Pub Date : 2021-05-24DOI: 10.1109/ICICS52457.2021.9464544
Ahmed Qarqaz, Malak Abdullah
This paper describes the winning system for the Mowjaz Multi-Topic Labelling Task. The goal of the task is to classify articles based on their topics and predict multiple topics in one article. The proposed system is an ensemble model that consists of six BERT-Based models trained on different versions of the dataset. It achieved an F1-Micro score of 0.886 and an Accuracy score of 0.843 on the validation data. It also achieved an F1-Micro score of 0.8595 on the Test data, which led to ranking the model 1st in the Mowjaz Multi-Topic Labelling leaderboard. The current research work discusses the pre-trained language models used for the experimentation that led to the proposed system and shows the models’ performances on the Arabic Articles dataset.
{"title":"Team R00 at Mowjaz Multi-Topic Labelling Task for Arabic Articles","authors":"Ahmed Qarqaz, Malak Abdullah","doi":"10.1109/ICICS52457.2021.9464544","DOIUrl":"https://doi.org/10.1109/ICICS52457.2021.9464544","url":null,"abstract":"This paper describes the winning system for the Mowjaz Multi-Topic Labelling Task. The goal of the task is to classify articles based on their topics and predict multiple topics in one article. The proposed system is an ensemble model that consists of six BERT-Based models trained on different versions of the dataset. It achieved an F1-Micro score of 0.886 and an Accuracy score of 0.843 on the validation data. It also achieved an F1-Micro score of 0.8595 on the Test data, which led to ranking the model 1st in the Mowjaz Multi-Topic Labelling leaderboard. The current research work discusses the pre-trained language models used for the experimentation that led to the proposed system and shows the models’ performances on the Arabic Articles dataset.","PeriodicalId":421803,"journal":{"name":"2021 12th International Conference on Information and Communication Systems (ICICS)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116192989","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 : 2021-05-24DOI: 10.1109/ICICS52457.2021.9464557
Yousef Shaheen, Aseel Mohammad Elian, R. Ibrahim, Muawya Al Dalain
Mobile application usage has been exceptionally increased during the past few years in many different fields such as education and finance, our research paper was proposed to identify and analyze the factors that affect adopting and using mobile banking application in Jordan based on TAM model. Mobile banking is a new technology that launched to the market in 2001 [1] to allow users to do their transaction without going to the bank. A quantitative research method was used with a size of 269 respondents. The data was collected using survey questionnaire and analyzed using IBM SPSS statistics tool. The study proved that the significant positive relationship between the selected independent factors including quality, benefit, innovation and risk with the dependent ones such as perceived ease of use and perceived usefulness. In addition, it was found that the innovation factor has no effect on mobile banking application acceptance as well as the quality of mobile banking application factor had the most significant effect on mobile banking application acceptance.
{"title":"Clients Acceptance towards Mobile Banking Application in Jordan Based on TAM Model","authors":"Yousef Shaheen, Aseel Mohammad Elian, R. Ibrahim, Muawya Al Dalain","doi":"10.1109/ICICS52457.2021.9464557","DOIUrl":"https://doi.org/10.1109/ICICS52457.2021.9464557","url":null,"abstract":"Mobile application usage has been exceptionally increased during the past few years in many different fields such as education and finance, our research paper was proposed to identify and analyze the factors that affect adopting and using mobile banking application in Jordan based on TAM model. Mobile banking is a new technology that launched to the market in 2001 [1] to allow users to do their transaction without going to the bank. A quantitative research method was used with a size of 269 respondents. The data was collected using survey questionnaire and analyzed using IBM SPSS statistics tool. The study proved that the significant positive relationship between the selected independent factors including quality, benefit, innovation and risk with the dependent ones such as perceived ease of use and perceived usefulness. In addition, it was found that the innovation factor has no effect on mobile banking application acceptance as well as the quality of mobile banking application factor had the most significant effect on mobile banking application acceptance.","PeriodicalId":421803,"journal":{"name":"2021 12th International Conference on Information and Communication Systems (ICICS)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116560137","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 : 2021-05-24DOI: 10.1109/ICICS52457.2021.9464588
Lilian D. Suárez-Riveros, Jejen-Salinas Santiango, Laura M. Patarroyo-Godoy, C. Dante
This investigation establishes the relationship between demand and generation of the Colombian energy market by characterizing hourly and daily consumption patterns and later forecasting electricity energy demand at the hourly-daily level. The dataset used had variables demand and generation of electricity at hourly and daily levels, from 1 January 2019 to 30 September 2020. Ward’s method was applied with cosine similarity to establish the consumption patterns. Linear Regression, Support Vector Machine, and Random Forest were implemented to forecast consumption, and the model chosen was the one whose lowest Mean Absolute Percentage Error (MAPE) was selected. Daily energy consumption was classified into three groups and hourly energy consumption in six groups. The generation is in line with the demand, which indicates that the system is efficient. The algorithm that best forecasted hourly energy demand was linear regression, except for days with low demand peaks, such as October and December holidays.
{"title":"Typification of the demand-generation relationship of Colombian electricity market and forecast of demand at an hourly-daily level based on consumption patterns","authors":"Lilian D. Suárez-Riveros, Jejen-Salinas Santiango, Laura M. Patarroyo-Godoy, C. Dante","doi":"10.1109/ICICS52457.2021.9464588","DOIUrl":"https://doi.org/10.1109/ICICS52457.2021.9464588","url":null,"abstract":"This investigation establishes the relationship between demand and generation of the Colombian energy market by characterizing hourly and daily consumption patterns and later forecasting electricity energy demand at the hourly-daily level. The dataset used had variables demand and generation of electricity at hourly and daily levels, from 1 January 2019 to 30 September 2020. Ward’s method was applied with cosine similarity to establish the consumption patterns. Linear Regression, Support Vector Machine, and Random Forest were implemented to forecast consumption, and the model chosen was the one whose lowest Mean Absolute Percentage Error (MAPE) was selected. Daily energy consumption was classified into three groups and hourly energy consumption in six groups. The generation is in line with the demand, which indicates that the system is efficient. The algorithm that best forecasted hourly energy demand was linear regression, except for days with low demand peaks, such as October and December holidays.","PeriodicalId":421803,"journal":{"name":"2021 12th International Conference on Information and Communication Systems (ICICS)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126225864","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 : 2021-05-24DOI: 10.1109/ICICS52457.2021.9464548
Faisal Abdullah, M. Al-Ayyoub, Ismail Hmeidi, Nouh Alhindaw
In this paper, we introduce both a Multi-Label Classification (MLC) method to determine all the emotions expressed in an Arabic tweet and a Multi-Target Regression (MTR) method to determine the emotions’ intensities. MLC involves the prediction of zero or more classes per sample. It is one of the interesting research topics in Natural Language Processing (NLP), especially for the Arabic language due to scarcity of works related to it. MTR is a harder task compared to MLC, but it lends itself as a suitable representation for Emotion Analysis (EA), which is gaining more interest due to the increasing use of social media and the wide range of applications related to it. This work introduces a new study on the use of Deep Learning (DL) techniques for emotions classification and quantification in Arabic tweets.
{"title":"A Deep Learning Approach to Classify and Quantify the Multiple Emotions of Arabic Tweets","authors":"Faisal Abdullah, M. Al-Ayyoub, Ismail Hmeidi, Nouh Alhindaw","doi":"10.1109/ICICS52457.2021.9464548","DOIUrl":"https://doi.org/10.1109/ICICS52457.2021.9464548","url":null,"abstract":"In this paper, we introduce both a Multi-Label Classification (MLC) method to determine all the emotions expressed in an Arabic tweet and a Multi-Target Regression (MTR) method to determine the emotions’ intensities. MLC involves the prediction of zero or more classes per sample. It is one of the interesting research topics in Natural Language Processing (NLP), especially for the Arabic language due to scarcity of works related to it. MTR is a harder task compared to MLC, but it lends itself as a suitable representation for Emotion Analysis (EA), which is gaining more interest due to the increasing use of social media and the wide range of applications related to it. This work introduces a new study on the use of Deep Learning (DL) techniques for emotions classification and quantification in Arabic tweets.","PeriodicalId":421803,"journal":{"name":"2021 12th International Conference on Information and Communication Systems (ICICS)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132048363","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 : 2021-05-24DOI: 10.1109/ICICS52457.2021.9464598
Arwa Okaidat, Shatha Melhem, Heba Alenezi, R. Duwairi
Since there are over a billion individuals worldwide below the international poverty line of less than $2 per day; the first goal of sustainable development is to eradicate poverty. The primary step before poverty can be eradicated is to understand the spatial distribution of poverty. However, the process of going around rural areas and manually tracking census data is time-consuming, needs a lot of human effort, and is expensive. On the other hand, high-resolution satellite images, are becoming largely available at a global scale and contains an abundance of information about landscape features that could be correlated with economic activity. Deep learning with satellite images provides a scalable way to make predicting the distribution of poverty faster, easier, and less expensive, and this helps in aiding organizations to distribute funds more efficiently and allow policymakers to enact and evaluate policies more effectively. This paper focuses on Africa as it is considered the poorest continent. The data, we have used, consist of three datasets which contain satellite images for three countries in Africa with different levels of poverty: Ethiopia, Malawi, and Nigeria. In order to classify the satellite images, two pre-trained Convolutional Neural Networks models (ResNet50 and VGG16) were implemented in addition to our novel structure of CNN. The test accuracy for CNN was 76% for the three countries. VGG16 average accuracy was 79.3% and ResNet average accuracy was 49.3%.
{"title":"Using Convolutional Neural Networks on Satellite Images to Predict Poverty","authors":"Arwa Okaidat, Shatha Melhem, Heba Alenezi, R. Duwairi","doi":"10.1109/ICICS52457.2021.9464598","DOIUrl":"https://doi.org/10.1109/ICICS52457.2021.9464598","url":null,"abstract":"Since there are over a billion individuals worldwide below the international poverty line of less than $2 per day; the first goal of sustainable development is to eradicate poverty. The primary step before poverty can be eradicated is to understand the spatial distribution of poverty. However, the process of going around rural areas and manually tracking census data is time-consuming, needs a lot of human effort, and is expensive. On the other hand, high-resolution satellite images, are becoming largely available at a global scale and contains an abundance of information about landscape features that could be correlated with economic activity. Deep learning with satellite images provides a scalable way to make predicting the distribution of poverty faster, easier, and less expensive, and this helps in aiding organizations to distribute funds more efficiently and allow policymakers to enact and evaluate policies more effectively. This paper focuses on Africa as it is considered the poorest continent. The data, we have used, consist of three datasets which contain satellite images for three countries in Africa with different levels of poverty: Ethiopia, Malawi, and Nigeria. In order to classify the satellite images, two pre-trained Convolutional Neural Networks models (ResNet50 and VGG16) were implemented in addition to our novel structure of CNN. The test accuracy for CNN was 76% for the three countries. VGG16 average accuracy was 79.3% and ResNet average accuracy was 49.3%.","PeriodicalId":421803,"journal":{"name":"2021 12th International Conference on Information and Communication Systems (ICICS)","volume":"256 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134361628","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 : 2021-05-24DOI: 10.1109/ICICS52457.2021.9464570
R. Alazrai, A. Awad, B. Alsaify, M. Daoud
This paper presents a new approach for recognizing human activities that involve two humans, referred to as human-human interactions, using Wi-Fi signals. The proposed approach utilizes the Channel State Information (CSI) metric of the Wi-Fi signals to characterize the performed interactions in indoor environment. Specifically, the proposed approach analyzes the CSI data and extracts a set of time-domain and frequency-domain features that comprise salient information to distinguish between the performed interactions. The extracted features are used to construct a multi-class support vector machine classifier that can recognize the classes of the interactions comprised within the CSI data. The performance of the proposed approach was evaluated using our publicly available human-human interaction CSI dataset that contains the CSI data recorded for 40 pairs of participants while performing 13 interactions. The experimental results indicate that our proposed approach achieved an average recognition accuracy of 69.78% computed overall the 13 interactions. The reported results for each pair of participants demonstrate the feasibility of our proposed approach to recognize human-human interactions using the CSI metric of the Wi-Fi signals.
{"title":"A Wi-Fi-based Approach for Recognizing Human-Human Interactions","authors":"R. Alazrai, A. Awad, B. Alsaify, M. Daoud","doi":"10.1109/ICICS52457.2021.9464570","DOIUrl":"https://doi.org/10.1109/ICICS52457.2021.9464570","url":null,"abstract":"This paper presents a new approach for recognizing human activities that involve two humans, referred to as human-human interactions, using Wi-Fi signals. The proposed approach utilizes the Channel State Information (CSI) metric of the Wi-Fi signals to characterize the performed interactions in indoor environment. Specifically, the proposed approach analyzes the CSI data and extracts a set of time-domain and frequency-domain features that comprise salient information to distinguish between the performed interactions. The extracted features are used to construct a multi-class support vector machine classifier that can recognize the classes of the interactions comprised within the CSI data. The performance of the proposed approach was evaluated using our publicly available human-human interaction CSI dataset that contains the CSI data recorded for 40 pairs of participants while performing 13 interactions. The experimental results indicate that our proposed approach achieved an average recognition accuracy of 69.78% computed overall the 13 interactions. The reported results for each pair of participants demonstrate the feasibility of our proposed approach to recognize human-human interactions using the CSI metric of the Wi-Fi signals.","PeriodicalId":421803,"journal":{"name":"2021 12th International Conference on Information and Communication Systems (ICICS)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131836974","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 : 2021-05-24DOI: 10.1109/ICICS52457.2021.9464608
Yara E. Alharahsheh, Malak Abdullah
Mental Health diseases affect prominent individuals worldwide. According to WHO, 264 million people globally are affected by one mental health disease, depression. The lack of resources about the disease causes the difficulty of diagnosis and producing an efficient treatment, which eventually increases the number of cases. Depression affects several countries with a lack of knowledge about the disease and lack of resources, such as psychiatrists, psychiatric nurses, mental psychologists. In Kenya, almost 50% of its population suffers from many depression cases. This paper aims to find a robust reliable supervised Machine Learning classifier that gives the best performance evaluation for predicting if an individual is likely suffering from depression or not. The study is based on a data survey made by Busara Center in Kenya. We evaluate different machine learning methods, SVM, Random Forest, Ada Boosting, and Voting-Ensemble models scored the highest f1-score and accuracy with 0.78 and 85%, respectively.
{"title":"Predicting Individuals Mental Health Status in Kenya using Machine Learning Methods","authors":"Yara E. Alharahsheh, Malak Abdullah","doi":"10.1109/ICICS52457.2021.9464608","DOIUrl":"https://doi.org/10.1109/ICICS52457.2021.9464608","url":null,"abstract":"Mental Health diseases affect prominent individuals worldwide. According to WHO, 264 million people globally are affected by one mental health disease, depression. The lack of resources about the disease causes the difficulty of diagnosis and producing an efficient treatment, which eventually increases the number of cases. Depression affects several countries with a lack of knowledge about the disease and lack of resources, such as psychiatrists, psychiatric nurses, mental psychologists. In Kenya, almost 50% of its population suffers from many depression cases. This paper aims to find a robust reliable supervised Machine Learning classifier that gives the best performance evaluation for predicting if an individual is likely suffering from depression or not. The study is based on a data survey made by Busara Center in Kenya. We evaluate different machine learning methods, SVM, Random Forest, Ada Boosting, and Voting-Ensemble models scored the highest f1-score and accuracy with 0.78 and 85%, respectively.","PeriodicalId":421803,"journal":{"name":"2021 12th International Conference on Information and Communication Systems (ICICS)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116257378","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 : 2021-05-24DOI: 10.1109/ICICS52457.2021.9464595
Sofiane Hamrioui, Samira Bokhari
Today’s companies are increasingly relying on Internet of Everything (IoE) to modernize their operations. The very complexes characteristics of such system expose their applications and their exchanged data to multiples risks and security breaches that make them targets for cyber attacks. The aim of our work in this paper is to provide an cybersecurity strategy whose objective is to prevent and anticipate threats related to the IoE. An economic approach is used in order to help to take decisions according to the reduction of the risks generated by the non definition of the appropriate levels of security. The considered problem have been resolved by exploiting a combinatorial optimization approach with a practical case of knapsack. We opted for a bi-objective modeling under uncertainty with a constraint of cardinality and a given budget to be respected. To guarantee a robustness of our strategy, we have also considered the criterion of uncertainty by taking into account all the possible threats that can be generated by a cyber attacks over IoE. Our strategy have been implemented and simulated under MATLAB environement and its performance results have been compared to those obtained by NSGA-II metaheuristic. Our proposed cyber security strategy recorded a clear improvment of efficiency according to the optimization of the security level and cost parametrs.
{"title":"A new Cybersecurity Strategy for IoE by Exploiting an Optimization Approach","authors":"Sofiane Hamrioui, Samira Bokhari","doi":"10.1109/ICICS52457.2021.9464595","DOIUrl":"https://doi.org/10.1109/ICICS52457.2021.9464595","url":null,"abstract":"Today’s companies are increasingly relying on Internet of Everything (IoE) to modernize their operations. The very complexes characteristics of such system expose their applications and their exchanged data to multiples risks and security breaches that make them targets for cyber attacks. The aim of our work in this paper is to provide an cybersecurity strategy whose objective is to prevent and anticipate threats related to the IoE. An economic approach is used in order to help to take decisions according to the reduction of the risks generated by the non definition of the appropriate levels of security. The considered problem have been resolved by exploiting a combinatorial optimization approach with a practical case of knapsack. We opted for a bi-objective modeling under uncertainty with a constraint of cardinality and a given budget to be respected. To guarantee a robustness of our strategy, we have also considered the criterion of uncertainty by taking into account all the possible threats that can be generated by a cyber attacks over IoE. Our strategy have been implemented and simulated under MATLAB environement and its performance results have been compared to those obtained by NSGA-II metaheuristic. Our proposed cyber security strategy recorded a clear improvment of efficiency according to the optimization of the security level and cost parametrs.","PeriodicalId":421803,"journal":{"name":"2021 12th International Conference on Information and Communication Systems (ICICS)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130549135","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 : 2021-05-24DOI: 10.1109/ICICS52457.2021.9464592
Aya Nuseir, M. Alsmirat, A. Nuseir, M. Al-Ayyoub, Mohammed Mahdi, A. AlOmari, H. Al-Balas
Sinuses disorders are among the most common disorders that affect people’s lives worldwide. Diagnosing such disorders requires highly skilled specialists to carefully inspect Computed Tomographic (CT) scans of the patient. The diagnosis process is time-consuming and very costly. To build a machine learning based computer system for the diagnosis process, an annotated set of CT scans representing different sinus disorders is needed to train and test such a system. In this work, we build an image set by collecting CT scans of 100 patients with an average of 94 slices per patient. In each scan, ten different sinuses and sinus parts are captured. These sinuses and sinus parts are distinguished as Frontal (right side), Frontal (left side), Maxillary (right side), Maxillary (left side), Anterior Ethmoid (right side), Anterior Ethmoid (left side), Posterior Ethmoid (right side), Posterior Ethmoid (left side), Sphenoid (right side), and Sphenoid (left side). The scans are segmented and annotated by specialists, where each segment is labeled with the sinus (or sinus part) it depicts (one out of the ten classes mentioned above) along with one of the following six classes representing the status of this part: Normal, Cyst, Osteoma, Chronic Rhinosinusitis (CRS), Antrochoanal polyp (ACP), and Missing sinus. The dataset is acquired from the King Abdullah University Hospital (KAUH) in Jordan and it consists of 48,324 different annotated samples making it the largest and most comprehensive dataset for sinus diseases to the best of our knowledge.
{"title":"Building a Large Comprehensive Medical Image Set of Sinus Diseases","authors":"Aya Nuseir, M. Alsmirat, A. Nuseir, M. Al-Ayyoub, Mohammed Mahdi, A. AlOmari, H. Al-Balas","doi":"10.1109/ICICS52457.2021.9464592","DOIUrl":"https://doi.org/10.1109/ICICS52457.2021.9464592","url":null,"abstract":"Sinuses disorders are among the most common disorders that affect people’s lives worldwide. Diagnosing such disorders requires highly skilled specialists to carefully inspect Computed Tomographic (CT) scans of the patient. The diagnosis process is time-consuming and very costly. To build a machine learning based computer system for the diagnosis process, an annotated set of CT scans representing different sinus disorders is needed to train and test such a system. In this work, we build an image set by collecting CT scans of 100 patients with an average of 94 slices per patient. In each scan, ten different sinuses and sinus parts are captured. These sinuses and sinus parts are distinguished as Frontal (right side), Frontal (left side), Maxillary (right side), Maxillary (left side), Anterior Ethmoid (right side), Anterior Ethmoid (left side), Posterior Ethmoid (right side), Posterior Ethmoid (left side), Sphenoid (right side), and Sphenoid (left side). The scans are segmented and annotated by specialists, where each segment is labeled with the sinus (or sinus part) it depicts (one out of the ten classes mentioned above) along with one of the following six classes representing the status of this part: Normal, Cyst, Osteoma, Chronic Rhinosinusitis (CRS), Antrochoanal polyp (ACP), and Missing sinus. The dataset is acquired from the King Abdullah University Hospital (KAUH) in Jordan and it consists of 48,324 different annotated samples making it the largest and most comprehensive dataset for sinus diseases to the best of our knowledge.","PeriodicalId":421803,"journal":{"name":"2021 12th International Conference on Information and Communication Systems (ICICS)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126743729","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 : 2021-05-24DOI: 10.1109/ICICS52457.2021.9464606
El-hacen Diallo, O. Dib, Khaldoun Al Agha
With the increasing number of autonomous vehicles, more intelligent applications and services are needed to build an efficient transportation system. That cannot be achieved without having an efficient and secure model for recording and sharing traffic-related data. Because of its important features in terms of architecture decentralization, data immutability, transparency of actions, and communications security, the blockchain technology has recently been proposed to mitigate early VANETs (Vehicular Ad Hoc Networks) designs’ security issues. In this work, we design a new consensus protocol based on Practical Byzantine Fault Tolerance (PBFT), aiming at proposing a secure traffic-related data sharing system in VANETs. The proposed consensus intelligently selects a set of Road Side Units (RSUs) to validate the traffic events emitted by vehicles and subsequently maintain the blockchain ledger to further exploit its immutable data. In this paper, we also introduce the concept of micro-transactions to reduce the size of the blockchain ledger and minimize the communications overhead between nodes. The performance of the proposed solution is assessed by simulating real-world VANETs’ settings. The experimental results validate the proposed work’s high performance in terms of blockchain throughput, latency, communication load, and storage cost.
{"title":"An Improved PBFT-based Consensus for Securing Traffic Messages in VANETs","authors":"El-hacen Diallo, O. Dib, Khaldoun Al Agha","doi":"10.1109/ICICS52457.2021.9464606","DOIUrl":"https://doi.org/10.1109/ICICS52457.2021.9464606","url":null,"abstract":"With the increasing number of autonomous vehicles, more intelligent applications and services are needed to build an efficient transportation system. That cannot be achieved without having an efficient and secure model for recording and sharing traffic-related data. Because of its important features in terms of architecture decentralization, data immutability, transparency of actions, and communications security, the blockchain technology has recently been proposed to mitigate early VANETs (Vehicular Ad Hoc Networks) designs’ security issues. In this work, we design a new consensus protocol based on Practical Byzantine Fault Tolerance (PBFT), aiming at proposing a secure traffic-related data sharing system in VANETs. The proposed consensus intelligently selects a set of Road Side Units (RSUs) to validate the traffic events emitted by vehicles and subsequently maintain the blockchain ledger to further exploit its immutable data. In this paper, we also introduce the concept of micro-transactions to reduce the size of the blockchain ledger and minimize the communications overhead between nodes. The performance of the proposed solution is assessed by simulating real-world VANETs’ settings. The experimental results validate the proposed work’s high performance in terms of blockchain throughput, latency, communication load, and storage cost.","PeriodicalId":421803,"journal":{"name":"2021 12th International Conference on Information and Communication Systems (ICICS)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126336619","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：