alexandria engineering journal最新文献

{"title":"On the implications of artificial intelligence methods for feature engineering in reliability sector with computer knowledge graph","authors":"Heling Jiang ,&nbsp;Yongping Xia ,&nbsp;Changjie Yu ,&nbsp;Zhao Qu ,&nbsp;Huaiyong Li","doi":"10.1016/j.aej.2025.01.093","DOIUrl":"10.1016/j.aej.2025.01.093","url":null,"abstract":"<div><div>This work employs support vector machine (SVM), K-Nearest Neighbors (KNN) and logistic regression models to predict the health state of the pump and to establish fault diagnosis. From the features like vibration, temperature of the motor, pressure, and flow rate, the models categorize the state of the pump into two; normal or No Fault, and Fault Detected. This makes it possible to detect specific faults and assist in creating preventive maintenance. Post analysis, it was inferred that with an accuracy of 0.92, the SVM with a linear kernel outperformed the competing models. While the KNN performed marginally worse with an accuracy of 0.85, the SVM with RBF and polynomial kernels as well as logistic regression both attained accuracy of 0.91. These findings highlight the SVM with a linear kernel’s superior generalization skills, which make it the best option for pump system defect identification. For defect detection, giving the SVM with a linear kernel priority guarantees precise predictions, allowing for proactive maintenance and minimizing downtime. To improve operational efficiency and lower long-term maintenance costs, policy ideas include standardizing data collection techniques, investing in real-time monitoring systems, and implementing machine learning-based predictive maintenance across industries.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"119 ","pages":"Pages 587-597"},"PeriodicalIF":6.2,"publicationDate":"2025-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143377121","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"On the assessment and reliability of political and ideological education in colleges using deep learning methods","authors":"Yongsheng Ma ,&nbsp;Xianhui Sun ,&nbsp;Aiqun Ma","doi":"10.1016/j.aej.2025.01.114","DOIUrl":"10.1016/j.aej.2025.01.114","url":null,"abstract":"<div><div>The reliability and effectiveness of teaching outcomes are reliant upon the accurate evaluation of ideological and political (IAP) education in colleges. This study focuses on predicting assessment scores to evaluate student performance, identify areas of vulnerability, and implement targeted interventions. Sophisticated deep learning techniques including artificial neural networks (ANN), convolutional neural networks (CNN), and support vector machines (SVM) were utilized to enhance the reliability of these evaluations. The results demonstrated clear distinctions between the training and test errors for the models. The ANN exhibited the highest errors, with a training RMSE (root mean squares error) of 14.13 and test RMSE of 13.55, indicating weak generalization. The CNN showed substantial improvement, with a training RMSE of 9.31 and test RMSE of 9.32, reflecting moderate but consistent performance. However, the SVM emerged as the most reliable model, achieving the lowest prediction errors: training RMSE of 7.68 and test RMSE of 8.0, with minimal discrepancies between training and test results. These findings provide valuable insights for instructors and policymakers to refine curriculum delivery, monitor student outcomes, and address educational disparities effectively. By adopting robust models like the SVM, institutions can ensure reliable predictions, fostering a more inclusive and outcome-oriented education system.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"119 ","pages":"Pages 511-517"},"PeriodicalIF":6.2,"publicationDate":"2025-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143377109","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A new statistical model with optimal fitting performance: Its assessments in management sciences and reliability","authors":"Zhidong Liang","doi":"10.1016/j.aej.2025.01.094","DOIUrl":"10.1016/j.aej.2025.01.094","url":null,"abstract":"<div><div>The study of real-world phenomena fundamentally hinges on probability distributions. This understanding has inspired researchers to design new statistical models, which has resulted in a variety of methodologies. Often, these methodologies are developed with new parameters. Unfortunately, the introduction of additional parameters can sometimes create difficulties related to re-parameterization. In the context of this particular research area, we introduce a groundbreaking statistical methodology designed to enhance the distributional flexibility of probability models without the addition of new parameters. The methodology we propose, which combines the sine function with the weighted T-<span><math><mi>X</mi></math></span> strategy, is referred to as the sine weighted-<span><math><mi>G</mi></math></span> (SW-<span><math><mi>G</mi></math></span>) family. The sine weighted-Weibull (SW-Weibull) distribution is examined through the SW-<span><math><mi>G</mi></math></span> method. Essential distributional functions for the SW-Weibull distribution are presented, along with corresponding visual representations. Additionally, properties based on quartiles are explored, and the derivation of maximum likelihood estimators is presented. A simulation study is conducted to enhance the understanding of the distribution. Ultimately, the relevance of the SW-Weibull distribution is confirmed by examining two real-world data sets from the management sciences and reliability sectors. Our findings, based on particular evaluation tests, indicate that the SW-Weibull distribution provides optimal performance when analyzing the aforementioned data sets.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"119 ","pages":"Pages 545-557"},"PeriodicalIF":6.2,"publicationDate":"2025-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143377112","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Optimizing alpha–beta filter for enhanced predictions accuracy in industrial applications using Mamdani fuzzy inference system","authors":"Junaid Khan ,&nbsp;Muhammad Fayaz ,&nbsp;Umar Zaman ,&nbsp;Eunkyu Lee ,&nbsp;Awatef Salim Balobaid ,&nbsp;Muhammad Bilal ,&nbsp;Kyungsup Kim","doi":"10.1016/j.aej.2025.01.116","DOIUrl":"10.1016/j.aej.2025.01.116","url":null,"abstract":"<div><div>This work presents a novel approach for dynamically optimizing the alpha–beta filter parameters through the Mamdani fuzzy inference system (MFIS) for industrial applications to estimate the state of dynamic systems based on sensor measurements. Our proposed method has two important components: the primary predictor utilizing the alpha–beta algorithm, and a rule-based mechanism leveraging the Mamdani fuzzy inference system. To illustrate our approach and simplify the demonstration, we selected two types of sensors: temperature and humidity. The model efficiently processes input from these sensors, refining the sensor data to filter out noise and improve prediction accuracy. The integration of MFIS significantly improves the system’s performance, significantly reducing the root mean square error (RMSE) and mean absolute error (MAE), which are critical indicators of predictive accuracy. To validate the effectiveness and robustness of our method, we executed an extensive set of experiments , which affirm the superior performance of our model.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"119 ","pages":"Pages 598-608"},"PeriodicalIF":6.2,"publicationDate":"2025-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143377122","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A new statistical approach with simulation study: Its implementations in management sciences and reliability","authors":"Zhidong Liang","doi":"10.1016/j.aej.2025.01.113","DOIUrl":"10.1016/j.aej.2025.01.113","url":null,"abstract":"<div><div>The analysis of practical phenomena is fundamentally reliant on probability distributions. This awareness has inspired researchers to develop new statistical models, resulting in a range of methodologies. Many of these methodologies are typically established with new parameters. Unfortunately, the addition of extra parameters can occasionally lead to complications concerning re-parameterization. Within this specific research domain, we propose a new statistical methodology intended to augment the distributional flexibility of probability models while avoiding the need for new parameters. This methodology, which merges the cosine function with the weighted T-<span><math><mi>X</mi></math></span> strategy, is designated as the cosine weighted-<span><math><mi>G</mi></math></span> (CW-<span><math><mi>G</mi></math></span>) family. We focus on the cosine weighted-Weibull (CW-Weibull) distribution, obtained through the CW-<span><math><mi>G</mi></math></span> method. Certain fundamental distributional functions pertaining to the CW-Weibull distribution are outlined, accompanied by visual depictions. We derive the quartile-based properties and formulates the maximum likelihood estimators. Additionally, a simulation study is performed to validate the theoretical findings. The relevance of the CW-Weibull distribution is affirmed through the scrutiny of two real-world data sets sourced from management sciences and reliability sectors. Our findings, derived from specific evaluation tests, indicate that the CW-Weibull distribution achieves optimal performance in the analysis of these data sets.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"119 ","pages":"Pages 531-544"},"PeriodicalIF":6.2,"publicationDate":"2025-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143377111","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"MDCKE: Multimodal deep-context knowledge extractor that integrates contextual information","authors":"Hyojin Ko,&nbsp;Joon Yoo,&nbsp;Ok-Ran Jeong","doi":"10.1016/j.aej.2025.01.119","DOIUrl":"10.1016/j.aej.2025.01.119","url":null,"abstract":"<div><div>Extraction of comprehensive information from diverse data sources remains a significant challenge in contemporary research. Although multimodal Named Entity Recognition (NER) and Relation Extraction (RE) tasks have garnered significant attention, existing methods often focus on surface-level information, underutilizing the potential depth of the available data. To address this issue, this study introduces a Multimodal Deep-Context Knowledge Extractor (MDCKE) that generates hierarchical multi-scale images and captions from original images. These connectors between image and text enhance information extraction by integrating more complex data relationships and contexts to build a multimodal knowledge graph. Captioning precedes feature extraction, leveraging semantic descriptions to align global and local image features and enhance inter- and intramodality alignment. Experimental validation on the Twitter2015 and Multimodal Neural Relation Extraction (MNRE) datasets demonstrated the novelty and accuracy of MDCKE, resulting in an improvement in the F1-score by up to 5.83% and 26.26%, respectively, compared to State-Of-The-Art (SOTA) models. MDCKE was compared with top models, case studies, and simulations in low-resource settings, proving its flexibility and efficacy. An ablation study further corroborated the contribution of each component, resulting in an approximately 6% enhancement in the F1-score across the datasets.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"119 ","pages":"Pages 478-492"},"PeriodicalIF":6.2,"publicationDate":"2025-02-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143350314","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Numerical investigation of heat and mass transfer for unsteady multiphase flow in a vented cavity filled with hybrid nanofluid","authors":"Muhammad Ashhad Shahid ,&nbsp;Mojtaba Dayer ,&nbsp;Muhammad Adil Sadiq ,&nbsp;Haris Ali ,&nbsp;Ishak Hashim","doi":"10.1016/j.aej.2025.01.103","DOIUrl":"10.1016/j.aej.2025.01.103","url":null,"abstract":"<div><div>Effective heat and mass transfer is crucial for enhancing efficiency and performance, particularly under varying flow conditions in devices such as heat exchangers, microfluidic systems, and chemical reactors. The current study investigates the effect of novel combination of unsteady condition and multiphase flow effect on hybrid nanofluid (HNF) convective heat and mass transfer (CHMT) within a vented cavity. The investigation employs a novel dimensionless mathematical model to explore these dynamics using Buongiorno’s approach, which considers Brownian motion and thermophoresis in nanofluids. Numerical simulations are conducted utilizing the Finite Element Method (FEM) to discretize the dimensionless governing equations. A parametric study is conducted to investigate the influence of key parameters, including the number of undulations (<span><math><mi>N</mi></math></span>) in the side walls of the cavity, Rayleigh number (<span><math><mrow><mi>R</mi><mi>a</mi></mrow></math></span>), and inflow velocity (<span><math><msub><mrow><mi>V</mi></mrow><mrow><mi>i</mi><mi>n</mi><mi>l</mi><mi>e</mi><mi>t</mi></mrow></msub></math></span>), on the Nusselt number (<span><math><mover><mrow><mi>N</mi><mi>u</mi></mrow><mo>¯</mo></mover></math></span>) and Sherwood number (<span><math><mover><mrow><mi>S</mi><mi>h</mi></mrow><mo>¯</mo></mover></math></span>). The analysis presents visualizations of streamlines, isothermal lines, and normalized solid volume fractions. Peak <span><math><mover><mrow><mi>N</mi><mi>u</mi></mrow><mo>¯</mo></mover></math></span> and <span><math><mover><mrow><mi>S</mi><mi>h</mi></mrow><mo>¯</mo></mover></math></span> of 4.0878 and 5.2526, respectively, indicated optimal heat and mass transfer efficiency, particularly under conditions that effectively disrupt the concentration boundary layer. The findings from this research are expected to contribute towards the development of more efficient nanofluid-based systems, particularly in systems with irregular geometries.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"119 ","pages":"Pages 451-464"},"PeriodicalIF":6.2,"publicationDate":"2025-02-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143350315","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Enhancing Arabic text-to-speech synthesis for emotional expression in visually impaired individuals using the artificial hummingbird and hybrid deep learning model","authors":"Mahmoud M. Selim ,&nbsp;Mohammed S. Assiri","doi":"10.1016/j.aej.2025.02.011","DOIUrl":"10.1016/j.aej.2025.02.011","url":null,"abstract":"<div><div>Depression is one of the most dangerous mental health conditions, often leading to suicide, which is the fourth leading cause of death in the Middle East. Particularly, Egypt has the highest suicide rate in the region, making it crucial to recognize depression and suicidal thoughts early. In Arab culture, awareness of mental health issues is limited, but in recent years, people have increasingly expressed their feelings on social media platforms. This shift presents an opportunity for mental health intervention through digital means. Furthermore, while facial expressions are not accessible to the blind and visually impaired, voice signals can convey emotional nuances, offering an alternative method for detecting mental health states. Natural Language Processing (NLP) and machine learning (ML) techniques provide powerful tools for analysing social media text data, helping detect emotional distress and providing timely support. By applying these technologies, AI-driven solutions can assist in understanding and addressing mental health concerns more inclusively. This study designs an Arabic Mood Changing and Depression Detection using the Artificial Hummingbird Optimization Algorithm with Deep Learning (AMCDD-AHODL) technique for visually impaired individuals. The AMCDD-AHODL technique detects different kinds of emotions and depression using Arabic tweets. After pre-processing, the word embedding process is carried out using the AraBERT model. Furthermore, the AMCDD-AHODL technique utilizes a hybrid LSTM+BiGRU model for the recognition and classification model. To improve the performance of the hybrid LSTM+BiGRU methodology, the AMCDD-AHODL technique comprises an AHO-based hyperparameter tuning process. Finally, the WaveNet model enhances the naturalness and clarity of text-to-speech synthesis, delivering high-quality, human-like audio output. The AMCDD-AHODL approach is examined using the Modern Standard Arabic dataset containing 1229 records. The performance validation of the AMCDD-AHODL approach portrayed a superior accuracy value of 95.80 % compared to the existing ML and DL models. Therefore, the AMCDD-AHODL technique is applied for the early identification of various kinds of depression that can decrease the distress from the illness and the stigma related to mental health problems.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"119 ","pages":"Pages 493-502"},"PeriodicalIF":6.2,"publicationDate":"2025-02-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143373040","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A low functional redundancy-based network slimming method for accelerating deep neural networks","authors":"Zheng Fang ,&nbsp;Bo Yin","doi":"10.1016/j.aej.2024.12.118","DOIUrl":"10.1016/j.aej.2024.12.118","url":null,"abstract":"<div><div>Deep neural networks (DNNs) have been widely criticized for their large parameters and computation demands, hindering deployment to edge and embedded devices. In order to reduce the floating point operations (FLOPs) running DNNs and accelerate the inference speed, we start from the model pruning, and realize this goal by removing useless network parameters. In this research, we propose a low functional redundancy-based network slimming method (LFRNS) that can find and remove functional redundant filters by feature clustering algorithm. However, the redundancy of some key features is beneficial to the model, and removing these features will limit the potential of the model to some extent. Build on this view, we propose feature contribution ranking unit (FCR unit) which can automatically learn the feature maps' contribution to the key information with training iterations. FCR unit can assist LFRNS restore some important elements in the pruning set to break the performance bottleneck of the slimming model. Our method mainly removes feature maps with similar functions instead of only pruning the unimportant parts, thus effectively ensuring the integrity of features’ functions and avoiding network degradation. We conduct experiments on image classification task based on CIFAR-10 and CIFAR-100 datasets. Our framework achieves over 2.0 × parameters and FLOPs reductions, while maintaining &lt; 1 % loss in accuracy, and even improve accuracy of large-volume models. We also introduce our method to the vision transformer model (ViT) and achieve performance comparable to state-of-the-art methods with nearly 1.5 × less computation.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"119 ","pages":"Pages 437-450"},"PeriodicalIF":6.2,"publicationDate":"2025-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143348973","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Advanced ellipse overlap computation based on segment area of circles","authors":"Minhye Kim ,&nbsp;Yongkuk Kim ,&nbsp;Giphil Cho","doi":"10.1016/j.aej.2025.01.127","DOIUrl":"10.1016/j.aej.2025.01.127","url":null,"abstract":"<div><div>To address the numerical limitations that may arise when calculating the overlapping area of two ellipses using algebraic and numerical methods, we propose a novel approach aimed at improving numerical accuracy. Given two ellipses of either the standard or general types, a quaternary equation can be derived for the intersection points of the two ellipses. By solving this equation, we classify the methods for calculating the area into five types and proposed area calculation approaches for each type. In addition, we propose a method for calculating the area of a segment of an ellipse without integration. This method calculates the area of a segment of a circle with the major axis of the ellipse as its diameter and multiplies the ratio of the major axis to the minor axis. The proposed method for calculating the overlapping area of two ellipses does not require integration, enabling straightforward computation while providing high accuracy. We compared our method with the traditional Monte Carlo method and found that when the relative error is 0.0245, our method operates approximately 6 times faster. Our research applies to fields like robotics, GIS, industrial clustering, and biology, with strong potential in medical imaging and diagnosis.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"119 ","pages":"Pages 425-436"},"PeriodicalIF":6.2,"publicationDate":"2025-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143348972","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}