Ali Yahyaouy
Sidi Mohamed Ben Abdellah University

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

Black spots identification on rural roads based on extreme learning machine Abdelilah Mbarek; Mouna Jiber; Ali Yahyaouy; Abdelouahed Sabri
International Journal of Electrical and Computer Engineering (IJECE) Vol 13, No 3: June 2023
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijece.v13i3.pp3149-3160

Abstract

Accident black spots are usually defined as road locations with a high risk of fatal accidents. A thorough analysis of these areas is essential to determine the real causes of mortality due to these accidents and can thus help anticipate the necessary decisions to be made to mitigate their effects. In this context, this study aims to develop a model for the identification, classification and analysis of black spots on roads in Morocco. These areas are first identified using extreme learning machine (ELM) algorithm, and then the infrastructure factors are analyzed by ordinal regression. The XGBoost model is adopted for weighted severity index (WSI) generation, which in turn generates the severity scores to be assigned to individual road segments. The latter are then classified into four classes by using a categorization approach (high, medium, low and safe). Finally, the bagging extreme learning machine is used to classify the severity of road segments according to infrastructures and environmental factors. Simulation results show that the proposed framework accurately and efficiently identified the black spots and outperformed the reputable competing models, especially in terms of accuracy 98.6%. In conclusion, the ordinal analysis revealed that pavement width, road curve type, shoulder width and position were the significant factors contributing to accidents on rural roads.
A novel decision-making approach based on a decision tree for micro-grid energy management Ibtissame Mansoury; Dounia El Bourakadi; Ali Yahyaouy; Jaouad Boumhidi
Indonesian Journal of Electrical Engineering and Computer Science Vol 30, No 2: May 2023
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v30.i2.pp1150-1158

Abstract

Environmental challenges such as climate change have accelerated humanity's need for renewable alternative energy sources. For this reason, we propose in this paper a decision-making strategy that allows controlling the flows of energy into a micro-grid (MG) compound of solar energy, batteries, and diesel generator (DG), and connected to the distributed network (DN). Therefore, the power supply to the loads is obtained either from the energy produced by solar sources, from the batteries, from the DN, or from the DG when renewable energy (RE) and batteries are depleted. To make the final decision, we consider four parameters at the same time: the energy produced by solar energy, the requested load, the state of charge of batteries (SoC), and the purchase or sale price. Decision tree (DT) is used to build the energy management strategy to ensure the availability of power on demand by making logical decisions about charging batteries, discharging batteries, buying necessary energy from DN, selling excess energy to DN, and recovering necessary energy from DG. The suggested DT approach is applied to a real MG to minimize the cost-benefit balance, and the comparison analysis demonstrates good results when compared to related works.