Chaotic System Modelling Using a Neural Network with Optimized Structure

Lamamra, Kheireddine; Vaidyanathan, Sundarapandian; Azar, Ahmad Taher; Salah, Chokri Ben

doi:10.1007/978-3-319-50249-6_29

Cited by 10 publications

(4 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Machine Learning techniques, especially unsupervised algorithms, have been broadly adopted to generate response surfaces because they have the power to model rough surfaces without requiring much prior knowledge of the target surface. Neural networks are nowadays undoubtedly the most widespread approach for such task, presenting impressive results on extremely challenging scenarios, such as chaotic systems (Lamamra et al 2017) and processes strongly governed by differential equations (Meng et al 2020). They are not a panacea, though.…”

Section: 24mentioning

confidence: 99%

Equation-Based Versus Agent-Based Models: Why Not Embrace Both for an Efficient Parameter Calibration?

Avegliano,

Sichman

2023

JASSS

View full text Add to dashboard Cite

In this work, we propose 2LevelCalibration, a multi-stage approach for the calibration of unknown parameters of agent-based models. First, we detail the aspects of agent-based models that make this task so cumbersome. Then, we conduct extensive research on common methods applied for this purpose in other domains, highlighting the strong points of each approach that could be explored to efficiently calibrate the parameters of agent-based models. Finally, we present a multi-stage method for this task, 2LevelCalibration, which benefits from the simplicity of equation-based models, used to faster explore a large set of possible combinations of parameters and to quickly select the more promising ones. These values are then analysed more carefully in the second step of our method, which performs the calibration of the agent-based model parameters' near the region of the search space that potentially contains the best set of parameters, previously identified in our method. This strategy outperformed traditional techniques when tested to calibrate the parameters of an agent-based model to replicate real-world observations of the housing market. With this testbed, we show that our method has highly desirable characteristics such as lightweight implementation and consistency, which are ideal for agent-based models' development process.

show abstract

Section: 24mentioning

confidence: 99%

Equation-Based Versus Agent-Based Models: Why Not Embrace Both for an Efficient Parameter Calibration?

Avegliano,

Sichman

2023

JASSS

View full text Add to dashboard Cite

show abstract

“…It focuses on the process that governs how the components and system change over time. In the literature, there are many applications of dynamic modeling in machine learning, deep learning, computational intelligence, control systems, robotics, sensor network and cyber-security (Ben Smida et al, 2018;Lamamra et al, 2017;Grassi et al, 2017;Mohanty et al, 2021 ;Ghoudelbourk et al, 2022Ghoudelbourk et al, , 2021Ghoudelbourk et al, , 2016Mekki et al, 2015;Dudekula et al, 2023 ;Hussain et al, 2023 ;El-Shorbagy et al, 2023 ;Ramadan et al, 2022 ;Ashfaq et al, 2022a,b;Waleed et al, 2022 ;Jothi et al, 2022Jothi et al, , 2020Jothi et al, , 2019Jothi et al, , 2013Lavanya et al, 2022 ;Inbarani et al, , 2018Inbarani et al, , 2014Inbarani et al, , 2015Boulmaiz et al, 2022 ;Fouad et al, 2021 ;Elfouly et al, 2021 ;Khan et al, 2021 ;Aslam et al, 2021 ;Nasser et al, 2021 ;Hussien et al, 2020 ;Kumar et al, 2019Kumar et al, , 2015aMjahed et al, 2020 ;Banu et al, 2017 ;Ben Abdallah et al, 2016Emary et al, 2014a,b;Anter et al, 2015Anter et al, , 2013Elshazly et al, 2013a,b ;Azar et al, 2013…”

Section: Modeling Of the Suggested Approachmentioning

confidence: 99%

A Design and Implementation of a New Control Based on Petri Nets for Three Phase PWM-Rectifier

Fekik

Hamida

Kais

et al. 2023

International Journal of Service Science, Management, Engineering, and Technology

View full text Add to dashboard Cite

This article introduces a novel and effective diagram based on direct instantaneous power control (DPC) of a PWM-controlled rectifier connected to the grid without a switching table. An optimum control vector of the PWM rectifier's input voltage, which depends on the switching states determined by a Petri nets controller, is adopted. This approach limits the instantaneous detection errors of reactive and active powers, maintains the DC bus voltage at a reference level, and ensures current close to a sinusoidal wave, guaranteeing operation at a unit power factor. The instantaneous tracking errors of active and reactive powers and the angular position of the voltage are used as input variables for the proposed controller, which then selects the best control vector for the converter based on the transition of a Petri net. The significant advantages of DPC based on Petri nets compared to traditional switching tables are that hysteresis comparators are not required, and the classical regulation of active and reactive powers is achieved in all sectors. Simulation and testing findings demonstrated excellent performance, supporting the viability of the suggested control approach using Petri nets.

show abstract

“…Several inspiring approaches, such as optimal control, nonlinear feedback control, adaptive control, sliding mode control, nonlinear dynamics, chaos control, chaos synchronization control, fuzzy logic control, fuzzy adaptive control, fractional order control, and robust control, as well as their integrations, have been proposed (Fekik et al, 2022(Fekik et al, . 2021a(Fekik et al, ,b,c, 2020a(Fekik et al, , 2019(Fekik et al, , 2018aDaraz et al, 2021;Pilla et al, 2021a;Abdul-Adheem et al, 2021Liu et al, 2020;Bouchemha et al, 2021;Gorripotu et al, 2021;Drhorhi et al, 2021 ;Alimi et al, 2021 ;Kumar et al, 2021 ;Acharyulu et al, 2021;Hamiche et al, 2021;Mittal et al, 2021;Pham et al, 2021Pham et al, , 2018Pham et al, , 2017aSambas et al, 2021a,b;Khan et al, 2020a,b;Khennaoui et al, 2020a,b;Kammogne et al, 2020;Alain et al, 2020Alain et al, , 2019Alain et al, , 2018Ouannas et al, 2021Ouannas et al, , 2020aOuannas et al, ,b,c,d,e,f, 2019aOuannas et al, ,b,c, 2017aOuannas et al, ,b,c,d,e,f,g,h,i,j,k, 2016Ammar et al, 2019;Radwan et al, 2018;Meghni et al, 2017aMeghni et al, ,b, 2018Singh et al, 2018aSingh et al, ,b,c, 2017Ben Smida et al, 2018;Lamamra et ...…”

Section: Design Of the Proposed Controlmentioning

confidence: 99%

Real-Time Fuzzy-PID for Mobile Robot Control and Vision-Based Obstacle Avoidance

Saidi¹,

Mellah²,

Fekik

et al. 2022

International Journal of Service Science, Management, Engineering, and Technology

Self Cite

View full text Add to dashboard Cite

In this work, the differential mobile robot is controlled utilizing fuzzy PID speed control, which combines fuzzy control with conventional PID control in real time. The path may be convoluted, and the surrounding environment may contain a range of arbitrary shape and size obstacles. A monocular camera is used to detect obstacles during the navigation process. To enable a robot to travel within an indoor space while avoiding obstacles, a basic image processing approach based on area of interest was used. The goal of this research is to develop a fuzzy PID speed controller on a real robot, as well as a simple and efficient visual obstacle avoidance system. MATLAB is used to implement the control system. GUIDE (graphical user interface development environment) has enabled the creation of graphical user interfaces. These interfaces make it easy to manipulate the system in real time and capture live video. The proposed methodologies are tested on a non-holonomic dr robot i90 mobile robot, and the results are satisfactory.

show abstract

Chaotic System Modelling Using a Neural Network with Optimized Structure

Cited by 10 publications

References 59 publications

Equation-Based Versus Agent-Based Models: Why Not Embrace Both for an Efficient Parameter Calibration?

Equation-Based Versus Agent-Based Models: Why Not Embrace Both for an Efficient Parameter Calibration?

A Design and Implementation of a New Control Based on Petri Nets for Three Phase PWM-Rectifier

Real-Time Fuzzy-PID for Mobile Robot Control and Vision-Based Obstacle Avoidance

Contact Info

Product

Resources

About