Journal of Theoretical and Applied Electronic Commerce Research
The risk of fraudulent activity has significantly increased with the rise in digital payments. To... more The risk of fraudulent activity has significantly increased with the rise in digital payments. To resolve this issue there is a need for reliable real-time fraud detection technologies. This research introduced an innovative method called stacked autoencoder kernel extreme learning machine optimized by the dandelion algorithm (S-AEKELM-DA) to detect fraudulent transactions. The primary objective was to enhance the kernel extreme learning machine (KELM) performance by integrating the dandelion technique into a stacked autoencoder kernel ELM architecture. This study aimed to improve the overall effectiveness of the proposed method in fraud detection by optimizing the regularization parameter (c) and the kernel parameter (σ). To evaluate the S-AEKELM-DA approach; simulations and experiments were conducted using four credit card datasets. The results demonstrated remarkable performance, with our method achieving high accuracy, recall, precision, and F1-score in real time for detecting f...
Electric vehicles (EVs) are a sustainable transportation solution with environmental benefits and... more Electric vehicles (EVs) are a sustainable transportation solution with environmental benefits and energy efficiency. However, their popularity has raised challenges in locating appropriate charging stations, especially in cities with limited infrastructure and dynamic charging demands. To address this, we propose a multi-agent deep deterministic policy gradient (MADDPG) method for optimal EV charging station recommendations, considering real-time traffic conditions. Our approach aims to minimize total travel time in a stochastic environment for efficient smart transportation management. We adopt a centralized learning and decentralized execution strategy, treating each region of charging stations as an individual agent. Agents cooperate to recommend optimal charging stations based on various incentive functions and competitive contexts. The problem is modeled as a Markov game, suitable for analyzing multi-agent decisions in stochastic environments. Intelligent transportation systems...
Indonesian Journal of Electrical Engineering and Computer Science
Environmental challenges such as climate change have accelerated humanity's need for renewabl... more 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 ...
International Journal of Electrical and Computer Engineering (IJECE)
Accident black spots are usually defined as road locations with a high risk of fatal accidents. A... more 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 an...
Self-driving vehicles need a robust positioning system to continue the revolution in intelligent ... more Self-driving vehicles need a robust positioning system to continue the revolution in intelligent transportation. Global navigation satellite systems (GNSS) are most commonly used to accomplish this task because of their ability to accurately locate the vehicle in the environment. However, recent publications have revealed serious cases where GNSS fails miserably to determine the position of the vehicle, for example, under a bridge, in a tunnel, or in dense forests. In this work, we propose a framework architecture of explaining deep learning LiDAR-based (XDLL) models that predicts the position of the vehicles by using only a few LiDAR points in the environment, which ensures the required fastness and accuracy of interactions between vehicle components. The proposed framework extracts non-semantic features from LiDAR scans using a clustering algorithm. The identified clusters serve as input to our deep learning model, which relies on LSTM and GRU layers to store the trajectory points...
With the development of autonomous vehicles, localization and mapping technologies have become cr... more With the development of autonomous vehicles, localization and mapping technologies have become crucial to equip the vehicle with the appropriate knowledge for its operation. In this paper, we extend our previous work by prepossessing a localization and mapping architecture for autonomous vehicles that do not rely on GPS, particularly in environments such as tunnels, under bridges, urban canyons, and dense tree canopies. The proposed approach is of two parts. Firstly, a K-means algorithm is employed to extract features from LiDAR scenes to create a local map of each scan. Then, we concatenate the local maps to create a global map of the environment and facilitate data association between frames. Secondly, the main localization task is performed by an adaptive particle filter that works in four steps: (a) generation of particles around an initial state (provided by the GPS); (b) updating the particle positions by providing the motion (translation and rotation) of the vehicle using an ...
International Journal of Advanced Computer Science and Applications
Recommendation systems aim at providing the user with large information that will be user-friendl... more Recommendation systems aim at providing the user with large information that will be user-friendly. They are techniques based on the individual's contribution in rating the items. The main principle of recommendation systems is that it is useful for user's sharing the same interests. Furthermore, collaborative filtering is a widely used technique for creating recommender systems, and it has been successfully applied in many programs. However, collaborative filtering faces multiple issues that affect the recommended accuracy, including data sparsity and cold start, which is caused by the lack of the user's feedback. To address these issues, a new method called "GlotMF" has been suggested to enhance the collaborative filtering method of recommendation accuracy. Trust-based social networks are also used by modelling the user's preferences and using different user's situations. The experimental results based on real data sets show that the proposed method performs better result compared to trust-based recommendation approaches, in terms of prediction accuracy.
International Journal of Electrical and Computer Engineering (IJECE)
In a stand-alone system, the use of renewable energies, load changes, and interruptions to transm... more In a stand-alone system, the use of renewable energies, load changes, and interruptions to transmission lines can cause voltage drops, impacting its reliability. A way to offset a change in the nature of hybrid renewable energy immediately is to utilize energy storage without needing to turn on other plants. Photovoltaic panels, a wind turbine, and a wallbox unit (responsible for providing the vehicle’s electrical need) are the components of the proposed system; in addition to being a power source, batteries also serve as a storage unit. Taking advantage of deep learning, particularly convolutional neural networks, and this new system will take advantage of recent advances in machine learning. By employing algorithms for deep Q-learning, the agent learns from the data of the various elements of the system to create the optimal policy for enhancing performance. To increase the learning efficiency, the reward function is implemented using a fuzzy Mamdani system. Our proposed experimen...
Extreme Learning Machine Based Multi-Agent System for Microgrid Energy Management
Advances in Intelligent Systems and Computing, 2019
In this paper, an intelligent energy management system is presented for distributed structure lik... more In this paper, an intelligent energy management system is presented for distributed structure like a smart microgrid. To model the microgrid, a Multi-Agent System is proposed based on Extreme Learning Machine algorithm to estimate the wind and photovoltaic power output from weather data. In this study a microgrid, with different generation units and storage units is considered. Provision of utility grid insertion is also given if the total energy produced by microgrid falls short of supplying the total load or if there is an excess of energy produced instead of to be wasted. Thus the goal of our Multi-Agent System is to control the amount of power delivered or taken from the main grid in order to reduce the electricity bill and make profit by selling the surplus in the energy market. After supplying the load requirements, Extreme Learning Machine algorithm for classification is used to make decision about selling/purchasing electricity from the main grid, and charging/discharging batteries. Finally for simulation, the Java Agent Development Framework platform is used to implement the approach and analyze the results.
Hybrid strategy based on MAS for an intelligent energy management: Application to an electric vehicle
2017 Intelligent Systems and Computer Vision (ISCV), 2017
This article proposes a multi-agent approach for managing electric vehicle energy. The vehicle po... more This article proposes a multi-agent approach for managing electric vehicle energy. The vehicle power source consists of a Lithium Metal Polymer (LMP) battery and a Super-capacitor. The adopted management strategy is a hybrid strategy, based on three techniques of artificial intelligence, on the fuzzy logic and the genetic algorithms on one hand, on the other hand, on the multi-agent systems. These main methods were combined in the developed system to carry out the management task. The fuzzy inference system is first optimized off-line by the genetic algorithm. Then it is used during on-line checking to take into account the uncertain case. The architecture of our system is based on the agents, they have been applied to distribute the control tasks and locate accordingly the command of the components of the hybrid electrical source. During the simulation tests (on the New European Driving Cycle NEDC) we succeeded, due to the results, to achieve the objective of this work; indeed the system works effectively with the used method. Thus, the hybrid strategy is operational, and it realizes an important sheath in terms of energy, that is to say a longer autonomy of electric vehicle.
Road traffic mortality in Morocco: Analysis of statistical data
2020 International Conference on Intelligent Systems and Computer Vision (ISCV), 2020
Over the last decade, around 3500 people lost their lives in road accidents each year in Morocco.... more Over the last decade, around 3500 people lost their lives in road accidents each year in Morocco. Between 2008 and 2017, the number of accidents has seen an increase of 38.11%. Several factors may contribute to the so-called “war on the roads”, such as the behavior of drivers or vehicle condition. Since human behavior is not always the leading cause of traffic crashes, in this work, we propose to study the effect of the environment and road conditions on accident mortality. The study is based on statistical data of accidents that caused death or bodily injuries in Morocco in 2017. The Case Fatality Rate (CFR) indicator was used to measure the severity of accidents, and the technique involved is the well-known non-parametric Analysis of Variance (ANOVA). Thirteen factors were taken into account to describe the state of the infrastructure and the physical conditions of roads. The analysis results show that the factors studied have a significant effect on accident fatality. More specifically, the type of intersection and the location proved to be the variables that contribute more to accident fatality.
The decision trees and the optimization of resources in Big Data solutions
2020 Fourth International Conference On Intelligent Computing in Data Sciences (ICDS), 2020
every day, we see that a quantitative explosion of digital data has forced researchers to find ne... more every day, we see that a quantitative explosion of digital data has forced researchers to find new strategies to collect, store, analyze and visualize data. In the context of storage and processing of a large massive amount of data we find a lack of powerful tools to master and control them. Also, during the process of executing tasks in real time in clustered IT platforms, we encounter the problem of optimizing parallel tasks. So we will propose in this article a method based on the algorithm of decision trees as an interpretable machine learning algorithm which can allow us to evaluate the impact of certain characteristics on the variable of the task execution time. This decision tree algorithm is useful and it helps us understand how we can optimize the different parameters that affect workloads in clustered applications. We can thus optimize the number of tasks in Big Data clustered applications without failure and performance degradation.
Hybrid spam is an undesirable e-mail (electronic mail) that contains both image and text parts. I... more Hybrid spam is an undesirable e-mail (electronic mail) that contains both image and text parts. It is more harmful and complex as compared to image-based and text-based spam e-mail. Thus, an efficient and intelligent approach is required to distinguish between spam and ham. To our knowledge, a small number of studies have been aimed at detecting hybrid spam e-mails. Most of these multimodal architectures adopted the decision-level fusion method, whereby the classification scores of each modality were concatenated and fed to another classification model to make a final decision. Unfortunately, this method not only demands many learning steps, but it also loses correlation in mixed feature space. In this paper, we propose a deep multimodal feature-level fusion architecture that concatenates two embedding vectors to have a strong representation of e-mails and increase the performance of the classification. The paragraph vector distributed bag of words (PV-DBOW) and the convolutional ne...
An autonomous vehicular system based on muli-agents control: Architecture and behavior simulation
2017 Intelligent Systems and Computer Vision (ISCV), 2017
Since the 21st century, vehicles have attracted a great interest due to their potential applicati... more Since the 21st century, vehicles have attracted a great interest due to their potential applications for transportation of people and goods. The initial concerns of industries and researchers were that radio-equipped vehicles are able to keep the drivers informed about risks and road conditions. However, recent researches focuses more on providing the drivers with more comfort an less effort. For instance, air-conditioning, automatic features, GPS, etc, insure the quality of service (QoS) for the users. Moreover, the researches are still in advance to promote more autonomy and dynamic to the vehicle. In this paper, we present an autonomous vehicular system based on multi-agents to reduce the complexity of the autonomous system. In fact, instead of executing several tasks by one process, we split them between different agents. Therefore, this complexity reduction reduces the execution time and provide a quick intervention in complex scenarios. Furthermore, our multi-agent system can ...
A Study of Energy Reduction Strategies in Renewable Hybrid Grid
Artificial Intelligence and Industrial Applications, 2020
Hybrid renewable energy systems (HRES) have been introduced to overcome intermittent nature of si... more Hybrid renewable energy systems (HRES) have been introduced to overcome intermittent nature of single source renewable energy generation. In order to utilize HRES optimally, two issues must be considered: optimal sizing and optimal operation. The first issue has been considered vastly in several articles but the second one needs more attention and work. The performance of hybrid renewable energy systems highly depends on how efficient the control of energy production is. This paper presents a comparative analysis of Multi-agent-system and Fuzzy Logic Controller based control strategies. The proposed system consists of photovoltaic panels and a wind turbine along with batteries as storage units. The comparison between two control strategies is analyzed and it is clear that MAS-based control system provides dynamic response and has higher efficiency than the FLC-based control technique. MAS-based system provides robustness toward the nonlinearity of the system. The current harmonics, unbalance current and the load reactive power are compensated effectively using the combination of MAS control strategy. The system was tested with empty batteries and full batteries and results showed that the system could satisfy the load demand while maintaining the level of the batteries between 30% (minimum discharging rate) and 80% (maximum charging rate).
A new model for black spots identification using Weighted Severity Index
2021 Fifth International Conference On Intelligent Computing in Data Sciences (ICDS), 2021
In Morocco, road accidents kill about 3,500 people and cause about 100,000 injuries each year. Be... more In Morocco, road accidents kill about 3,500 people and cause about 100,000 injuries each year. Between 2009 and 2019, the number of accidents has seen an increase of 53.43%. Identification of road black spots is an important task in the process of road safety and plays a vital role in reducing the number of accidents. Indeed, among the various techniques used for treating this issue is the weighted severity index method. It combines accident casualties by weighting each of them with a specific score. For this purpose, we use three ensemble methods, which are capable of attributing importance scores to model features (accident casualties). This paper shows the possibility of combining feature importance tool of XGBoost with Weighted Severity Index method in order to improve identification of accident Black Spots. The analysis of 1584 sections on rural roads in Morocco shows that 173 areas are classified as black spots. Our approach turned out to be efficient in identifying locations with high risk of accidents. In consequence, road sector stakeholders in the country may consider these results with the aim of improving the road safety in the future.
Uploads
Papers by Ali Yahyaouy