E-learning is globalized in a short period of time due to the physical distancing requirement for curbing the spread of COVID-19. There are two major challenges imposed by the migration from face-to-face learning to E-learning: live lecturing and lab sessions. In this survey, we studied the E-learning platforms used in the COVID-19 pandemic: learning management systems or course management systems, tools for live-lecturing and tools for lab sessions. We found that this migration is quite smooth with contemporary technologies and the Internet. Prescriptive suggestions are also provided for this migration. For the future trend of education, it is expected that E-learning will become a preferable education and learning style in the future, especially for self-study and life-long learning.
{"title":"A Survey on the E-learning platforms used during COVID-19","authors":"Xianping Wang, Weiru Chen, Hao Qiu, Awad M. Eldurssi, Fei Xie, Jiayue Shen","doi":"10.1109/IEMCON51383.2020.9284840","DOIUrl":"https://doi.org/10.1109/IEMCON51383.2020.9284840","url":null,"abstract":"E-learning is globalized in a short period of time due to the physical distancing requirement for curbing the spread of COVID-19. There are two major challenges imposed by the migration from face-to-face learning to E-learning: live lecturing and lab sessions. In this survey, we studied the E-learning platforms used in the COVID-19 pandemic: learning management systems or course management systems, tools for live-lecturing and tools for lab sessions. We found that this migration is quite smooth with contemporary technologies and the Internet. Prescriptive suggestions are also provided for this migration. For the future trend of education, it is expected that E-learning will become a preferable education and learning style in the future, especially for self-study and life-long learning.","PeriodicalId":6871,"journal":{"name":"2020 11th IEEE Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"75 1","pages":"0808-0814"},"PeriodicalIF":0.0,"publicationDate":"2020-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83223713","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 : 2020-11-04DOI: 10.1109/IEMCON51383.2020.9284917
Aierken Shalayiding, Z. Arnavut, B. Koc, H. Kocak
Medical imaging is a very useful component in diagnosing diseases. For future use, and further study and analysis, hospitals must keep all patients' medical images in databases. In this work, a new lossless image compression technique is proposed for efficient storage and transmission of medical images. The newly proposed technique is based on encoding prediction errors with a suitable entropy coder upon transforming them with the Burrows-Wheeler Transformation (BWT). We show that the newly proposed technique yields better compression than the mainstream lossless compression algorithms JPEG-2000 and JPEG-LS.
{"title":"Burrows-Wheeler Transformation for Medical Image Compression","authors":"Aierken Shalayiding, Z. Arnavut, B. Koc, H. Kocak","doi":"10.1109/IEMCON51383.2020.9284917","DOIUrl":"https://doi.org/10.1109/IEMCON51383.2020.9284917","url":null,"abstract":"Medical imaging is a very useful component in diagnosing diseases. For future use, and further study and analysis, hospitals must keep all patients' medical images in databases. In this work, a new lossless image compression technique is proposed for efficient storage and transmission of medical images. The newly proposed technique is based on encoding prediction errors with a suitable entropy coder upon transforming them with the Burrows-Wheeler Transformation (BWT). We show that the newly proposed technique yields better compression than the mainstream lossless compression algorithms JPEG-2000 and JPEG-LS.","PeriodicalId":6871,"journal":{"name":"2020 11th IEEE Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"16 1","pages":"0723-0727"},"PeriodicalIF":0.0,"publicationDate":"2020-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91547363","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 : 2020-11-04DOI: 10.1109/IEMCON51383.2020.9284940
A. Fernando, M.D.C Muthuarachchi, D. Anandakumar, W.N.R.B Chamalka, M. Gamage, N.C Amarasena
Motorcycles are an important part of daily transportation. They are specially used to avoid traffic congestions downtown and most of the individuals tend to use a motorcycle because it takes less time to get to the destination. The rapid increase of motorcycle usage has led to a significant increase in the number of motorcycle-related accidents and fatalities. The reasons for accidents which were considered are speeding, collision with objects, lack of focus or drowsiness where only the rider's head is protected but not the body. And accidents may lead to death when help is not called immediately. By considering these, author introduces a Motorcyclists Safety Assistant Application (MSAA). This research tries to address four major factors that caused most road accidents and fatalities in Sri Lanka. They are excess speed, 360-degree threat detection, motorcyclist safety balloons, and emergency alert system. Here, MSAA can detect the vehicle's real-time speed and inform the user when a certain speed limit has been exceeded. Also, it has proposed a system which automatically detects threats that occur in each collision and alerts the rider via visual and audio cues. Moreover, the next system will be focusing on safeguarding the rider's body by inflating an airbag which will be connected to the rider's jacket. An automatic alert system is also introduced where the main objective is to mitigate the consequences of accidents by sending a message to the registered mobile using wireless communication techniques and checks whether an accident has occurred using vibration frequency limits. Location will be sent through the tracking system to cover the geographical coordinates over the area. The proposed domain successfully contributes to a drastic reduction in road accidents. The ultimate objective is to create a better future for everybody through road safety. The survey conducted to test the user satisfactory level, demonstrated high user satisfaction.
{"title":"Motorcyclists Safety Assistant App","authors":"A. Fernando, M.D.C Muthuarachchi, D. Anandakumar, W.N.R.B Chamalka, M. Gamage, N.C Amarasena","doi":"10.1109/IEMCON51383.2020.9284940","DOIUrl":"https://doi.org/10.1109/IEMCON51383.2020.9284940","url":null,"abstract":"Motorcycles are an important part of daily transportation. They are specially used to avoid traffic congestions downtown and most of the individuals tend to use a motorcycle because it takes less time to get to the destination. The rapid increase of motorcycle usage has led to a significant increase in the number of motorcycle-related accidents and fatalities. The reasons for accidents which were considered are speeding, collision with objects, lack of focus or drowsiness where only the rider's head is protected but not the body. And accidents may lead to death when help is not called immediately. By considering these, author introduces a Motorcyclists Safety Assistant Application (MSAA). This research tries to address four major factors that caused most road accidents and fatalities in Sri Lanka. They are excess speed, 360-degree threat detection, motorcyclist safety balloons, and emergency alert system. Here, MSAA can detect the vehicle's real-time speed and inform the user when a certain speed limit has been exceeded. Also, it has proposed a system which automatically detects threats that occur in each collision and alerts the rider via visual and audio cues. Moreover, the next system will be focusing on safeguarding the rider's body by inflating an airbag which will be connected to the rider's jacket. An automatic alert system is also introduced where the main objective is to mitigate the consequences of accidents by sending a message to the registered mobile using wireless communication techniques and checks whether an accident has occurred using vibration frequency limits. Location will be sent through the tracking system to cover the geographical coordinates over the area. The proposed domain successfully contributes to a drastic reduction in road accidents. The ultimate objective is to create a better future for everybody through road safety. The survey conducted to test the user satisfactory level, demonstrated high user satisfaction.","PeriodicalId":6871,"journal":{"name":"2020 11th IEEE Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"122 1","pages":"0414-0419"},"PeriodicalIF":0.0,"publicationDate":"2020-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85263812","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 : 2020-11-04DOI: 10.1109/IEMCON51383.2020.9284903
Songchenchen Gong, E. Bourennane, Xuecan Yang
The crowd counting task involves the issue of security, so now more and more people are concerned about it. At present, the most difficult problem of population counting consists in: how to make the model distinguish human head features more finely in the densely populated area, such as head overlap and how to find a small-scale local head feature in an image with a wide range of population density. Facing these challenges, we propose a network for multiple feature convolutional neural network, which is called MFNet. It aims to get high-quality density maps in the high-density crowd scene, and at the same time to perform the task of the count and estimation of the crowd. In terms of crowd counting, we use multiple sources of information, that is HOG, LBP and CANNY. With the support vector machine (SVM), each source provides us not merely a separate count estimation, but other statistical measures. In order to effectively solve the problem of extracting scale-related features in crowd counting, we have integrated MFNet, a convolutional neural network architecture. By comparing the experimental results of multiple data sets, MFNet is superior to other population counting methods.
{"title":"MFNet: Multi-feature convolutional neural network for high-density crowd counting","authors":"Songchenchen Gong, E. Bourennane, Xuecan Yang","doi":"10.1109/IEMCON51383.2020.9284903","DOIUrl":"https://doi.org/10.1109/IEMCON51383.2020.9284903","url":null,"abstract":"The crowd counting task involves the issue of security, so now more and more people are concerned about it. At present, the most difficult problem of population counting consists in: how to make the model distinguish human head features more finely in the densely populated area, such as head overlap and how to find a small-scale local head feature in an image with a wide range of population density. Facing these challenges, we propose a network for multiple feature convolutional neural network, which is called MFNet. It aims to get high-quality density maps in the high-density crowd scene, and at the same time to perform the task of the count and estimation of the crowd. In terms of crowd counting, we use multiple sources of information, that is HOG, LBP and CANNY. With the support vector machine (SVM), each source provides us not merely a separate count estimation, but other statistical measures. In order to effectively solve the problem of extracting scale-related features in crowd counting, we have integrated MFNet, a convolutional neural network architecture. By comparing the experimental results of multiple data sets, MFNet is superior to other population counting methods.","PeriodicalId":6871,"journal":{"name":"2020 11th IEEE Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"63 1","pages":"0384-0390"},"PeriodicalIF":0.0,"publicationDate":"2020-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84496047","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 : 2020-11-04DOI: 10.1109/IEMCON51383.2020.9284901
Pasquale A. T. Zingo, A. Novocin
Recent attempts to introduce the Generative Adversarial Network (GAN) to the computer network traffic domain have shown promise, including several frameworks which generate realistic traffic. This paper presents the ‘GAN vs Real (GvR) score’, a task-based metric which quantifies how well a traffic GAN generator informs a classifier compared to the original data. This metric is derived from the ‘Train-on-Synthetic, Test-on-Real’ (TSTR) method, with the added step of comparing the TSTR accuracy to the performance of the same classifier trained on real data and tested on real data. We use this framework to evaluate the B-WGAN-GP model for generating NetFlow traffic records using several stock classifiers. Using GvR we conclude that it is possible to train accurate traffic anomaly detectors with GAN-generated network traffic data.
最近将生成对抗网络(GAN)引入计算机网络流量领域的尝试显示出了希望，包括几个生成现实流量的框架。本文提出了“GAN vs Real (GvR)分数”，这是一种基于任务的度量，用于量化与原始数据相比，交通GAN生成器通知分类器的程度。这个度量来源于“合成训练，真实测试”(TSTR)方法，增加了将TSTR精度与在真实数据上训练和测试的同一分类器的性能进行比较的步骤。我们使用该框架来评估B-WGAN-GP模型，该模型使用几个存量分类器生成NetFlow流量记录。使用GvR，我们得出结论，可以用gan生成的网络流量数据训练准确的流量异常检测器。
{"title":"Can GAN-Generated Network Traffic be used to Train Traffic Anomaly Classifiers?","authors":"Pasquale A. T. Zingo, A. Novocin","doi":"10.1109/IEMCON51383.2020.9284901","DOIUrl":"https://doi.org/10.1109/IEMCON51383.2020.9284901","url":null,"abstract":"Recent attempts to introduce the Generative Adversarial Network (GAN) to the computer network traffic domain have shown promise, including several frameworks which generate realistic traffic. This paper presents the ‘GAN vs Real (GvR) score’, a task-based metric which quantifies how well a traffic GAN generator informs a classifier compared to the original data. This metric is derived from the ‘Train-on-Synthetic, Test-on-Real’ (TSTR) method, with the added step of comparing the TSTR accuracy to the performance of the same classifier trained on real data and tested on real data. We use this framework to evaluate the B-WGAN-GP model for generating NetFlow traffic records using several stock classifiers. Using GvR we conclude that it is possible to train accurate traffic anomaly detectors with GAN-generated network traffic data.","PeriodicalId":6871,"journal":{"name":"2020 11th IEEE Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"56 1","pages":"0540-0545"},"PeriodicalIF":0.0,"publicationDate":"2020-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89344153","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 : 2020-11-04DOI: 10.1109/IEMCON51383.2020.9284906
Nada A. Ezz-Eldien, Mohamed F. Abdelkader, M. Abdalla, H. Abdel-Atty
Moving to the next generations of mobile networks means to deal with multi-heterogeneous network dense deployment as there will be no single network type capable of meeting all the rapid changes in customer demand optimally. A major problem is how to efficiently select the network to be handed over by the mobile user to continually maintain the user service with a better degree of satisfaction. It is a complicated task to solve this problem as the selection of an access network in such an environment relies on several factors with various relative impacts, such as the network parameters, the user preferences and the service cost. The network selection process compromises between the number of considered factors and the complexity of the process itself as each network has its own properties, different from other networks, which make a specific network the best solution corresponding to specific mobile user depending on the considered factors when taking the decision. In order to perform the network selection process on a correct base and guarantee the selection of the most suited network achieving satisfaction for the users along with acceptable network performance, this paper proposed an improved vertical handover algorithm (I-VHO) considering various factors combined together in the same scenario including user speed and signal strength with other network parameters for different services while keeping the load distribution for all candidate networks fair enough to maintain the performance as efficient as possible. The proposed handover algorithm is suitable and applicable for a general case of the heterogeneous network consists of different candidate networks and also effective to users differ on moving speed and type of application. A comparative simulation for the proposed algorithm and the previous works is included. The numerical simulation results and discussions are presented to show the effectiveness of the proposed algorithm.
{"title":"Handover Performance Improvement in Heterogeneous Wireless Network","authors":"Nada A. Ezz-Eldien, Mohamed F. Abdelkader, M. Abdalla, H. Abdel-Atty","doi":"10.1109/IEMCON51383.2020.9284906","DOIUrl":"https://doi.org/10.1109/IEMCON51383.2020.9284906","url":null,"abstract":"Moving to the next generations of mobile networks means to deal with multi-heterogeneous network dense deployment as there will be no single network type capable of meeting all the rapid changes in customer demand optimally. A major problem is how to efficiently select the network to be handed over by the mobile user to continually maintain the user service with a better degree of satisfaction. It is a complicated task to solve this problem as the selection of an access network in such an environment relies on several factors with various relative impacts, such as the network parameters, the user preferences and the service cost. The network selection process compromises between the number of considered factors and the complexity of the process itself as each network has its own properties, different from other networks, which make a specific network the best solution corresponding to specific mobile user depending on the considered factors when taking the decision. In order to perform the network selection process on a correct base and guarantee the selection of the most suited network achieving satisfaction for the users along with acceptable network performance, this paper proposed an improved vertical handover algorithm (I-VHO) considering various factors combined together in the same scenario including user speed and signal strength with other network parameters for different services while keeping the load distribution for all candidate networks fair enough to maintain the performance as efficient as possible. The proposed handover algorithm is suitable and applicable for a general case of the heterogeneous network consists of different candidate networks and also effective to users differ on moving speed and type of application. A comparative simulation for the proposed algorithm and the previous works is included. The numerical simulation results and discussions are presented to show the effectiveness of the proposed algorithm.","PeriodicalId":6871,"journal":{"name":"2020 11th IEEE Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"30 1","pages":"0821-0830"},"PeriodicalIF":0.0,"publicationDate":"2020-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88110649","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 : 2020-11-04DOI: 10.1109/IEMCON51383.2020.9284920
A. Gordon, Gustavo Salazar-Chacón
The present study describes the current relevance of designing a Disaster Recovery Plan (DRP) for modern businesses, even more for those which have a Data Center (DC) inside their infrastructures. The main purpose of any DRP is to achieve the continuity of the most important services for the enterprise, this being more important in times of COVID-19 pandemic due to the extreme technological dependence required. DRPs try to minimize the risks that may cause any affectation on a critical service. Based on field studies, a risk analysis is executed according to ISO27001 standard and a risk treatment matrix is done to reduce the emergence probability, having identified the power back-up failure as the main risk in the analyzed DC. A private cloud-based recovery design is also proposed in the event of a possible impact due to power and back-up procedure failures. According to the final analysis and execution of the DRP, it is concluded that the recovery of service is performed in an adequate time to preserve the critical business services running, despite electrical failures.
{"title":"DRP Analysis: Service Outage in Data Center due to Power Failures","authors":"A. Gordon, Gustavo Salazar-Chacón","doi":"10.1109/IEMCON51383.2020.9284920","DOIUrl":"https://doi.org/10.1109/IEMCON51383.2020.9284920","url":null,"abstract":"The present study describes the current relevance of designing a Disaster Recovery Plan (DRP) for modern businesses, even more for those which have a Data Center (DC) inside their infrastructures. The main purpose of any DRP is to achieve the continuity of the most important services for the enterprise, this being more important in times of COVID-19 pandemic due to the extreme technological dependence required. DRPs try to minimize the risks that may cause any affectation on a critical service. Based on field studies, a risk analysis is executed according to ISO27001 standard and a risk treatment matrix is done to reduce the emergence probability, having identified the power back-up failure as the main risk in the analyzed DC. A private cloud-based recovery design is also proposed in the event of a possible impact due to power and back-up procedure failures. According to the final analysis and execution of the DRP, it is concluded that the recovery of service is performed in an adequate time to preserve the critical business services running, despite electrical failures.","PeriodicalId":6871,"journal":{"name":"2020 11th IEEE Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"138 1","pages":"0182-0187"},"PeriodicalIF":0.0,"publicationDate":"2020-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86270574","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 : 2020-11-04DOI: 10.1109/IEMCON51383.2020.9284821
Amean Al-Safi, A. Al-Khayyat, Alyaa Muhsen Manati, Liqaa Alhafadhi
The use of Field Programmable Gate Arrays (FPGAs) for implementing different types of Pulse Width Modulation (PWM) controllers has increased steadily in the last few years. They become dominant tools for implementing different types of PWM due to the flexibility they provide compared to other Digital Signal Processors (DSPs). Different PWMs have been implemented for single and three phase circuits such as Digital PWM (DPWM), Sinusoidal PWM (SPWM), Space Vector (SVPWM), carrier phase shifted SPWM (CPS-SPWM), Third Harmonic Injection Sinusoidal Pulse Width Modulation (THISPWM) using FPGA boards. This paper presents a systematic review for the implemented PWM controllers based on FPGA. It describes in detail their types, architectures, and intended applications they used for. It also addresses the main contributions, advantages, and disadvantages of different research paper in this area. Current limitations and future development have been drawn based on highlighting the implemented and unimplemented PWM based on FPGA.
{"title":"Advances in FPGA Based PWM Generation for Power Electronics Applications: Literature Review","authors":"Amean Al-Safi, A. Al-Khayyat, Alyaa Muhsen Manati, Liqaa Alhafadhi","doi":"10.1109/IEMCON51383.2020.9284821","DOIUrl":"https://doi.org/10.1109/IEMCON51383.2020.9284821","url":null,"abstract":"The use of Field Programmable Gate Arrays (FPGAs) for implementing different types of Pulse Width Modulation (PWM) controllers has increased steadily in the last few years. They become dominant tools for implementing different types of PWM due to the flexibility they provide compared to other Digital Signal Processors (DSPs). Different PWMs have been implemented for single and three phase circuits such as Digital PWM (DPWM), Sinusoidal PWM (SPWM), Space Vector (SVPWM), carrier phase shifted SPWM (CPS-SPWM), Third Harmonic Injection Sinusoidal Pulse Width Modulation (THISPWM) using FPGA boards. This paper presents a systematic review for the implemented PWM controllers based on FPGA. It describes in detail their types, architectures, and intended applications they used for. It also addresses the main contributions, advantages, and disadvantages of different research paper in this area. Current limitations and future development have been drawn based on highlighting the implemented and unimplemented PWM based on FPGA.","PeriodicalId":6871,"journal":{"name":"2020 11th IEEE Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"56 1 1","pages":"0252-0259"},"PeriodicalIF":0.0,"publicationDate":"2020-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77395965","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 : 2020-11-04DOI: 10.1109/IEMCON51383.2020.9284929
Y. Kotb, Mouhammad Alakkoummi, H. Kanj
Smart autonomous systems are system that take decisions independently and on run time without the need for human interaction. One of the most important components that plays a big roll in system autonomy is fault tolerance and avoidance which is a basic capability that autonomous systems should have in order to be able to survive surrounding environment state change without the need for supervision. In this paper, a framework is proposed where fault tolerance and avoidance is achieved through a reinforcement learning based framework. The framework adapts to changes and learns new processes for fault tolerance and avoidance whenever environment states change. The framework has a set of predefined actions and an observable environment. Reinforcement learning is being applied in order to learn the sequence of actions that needs to be taken to avoid or tolerate failure. The outcome of the learning process is a sequence of actions to help the system reach a desired state while avoiding fault states. These are used for later execution when the same situation occurs when the agent is in similar environment state while having the similar readings. Two Theorems and a Lemma are proposed to define the validity and correctness of the framework. The proposed framework is then simulated and tested.
{"title":"Reinforcement Learning Based Framework for Real Time Fault Tolerance","authors":"Y. Kotb, Mouhammad Alakkoummi, H. Kanj","doi":"10.1109/IEMCON51383.2020.9284929","DOIUrl":"https://doi.org/10.1109/IEMCON51383.2020.9284929","url":null,"abstract":"Smart autonomous systems are system that take decisions independently and on run time without the need for human interaction. One of the most important components that plays a big roll in system autonomy is fault tolerance and avoidance which is a basic capability that autonomous systems should have in order to be able to survive surrounding environment state change without the need for supervision. In this paper, a framework is proposed where fault tolerance and avoidance is achieved through a reinforcement learning based framework. The framework adapts to changes and learns new processes for fault tolerance and avoidance whenever environment states change. The framework has a set of predefined actions and an observable environment. Reinforcement learning is being applied in order to learn the sequence of actions that needs to be taken to avoid or tolerate failure. The outcome of the learning process is a sequence of actions to help the system reach a desired state while avoiding fault states. These are used for later execution when the same situation occurs when the agent is in similar environment state while having the similar readings. Two Theorems and a Lemma are proposed to define the validity and correctness of the framework. The proposed framework is then simulated and tested.","PeriodicalId":6871,"journal":{"name":"2020 11th IEEE Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"20 1","pages":"0357-0364"},"PeriodicalIF":0.0,"publicationDate":"2020-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82561334","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 : 2020-11-04DOI: 10.1109/IEMCON51383.2020.9284858
Swapna Gottipati, Kyong Jin Shim, Angeline Weiling Jiang, Andre Justin Sheng Wei Lee
Our study presents a comprehensive analysis of news articles from FlightGlobal website during the first half of 2020. Our analyses reveal useful insights on themes and trends concerning the aviation industry during the COVID-19 period. We applied text mining and NLP techniques to analyse the articles for extracting the aviation themes and article sentiments (positive and negative). Our results show that there is a variation in the sentiment trends for themes aligned with the real-world developments of the pandemic. The article sentiment analysis can offer industry players a quick sense of the nature of developments in the industry. Our article theme analysis adds further value by summarizing the common key topics within the positive and negative corpora, allowing stakeholders in the aviation industry to gain more insights on areas of concerns or aspects that are affected by the pandemic.
{"title":"Exploring the Impact of COVID-19 on Aviation Industry: A Text Mining Approach","authors":"Swapna Gottipati, Kyong Jin Shim, Angeline Weiling Jiang, Andre Justin Sheng Wei Lee","doi":"10.1109/IEMCON51383.2020.9284858","DOIUrl":"https://doi.org/10.1109/IEMCON51383.2020.9284858","url":null,"abstract":"Our study presents a comprehensive analysis of news articles from FlightGlobal website during the first half of 2020. Our analyses reveal useful insights on themes and trends concerning the aviation industry during the COVID-19 period. We applied text mining and NLP techniques to analyse the articles for extracting the aviation themes and article sentiments (positive and negative). Our results show that there is a variation in the sentiment trends for themes aligned with the real-world developments of the pandemic. The article sentiment analysis can offer industry players a quick sense of the nature of developments in the industry. Our article theme analysis adds further value by summarizing the common key topics within the positive and negative corpora, allowing stakeholders in the aviation industry to gain more insights on areas of concerns or aspects that are affected by the pandemic.","PeriodicalId":6871,"journal":{"name":"2020 11th IEEE Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"85 1","pages":"0208-0215"},"PeriodicalIF":0.0,"publicationDate":"2020-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76182958","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：