alexandria engineering journal最新文献

{"title":"Hybrid TCN-transformer model for predicting sustainable food supply and ensuring resilience","authors":"Ibrahim Alrashdi ,&nbsp;Rasha M. Abd El-Aziz ,&nbsp;Ahmed I. Taloba ,&nbsp;Mohammed Farsi","doi":"10.1016/j.aej.2025.05.044","DOIUrl":"10.1016/j.aej.2025.05.044","url":null,"abstract":"<div><div>Major concerns occur in maintaining a sustainable food supply due to population expansion, supply chain interruptions, and climate-related changes. Traditional forecasting models, such as ARIMA, LSTM, and GRU, fail to deal with the dynamic fluctuations and long-range correlations. These methods often have reduced accuracy, high computational cost, and poor generalization when applied to shifting patterns in the food supply system. Based on the abovementioned limitations, this study proposes a Hybrid TCN-Transformer Model by combining the strength of Temporal Convolutional Networks (TCN) with Transformer Attention to provide accurate and efficient food supply prediction. Thus, the project's key objective is to develop a deep learning system that effectively handles massive quantities of temporal data while preserving dependence in short and long durations. The proposed method is novel since it integrates TCN's causal convolutions for extracting sequential patterns. It uses a Transformer Model's self-attention mechanism to capture the complex interactions across time steps. Hybrid design enables faster training, increased interpretability, and better prediction accuracy than current methods. Results from experiments have revealed that the suggested model surpasses the performance of the stand-alone TCN, ARIMA, LSTM, and GRU models in terms of accuracy of predictions, efficiency of computations, and adaptability. Findings thus far suggest deep learning-based predictive analytics has helped improve the food supply chain management by mitigating food wastage, making it environmentally resilient.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"127 ","pages":"Pages 380-391"},"PeriodicalIF":6.2,"publicationDate":"2025-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143947862","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Optimization of four-diode equivalent circuit models for solar cells: Analytical formulation and performance enhancement","authors":"Martin Calasan ,&nbsp;Snezana Vujosevic ,&nbsp;Mohammed Alruwaili ,&nbsp;Moustafa Ahmed Ibrahim","doi":"10.1016/j.aej.2025.05.047","DOIUrl":"10.1016/j.aej.2025.05.047","url":null,"abstract":"<div><div>The ongoing evolution of power systems and the growing penetration of photovoltaic (PV) technologies necessitate the development of solar cell models that are both highly accurate and computationally efficient. This work presents two novel Four-Diode Model (FDM) equivalent circuits—PEC1 and PEC2—that offer closed-form current–voltage (I–V) characteristics derived analytically via the Lambert W function. By eliminating the need for iterative solvers, these models enhance numerical stability and significantly reduce computational burden, making them well-suited for large-scale and real-time applications. Extensive validation was performed on several benchmark PV modules, including KC200GT, PHOTOWATT-PWP 201, and mSi0188, under varying environmental conditions. For the PHOTOWATT PWP 201 solar panel, the proposed models achieved up to a 29 % reduction in root-mean-square error (RMSE) compared to the most accurate method reported in the literature. In addition, the models were experimentally verified using a laboratory-scale ET 250 photovoltaic training system, further confirming their precision and applicability under real-world operating scenarios. Across all tested modules and conditions, the models demonstrated strong agreement with measured data, exhibiting robustness, adaptability, and generalization capabilities. The combination of analytical solvability, low complexity, and broad applicability renders the proposed FDM models particularly advantageous for integration into PV simulation software, energy management systems, and smart grid optimization environments, where modeling speed and precision are critical. These attributes highlight the models’ relevance for both academic research and industrial deployment.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"127 ","pages":"Pages 411-430"},"PeriodicalIF":6.2,"publicationDate":"2025-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144069785","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Controllability analysis of mechanical multibody dynamics control systems based on lie symmetry","authors":"Zheng Mingliang","doi":"10.1016/j.aej.2025.05.048","DOIUrl":"10.1016/j.aej.2025.05.048","url":null,"abstract":"<div><div>To quantitatively characterize the dynamic controlled performance of mechanical multibody systems and design collaborative control strategies, this paper investigates the controllability of mechanical multibody dynamic control systems. Firstly, under the affine connection framework of Lagrange mechanical control systems, we establish the Euler-Poincaré equations of unconstrained mechanical multibody dynamics control systems by differential geometry method; Further, we transform the Euler-Poincaré equations into the classical state space form of nonlinear control systems by augmented vector method; Secondly, by introducing Lie group representation theory, the definition and the solution of generalized Lie symmetry for mechanical multibody dynamics control systems are given, and the necessary and sufficient conditions for state controllability (local controllability) are given by using Lie symmetry; Finally, an application example of dynamic control of a single degree of freedom manipulator with basic vibration is provided, it explains the effectiveness and correctness of the Lie symmetry method in this paper. The research has shown that using Lie symmetry to analyze the controllability problem of mechanical multibody dynamics control systems can be transformed into its low-dimensional quotient space analysis, and if the quotient space is controllable at a point, then the system can be controllable for all points on the orbit where that point at.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"127 ","pages":"Pages 374-379"},"PeriodicalIF":6.2,"publicationDate":"2025-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143947861","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Synergizing vision transformer with ensemble of deep learning model for accurate kidney stone detection using CT imaging","authors":"Arwa Alzughaibi ,&nbsp;Adwan A. Alanazi ,&nbsp;Mohammed Alshahrani ,&nbsp;Ines Hilali Jaghdam ,&nbsp;Abaker A. Hassaballa","doi":"10.1016/j.aej.2025.05.025","DOIUrl":"10.1016/j.aej.2025.05.025","url":null,"abstract":"<div><div>The disease of Kidney stones is a risky disease for individuals all over the world. Many people with kidney stones in the early phase do not detect it as an illness, and it harms the organ gradually. Precise analysis of kidney illness is vital, as it is a major health concern that needs accurate detection for appropriate and effective treatment. CT scans are one of the most extensively accessible imaging models, and they are employed for effective diagnosis. Deep learning (DL) techniques are gradually identified as beneficial tools for analyzing illness in the medical field. However, present techniques employing deep networks often meet low accuracy and overfitting challenges, demanding further alteration for optimum performance. This study presents a Leveraging Flying Foxes Optimization with an Ensemble of Deep Learning for Accurate Kidney Stone Detection (LFFOEDL-AKSD) technique in CT scans. The presented LFFOEDL-AKSD technique mainly focuses on detecting kidney stones using CI imaging. At first, the presented LFFOEDL-AKSD technique applies the pre-processing phase, which involves image resizing for uniform CT scan dimensions and data augmentation through transformations like rotation and flipping to reduce overfitting, sobel filtering (SF) sharpens edges, and the data is separated into training, validation, and testing sets for model development. The presented LFFOEDL-AKSD technique employs the swin transformer (ST) model for the feature extraction method. Furthermore, the majority voting ensemble of three DL approaches, such as the graph convolutional network (GCN), temporal convolutional network (TCN), and three-dimensional convolutional autoencoder (3D-CAE) approaches, are employed to increase the precision and reliability of the kidney stone recognition. Finally, the presented LFFOEDL-AKSD technique implements the flying foxes optimization (FFO) approach for the hyperparameter tuning involved in the ensemble learning models. An extensive experiment is conducted to validate the performance of the LFFOEDL-AKSD methodology under a kidney stone imaging dataset. The experimental validation of the LFFOEDL-AKSD methodology portrayed a superior accuracy value of 98.97 % over existing models.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"127 ","pages":"Pages 357-373"},"PeriodicalIF":6.2,"publicationDate":"2025-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143947858","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Research on the application of a model combining improved optimization algorithms and neural networks in trajectory tracking of robotic arms","authors":"Yanhui Lai,&nbsp;Zuobing Chen,&nbsp;Ya Mao","doi":"10.1016/j.aej.2025.05.009","DOIUrl":"10.1016/j.aej.2025.05.009","url":null,"abstract":"<div><div>This study presents an enhancement to the Mountain Gazelle Optimizer (MGO) and proposes a new optimization algorithm—Mapping Mountain Gazelle Optimizer (MMGO). Through systematic experiments, we have validated the performance of the MMGO in addressing complex optimization problems. To further enhance optimization effectiveness, we integrated the new algorithm MMGO with Radial Basis Function (RBF) neural networks, resulting in the development of two optimization algorithm models: RBF_MMGO and RBF_MGO. In the practical application of robotic arm trajectory tracking control, we conducted a comprehensive performance evaluation and comparison of these two optimization algorithm models. Experimental results indicate that RBF_MMGO significantly outperforms RBF_MGO in terms of tracking accuracy and stability. This finding not only validates the effectiveness of MMGO in optimization problems but also demonstrates the application potential of optimization algorithm models in robotic arm control. Through comparative analysis, we discovered that the RBF_MMGO model exhibits greater adaptability in dynamic environments, enabling it to better cope with the challenges posed by trajectory changes. This model has shown higher accuracy and lower tracking errors when handling complex nonlinear systems. These advantages suggest that the MMGO has broader applicability and higher reliability in practical applications. This research provides theoretical insights into the MMGO's application and lays the foundation for advancements in robotic arm trajectory tracking control. It illustrates the feasibility of combining optimization algorithms with neural networks, offering innovative approaches for future research.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"127 ","pages":"Pages 336-356"},"PeriodicalIF":6.2,"publicationDate":"2025-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143947860","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"ANN-based analysis of thin film Maxwell fluid dynamics with electro-osmotic and nonlinear thermal effects","authors":"Irfan Saif Ud Din ,&nbsp;Imran Siddique ,&nbsp;Zohaib Zahid ,&nbsp;Muhammad Nadeem ,&nbsp;S. Islam","doi":"10.1016/j.aej.2025.04.084","DOIUrl":"10.1016/j.aej.2025.04.084","url":null,"abstract":"<div><div>An intelligent Levenberg-Marquardt Technique (LMT) with artificial neural network (ANN) backpropagation (BP) has been used to analyze the thermal heat and mass transfer of unsteady magnetohydrodynamics (MHD) thin film Maxwell fluid flow in a porous inclined sheet with an emphasis on the influence of electro-osmosis. The activation energy, chemical reaction, mixed convection, melting heat, joule heating, nonlinear thermal radiation, variable thermal conductivity and thermal source/sink effect are taken into account for transport expressions. Appropriate similarity transformations were used to translate partial differential equations (PDEs) into ordinary differential equations (ODEs). After that, the built-in MATLAB BVP4C method was used for a data set assessed using the LMT-ANN strategy to solve these ODEs. The physical significance of the designed parameters is thoroughly discussed in both tabular and graphical form. The observed <em>R</em>-squared value is 1, and the mean square error up to <span><math><msup><mrow><mn>10</mn></mrow><mrow><mo>−</mo><mn>15</mn></mrow></msup></math></span> demonstrates the LMT-ANN's precise and accurate computing capability. The model’s validity is also confirmed by the strong agreement between the obtained predicted findings and numerical results, which shows a high degree of accuracy within the range of <span><math><msup><mrow><mn>10</mn></mrow><mrow><mo>−</mo><mn>8</mn></mrow></msup></math></span> to <span><math><mrow><msup><mrow><mn>10</mn></mrow><mrow><mo>−</mo><mn>11</mn></mrow></msup><mo>.</mo></mrow></math></span> It was revealed that radiative heat considerably increases surface heat energy through accumulation, improving heat transfer qualities, whereas fluid temperature is raised by Joule dissipation, variable thermal conductivity, and heat source. Electro-osmosis and magnetic fields reduce fluid velocity by generating opposing forces that resist the flow. This problem works best in microscale fluid transport systems and drilling operations, where magnetic and electro-osmotic control are crucial. These systems include micro-electromechanical systems, lab-on-a-chip devices, porous geological formations, and thin film coating technologies.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"127 ","pages":"Pages 392-410"},"PeriodicalIF":6.2,"publicationDate":"2025-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144069784","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"IoT-enhanced multi-attention and lightweight feature integration for human pose estimation in motion training systems","authors":"Junwen Chen ,&nbsp;Jian Yang ,&nbsp;Zhiqun Wang","doi":"10.1016/j.aej.2025.04.074","DOIUrl":"10.1016/j.aej.2025.04.074","url":null,"abstract":"<div><div>Human pose estimation is widely used in intelligent sports training, rehabilitation assistance, and human–computer interaction, providing precise motion feedback and training guidance. However, existing methods suffer from keypoint localization errors and insufficient global coherence in complex backgrounds, occlusions, and high-dynamic motion scenarios. To address these challenges, this paper proposes a hybrid IoT-vision deep learning model for human pose estimation and motion training feedback. IoT-based motion sensors are integrated with vision-based keypoint detection to enhance pose estimation accuracy, particularly in occluded or high-speed movement scenarios. The model employs the LSFE stacked feature extraction module to enhance multi-scale feature adaptability, incorporates the LFAM local attention mechanism (SPAM + CARM) to improve key joint modeling, and introduces the GEAM global enhancement module to ensure keypoint stability and consistency. Additionally, an ECA-based lightweight channel attention mechanism reduces computational complexity while enhancing key feature responses. Experimental results show that the proposed model achieves Mean Accuracy of 0.946 and 0.949 on the LSP and MPII datasets, respectively, with PCK scores of 0.97 and 0.95. This model demonstrates significant improvements over existing methods in real-time performance and robustness, particularly in complex scenarios such as sports training, rehabilitation, and monitoring.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"127 ","pages":"Pages 284-295"},"PeriodicalIF":6.2,"publicationDate":"2025-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143942272","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Enhanced sentiment analysis framework: Ensemble attention enhanced bidirectional long-short-term encoder for accurate classification of consumer reviews","authors":"Ali Jaber Almalki","doi":"10.1016/j.aej.2025.05.022","DOIUrl":"10.1016/j.aej.2025.05.022","url":null,"abstract":"<div><div>The fast growth of today's technology on social media, the web, etc caused the ongoing and fast creation of opinionated textual data. In this context, internet reviews by consumers determine upcoming consumers whether can buy a particular product or not. Because the thoughts regarding the products are expressed by commenting on reviews. The sentiment analysis is more supportive for comprehending feedback and the attitude of consumers regarding the product’s characteristics. More sentiment classification tasks are carried out by the researchers but attained low level output due to difficulty in learning contextual words. To rectify this type of issue, current work focuses on developing a sentiment analysis framework by progressive techniques. The novel namely Ensemble Attention Enhanced Bidirectional Long-short-term Encoder (EAE-BiLE) is developed. The developed method analyzes online reviews and gains reviews from Amazon and the second task is to form high-quality input. The BERT model generates contextual word embeddings and Bi-directional Long-Short-Term Memory (Bi-LSTM) processes these embeddings in order to capture both backward and forward dependencies from the text. The novel method makes the accurate classification by focusing on important and relevant parts in the text using an attention mechanism that assigns different weights. Detailed experiments that expose the performance of the developed method are performed in this work. This requires a few evaluation metrics that can measure the effectiveness of the developed method, which is accomplished by F1-score, recall, accuracy, and precision. The developed EAE-BiLE framework yields higher rates of 97.2 %, 97.2 %, 99.1 %, and 98.4 % for precision, F1-score, accuracy, and recall. Its error performance is also low, which represents the developed method makes the precise classification. The developed EAE-BiLE excels with higher effectiveness than prior techniques for efficacious sentiment classification.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"127 ","pages":"Pages 265-283"},"PeriodicalIF":6.2,"publicationDate":"2025-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143942271","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The influence of fear effect and phase of chaos control of discrete predator–prey system with mixed Holling types","authors":"A.M. Madian ,&nbsp;Rong Zheng ,&nbsp;M.M.A. El-sheikh ,&nbsp;M.F. Elettreby ,&nbsp;A.A. El-Gaber","doi":"10.1016/j.aej.2025.04.048","DOIUrl":"10.1016/j.aej.2025.04.048","url":null,"abstract":"<div><div>In this paper, a discrete-time predator–prey system with mixed Holling types I and III functional responses and fear effect is discussed. Three fixed points are determined and their stability is established. Analytical criteria for Neimark Sacker bifurcation (NSB) and flip bifurcation (FB) are proposed. Applying the technique of state feedback control, we introduce the corresponding controlled system. At an unstable fixed point the chaotic orbits can be stabilized. We show that the fear effect of prey species has a negative effect on the density of predator species in our model. Furthermore, fear effect may increase the possibility that prey species will go extinct, which implies that Allee effect may occur in this case. These analytical studies are illustrated with some numerical simulations.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"127 ","pages":"Pages 296-308"},"PeriodicalIF":6.2,"publicationDate":"2025-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143942273","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A review to elucidate the influence of promoters on the acidity/basicity, reducibility, and metal-support interaction of catalysts in methane dry reforming","authors":"Osarieme Uyi Osazuwa ,&nbsp;Kim Hoong Ng","doi":"10.1016/j.aej.2025.04.104","DOIUrl":"10.1016/j.aej.2025.04.104","url":null,"abstract":"<div><div>Past researches had identified the importance the acidity/basicity, reducibility, and metal-support interactions of catalyst in impacting its performances in methane dry reforming (MDR). This review provides an in-depth overview of the roles of acidity/basicity in MDR reactions, focusing on their impacts on reducibility and metal-support interactions. The discussion is categorized based on the incorporated promoter, including rare earth metals, transition metals, noble metals, and alkali earth metals. The acidity and basicity of catalysts play a crucial role in MDR reactions. Brønsted acidic sites enhance catalyst activation, reducibility, and metal-support interaction, while Lewis acidic sites facilitate CH₄ and CO₂ activation more prominently. However, excessive acidity can lead to reduced reducibility and increased catalyst deactivation. Also, basic sites formed via basic metal oxides can enhance reducibility, metal-support interaction, and overall catalytic performance. A moderate level of basicity is favoured, as it can effectively modulate reducibility and metal-support interaction without inducing excessive metal dispersion or deactivation. Understanding the complex interplay between acidity and basicity is essential for designing high-performance MDR catalysts with improved reducibility, metal-support interaction, stability, and activity. Future research directions include novel promoter developments, incorporation of machine learning, and investigation of catalyst deactivation mechanisms to ensure the sustainability of MDR technology.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"127 ","pages":"Pages 309-335"},"PeriodicalIF":6.2,"publicationDate":"2025-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143947859","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}