{"title":"Instrumentation of real-time acquisition system for diagnosis in a photovoltaic generator","authors":"Ousmane W. Compaore, Z. Koalaga, G. Hoblos","doi":"10.1109/MNE3SD53781.2022.9723255","DOIUrl":"https://doi.org/10.1109/MNE3SD53781.2022.9723255","url":null,"abstract":"Predictive maintenance provides a better return on investment when considering the operation of a photovoltaic generator (PVG). It requires the installation of good instrumentation, able of acquiring data in real time, linked to the performance of the energy production system based on PV panels. Through this instrumentation judiciously chosen and embedded in Arduino, we wish to save the real data of the production, in order to then submit them to an appropriate diagnosis method. This will make it possible to undertake preventive maintenance actions thanks to the real-time monitoring of the production performance of a PVG either instantly for connected sites or a posteriori for isolated production sites.","PeriodicalId":355503,"journal":{"name":"2022 IEEE Multi-conference on Natural and Engineering Sciences for Sahel's Sustainable Development (MNE3SD)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127162092","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":"MNE3SD 2022 Cover Page","authors":"","doi":"10.1109/mne3sd53781.2022.9723141","DOIUrl":"https://doi.org/10.1109/mne3sd53781.2022.9723141","url":null,"abstract":"","PeriodicalId":355503,"journal":{"name":"2022 IEEE Multi-conference on Natural and Engineering Sciences for Sahel's Sustainable Development (MNE3SD)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124467812","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":"An AI-based approach to the prediction of water points quality indicators for schistosomiasis prevention","authors":"Teegwende Zougmore, B. Gueye, Sadouanouan Malo","doi":"10.1109/MNE3SD53781.2022.9723395","DOIUrl":"https://doi.org/10.1109/MNE3SD53781.2022.9723395","url":null,"abstract":"We investigate the simultaneous daily prediction of the pH and temperature of a water point using AI-based methods. These parameters are part of the physicochemical parameters of surface water favoring the reproduction of parasitic worms responsible for Schistosomiasis. Wavelet Artificial Neural Network (WANN), Long Short Term Memory (LSTM) and Support Vector Regression (SVR) are the AI-based methods employed to build models with fifteen months collected data. They are evaluated through two metrics: root mean square (RMSE) and mean absolute error (MAE). The results show that in overall three methods give acceptable RMSE which varies from 1.59 to 0.17. WANN model shows the best performance with a RMSE equals to 0.17 and a MAE equals to MAE 0.12 over LSTM and SVR ones in forecasting parameters values one day ahead based on their two previous days observations.","PeriodicalId":355503,"journal":{"name":"2022 IEEE Multi-conference on Natural and Engineering Sciences for Sahel's Sustainable Development (MNE3SD)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130105004","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":"A Self-adaptive QoS-management Framework for Highly Dynamic IoT Networks","authors":"Avewe Bassene, B. Gueye","doi":"10.1109/MNE3SD53781.2022.9723303","DOIUrl":"https://doi.org/10.1109/MNE3SD53781.2022.9723303","url":null,"abstract":"IoT infrastructure makes great demands on network control methods for dynamic and efficient management of massive amounts of nodes. Software-Defined Networking (SDN) enables to handle dynamically network traffic as well as flexible traffic control in real-time. However, while providing flexibility and scalability, SDN-based architecture still remains ineffective to self-adapt with respect to network topologies with more or less switches in the data plane (highly dynamic topology). Having a centralized control plane is not an acceptable situation because that would represent a single point of failure in the network. Using multiple controllers that ensure flexibility and high availability would be a solution; meaning that if one controller has problems and fails, the other would be ready to take over and control the network. Thus, having a single controller raises the problem of scalability while multiple controllers call for a distributed states management problem. To overcome such issues, we propose EFQM++, a selfadaptive framework for highly dynamic network topology changes. By leveraging SDN controller topology discovery mechanism, EFQM++ improves flow end-to-end transmission delay. It tackles flexibility and scalability related to a single point of failure problem and gives distributed states management solutions in large scale IoT networks. EFQM++ reduces up to 6% and 13% the average delay in contrast to previous works like EFQM and AQRA, respectively.","PeriodicalId":355503,"journal":{"name":"2022 IEEE Multi-conference on Natural and Engineering Sciences for Sahel's Sustainable Development (MNE3SD)","volume":"120 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123758870","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":"Design and realization of an NLP application for the massive processing of large volumes of resumes","authors":"Abdou Karim Kandji, S. Ndiaye","doi":"10.1109/MNE3SD53781.2022.9723408","DOIUrl":"https://doi.org/10.1109/MNE3SD53781.2022.9723408","url":null,"abstract":"Information and communication technologies (ICTs) today impact all aspects of the life of businesses and organizations. This is particularly the case with the recruitment process, with the establishment of e-recruitment platforms. These platforms allow candidates to post their information online, including their resume. This undeniable progress has resulted in an explosion of applications for offers posted by companies. This is how large organizations today receive up to hundreds of thousands of applications for certain vacancies. E-recruitment platforms make it easy to eliminate applications that do not meet the mandatory conditions (hard skills) by using simple calculations (SQL queries). But after this first step, there are still hundreds of thousands of applications to process. At this level, the platforms show their limits. Indeed, you have to read each resume and detect the soft skills of the candidates to decide between them. We propose to design and implement a solution based on natural language processing (NLP) technologies to allow the recruiter to select the best candidates using their resume.","PeriodicalId":355503,"journal":{"name":"2022 IEEE Multi-conference on Natural and Engineering Sciences for Sahel's Sustainable Development (MNE3SD)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134598473","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}
Ahmed Sawadogo, Y. Soro, Wennd Kouni Igor. Ouédraogo
{"title":"Determination of the Maximum Solar Photovoltaic Penetration Rate of a Slightly Mesh Network: Burkina Faso Interconnected Electrical Grid Case Study.","authors":"Ahmed Sawadogo, Y. Soro, Wennd Kouni Igor. Ouédraogo","doi":"10.1109/MNE3SD53781.2022.9723420","DOIUrl":"https://doi.org/10.1109/MNE3SD53781.2022.9723420","url":null,"abstract":"This paper present the determination of the maximum penetration rate of the solar photovoltaic power plants production of the national interconnected electrical grid of Burkina Faso where several solar photovoltaic power plants in the upcoming years must be hosted. Since 2017, the first solar photovoltaic power plant has been inaugurated in its phase 1 with an installed capacity of 33 MWp, the total installed capacity should reach 50 MWp after the phase 2. Similar projected solar PV power plants should increase the national PV production over 100 MWp by 2022. This study analyzes the impacts of the solar power plants connected to the grid with different penetration rates. The solar power plants are primarily connected to the grid through medium voltage and high voltage busbars. The modeling and simulations have been carried using the software NEPLAN. With a penetration rate of 40%, the electrical grid reaches its optimal operation limits. This rate equals a power of 103.4 MW, overvoltage occur in busbars and overloads in transformers. Beyond this rate, important reinforcement works are requisite for a proper functioning.","PeriodicalId":355503,"journal":{"name":"2022 IEEE Multi-conference on Natural and Engineering Sciences for Sahel's Sustainable Development (MNE3SD)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131742877","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":"Multi-Linear LoRa network topology deployment with interference avoidance for white area monitoring","authors":"E. H. M. Ndoye, O. Diallo, N. Hakem","doi":"10.1109/MNE3SD53781.2022.9723369","DOIUrl":"https://doi.org/10.1109/MNE3SD53781.2022.9723369","url":null,"abstract":"The emergence of the Internet of Things (IoT) has given a new dimension for monitoring applications due in particular to new communication technologies such as LoRa/LoRaWAN. These innovations in the technology have driven the curiosity to use LoRa-based network in applications such as smart agriculture management and monitoring system, road tracks or railways monitoring, border monitoring, Oil and Gas, or even water pipeline supervision, etc. This kind of network is called linear network topology LoRa imposed by the linearity of monitored infrastructure. Some of the challenges faced in a linear network are mainly: interference management, energy efficiency and network lifetime increase.The main goal of this paper is to propose a Linear LoRa sensor network architecture for the monitoring of so-called white areas located on the southern Senegal in West Africa. The simplified architecture is composed by end device nodes and gateways communicating by LoRa radio links. The choice of such a physical topology is explained by the fairly complex nature of the node deployment environment, which is very rugged. The objective of this study is to find a better deployment of nodes to achieve a better coverage of infrastructure deployed in non-connected far areas.","PeriodicalId":355503,"journal":{"name":"2022 IEEE Multi-conference on Natural and Engineering Sciences for Sahel's Sustainable Development (MNE3SD)","volume":"91 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125166071","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}
P. B. Himbane, Georges Ambouor Diedhiou, L. Ndiaye
{"title":"Preliminary study of hot air generator: a measure of gas emissions and temperatures","authors":"P. B. Himbane, Georges Ambouor Diedhiou, L. Ndiaye","doi":"10.1109/MNE3SD53781.2022.9723351","DOIUrl":"https://doi.org/10.1109/MNE3SD53781.2022.9723351","url":null,"abstract":"Combustion tests were conducted with peanut shells and biochar briquettes of peanut shells to examine emissions gas and air temperature at the outlet of a heat exchanger, in an indirect hot air generator. Gas emissions were monitored using the RASI700Bio analyzer. Temperatures were recorded using Arduino data acquisition. For peanut shells five (05) kilograms were burned in the combustion chamber with an open door and closed door. Average emissions of CO and NOx were 1585.59 and 66.34 mg/m3, respectively for combustion with an open door. For combustion with a closed door, average emissions of CO were 12625.93 mg / m3 and those of NOx were 139.91 mg/m3. Air temperatures at the outlet of the heat exchanger were 98.25 and 122.25° C, respectively for combustion with an open door and closed door. For the biochar briquettes, five kilograms were also burned in the combustion chamber with an open door and closed door. Average emissions of CO and NOI were 1762.74 and 40.21 mg/m3, respectively for combustion with an open door. For combustion with a closed door, average emissions of CO were 1915.66 mg/m3 and for those of NOx, we obtained 62.02 mg/m3. Air temperatures at the outlet of the heat exchanger were 78.25 and 89.25°C, respectively for combustion with an open door and closed door. Combustion of the biochar briquettes produced higher CO and lower NOx emissions in the open door, compared to those of peanut shells. In closed-door, combustion of the biochar briquettes produced lower CO and lower NOx emissions, compared to those of peanut shells.","PeriodicalId":355503,"journal":{"name":"2022 IEEE Multi-conference on Natural and Engineering Sciences for Sahel's Sustainable Development (MNE3SD)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125598522","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}
I. B. Sani, I. Zakari, M. M. Idrissa, D. Abdourahimoun
{"title":"Machine Learning based Classification of Traffic Signs Images from a Robot-car","authors":"I. B. Sani, I. Zakari, M. M. Idrissa, D. Abdourahimoun","doi":"10.1109/MNE3SD53781.2022.9723100","DOIUrl":"https://doi.org/10.1109/MNE3SD53781.2022.9723100","url":null,"abstract":"In this paper we analyzed the performance of some machine learning techniques in order to create a robust model for an application to a robot car traffic on a road model. The techniques evaluated support vector machines and convolutional neural networks. Several classifiers from these techniques were tested on 3000 images of traffic signs that were collected from an application environment under different lighting conditions. In addition, other images were collected outside the road model and others on the web for a better robustness analysis of the different classifiers.Our experimental results suggest that the Convolutional Neural Network (CNN) model is more accurate than that of the Support Vector Machine (SVM). But CNN has an implementation difficulty compared to SVM. In addition, the use of CNN seems to be a complex task due to the fairly high response time.","PeriodicalId":355503,"journal":{"name":"2022 IEEE Multi-conference on Natural and Engineering Sciences for Sahel's Sustainable Development (MNE3SD)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129109976","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":"Determination and comparison of combustion kinetics parameters of peanut shells, cashew nut shells, palm nut shells, and millet stem","authors":"Ba Mamadou Seydou, P. B. Himbane, L. Ndiaye","doi":"10.1109/MNE3SD53781.2022.9723216","DOIUrl":"https://doi.org/10.1109/MNE3SD53781.2022.9723216","url":null,"abstract":"The energetic valorization of agricultural or forest residues, allows us to preserve, our ecosystem under the threat of the disappearance of certain vegetable species, to the abusive cutting of wood. The study carried out on this paper consists in making a kinetic of thermal decomposition of the coproducts: peanut shells (PNS), cashew nut shells (CNS), palm nut shells (PLS), and millet stems (MS) coming from the natural region of Casamance. Thermogravimetric analysis at three heating rates of 5°C.min-1, 10°C.min-1 and 20°C.min-1 under pure air up to $800^{circ}mathrm{C}$ was necessary to conduct our kinetic study. This thermal degradation of our samples allowed deconvolution by the Fraser-Suzuki method, which assumes that decomposition occurs independently for each pseudo-component (hemicelluloses, cellulose, and lignin). Friedmann (Fri), Kissinger-Akahira-Sunose (KAS), and Flynn-Wall-Ozawa (FWO) methods were to determine the activation energy of the three pseudo-components of our studied coproducts. The average activation energy being the energy required to decompose a material, was higher than for cellulose for all four coproducts. The latter varies from 116,30 MJ.mol-1, 87,84116,30 $mathrm{M}mathrm{J}.mathrm{m}mathrm{ol}^{-1}$; 209,55 MJ.mol-1 and 339,64 MJ.mol-1 for PNS, CNS, PLS and MS respectively.","PeriodicalId":355503,"journal":{"name":"2022 IEEE Multi-conference on Natural and Engineering Sciences for Sahel's Sustainable Development (MNE3SD)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125189271","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}