Shaymaa Alsamia

57218936191

Publications - 8

Flower fertilization optimization algorithm with application to adaptive controllers

Edina Koch Hazim Albedran Shaymaa Alsamia

Publication Name: Scientific Reports

Publication Date: 2025-12-01

Volume: 15

Issue: 1

Page Range: Unknown

Description:

This article presents the Flower Fertilization Optimization Algorithm (FFO), a novel bio-inspired optimization technique inspired by the natural fertilization process of flowering plants. The FFO emulates the behavior of pollen grains navigating through the search space to fertilize ovules, effectively balancing exploration and exploitation mechanisms. The developed FFO is theoretically introduced through the article and rigorously evaluated on a diverse set of 32 benchmark optimization problems, encompassing unimodal, multimodal, and fixed-dimension functions. The algorithm consistently outperformed 14 state-of-the-art metaheuristic algorithms, demonstrating superior accuracy, convergence speed, and robustness across all test cases. Also, exploitation, exploration, and parameter sensitivity analyses were performed to have a comprehensive understanding of the new algorithm. Additionally, FFO was applied to optimize the parameters of a Proportional-Integral-Derivative (PID) controller for magnetic train positioning—a complex and nonlinear control challenge. The FFO efficiently fine-tuned the PID gains, enhancing system stability, precise positioning, and improved response times. The successful implementation underscores the algorithm’s versatility and effectiveness in handling real-world engineering problems. The positive outcomes from extensive benchmarking and practical application show the FFO’s potential as a powerful optimization tool. In applying multi-objective PID controller parameter optimization, FFO demonstrated superior performance with a sum of mean errors of 190.563, outperforming particle swarm optimization (250.075) and dynamic differential annealed optimization (219.629). These results indicate FFO’s ability to achieve precise and reliable PID tuning for control systems. Furthermore, FFO achieved competitive results on large-scale optimization problems, demonstrating its scalability and robustness.

Open Access: Yes

DOI: 10.1038/s41598-025-89840-1

Flower Pollination Algorithm on optimal design of space trusses

Edina Koch M. Movahedi Rad Shaymaa Alsamia

Publication Name: International Review of Applied Sciences and Engineering

Publication Date: 2025-10-13

Volume: 16

Issue: 3

Page Range: 418-427

Description:

Abstract: This study assesses the performance of four nature-inspired optimization algorithms—Dynamic Differential Annealed Optimization (DDAO), Flower Pollination Algorithm (FPA), Firefly Algorithm (FF), and Particle Swarm Optimization (PSO) for achieving optimal space truss design. The aim is to minimize the structural weight of three benchmark trusses (10-bar, 25-bar, and 72-bar) while meeting stress and displacement constraints. The key contribution of this work is the first systematic evaluation of FPA in space truss optimization, demonstrating its greater effectiveness in obtaining optimal or near-optimal solutions with faster convergence and higher stability compared to PSO and FF. The results also highlight the limitations of DDAO in handling constrained engineering problems. Findings confirm that FPA and FF are highly effective for structural optimization, offering robust solutions with minimal computational cost. These insights contribute to advancing metaheuristic-based structural design, supporting the adoption of FPA in large-scale optimization problems.

Open Access: Yes

DOI: 10.1556/1848.2025.00958

Adaptive Exploration Artificial Bee Colony for Mathematical Optimization

Edina Koch Hazim Albedran Shaymaa Alsamia R. P. Ray

Publication Name: AI Switzerland

Publication Date: 2024-12-01

Volume: 5

Issue: 4

Page Range: 2218-2236

Description:

The artificial bee colony (ABC) algorithm is a famous swarm intelligence method utilized across various disciplines due to its robustness. However, it exhibits limitations in exploration mechanisms, particularly in high-dimensional or complex landscapes. This article introduces the adaptive exploration artificial bee colony (AEABC), a novel variant that reinspires the ABC algorithm based on real-world phenomena. AEABC incorporates new distance-based parameters and mechanisms to correct the original design, enhancing its robustness. The performance of AEABC was evaluated against 33 state-of-the-art metaheuristics across twenty-five benchmark functions and an engineering application. AEABC consistently outperformed its counterparts, demonstrating superior efficiency and accuracy. In a variable-sized problem (n = 10), the traditional ABC algorithm converged to 3.086 × 106, while AEABC achieved a convergence of 2.0596 × 10−255, highlighting its robust performance. By addressing the shortcomings of the traditional ABC algorithm, AEABC significantly advances mathematical optimization, especially in engineering applications. This work underscores the significance of the inspiration of the traditional ABC algorithm in enhancing the capabilities of swarm intelligence.

Open Access: Yes

DOI: 10.3390/ai5040109

Applying clustered artificial neural networks to enhance contaminant diffusion prediction in geotechnical engineering

Edina Koch Shaymaa Alsamia

Publication Name: Scientific Reports

Publication Date: 2024-12-01

Volume: 14

Issue: 1

Page Range: Unknown

Description:

This paper introduces a novel approach using Clustered Artificial Neural Networks (CLANN) to address the challenge of developing predictive models for multimodal dataset with extreme parameter values. The CLANN method strategically decomposes the dataset, derived from Finite Element Analysis (FEA), into clusters, each representing distinct diffusion behaviors, and applies specialized neural networks within these clusters. The CLANN model was rigorously evaluated and demonstrated superior accuracy and consistency compared to traditional methods such as the Adaptive Neuro-Fuzzy Inference System (ANFIS) and fuzzy expert systems. While these conventional models struggled to capture the full range of diffusion dynamics, particularly under extreme conditions, CLANN consistently provided predictions that closely aligned with the actual FEA data across all scenarios. The versatility of the CLANN approach extends beyond its application to soil contamination. Its ability to handle complex, multimodal datasets suggests that this methodology can be generalized to a wide range of scientific and engineering problems characterized by similar data structures. This makes CLANN not only a powerful tool for geotechnical engineers but also a promising framework for broader applications where traditional models fall short. The findings of this study pave the way for more accurate, reliable, and adaptable predictive modeling in diverse domains, enhancing our ability to manage and mitigate environmental and engineering challenges.

Open Access: Yes

DOI: 10.1038/s41598-024-79983-y

Random forest regression on pullout resistance of a pile

Edina Koch Shaymaa Alsamia

Publication Name: Pollack Periodica

Publication Date: 2024-10-16

Volume: 19

Issue: 3

Page Range: 28-33

Description:

This research aims to study the pullout resistance of a helical pile using three methods of machine learning techniques, which are: random forest regression, support vector regression, and adaptive neuro-fuzzy inference system, based on experimental results of a helical pile. The performance of these three techniques has been d compared and the results show that random forest algorithm has best performance than neuro-fuzzy inference system and support vector technique. The results show that machine learning considered a good tool in terms of estimating the pullout resistance of helical piles in the soil.

Open Access: Yes

DOI: 10.1556/606.2024.01052

Finite Element Analysis of Microtunneling Under a Railway Track

Edina Koch Zoltán Major Shaymaa Alsamia

Publication Name: Advances in Transdisciplinary Engineering

Publication Date: 2024-01-01

Volume: 59

Issue: Unknown

Page Range: 351-357

Description:

Microtunneling is a trenchless construction method used to install pipelines beneath highways, railroads, runways, harbors, rivers, and environmentally sensitive areas. For railway lines, the primary objective of the method is to address the challenges posed by the installation of utilities without disrupting rail operations. The aim is to minimize the impact on railway services, ensuring the uninterrupted flow of transportation while facilitating essential infrastructure development. Traditional excavation methods often involve significant ground disturbance and pose risks to the stability of the railway track, leading to service interruptions and safety hazards. Microtunneling, on the other hand, offers a non-disruptive alternative by utilizing advanced tunneling equipment that minimizes ground settlement and vibration, reducing the risk of damage to the railway structure. The technique involves the use of remotely controlled boring machines to excavate tunnels with precision, allowing for the installation of pipelines or other utilities with minimal impact on the railway infrastructure above. The aim is to achieve a seamless integration of new underground utilities while maintaining the structural integrity and operational functionality of the railway line. Furthermore, microtunneling under a railway line contributes to sustainable development by minimizing the environmental footprint associated with construction activities. The reduced excavation and disturbance to the surrounding environment lead to lower levels of noise, dust, and disruption, aligning with modern principles of environmentally conscious infrastructure development. In this study, the installation of a sewage pipeline constructed by microtunneling under an existing railway track is investigated using geotechnical and structural FEM.

Open Access: Yes

DOI: 10.3233/ATDE240566

Comparative study of metaheuristics on optimal design of gravity retaining wall

Edina Koch Shaymaa Alsamia Hanaa Shihab Hamadi

Publication Name: Pollack Periodica

Publication Date: 2023-07-11

Volume: 18

Issue: 2

Page Range: 35-40

Description:

Retaining walls are typical geotechnical engineering applications analyzed extensively in the literature. However, the optimal design of these walls is still unsolved due to the optimization problem's complexity and the unrecognized best solver that can be used. Most similar works present a single optimizer for this problem. This work used six metaheuristics to formulate and solve the optimal gravity retaining wall problem design. The comparative study was achieved among particle swarm optimization, grey wolf optimizer, artificial bee colony, dynamic differential annealed optimization, fertilization optimization algorithm, and whale optimization algorithm. The problem and its results were discussed in detail within the respective sections.

Open Access: Yes

DOI: 10.1556/606.2023.00826

EVALUATION THE BEHAVIOR OF PULLOUT FORCE AND DISPLACEMENT FOR A SINGLE PILE: EXPERIMENTAL VALIDATION WITH PLAXIS 3D

Edina Koch Shaymaa Alsamia

Publication Name: Kufa Journal of Engineering

Publication Date: 2023-04-01

Volume: 14

Issue: 2

Page Range: 105-116

Description:

This study conducted an experimental and numerical investigation to examine the pullout behavior of a single pile in sand soil with a specific density. The soil testing model was constructed to simulate real-world geotechnical applications where the soil is subjected to varying pullout forces. The experimental setup involved measuring vertical displacement corresponding to different values of pullout forces. The results were then compared to numerical results obtained from a PLAXIS 3D model with HS-small. The experimental and numerical results showed good agreement, demonstrating the effectiveness of the numerical model in simulating real-world geotechnical applications. The study provides valuable insights into the pullout behavior of a pile in soil with specific density and can be used to improve the design and construction of geotechnical structures. The difference between experimental results and numerical predictions was in acceptable values.

Open Access: Yes

DOI: 10.30572/2018/KJE/140207