Pub Date : 2020-11-28DOI: 10.1109/ACIT50332.2020.9300103
M. Zaiter, S. Hacini
IoT environment is one of important upshots of IT development; it offers comfort to human daily life. We are interested in our paper in the healthcare IoT field which aims to remotely monitor the patient's health state using a set of physiological IoT sensors. In IoT systems dependability is a strong constraint because the fault occurrence can have a bad consequence on human life. The fault tolerance is one of the mechanisms that can insure a dependable function of the IoT healthcare system. To do this, we improve in this paper the centralized agent based architecture [1] by proposing more robust distributed one. That is by eliminating the weakness due to the centralization of the control. This upgrading is motivated by the fact that the current improvement of the network technologies and the occurrence of new promising paradigms like edge computing and 5G [2] require different reasoning philosophy.
{"title":"A Distributed Fault Tolerance Mechanism for an IoT Healthcare system","authors":"M. Zaiter, S. Hacini","doi":"10.1109/ACIT50332.2020.9300103","DOIUrl":"https://doi.org/10.1109/ACIT50332.2020.9300103","url":null,"abstract":"IoT environment is one of important upshots of IT development; it offers comfort to human daily life. We are interested in our paper in the healthcare IoT field which aims to remotely monitor the patient's health state using a set of physiological IoT sensors. In IoT systems dependability is a strong constraint because the fault occurrence can have a bad consequence on human life. The fault tolerance is one of the mechanisms that can insure a dependable function of the IoT healthcare system. To do this, we improve in this paper the centralized agent based architecture [1] by proposing more robust distributed one. That is by eliminating the weakness due to the centralization of the control. This upgrading is motivated by the fact that the current improvement of the network technologies and the occurrence of new promising paradigms like edge computing and 5G [2] require different reasoning philosophy.","PeriodicalId":193891,"journal":{"name":"2020 21st International Arab Conference on Information Technology (ACIT)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133736286","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 : 2020-11-28DOI: 10.1109/ACIT50332.2020.9300112
Fadia Shoura, Ammar Gharaibeh, S. Alouneh
Today's networks are concerned about making the control of communication flexible and improving the existing management systems in such a manner that reduces the Capital expenditures (CAPEX) and operating expenses (OPEX), through reducing equipment costs and energy efficiency. Along with the benefits of decreasing the time to promote new services to the clients, service providers' attention has gradually moved to Network Function Virtualization (NFV), which is a potential technology decoupling network functionalities from hardware and is a promise of high performance service provision with optimizing resource utilization across various infrastructures. However, to simultaneously achieve these goals, sometimes it is necessary to instantiate a new function depending on the traffic pattern of high-bandwidth characteristics and Quality of Service (QoS) measures. Due to the limited resources at the node, other functions in the node may need to be migrated to other nodes in order to provide resources for the new functions. Existing works related to the Virtual Network Function (VNF) deployment and migration usually focus on proposing new deployment strategies and migration mechanisms. However, reducing migration cost restricted to memory, CPU, and bandwidth capacities is not considered in those studies. In this work, the problem of virtual network functions migration is formulated as an Integer Linear Program (ILP) with the objective of minimizing the migration cost while satisfying computing and network resource capacities constraints and selecting the minimum cost path from the source to the destination node. Since the ILP is NP-complete, we propose a greedy minimum migration cost (GMMC) algorithm. Simulation results show that the proposed GMMC algorithm can reduce the total migration cost by up to 61% and the number of migrations by up to 52% when compared to the state-of-the-art schemes.
{"title":"Optimization of Migration Cost for Network Function Virtualization Replacement","authors":"Fadia Shoura, Ammar Gharaibeh, S. Alouneh","doi":"10.1109/ACIT50332.2020.9300112","DOIUrl":"https://doi.org/10.1109/ACIT50332.2020.9300112","url":null,"abstract":"Today's networks are concerned about making the control of communication flexible and improving the existing management systems in such a manner that reduces the Capital expenditures (CAPEX) and operating expenses (OPEX), through reducing equipment costs and energy efficiency. Along with the benefits of decreasing the time to promote new services to the clients, service providers' attention has gradually moved to Network Function Virtualization (NFV), which is a potential technology decoupling network functionalities from hardware and is a promise of high performance service provision with optimizing resource utilization across various infrastructures. However, to simultaneously achieve these goals, sometimes it is necessary to instantiate a new function depending on the traffic pattern of high-bandwidth characteristics and Quality of Service (QoS) measures. Due to the limited resources at the node, other functions in the node may need to be migrated to other nodes in order to provide resources for the new functions. Existing works related to the Virtual Network Function (VNF) deployment and migration usually focus on proposing new deployment strategies and migration mechanisms. However, reducing migration cost restricted to memory, CPU, and bandwidth capacities is not considered in those studies. In this work, the problem of virtual network functions migration is formulated as an Integer Linear Program (ILP) with the objective of minimizing the migration cost while satisfying computing and network resource capacities constraints and selecting the minimum cost path from the source to the destination node. Since the ILP is NP-complete, we propose a greedy minimum migration cost (GMMC) algorithm. Simulation results show that the proposed GMMC algorithm can reduce the total migration cost by up to 61% and the number of migrations by up to 52% when compared to the state-of-the-art schemes.","PeriodicalId":193891,"journal":{"name":"2020 21st International Arab Conference on Information Technology (ACIT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129274016","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 : 2020-11-28DOI: 10.1109/ACIT50332.2020.9299964
A. Yahya, Y. Asiri, Ibrahim Alyami
In pharmacovigilance, the detection of adverse drug reactions is a task of utmost importance. This paper presents a data mining-based method to detect adverse drug reactions of anti-epileptic drugs from a dataset of patients' reviews collected from an online health community. The dataset is preprocessed and the unigram, bigram, and trigram are generated and then the adverse drug reactions of each anti-epileptic drug are extracted with the help of consumer health vocabulary and adverse drug reactions lexicon. Proportional reporting ratio is used to measure the association between each adverse drug reaction and antiepileptic drug. A list of ranked adverse drug reactions for each anti-epileptic drug is generated and validated against Drugs.com database. The results show the validity and utility of using patients' reviews in online health communities as a source for adverse drug reactions detection.
{"title":"Mining Patients' Reviews in Online Health Communities for Adverse Drug Reaction Detection of Antiepileptic Drugs","authors":"A. Yahya, Y. Asiri, Ibrahim Alyami","doi":"10.1109/ACIT50332.2020.9299964","DOIUrl":"https://doi.org/10.1109/ACIT50332.2020.9299964","url":null,"abstract":"In pharmacovigilance, the detection of adverse drug reactions is a task of utmost importance. This paper presents a data mining-based method to detect adverse drug reactions of anti-epileptic drugs from a dataset of patients' reviews collected from an online health community. The dataset is preprocessed and the unigram, bigram, and trigram are generated and then the adverse drug reactions of each anti-epileptic drug are extracted with the help of consumer health vocabulary and adverse drug reactions lexicon. Proportional reporting ratio is used to measure the association between each adverse drug reaction and antiepileptic drug. A list of ranked adverse drug reactions for each anti-epileptic drug is generated and validated against Drugs.com database. The results show the validity and utility of using patients' reviews in online health communities as a source for adverse drug reactions detection.","PeriodicalId":193891,"journal":{"name":"2020 21st International Arab Conference on Information Technology (ACIT)","volume":"95 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124074275","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 : 2020-11-28DOI: 10.1109/ACIT50332.2020.9300109
B. Omarov, Aidar Batyrbekov, A. Suliman, Bakhytzhan Omarov, Yerlan Sabdenbekov, S. Aknazarov
Cardiovascular diseases (CVD) are one of the main causes of death and disability in most countries of the world. As part of the fight against high morbidity, there is a clear shift in the global health paradigm towards active prevention and prevention, rather than treatment, of diseases, and a desire to reduce inpatient care in favor of outpatient treatment, home care, and self-care of patients about their own health. Most current global clinical guidelines clearly indicate the sequence of actions of the doctor to whom the patient sought help, including the obligation to evaluate objective health data, identify risk factors and based on them to determine the cardiovascular risk in a particular patient, and then take steps to reduce this risk. However, most countries do not currently have a comprehensive mass identification of risk factors and an overall assessment of the risk of developing CVD. Most heart diseases are related and are reflected by the sounds that the heart produces. Auscultation of the heart, defined as listening to the sound of the heart, was a very important method for early diagnosis of cardiac dysfunction. In this case, phonocardiogram (PCG) records heart sounds and noises that contain significant information about heart health. Analysis of the PCG signal has the potential to detect an abnormal heart condition. Traditional auscultation requires significant clinical experience and good listening skills. The advent of the electronic stethoscope paved the way for a new field of computer auscultation. This article discusses in detail the technology of an electronic stethoscope and the method of diagnosing heart rhythm disorders based on computer auscultation.
{"title":"Electronic stethoscope for detecting heart abnormalities in athletes","authors":"B. Omarov, Aidar Batyrbekov, A. Suliman, Bakhytzhan Omarov, Yerlan Sabdenbekov, S. Aknazarov","doi":"10.1109/ACIT50332.2020.9300109","DOIUrl":"https://doi.org/10.1109/ACIT50332.2020.9300109","url":null,"abstract":"Cardiovascular diseases (CVD) are one of the main causes of death and disability in most countries of the world. As part of the fight against high morbidity, there is a clear shift in the global health paradigm towards active prevention and prevention, rather than treatment, of diseases, and a desire to reduce inpatient care in favor of outpatient treatment, home care, and self-care of patients about their own health. Most current global clinical guidelines clearly indicate the sequence of actions of the doctor to whom the patient sought help, including the obligation to evaluate objective health data, identify risk factors and based on them to determine the cardiovascular risk in a particular patient, and then take steps to reduce this risk. However, most countries do not currently have a comprehensive mass identification of risk factors and an overall assessment of the risk of developing CVD. Most heart diseases are related and are reflected by the sounds that the heart produces. Auscultation of the heart, defined as listening to the sound of the heart, was a very important method for early diagnosis of cardiac dysfunction. In this case, phonocardiogram (PCG) records heart sounds and noises that contain significant information about heart health. Analysis of the PCG signal has the potential to detect an abnormal heart condition. Traditional auscultation requires significant clinical experience and good listening skills. The advent of the electronic stethoscope paved the way for a new field of computer auscultation. This article discusses in detail the technology of an electronic stethoscope and the method of diagnosing heart rhythm disorders based on computer auscultation.","PeriodicalId":193891,"journal":{"name":"2020 21st International Arab Conference on Information Technology (ACIT)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127955176","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 : 2020-11-28DOI: 10.1109/ACIT50332.2020.9300096
Salam Hamdan, Sufyan Almajali, M. Ayyash
Applying machine learning in IoT devices is a challenge due to various reasons, such as the tremendous amount of data generated from IoT, the limitation of IoT devices' resources, and the non-IID nature of IoT data. On the other hand, transferring the generated IoT data to the cloud to train machine learning models consumes a lot of Bandwidth. Applying the distributed learning aspect in IoT large-scale deployments solves such issues, by employing edge computing devices as local cloud models in each location. This solution enhances the network overhead and helps in obtaining general models. However, this comes at the expense of the accuracy of the generated models. This paper provides a comparison study between applying a conventional machine learning model with a distributed multi-task learning model and discusses the factors that affect the distributed multi-task learning model.
{"title":"Comparison study between conventional machine learning and distributed multi-task learning models","authors":"Salam Hamdan, Sufyan Almajali, M. Ayyash","doi":"10.1109/ACIT50332.2020.9300096","DOIUrl":"https://doi.org/10.1109/ACIT50332.2020.9300096","url":null,"abstract":"Applying machine learning in IoT devices is a challenge due to various reasons, such as the tremendous amount of data generated from IoT, the limitation of IoT devices' resources, and the non-IID nature of IoT data. On the other hand, transferring the generated IoT data to the cloud to train machine learning models consumes a lot of Bandwidth. Applying the distributed learning aspect in IoT large-scale deployments solves such issues, by employing edge computing devices as local cloud models in each location. This solution enhances the network overhead and helps in obtaining general models. However, this comes at the expense of the accuracy of the generated models. This paper provides a comparison study between applying a conventional machine learning model with a distributed multi-task learning model and discusses the factors that affect the distributed multi-task learning model.","PeriodicalId":193891,"journal":{"name":"2020 21st International Arab Conference on Information Technology (ACIT)","volume":"150 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132194406","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 : 2020-11-28DOI: 10.1109/ACIT50332.2020.9300117
A. Khalifeh, Khaled Aldahdouh, S. Alouneh
Long range wide area network (LoRaWAN) is a type of Low Power Wide Area (LPWA) technologies, which is designed to support long-range communication with low data rates and low power consumption requirements. LoRaWAN consists of many nodes that sense the environment and send their measurements to the gateway, which in turn directs the received data to the network server to process the collected data. Each one of these nodes is configured using five transmission parameters, (the spreading factor (SF), center frequency (CF), bandwidth (BW), coding rate (CR), and transmission power (TP). The optimal selection of the values plays a vital role in providing an efficient and energy preserving network implementation. In this paper, an algorithm that selects the optimal transmission power for each node in the network depending on the receiver sensitivity and the path loss of the communication link between the node and the gateway is developed by utilizing the Reinforcement Learning algorithm that is used to choose the best value of spreading factor. The simulation results of our proposed algorithm showed a significant decrease in the consumed power in the network compared with the other techniques in literature.
LoRaWAN (Long range wide area network)是一种低功耗广域网(LPWA)技术，旨在支持低数据速率和低功耗要求的远程通信。LoRaWAN由许多节点组成，这些节点感知环境并将其测量结果发送到网关，网关反过来将接收到的数据定向到网络服务器以处理收集到的数据。每个节点使用5个传输参数进行配置，分别是扩频因子(SF)、中心频率(CF)、带宽(BW)、编码速率(CR)和传输功率(TP)。这些值的最优选择对于提供高效节能的网络实现起着至关重要的作用。本文利用选择传播因子最优值的强化学习算法，根据接收方灵敏度和节点与网关之间通信链路的路径损耗，开发了一种选择网络中各节点最优传输功率的算法。仿真结果表明，与文献中的其他技术相比，我们提出的算法在网络中消耗的功率显著降低。
{"title":"Optimizing the Energy Consumption Level in LoRaWan Networks","authors":"A. Khalifeh, Khaled Aldahdouh, S. Alouneh","doi":"10.1109/ACIT50332.2020.9300117","DOIUrl":"https://doi.org/10.1109/ACIT50332.2020.9300117","url":null,"abstract":"Long range wide area network (LoRaWAN) is a type of Low Power Wide Area (LPWA) technologies, which is designed to support long-range communication with low data rates and low power consumption requirements. LoRaWAN consists of many nodes that sense the environment and send their measurements to the gateway, which in turn directs the received data to the network server to process the collected data. Each one of these nodes is configured using five transmission parameters, (the spreading factor (SF), center frequency (CF), bandwidth (BW), coding rate (CR), and transmission power (TP). The optimal selection of the values plays a vital role in providing an efficient and energy preserving network implementation. In this paper, an algorithm that selects the optimal transmission power for each node in the network depending on the receiver sensitivity and the path loss of the communication link between the node and the gateway is developed by utilizing the Reinforcement Learning algorithm that is used to choose the best value of spreading factor. The simulation results of our proposed algorithm showed a significant decrease in the consumed power in the network compared with the other techniques in literature.","PeriodicalId":193891,"journal":{"name":"2020 21st International Arab Conference on Information Technology (ACIT)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131534420","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 : 2020-11-28DOI: 10.1109/ACIT50332.2020.9300070
Lara Saleh, Waleed al-sitt
Fault tolerance is a major concern in clouds in order to guarantee the reliability and the availability, also the data backup and recovery is one of the most important issue in cloud computing environments, and the need of efficient techniques for the data recovery are increasing by the days. When the server can't provide the data for the users or the data has been lost because of one of the different kinds of failures the data recovery techniques used to retrieve the data from the backup server. This paper illustrated the cloud computing failures, recovery approaches and management tools.
{"title":"Cloud Computing Failures, Recovery Approaches and Management Tools","authors":"Lara Saleh, Waleed al-sitt","doi":"10.1109/ACIT50332.2020.9300070","DOIUrl":"https://doi.org/10.1109/ACIT50332.2020.9300070","url":null,"abstract":"Fault tolerance is a major concern in clouds in order to guarantee the reliability and the availability, also the data backup and recovery is one of the most important issue in cloud computing environments, and the need of efficient techniques for the data recovery are increasing by the days. When the server can't provide the data for the users or the data has been lost because of one of the different kinds of failures the data recovery techniques used to retrieve the data from the backup server. This paper illustrated the cloud computing failures, recovery approaches and management tools.","PeriodicalId":193891,"journal":{"name":"2020 21st International Arab Conference on Information Technology (ACIT)","volume":"9 10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134565259","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 : 2020-11-28DOI: 10.1109/ACIT50332.2020.9300083
P. Maya, C. Tharini
The modern world requires intelligent vehicle systems. The lane detection is one of the key process steps in intelligent vehicle systems. This paper proposes a new optimized approach to lane detection using partial Hough transform with image enhancement techniques. A proposed partial Hough parameter space is used for detecting lanes and the approach is verified with different image sets. This method of detection follows fixing region of interest, gray scale conversion of the image, edge detection and lane detection using proposed partial Hough transform. The results of lane detection is compared to the standard Hough transform approach and the improvements are discussed.
{"title":"Performance Analysis of Lane Detection Algorithm using Partial Hough Transform","authors":"P. Maya, C. Tharini","doi":"10.1109/ACIT50332.2020.9300083","DOIUrl":"https://doi.org/10.1109/ACIT50332.2020.9300083","url":null,"abstract":"The modern world requires intelligent vehicle systems. The lane detection is one of the key process steps in intelligent vehicle systems. This paper proposes a new optimized approach to lane detection using partial Hough transform with image enhancement techniques. A proposed partial Hough parameter space is used for detecting lanes and the approach is verified with different image sets. This method of detection follows fixing region of interest, gray scale conversion of the image, edge detection and lane detection using proposed partial Hough transform. The results of lane detection is compared to the standard Hough transform approach and the improvements are discussed.","PeriodicalId":193891,"journal":{"name":"2020 21st International Arab Conference on Information Technology (ACIT)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123836374","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 : 2020-11-28DOI: 10.1109/ACIT50332.2020.9300059
Tahani Alshareef, M. Siddiqui
A Conversational Agent (CA), or dialogue system, is a computer system that has the ability to respond to humans automatically using natural language. CAs offer instant responses and can concurrently assist a potentially unlimited number of users. The modeling of CAs in Arabic has so far received less attention when compared with other languages due to the complexity of the Arabic language, the existence of several dialects, and a lack of data resources. The literature contends that modeling a CA in Arabic mostly done using pattern-matching and information retrieval, employing classification approaches with a closed-domain data source. There is extremely limited research so far on modeling an open-domain CA in the Arabic dialect. This research has utilized a deep-learning architecture, known as the Seq2Seq neural network, to build a CA in the Arabic Gulf dialect. We formulated the CA problem as a machine translation problem and, therefore, built our corpus from tweets, in the post-reply format, to train and evaluate the model. We investigated the effects of pretrained embeddings on the performance of the CA. For our evaluation, a Bilingual Evaluation Understudy (BLEU) score and human evaluators were used. The performance of the model was found to be comparable with existing deep learning models that have been trained on much larger corpora and in other languages. Our results present a promising first step towards building an open-domain CA in the Gulf Arabic dialect.
{"title":"A seq2seq Neural Network based Conversational Agent for Gulf Arabic Dialect","authors":"Tahani Alshareef, M. Siddiqui","doi":"10.1109/ACIT50332.2020.9300059","DOIUrl":"https://doi.org/10.1109/ACIT50332.2020.9300059","url":null,"abstract":"A Conversational Agent (CA), or dialogue system, is a computer system that has the ability to respond to humans automatically using natural language. CAs offer instant responses and can concurrently assist a potentially unlimited number of users. The modeling of CAs in Arabic has so far received less attention when compared with other languages due to the complexity of the Arabic language, the existence of several dialects, and a lack of data resources. The literature contends that modeling a CA in Arabic mostly done using pattern-matching and information retrieval, employing classification approaches with a closed-domain data source. There is extremely limited research so far on modeling an open-domain CA in the Arabic dialect. This research has utilized a deep-learning architecture, known as the Seq2Seq neural network, to build a CA in the Arabic Gulf dialect. We formulated the CA problem as a machine translation problem and, therefore, built our corpus from tweets, in the post-reply format, to train and evaluate the model. We investigated the effects of pretrained embeddings on the performance of the CA. For our evaluation, a Bilingual Evaluation Understudy (BLEU) score and human evaluators were used. The performance of the model was found to be comparable with existing deep learning models that have been trained on much larger corpora and in other languages. Our results present a promising first step towards building an open-domain CA in the Gulf Arabic dialect.","PeriodicalId":193891,"journal":{"name":"2020 21st International Arab Conference on Information Technology (ACIT)","volume":"101 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114490422","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 : 2020-11-28DOI: 10.1109/ACIT50332.2020.9300049
Maha Rahrouh, Mamdouh Ghanem
This research attempts to study students' satisfaction with online statistics courses. Student satisfaction is verified in terms of the following dimensions of the students' e-learning process. Flexibility of time and virtual attendance location, ease of understanding, effective communication between students and teachers, and effective communication among students themselves. The research also examines the relationship between student's level of satisfaction and demographics (such as age, employment, and gender) and previous online educational experience.
{"title":"An analytical study of student satisfaction with the Statistics courses in e-learning as a new experience after Covid-19 at Al Ain University","authors":"Maha Rahrouh, Mamdouh Ghanem","doi":"10.1109/ACIT50332.2020.9300049","DOIUrl":"https://doi.org/10.1109/ACIT50332.2020.9300049","url":null,"abstract":"This research attempts to study students' satisfaction with online statistics courses. Student satisfaction is verified in terms of the following dimensions of the students' e-learning process. Flexibility of time and virtual attendance location, ease of understanding, effective communication between students and teachers, and effective communication among students themselves. The research also examines the relationship between student's level of satisfaction and demographics (such as age, employment, and gender) and previous online educational experience.","PeriodicalId":193891,"journal":{"name":"2020 21st International Arab Conference on Information Technology (ACIT)","volume":"245 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120932582","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：