Haitham Al Ajmi

Sultan Qaboos University

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Trends

Author Order

Document Type

Co-Authors

Mohammed M. Bait‐Suwailam

Sultan Qaboos University

Lazhar Khriji

Sultan Qaboos University

Hassan Al-Lawati

Sultan Qaboos University

Muhammad Shafiq

Sultan Qaboos University

Mahmoud Masoud

King Fahd University of Petroleum and Minerals

Cooperative Institutions

Sultan Qaboos University

Muscat College

University of Sheffield

Sultan Qaboos University Hospital

King Faisal Specialist Hospital & Research Centre

United Arab Emirates University

Curtin University

Northumbria University

Sir Syed University of Engineering and Technology

Jacobs (United Kingdom)

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Field

Prediction Enhancement of Metasurface Absorber Design Using Adaptive Cascaded Deep Learning (ACDL) Model

Electronics (2024)

Haitham Al Ajmi Mohammed M. Bait‐Suwailam Lazhar Khriji Hassan Al-Lawati

This paper presents a customized adaptive cascaded deep learning (ACDL) model for the design and performance prediction of metasurface absorbers. A multi-resonant metasurface absorber structure is introduced, with 10 target-driven design parameters. The proposed deep learning model takes advantage of cascading several sub-deep neural network (DNN) layers with forward noise mitigation capabilities. The inherent appearance of sparse data is dealt with in this work by proposing a trained data-adaptive selection technique. On the basis of the findings, the prediction response is quite fast and accurate enough to retrieve the design parameters of the studied metasurface absorber with two patches of 4000- and 7000-sample datasets. The training loss taken from the second DNN of our proposed model showed logarithmic mean squared errors of 0.039 and 0.033 when using Keras and the adaptive method, respectively, with a dataset split of 4000. On the contrary, for a dataset split of 7000, the errors were 0.049 with Keras and 0.045 with the adaptive method. On the other hand, the validation loss was evaluated using the mean square error method, which resulted in a loss of 0.044 with the 4000-sample datasets split with the Keras method, while this was 0.020 with the adaptive method. When extending the dataset to 7000 samples, the validation loss with the Keras splitting method was 0.0073, while it was improved, reaching 0.006, with the proposed adaptive method, and achieved a prediction accuracy of 94%. This proposed deep learning model can be deployed in the design process and synthesis of multi-resonant metasurface absorber structures. The proposed model shows the advantages of making the design process more efficient in sparse dataset handling, being an efficient approach in multi-resonance metasurface data pre-processing, being less time consuming, and being computationally valuable.

10.3390/electronics13050822

Cite

Citations (2)

A Comparison Study of Deep Learning Algorithms for Metasurface Harvester Designs

Haitham Al Ajmi Mohammed M. Bait‐Suwailam Lazhar Khriji

The paper compares three deep learning artificial intelligence algorithms used for metasurface design. In-house design code for designing metasurface structures was developed with Python, the NumPy library. To facilitate the study, the three algorithms used are AdaBelief, Adam, and Yogi. According to the numerical comparison study, Adam has a better performance in terms of model generalization with a large dataset (in our case 7000 samples), while Adabelief and Yogi show a better performance in terms of a low dataset (in our case 4,000 samples), and Yogi has a better performance with a lower dataset correlation between the predicted performance of the energy harvester obtained from three algorithms. Yogi and Adablief performance could be improved by manipulating the hyper-parameters.

Python

10.1109/iccns58795.2023.10193585

Cite

Citations (2)

EFFICIENCY ENHANCEMENT OF PHOTOVOLTAIC SOLAR CELLS USING METAMATERIALS ABSORBING SCREEN

The Journal of Engineering Research [TJER] (2023)

Haitham Al Ajmi Mohammed M. Bait‐Suwailam Mahmoud Masoud Muhammad Shafiq

This paper proposes a novel technique for the efficiency enhancement of photovoltaic (PV) solar cells using metamaterials absorbing screens. This kind of engineered material comprises resonant metallic rings that are printed on a host low-loss dielectric substance and made periodic in a two-dimensional lattice. The absorbing screen has been carefully designed, and its retrieved effective constitutive parameters, effective electric permittivity ϵeff and effective magnetic permeability µeff, are integrated within a numerically modelled amorphous-Silicon-based PV solar cell structure as an impedance matching layer. Such arrangement will greatly achieve matching between the effective impedance of the composite solar cell structure and free-space impedance and will result in higher photons absorption through the metamaterials anti-reflective screen. Numerical full-wave electromagnetic simulations are carried out using CST Microwave Studio for the design of a metamaterial absorbing screen. Due to the large computational resources required, COMSOL Multiphysics was adopted in the design and analysis of the composite structure comprising a two-dimensional PV solar cells layer. Based on the numerical results, both optical and electric characteristics of the PV solar cell structure were enhanced with the use of a metamaterial layer. Moreover, efficiency enhancement by 5% was permissible, in which efficiency reached 12% with the use of metamaterials as compared to the efficiency of the classical PV cells of 7%. The obtained results are very promising, and the potential integration of metamaterials in commercial PV solar cells will show significant advancement in efficiency enhancement of PV cells and realization of smart PV solar cells with the consideration of additional features from metamaterials.

Multiphysics

10.53540/tjer.vol19iss2pp85-94

Cite

Citations (1)

Prediction Enhancement of Metasurface Absorbers Design Using Adaptive Cascaded Deep Learning (Acdl) Model

Haitham Al Ajmi Mohammed M. Bait‐Suwailam Lazhar Khriji Hassan Al-Lawati

This paper presents a customized adaptive cascaded deep learning (ACDL) model for the design and performance prediction of metasurface absorbers. A multi-resonant metasurface absorber structure is introduced, with 10 target-driven design parameters. The proposed deep learning model takes advantage of cascading several sub-deep neural network (DNN) layers with forward noise mitigation capability. The inherent appearance of sparse data is completely dealt with in this work by proposing a trained adaptive selection technique. On the basis of the findings, the prediction response is quite fast and accurate enough to retrieve the design parameters of the studied metasurface absorber and with two sized patches of 4000 and 7000 datasets. The training loss taken form the second DNN of our proposed model shows logarithmic mean squared errors of 0.039 and 0.033 when using Keras and the adaptive method, respectively, with a dataset split of 4000. On the contrary, for a dataset split of 7000, the errors are 0.049 with Keras and 0.045 with the adaptive method. On the other hand, the validation loss is evaluated using the mean square error method, which results in a loss with 4000 datasets split with the Keras method of 0.044, while it is 0.020 with the adaptive method. When extending the dataset to 7000, the validation loss with the keras splitting method is 0.0073, while it is improved, reaching 0.006 with the proposed adaptive method, and achieving a prediction accuracy of 94%. This proposed deep learning model can be deployed in the design process and synthesis of multi-resonant metasurface absorber structures. The proposed model shows its advantages of making the design process more efficient in sparse dataset handling, efficient approach in multi-resonance metasurface data pre-processing, less time consuming, and computationally valuable.

Deep Neural Networks

10.20944/preprints202401.0763.v1

Cite

Citations (0)

Multi-Band Electromagnetic Metasurface Absorber Design Using Concentric Split-Ring Resonators

2022 International Symposium on Networks, Computers and Communications (ISNCC) (2023)

Haitham Al Ajmi Mohammed M. Bait‐Suwailam

In this paper, we present a novel multi-band meta-surface absorber design for low-powered Internet of Things (IoT) devices. The absorber design is composed of concentric metallic split-ring resonators that collectively are able to absorb energy over multiple frequency bands, covering 2.5 GHz, 3.6 GHz, and 5 GHz bands. The metallic rings are etched from the top layer of the dielectric laminate and backed with a solid metallic ground layer. Based on the numerical simulation results, the electromagnetic harvester shows good performance, with absorption strength over 70% on average over the three bands and with an adequate performance as the angle of the incident is varied. The design can be fabricated using printed circuit board technology.

Split-ring resonator

10.1109/isncc58260.2023.10323928

Cite

Citations (0)