Pub Date : 2021-06-01DOI: 10.1109/ICDATA52997.2021.00043
A. Ouchatti, Azeddine Wahbi, A. Moutabir, Youness Benkhanous, A. Taouni, Redouane Majdoul
In recent years, the multilevel DC/AC static converters are increasingly used for their benefits especially in terms of reduction of total harmonic distortion (THD) of the output current and reduced voltage stress on semiconductors at switching moments. In this article, an Extended T-Type structure of multilevel inverter is proposed for photovoltaic systems. This structure has the advantage of being simple; on the one hand, it contains only switches (no switching capacitors and clamping diodes, etc.) and the number of these switches corresponds exactly to the required number of voltage levels, and on the other hand, the control scheme is much simpler to implement and suitable for variable RMS value operations. The modulation used is based on the technique of sinusoidal fundamental frequency pulse width modulation (PWM) with a single carrier. The performances (THD, voltage stress on the semiconductors) of the inverter are analyzed by simulations in the Matlab-Simulink environment on an example of a nine-level inverter.
{"title":"Extended T-Type Topology of Single-Phase Multi-Level Inverter","authors":"A. Ouchatti, Azeddine Wahbi, A. Moutabir, Youness Benkhanous, A. Taouni, Redouane Majdoul","doi":"10.1109/ICDATA52997.2021.00043","DOIUrl":"https://doi.org/10.1109/ICDATA52997.2021.00043","url":null,"abstract":"In recent years, the multilevel DC/AC static converters are increasingly used for their benefits especially in terms of reduction of total harmonic distortion (THD) of the output current and reduced voltage stress on semiconductors at switching moments. In this article, an Extended T-Type structure of multilevel inverter is proposed for photovoltaic systems. This structure has the advantage of being simple; on the one hand, it contains only switches (no switching capacitors and clamping diodes, etc.) and the number of these switches corresponds exactly to the required number of voltage levels, and on the other hand, the control scheme is much simpler to implement and suitable for variable RMS value operations. The modulation used is based on the technique of sinusoidal fundamental frequency pulse width modulation (PWM) with a single carrier. The performances (THD, voltage stress on the semiconductors) of the inverter are analyzed by simulations in the Matlab-Simulink environment on an example of a nine-level inverter.","PeriodicalId":231714,"journal":{"name":"2021 International Conference on Digital Age & Technological Advances for Sustainable Development (ICDATA)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114221597","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-06-01DOI: 10.1109/ICDATA52997.2021.00030
D. Amina, Mohamed Ben Ali Yamina
In the e- learning systems, a learning path is known as a sequence of learning materials linked to each others to help learners achieving their learning goals. As it is difficult to have the same learning path that suits different learners, the Curriculum Sequencing problem (CS) consists of the generation of a personalized learning path for each learner according to his learner profile. This last one is represented through competencies. The proposed approach includes two components: (1) competency based approach that is used to represent the knowledge model and to deliver to the learner the learning path; and (2) a DNA computing approach based on a weighted graph is used to deliver a learning path to each learner. An example regarding the course of algorithmic is presented to demonstrate the effectiveness of the proposed design. Results show that competency based DNA computing approach can generate a personalized learning path successfully.
{"title":"Competenty-Based Approach for Learning Objects sequencing using DNA computing","authors":"D. Amina, Mohamed Ben Ali Yamina","doi":"10.1109/ICDATA52997.2021.00030","DOIUrl":"https://doi.org/10.1109/ICDATA52997.2021.00030","url":null,"abstract":"In the e- learning systems, a learning path is known as a sequence of learning materials linked to each others to help learners achieving their learning goals. As it is difficult to have the same learning path that suits different learners, the Curriculum Sequencing problem (CS) consists of the generation of a personalized learning path for each learner according to his learner profile. This last one is represented through competencies. The proposed approach includes two components: (1) competency based approach that is used to represent the knowledge model and to deliver to the learner the learning path; and (2) a DNA computing approach based on a weighted graph is used to deliver a learning path to each learner. An example regarding the course of algorithmic is presented to demonstrate the effectiveness of the proposed design. Results show that competency based DNA computing approach can generate a personalized learning path successfully.","PeriodicalId":231714,"journal":{"name":"2021 International Conference on Digital Age & Technological Advances for Sustainable Development (ICDATA)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129929115","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-06-01DOI: 10.1109/ICDATA52997.2021.00021
Zineb Ellaky, F. Benabbou, Sara Ouahabi, N. Sael
Online Social networks (OSN) have become an integral part of people's lives. People from all over the world interact instantly between each other by sharing pictures and content. They can also express their opinion about politics, sport, and be part of influencing users in OSN. So, with the large growth of the number of users of OSN, it has become a target for the vicious people that post spam contents and messages. The malicious social bots (MSB) are one of the biggest threats that menace the social networks security and several studies have been conducted to detect them. In this work we focus on spam bots and reviewed all the existing bot detection techniques based on different features extracted from users' profiles and interactions. The paper analyzed and compared the proposed techniques between 2014 and 2021 to get the most relevant features that improve the spam bot detection and the most efficient Machine learning ML and Deep learning DL techniques from OSN. An investigation on existing datasets is proposed, some limitations of the studied approaches are outlined and future directions for social bot techniques detection improvement are proposed.
{"title":"A Survey of Spam Bots Detection in Online Social Networks","authors":"Zineb Ellaky, F. Benabbou, Sara Ouahabi, N. Sael","doi":"10.1109/ICDATA52997.2021.00021","DOIUrl":"https://doi.org/10.1109/ICDATA52997.2021.00021","url":null,"abstract":"Online Social networks (OSN) have become an integral part of people's lives. People from all over the world interact instantly between each other by sharing pictures and content. They can also express their opinion about politics, sport, and be part of influencing users in OSN. So, with the large growth of the number of users of OSN, it has become a target for the vicious people that post spam contents and messages. The malicious social bots (MSB) are one of the biggest threats that menace the social networks security and several studies have been conducted to detect them. In this work we focus on spam bots and reviewed all the existing bot detection techniques based on different features extracted from users' profiles and interactions. The paper analyzed and compared the proposed techniques between 2014 and 2021 to get the most relevant features that improve the spam bot detection and the most efficient Machine learning ML and Deep learning DL techniques from OSN. An investigation on existing datasets is proposed, some limitations of the studied approaches are outlined and future directions for social bot techniques detection improvement are proposed.","PeriodicalId":231714,"journal":{"name":"2021 International Conference on Digital Age & Technological Advances for Sustainable Development (ICDATA)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117142753","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-06-01DOI: 10.1109/ICDATA52997.2021.00046
Jesus Ekie, Bassirou Gueye, Tresor Ekie, I. Niang
The advent of health crises like COVID-19 in West Africa, and more particularly in Senegal, led the MoHSA, with the support of several development partners, to set up a real-time alert and information reporting system through the mInfoSante project. These informations are retrieved from Chief Nursing Officers, Chief Veterinary Officers, and more than 2,000 Community Watch & Alert Committees dispatched throughout the national territory. The ease of use of mInfoSante and its advantages has seduced professionals in the health sector. However, one will quickly realize that the exploitation of information can be tedious without the support of a system dedicated to this task. Due to the specificity of the sector as well as the technical and institutional environment, we had to adapt to a certain number of constraints in the identification and implementation of such a solution. To do this, we have studied a set of open-source and powerful Business Intelligence and Dashboarding solutions. According to the performed analysis, our solution, which make use of REST-based service composition, presents advantages of having functionalities related to the distributed storage & processing of large data sets, a capacity for rapid processing of all data types, good computing power offered by its optimized components, and fault tolerance due to integration of distributed infrastructure model.
{"title":"An Evidence-Based Approach on Public Health Decisions in Low-Middle Income Countries: Use Case of Senegal at the Verge of COVID-19","authors":"Jesus Ekie, Bassirou Gueye, Tresor Ekie, I. Niang","doi":"10.1109/ICDATA52997.2021.00046","DOIUrl":"https://doi.org/10.1109/ICDATA52997.2021.00046","url":null,"abstract":"The advent of health crises like COVID-19 in West Africa, and more particularly in Senegal, led the MoHSA, with the support of several development partners, to set up a real-time alert and information reporting system through the mInfoSante project. These informations are retrieved from Chief Nursing Officers, Chief Veterinary Officers, and more than 2,000 Community Watch & Alert Committees dispatched throughout the national territory. The ease of use of mInfoSante and its advantages has seduced professionals in the health sector. However, one will quickly realize that the exploitation of information can be tedious without the support of a system dedicated to this task. Due to the specificity of the sector as well as the technical and institutional environment, we had to adapt to a certain number of constraints in the identification and implementation of such a solution. To do this, we have studied a set of open-source and powerful Business Intelligence and Dashboarding solutions. According to the performed analysis, our solution, which make use of REST-based service composition, presents advantages of having functionalities related to the distributed storage & processing of large data sets, a capacity for rapid processing of all data types, good computing power offered by its optimized components, and fault tolerance due to integration of distributed infrastructure model.","PeriodicalId":231714,"journal":{"name":"2021 International Conference on Digital Age & Technological Advances for Sustainable Development (ICDATA)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128725212","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-06-01DOI: 10.1109/ICDATA52997.2021.00024
Yassir Matrane, F. Benabbou, N. Sael
Nowadays, Sentiment Analysis (SA) represents a big chunk of Natural Language Processing (NLP) problems. The latter makes it possible to assign feelings and polarity to portions of text, which comes handy in multiple areas of social conduct such as product reviewing in business, determining political opinions of the masses and other uses. Nevertheless, sentiment analysis can be tricky when dealing with unstructured languages due to the lack of conventional syntactic and morphological structures. In this paper, we discuss several attempts of the literature at solving the challenge of Sentiment analysis of regional dialects, and we propose an approach based on AraBERT word embedding for Moroccan dialect (MD) sentiment analysis. The method goes through a pipeline of steps starting with preprocessing, lexicon-based translation and feature extraction. Afterwards we conduct a comparative study, in 2-way classification, of machine learning algorithms as SVM, DT, LR, RF, NB and deep learning algorithms such as LSTM, BiLSTM and LSTM-CNN from state of art. On the other hand, we managed to train our model with four different outputs in 4 way classification. As a result, BiLSTM proved to be the best in both 2-way classification scoring 83% accuracy, and in 4-way classification achieving scores ranging between 62% and 92% of accuracy for each of the 4 classes.
{"title":"Sentiment analysis through word embedding using AraBERT: Moroccan dialect use case","authors":"Yassir Matrane, F. Benabbou, N. Sael","doi":"10.1109/ICDATA52997.2021.00024","DOIUrl":"https://doi.org/10.1109/ICDATA52997.2021.00024","url":null,"abstract":"Nowadays, Sentiment Analysis (SA) represents a big chunk of Natural Language Processing (NLP) problems. The latter makes it possible to assign feelings and polarity to portions of text, which comes handy in multiple areas of social conduct such as product reviewing in business, determining political opinions of the masses and other uses. Nevertheless, sentiment analysis can be tricky when dealing with unstructured languages due to the lack of conventional syntactic and morphological structures. In this paper, we discuss several attempts of the literature at solving the challenge of Sentiment analysis of regional dialects, and we propose an approach based on AraBERT word embedding for Moroccan dialect (MD) sentiment analysis. The method goes through a pipeline of steps starting with preprocessing, lexicon-based translation and feature extraction. Afterwards we conduct a comparative study, in 2-way classification, of machine learning algorithms as SVM, DT, LR, RF, NB and deep learning algorithms such as LSTM, BiLSTM and LSTM-CNN from state of art. On the other hand, we managed to train our model with four different outputs in 4 way classification. As a result, BiLSTM proved to be the best in both 2-way classification scoring 83% accuracy, and in 4-way classification achieving scores ranging between 62% and 92% of accuracy for each of the 4 classes.","PeriodicalId":231714,"journal":{"name":"2021 International Conference on Digital Age & Technological Advances for Sustainable Development (ICDATA)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115049621","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-06-01DOI: 10.1109/ICDATA52997.2021.00014
Ikram Ben abdel ouahab, Lotfi Elaachak, M. Bouhorma, Yasser A. Alluhaidan
Medical staffs wear face masks to prevent the spread of the disease. Nowadays, with the coronavirus pandemic everyone must wear a facemask for the same reason. When a person near to you coughs, talks, sneezes he could release germs into the air that may infect you or anyone nearby. Wearing a facemask is a part of an infection control strategy to avoid and eliminate cross-contamination. Even so, people are getting tired of wearing facemasks or they are not conscious enough of the seriousness of the actual covid19. In this paper, we propose a facemask detector based on IoT embedded devices and deep learning algorithm. Our main goal is to warn people in real-time if they are not wearing a facemask or they are not wearing it correctly. The proposed solution generates loud vocal alerts after detection disrespect of facemask wear in real-time for a fast reaction. To have the most efficient detector in real-time we tested the facemask detection model using various versions of the Raspberry Pi and NCS2. As a result, the facemask detector works perfectly on powerful devices, however its performance decrease in realtime using less powerful devices such as an old version of the Raspberry Pi.
{"title":"Real-time Facemask Detector using Deep Learning and Raspberry Pi","authors":"Ikram Ben abdel ouahab, Lotfi Elaachak, M. Bouhorma, Yasser A. Alluhaidan","doi":"10.1109/ICDATA52997.2021.00014","DOIUrl":"https://doi.org/10.1109/ICDATA52997.2021.00014","url":null,"abstract":"Medical staffs wear face masks to prevent the spread of the disease. Nowadays, with the coronavirus pandemic everyone must wear a facemask for the same reason. When a person near to you coughs, talks, sneezes he could release germs into the air that may infect you or anyone nearby. Wearing a facemask is a part of an infection control strategy to avoid and eliminate cross-contamination. Even so, people are getting tired of wearing facemasks or they are not conscious enough of the seriousness of the actual covid19. In this paper, we propose a facemask detector based on IoT embedded devices and deep learning algorithm. Our main goal is to warn people in real-time if they are not wearing a facemask or they are not wearing it correctly. The proposed solution generates loud vocal alerts after detection disrespect of facemask wear in real-time for a fast reaction. To have the most efficient detector in real-time we tested the facemask detection model using various versions of the Raspberry Pi and NCS2. As a result, the facemask detector works perfectly on powerful devices, however its performance decrease in realtime using less powerful devices such as an old version of the Raspberry Pi.","PeriodicalId":231714,"journal":{"name":"2021 International Conference on Digital Age & Technological Advances for Sustainable Development (ICDATA)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132420667","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-06-01DOI: 10.1109/ICDATA52997.2021.00026
Chouaib El Hachimi, S. Belaqziz, S. Khabba, A. Chehbouni
Statistical models predict that the world's population will reach 8.5 billion by the end of 2030. This represents a real threat to our food security and puts the current food production system under pressure. Efficient use of Earth's natural resources is the only solution to facing future challenges such as global hunger. The implementation of precision agriculture using new technologies such as artificial intelligence, big data, IoT and remote sensing is the first step towards this goal. In this paper, we investigated several machine learning models to create two services: one for recommending the best crop to grow based on soil and the region's weather characteristics, and another for the forecasting of the hourly average air temperature. Performance evaluation results for the first service show that Random Forest has the best metrics as a classifier (accuracy = 100%, precision = 100%, recall = 100%) compared to K-Nearest Neighbors (KNN), Decision Tree, Naive Bayes, Logistic Regression, Convolutional Neural Network, and Feed Forward Neural Network. This is a confirmation that classic machine learning algorithms perform better on small-size datasets. In our case, we used a dataset of 2200 instances available online. On the other hand, Facebook Prophet was more accurate (R2 = 0.81, RMSE = 3.74) than our proposed LSTM architecture in time series forecasting at hourly scale using historical weather data provided by the weather station of our study area. These two optimal models are then integrated as the first building blocks in our decision support platform, intended for both farmers and policymakers with the aim of making agriculture in Morocco more efficient and more sustainable.
{"title":"Towards precision agriculture in Morocco: A machine learning approach for recommending crops and forecasting weather","authors":"Chouaib El Hachimi, S. Belaqziz, S. Khabba, A. Chehbouni","doi":"10.1109/ICDATA52997.2021.00026","DOIUrl":"https://doi.org/10.1109/ICDATA52997.2021.00026","url":null,"abstract":"Statistical models predict that the world's population will reach 8.5 billion by the end of 2030. This represents a real threat to our food security and puts the current food production system under pressure. Efficient use of Earth's natural resources is the only solution to facing future challenges such as global hunger. The implementation of precision agriculture using new technologies such as artificial intelligence, big data, IoT and remote sensing is the first step towards this goal. In this paper, we investigated several machine learning models to create two services: one for recommending the best crop to grow based on soil and the region's weather characteristics, and another for the forecasting of the hourly average air temperature. Performance evaluation results for the first service show that Random Forest has the best metrics as a classifier (accuracy = 100%, precision = 100%, recall = 100%) compared to K-Nearest Neighbors (KNN), Decision Tree, Naive Bayes, Logistic Regression, Convolutional Neural Network, and Feed Forward Neural Network. This is a confirmation that classic machine learning algorithms perform better on small-size datasets. In our case, we used a dataset of 2200 instances available online. On the other hand, Facebook Prophet was more accurate (R2 = 0.81, RMSE = 3.74) than our proposed LSTM architecture in time series forecasting at hourly scale using historical weather data provided by the weather station of our study area. These two optimal models are then integrated as the first building blocks in our decision support platform, intended for both farmers and policymakers with the aim of making agriculture in Morocco more efficient and more sustainable.","PeriodicalId":231714,"journal":{"name":"2021 International Conference on Digital Age & Technological Advances for Sustainable Development (ICDATA)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129315833","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-06-01DOI: 10.1109/ICDATA52997.2021.00032
Abdelghani Babori, Khalid Ghoulam, N. Falih, Hicham Ouchitachen
Over the last years, various studies have concentrated on E-learning and its impact on the performance of students. This learning context has raised and guided several studies of E-learning from educational and technical perspectives. However, there is a paucity of literature review about web 4.0 research for teaching and learning. Thus, this study aims to examine the research trends on E-learning 4.0 (web 4.0 destined for learning purposes). More particularly, this literature review presents the major topics, techniques and tools identified by analyzing the research focusing on the use of Artificial intelligence (AI) and the Internet of things (IoT) in distance learning contexts. Implications for future research, especially during the period of the Covid 19 pandemic, are described as well.
{"title":"Elearning 4.0 for higher education: literature review, trends and perspectives","authors":"Abdelghani Babori, Khalid Ghoulam, N. Falih, Hicham Ouchitachen","doi":"10.1109/ICDATA52997.2021.00032","DOIUrl":"https://doi.org/10.1109/ICDATA52997.2021.00032","url":null,"abstract":"Over the last years, various studies have concentrated on E-learning and its impact on the performance of students. This learning context has raised and guided several studies of E-learning from educational and technical perspectives. However, there is a paucity of literature review about web 4.0 research for teaching and learning. Thus, this study aims to examine the research trends on E-learning 4.0 (web 4.0 destined for learning purposes). More particularly, this literature review presents the major topics, techniques and tools identified by analyzing the research focusing on the use of Artificial intelligence (AI) and the Internet of things (IoT) in distance learning contexts. Implications for future research, especially during the period of the Covid 19 pandemic, are described as well.","PeriodicalId":231714,"journal":{"name":"2021 International Conference on Digital Age & Technological Advances for Sustainable Development (ICDATA)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131448958","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-06-01DOI: 10.1109/ICDATA52997.2021.00019
Abderrahim Zannou, Abdelhak Boulaalam, E. Nfaoui
Monitoring and managing traffic congestion is the most challenging problem for many cities today. It has an effect on the environment and disrupts our everyday lives. As the population expands, the number of roads and cars, creating a slew of issues such as travel time delays, fuel waste, air pollution, and transportation-related issues. On another side, the Internet of Things (IoT) provides different devices and systems to monitor and manage the real-time traffic for smart cities. In this paper, we propose a new approach to avoid traffic congestion and obtain an optimal route for vehicles in the smart city exploiting IoT devices. To do this, we create a map of all possible sources and destinations, secondly and we suggested new parameters to determine the optimal path for the vehicle's traffic. The first phase is to obtain a set of candidate paths for each possible source and destination using Ant Colony Optimization based on the unvaried constraints. The second phase is to obtain the principal path for the vehicle to achieve its destination. The simulation results show that our solution reduces the distance and the time of travel and avoids traffic congestion.
{"title":"Predicting the Traffic Congestion and Optimal Route in a Smart City Exploiting IoT Devices","authors":"Abderrahim Zannou, Abdelhak Boulaalam, E. Nfaoui","doi":"10.1109/ICDATA52997.2021.00019","DOIUrl":"https://doi.org/10.1109/ICDATA52997.2021.00019","url":null,"abstract":"Monitoring and managing traffic congestion is the most challenging problem for many cities today. It has an effect on the environment and disrupts our everyday lives. As the population expands, the number of roads and cars, creating a slew of issues such as travel time delays, fuel waste, air pollution, and transportation-related issues. On another side, the Internet of Things (IoT) provides different devices and systems to monitor and manage the real-time traffic for smart cities. In this paper, we propose a new approach to avoid traffic congestion and obtain an optimal route for vehicles in the smart city exploiting IoT devices. To do this, we create a map of all possible sources and destinations, secondly and we suggested new parameters to determine the optimal path for the vehicle's traffic. The first phase is to obtain a set of candidate paths for each possible source and destination using Ant Colony Optimization based on the unvaried constraints. The second phase is to obtain the principal path for the vehicle to achieve its destination. The simulation results show that our solution reduces the distance and the time of travel and avoids traffic congestion.","PeriodicalId":231714,"journal":{"name":"2021 International Conference on Digital Age & Technological Advances for Sustainable Development (ICDATA)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128630494","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-06-01DOI: 10.1109/ICDATA52997.2021.00017
S. Bouhsissin, N. Sael, F. Benabbou
Over the last years, the number of cars used in road traffic growth at a staggering rate. This situation had resulted in a significant increase of accidents and several traffic problems resulting huge losses. One of the most important road safety technologies is to automatically recognize dangerous situations and quickly share this information with nearby vehicles. In this work, we first, analyze various researches in the detection and classification of traffic anomalies and then propose to explore the potential of VGG19, which is a transfer-learning model to classify anomalies (accidents). In addition, we have compared the proposed algorithm to the other methods used. Our experience shows that our enhanced VGG19 model gives the best performance with 96% accuracy, and 0.99 AUC compared to the Convolutional Neural Network (CNN), which is the most widely used deep learning technique for image (accident image) classification, and the VGG19 models proposed over the last researches.
{"title":"Enhanced VGG19 Model for Accident Detection and Classification from Video","authors":"S. Bouhsissin, N. Sael, F. Benabbou","doi":"10.1109/ICDATA52997.2021.00017","DOIUrl":"https://doi.org/10.1109/ICDATA52997.2021.00017","url":null,"abstract":"Over the last years, the number of cars used in road traffic growth at a staggering rate. This situation had resulted in a significant increase of accidents and several traffic problems resulting huge losses. One of the most important road safety technologies is to automatically recognize dangerous situations and quickly share this information with nearby vehicles. In this work, we first, analyze various researches in the detection and classification of traffic anomalies and then propose to explore the potential of VGG19, which is a transfer-learning model to classify anomalies (accidents). In addition, we have compared the proposed algorithm to the other methods used. Our experience shows that our enhanced VGG19 model gives the best performance with 96% accuracy, and 0.99 AUC compared to the Convolutional Neural Network (CNN), which is the most widely used deep learning technique for image (accident image) classification, and the VGG19 models proposed over the last researches.","PeriodicalId":231714,"journal":{"name":"2021 International Conference on Digital Age & Technological Advances for Sustainable Development (ICDATA)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128541444","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：