Hamid Reza Khajeha, Mansoor Fateh, Vahid Abolghasemi
{"title":"Diagnosis of glaucoma using multi‐scale attention block in convolution neural network and data augmentation techniques","authors":"Hamid Reza Khajeha, Mansoor Fateh, Vahid Abolghasemi","doi":"10.1002/eng2.12866","DOIUrl":"https://doi.org/10.1002/eng2.12866","url":null,"abstract":"Glaucoma is defined as an eye disease leading to vision loss due to the optic nerve damage. It is often asymptomatic, thus, timely diagnosis and treatment is crucial. In this article, we propose a novel approach for diagnosing glaucoma using deep neural networks, trained on fundus images. Our proposed approach involves several key steps, including data sampling, pre‐processing, and classification. To address the data imbalance issue, we employ a combination of suitable image augmentation techniques and Multi‐Scale Attention Block (MAS Block) architecture in our deep neural network model. The MAS Block is a specific architecture design for CNNs that allows multiple convolutional filters of various sizes to capture features at several scales in parallel. This will prevent the over‐fitting problem and increases the detection accuracy. Through extensive experiments with the ACRIMA dataset, we demonstrate that our proposed approach achieves high accuracy in diagnosing glaucoma. Notably, we recorded the highest accuracy (97.18%) among previous studies. The results from this study reveal the potential of our approach to improve early detection of glaucoma and offer more effective treatment strategies for doctors and clinicians in the future. Timely diagnosis plays a crucial role in managing glaucoma since it is often asymptomatic. Our proposed method utilizing deep neural networks shows promise in enhancing diagnostic accuracy and aiding healthcare professionals in making informed decisions.","PeriodicalId":502604,"journal":{"name":"Engineering Reports","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140251325","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Enhancing fire‐resistant design of reinforced concrete beams by investigating the influence of reliability‐based analysis","authors":"János Szép, M. Movahedi Rad, M. Habashneh","doi":"10.1002/eng2.12879","DOIUrl":"https://doi.org/10.1002/eng2.12879","url":null,"abstract":"A depth investigation into the impact of high temperatures on the load‐bearing capacity of reinforced concrete beams in the case of probabilistic design is presented in this paper, employing advanced finite element analysis techniques. This study addresses a critical knowledge gap in the design of fire‐resistant concrete structures, with specific emphasis on the function of concrete cover. The research aims to enhance the overall safety and reliability of concrete buildings under high temperature conditions by providing valuable insights into the behavior of reinforced concrete beams under thermal loading. The analysis incorporates reliability‐based modeling to account for uncertainties in temperature distribution within the beams. A validated finite element model is employed to simulate the performance of reinforced concrete beams at elevated temperatures. By considering various concrete cover thicknesses and heat distribution scenarios, the influence of these factors on the load‐bearing capacity is thoroughly examined. The results underscore the importance of augmenting the concrete cover to enhance the load‐carrying capacity of the beams. Furthermore, the study examines the impact of temperature distribution uncertainties, unveiling diverse load capacities associated with different configurations of concrete cover.","PeriodicalId":502604,"journal":{"name":"Engineering Reports","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140252513","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Chengqiang Xuan, Yangsong Zhang, Wentao Xu, Xiaozhao Li, Ning Zhang
{"title":"Beishan exploration tunnel surrounding rock discontinuity identification based on structure from motion photogrammetry technology","authors":"Chengqiang Xuan, Yangsong Zhang, Wentao Xu, Xiaozhao Li, Ning Zhang","doi":"10.1002/eng2.12882","DOIUrl":"https://doi.org/10.1002/eng2.12882","url":null,"abstract":"The Beishan Exploration Tunnel (BET) is a facility built to develop technologies associated with the safety of China's first high‐level radioactive nuclear waste(HLW) disposal. The surrounding rock discontinuity identification is a key research topic in BET, which could provide essential geological data for future HLW disposal stability and integrity research. This article presents the rock discontinuity identification research progress in BET based on Structure from Motion (SfM) photogrammetry technology. The discontinuity identification algorithm is improved by introducing the region‐growing algorithm to optimize the candidate subplane. This algorithm automatically picks the seed, avoids human intervention, and thus increases the work efficiency of the discontinuity identification. The FCM method is improved by embedding with the CFSFDP algorithm in the discontinuity sets grouping. The CFSFDP algorithm coincides well with the Fisher distribution of discontinuity orientations, which is suitable for the Beishan situation. A parallel scheme is used when implementing the method, which accelerates the discontinuity calculation. This improved rock discontinuity identification method was tested on a slope above the BET and applied in the BET. The discontinuity identification results were compared with the results from the manual field measurement and the open‐source software DSE. The results show that the improved discontinuity identification method obtains reliable discontinuity data and costs less time and human workload than the other two methods. The surrounding rock discontinuity identification research provides a powerful tool for the Beishan HLW disposal geological investigation.","PeriodicalId":502604,"journal":{"name":"Engineering Reports","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140254162","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Use of instructional videos to teach mechanical systems analysis based on the finite element method in a class with local and overseas students","authors":"Selim Bozkurt","doi":"10.1002/eng2.12880","DOIUrl":"https://doi.org/10.1002/eng2.12880","url":null,"abstract":"Instructional videos have the advantage of delivering visual and verbal learning materials simultaneously and they can be used for teaching. The aim of this study is to evaluate the learning outcomes in Mechanical Systems Analysis based on the Finite Element Method for video‐based teaching blended with face‐to‐face education. Forty‐five students whose first languages are English, Mandarin and others participated in a survey to evaluate learning outcomes. The learning outcomes were analyzed using the one‐sample Chi‐square test or binomial test. The correlation between the usefulness of the text‐based and video‐based learning materials and the first language of the students was analyzed using the Pearson Chi‐square test. P values smaller than 0.05 were assumed to be statistically significant. Overall 34 students found video‐based learning materials very useful whereas 10 students found them useful resulting in a statistically significant difference. Twenty‐four students found text‐based learning materials very useful whereas 20 students found them useful without statistically significant difference. Student cohorts speaking English and Mandarin as their first language found video‐based learning materials significantly very useful. Video‐based learning materials can be used to improve learning outcomes in courses with computer applications and students can benefit from a blended teaching strategy regardless of their first language.","PeriodicalId":502604,"journal":{"name":"Engineering Reports","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140258729","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Yunlong Luo, Christopher T. Gibson, Youhong Tang, Xian Zhang, Ravi Naidu, Cheng Fang
{"title":"Microplastic and nanoplastic debris left behind by a plastic water tank subjected to a mimicked bushfire","authors":"Yunlong Luo, Christopher T. Gibson, Youhong Tang, Xian Zhang, Ravi Naidu, Cheng Fang","doi":"10.1002/eng2.12875","DOIUrl":"https://doi.org/10.1002/eng2.12875","url":null,"abstract":"Little is known about the catastrophic bushfire from a micro‐pollution point of view, and there is also very limited understanding of the emerging contamination of microplastics and nanoplastics. Upon exposure to fire, plastic items, such as water tanks, may release a substantial quantity of microplastics and nanoplastics, as characterized in this study through the analysis of residual debris. Using Raman imaging with the scanning pixel size down to 100 nm × 100 nm, we over‐scan the sample surface to collect a hyperspectral matrix. In order to map and convert the scanning hyperspectral matrix to an image, we compare and advance the chemometrics of algorithms, including logic and principal component analysis (PCA), to extract the weak signal of microplastics and particularly nanoplastics, which enables us to directly visualize the different degrees of burning. By doing so, we can identify the microplastics and nanoplastics down to ˜100 nm, which means that we can break through the diffraction limit of the laser which is ˜296 nm (λ/2NA) to capture nanoplastics. Using statistical analysis, we estimate that 1.4–4.7 million micro‐ and nanoplastics per cm2 can be left behind by the mimicked‐bushfire‐burned plastic tank. This study suggests that bushfire can accelerate the release of micro‐ and nanoplastics in the environment. This study not only contributes essential insights into the micro‐pollution consequences of fire burning but also underscores the urgency of addressing this understudied aspect to inform environmental conservation strategies and public health measures.","PeriodicalId":502604,"journal":{"name":"Engineering Reports","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140261400","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Adjustable graphene disk‐based THz absorber for biomedical sensing: Theoretical description","authors":"Masoud Soltani Zanjani, Hassan Sadrnia","doi":"10.1002/eng2.12871","DOIUrl":"https://doi.org/10.1002/eng2.12871","url":null,"abstract":"As a basic building block, the THz wave absorber has intense imaging, sensing, and nondestructive testing applications. There are several methods for tuning THz absorbers, including electricity modulation, light modulation, mechanical tuning, using phase change materials, liquid crystal, flexible materials, MEMS technology, and thermally tuning vanadium dioxide. The choice of tuning method depends on the specific application and the desired performance characteristics of the THz absorber. In this work, we report a theoretical description of mechanically tunable THz absorber based on overlapping periodic arrays of graphene nano‐disks. The basis of this work is based on the movement of a dielectric surface covered on both sides with graphene disks. This surface moves on a fixed plane while the distance between these two surfaces is free space. Also, the fixed surface consists of a relatively thick layer of gold at the bottom, dielectric on it, and graphene disk patterns on the dielectric. Now, by moving the movable surface in the horizontal direction, it is possible to adjust the amount of absorption in different frequencies of the terahertz (THz) band. Additionally, an equivalent RLC circuit model is developed and theoretical results match with simulated data. The proposed mechanically tunable THz absorber can be exploited in various emerging applications such as sensing due to its capability of covering all of the THz gap and beyond with multiple absorption peaks.","PeriodicalId":502604,"journal":{"name":"Engineering Reports","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140266334","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Duha Mohamed Adam Bakhit, Lawrence Nderu, Antony Ngunyi
{"title":"A hybrid neural network model based on transfer learning for Arabic sentiment analysis of customer satisfaction","authors":"Duha Mohamed Adam Bakhit, Lawrence Nderu, Antony Ngunyi","doi":"10.1002/eng2.12874","DOIUrl":"https://doi.org/10.1002/eng2.12874","url":null,"abstract":"Sentiment analysis, a method used to classify textual content into positive, negative, or neutral sentiments, is commonly applied to data from social media platforms. Arabic, an official language of the United Nations, presents unique challenges for sentiment analysis due to its complex morphology and dialectal diversity. Compared to English, research on Arabic sentiment analysis is relatively scarce. Transfer learning, which applies the knowledge learned from one domain to another, can address the limitations of training time and computational resources. However, the development of transfer learning for Arabic sentiment analysis is still underdeveloped. In this study, we develop a new hybrid model, RNN‐BiLSTM, which merges recurrent neural networks (RNN) and bidirectional long short‐term memory (BiLSTM) networks. We used Arabic bidirectional encoder representations from transformers (AraBERT), a state‐of‐the‐art Arabic language pre‐trained transformer‐based model, to generate word‐embedding vectors. The RNN‐BiLSTM model integrates the strengths of RNN and BiLSTM, including the ability to learn sequential dependencies and bidirectional context. We trained the RNN‐BiLSTM model on the source domain, specifically the Arabic reviews dataset (ARD). The RNN‐BiLSTM model outperforms the RNN and BiLSTM models with default parameters, achieving an accuracy of 95.75%. We further applied transfer learning to the RNN‐BiLSTM model by fine‐tuning its parameters using random search. We compared the performance of the fine‐tuned RNN‐BiLSTM model with the RNN and BiLSTM models on two target domain datasets: ASTD and Aracust. The results showed that the fine‐tuned RNN‐BiLSTM model is more effective for transfer learning, achieving an accuracy of 95.44% and 96.19% on the ASTD and Aracust datasets, respectively.","PeriodicalId":502604,"journal":{"name":"Engineering Reports","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140081228","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Tanvir Ahmed, Md. Choyon Islam, Md. Alamin Hossain Pappu, S. Mostaque, B. K. Mondal, J. Hossain
{"title":"A highly efficient n‐CdS/p‐Ag2S/p+‐SnS thin film solar cell: Design and simulation","authors":"Tanvir Ahmed, Md. Choyon Islam, Md. Alamin Hossain Pappu, S. Mostaque, B. K. Mondal, J. Hossain","doi":"10.1002/eng2.12849","DOIUrl":"https://doi.org/10.1002/eng2.12849","url":null,"abstract":"Silver sulfide (Ag2S) chalcogenide compound can be a viable absorber in the applications of thin film solar cells owing to its optimum bandgap of 1.1 eV and high absorption coefficient. Herein, we propose a novel Ag2S‐based n‐CdS/p‐Ag2S/p+‐SnS double‐heterojunction solar cell. The numerical analysis of the device has been performed with SCAPS‐1D (Solar Cell Capacitance Simulator). In the case of single heterojunction, n‐CdS/p‐Ag2S manifests an efficiency of 19.75%, where VOC = 0.66 V, JSC = 36.99 mA/cm2 and FF = 81.50%. However, Ag2S‐based double‐heterojunction device with optimized structure provides the efficiency of 29.51% with VOC = 0.81 V, JSC = 42.81 mA/cm2 and FF =85.24%. The noteworthy augmentation of VOC and JSC in double‐heterojunction results from the reduction in surface recombination velocity and rise in built‐in voltage in the p‐Ag2S/p+‐SnS hetero‐interfaces that promote the higher efficiency of the device. These theoretical insights indicate a path for fabrication of an efficient Ag2S based thin film solar cell.","PeriodicalId":502604,"journal":{"name":"Engineering Reports","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-01-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139599031","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Synergistic mechanism of amidation on corrosion inhibition of laurate triethanolamine for HT300 gray cast iron in NaCl solution","authors":"Zhijun Hang","doi":"10.1002/eng2.12843","DOIUrl":"https://doi.org/10.1002/eng2.12843","url":null,"abstract":"Sarcosine was inserted between fatty chain and carboxylic group of lauric acid to obtain lauroyl sarcosine, and the corrosion inhibition of lauroyl sarcosine triethanolamine (LSTEA) was significantly improved. The synergistic mechanism of amide group and lauric acid was investigated by comparing the corrosion behavior on the surface of HT300 gray cast iron in 330 mg/L NaCl solution. The results showed that both lauryl triethanolamine (LATEA) and LSTEA could prevent corrosion. At 298 K, when 1000 mg/L inhibitor was added, the inhibition rates are 71.93% and 83.89%, respectively. The morphology analysis also verified that LSTEA had better inhibition properties than LATEA. Comparing the adsorption parameters and Density Functional Theory (DFT) calculation results, it was found that LATEA and LSTEA could spontaneously adsorb on the surface of gray cast iron as monolayer to form a stable protective layer. However, the chelation of amide group and the electron absorption effect could make the electron density distributed at the polar end of the whole molecule, covering the active sites at the interface to the maximum extent, so that LSTEA has more excellent corrosion inhibition for gray cast iron.","PeriodicalId":502604,"journal":{"name":"Engineering Reports","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-01-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139598110","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Non‐uniform voltage distribution characteristics of metallized film capacitors in flexible HVDC projects","authors":"Zheng Zhao, Shangfu Teng, Shuo Liu, Zixuan Zhao, Cong Wang, Youping Tu","doi":"10.1002/eng2.12844","DOIUrl":"https://doi.org/10.1002/eng2.12844","url":null,"abstract":"The problem of non‐uniform voltage distribution in the internal element of metallized film capacitors in flexible HVDC transmission systems exists, the influence of electrical parameters of dielectric and metal copper row are not considered in the existing metallized film capacitor equivalent circuit model. In this paper, the conductance of biaxially oriented polypropylene film (BOPP) for metalized film capacitors is measured at different electric field intensity and dielectric properties at different frequencies. The current density distribution and voltammetric properties of the metalized film capacitor elements under AC and DC superimposed voltages are calculated by the finite element method, and the voltammetric properties of the copper row considering the skin effect are derived. The equivalent circuit model of the metalized film capacitor under the AC‐DC superposition voltage is proposed. The simulation results of the capacitor equivalent circuit model show that the voltage distribution of the internal elements of the capacitor is uniform at low frequency AC voltages (<102 Hz), and the voltage amplitude and phase difference between the elements of the capacitor gradually increases with increasing AC voltage frequency. At an AC voltage frequency of 105 Hz, the difference in magnitude between the two capacitor elements on the same copper row was up to 2.01% and the phase difference was 13.5%, while the difference in magnitude between capacitors at the same horizontal position on different copper rows was up to 56.8% and the phase difference was 10.44%. The results of this paper provide some guidance for the modeling of the internal components of metalized film capacitors, the calculation of voltage distribution and the structural optimization design.","PeriodicalId":502604,"journal":{"name":"Engineering Reports","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139602576","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}