Journal of Engineering Research最新文献

Leveraging edge detection techniques to enhance Arabic sign language static-gesture recognition using deep learning 利用边缘检测技术增强使用深度学习的阿拉伯手语静态手势识别

IF 2.2 4区工程技术 Q3 ENGINEERING, MULTIDISCIPLINARY

Journal of Engineering Research

Pub Date : 2026-03-01 Epub Date: 2025-09-24 DOI: 10.1016/j.jer.2025.09.011

Wahiba Ismaiel , Lilia kechiche , Yassine Aribi , Omer Salih Dawood Omer , Walied Merghani

Recently, there has been a growing interest in developing solutions to address communication barriers for the deaf and hard-of-hearing community. Sign language is the primary language of this group. Computer vision technology is used to process sign language due to its ease of application. Sign language recognition involves the use of technology to bridge communication gaps and enhance accessibility for individuals who use sign language as their primary form of communication. Many researchers have presented various methods to facilitate communication, among others. These methods include sign language recognition techniques, translation between sign and text or audio, and hand gesture identification, among others. We proposed an effective approach to improve the feature extraction process for Arabic sign gesture recognition. Feature extraction is a crucial aspect of deep learning models because it facilitates data processing, improves performance, and helps interpret results. This process also enables models to manage large datasets more efficiently. We presented two deep learning models: the agile convolutional neural network (ASLR_CNN) and ResNet50, to improve the comprehensiveness of the extracted features. These models were combined with the Canny Edge Detector (CED), which identifies the edges of Arabic hand gestures, as well as the complex features extracted from the edges by the proposed models. To evaluate the effectiveness of our methodology, we trained the proposed models on two public datasets: AASL and ArASL. The performance of these models was evaluated using a variety of metrics, including accuracy, precision, recall, F-score, and confusion matrix. The results indicated that both the ASLR_CNN and ResNet50 models achieved high accuracy on the ArASL dataset, reaching 97.14 % and 96.88 %, respectively. In contrast, the accuracy dropped to 89.49 % and 86.12 % for the ASLR_CNN and ResNet50 models, respectively, when using the AASL dataset.

最近，人们对开发解决聋人和听障群体沟通障碍的解决方案越来越感兴趣。手语是这个群体的主要语言。计算机视觉技术因其易于应用而被用于处理手语。手语识别涉及使用技术来弥合沟通差距，并提高使用手语作为主要沟通形式的个人的可及性。许多研究人员提出了各种各样的方法来促进交流。这些方法包括手语识别技术、手语与文本或音频之间的翻译以及手势识别等。提出了一种改进阿拉伯手势识别特征提取过程的有效方法。特征提取是深度学习模型的一个关键方面，因为它简化了数据处理，提高了性能，并有助于解释结果。这个过程还使模型能够更有效地管理大型数据集。为了提高特征提取的全面性，我们提出了两种深度学习模型：敏捷卷积神经网络（ASLR_CNN）和ResNet50。这些模型与Canny边缘检测器（CED）相结合，Canny边缘检测器识别阿拉伯手势的边缘，以及由所提出的模型从边缘提取的复杂特征。为了评估我们方法的有效性，我们在两个公共数据集上训练了所提出的模型：AASL和ArASL。使用各种指标评估这些模型的性能，包括准确性、精密度、召回率、f分数和混淆矩阵。结果表明，ASLR_CNN和ResNet50模型在ArASL数据集上均取得了较高的准确率，分别达到97.14 %和96.88 %。相比之下，当使用AASL数据集时，ASLR_CNN和ResNet50模型的准确率分别下降到89.49 %和86.12 %。

{"title":"Leveraging edge detection techniques to enhance Arabic sign language static-gesture recognition using deep learning","authors":"Wahiba Ismaiel , Lilia kechiche , Yassine Aribi , Omer Salih Dawood Omer , Walied Merghani","doi":"10.1016/j.jer.2025.09.011","DOIUrl":"10.1016/j.jer.2025.09.011","url":null,"abstract":"<div><div>Recently, there has been a growing interest in developing solutions to address communication barriers for the deaf and hard-of-hearing community. Sign language is the primary language of this group. Computer vision technology is used to process sign language due to its ease of application. Sign language recognition involves the use of technology to bridge communication gaps and enhance accessibility for individuals who use sign language as their primary form of communication. Many researchers have presented various methods to facilitate communication, among others. These methods include sign language recognition techniques, translation between sign and text or audio, and hand gesture identification, among others. We proposed an effective approach to improve the feature extraction process for Arabic sign gesture recognition. Feature extraction is a crucial aspect of deep learning models because it facilitates data processing, improves performance, and helps interpret results. This process also enables models to manage large datasets more efficiently. We presented two deep learning models: the agile convolutional neural network (ASLR_CNN) and ResNet50, to improve the comprehensiveness of the extracted features. These models were combined with the Canny Edge Detector (CED), which identifies the edges of Arabic hand gestures, as well as the complex features extracted from the edges by the proposed models. To evaluate the effectiveness of our methodology, we trained the proposed models on two public datasets: AASL and ArASL. The performance of these models was evaluated using a variety of metrics, including accuracy, precision, recall, F-score, and confusion matrix. The results indicated that both the ASLR_CNN and ResNet50 models achieved high accuracy on the ArASL dataset, reaching 97.14 % and 96.88 %, respectively. In contrast, the accuracy dropped to 89.49 % and 86.12 % for the ASLR_CNN and ResNet50 models, respectively, when using the AASL dataset.</div></div>","PeriodicalId":48803,"journal":{"name":"Journal of Engineering Research","volume":"14 1","pages":"Pages 896-915"},"PeriodicalIF":2.2,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147454235","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Analysis of geometric dimensioning and tolerancing in sustainable hard drilling using vegetable oil-based MQL 植物油基MQL可持续硬钻的几何尺寸及公差分析

IF 2.2 4区工程技术 Q3 ENGINEERING, MULTIDISCIPLINARY

Journal of Engineering Research

Pub Date : 2026-03-01 Epub Date: 2025-06-02 DOI: 10.1016/j.jer.2025.05.012

Amir Rasti , Ahmad Reza Omiddodman, Mehdi Ustad

This study investigates the influence of cutting parameters on the hole precision in hard drilling of AISI 4340, with a particular emphasis on vegetable-based minimum quantity lubrication (MQL) as a green machining approach. The effect of key parameters including cutting speed, feed rate, and workpiece hardness was analyzed on the cutting force and hole precision using soybean oil as the cutting fluid. The results showed a stable trend in the time history of cutting forces during the cutting process, with no significant wear or other disruptions, indicating that vegetable oil can provide effective lubrication during hard drilling. The axial cutting force was lower than 8000 N in the studied range of cutting parameters. The findings also revealed that feed rate is the most important factor influencing output characteristics, which deteriorated hole diameter, circularity, and cylindricity tolerances of up to 200 %. This is especially evident with softer materials (30 HRC). Furthermore, workpiece hardness had a minor effect on circularity, but a significant impact on straightness and overall cylindricity up to 56 %. Soybean oil-assisted MQL resulted in tolerances magnitude of less than 60 μm, demonstrating its effectiveness in hard drilling AISI 4340.

本研究探讨了切削参数对AISI 4340硬钻孔精度的影响，特别强调了基于蔬菜的最小量润滑（MQL）作为一种绿色加工方法。以大豆油为切削液，分析了切削速度、进给速度、工件硬度等关键参数对切削力和孔精度的影响。结果表明，在切削过程中，切削力的时间历史趋势稳定，没有明显的磨损或其他中断，表明植物油可以在硬钻过程中提供有效的润滑。在所研究的切削参数范围内，轴向切削力均小于8000 N。研究结果还表明，进给量是影响输出特性的最重要因素，它使孔径、圆度和圆柱度公差降低了200 %。这对于较软的材料（30 HRC）尤其明显。此外，工件硬度对圆度的影响较小，但对直线度和整体圆柱度的影响显著，高达56% %。大豆油辅助MQL的公差小于60 μm，证明了其在硬钻进AISI 4340中的有效性。

{"title":"Analysis of geometric dimensioning and tolerancing in sustainable hard drilling using vegetable oil-based MQL","authors":"Amir Rasti , Ahmad Reza Omiddodman, Mehdi Ustad","doi":"10.1016/j.jer.2025.05.012","DOIUrl":"10.1016/j.jer.2025.05.012","url":null,"abstract":"<div><div>This study investigates the influence of cutting parameters on the hole precision in hard drilling of AISI 4340, with a particular emphasis on vegetable-based minimum quantity lubrication (MQL) as a green machining approach. The effect of key parameters including cutting speed, feed rate, and workpiece hardness was analyzed on the cutting force and hole precision using soybean oil as the cutting fluid. The results showed a stable trend in the time history of cutting forces during the cutting process, with no significant wear or other disruptions, indicating that vegetable oil can provide effective lubrication during hard drilling. The axial cutting force was lower than 8000 N in the studied range of cutting parameters. The findings also revealed that feed rate is the most important factor influencing output characteristics, which deteriorated hole diameter, circularity, and cylindricity tolerances of up to 200 %. This is especially evident with softer materials (30 HRC). Furthermore, workpiece hardness had a minor effect on circularity, but a significant impact on straightness and overall cylindricity up to 56 %. Soybean oil-assisted MQL resulted in tolerances magnitude of less than 60 μm, demonstrating its effectiveness in hard drilling AISI 4340.</div></div>","PeriodicalId":48803,"journal":{"name":"Journal of Engineering Research","volume":"14 1","pages":"Pages 315-323"},"PeriodicalIF":2.2,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147453734","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

MSpace: Multi security namespace management for containers MSpace：用于容器的多安全命名空间管理

IF 2.2 4区工程技术 Q3 ENGINEERING, MULTIDISCIPLINARY

Journal of Engineering Research

Pub Date : 2026-03-01 Epub Date: 2025-05-05 DOI: 10.1016/j.jer.2025.04.007

Hao Liang , Gongshan He , Jinhu Jiang

Existing system security frameworks like LSM are primarily designed for the operating system kernel and are not applicable to user-level container methods. This is primarily because the system security framework is designed and implemented within the operating system kernel, which is shared across the entire system and cannot fulfill the isolation requirements of containers. The security policies of multiple containers are intermixed in the underlying system kernel, which impacts each other and increases the overhead of monitoring, leading to inefficiencies in cloud servers running numerous containers. Improvements to the security of containers are ad hoc and partial, often lacking support for the universal SELinux mode. In this paper, we introduce MSpace, an enhanced kernel SELinux framework that supports containerized secure spaces with individual security policies and mechanisms. To enhance security, we first introduce an instantiation mechanism for virtual hook tables, which, in conjunction with the container’s namespace, ensures each has its own instantiated hook tables instead of a system-wide one, thereby isolating secure spaces. Subsequently, a security namespace method was devised to support container-specific private security policies. Lastly, to maintain compatibility, only the instantiation and deallocation interfaces were added while preserving the original interfaces unchanged. The results demonstrate that MSpace effectively alleviates the issue of using SELinux for internal containers, with an average reduction of 2.83 % in system call latency compared to using host SELinux directly.

现有的系统安全框架（如LSM）主要是为操作系统内核设计的，不适用于用户级容器方法。这主要是因为系统安全框架是在操作系统内核中设计和实现的，内核在整个系统中共享，不能满足容器的隔离需求。多个容器的安全策略混合在底层系统内核中，它们相互影响并增加监视开销，导致运行大量容器的云服务器效率低下。对容器安全性的改进是特别的和部分的，通常缺乏对通用SELinux模式的支持。在本文中，我们将介绍MSpace，这是一个增强的内核SELinux框架，它支持具有单独安全策略和机制的容器化安全空间。为了增强安全性，我们首先引入虚拟钩子表的实例化机制，它与容器的命名空间结合起来，确保每个都有自己的实例化钩子表，而不是系统范围的钩子表，从而隔离安全空间。随后，设计了一个安全名称空间方法来支持特定于容器的私有安全策略。最后，为了保持兼容性，只添加实例化和回收接口，同时保持原始接口不变。结果表明，MSpace有效地缓解了将SELinux用于内部容器的问题，与直接使用主机SELinux相比，系统调用延迟平均减少了2.83 %。

{"title":"MSpace: Multi security namespace management for containers","authors":"Hao Liang , Gongshan He , Jinhu Jiang","doi":"10.1016/j.jer.2025.04.007","DOIUrl":"10.1016/j.jer.2025.04.007","url":null,"abstract":"<div><div>Existing system security frameworks like LSM are primarily designed for the operating system kernel and are not applicable to user-level container methods. This is primarily because the system security framework is designed and implemented within the operating system kernel, which is shared across the entire system and cannot fulfill the isolation requirements of containers. The security policies of multiple containers are intermixed in the underlying system kernel, which impacts each other and increases the overhead of monitoring, leading to inefficiencies in cloud servers running numerous containers. Improvements to the security of containers are ad hoc and partial, often lacking support for the universal SELinux mode. In this paper, we introduce MSpace, an enhanced kernel SELinux framework that supports containerized secure spaces with individual security policies and mechanisms. To enhance security, we first introduce an instantiation mechanism for virtual hook tables, which, in conjunction with the container’s namespace, ensures each has its own instantiated hook tables instead of a system-wide one, thereby isolating secure spaces. Subsequently, a security namespace method was devised to support container-specific private security policies. Lastly, to maintain compatibility, only the instantiation and deallocation interfaces were added while preserving the original interfaces unchanged. The results demonstrate that MSpace effectively alleviates the issue of using SELinux for internal containers, with an average reduction of 2.83 % in system call latency compared to using host SELinux directly.</div></div>","PeriodicalId":48803,"journal":{"name":"Journal of Engineering Research","volume":"14 1","pages":"Pages 681-687"},"PeriodicalIF":2.2,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147453809","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Dispatch under pressure: An investigation into the cognitive load of Kuwait’s emergency responders 压力下的调度：对科威特紧急救援人员认知负荷的调查

IF 2.2 4区工程技术 Q3 ENGINEERING, MULTIDISCIPLINARY

Journal of Engineering Research

Pub Date : 2026-03-01 Epub Date: 2025-06-28 DOI: 10.1016/j.jer.2025.06.004

Mohammad Alsager Alzayed , Nourah Alsardi

Emergency dispatchers play a pivotal role in ensuring efficient and effective emergency response systems. Reducing emergency dispatcher cognitive workload is crucial for enhancing response efficiency and accuracy, ultimately saving lives by ensuring rapid and precise coordination of critical resources. This study aims to assess the impact of age, work shift, and experience on the cognitive workload experienced by emergency dispatchers in Kuwait. A series of survey questions, structured around the dimensions of the NASA-TLX, were administered to gather quantitative data from 110 emergency dispatchers. In addition to quantitative analysis, qualitative data were obtained through interviews conducted with 11 dispatchers. Analysis of survey responses revealed elevated NASA-TLX scores among the participants, indicating significant cognitive workload. Results indicated that years of experience significantly influenced the cognitive workload experienced by dispatchers. By categorizing responses into the NASA-TLX dimensions, the study identified the most prevalent factors contributing to cognitive workload among emergency dispatchers. This research provides valuable insights into the cognitive demands faced by emergency dispatchers in Kuwait, highlighting the importance of experience in managing workload effectively. The findings contribute to the development of strategies aimed at optimizing the cognitive ergonomics of emergency dispatch operations, ultimately enhancing the efficiency and quality of emergency response systems.

应急调度员在确保应急系统的高效和有效方面发挥着关键作用。减少紧急调度员的认知工作量对于提高响应效率和准确性至关重要，通过确保关键资源的快速和精确协调，最终挽救生命。本研究旨在评估年龄、轮班和经验对科威特紧急调度员认知工作量的影响。围绕NASA-TLX的尺寸设计了一系列调查问题，从110名紧急调度员那里收集定量数据。除了定量分析外，还通过对11名调度员的访谈获得了定性数据。对调查结果的分析显示，参与者的NASA-TLX得分升高，表明认知负荷显著。结果表明，工作年限对调度员的认知工作量有显著影响。通过将响应分类到NASA-TLX维度，该研究确定了导致紧急调度员认知工作量的最普遍因素。这项研究对科威特紧急调度员面临的认知需求提供了有价值的见解，突出了有效管理工作量经验的重要性。研究结果有助于制定旨在优化应急调度业务认知人体工程学的战略，最终提高应急响应系统的效率和质量。

{"title":"Dispatch under pressure: An investigation into the cognitive load of Kuwait’s emergency responders","authors":"Mohammad Alsager Alzayed , Nourah Alsardi","doi":"10.1016/j.jer.2025.06.004","DOIUrl":"10.1016/j.jer.2025.06.004","url":null,"abstract":"<div><div>Emergency dispatchers play a pivotal role in ensuring efficient and effective emergency response systems. Reducing emergency dispatcher cognitive workload is crucial for enhancing response efficiency and accuracy, ultimately saving lives by ensuring rapid and precise coordination of critical resources. This study aims to assess the impact of age, work shift, and experience on the cognitive workload experienced by emergency dispatchers in Kuwait. A series of survey questions, structured around the dimensions of the NASA-TLX, were administered to gather quantitative data from 110 emergency dispatchers. In addition to quantitative analysis, qualitative data were obtained through interviews conducted with 11 dispatchers. Analysis of survey responses revealed elevated NASA-TLX scores among the participants, indicating significant cognitive workload. Results indicated that years of experience significantly influenced the cognitive workload experienced by dispatchers. By categorizing responses into the NASA-TLX dimensions, the study identified the most prevalent factors contributing to cognitive workload among emergency dispatchers. This research provides valuable insights into the cognitive demands faced by emergency dispatchers in Kuwait, highlighting the importance of experience in managing workload effectively. The findings contribute to the development of strategies aimed at optimizing the cognitive ergonomics of emergency dispatch operations, ultimately enhancing the efficiency and quality of emergency response systems.</div></div>","PeriodicalId":48803,"journal":{"name":"Journal of Engineering Research","volume":"14 1","pages":"Pages 1039-1048"},"PeriodicalIF":2.2,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147453896","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Fire swin: Video anomaly detection using a hybrid model with convolutional layers, fire module, and swin transformer Fire swin：使用卷积层、Fire模块和swin变压器的混合模型进行视频异常检测

IF 2.2 4区工程技术 Q3 ENGINEERING, MULTIDISCIPLINARY

Journal of Engineering Research

Pub Date : 2026-03-01 Epub Date: 2025-08-22 DOI: 10.1016/j.jer.2025.08.016

Abdulrahman Alshalawi, Wadood Abdul, Ghulam Muhammad

There are more than one billion surveillance cameras installed throughout the world that produce enormous volumes of video data on daily basis. Manual search of anomalous events in such huge amounts of data is laborious and extensively time consuming. In contrast, various computer vision methods have been used, and recently deep learning methods have been extensively investigated. However, video anomaly detection in surveillance videos is a complex and challenging task due to varied backgrounds, capturing positions, context, and unexpected events that require high-level semantic understanding and spatiotemporal reasoning. In this paper, we propose an end-to-end novel hybrid model that contains time distributed convolutional layers with a fire module for spatial feature extraction, compression for efficient processing, and a Swin transformer for self-attention mechanism that can capture long-range dependencies and local details. We applied our method to the UCF crime dataset and CUHK Avenue dataset which contains realistic and varied anomalous events with the standard split ratio of used in both UCF crime and CUHK Avenue datasets for training and testing respectively. We demonstrated with extensive experiments that the proposed model achieved 92.20 % accuracy in detecting various anomalies in UCF Crime, and 94.40 % using CUHK dataset, an increase in performance as compared to existing state-of-the-art methods.

全世界安装了超过10亿个监控摄像头，每天产生大量的视频数据。在如此庞大的数据量中手动搜索异常事件是费力且耗时的。相比之下，已经使用了各种计算机视觉方法，最近深度学习方法得到了广泛的研究。然而，监控视频中的视频异常检测是一项复杂而具有挑战性的任务，因为背景不同，捕获位置，上下文和意外事件需要高水平的语义理解和时空推理。在本文中，我们提出了一个端到端的新型混合模型，该模型包含时间分布的卷积层，其中包含用于空间特征提取的fire模块，用于有效处理的压缩，以及用于捕获远程依赖关系和局部细节的自关注机制的Swin变压器。我们将该方法应用于UCF犯罪数据集和中大大道数据集，其中包含现实和变化的异常事件，并分别使用UCF犯罪和中大大道数据集的标准分割率进行训练和测试。我们通过大量的实验证明，所提出的模型在检测UCF犯罪的各种异常方面达到92.20 %的准确率，而在使用中大数据集时达到94.40 %的准确率，与现有的最先进的方法相比，性能有所提高。

{"title":"Fire swin: Video anomaly detection using a hybrid model with convolutional layers, fire module, and swin transformer","authors":"Abdulrahman Alshalawi, Wadood Abdul, Ghulam Muhammad","doi":"10.1016/j.jer.2025.08.016","DOIUrl":"10.1016/j.jer.2025.08.016","url":null,"abstract":"<div><div>There are more than one billion surveillance cameras installed throughout the world that produce enormous volumes of video data on daily basis. Manual search of anomalous events in such huge amounts of data is laborious and extensively time consuming. In contrast, various computer vision methods have been used, and recently deep learning methods have been extensively investigated. However, video anomaly detection in surveillance videos is a complex and challenging task due to varied backgrounds, capturing positions, context, and unexpected events that require high-level semantic understanding and spatiotemporal reasoning. In this paper, we propose an end-to-end novel hybrid model that contains time distributed convolutional layers with a fire module for spatial feature extraction, compression for efficient processing, and a Swin transformer for self-attention mechanism that can capture long-range dependencies and local details. We applied our method to the UCF crime dataset and CUHK Avenue dataset which contains realistic and varied anomalous events with the standard split ratio of used in both UCF crime and CUHK Avenue datasets for training and testing respectively. We demonstrated with extensive experiments that the proposed model achieved 92.20 % accuracy in detecting various anomalies in UCF Crime, and 94.40 % using CUHK dataset, an increase in performance as compared to existing state-of-the-art methods.</div></div>","PeriodicalId":48803,"journal":{"name":"Journal of Engineering Research","volume":"14 1","pages":"Pages 811-819"},"PeriodicalIF":2.2,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147453898","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Assessing the quality and service levels of walkways in the state of Kuwait 评估科威特步道的质量和服务水平

IF 2.2 4区工程技术 Q3 ENGINEERING, MULTIDISCIPLINARY

Journal of Engineering Research

Pub Date : 2026-03-01 Epub Date: 2025-08-08 DOI: 10.1016/j.jer.2025.08.004

Duaij S. AlRukaibi , Ahmed O. Abdulhadi

Walkways are easy, safe, convenient, and healthy routes for pedestrians to walk and participate in other activities such as running, jogging, and aerobic exercise. This paper aims to evaluate different walkways by assessing three comfort levels: physical, psychological, and physiological, represented by a comprehensive environmental walkability index (EWI), which provides a grading system from A to F depending on the quality and service levels of the walkways. The scope of this study was conducted across five different walkways in the state of Kuwait. The evaluation of service level gives values at the macro scale for the condition and infrastructure of the walkway, while the evaluation of quality level looks at the micro-scale of the comfort and quality of walkability for pedestrians. Analytic hierarchy process (AHP) is used to estimate the importance weights of each parameter in comfort levels. The air quality index (AQI) was adopted to analyze the overall ambient air quality level and determine the primary responsible pollutant. Different pollutant concentration data were analyzed on an hourly and monthly basis and compared to EPA’s National Ambient Air Quality Standards (NAAQS) to evaluate the air quality situation in the walkways. The results indicate CO, NO₂, SO_2, and O₃ compliance with NAAQS standards and showed PM₁₀ exceeding permitted levels in afternoon hours and summer months. Elevated levels of PM₁₀ concentration were observed in February 2015 because of the dust storm. AQI analysis results show that PM₁₀ is the primary responsible pollutant. The EWI model assessed the selected walkways and assigned grades for the year 2019, revealing that Ahmadi Walkway (AW) has the highest grade (B) among the walkways because of the high level of facilities and walkway surface quality, while Ali Subah Al Salem Walkway (ASW) obtained the lowest grade (D) because of the lack of facilities, low-quality surface type, and high air quality index. This study provides an integrated assessment that delivers environmental walkability index outcomes to enable professionals to improve quality and service levels in the walkways.

人行道是行人步行和参加跑步、慢跑、有氧运动等其他活动的简单、安全、方便、健康的路线。本文旨在通过评估物理、心理和生理三个舒适度来评价不同的人行道，以综合环境步行指数（EWI）为代表，该指数根据人行道的质量和服务水平提供了从a到F的评分系统。这项研究的范围是在科威特的五个不同的人行道上进行的。服务水平的评价在宏观尺度上给出了人行道条件和基础设施的价值，而质量水平的评价则着眼于微观尺度上行人的舒适度和可步行性的质量。采用层次分析法（AHP）估计舒适度各参数的重要性权重。采用空气质量指数（AQI）分析整体环境空气质量水平，确定主要责任污染物。每小时和每月分析不同的污染物浓度数据，并与美国环保署的国家环境空气质量标准（NAAQS）进行比较，以评估人行道的空气质量状况。结果显示，北京的CO、NO2、SO2和O3均符合国家空气质量标准，PM10在下午和夏季均超过规定标准。由于沙尘暴，2015年2月观测到PM10浓度升高。AQI分析结果表明，PM10是主要负责污染物。EWI模型对2019年选定的人行道和分配的等级进行了评估，结果显示，Ahmadi人行道（AW）由于设施水平和人行道表面质量高，在人行道中获得了最高等级(B)，而Ali Subah Al Salem人行道（ASW）由于缺乏设施，低质量的表面类型和高空气质量指数而获得了最低等级(D)。这项研究提供了一个综合评估，提供环境步行指数结果，使专业人员能够提高人行道的质量和服务水平。

{"title":"Assessing the quality and service levels of walkways in the state of Kuwait","authors":"Duaij S. AlRukaibi , Ahmed O. Abdulhadi","doi":"10.1016/j.jer.2025.08.004","DOIUrl":"10.1016/j.jer.2025.08.004","url":null,"abstract":"<div><div>Walkways are easy, safe, convenient, and healthy routes for pedestrians to walk and participate in other activities such as running, jogging, and aerobic exercise. This paper aims to evaluate different walkways by assessing three comfort levels: physical, psychological, and physiological, represented by a comprehensive environmental walkability index (EWI), which provides a grading system from A to F depending on the quality and service levels of the walkways. The scope of this study was conducted across five different walkways in the state of Kuwait. The evaluation of service level gives values at the macro scale for the condition and infrastructure of the walkway, while the evaluation of quality level looks at the micro-scale of the comfort and quality of walkability for pedestrians. Analytic hierarchy process (AHP) is used to estimate the importance weights of each parameter in comfort levels. The air quality index (AQI) was adopted to analyze the overall ambient air quality level and determine the primary responsible pollutant. Different pollutant concentration data were analyzed on an hourly and monthly basis and compared to EPA’s National Ambient Air Quality Standards (NAAQS) to evaluate the air quality situation in the walkways. The results indicate CO, NO<sub>2</sub>, SO<sub>2,</sub> and O<sub>3</sub> compliance with NAAQS standards and showed PM<sub>10</sub> exceeding permitted levels in afternoon hours and summer months. Elevated levels of PM<sub>10</sub> concentration were observed in February 2015 because of the dust storm. AQI analysis results show that PM<sub>10</sub> is the primary responsible pollutant. The EWI model assessed the selected walkways and assigned grades for the year 2019, revealing that Ahmadi Walkway (AW) has the highest grade (B) among the walkways because of the high level of facilities and walkway surface quality, while Ali Subah Al Salem Walkway (ASW) obtained the lowest grade (D) because of the lack of facilities, low-quality surface type, and high air quality index. This study provides an integrated assessment that delivers environmental walkability index outcomes to enable professionals to improve quality and service levels in the walkways.</div></div>","PeriodicalId":48803,"journal":{"name":"Journal of Engineering Research","volume":"14 1","pages":"Pages 121-137"},"PeriodicalIF":2.2,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147454152","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Corrigendum to “Unraveling the role of sintering temperature on physical, structural and tribological characteristics of ball milled Co28Cr6Mo biomaterial based alloy” [J. Eng. Res. 12 (2024) 571–579] “揭示烧结温度对球磨Co28Cr6Mo生物材料基合金的物理、结构和摩擦学特性的作用”[J]。Eng。Res. 12 (2024) 571-579]

IF 2.2 4区工程技术 Q3 ENGINEERING, MULTIDISCIPLINARY

Journal of Engineering Research

Pub Date : 2026-03-01 Epub Date: 2025-12-30 DOI: 10.1016/j.jer.2025.12.010

Mohammed Farah , Mamoun Fellah , Dikra Bouras , Naouel Hezil , Abderrachid Becheri , Barille Regis , Henda Daoudi , Alex Montagne , Tmader Alballa , Abd El-Wahed Khalifa Hamiden

引用次数: 0

Hybrid numerical–machine learning framework for heat transfer prediction in TiO₂ nanofluid microtubes 纳米流体微管传热预测的混合数值-机器学习框架

IF 2.2 4区工程技术 Q3 ENGINEERING, MULTIDISCIPLINARY

Journal of Engineering Research

Pub Date : 2026-03-01 Epub Date: 2025-12-22 DOI: 10.1016/j.jer.2025.12.007

Muhammed Said Ates , Ebru Akpinar , Cagri Kaymak , Mehmet Das

Heating and cooling processes using microtubes are crucial for the thermal management of electronic devices. The investigation of such complex conjugate heat transfer systems via traditional numerical methods demands significant computational time and resources. Therefore, the necessity of this study arises from the need for faster, cost-effective, and highly accurate prediction models to accelerate the design and optimization of micro-scale cooling systems. The primary aim of this study is to numerically investigate the thermal performance of a water-based TiO₂ nanofluid flowing through thick-walled microtubes and, crucially, to develop a robust hybrid numerical–machine learning framework capable of offering high predictive accuracy. This study aims to address a gap in the literature. The model considers an infinitely long microtubes with a heated section of length L, where a constant surface heat flux is applied. The governing two-dimensional laminar flow and energy equations, expressed in cylindrical coordinates, were non-dimensionalized, discretized via finite and central difference schemes, and solved numerically. Viscous damping and slip velocity boundary conditions were also incorporated. Results show that conjugate heat transfer effects intensify with increasing wall thickness but diminish with lower wall–fluid interface and Peclet parameters. These parameters influence transient and steady-state behavior differently. The distinctive contribution of this work lies in the data-driven modeling and prediction of the microtube heat transfer parameter (Qwi) using six regression methods: Linear Regression, Random Forest, Support Vector Regression (RBF kernel), Extreme Gradient Boosting (XGBoost), Multi-Layer Perceptron (MLP), and one-dimensional Convolutional Neural Network (1D-CNN). All models achieved high predictive accuracy (R² > 0.96), with ensemble and kernel-based methods—particularly XGBoost and SVR—producing the best results (R² = 0.9999, RMSE < 0.001). The findings demonstrate that while tree- and kernel-based models outperform the linear baseline, deep learning architectures exhibit strong generalization to nonlinear behaviors, underscoring the potential of AI-driven modeling in nanofluid-based thermal systems.

使用微管的加热和冷却过程对于电子设备的热管理至关重要。用传统的数值方法研究这种复杂的共轭传热系统需要大量的计算时间和资源。因此，本研究的必要性源于对更快，成本效益高，高度准确的预测模型的需求，以加速微尺度冷却系统的设计和优化。本研究的主要目的是通过数值研究水基tio2纳米流体流过厚壁微管的热性能，并且至关重要的是，开发能够提供高预测精度的强大混合数字-机器学习框架。本研究旨在解决文献中的空白。该模型考虑具有长度为L的加热段的无限长微管，其中施加恒定的表面热流。控制二维层流和能量方程以柱坐标表示，通过有限差分格式和中心差分格式进行无量纲化离散，并进行数值求解。同时还考虑了粘滞阻尼和滑移速度边界条件。结果表明，随着壁厚的增加，共轭换热效应增强，而随着壁流界面和Peclet参数的降低，共轭换热效应减弱。这些参数对暂态和稳态行为的影响不同。这项工作的独特贡献在于使用六种回归方法对微管传热参数（Qwi）进行数据驱动建模和预测：线性回归、随机森林、支持向量回归（RBF kernel）、极端梯度增强（XGBoost）、多层感知器（MLP）和一维卷积神经网络（1D-CNN）。所有模型都达到了很高的预测精度（R²> 0.96），其中集成和基于核的方法——特别是XGBoost和svr——产生了最好的结果（R²= 0.9999,RMSE < 0.001）。研究结果表明，尽管基于树和核的模型优于线性基线，但深度学习架构对非线性行为具有很强的泛化能力，这突显了人工智能驱动的建模在基于纳米流体的热系统中的潜力。

{"title":"Hybrid numerical–machine learning framework for heat transfer prediction in TiO₂ nanofluid microtubes","authors":"Muhammed Said Ates , Ebru Akpinar , Cagri Kaymak , Mehmet Das","doi":"10.1016/j.jer.2025.12.007","DOIUrl":"10.1016/j.jer.2025.12.007","url":null,"abstract":"<div><div>Heating and cooling processes using microtubes are crucial for the thermal management of electronic devices. The investigation of such complex conjugate heat transfer systems via traditional numerical methods demands significant computational time and resources. Therefore, the necessity of this study arises from the need for faster, cost-effective, and highly accurate prediction models to accelerate the design and optimization of micro-scale cooling systems. The primary aim of this study is to numerically investigate the thermal performance of a water-based TiO₂ nanofluid flowing through thick-walled microtubes and, crucially, to develop a robust hybrid numerical–machine learning framework capable of offering high predictive accuracy. This study aims to address a gap in the literature. The model considers an infinitely long microtubes with a heated section of length L, where a constant surface heat flux is applied. The governing two-dimensional laminar flow and energy equations, expressed in cylindrical coordinates, were non-dimensionalized, discretized via finite and central difference schemes, and solved numerically. Viscous damping and slip velocity boundary conditions were also incorporated. Results show that conjugate heat transfer effects intensify with increasing wall thickness but diminish with lower wall–fluid interface and Peclet parameters. These parameters influence transient and steady-state behavior differently. The distinctive contribution of this work lies in the data-driven modeling and prediction of the microtube heat transfer parameter (Qwi) using six regression methods: Linear Regression, Random Forest, Support Vector Regression (RBF kernel), Extreme Gradient Boosting (XGBoost), Multi-Layer Perceptron (MLP), and one-dimensional Convolutional Neural Network (1D-CNN). All models achieved high predictive accuracy (R² > 0.96), with ensemble and kernel-based methods—particularly XGBoost and SVR—producing the best results (R² = 0.9999, RMSE < 0.001). The findings demonstrate that while tree- and kernel-based models outperform the linear baseline, deep learning architectures exhibit strong generalization to nonlinear behaviors, underscoring the potential of AI-driven modeling in nanofluid-based thermal systems.</div></div>","PeriodicalId":48803,"journal":{"name":"Journal of Engineering Research","volume":"14 1","pages":"Pages 659-680"},"PeriodicalIF":2.2,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147453726","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

An efficient baseline for multi-view 3d human pose estimation 多视图三维人体姿态估计的有效基线

IF 2.2 4区工程技术 Q3 ENGINEERING, MULTIDISCIPLINARY

Journal of Engineering Research

Pub Date : 2026-03-01 Epub Date: 2025-08-13 DOI: 10.1016/j.jer.2025.07.007

Guozheng Peng, Lixin Han

Recent advancements have been made in calculating 3D human pose keypoints from 2D joint locations obtained via a 2D backbone. While these methods demonstrate excellent performance, they demand substantial computing resources. In this work, we propose a baseline method for multi-view 3D human pose estimation using a fully connected neural network to predict 3D keypoint positions. Our approach provides a straightforward framework for fusing 2D poses from multiple camera views and regressing 3D human pose. Extensive experiments demonstrate the effectiveness of our proposed method on Human3.6M, the largest publicly available benchmark for 3D human pose estimation. Furthermore, it is important to note that increasing the number of input camera views does not inherently guarantee improved 3D pose reconstruction accuracy and quality. The optimal number of views and strategic selection of viewpoint combinations are critical factors in achieving precise 3D pose estimation results.

最近的进展已经在计算三维人体姿态关键点从二维关节位置获得通过二维骨干。虽然这些方法表现出优异的性能，但它们需要大量的计算资源。在这项工作中，我们提出了一种使用全连接神经网络预测3D关键点位置的多视图3D人体姿态估计基线方法。我们的方法提供了一个简单的框架，用于融合来自多个摄像机视图的2D姿势和回归3D人体姿势。大量的实验证明了我们提出的方法在Human3.6M上的有效性，Human3.6M是3D人体姿态估计的最大公开基准。此外，需要注意的是，增加输入摄像机视图的数量并不能保证提高3D姿态重建的精度和质量。最佳视点数和视点组合的策略选择是获得精确三维姿态估计结果的关键因素。

引用次数: 0

Multi-objective optimization of EV battery packs: Lightweight and safety via Pearson-RSM-NSGA-II 基于Pearson-RSM-NSGA-II的电动汽车电池组轻量化与安全性多目标优化

IF 2.2 4区工程技术 Q3 ENGINEERING, MULTIDISCIPLINARY

Journal of Engineering Research

Pub Date : 2026-03-01 Epub Date: 2025-06-28 DOI: 10.1016/j.jer.2025.06.009

Yuanyi Zhao , Zhenfei Zhan , Zhiwei Zhao , Yangchen Ou , Jun Wang

With the rapid development of electric vehicles and energy storage systems, traditional battery pack designs often encounter multi-objective conflicts. Optimizing the battery pack structure to improve safety and reduce weight while ensuring strength, stiffness, and dynamic performance has become a significant challenge in the design process. To address the multi-objective co-optimization challenge of lightweighting and safety in electric vehicle battery packs, this paper proposes a multi-objective optimization framework that integrates the Pearson correlation coefficient, response surface methodology (RSM), and the non-dominated sorting genetic algorithm II (NSGA-II). For the first time, the Pearson correlation coefficient was incorporated into the multi-objective optimization process of battery packs to quantitatively assess the linear relationship between component thickness and performance metrics, thereby overcoming the limitations of conventional parameter screening methods. First, a finite element model of the battery pack shell is established. Based on the simulation software Abaqus/CAE, extrusion and modal simulations are conducted according to the test criteria. Subsequently, the linear correlation between the thickness of quantitative components and performance indices is analyzed using Pearson correlation coefficient to rapidly identify vibration-sensitive and collision-vulnerable components, thereby determining the specific optimization range. A multi-objective optimization model is then established, with mass minimization and modal frequency maximization as the core objectives, by combining the RSM surrogate model and the NSGA-II algorithm. After optimization, the mass of the battery pack is reduced by 1.73 %, and the first-order modal frequency increases from 12.911 Hz to 18.401 Hz, representing a 42.5 % improvement. Compared with conventional optimization methods, the proposed approach achieves a 26.8 % increase in the first-order modal frequency and a 0.2 kg reduction in weight, demonstrating the superiority of the optimization process. Additionally, modal, crash, and crush simulations are performed to validate the optimized battery pack, confirming that its crashworthiness meets safety standards.

随着电动汽车和储能系统的快速发展，传统的电池组设计经常遇到多目标冲突。优化电池组结构以提高安全性和减轻重量，同时保证强度、刚度和动态性能已成为设计过程中的重大挑战。为了解决电动汽车电池组轻量化和安全性的多目标协同优化问题，本文提出了一个整合Pearson相关系数、响应面法（RSM）和非主导排序遗传算法II （NSGA-II）的多目标优化框架。首次将Pearson相关系数引入到电池组的多目标优化过程中，定量评估组件厚度与性能指标之间的线性关系，从而克服了传统参数筛选方法的局限性。首先，建立了电池包壳的有限元模型。基于仿真软件Abaqus/CAE，按照试验准则进行了挤压和模态仿真。随后，利用Pearson相关系数分析定量构件厚度与性能指标之间的线性相关性，快速识别振动敏感和碰撞脆弱构件，从而确定具体的优化范围。将RSM代理模型与NSGA-II算法相结合，建立了以质量最小化和模态频率最大化为核心目标的多目标优化模型。优化后的电池组质量降低了1.73 %，一阶模态频率从12.911 Hz提高到18.401 Hz，提高了42.5 %。与传统优化方法相比，该方法的一阶模态频率提高26.8% %，重量减轻0.2 kg，表明了优化过程的优越性。此外，还进行了模态、碰撞和挤压模拟，以验证优化后的电池组，确认其耐撞性符合安全标准。

{"title":"Multi-objective optimization of EV battery packs: Lightweight and safety via Pearson-RSM-NSGA-II","authors":"Yuanyi Zhao , Zhenfei Zhan , Zhiwei Zhao , Yangchen Ou , Jun Wang","doi":"10.1016/j.jer.2025.06.009","DOIUrl":"10.1016/j.jer.2025.06.009","url":null,"abstract":"<div><div>With the rapid development of electric vehicles and energy storage systems, traditional battery pack designs often encounter multi-objective conflicts. Optimizing the battery pack structure to improve safety and reduce weight while ensuring strength, stiffness, and dynamic performance has become a significant challenge in the design process. To address the multi-objective co-optimization challenge of lightweighting and safety in electric vehicle battery packs, this paper proposes a multi-objective optimization framework that integrates the Pearson correlation coefficient, response surface methodology (RSM), and the non-dominated sorting genetic algorithm II (NSGA-II). For the first time, the Pearson correlation coefficient was incorporated into the multi-objective optimization process of battery packs to quantitatively assess the linear relationship between component thickness and performance metrics, thereby overcoming the limitations of conventional parameter screening methods. First, a finite element model of the battery pack shell is established. Based on the simulation software Abaqus/CAE, extrusion and modal simulations are conducted according to the test criteria. Subsequently, the linear correlation between the thickness of quantitative components and performance indices is analyzed using Pearson correlation coefficient to rapidly identify vibration-sensitive and collision-vulnerable components, thereby determining the specific optimization range. A multi-objective optimization model is then established, with mass minimization and modal frequency maximization as the core objectives, by combining the RSM surrogate model and the NSGA-II algorithm. After optimization, the mass of the battery pack is reduced by 1.73 %, and the first-order modal frequency increases from 12.911 Hz to 18.401 Hz, representing a 42.5 % improvement. Compared with conventional optimization methods, the proposed approach achieves a 26.8 % increase in the first-order modal frequency and a 0.2 kg reduction in weight, demonstrating the superiority of the optimization process. Additionally, modal, crash, and crush simulations are performed to validate the optimized battery pack, confirming that its crashworthiness meets safety standards.</div></div>","PeriodicalId":48803,"journal":{"name":"Journal of Engineering Research","volume":"14 1","pages":"Pages 335-346"},"PeriodicalIF":2.2,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147453737","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0