Mariam Rahman, R. Rahman, Khadiza Akter Supty, Rakefa Tus Sabah, Md. Rajibul Islam, Md. Rashedul Islam, Nadeem Ahmed
{"title":"A Real Time Abysmal Activity Detection System Towards the Enhancement of Road Safety","authors":"Mariam Rahman, R. Rahman, Khadiza Akter Supty, Rakefa Tus Sabah, Md. Rajibul Islam, Md. Rashedul Islam, Nadeem Ahmed","doi":"10.1109/IRASET52964.2022.9738165","DOIUrl":"https://doi.org/10.1109/IRASET52964.2022.9738165","url":null,"abstract":"Nowadays, road accidents are a serious worry particularly in the developed countries where the rules and regulations are not maintained properly. The majority of traffic accidents are caused by the drivers' error or hostile behavior against the drivers inside the vehicle. In a nutshell, any type of abysmal action occurring inside the vehicle can result in a traffic accident. If these behaviors can be detected in real time, unexpected accidents can be reduced in a significant manner. Due to the increasing frequency of road accidents over the years, it has attracted the researchers' curiosity, and they are attempting to mitigate the abysmal activities inside the vehicle. In this regard, the deep learning algorithms can present a real-time abysmal activity detection system for inside use in a vehicle with the goal of reducing road accidents and thus increasing the passengers' safety. In this investigation, a dataset of abysmal activity inside a vehicle has been created, consisting of 10400 diverse photos divided into 9 classes. To the best of our knowledge, it is the largest dataset in this regard. Then, a real-time activity detection model called You Only Look Once (Yolov4) has been successfully employed, which obtained an outstanding accuracy of 99.402%.","PeriodicalId":377115,"journal":{"name":"2022 2nd International Conference on Innovative Research in Applied Science, Engineering and Technology (IRASET)","volume":"85 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126935821","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}
{"title":"Using Bayesian Ridge Regression to predict the Overall Equipment Effectiveness performance","authors":"Mjimer Imane, Es-Saâdia Aoula, E. H. Achouyab","doi":"10.1109/IRASET52964.2022.9738316","DOIUrl":"https://doi.org/10.1109/IRASET52964.2022.9738316","url":null,"abstract":"To be competitive in the market, each company tries to decrease all kind of waste in the production system, for this reason, the company try to put in place key performance indicators used to measure the company performance, one of the good indicators used is the overall equipment effectiveness (OEE). This study aims to predict the OEE using the supervised machine learning techniques, known by their ability to treat an important size of data, the supervised learning techniques will help us to treat the data and know the trajectory of the company performance. In our case, we have used the Bayesian Ridge regression algorithm. The results of applying this technique show a very high accuracy higher than 99%.","PeriodicalId":377115,"journal":{"name":"2022 2nd International Conference on Innovative Research in Applied Science, Engineering and Technology (IRASET)","volume":"418 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124192301","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}
Bellat Abdelouahad, K. Mansouri, Raihani Abdelhadi
{"title":"New approach for optimizing the yaw of a wind farm using the random algorithm","authors":"Bellat Abdelouahad, K. Mansouri, Raihani Abdelhadi","doi":"10.1109/IRASET52964.2022.9738271","DOIUrl":"https://doi.org/10.1109/IRASET52964.2022.9738271","url":null,"abstract":"Reducing wake interactions from upstream turbines is one way to improve the output of wind farms in wind farms. This can be achieved by adjusting the layout of the turbines and the yaw and pitch angles of the turbines. The direction of the wake of wind farms via the optimization of the yaw angles has received particular attention recently. Developing rapid optimization algorithms capable of identifying the right solutions in real time is one of the challenges of optimizing yaw. In this article we have devised a random search strategy to find the best yaw angles. The configuration of 39 wind turbines in a 2 km by 2 km region has been optimized in a wind farm designed diagonally to expose the maximum surface area to the wind. In order to maximize the quality of the solution while minimizing the computation costs, the algorithmic parameters have been refined. According to the results of the tests, this algorithm can systematically identify solutions close to the ideal (less than 1% of the best-known solutions) and quality solutions can be obtained with fewer iterations (less than 200). As the density of wind farms increases, the possibility of yaw optimization also increases, and good solutions are likely to be available in large numbers.","PeriodicalId":377115,"journal":{"name":"2022 2nd International Conference on Innovative Research in Applied Science, Engineering and Technology (IRASET)","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121491963","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}
{"title":"Benchmark of deep learning models for single image super-resolution (SISR)","authors":"Omar Soufi, Zineb Aarab, Fatima-Zahra Belouadha","doi":"10.1109/IRASET52964.2022.9738274","DOIUrl":"https://doi.org/10.1109/IRASET52964.2022.9738274","url":null,"abstract":"In this paper we present a study of deep learning models for single image super-resolution (SISR), through the some latest methods used in neural networks for super-resolution, exploring many methods used and proposed. Moreover, this paper presents a global and complete technical benchmark of state-of-the-art machine learning algorithms based on reference metrics (PSNR and SSIM) in the field of visualization and perception. This study involved 53 different neural networks tested on 7 datasets established as reference in the vision domain (Set5, Set14, BSD100, Urban100, DIV2K, Manga109, DIV8K). This work allows us to have a reference to demonstrate the performances and the limits of these algorithms as well as to orient future research in the field of super resolution images in order to develop efficient algorithms. The benchmark covered many neural network architectures (GAN, RNN and Residual Networks), using different techniques and distinct technologies.","PeriodicalId":377115,"journal":{"name":"2022 2nd International Conference on Innovative Research in Applied Science, Engineering and Technology (IRASET)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124448059","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}
Wiam Fadel, Imane Araf, T. Bouchentouf, Pierre-André Buvet, F. Bourzeix, Omar Bourja
{"title":"Which French speech recognition system for assistant robots?","authors":"Wiam Fadel, Imane Araf, T. Bouchentouf, Pierre-André Buvet, F. Bourzeix, Omar Bourja","doi":"10.1109/IRASET52964.2022.9737976","DOIUrl":"https://doi.org/10.1109/IRASET52964.2022.9737976","url":null,"abstract":"Artificial intelligence-based speech recognition systems are already available and capable of recognizing the French language. Still, it is quite time-consuming to compare which one will be effective for an assistant robot. The study aims to select the best French-language speech recognition system with the least error in a real environment. In this paper, we present related works on how an Automatic Speech Recognition (ASR) system works, the models used by each of its components, several open-source French datasets, and the frequently used evaluation techniques. Next, we compare deep learning-based speech recognition APIs and pre-trained models for French on two different datasets using the Word Error Rate (WER) metric. The experimental results reveal that Google's Speech-to-Text API outperforms the other systems, namely VOSK API, Wav2vec 2.0, QuartzNet, and Speech Brain's Convolutional, Recurrent, and Fully-connected Networks (CRDNN) model.","PeriodicalId":377115,"journal":{"name":"2022 2nd International Conference on Innovative Research in Applied Science, Engineering and Technology (IRASET)","volume":"77 5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128176192","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}
Adamou Moussa Saley, M. Ndiaye, K. Niane, A. Raimy, Papa Ndiaga Ba
{"title":"Study and Evaluation of a hybrid architecture to optimize resources in the 5G core network","authors":"Adamou Moussa Saley, M. Ndiaye, K. Niane, A. Raimy, Papa Ndiaga Ba","doi":"10.1109/IRASET52964.2022.9738067","DOIUrl":"https://doi.org/10.1109/IRASET52964.2022.9738067","url":null,"abstract":"Previous cellular generations have had the main objective of providing fast and reliable cellular data services to diverse network users. 5G has historically expanded this scope to offer a wide range of wireless services, delivered to the user across multiple access platforms and via multi-layer networks. As 5G offers a coherent, flexible and dynamic platform for multiple advanced technologies supporting a wide range of applications, it is of paramount importance to design and optimize a network architecture model from a QoS perspective. Thus. There are several service architectures the dedicated architecture or the shared architecture. The objective of the paper is to appreciate the best quality of service in terms of latency provided according to the type of architecture chosen. The objectives of the convergence architecture in the 5G era will be addressed in this paper, with a look at the capabilities of function reuse, resource pooling for real optimization. This research work will also allow to make a comparison with the industrial world and precisely with the telecom operators and to make technical proposals to bring an answer to the stakes that are the optimization of the costs, the quality of the experience and the quality of services to boost the innovation. to carry out the practice research, this paper uses a multi-agent system framework based on Python, the osBrain environment. Evaluating the results of the simulation, the hybrid architecture proposes more efficiency by its reliability, low latency and scalability and therefore the most optimal in terms of value creation.","PeriodicalId":377115,"journal":{"name":"2022 2nd International Conference on Innovative Research in Applied Science, Engineering and Technology (IRASET)","volume":"97 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130700188","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}
{"title":"Customer Service Enhancement in Banking Field using IoT Technologies","authors":"M. Ennafiri, M. E. H. Charaf, Abdessalam Ait Madi","doi":"10.1109/IRASET52964.2022.9738035","DOIUrl":"https://doi.org/10.1109/IRASET52964.2022.9738035","url":null,"abstract":"Customer service is one of the highest priorities in the banking field. Each year, banks globally allocate approximately 20 percent of their revenues to innovate and protect their information system. During the coronavirus period, Moroccan banks have faced difficulties serving their customers, which led to the development of a bad relationship between the two sides and negatively affected the financial performance of banks. The Moroccan customers want to have 24/7 access to their banking services on their phones, on the web at home, and in physical branches. Even if digital banking applications have helped to provide options and to ease access to various banking services, many Moroccans who are less technologically engaged prefer in-person banking at the agency, which sometimes leads to overcrowded agencies. It has become necessary for the banks to propose new solutions to serve their customers while reducing the risk of covid-19 virus transmission. In this paper, we will present a solution based on the Internet of Things (IoT) technology in order to gain customer satisfaction by minimizing long wait times, reducing the number of people at the agency, reducing close interactions while managing a safe, smooth, and effective customer service.","PeriodicalId":377115,"journal":{"name":"2022 2nd International Conference on Innovative Research in Applied Science, Engineering and Technology (IRASET)","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115540173","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}
El Farnane Abdelhafid, Y. M. Abdelkader, Mouhsen Ahmed, El Hafiane Doha, El Khalidi Oumayma, El Aissaoui Abdellah
{"title":"Localization based on DGPS for Autonomous Robots in Precision Agriculture","authors":"El Farnane Abdelhafid, Y. M. Abdelkader, Mouhsen Ahmed, El Hafiane Doha, El Khalidi Oumayma, El Aissaoui Abdellah","doi":"10.1109/IRASET52964.2022.9737758","DOIUrl":"https://doi.org/10.1109/IRASET52964.2022.9737758","url":null,"abstract":"In recent years, self-driving systems have smoothly penetrated several sectors, including precision farming. In this context, the Regional Center for Agronomic Research (CRRA) of Settat is working on a project to develop a low-cost autonomous driving tricycle robot for Precision Agriculture (PA). The robot will allow us to perform various tasks, such as data acquisition and the management of operations using a prescription map. The localization of the autonomous robot is a critical part of promoting its use. This paper focuses on the implementation of a Differential Global Positioning System (DGPS) localization system. This low-cost solution is mounted using an Arduino coupled to a GPS module for acquiring localization data that will be served for robot guidance. The experimental results show that our system provides adequate localization accuracy for agricultural robots.","PeriodicalId":377115,"journal":{"name":"2022 2nd International Conference on Innovative Research in Applied Science, Engineering and Technology (IRASET)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124506526","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}
Mohammed Belghazdis, El-Kaber HACHEM, H. Benmoussa
{"title":"Quantification of clay minerals from Meknes: Theory and application","authors":"Mohammed Belghazdis, El-Kaber HACHEM, H. Benmoussa","doi":"10.1109/IRASET52964.2022.9737967","DOIUrl":"https://doi.org/10.1109/IRASET52964.2022.9737967","url":null,"abstract":"A great number of fields are concerned with the determination of the quantity of clay minerals present in the soil and the rocks rich in clay, but this will run up against the difficulty of the operation and the lack of interesting research in the field. This difficulty is mainly due to the unique structure as well as the very variable chemical composition characterizing the clay minerals. In this review, we have discussed the most important mineral quantification techniques available, with a discussion of their advantages and disadvantages. The emphasis was put on the techniques based on X-ray diffraction (XRD), because they are the best known and most accurate and have been considerably improved in recent years following the development of specific computer processing systems. We are interested in single peak techniques (Mineral Intensity Factor (MIF), Reference Intensity Ratio (RIR)), and those based on the full pattern (Rietveld, full pattern summation). After that, we applied the XRD technique and the XRF technique for the quantification of the natural clay from Meknes. The results of quantification by XRD of the minerals constituting the natural clay from Meknes, show the dominance of quartz (66.83%), followed by an important quantity of illite (15.8%), then kaolinite (9.1%) and finally smectite (8.26%). While the results obtained by XRF application show that kaolinite is present with a small percentage (0.08%). The percentage of illite, smectite and quartz are, respectively, (26.32%), (5.04) et (68.56%).","PeriodicalId":377115,"journal":{"name":"2022 2nd International Conference on Innovative Research in Applied Science, Engineering and Technology (IRASET)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114633244","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}
Mbarek Outazkrit, Faicel El Aamri, Essaid Jaoide, A. Mouhsen, A. Radouane
{"title":"Performance of Modular Multilevel Converter under LS-PWM and NLC Modulation","authors":"Mbarek Outazkrit, Faicel El Aamri, Essaid Jaoide, A. Mouhsen, A. Radouane","doi":"10.1109/IRASET52964.2022.9737889","DOIUrl":"https://doi.org/10.1109/IRASET52964.2022.9737889","url":null,"abstract":"This paper reports a performance comparison of two different modulation techniques applied to the modular multilevel converter (MMC). Level-shifted pulse-width modulation (LS-PWM) and the nearest level control (NLC) are studied in this work. This comparison focused on total harmonic distortion (THD) of the output current and switching frequency. A three-phase MMC operating as an inverter is modeled and simulated in the Piecewise Linear Electrical Circuit Simulation (PLECS) environment to evaluate the performance of each modulation studied.","PeriodicalId":377115,"journal":{"name":"2022 2nd International Conference on Innovative Research in Applied Science, Engineering and Technology (IRASET)","volume":"211 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116399332","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}