INAS Bouzateur

User profile picture

INAS Bouzateur

بوزعتر إناس

inas.bouzateur@univ-msila.dz

0797713118

  • Departement of ELECTRONICS
  • Faculty of Technology
  • Grade PHd
Send Mail

About Me

Education

PHD Student. in Universitie Mohamed Boudiaf de Msila

Location

Msila, Msila

Msila, ALGERIA

  • 2023-12-25
  • 2023-12-25

    Predicting Lattice Constant for Complex Cubic Peroveskite X2YY’O6 using LSTM machine learning method

    Double perovskite oxides have drawn a lot of attention in the last ten years due to their unique and flexible material characteristics. The lattice constant is the only variable among the six parameters that make up the cubic structure, is crucial for the development of materials for specific technological applications and clearly identifies the crystal structure of the material. In this paper, Long short-term memory (LSTM) method is used to correlate the lattice constant of X2+2YY′O6 cubic perovskite compounds with their physico chemical properties, such as ionic radii, electronegativity and oxidation state, in the aim of predict new cubic peroveskites compounds lattice constant’s with higher accuracy . We investigated 147 compounds with their lattice constants between 7.700 Å and 8.890Å.On the basis of root mean square error (RMSE), mean absolute error (MAE) and the coefficient of determination (R2 ), the proposed LSTM model is compared with existing model of Sandra et al . on the basis of RMSE and MAE. The proposed LSTM model performs better than Sandra et al models, with performance improvement of 14% and 22% ,respectively . As a result, our prediction method has a high level of accuracy and stability and provides accurate prediction of lattice constants.

    Citation

    Inas bouzateur , ,(2023-12-25), Predicting Lattice Constant for Complex Cubic Peroveskite X2YY’O6 using LSTM machine learning method,3rd International Conference on Scientific and Academic Research,Konya/Turkey.

    See publication
  • 2023-12-25
  • 2023-12-25

    Predicting Lattice Constant for Complex Cubic Perovskite X2YY’O6 using LSTM machine learning method.

    Predicting Lattice Constant for Complex Cubic Perovskite X2YY’O6 using LSTM machine learning method.

    Citation

    Hamza BENNACER , MOHAMMED ASSAM Ouali , Inas bouzateur , ,(2023-12-25), Predicting Lattice Constant for Complex Cubic Perovskite X2YY’O6 using LSTM machine learning method.,3rd International Conference on Scientific and Academic Research.,Konya/Turkey.

    See publication
  • 2023-09-04
  • 2023-09-04

    Perovskite lattice constant prediction framework using optimized artificial neural network and fuzzy logic models by metaheuristic algorithms

    Perovskites have gained significant attention in recent years due to their unique and versatile material properties. The lattice parameters of the perovskite compounds play a crucial role in the engineering of layers and substrates for heteroepitaxial thin films. As an essential parameter in the cubic perovskite structure, the lattice constant, plays a significant role in the development of materials for specific technological applications and serves as a distinctive identifier of the crystal structure of the material. In the field of materials science, advanced Computational Intelligence (CI)-based techniques have become increasingly important for simulating the relationship between the physicochemical parameters of chemical elements and the physical properties of materials and compounds. Hence, this paper presents efficient techniques based on artificial neural network (ANN) and fuzzy logic to predict the lattice constants of pseudo-cubic and cubic perovskites. The identification of optimized parameters for the ANN and fuzzy logic models is accomplished using innovative metaheuristic algorithms such as, Particle Swarm Optimization (PSO), Invasive Weed Optimization (IWO) and Imperialist Competitive Algorithm (ICA). In the first part, the study assessed, the effectiveness of various metaheuristic algorithms (PSO-IWO-ICA) in tuning the parameters of the ANN prediction structure in order to get the optimal parameter of the ANN. Whereas in the second part, once we extracted the best optimization algorithm, we combined it with the fuzzy logic technique and then we compared the effectiveness of the two techniques, ANN and Fuzzy logic. On the basis of root mean square error (RMSE), mean absolute error (MAE) and the coefficient of determination (R2), the proposed PSO-ANN and PSO-Fuzzy based models are compared with existing and recent models such as Ubic, Sidey, and Owolabi. The proposed PSO-Fuzzy model performs better than our PSO-ANN model, the Ubic, Sidey, and Owolabi models, with performance improvement of 70.90%, 90.36%, 89.74% 84.46%, respectively on the basis of RMSE. Similarly, it attains performance improvement of 71.26%, 90.31%, 89.58%, and 85.02% on the basis of MAE. Furthermore, the developed PSO-ANN based model outperforms the Ubic, Sidey and Owolabi models with performance improvement of 66.86%, 64.74% and 46.60% respectively, on the basis of RMSE and percentage enhancement of 66.27%, 63.75%, and 47.90% when compared on the basis of MAE. Although the PSO-Fuzzy model has the best performance of all the compared models, the developed PSO-ANN based model possesses the advantage of easy implementation in addition to its moderate performance.

    Citation

    Hamza BENNACER , MOHAMMED ASSAM Ouali , Inas bouzateur , , (2023-09-04), Perovskite lattice constant prediction framework using optimized artificial neural network and fuzzy logic models by metaheuristic algorithms, Materials today communications, Vol:37, Issue:, pages:107021, Elsevier

    See publication
  • 2023-07-12
  • 2023-07-12

    New Materials for Solid Oxide Fuel Cells with Dual ion-conducting Electrolyte

    Solid oxide fuel cells (SOFCs) have emerged as a promising and efficient technology for clean energy conversion. The performance of SOFCs relies on the electrolyte, which is responsible for transporting oxygen ions within the cell. However, traditional SOFC electrolytes are limited by their single ion-conducting nature, affecting overall performance and stability.Recently, there has been increasing interest in developing new materials with dual ion-conducting electrolytes to enhance SOFC performance. These electrolytes enable the simultaneous transport of both oxygen ions and protonic species, offering significant advantages over single ion-conducting systems.This abstract provides an overview of recent advancements in the field of dual ion-conducting electrolytes for SOFCs, focusing on novel materials and their synthesis methods. Various strategies, such as doping, nanostructuring, and composite approaches, are discussed for achieving dual ion conduction. The benefits of dual ion- conducting electrolytes, including improved electrode kinetics, reduced polarization losses, and enhanced tolerance to fuel impurities, are highlighted.Furthermore, the abstract addresses the challenges associated with designing, fabricating, and characterizing dual ion-conducting electrolytes. Emphasis is placed on optimizing the microstructure and ensuring interface compatibility in these materials. Finally, the potential applications and future directions of dual ion-conducting electrolytes in SOFC technology are discussed, emphasizing their role in advancing the performance and commercial viability of solid oxide fuel cells.

    Citation

    Inas bouzateur , ,(2023-07-12), New Materials for Solid Oxide Fuel Cells with Dual ion-conducting Electrolyte,5th International Conference on Applied Engineering and Natural Sciences,Konya/Turkey.

    See publication
  • 2023
  • 2023

    A Tunable band-stop plasmonic filter based on Metal-insulator-metal (MIM) waveguide

    The phenomenon known as surface plasmon polaritons (SPPs) has attracted much attention in the future nano-photonic systems. SPPs can overcome the traditional diffraction limit of lightwave and localization of light in subwavelength dimensions. The SPP waves are excited by the transverse magnetic (TM) mode inside the MIM structure. In this paper, a tunable band-stop plasmonic filter in infrared (IR) wavelength range is proposed. The designed filter composed of a MIM waveguide coupled with cavity resonator. The reflection characteristics of the filter obtained by the finite-difference time-domain (FDTD) method using R-Soft CAD commercial software with perfectly matched layers (PML). Moreover, the plasmonic filter can be achieved by tuning the parameter of cavity resonator and controlling and manipulating the shifts of the resonance wavelength of the peaks we archives. This structure so may have significant applications in highly integrated photonic circuits.

    Citation

    Inas bouzateur , i.zeggar@univ-boumerdes.dz, ,(2023), A Tunable band-stop plasmonic filter based on Metal-insulator-metal (MIM) waveguide,the National Seminar of Physics, Chemistry, and Their Applications Webinar (NSPCA'23),University Mohamed El Bachir El Ibrahimi of Bordj Bou Arreridj, Algeria.

    See publication
  • 2023
  • 2023

    A new ANN-PSO framework to chalcopyrite’s energy band gaps prediction

    The electronic band gap energy is an essential photo-electronic parameter in the energy applications of engineering materials, particularly in solar cells and photo-catalysis domains. A prediction model that can correctly predict this band gap energy is desirable. A new approach for predicting a band gap energy is suggested in this paper. The proposed structure is based on artificial neural networks (ANN) and the particle swarm optimization algorithm (PSO); this structure can solve the artificial neural network’s local minima issue while preserving the fitting quality. Our technique will hasten the identification of novel chalcopyrite in photovoltaic solar cells with improved resolution. The suggested model combines two sub-systems in a parallel configuration. A conventional prediction system with a low resolution for the training data being considered makes up the first ANN subsystem. A second ANN sub-system, labelled the error model, is introduced to the primary system to address the resolution quality issue, representing uncertainty in the primary model. The particle swarm optimization algorithm is used to identify the parameters of the proposed neural system. The method’s effectiveness is assessed in terms of several criteria, and the output of our system shows good performance compared to experimental and other calculated results. Several benchmark approaches were compared with the proposed system in detail. Numerous computer tests show that the suggested strategy can significantly enhance convergence and resolution.

    Citation

    Inas bouzateur , Hamza BENNACER , MOHAMMED ASSAM Ouali , Mohamed Ladjal , , (2023), A new ANN-PSO framework to chalcopyrite’s energy band gaps prediction, Materials Today Communications, Vol:34, Issue:105311, pages:11, Bouzateur inas

    See publication
  • 2022
  • 2022

    A New PSO-ANN Scheme for Composite materials Properties prediction

    In this investigation a novel PSO-ANN scheme for composite materials properties prediction is presented. It is based on neural networks which are used in many applications such as image recognition, classification, control and system identification.This approach will deal with local minima problem of the neuronal networks architecture and simultaneously preserve the fitting quality. The proposed scheme comprises a parallel interconnection of tow sub-ANN prediction systems. The first sub-ANN prediction system is the primary system, which represents an ordinary system with a low resolution for the training data under consideration (composite materials properties). To overcome resolution quality problem, and obtain a prediction system with higher resolution, we will introduce a second ANN sub model. ANN scheme Identification is achieved by innovative metaheuristic algorithm such asparticle swarm optimization (PSO). The method’s effectiveness is evaluated through testing on the composite materials to predict their physical properties. Intensive computer experimentations confirm that the proposed approach can significantly improve convergence and resolution.

    Citation

    Inas bouzateur , ,(2022), A New PSO-ANN Scheme for Composite materials Properties prediction,INTERNATIONAL SYMPOSIUM ON APPLIED MATHEMATICS AND ENGINEERIN,Biruni University Istanbul-Turkey

    See publication
  • 2022
  • 2022

    Lattice Constant Prediction of Complex Cubic Peroveskite A2BCO6 using Extreme Learning Machine

    Double perovskite oxides have received a lot of interest in the last ten years because of their distinctive and adaptable material properties. Among the six parameters in the cubic structure, the lattice constant is the sole changeable parameter, which plays an important role in developing materials for particular technological applications and distinctively identifies the crystal structure of the material. In this paper, the extreme learning machine (ELM) is used to correlate the lattice constant of A_2^(+2) BCO_6 cubic perovskite compounds, such as their ionic radii, electronegativity, oxidation state, and lattice constant. We investigated 147 compounds with lattice constants between 7.700 and 8.890Å. The prediction method has a high level of accuracy and stability and provides accurate estimates of lattice constants.

    Citation

    Hamza BENNACER , MOHAMMED ASSAM Ouali , Mohamed Ladjal , Moufdi Hadjab , Inas bouzateur , ,(2022), Lattice Constant Prediction of Complex Cubic Peroveskite A2BCO6 using Extreme Learning Machine,International Conference of advanced Technology in Electronic and Electrical Engineering (ICATEEE),Msila, Algeria

    See publication
  • 2022
  • 2022

    ab-initio and artificial intelligence based methods for physical properties

    presentation oral

    Citation

    Inas bouzateur , ,(2022), ab-initio and artificial intelligence based methods for physical properties,journey doctoral,University of Mohamed Boudiaf of Msila-Algeria

    See publication