencies 30.1 GHz, 60 GHz, and 81.3 GHz respectively. The proposed antenna has a high gain and a broad bandwidth making it a candidate for 5G millimeter-wave (mmwave) applications. Higher Frequency Structural Simulator (HFSS v13) tool is used to simulate the proposed antenna.","PeriodicalId":334654,"journal":{"name":"2021 International Conference of Technology, Science and Administration (ICTSA)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117154594","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 : 2021-03-22DOI: 10.1109/ICTSA52017.2021.9406538
Khaled Moghalles, Hengchao Li, Zaid Al-Huda, E. Hezzam
Building extraction from very high resolution (VHR) imagery plays an important role in urban planning, disaster management, navigation, updating geographic databases, and several other geospatial applications. The automatic generation of buildings from satellite images presents a considerable challenge due to the complexity of building shapes. Compared with the traditional building extraction approaches, deep learning networks have shown outstanding performance in this task by using both high-level and low-level feature maps. Recently, many deep networks derived from U-Net has been extensively used in various buildings segmentation tasks. However, in most of the cases, U-net produce coarse and non-smooth segmentations with lots of discontinuities. To improve and refine the performance of U-Net network, we propose a deep end-to-end network, which use a single encoder and two parallel decoders along with performing the mask predictions also perform distance map estimation. The distance map aid in ensuring smoothness in the segmentation predictions. We also propose a new joint loss function for the proposed architecture. Experimental results based on public international society for photogrammetry and remote sensing (ISPRS) datasets with only (RGB) images demonstrated that the proposed framework can significantly improve the quality of building segmentation.
{"title":"Multi-Task Deep Network for Semantic Segmentation of Building in Very High Resolution Imagery","authors":"Khaled Moghalles, Hengchao Li, Zaid Al-Huda, E. Hezzam","doi":"10.1109/ICTSA52017.2021.9406538","DOIUrl":"https://doi.org/10.1109/ICTSA52017.2021.9406538","url":null,"abstract":"Building extraction from very high resolution (VHR) imagery plays an important role in urban planning, disaster management, navigation, updating geographic databases, and several other geospatial applications. The automatic generation of buildings from satellite images presents a considerable challenge due to the complexity of building shapes. Compared with the traditional building extraction approaches, deep learning networks have shown outstanding performance in this task by using both high-level and low-level feature maps. Recently, many deep networks derived from U-Net has been extensively used in various buildings segmentation tasks. However, in most of the cases, U-net produce coarse and non-smooth segmentations with lots of discontinuities. To improve and refine the performance of U-Net network, we propose a deep end-to-end network, which use a single encoder and two parallel decoders along with performing the mask predictions also perform distance map estimation. The distance map aid in ensuring smoothness in the segmentation predictions. We also propose a new joint loss function for the proposed architecture. Experimental results based on public international society for photogrammetry and remote sensing (ISPRS) datasets with only (RGB) images demonstrated that the proposed framework can significantly improve the quality of building segmentation.","PeriodicalId":334654,"journal":{"name":"2021 International Conference of Technology, Science and Administration (ICTSA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121872213","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 : 2021-03-22DOI: 10.1109/ICTSA52017.2021.9406551
Yousef Fazea, Fathey Mohammed, Nabil Hasan Al-Kumaim, M. S. Sajat
Hardware Trojan (HT) is a malicious program that can cause various kinds of effects related to sensitive information leakage, changes in computer functionality, and Denial of Service (DoS). Hardware Trojan Detection (HT Detection) is a tool developed during the process of making Integrated Circuits (ICs) to avoid anything that might be suspicious. Furthermore, different types of security mechanisms have been created to help and prevent HT from causing any damages. This paper aims to critically review current and previous HT detection approaches and comprehensively discuss the HT detection and prevention techniques that are attacking and triggering the system. Also, the current issues and challenges that arise and the approaches to addressing the issues will be gathered.
{"title":"Automatic Hardware Trojan Generation Platforms in Integrated Circuits: A Critical Review","authors":"Yousef Fazea, Fathey Mohammed, Nabil Hasan Al-Kumaim, M. S. Sajat","doi":"10.1109/ICTSA52017.2021.9406551","DOIUrl":"https://doi.org/10.1109/ICTSA52017.2021.9406551","url":null,"abstract":"Hardware Trojan (HT) is a malicious program that can cause various kinds of effects related to sensitive information leakage, changes in computer functionality, and Denial of Service (DoS). Hardware Trojan Detection (HT Detection) is a tool developed during the process of making Integrated Circuits (ICs) to avoid anything that might be suspicious. Furthermore, different types of security mechanisms have been created to help and prevent HT from causing any damages. This paper aims to critically review current and previous HT detection approaches and comprehensively discuss the HT detection and prevention techniques that are attacking and triggering the system. Also, the current issues and challenges that arise and the approaches to addressing the issues will be gathered.","PeriodicalId":334654,"journal":{"name":"2021 International Conference of Technology, Science and Administration (ICTSA)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122682297","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 : 2021-03-22DOI: 10.1109/ICTSA52017.2021.9406522
A. Sallam, A. Gaid, W. Saif, Hana’a A.S Kaid, Reem A. Abdulkareem, K. Ahmed, Ahmed Y. A. Saeed, Abduljalil Radman
Glaucoma is one of the common diseases that might cause visual field loss, and typically affects elderly people. It is caused by fluid imbalance within the eye that leads to increase in intraocular pressure (IOP), and therefore a damage to the optic nerve head (ONH) which is responsible in transmitting visual neurological signals to the brain. Traditional methods for detecting Glaucoma disease either tedious and slow or too expensive. Hence, early detection of Glaucoma is essential to avoid permanent blindness which might be caused by the ONH failure. In this paper, an automated detection method on the basis of pre-trained Convolutional Neural Network (CNN) models is proposed to detect Glaucoma from fundus images. The proposed method not only contributes to early detection of Glaucoma disease, but also helps optometry doctors in making fast decision with inexpensive tools. Pre-trained AlexNet, VGG11, VGG16, VGG19, GoogleNet (Inception V1), ResNET-18, ResNET-50, ResNET-101 and ResNet-152 models were leveraged to develop the proposed Glaucoma detection method. The proposed method was evaluated by Large-scale Attention based Glaucoma (LAG) dataset. Satisfying results of 81.4%, 80%, 82.2%, 80.9%, 82.9%, 86.7%, 85.6%, 86.2%, and 86.9% were observed on LAG dataset using AlexNet, VGG11, VGG16, VGG19, GoogleNet (Inception V1), ResNET-18, ResNET-50, ResNET-101 and ResNet-152 models respectively. Out of these results, the ResNet-152 model found to be the best that achieved a high accuracy with precision 86.9% and recall 86.9%.
{"title":"Early Detection of Glaucoma using Transfer Learning from Pre-trained CNN Models","authors":"A. Sallam, A. Gaid, W. Saif, Hana’a A.S Kaid, Reem A. Abdulkareem, K. Ahmed, Ahmed Y. A. Saeed, Abduljalil Radman","doi":"10.1109/ICTSA52017.2021.9406522","DOIUrl":"https://doi.org/10.1109/ICTSA52017.2021.9406522","url":null,"abstract":"Glaucoma is one of the common diseases that might cause visual field loss, and typically affects elderly people. It is caused by fluid imbalance within the eye that leads to increase in intraocular pressure (IOP), and therefore a damage to the optic nerve head (ONH) which is responsible in transmitting visual neurological signals to the brain. Traditional methods for detecting Glaucoma disease either tedious and slow or too expensive. Hence, early detection of Glaucoma is essential to avoid permanent blindness which might be caused by the ONH failure. In this paper, an automated detection method on the basis of pre-trained Convolutional Neural Network (CNN) models is proposed to detect Glaucoma from fundus images. The proposed method not only contributes to early detection of Glaucoma disease, but also helps optometry doctors in making fast decision with inexpensive tools. Pre-trained AlexNet, VGG11, VGG16, VGG19, GoogleNet (Inception V1), ResNET-18, ResNET-50, ResNET-101 and ResNet-152 models were leveraged to develop the proposed Glaucoma detection method. The proposed method was evaluated by Large-scale Attention based Glaucoma (LAG) dataset. Satisfying results of 81.4%, 80%, 82.2%, 80.9%, 82.9%, 86.7%, 85.6%, 86.2%, and 86.9% were observed on LAG dataset using AlexNet, VGG11, VGG16, VGG19, GoogleNet (Inception V1), ResNET-18, ResNET-50, ResNET-101 and ResNet-152 models respectively. Out of these results, the ResNet-152 model found to be the best that achieved a high accuracy with precision 86.9% and recall 86.9%.","PeriodicalId":334654,"journal":{"name":"2021 International Conference of Technology, Science and Administration (ICTSA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132509784","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 : 2021-03-22DOI: 10.1109/ICTSA52017.2021.9406530
Sameha Abdullah Moogab, A. A. Al-Shalabi, I. Al-Baltah
The Holy Quran is a cyclopedia document that contains a huge volume of knowledge. Many modern scientific discoveries are much similar to some verses of the Quran, which the Islamic scientists call a scientific miracle in the Holy Quran. However, representing knowledge of scientific miracles in the Holy Quran on the semantic web in a such way that enables sharing and reusing is still a research issue. This research suggests a general structure for these scientific facts mentioned in the Holy Quran and then represents this structure by creating Scientific Miracle Ontology (SMO) using METHONTOLOGY methodology. The results of SMO have been evaluated by competency questions and translated these competency questions into SPARQL queries and the results obtained emphasized that SMO was effective in retrieval relevant concepts and verses of scientific miracles in the Holy Quran.
{"title":"An Ontological Model for Scientific Miracle in the Holy Quran","authors":"Sameha Abdullah Moogab, A. A. Al-Shalabi, I. Al-Baltah","doi":"10.1109/ICTSA52017.2021.9406530","DOIUrl":"https://doi.org/10.1109/ICTSA52017.2021.9406530","url":null,"abstract":"The Holy Quran is a cyclopedia document that contains a huge volume of knowledge. Many modern scientific discoveries are much similar to some verses of the Quran, which the Islamic scientists call a scientific miracle in the Holy Quran. However, representing knowledge of scientific miracles in the Holy Quran on the semantic web in a such way that enables sharing and reusing is still a research issue. This research suggests a general structure for these scientific facts mentioned in the Holy Quran and then represents this structure by creating Scientific Miracle Ontology (SMO) using METHONTOLOGY methodology. The results of SMO have been evaluated by competency questions and translated these competency questions into SPARQL queries and the results obtained emphasized that SMO was effective in retrieval relevant concepts and verses of scientific miracles in the Holy Quran.","PeriodicalId":334654,"journal":{"name":"2021 International Conference of Technology, Science and Administration (ICTSA)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127269739","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 : 2021-03-22DOI: 10.1109/ICTSA52017.2021.9406535
R. Q. Shaddad, Neda’a A. Alsarori, Mushira O. Alzylai, Tareq M. Shami
The deployment of heterogeneous networks (HetNets) is one of the promising approaches to meet the 5G requirements. The traditional user association approach is inefficient for HetNets due to the high transmission power of macro base stations (BSs) and the low transmission power of small cell BSs, i.e., pico and femto BSs. This approach causes macro BSs to be overloaded whereas small cell BSs are lightly loaded. To address this load imbalance in 5G HetNets, 3GPP introduced the concept of cell range expansion (CRE) where the coverage area of small cell BSs is artificially increased by adding a bias value to the power received from small cells. Although the biasing approach can better balance the load among tiers, users at the expansion area suffer from severe interference coming from neighbouring macro BSs. This work utilizes coordinated multi-point transmission (CoMP) to reduce interference. User-centric clustering where a user can be served by a number of BSs is implemented. The results have sown that user-centric CoMP can significantly improve the SINR levels of all users and cell-edge users as well.
{"title":"Biased User Association in 5G Heterogeneous Networks","authors":"R. Q. Shaddad, Neda’a A. Alsarori, Mushira O. Alzylai, Tareq M. Shami","doi":"10.1109/ICTSA52017.2021.9406535","DOIUrl":"https://doi.org/10.1109/ICTSA52017.2021.9406535","url":null,"abstract":"The deployment of heterogeneous networks (HetNets) is one of the promising approaches to meet the 5G requirements. The traditional user association approach is inefficient for HetNets due to the high transmission power of macro base stations (BSs) and the low transmission power of small cell BSs, i.e., pico and femto BSs. This approach causes macro BSs to be overloaded whereas small cell BSs are lightly loaded. To address this load imbalance in 5G HetNets, 3GPP introduced the concept of cell range expansion (CRE) where the coverage area of small cell BSs is artificially increased by adding a bias value to the power received from small cells. Although the biasing approach can better balance the load among tiers, users at the expansion area suffer from severe interference coming from neighbouring macro BSs. This work utilizes coordinated multi-point transmission (CoMP) to reduce interference. User-centric clustering where a user can be served by a number of BSs is implemented. The results have sown that user-centric CoMP can significantly improve the SINR levels of all users and cell-edge users as well.","PeriodicalId":334654,"journal":{"name":"2021 International Conference of Technology, Science and Administration (ICTSA)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128954275","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 : 2021-03-22DOI: 10.1109/ICTSA52017.2021.9406539
Ghazi Alnowaini, Amjad Abdullah Aljomai
Building of university timetable is one of the problems that are difficult to be solved because of the large number of lectures and conflicts between them. This makes it difficult to introduce schedule-building restrictions that consume time and effort for table production. Many methods have been suggested that the computer is used to solve this problem, including a Genetic Algorithm (GA) where the main purpose of the algorithm is to reduce the number of conflicts in the timesheet and to reduce the search space encoding. This paper proposes an automated system to build a faculty timetable using a genetic algorithm. A genetic algorithm had been used to schedule the timetable of the faculty of engineering and information technology with a dynamic chromosome size that is flexible with the course numbers of each department. This algorithm can be applied in different institutions (i.e. faculties, or institutes) According to their limitations. The proposed system achieved great results during the evaluation phase of around 93% compared to manual scheduling or the systems available.
{"title":"Genetic Algorithm For Solving University Course Timetabling Problem Using Dynamic Chromosomes","authors":"Ghazi Alnowaini, Amjad Abdullah Aljomai","doi":"10.1109/ICTSA52017.2021.9406539","DOIUrl":"https://doi.org/10.1109/ICTSA52017.2021.9406539","url":null,"abstract":"Building of university timetable is one of the problems that are difficult to be solved because of the large number of lectures and conflicts between them. This makes it difficult to introduce schedule-building restrictions that consume time and effort for table production. Many methods have been suggested that the computer is used to solve this problem, including a Genetic Algorithm (GA) where the main purpose of the algorithm is to reduce the number of conflicts in the timesheet and to reduce the search space encoding. This paper proposes an automated system to build a faculty timetable using a genetic algorithm. A genetic algorithm had been used to schedule the timetable of the faculty of engineering and information technology with a dynamic chromosome size that is flexible with the course numbers of each department. This algorithm can be applied in different institutions (i.e. faculties, or institutes) According to their limitations. The proposed system achieved great results during the evaluation phase of around 93% compared to manual scheduling or the systems available.","PeriodicalId":334654,"journal":{"name":"2021 International Conference of Technology, Science and Administration (ICTSA)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121111593","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 : 2021-03-22DOI: 10.1109/ICTSA52017.2021.9406553
Mohammed Hashem Almourish, Alaa A. Saif, Borhan M. N. Radman, Ahmed Y. A. Saeed
the NOVEL (COVID-19) coronavirus has recently grown into a pandemic in the world due to the severe acute respiratory syndrome (SARSCoV-2). According to studies in this area, about 34,440,235 people are infected with COVID-19, 1,023,430 is the number of deaths, and around 25,633,956 patients are being subjected to treatment worldwide. In this paper researchers used five pre-trained models. They are: ResNet-50, ResNet-101, AlexNet, VGG11, and SqueezeNetV-1.0. DTL (deep transfer learning) is used to diagnose the NOVEL (COVID-19) by training the COVID-19 coronavirus dataset with 32-batch size and 25 epochs. In training, ResNet-50 gives the best value in loss rate (0.22) with an accuracy of 93.2%, whereas, VGG11 showed the worst value (0.38). Also, in validation, the results showed that ResNet-50 (0.28) is the best, and VGG11 achieved (0.39) as the worst value.
最近，新型冠状病毒(COVID-19)因严重急性呼吸系统综合征(SARSCoV-2)而在世界范围内蔓延。据该领域的研究，全球新冠肺炎感染人数约为34440235人，死亡人数为1023430人，正在接受治疗的患者约为25633956人。在本文中，研究者使用了五个预训练模型。它们是:ResNet-50、ResNet-101、AlexNet、VGG11和SqueezeNetV-1.0。DTL (deep transfer learning)通过训练32批大小、25 epoch的COVID-19冠状病毒数据集来诊断新型冠状病毒(COVID-19)。在训练中，ResNet-50的损失率最好(0.22)，准确率为93.2%，而VGG11的损失率最差(0.38)。在验证中，结果显示ResNet-50为最佳值(0.28)，VGG11为最差值(0.39)。
{"title":"Covid-19 Diagnosis Based on CT Images Using Pre-Trained Models","authors":"Mohammed Hashem Almourish, Alaa A. Saif, Borhan M. N. Radman, Ahmed Y. A. Saeed","doi":"10.1109/ICTSA52017.2021.9406553","DOIUrl":"https://doi.org/10.1109/ICTSA52017.2021.9406553","url":null,"abstract":"the NOVEL (COVID-19) coronavirus has recently grown into a pandemic in the world due to the severe acute respiratory syndrome (SARSCoV-2). According to studies in this area, about 34,440,235 people are infected with COVID-19, 1,023,430 is the number of deaths, and around 25,633,956 patients are being subjected to treatment worldwide. In this paper researchers used five pre-trained models. They are: ResNet-50, ResNet-101, AlexNet, VGG11, and SqueezeNetV-1.0. DTL (deep transfer learning) is used to diagnose the NOVEL (COVID-19) by training the COVID-19 coronavirus dataset with 32-batch size and 25 epochs. In training, ResNet-50 gives the best value in loss rate (0.22) with an accuracy of 93.2%, whereas, VGG11 showed the worst value (0.38). Also, in validation, the results showed that ResNet-50 (0.28) is the best, and VGG11 achieved (0.39) as the worst value.","PeriodicalId":334654,"journal":{"name":"2021 International Conference of Technology, Science and Administration (ICTSA)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124474376","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 : 2021-03-22DOI: 10.1109/ICTSA52017.2021.9406552
R. Q. Shaddad, Aimn M. Al-Ssarary, Suhail A. Al-mekhlafi, Mazen D.Qaid, Zeyad M.Farhan
Over the last few years, optical switching technology for data centers (DC) has gained much attention due to the potential and benefits of using optical components. The performance of the optical network is directly related to the type of optical switching technique used. Optical burst switch (OBS) is currently being developed as a technology capable of supporting wide bandwidth, enabling high transmission of information and various types of traffic. Losses due to contention between bursts at the core nodes are one of the main problems that prevent the achievement of optical burst switching (OBS) technology on core networks. In this paper, wavelength conversion and deflection routing techniques used together to get the best solution for the problem of contention bursts that might be occurred at the core node. Performance evaluation was investigated by analysis of burst loss probability and steady-state throughput using steady-state occupancy probabilities and Poisson traffic model arrivals and the analyzed results are presented at different mean burst arrival rates and the different number of wavelengths.
{"title":"Contention Resolution of Optical Burst Switching for Data Center","authors":"R. Q. Shaddad, Aimn M. Al-Ssarary, Suhail A. Al-mekhlafi, Mazen D.Qaid, Zeyad M.Farhan","doi":"10.1109/ICTSA52017.2021.9406552","DOIUrl":"https://doi.org/10.1109/ICTSA52017.2021.9406552","url":null,"abstract":"Over the last few years, optical switching technology for data centers (DC) has gained much attention due to the potential and benefits of using optical components. The performance of the optical network is directly related to the type of optical switching technique used. Optical burst switch (OBS) is currently being developed as a technology capable of supporting wide bandwidth, enabling high transmission of information and various types of traffic. Losses due to contention between bursts at the core nodes are one of the main problems that prevent the achievement of optical burst switching (OBS) technology on core networks. In this paper, wavelength conversion and deflection routing techniques used together to get the best solution for the problem of contention bursts that might be occurred at the core node. Performance evaluation was investigated by analysis of burst loss probability and steady-state throughput using steady-state occupancy probabilities and Poisson traffic model arrivals and the analyzed results are presented at different mean burst arrival rates and the different number of wavelengths.","PeriodicalId":334654,"journal":{"name":"2021 International Conference of Technology, Science and Administration (ICTSA)","volume":"194 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115501868","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 : 2021-03-22DOI: 10.1109/ICTSA52017.2021.9406531
R. Q. Shaddad, Abduljalil Ali A. Mohammed, Mohammed Kh. Alwajih
FiWi access network provides the end-users with a large amount of bandwidth and reliability in a flexible manner as it integrates the technical merit of the fiber and wireless network, FiWi access network is a promising access technology, because of the tremendous increase in traffic demands in the FiWi access network, achieving good survivability is facing major challenges as vast traffic could be disrupted due to the failure of any FiWi portion. In this study, all-optical network failures are addressed. Single and multiple segments addressing is allocated an ONU backup in each segment satisfying the shortest distance to backup ONUs in other segments and classified network segments as a cluster. So, backup fibers are deployed between the backup ONUs in each cluster in separate segments to create a protection scheme that satisfies maximum protection and minimum cost. The results accomplished minimizing the backup fiber cost by 20 % compared with the ring scheme and minimize the spare capacity that needs for maximum protection by sharing the spare capacity for segments in the same cluster
{"title":"Survivability of Fiber Wireless (FiWi) Access Network","authors":"R. Q. Shaddad, Abduljalil Ali A. Mohammed, Mohammed Kh. Alwajih","doi":"10.1109/ICTSA52017.2021.9406531","DOIUrl":"https://doi.org/10.1109/ICTSA52017.2021.9406531","url":null,"abstract":"FiWi access network provides the end-users with a large amount of bandwidth and reliability in a flexible manner as it integrates the technical merit of the fiber and wireless network, FiWi access network is a promising access technology, because of the tremendous increase in traffic demands in the FiWi access network, achieving good survivability is facing major challenges as vast traffic could be disrupted due to the failure of any FiWi portion. In this study, all-optical network failures are addressed. Single and multiple segments addressing is allocated an ONU backup in each segment satisfying the shortest distance to backup ONUs in other segments and classified network segments as a cluster. So, backup fibers are deployed between the backup ONUs in each cluster in separate segments to create a protection scheme that satisfies maximum protection and minimum cost. The results accomplished minimizing the backup fiber cost by 20 % compared with the ring scheme and minimize the spare capacity that needs for maximum protection by sharing the spare capacity for segments in the same cluster","PeriodicalId":334654,"journal":{"name":"2021 International Conference of Technology, Science and Administration (ICTSA)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115604592","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：