Arabian Journal for Science and Engineering最新文献

{"title":"Violence Detection Using Deep Learning","authors":"Lobna Hsairi, Sara Matar Alosaimi, Ghada Abdulkareem Alharaz","doi":"10.1007/s13369-024-09536-y","DOIUrl":"https://doi.org/10.1007/s13369-024-09536-y","url":null,"abstract":"<p>Detecting violence is important for preserving security and reducing crime against humans, animals, and properties. Deep learning algorithms have shown potential for detecting violent acts. Further, the reach of large and diverse datasets is critical for training and testing these algorithms. In this study, the aim is to detect violence in images using deep learning techniques to enhance safety and security measures in various applications. For that, we adopted the most utilized and accurate models, such as sequential CNN, MobileNetV2, and VGG-16 which are well known in this field to measure the performance for each classification model on a large dataset of annotated images of eight classes containing both violent and non-violent content. The techniques like data augmentation, transfer learning, and fine-tuning are utilized to improve model performance. As a result, the VGG-16 model has achieved a 71% test accuracy that outperform than Sequential CNN and MobileNetV2 with suitable hyperparameters showcasing its potential for integration into surveillance systems, social media monitoring tools, and other security applications.</p>","PeriodicalId":8109,"journal":{"name":"Arabian Journal for Science and Engineering","volume":"13 1","pages":""},"PeriodicalIF":2.9,"publicationDate":"2024-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142256155","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Experimental Analysis of Reinforced Concrete Deep Beams with Circular Openings Strengthened by GFRP and Steel Bars","authors":"M. Mirzaie Aliabadi, P. Homami, A. Massumi","doi":"10.1007/s13369-024-09541-1","DOIUrl":"https://doi.org/10.1007/s13369-024-09541-1","url":null,"abstract":"<p>This study investigated the behavior of deep beams with openings that have been reinforced with GFRP and steel bars. A total of 14 reinforced concrete deep beams having a rectangular cross-section of 150 × 500 mm and a total length of 1600 mm were constructed with or without openings and tested up to failure under a four-point bending test. The parameters studied were the opening diameter (140 and 240 mm), number and location of the openings and the shear span-to-depth ratio (<i>a/d</i>). These beams were divided into Group I (<i>a/d</i> = 0.9) and Group II (<i>a/d</i> = 0.5). In each group, one beam had no opening to serve as the control beam. Two beams had one opening in the shear area, two had one at the mid-span of the beam and two had two openings, one on each side of the beam. Finite element modeling with strong correlation with the laboratory results was performed. The results showed that an increase in <i>a/d</i> caused a decrease in the final strength of the beam. The number of openings and their locations on the load transfer path were factors that significantly reduced the ultimate load borne by the beam. Comparison of the test results with the relations provided in design regulations indicated that the ultimate strengths of the beams were higher than the values obtained from the regulations. On average, the values calculated based on ACI 318–19 and Canadian S806-2012 were 86.95 and 55.55% lower than the test results, respectively.</p>","PeriodicalId":8109,"journal":{"name":"Arabian Journal for Science and Engineering","volume":"18 1","pages":""},"PeriodicalIF":2.9,"publicationDate":"2024-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142256149","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Sensitivity Analysis of Compressive Strength in CNT-Reinforced Composites: A Comparative Study of Sample-Based, Linearization, and Global Methods","authors":"Majid Ilchi Ghazaan, Amirali Khademi","doi":"10.1007/s13369-024-09580-8","DOIUrl":"https://doi.org/10.1007/s13369-024-09580-8","url":null,"abstract":"<p>Sensitivity analysis (SA) methods determine and quantify how different values of dependent or independent variables affect an output under specific circumstances, such as those represented by a surrogate model. Put differently, sensitivity analyses explore how various sources of uncertainty within a mathematical model collectively impact the model’s overall uncertainty. This study addresses the influence of different parameters—namely, the W/C ratio, CNT type, CNT content, CNT length, CNT diameter, S/C ratio, dispersion method, curing days, and the compressive strength of the control sample (C0) on the compressive strength of carbon nanotube (CNT)-reinforced cementitious nanocomposites as an output. This is achieved by applying four sensitivity analysis methods, including correlation-based indices, Cotter indices, Morris indices, and Borgonovo indices. To implement these four methodologies, a Genetic Programming-based function-finding algorithm known as Gene Expression Programming (GEP) is developed. This algorithm utilizes a collected dataset comprising 326 experimental data points obtained from a comprehensive campaign. Based on the results of the four sensitivity analysis methods, the W/C ratio and the length of CNTs are identified as the most influential input variables across all methods, with CNT type identified in three methods and CNT content in two methods as significant factors affecting compressive strength. Consequently, the W/C ratio, length of CNTs, CNT type, and CNT content are highlighted as the most impactful parameters on the compressive strength of CNT-reinforced cementitious nanocomposites.</p>","PeriodicalId":8109,"journal":{"name":"Arabian Journal for Science and Engineering","volume":"16 1","pages":""},"PeriodicalIF":2.9,"publicationDate":"2024-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142256154","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Novel Deep Learning-Based Method for Seismic-Induced Damage Detection","authors":"Ahmed Atia, Mohammadreza Vafaei, Sophia C. Alih, Kong Fah Tee","doi":"10.1007/s13369-024-09316-8","DOIUrl":"https://doi.org/10.1007/s13369-024-09316-8","url":null,"abstract":"<p>In recent decades, the challenges of traditional visual inspection methods after catastrophic events, which are time- and money-consuming, have necessitated innovative approaches. As a result, a seismic-induced damage detection method utilizing deep learning has been developed to overcome the limitations of conventional techniques. Structure health monitoring (SHM) has emerged to address the limitations of the traditional methods of visual inspections, and among the most effective automatic feature extractor methods is Deep Learning Neural Networks (DLNNs). The DLNN method has proven highly effective compared to other methods, such as traditional methods used in damage detection when used as a feature extractor for seismic-induced damage detection. This study proposes a novel deep learning-based damage detection method for automatically extracting damage features from time series data, eliminating the need for intermediate preprocessing tools. The CNNs algorithm attains a validation accuracy of 91% when applied to a 7-story frame structure by subjecting the structures to different sets of incremental dynamic loading. The study investigates real-time applications, including environmental variables such as noise and temperature effects, examining unseen datasets of different earthquake groups and validating multiple structures in synthesis datasets. The algorithm is further investigated using the IASC-ASCE Benchmark experimental dataset conducted at the University of British Columbia laboratory. A comparative analysis is also performed in terms of time and performance on different deep learning algorithms, such as LSTM, 1D CNN, 2D CNNs and DNNs, while the 1D-CNNs showed the best performance. The results reveal that the proposed method effectively quantifies damage in different structures, including 7-story story steel and concrete structures, and the IASC-ASCE Benchmark dataset, with 93% validation accuracy. The study investigates different earthquake characteristics that affect deep learning performance, such as earthquake time step, and duration, while a specific group was examined to strengthen the claim and show 94% validation accuracy.</p>","PeriodicalId":8109,"journal":{"name":"Arabian Journal for Science and Engineering","volume":"15 1","pages":""},"PeriodicalIF":2.9,"publicationDate":"2024-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142256150","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Scenario-Based Approach to the Implementation of Refueling Stations in Drone-Based non-Emergency of Blood Supply Transportation","authors":"Haitham Saleh, Mohammed Sayad, Anas Alghazi, Yasser Almoghathawi","doi":"10.1007/s13369-024-09549-7","DOIUrl":"https://doi.org/10.1007/s13369-024-09549-7","url":null,"abstract":"<p>In view of the perishable nature and complex storage requirements of certain blood products, the delivery of blood groups from blood banks to hospitals is a key aspect of the healthcare system. The centralization of blood supply facilities for economic reasons and an increase in traffic volume have led to significant delays in the use of traditional emergency vehicles. The aim of the proposed mathematical model is to minimize logistics costs by strategically positioning launch and refueling stations and assigning requests to these stations. The proposed approach employs integer binary linear programming to offer four possible scenarios that consider the flight range and supply node capacity of the drone. The study conducted a scenario-based analysis to examine the primary decision-making process for transporting blood groups and identified the optimal configuration for launching and refueling stations based on 50 group requests. The study uncovered two essential factors, NL and NR, which signify the ideal number of launching stations and the number of refueling stations situated away from the optimal launching sites. The findings offer decision-makers the precise number of stations necessary for an ideal outcome, whereas information on refueling station locations assists in resource distribution planning. Introducing refueling stations for blood supply can extend the mission range and improve coverage in nonemergency situations. Gradual implementation can prevent operational disruptions, such as station closures. This approach can also reduce delivery times and minimize delays, potentially saving lives, as refueling stations have a significant impact on the management of blood supply and logistics.</p>","PeriodicalId":8109,"journal":{"name":"Arabian Journal for Science and Engineering","volume":"2 1","pages":""},"PeriodicalIF":2.9,"publicationDate":"2024-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142256156","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Improving Hate Speech Classification Through Ensemble Learning and Explainable AI Techniques","authors":"Priya Garg, M. K. Sharma, Parteek Kumar","doi":"10.1007/s13369-024-09540-2","DOIUrl":"https://doi.org/10.1007/s13369-024-09540-2","url":null,"abstract":"<p>Identifying offensive and discriminatory content, commonly referred to as hate speech, within textual data is a critical task. This study addresses the task of identifying hate speech in textual data, focusing on the challenge of selecting optimal word embedding methods and classifiers. Leveraging the Google Jigsaw dataset, the research employs explainable artificial intelligence (XAI) for hate speech detection. Following preprocessing, which includes converting text to lowercase, removing punctuation, extra whitespace, numbers, and non-ASCII characters, a thorough analysis reveals high-frequency words. The research extensively compares three-word embedding techniques—CountVectorizer, GloVe, and bidirectional encoder representations from transformers (BERT)—in combination with two machine learning models (support vector classifier and logistic regression) and four deep learning models [artificial neural network (ANN), recurrent neural network (RNN), bidirectional gated recurrent unit (Bi-GRU), bidirectional long-short term memory (Bi-LSTM)] for hate speech detection. The fusion of BERT with a bidirectional gated recurrent unit (Bi-GRU) achieved an impressive accuracy of 92%, and an ensemble of the top-performing models further improves accuracy by nearly 2%. To enhance result interpretability, the study employs XAI techniques such as local interpretable model agnostic explanations (LIME) and Shapley additive explanations (SHAP) on the top-performing ensembled model to provide insights into its predictions. The paper concludes by suggesting potential future research directions, including exploring additional embedding techniques and models, addressing dataset generalizability, improving interpretability methods, and considering computational resource constraints.</p>","PeriodicalId":8109,"journal":{"name":"Arabian Journal for Science and Engineering","volume":"31 1","pages":""},"PeriodicalIF":2.9,"publicationDate":"2024-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142256231","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Localization Scheme Using Single Anchor Node for Mobile Wireless Sensor Nodes in WSNs","authors":"Sanjeev Kumar, Manjeet Singh","doi":"10.1007/s13369-024-09546-w","DOIUrl":"https://doi.org/10.1007/s13369-024-09546-w","url":null,"abstract":"<p>Mobile wireless sensor networks (MWSNs) have revolutionized observing and tracking. Accurately locating mobile sensor nodes remains a challenging task. The precisely identifying event source location is very important. To locate mobile sensor nodes there is a need of developing an efficient localization method. Most of the researcher have used multiple anchor nodes for localization. Therefore, in resource constraint networks reducing number of anchor nodes is an open research issue. The main idea of this work is to propose a localization method using single anchor node. To achieve this, a novel coordinated auto-localization algorithm with particle swarm optimization (PSO) is introduced to enhance localization and tracking of mobile sensor nodes. A mathematical framework has been developed which uses parallel coordinate system to identify location and PSO to track movement pattern of sensor nodes. PSO minimized localization error by refining position accuracy through iterative convergence. It achieves 10% reduction in localization error and a 25% increase in correctly localized nodes, with an overall tracking precision of 80%. Comparative analysis with different techniques like mobile anchor positioning with mobile anchor &amp; neighbor, fish swarm optimization algorithm, DV-hop localization, and autonomous groups particle swarm optimization shows that this method reduces the average localization error to 10% and improves localization efficiency by reducing the required time by 16% compared to other techniques. A pairwise Wilcoxon rank test with a 95% confidence interval shows the proposed method’s superior performance, with a mean of 2.6321E-18 and standard deviation of 3.2705E-19, compared to other metaheuristic algorithms.</p>","PeriodicalId":8109,"journal":{"name":"Arabian Journal for Science and Engineering","volume":"48 1","pages":""},"PeriodicalIF":2.9,"publicationDate":"2024-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142256152","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Influence of Labyrinth Side Weir Shape Modification on the Hydrodynamic Performance: Experimental and Numerical Study","authors":"Bshkoj S. Hussein, Shaker A. Jalil","doi":"10.1007/s13369-024-09563-9","DOIUrl":"https://doi.org/10.1007/s13369-024-09563-9","url":null,"abstract":"<p>Controlling water levels in main channels by constructing side weirs can be influenced by geometric modification. Therefore, proposed geometric changes to the crest of the traditional sharp-crested weir are tested to study the hydrodynamic performance of these weirs. Triangular labyrinth side weir with and without a ramp, curved wing crest and 3 different diameters of circular crest were investigated experimentally and numerically. All the tested shapes have three inclusion angles (<i>θ</i> = 30, 45, and 60°), and three heights (0.1, 0.15, 0.2 m). The fluid volume (VOF) and the turbulence renormalization (RNG k-ϵ) method were selected for simulation and verifying the free surface flow along the center line and beside the weir in the main channel and measuring the velocity at certain cross sectionssections. The smaller inclusion angle between the walls (<i>θ</i> = 30°) performs better in discharging side flow and has a higher discharge coefficient than others. Upon comparison with a traditional labyrinth side weir, a modified side weir with a curved wing and a smaller circular crest diameter increases discharge coefficient (Cd) by about 20.7% and 6.43%, respectively, while its value reduced with the increase of crest diameter and its performance decreased about 17% by increasing the weir crest diameter from 2.5 to 5 cm. However, no improvements have been visualized for adding an upstream ramp. Moreover, in a smaller inclusion angle, the diverting streamline width of flow was obtained to be 0.81 and 0.65 times the main channel width for the modified weir with a curved wing and triangular labyrinth side weir, respectively. In addition, the highest separation zone width downstream of the parent channel for inclusion angle (30°) was observed to be about 2.5 and 1.8 times its width of angle (60°) for curved wing and traditional labyrinth weir, respectively. The discharge coefficient of the curved wing was 3 times the normal rectangular side weir coefficient.</p>","PeriodicalId":8109,"journal":{"name":"Arabian Journal for Science and Engineering","volume":"4 1","pages":""},"PeriodicalIF":2.9,"publicationDate":"2024-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142256183","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Prevalence of ESBL-Producing Gram-Negative Bacteria Among Isolates Obtained from Fecal Samples of Outpatients of Nablus Area, West Bank-Palestine","authors":"Muna M. Abbas, Israa Massarwa, Alaa Abu Alhija, Saja Nashef, Alaeddin Abuzant, Motasem Almasri, Raghad Abuzant, Alaa Salman, Mazen Salman","doi":"10.1007/s13369-024-09581-7","DOIUrl":"https://doi.org/10.1007/s13369-024-09581-7","url":null,"abstract":"<p>Extended-spectrum <i>β</i>-lactamase (ESBL)-producing bacteria are responsible for a considerable burden of difficult to treat infections in different regions of the world. This study was conducted to assess the prevalence, characterize the isolates, and assess the antibiotic susceptibility profiles of ESBL-producing bacteria in fecal samples of outpatients in Nablus, Palestine. The design of this study was a retrospective cross-sectional design, during which 161 Gram-negative bacterial isolates were obtained from the fecal samples of 268 outpatients et al.-Rahma Center, Rafidia Surgical Hospital, and Al-Watani Hospital. These bacterial isolates were identified previously as potential ESBL-producers and then were stored at − 8 0 °C. Out of these isolates 112 (41.7%) were phenotypically confirmed to be ESBL producers and their antibiotic-resistance profile were examined using the disk diffusion method. Female patients were 2.21-times more likely to test positive for ESBL-producing bacteria compared to male patients (95% CI 1.08–4.52) among the tested isolates. <i>Escherichia coli</i>, <i>Klebsiella pneumoniae</i>, and <i>Klebsiella oxytoca</i> were the most prevalent ESBL-producing bacteria.</p>","PeriodicalId":8109,"journal":{"name":"Arabian Journal for Science and Engineering","volume":"32 1","pages":""},"PeriodicalIF":2.9,"publicationDate":"2024-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142256180","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The Macro-Properties of Reinforced Soil by Rice Straw With/Without PVA Treatment","authors":"Lihua Li, Gang Liu, Yuxia Bai, Chengbin Fan","doi":"10.1007/s13369-024-09498-1","DOIUrl":"https://doi.org/10.1007/s13369-024-09498-1","url":null,"abstract":"<p>This study explores the potential of rice straw. The durability and effectiveness of polyvinyl alcohol (PVA)-treated rice straw in reinforcing silty clay were evaluated by measuring its adhesive absorption, tensile strength, and water absorption. The study found that the compressive strength of the reinforced soil first increased and then decreased with the addition of straw, with an optimal mix of 0.3%. The water stability of the reinforced soil improved significantly, with reduced disintegration rates and extended disintegration times. The germination rate, growth height, and coverage of plants in the reinforced soil also increased significantly. As the curing time increased, the compressive strength of the reinforced soil peaked at 7 days before declining. The soil reinforced with PVA-treated straw showed better compressive strength and water stability than untreated straw. The PVA treatment did not negatively affect plant germination or growth, only slightly affecting early plant promotion. The test results provide a scientific basis for the implementation of more sustainable and environmentally friendly civil engineering practices.</p>","PeriodicalId":8109,"journal":{"name":"Arabian Journal for Science and Engineering","volume":"21 1","pages":""},"PeriodicalIF":2.9,"publicationDate":"2024-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142269810","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}