alexandria engineering journal最新文献

{"title":"Shuffle-PG: Lightweight feature extraction model for retrieving images of plant diseases and pests with deep metric learning","authors":"Dong Jin ,&nbsp;Helin Yin ,&nbsp;Yeong Hyeon Gu","doi":"10.1016/j.aej.2024.11.052","DOIUrl":"10.1016/j.aej.2024.11.052","url":null,"abstract":"<div><div>Disease and pest diagnosis plays a critical role in managing and controlling the damage caused by plant diseases and pests. This study employs a content-based image retrieval approach to diagnose diseases and pests, suggesting similar candidate images to assist in decision-making. Previous research in disease and pest diagnosis has relied on large models for feature extraction, posing challenges for deployment in resource-constrained environments like mobile devices. To address these challenges, this study proposes a lightweight feature extraction model, Shuffle-PG, which integrates the computationally efficient ShuffleNet v2 model with pointwise group convolution. Additionally, a method for fine-tuning the feature extraction model using deep metric learning based on contrastive loss was developed to enhance discriminative feature extraction. To validate the effectiveness of the proposed method, experiments were conducted using plant disease and pest datasets specifically collected for this study. The results show that the proposed Shuffle-PG model uses approximately 20 times fewer parameters and reduces computational costs by an order of magnitude compared to existing benchmark models, while achieving higher mean average precision scores of 97.7 % and 98.8 % for the disease and pest datasets, respectively.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"113 ","pages":"Pages 138-149"},"PeriodicalIF":6.2,"publicationDate":"2024-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142652907","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":"Intelligence algorithm for the treatment of gastrointestinal diseases based on immune monitoring and neuroscience: A revolutionary tool for translational medicine","authors":"Liangyu Li ,&nbsp;Xuewen Qin ,&nbsp;Guangwei Wang ,&nbsp;Siyi Li ,&nbsp;Xudong Li ,&nbsp;Lizhong Guo ,&nbsp;Javier Santos ,&nbsp;Ana María Gonzalez-Castro ,&nbsp;Yanyang Tu ,&nbsp;Yi Qin","doi":"10.1016/j.aej.2024.11.028","DOIUrl":"10.1016/j.aej.2024.11.028","url":null,"abstract":"<div><div>The research team has developed an information system based on clinical blood cell analysis and designed and implemented highly innovative algorithms. A neural network model was created based on these feature data of the blood cell population. Artificial intelligence algorithms can label susceptible populations for digestive tract cancer with an accuracy rate of over 80 %. A multi universe optimized BP neural network model was implemented based on TCGA data of common immune antigens in clinical laboratories. The working mechanism of this model is to assign values to the parameters of the BP neural network by using the process of searching for the best fitness in multiple universes. This model can predict the five-year survival rate of patients based on immunohistochemical data. Based on these data, an AI algorithm was used to develop a clinical prognostic model with an accuracy rate of over 99 %. The research team used single-cell sequencing data to locate cell subtypes in the features of immunohistochemical data, providing a biological basis for artificial intelligence models. The research team explored the potential biological mechanisms of cancer progression and occurrence based on gastrointestinal neuroendocrine products, and these algorithms have contributed to the prediction of cancer survival and incidence,team invented a simple and efficient algorithm.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"113 ","pages":"Pages 91-137"},"PeriodicalIF":6.2,"publicationDate":"2024-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142652906","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":"Optimal compensation method for centrifugal impeller considering aerodynamic performance and dimensional accuracy","authors":"Tao Zhou ,&nbsp;Sitong Xiang ,&nbsp;Hainan Zhang ,&nbsp;Jianguo Yang","doi":"10.1016/j.aej.2024.11.055","DOIUrl":"10.1016/j.aej.2024.11.055","url":null,"abstract":"<div><div>Impellers are crucial components in centrifugal compressors, and their precision and performance determine the compressor’s work efficiency. The traditional impeller error compensation method only compensates for dimensional errors without considering aerodynamic performance, which leads to a performance loss after compensation. This study proposes a novel optimal compensation method for centrifugal impellers that comprehensively considers the aerodynamic performance and dimensional accuracy. First, a nonlinear mapping relationship between the key geometric parameters of the blade and the aerodynamic performance was established. Then, using on-machine measurement data, the impeller machining error was calculated, and a mirror compensation surface was generated. Finally, based on the mapping model, the second-generation non-dominated sorting genetic algorithm was used to optimize the control points of the mirror compensation surface, and thereby obtain the optimal compensation surface. The experimental results showed that, after optimal compensation, the impeller dimensional error was reduced by 90.17 %, the total pressure ratio increased by 2.89 %, and the isentropic efficiency increased by 7.29 %. Compared to the traditional mirror compensation method, the dimensional accuracy, total pressure ratio, and isentropic efficiency were improved by 28.57 %, 1.56 %, and 4.24 %, respectively. Therefore, this compensation method can simultaneously improve the dimensional accuracy and aerodynamic performance of impellers.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"113 ","pages":"Pages 74-90"},"PeriodicalIF":6.2,"publicationDate":"2024-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142652905","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":"Fractional-order PID feedback synthesis controller including some external influences on insulin and glucose monitoring","authors":"Kottakkaran Sooppy Nisar ,&nbsp;Muhammad Farman ,&nbsp;Khadija Jamil ,&nbsp;Saba Jamil ,&nbsp;Evren Hincal","doi":"10.1016/j.aej.2024.11.017","DOIUrl":"10.1016/j.aej.2024.11.017","url":null,"abstract":"<div><div>The article aims to develop a fractional-order proportional integral derivative (PID) controller to monitor insulin and glucose levels in humans under the influences of stress, excitement, and trauma. A novel fractional-order diabetes mellitus model is proposed, incorporating a nonsingular, nonlocal kernel (Mittag-Leffler function) to account for the effect of epinephrine on suppressing insulin secretion and the dynamics of beta-cell mass. As beta-cell mass increases in the presence of adrenaline, the system remains highly responsive to rising blood glucose and falling insulin levels, driven by the hormone’s suppressive effects. The key advantage of this model is its ability to incorporate these physiological stressors and use fractional-order derivatives to describe the nonlocal dynamics within the system. The innovations of this work include a fractional-order diabetes mellitus model that captures the biological memory and hereditary effects of glucose regulation under stress, and a fractional-order PID controller that offers greater stability and robustness compared to conventional controllers, particularly in managing adrenaline-induced hyperglycemia. The model’s positivity, boundedness, and equilibrium solutions are rigorously analyzed to ensure feasibility. Additionally, a new theorem is proven using fixed-point theory, confirming the existence and uniqueness of the fractional-order model. Ulam–Hyers stability analysis further demonstrates the model’s robustness and well-posedness, while qualitative properties are explored. Numerical simulations to explore which is done by solutions with a two-step Lagrange polynomial for generalized Mittag Leffler kernel showed that prolonged and severe hyperglycemia was caused by regular release of adrenaline into the blood at different fractional order values and fractal dimensions by changing initial values for normal and diabetes patients. PID and controller results are analyzed to increase the stability of the system to monitor and assess of glucose–insulin system with beta cell mass to control the hyperglycemia. Lastly, the results are obtained and visually shown using graphical representations, which provide empirical evidence in support of our theoretical findings. At the end comparison of numerical simulations is constructed to show the efficiency, convergence, and accuracy of proposed techniques at different fractional values with power law and exponential kernels. Numerical simulations, mathematical modeling, and analysis work together to shed light on the dynamics of diabetes mellitus and make important advances in the knowledge and treatment of this common disease.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"113 ","pages":"Pages 60-73"},"PeriodicalIF":6.2,"publicationDate":"2024-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142652959","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":"Quantum features for a system of two qutrits in the presence of power-law potential field","authors":"Bahaaudin M. Raffah ,&nbsp;K. Berrada ,&nbsp;E.M. Khalil ,&nbsp;S. Abdel-Khalek","doi":"10.1016/j.aej.2024.11.022","DOIUrl":"10.1016/j.aej.2024.11.022","url":null,"abstract":"<div><div>In this article, we present a quantum model of the two-qutrit (T-Q) in the Λ-type configuration interacting with a field mode initially in a coherent state of power lower potential. We analyze the dynamical characteristics of this quantum system, taking into account the influences of both the T-Q initial state and the field parameters. We investigate the entanglement between the T-Q and field, the Q–Q state entanglement, as well as the T-Q quantum coherence. We quantify the nonclassical properties of the power lower potential field based on the evolution of the Mandel parameter. The effects of power lower potential parameters on the evolution of quantum measures such as negativity, quantum coherence, von Neumann entropy, and the Mandel parameter are analyzed when the T-Q are initially in the upper and Bell states. Our findings indicate that the system exhibits a quasi-periodic occurrence of maximum entanglement and coherence when the T-Q are initially in the Bell state.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"113 ","pages":"Pages 12-18"},"PeriodicalIF":6.2,"publicationDate":"2024-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142653030","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 computational role of blood nanofluid induced by a stenosed artery with porous medium and thermophoretic particle deposition effects","authors":"Shivalila Hangaragi ,&nbsp;N. Neelima ,&nbsp;N. Beemkumar ,&nbsp;Ankur Kulshreshta ,&nbsp;Umair Khan ,&nbsp;Noreen Sher Akbar ,&nbsp;Mohammad Kanan ,&nbsp;Mona Mahmoud","doi":"10.1016/j.aej.2024.11.010","DOIUrl":"10.1016/j.aej.2024.11.010","url":null,"abstract":"<div><div>The rising prevalence of cardiovascular disorders highlights the need for a deeper understanding of blood flow dynamics in the stenotic arteries to improve diagnostic and therapeutic approaches. This investigation is motivated by the potential of the Casson nanofluids, which exhibit exceptional thermal properties, offering promising applications in medical treatments such as targeted drug delivery and hyperthermia therapy. The present work focuses on understanding the flow behavior of the Casson nanofluids through the stenosed artery under the influence of porosity, thermal radiation, thermophoretic particle diffusion and Stefen blowing. The study makes certain key assumptions, including the consideration of the porous nature of the arterial walls and the impacts of external thermal influences. Based on these assumptions, the governing equations are formulated and transformed into a system of ordinary differential equations using appropriate similarity transformations. These reduced equations are solved numerically using the Runge-Kutta-Fehlberg fourth-fifth-order schemes. The important nondimensional factors affecting fluid velocity, thermal, and concentration profiles are analyzed. Further, the investigation utilizes advanced methods of deep learning to create models and forecast the intricate relationships among various variables, offering a thorough analysis. Escalated values of radiation and curvature parameters will enhance the temperature profile. Deep learning models demonstrate significant efficacy in analyzing and predicting stenotic conditions. The novel outcomes of this research highlight the effectiveness of deep learning models in predicting and analyzing stenotic blood flow conditions, contributing to improved diagnostic approaches to improve the patient's healthcare and reduce the mortality rate.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"113 ","pages":"Pages 32-43"},"PeriodicalIF":6.2,"publicationDate":"2024-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142652957","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 thermo-magnetohydrodynamic particle-fluid suspension moves peristaltically through a porous medium","authors":"N.M. Hafez ,&nbsp;A.M. Abd-Alla ,&nbsp;S.R. Mahmoud","doi":"10.1016/j.aej.2024.10.109","DOIUrl":"10.1016/j.aej.2024.10.109","url":null,"abstract":"<div><div>A computational study is conducted on the magnetohydrodynamic peristaltic circulation of Casson nanofluid within a non-uniform conduit when Joule heating, thermal radiation, and combined mass/heat transportation impacts are present and the porous medium is saturated. The preparation of nanofluid involves the suspension of copper oxide nanoparticles in blood, with blood serving as the base fluid in this instance. Basic flow equations are linearized mathematically by assuming a high wavelength and a low Reynolds number. For both the fluid and particle phases, analytical formulae for temperature, velocity, concentration profiles, and volumetric flow rate are provided. Numerical integration is applied for estimating the friction force and the parameters of the pumping rate. The impact of the model’s different parameters is shown graphically in detail using the Mathematica program. The skin friction coefficient behavior as well as the Sherwood and Nusselt numbers behavior have been graphically illustrated for the relevant parameters. Notably, raising the medium permeability, Casson parameter, and Hartmann number improve temperature fields, velocity, Sherwood number, and skin friction coefficient; however, they have a reverse effect on concentration profiles and Nusselt number in the range <span><math><mrow><mo>−</mo><mn>1</mn><mo>&lt;</mo><mi>y</mi><mo>&lt;</mo><mn>1</mn></mrow></math></span>. The fluid bolus shrinks in size and quantity in response to rising Hartmann numbers, Casson parameters, and medium permeability values. In addition to managing blood flow during surgery by adjusting magnetic field intensity, the current study has biomechanical implications for cancer therapy, medication administration, and chyme motility regulation in the gastrointestinal tract.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"112 ","pages":"Pages 598-632"},"PeriodicalIF":6.2,"publicationDate":"2024-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142663876","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":"Chaos Game Optimization with stacked LSTM sequence to sequence autoencoder for malware detection in IoT cloud environment","authors":"Moneerah Alotaibi ,&nbsp;Ghadah Aldehim ,&nbsp;Mashael Maashi ,&nbsp;Mashael M. Asiri ,&nbsp;Faheed A.F. Alrslani ,&nbsp;Sultan Refa Alotaibi ,&nbsp;Ayman Yafoz ,&nbsp;Raed Alsini","doi":"10.1016/j.aej.2024.10.102","DOIUrl":"10.1016/j.aej.2024.10.102","url":null,"abstract":"<div><div>Malware detection in Internet of Things (IoT) cloud platforms is a crucial security system for securing data and devices' integrity, secrecy, and availability. IoT devices are linked to cloud-based services offering storage, calculating, and analytics abilities. However, these devices are also exposed to malware attacks that could cause significant damage. Malware detection in IoT cloud platforms involves analyzing and identifying potential threats like Trojans, viruses, ransomware, and worms. It is done through several processes, including behavior-based detection, signature-based detection, and anomaly-based detection. The study proposes a Chaos Game Optimization with improved deep learning for Malware Detection (CGOIDL-MD) technique in the IoT cloud platform. The proposed CGOIDL-MD technique majorly concentrates on the automated detection and classification of malware in the IoT cloud framework. The CGOIDL-MD method applies the CGO-based feature subset selection (CGO-FSS) approach to select features. Besides, the stacked long short-term memory sequence-to-sequence autoencoder (SLSTM-SSAE) approach was exploited for malware classification and detection. Moreover, the arithmetic optimization algorithm (AOA) technique was exploited for the hyperparameter selection technique. The simulation outcomes of the CGOIDL-MD technique were tested on the malware dataset, and the outcome can be studied from different perspectives. The experimentation outcomes illustrate the betterment of the CGOIDL-MD technique under various measures.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"112 ","pages":"Pages 688-700"},"PeriodicalIF":6.2,"publicationDate":"2024-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142663867","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":"Trustworthy collaborative evaluation of multi-service subjects in the cloud manufacturing model","authors":"Tao Yang,&nbsp;Yihuan Ding,&nbsp;Wei Chen","doi":"10.1016/j.aej.2024.11.021","DOIUrl":"10.1016/j.aej.2024.11.021","url":null,"abstract":"<div><div>In the context of cloud manufacturing, challenges related to trust, including malicious deception and dishonest feedback, are exacerbated by information asymmetry among platform participants. To address these issues, a novel approach for evaluating collaboration credibility among multi-service subjects within the cloud manufacturing framework is introduced. Initially, an evaluation index system is constructed, incorporating both internal and external data from the platform. This system is framed around four critical dimensions: subject characteristics, service characteristics, product characteristics, and task characteristics. The attribute weights are determined using an integrated assignment method. Subsequently, to effectively address the issues of ambiguity, uncertainty and randomness of evaluation information in the integrated evaluation process, this paper proposed a comprehensive evaluation model. This model capitalizes on the strengths of intuitionistic fuzzy sets (IFSs) and cloud models in converting qualitative assessments into quantitative evaluations, and leverages the method of approximation of the order of ideal solutions (TOPSIS) to carry out a comprehensive assessment of the degree of trustworthy collaboration of the service subject. The practicality and validity of the proposed methodology are demonstrated through a case study analysis, which confirms the model's effectiveness in enhancing the reliability of collaborative evaluations under the cloud manufacturing model.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"113 ","pages":"Pages 1-11"},"PeriodicalIF":6.2,"publicationDate":"2024-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142653031","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":"IoT-based approach to multimodal music emotion recognition","authors":"Hanbing Zhao ,&nbsp;Ling Jin","doi":"10.1016/j.aej.2024.10.059","DOIUrl":"10.1016/j.aej.2024.10.059","url":null,"abstract":"<div><div>With the rapid development of Internet of Things (IoT) technology, multimodal emotion recognition has gradually become an important research direction in the field of artificial intelligence. However, existing methods often face challenges in efficiency and accuracy when processing multimodal data. This study aims to propose an IoT-supported multimodal music emotion recognition model that integrates audio and video signals to achieve real-time emotion recognition and classification. The proposed CGF-Net model combines a 3D Convolutional Neural Network (3D-CNN), Gated Recurrent Unit (GRU), and Fully Connected Network (FCN). By effectively fusing multimodal data, the model enhances the accuracy and efficiency of music emotion recognition. Extensive experiments were conducted on two public datasets, DEAM and DEAP, and the results demonstrate that CGF-Net performs exceptionally well in various emotion recognition tasks, particularly achieving high accuracy and F1 scores in recognizing positive emotions such as ”Happy” and ”Relax.” Compared to other benchmark models, CGF-Net shows significant advantages in both accuracy and stability. This study presents an effective solution for multimodal emotion recognition, demonstrating its broad potential in applications such as intelligent emotional interaction and music recommendation systems.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"113 ","pages":"Pages 19-31"},"PeriodicalIF":6.2,"publicationDate":"2024-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142652922","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}