Pub Date : 2021-06-11DOI: 10.1109/HORA52670.2021.9461285
S. Hizal, Ü. Çavuşoğlu, D. Akgün
Cloud computing is used in many different research areas thanks to its high computing power and network capacity. Data security, cost-effectiveness, and flexibility of working options for remote workers have made this technology even more attractive today. Today, servers in cloud computing should protect themselves from threats more intelligently and provide security by preventing a new threat. A new deep learning model based on convolutional neural networks and recurrent neural networks for intrusion detection has been developed for cloud security in this study. The proposed model was trained and tested using NSL-KDD train dataset. With our deep learning model, any detected and not approved traffic is prevented from reaching the server in the cloud. The proposed system has 99.86% accuracy for five-class classification, which is the best result comparative to studies in the literature.
{"title":"A new Deep Learning Based Intrusion Detection System for Cloud Security","authors":"S. Hizal, Ü. Çavuşoğlu, D. Akgün","doi":"10.1109/HORA52670.2021.9461285","DOIUrl":"https://doi.org/10.1109/HORA52670.2021.9461285","url":null,"abstract":"Cloud computing is used in many different research areas thanks to its high computing power and network capacity. Data security, cost-effectiveness, and flexibility of working options for remote workers have made this technology even more attractive today. Today, servers in cloud computing should protect themselves from threats more intelligently and provide security by preventing a new threat. A new deep learning model based on convolutional neural networks and recurrent neural networks for intrusion detection has been developed for cloud security in this study. The proposed model was trained and tested using NSL-KDD train dataset. With our deep learning model, any detected and not approved traffic is prevented from reaching the server in the cloud. The proposed system has 99.86% accuracy for five-class classification, which is the best result comparative to studies in the literature.","PeriodicalId":270469,"journal":{"name":"2021 3rd International Congress on Human-Computer Interaction, Optimization and Robotic Applications (HORA)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132211567","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 : 2021-06-11DOI: 10.1109/HORA52670.2021.9461368
V. Hristov, B. Kostov
The current paper presents the implementation of machine learning to improve the algorithm for taking a part with a specific marker from a 6-axis robot, by serve it to a 2D camera for visual inspection and its correct orientation based on information received from the camera and placement on another part with a pre-marked marker direction. The aim of the present development is to increase the efficiency of automated production of electronic products. After the introduction of machine learning in the algorithm for determining distortions, injuries or other damage to the part, an improvement was achieved in the quality of the processed parts and a reduction of production waste by up to 30%, which led to an increase in system efficiency by 25%.
{"title":"Application of Machine Learning for Improving the Algorithm for Capturing, Orienting and Placing an Object with 6-Axis Robot and 2d Visual Inspection Camera","authors":"V. Hristov, B. Kostov","doi":"10.1109/HORA52670.2021.9461368","DOIUrl":"https://doi.org/10.1109/HORA52670.2021.9461368","url":null,"abstract":"The current paper presents the implementation of machine learning to improve the algorithm for taking a part with a specific marker from a 6-axis robot, by serve it to a 2D camera for visual inspection and its correct orientation based on information received from the camera and placement on another part with a pre-marked marker direction. The aim of the present development is to increase the efficiency of automated production of electronic products. After the introduction of machine learning in the algorithm for determining distortions, injuries or other damage to the part, an improvement was achieved in the quality of the processed parts and a reduction of production waste by up to 30%, which led to an increase in system efficiency by 25%.","PeriodicalId":270469,"journal":{"name":"2021 3rd International Congress on Human-Computer Interaction, Optimization and Robotic Applications (HORA)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134244681","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 : 2021-06-11DOI: 10.1109/HORA52670.2021.9461279
Erdem Bayhan, Zehra Ozkan, Mustafa Namdar, Arif Basgumus
In this study, the methods of deep learning-based detection and recognition of the threats, evaluated in terms of military and defense industry, by unmanned aerial vehicles (UAV) are presented. In the proposed approach, firstly, the training for machine learning on the objects is carried out using convolutional neural networks, which is one of the deep learning algorithms. By choosing the Faster-RCNN and YoloV4 architectures of the deep learning method, it is aimed to compare the achievements of the accuracy in the training process. In order to be used in the training and testing stages of the recommended methods, data sets containing images selected from different weather, land conditions and different time periods of the day are determined. The model for the detection and recognition of the threatening elements is trained, using 2595 images. The method of detecting and recognizing the objects is tested with military operation images and records taken by the UAVs. While an accuracy rate of 93% has been achieved in the Faster-RCNN architecture in object detection and recognition, this rate has been observed as 88% in the YoloV4 architecture.
{"title":"Deep Learning Based Object Detection and Recognition of Unmanned Aerial Vehicles","authors":"Erdem Bayhan, Zehra Ozkan, Mustafa Namdar, Arif Basgumus","doi":"10.1109/HORA52670.2021.9461279","DOIUrl":"https://doi.org/10.1109/HORA52670.2021.9461279","url":null,"abstract":"In this study, the methods of deep learning-based detection and recognition of the threats, evaluated in terms of military and defense industry, by unmanned aerial vehicles (UAV) are presented. In the proposed approach, firstly, the training for machine learning on the objects is carried out using convolutional neural networks, which is one of the deep learning algorithms. By choosing the Faster-RCNN and YoloV4 architectures of the deep learning method, it is aimed to compare the achievements of the accuracy in the training process. In order to be used in the training and testing stages of the recommended methods, data sets containing images selected from different weather, land conditions and different time periods of the day are determined. The model for the detection and recognition of the threatening elements is trained, using 2595 images. The method of detecting and recognizing the objects is tested with military operation images and records taken by the UAVs. While an accuracy rate of 93% has been achieved in the Faster-RCNN architecture in object detection and recognition, this rate has been observed as 88% in the YoloV4 architecture.","PeriodicalId":270469,"journal":{"name":"2021 3rd International Congress on Human-Computer Interaction, Optimization and Robotic Applications (HORA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133422846","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 : 2021-06-11DOI: 10.1109/HORA52670.2021.9461310
Sameer Alani, Z. Zakaria, Asmala Ahmad
Owing to its specific characteristics such as short-range, non-ionizing, and wide bandwidth, UWB technology is now widely recommended for use in such an application. This paper examines the process of imaging and localizing breast cancer using a UWB antenna sensor network. We concentrate on a two-dimensional network of UWB antenna sensors that are used to activate the object as well as capture delayed and phase-shifted data. The data must be analyzed using an algorithm that eliminates noise and clutter while displaying the image in high resolution. The sensitivity and efficiency of the machine are improved by using more UWB sensors. Preliminary findings are displayed in the simulation setting to assess the viability of the suggested solution.
{"title":"Localizing and Imaging of Breast Cancer Based on UWB Antenna Sensor Network","authors":"Sameer Alani, Z. Zakaria, Asmala Ahmad","doi":"10.1109/HORA52670.2021.9461310","DOIUrl":"https://doi.org/10.1109/HORA52670.2021.9461310","url":null,"abstract":"Owing to its specific characteristics such as short-range, non-ionizing, and wide bandwidth, UWB technology is now widely recommended for use in such an application. This paper examines the process of imaging and localizing breast cancer using a UWB antenna sensor network. We concentrate on a two-dimensional network of UWB antenna sensors that are used to activate the object as well as capture delayed and phase-shifted data. The data must be analyzed using an algorithm that eliminates noise and clutter while displaying the image in high resolution. The sensitivity and efficiency of the machine are improved by using more UWB sensors. Preliminary findings are displayed in the simulation setting to assess the viability of the suggested solution.","PeriodicalId":270469,"journal":{"name":"2021 3rd International Congress on Human-Computer Interaction, Optimization and Robotic Applications (HORA)","volume":"80 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116755748","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 : 2021-06-11DOI: 10.1109/HORA52670.2021.9461354
Mert İleri, M. Turan
In the last decade, enormous data are being shared throughout the world. In many of today’s big data world, the companies are trying to use some sentiment or emotion analysis techniques to analyze their customer moods and improve their efficiencies according to sentiments. As a different application we focused on the sentiment analysis of closed places in this research. It requires low noise environments obviously. Otherwise, system may be affected by distortion, and it may be contradiction for multiple sentiments. In this regard, an artificial neural network using meaningful voice features are proposed. Ryerson Audio Visual Database of Emotional Speech and Song (RAVDESS) dataset was used in this research. Normalization was applied to data. The artificial neural network was fed by training data and a classifier model was created. Estimation was made using the test data part and it was seen that accuracy of model is about 85%.
{"title":"Sentiment Analysis of Meeting Room","authors":"Mert İleri, M. Turan","doi":"10.1109/HORA52670.2021.9461354","DOIUrl":"https://doi.org/10.1109/HORA52670.2021.9461354","url":null,"abstract":"In the last decade, enormous data are being shared throughout the world. In many of today’s big data world, the companies are trying to use some sentiment or emotion analysis techniques to analyze their customer moods and improve their efficiencies according to sentiments. As a different application we focused on the sentiment analysis of closed places in this research. It requires low noise environments obviously. Otherwise, system may be affected by distortion, and it may be contradiction for multiple sentiments. In this regard, an artificial neural network using meaningful voice features are proposed. Ryerson Audio Visual Database of Emotional Speech and Song (RAVDESS) dataset was used in this research. Normalization was applied to data. The artificial neural network was fed by training data and a classifier model was created. Estimation was made using the test data part and it was seen that accuracy of model is about 85%.","PeriodicalId":270469,"journal":{"name":"2021 3rd International Congress on Human-Computer Interaction, Optimization and Robotic Applications (HORA)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130209011","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 : 2021-06-11DOI: 10.1109/HORA52670.2021.9461292
M. Al-Mashhadani, Mustafa Maad Hamdi, A. Mustafa
With the latest technological developments in UAVs and the ever-increasing evolution of commercialization, new UAV technologies have emerged for wireless sensor networks for data collection. The integration of UAVs in smart ground WSNs proved an effective and stable solution in many advanced applications for information collection, control, analysis, and decision-making. In this area, a wireless network of unnamed aerial-vehicle - wireless sensor network still faces many open technical challenges, despite the success of numerous applications and studies. These include pre-defined UAV paths, medium access control (MAC), UAV performance, and unexpected feature. The objectives of this research are to review and investigate the WSN system with UAV assistance focusing on the wide range of monitoring applications and the open problems for the operation of the system.
{"title":"Role and challenges of the use of UAV-aided WSN monitoring system in large-scale sectors","authors":"M. Al-Mashhadani, Mustafa Maad Hamdi, A. Mustafa","doi":"10.1109/HORA52670.2021.9461292","DOIUrl":"https://doi.org/10.1109/HORA52670.2021.9461292","url":null,"abstract":"With the latest technological developments in UAVs and the ever-increasing evolution of commercialization, new UAV technologies have emerged for wireless sensor networks for data collection. The integration of UAVs in smart ground WSNs proved an effective and stable solution in many advanced applications for information collection, control, analysis, and decision-making. In this area, a wireless network of unnamed aerial-vehicle - wireless sensor network still faces many open technical challenges, despite the success of numerous applications and studies. These include pre-defined UAV paths, medium access control (MAC), UAV performance, and unexpected feature. The objectives of this research are to review and investigate the WSN system with UAV assistance focusing on the wide range of monitoring applications and the open problems for the operation of the system.","PeriodicalId":270469,"journal":{"name":"2021 3rd International Congress on Human-Computer Interaction, Optimization and Robotic Applications (HORA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130126840","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 : 2021-06-11DOI: 10.1109/HORA52670.2021.9461296
Hussain Falih Mahdi, Rishit Dagli, A. Mustufa, Sameer Nanivadekar
In this paper, we focus on creating a keywords extractor especially for a given job description job-related text corpus for better search engine optimization using attention based deep learning techniques. Millions of jobs are posted but most of them end up not being located due to improper SEO and keyword management. We aim to make this as easy to use as possible and allow us to use this for a large number of job descriptions very easily. We also make use of these algorithms to screen or get insights from large number of resumes, summarize and create keywords for a general piece of text or scientific articles. We also investigate the modeling power of BERT (Bidirectional Encoder Representations from Transformers) for the task of keyword extraction from job descriptions. We further validate our results by providing a fully-functional API and testing out the model with real-time job descriptions.
{"title":"Job Descriptions Keyword Extraction using Attention based Deep Learning Models with BERT","authors":"Hussain Falih Mahdi, Rishit Dagli, A. Mustufa, Sameer Nanivadekar","doi":"10.1109/HORA52670.2021.9461296","DOIUrl":"https://doi.org/10.1109/HORA52670.2021.9461296","url":null,"abstract":"In this paper, we focus on creating a keywords extractor especially for a given job description job-related text corpus for better search engine optimization using attention based deep learning techniques. Millions of jobs are posted but most of them end up not being located due to improper SEO and keyword management. We aim to make this as easy to use as possible and allow us to use this for a large number of job descriptions very easily. We also make use of these algorithms to screen or get insights from large number of resumes, summarize and create keywords for a general piece of text or scientific articles. We also investigate the modeling power of BERT (Bidirectional Encoder Representations from Transformers) for the task of keyword extraction from job descriptions. We further validate our results by providing a fully-functional API and testing out the model with real-time job descriptions.","PeriodicalId":270469,"journal":{"name":"2021 3rd International Congress on Human-Computer Interaction, Optimization and Robotic Applications (HORA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129647384","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 : 2021-06-11DOI: 10.1109/HORA52670.2021.9461352
Tsvetelina Mladenova, Yordan Kalmukov, Irena Valova
Research and analysis of user experience in software applications is a current area in the design and development of the user interface. Analysis of users’ behavior in a specific application can help detect vulnerabilities in the interface and direct developers to places to change. There are different approaches to data collection and analysis of user experience, as well as ready-made software environments that implement this. In this paper, we describe a particular approach to collecting, processing, and analyzing user behavior data in a web-based specific-task-oriented system. Information about the number of user sessions and clicks on various elements of the user interface is stored with the purpose of collecting enough historical data that can be further analyzed. The dataset examined in this paper consist of information about the sequences of actions of each user for five months. The dataset is unique because it contains user sessions right from the release of the application, giving the opportunity to examine the first responses of the users and to follow the development of their habits while working with it. The different groups of users (known in advance) and their behavior in the system are described. Conclusions are made about the benefits of changes to the interface and the added new features, as well as the way users perceive and use them.
{"title":"Analysis of the user experience in a web-based university staff’s publication management system","authors":"Tsvetelina Mladenova, Yordan Kalmukov, Irena Valova","doi":"10.1109/HORA52670.2021.9461352","DOIUrl":"https://doi.org/10.1109/HORA52670.2021.9461352","url":null,"abstract":"Research and analysis of user experience in software applications is a current area in the design and development of the user interface. Analysis of users’ behavior in a specific application can help detect vulnerabilities in the interface and direct developers to places to change. There are different approaches to data collection and analysis of user experience, as well as ready-made software environments that implement this. In this paper, we describe a particular approach to collecting, processing, and analyzing user behavior data in a web-based specific-task-oriented system. Information about the number of user sessions and clicks on various elements of the user interface is stored with the purpose of collecting enough historical data that can be further analyzed. The dataset examined in this paper consist of information about the sequences of actions of each user for five months. The dataset is unique because it contains user sessions right from the release of the application, giving the opportunity to examine the first responses of the users and to follow the development of their habits while working with it. The different groups of users (known in advance) and their behavior in the system are described. Conclusions are made about the benefits of changes to the interface and the added new features, as well as the way users perceive and use them.","PeriodicalId":270469,"journal":{"name":"2021 3rd International Congress on Human-Computer Interaction, Optimization and Robotic Applications (HORA)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129466660","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 : 2021-06-11DOI: 10.1109/HORA52670.2021.9461298
Diyana Kinaneva, Georgi V. Hristov, Petko Kyuchukov, G. Georgiev, P. Zahariev, Rosen Daskalov
Machine learning has become extremely popular in recent years due to its ability to train models to deal with complex task. Machine learning (ML) algorithms are one of the fundamentals behind Artificial Intelligence (AI), which is now widely spread among different areas of our lives. The success of the machine-learning algorithm very depends on the training datasets. In order to achieve good accuracy ML algorithms must be trained with well-prepared input datasets. Data preparation is a set of procedures that helps make the dataset more suitable for machine learning. The goal of the paper is to summarize different techniques for data preparation and to make analysis which of them directly affect the accuracy of the final model. Different ML algorithms are considers and tested for training a model to predict numerical variables which is not based on neural networks.
{"title":"Machine Learning Algorithms for Regression Analysis and Predictions of Numerical Data","authors":"Diyana Kinaneva, Georgi V. Hristov, Petko Kyuchukov, G. Georgiev, P. Zahariev, Rosen Daskalov","doi":"10.1109/HORA52670.2021.9461298","DOIUrl":"https://doi.org/10.1109/HORA52670.2021.9461298","url":null,"abstract":"Machine learning has become extremely popular in recent years due to its ability to train models to deal with complex task. Machine learning (ML) algorithms are one of the fundamentals behind Artificial Intelligence (AI), which is now widely spread among different areas of our lives. The success of the machine-learning algorithm very depends on the training datasets. In order to achieve good accuracy ML algorithms must be trained with well-prepared input datasets. Data preparation is a set of procedures that helps make the dataset more suitable for machine learning. The goal of the paper is to summarize different techniques for data preparation and to make analysis which of them directly affect the accuracy of the final model. Different ML algorithms are considers and tested for training a model to predict numerical variables which is not based on neural networks.","PeriodicalId":270469,"journal":{"name":"2021 3rd International Congress on Human-Computer Interaction, Optimization and Robotic Applications (HORA)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124462381","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 : 2021-06-11DOI: 10.1109/HORA52670.2021.9461358
A. Mohammed, N. Abdullah, Sameer Alani, Othman S. Alheety, Mohammed Mudhafar Shaker, M. A. Saad, S. Mahmood
A Mobile Ad-hoc Network (MANET) is a self-directed group of mobile handlers that communicate over relatively bandwidth constrained wireless channels. Many types of data could be transferred in MANET such as data, voice, and video streaming which is required sufficient packet routing and scheduling mechanisms. These scheduling algorithms have the responsibility to guarantee the different quality of service classes such as Unsolicited Grant Service (UGS), Real-Time Polling Service (RTPS), Non-Real-Time Polling Service (NRTPS), and Best Effort (BE). The demand for performance evaluation for different scheduling algorithms is imposed to this project, in which four famous MANET scheduling algorithms are selected and investigated. These algorithms are Round Robin (RR), Strict Priority (SP), Weighted Fair (WF), and Weighted Round Robin (WRR). The MANET scenario which is consisting of 50 random mobile nodes is built using network simulator QualNet 2.0.1. The results show the performance metrics of the network such as the throughput and the end-end delay as well as queuing metrics such as peak queue size, average queue length, the average time in queue, and total packets dropped. Regrading throughput, the SP algorithm has higher throughput than WF, RR, and WRR by 4.5%, 2.4%, and 1.42%, but WRR has outperformed others regarding the end-to-end delay. Moreover, WRR represents the best scheduling algorithm regarding both peak queue size since its higher than RP, WF, and WRR by 10.13%, 9.6%, and 5.32%, in order, and average output queue length.in contrast, WRR worst more time in queuing but it is the best in preventing the packets from dropping.
{"title":"Weighted Round Robin Scheduling Algorithms in Mobile AD HOC Network","authors":"A. Mohammed, N. Abdullah, Sameer Alani, Othman S. Alheety, Mohammed Mudhafar Shaker, M. A. Saad, S. Mahmood","doi":"10.1109/HORA52670.2021.9461358","DOIUrl":"https://doi.org/10.1109/HORA52670.2021.9461358","url":null,"abstract":"A Mobile Ad-hoc Network (MANET) is a self-directed group of mobile handlers that communicate over relatively bandwidth constrained wireless channels. Many types of data could be transferred in MANET such as data, voice, and video streaming which is required sufficient packet routing and scheduling mechanisms. These scheduling algorithms have the responsibility to guarantee the different quality of service classes such as Unsolicited Grant Service (UGS), Real-Time Polling Service (RTPS), Non-Real-Time Polling Service (NRTPS), and Best Effort (BE). The demand for performance evaluation for different scheduling algorithms is imposed to this project, in which four famous MANET scheduling algorithms are selected and investigated. These algorithms are Round Robin (RR), Strict Priority (SP), Weighted Fair (WF), and Weighted Round Robin (WRR). The MANET scenario which is consisting of 50 random mobile nodes is built using network simulator QualNet 2.0.1. The results show the performance metrics of the network such as the throughput and the end-end delay as well as queuing metrics such as peak queue size, average queue length, the average time in queue, and total packets dropped. Regrading throughput, the SP algorithm has higher throughput than WF, RR, and WRR by 4.5%, 2.4%, and 1.42%, but WRR has outperformed others regarding the end-to-end delay. Moreover, WRR represents the best scheduling algorithm regarding both peak queue size since its higher than RP, WF, and WRR by 10.13%, 9.6%, and 5.32%, in order, and average output queue length.in contrast, WRR worst more time in queuing but it is the best in preventing the packets from dropping.","PeriodicalId":270469,"journal":{"name":"2021 3rd International Congress on Human-Computer Interaction, Optimization and Robotic Applications (HORA)","volume":"88 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124559043","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：