Pub Date : 2026-03-01Epub Date: 2026-02-15DOI: 10.1016/j.asej.2026.104012
Puja Supakar , Mitali Sarkar , Biswajit Sarkar
This study introduces predictive modeling based on Extreme Gradient Boosting (XGBoost), which utilizes Optuna for hyperparameter optimization and evaluates performance against GridSearchCV and RandomizedSearchCV using a 500-day dataset. To ensure statistical reliability of the findings, a bootstrapping with 1000 iterations is used to calculate 95% confidence intervals for all performance measures. Although GridSearchCV and RandomizedSearchCV achieve consistent performance, their average R-squared test performances are 0.81677 and 0.85538, respectively. In contrast, Optuna outperforms both methods by identifying better regions of optimal parameters, with an average R-squared of 0.94146. Furthermore, the computational efficiency analysis shows that Optuna’s average execution time of 28.31 s is a practical trade-off for running on consumer-grade hardware. Model interpretability is confirmed through Shapley Additive Explanations (SHAP) analysis, which identified the 3-day rolling average as the most important driving factor of demand.
{"title":"Forecasting grocery item sales using gradient boosting models: A study of GridSearchCV, RandomizedSearchCV, and optuna optimization approaches","authors":"Puja Supakar , Mitali Sarkar , Biswajit Sarkar","doi":"10.1016/j.asej.2026.104012","DOIUrl":"10.1016/j.asej.2026.104012","url":null,"abstract":"<div><div>This study introduces predictive modeling based on Extreme Gradient Boosting (XGBoost), which utilizes Optuna for hyperparameter optimization and evaluates performance against GridSearchCV and RandomizedSearchCV using a 500-day dataset. To ensure statistical reliability of the findings, a bootstrapping with 1000 iterations is used to calculate 95% confidence intervals for all performance measures. Although GridSearchCV and RandomizedSearchCV achieve consistent performance, their average R-squared test performances are 0.81677 and 0.85538, respectively. In contrast, Optuna outperforms both methods by identifying better regions of optimal parameters, with an average R-squared of 0.94146. Furthermore, the computational efficiency analysis shows that Optuna’s average execution time of 28.31 s is a practical trade-off for running on consumer-grade hardware. Model interpretability is confirmed through Shapley Additive Explanations (SHAP) analysis, which identified the 3-day rolling average as the most important driving factor of demand.</div></div>","PeriodicalId":48648,"journal":{"name":"Ain Shams Engineering Journal","volume":"17 3","pages":"Article 104012"},"PeriodicalIF":5.9,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147422245","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-03-01Epub Date: 2026-01-29DOI: 10.1016/j.asej.2026.104000
Nan Zhao , Chao Liu , Chao Zhu , Sheliang Wang , Haijun He
Concrete infrastructures located in coastal areas are frequently subjected to coupled sulfate corrosion and wet–dry cycling (WDC). The durability behavior of concrete incorporating bentonite and fly ash (FA) was evaluated under the simultaneous influence of WDC. Concrete containing nine mixtures of different amounts of bentonite and FA were exposed to 150 WDC in Na2SO4(aq), MgSO4(aq) and water, respectively. Physical and mechanical properties, for instance, compressive strength along with the relative dynamic modulus of elasticity (RDEM) were tested to assess the degree of deterioration of the concrete during WDC. In addition, the concrete stress–strain characteristics were analyzed to determine the linkage among modulus of elasticity, peak stress, and peak strain in different sulfate solutions and the frequency of WDC. Furthermore, environmental SEM and industrial computed tomography (CT) were employed to examine the product composition and pore structure evolution at various erosion phases. Results show that concrete incorporating fly ash and bentonite exhibited up to a 33.2% increase in compressive strength in Na2SO4 and a 61.5 MPa peak strength in water during WDC. However, RDEM decreased by up to 53.5% in high–fly ash mixtures after 150 cycles. CT analysis further revealed that pores larger than 0.1 mm3 increased by 120.11% in the control group, whereas the addition of bentonite and fly ash reduced macropore volume by 49.21%, demonstrating their synergistic role in refining the pore structure and enhancing durability. The peak stress followed the same increase–decrease pattern in sulfate environments but continued to rise in water with more WDC cycles. This study introduces a novel multiscale evaluation of fiber-reinforced concrete incorporating bentonite and fly ash under coupled sulfate attack and wet–dry cycling, a combination rarely addressed in previous research. By integrating mechanical testing, stress–strain modeling, SEM, and 3D CT pore analysis, the work reveals the synergistic roles of bentonite and fly ash in refining pore structure and governing deterioration mechanisms. These findings provide new insights for designing durable concrete for coastal environments.
{"title":"Microstructural and mechanical response of fly ash–bentonite modified fiber-reinforced concrete under coupled sulfate attack and wet–dry cycles","authors":"Nan Zhao , Chao Liu , Chao Zhu , Sheliang Wang , Haijun He","doi":"10.1016/j.asej.2026.104000","DOIUrl":"10.1016/j.asej.2026.104000","url":null,"abstract":"<div><div>Concrete infrastructures located in coastal areas are frequently subjected to coupled sulfate corrosion and wet–dry cycling (WDC). The durability behavior of concrete incorporating bentonite and fly ash (FA) was evaluated under the simultaneous influence of WDC. Concrete containing nine mixtures of different amounts of bentonite and FA were exposed to 150 WDC in Na<sub>2</sub>SO<sub>4</sub>(aq), MgSO<sub>4</sub>(aq) and water, respectively. Physical and mechanical properties, for instance, compressive strength along with the relative dynamic modulus of elasticity (RDEM) were tested to assess the degree of deterioration of the concrete during WDC. In addition, the concrete stress–strain characteristics were analyzed to determine the linkage among modulus of elasticity, peak stress, and peak strain in different sulfate solutions and the frequency of WDC. Furthermore, environmental SEM and industrial computed tomography (CT) were employed to examine the product composition and pore structure evolution at various erosion phases. Results show that concrete incorporating fly ash and bentonite exhibited up to a 33.2% increase in compressive strength in Na<sub>2</sub>SO<sub>4</sub> and a 61.5 MPa peak strength in water during WDC. However, RDEM decreased by up to 53.5% in high–fly ash mixtures after 150 cycles. CT analysis further revealed that pores larger than 0.1 mm<sup>3</sup> increased by 120.11% in the control group, whereas the addition of bentonite and fly ash reduced macropore volume by 49.21%, demonstrating their synergistic role in refining the pore structure and enhancing durability. The peak stress followed the same increase–decrease pattern in sulfate environments but continued to rise in water with more WDC cycles. This study introduces a novel multiscale evaluation of fiber-reinforced concrete incorporating bentonite and fly ash under coupled sulfate attack and wet–dry cycling, a combination rarely addressed in previous research. By integrating mechanical testing, stress–strain modeling, SEM, and 3D CT pore analysis, the work reveals the synergistic roles of bentonite and fly ash in refining pore structure and governing deterioration mechanisms. These findings provide new insights for designing durable concrete for coastal environments.</div></div>","PeriodicalId":48648,"journal":{"name":"Ain Shams Engineering Journal","volume":"17 3","pages":"Article 104000"},"PeriodicalIF":5.9,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146057589","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-03-01Epub Date: 2026-02-25DOI: 10.1016/j.asej.2026.104068
Bayram KIZILKAYA
In this study, waste products such as fish bones (H) known as biocompatible natural apatite sources were performed to develop sustainable, recycled and environmentally friendly materials. The study investigated the polymerization of 1-vinylimidazole (VIM) monomer on direct and silane-assisted waste fish bone particle surfaces. In the first method (HP5), direct polymerization of VIM was performed on the fish bone particles. In the second method (HS3P5), the apatite surface was firstly silanized with 3-(Methacryloyloxy)propyl-trimethoxy silane (MPS) and then polymerized with VIM. Elemental analysis results showed that the number of monomers bound to the surface was calculated as 302 µmol/g for HP5 and 714 µmol/g for HS3P5, using nitrogen as the indicator element for VIM. Zeta potential shifted from −20.40 to −35.91 mV and conductivity from 3.03 × 10−2 to 7.67 × 10−2 S/cm. This study proposes an eco-friendly and sustainable material design by reusing biological waste and employing non-toxic, biocompatible polymers.
{"title":"Surface modification and functionalization of biogenic apatite via direct and silane-assisted vinylimidazole polymerization: Comparative evaluation of structural and surface properties","authors":"Bayram KIZILKAYA","doi":"10.1016/j.asej.2026.104068","DOIUrl":"10.1016/j.asej.2026.104068","url":null,"abstract":"<div><div>In this study, waste products such as fish bones (H) known as biocompatible natural apatite sources were performed to develop sustainable, recycled and environmentally friendly materials. The study investigated the polymerization of 1-vinylimidazole (VIM) monomer on direct and silane-assisted waste fish bone particle surfaces. In the first method (HP<sub>5</sub>), direct polymerization of VIM was performed on the fish bone particles. In the second method (HS<sub>3</sub>P<sub>5</sub>), the apatite surface was firstly silanized with 3-(Methacryloyloxy)propyl-trimethoxy silane (MPS) and then polymerized with VIM. Elemental analysis results showed that the number of monomers bound to the surface was calculated as 302 µmol/g for HP5 and 714 µmol/g for HS3P5, using nitrogen as the indicator element for VIM. Zeta potential shifted from −20.40 to −35.91 mV and conductivity from 3.03 × 10<sup>−2</sup> to 7.67 × 10<sup>−2</sup> S/cm. This study proposes an eco-friendly and sustainable material design by reusing biological waste and employing non-toxic, biocompatible polymers.</div></div>","PeriodicalId":48648,"journal":{"name":"Ain Shams Engineering Journal","volume":"17 3","pages":"Article 104068"},"PeriodicalIF":5.9,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147422175","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Solar photovoltaic (PV) systems are becoming more and more important for producing sustainable energy, but cell-level flaws—which are frequently detected by electroluminescence (EL) imaging—have a major impact on their dependability. Although deep learning models for PV defect classification have been used in earlier research, the majority of these studies rely on single architectures, small datasets, and traditional training techniques, which limits detection accuracy and generalization. This work introduces a novel hybrid learning framework that systematically combines transformer-based and convolution-based architectures—PiT-base and ConvNeXt—to exploit their complementary feature extraction capabilities for PV EL defect classification. Unlike prior approaches, the proposed method is further distinguished by the first comprehensive evaluation of the Lion optimizer in this application domain, demonstrating its superior stability and convergence behavior compared to traditional optimizers. The framework is evaluated under both offline and online learning scenarios, providing new insights into training and deployment performance that are largely unexplored in existing literature. Extensive experiments are conducted on two benchmark datasets—ELPV and PVELAD—thereby extending validation beyond the commonly used ELPV dataset. The proposed approach achieves accuracies of 82.45% (offline) and 81.94% (online) on ELPV, and 86.96% (offline) and 86.74% (online) on PVELAD, significantly outperforming previously reported state-of-the-art results.
{"title":"LiCPV: hybrid deep learning for PV fault detection","authors":"Samar Elbedwehy , M. Turki-Hadj Alouane , Esraa Hassan , Zahraa Tarek","doi":"10.1016/j.asej.2026.104041","DOIUrl":"10.1016/j.asej.2026.104041","url":null,"abstract":"<div><div>Solar photovoltaic (PV) systems are becoming more and more important for producing sustainable energy, but cell-level flaws—which are frequently detected by electroluminescence (EL) imaging—have a major impact on their dependability. Although deep learning models for PV defect classification have been used in earlier research, the majority of these studies rely on single architectures, small datasets, and traditional training techniques, which limits detection accuracy and generalization. This work introduces a novel hybrid learning framework that systematically combines transformer-based and convolution-based architectures—PiT-base and ConvNeXt—to exploit their complementary feature extraction capabilities for PV EL defect classification. Unlike prior approaches, the proposed method is further distinguished by the first comprehensive evaluation of the Lion optimizer in this application domain, demonstrating its superior stability and convergence behavior compared to traditional optimizers. The framework is evaluated under both offline and online learning scenarios, providing new insights into training and deployment performance that are largely unexplored in existing literature. Extensive experiments are conducted on two benchmark datasets—ELPV and PVELAD—thereby extending validation beyond the commonly used ELPV dataset. The proposed approach achieves accuracies of 82.45% (offline) and 81.94% (online) on ELPV, and 86.96% (offline) and 86.74% (online) on PVELAD, significantly outperforming previously reported state-of-the-art results.</div></div>","PeriodicalId":48648,"journal":{"name":"Ain Shams Engineering Journal","volume":"17 3","pages":"Article 104041"},"PeriodicalIF":5.9,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147422177","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-03-01Epub Date: 2026-02-14DOI: 10.1016/j.asej.2026.104040
Shahr Alshahr , Ahmed Alshahir , Hammad Alnuman , Meshari D. Alanazi , Amr Yousef , Ghulam Abbas
The rapid emergence of Electric Vehicles (EVs) presents both opportunities and challenges for sustainable transportation, particularly in integrating renewable energy sources into charging infrastructure while maintaining grid stability. Current EV charging systems exhibit inefficient energy utilization, peak demand stress, and suboptimal integration of intermittent renewable energy sources, primarily due to their reliance on conventional grid power and the lack of intelligent distribution mechanisms. Hence, the research introduces Smart Renewable Optimization with Vehicle-aware Reinforcement Learning (SRO-VRL), a model-based RL approach that makes real-time, adaptive decisions on energy distribution. This model dynamically optimizes EV charging schedules by prioritizing renewable energy sources, EV demand, and grid constraints to ensure efficient charging. The model begins by collecting real-time data from EV charging stations, grid load measurements, and renewable energy sources. The approach relies on collecting real-time data from private and public EV charging stations connected to local distribution grids at the community/microgrid level in Europe. This infrastructure includes mixed residential chargers (Type-2/Type-3 AC) and community charging stations. Its hybrid renewable energy mix, which is supported by battery energy storage, primarily comes from solar energy. The local utility system supplies additional power. Grid data show low-voltage feeders that are constrained by capacity and pricing. In comparison to benchmark reinforcement learning and rule-based strategies, the results demonstrate the effectiveness and scalability of the proposed SRO-VRL framework for community-scale microgrids and regional smart grids, improving renewable energy utilization by approximately 4–5%, lowering peak grid load by approximately 7–8%, and reducing overall EV charging costs by approximately 5–6%. System states are then formulated to encompass EV state-of-charge (SoC), predicted renewable supply, and grid constraints, while charging power allocations constitute the action space. In comparison to benchmark reinforcement learning and rule-based strategies, the results demonstrate the effectiveness and scalability of the proposed SRO-VRL framework for community-scale microgrids and regional smart grids, improving renewable energy utilization by approximately 4–5%, reducing peak grid load by approximately 7–8%, and lowering overall EV charging costs by approximately 5–6%.
{"title":"Dynamic renewable energy integration for EV charging via model-based reinforcement learning","authors":"Shahr Alshahr , Ahmed Alshahir , Hammad Alnuman , Meshari D. Alanazi , Amr Yousef , Ghulam Abbas","doi":"10.1016/j.asej.2026.104040","DOIUrl":"10.1016/j.asej.2026.104040","url":null,"abstract":"<div><div>The rapid emergence of Electric Vehicles (EVs) presents both opportunities and challenges for sustainable transportation, particularly in integrating renewable energy sources into charging infrastructure while maintaining grid stability. Current EV charging systems exhibit inefficient energy utilization, peak demand stress, and suboptimal integration of intermittent renewable energy sources, primarily due to their reliance on conventional grid power and the lack of intelligent distribution mechanisms. Hence, the research introduces Smart Renewable Optimization with Vehicle-aware Reinforcement Learning (SRO-VRL), a model-based RL approach that makes real-time, adaptive decisions on energy distribution. This model dynamically optimizes EV charging schedules by prioritizing renewable energy sources, EV demand, and grid constraints to ensure efficient charging. The model begins by collecting real-time data from EV charging stations, grid load measurements, and renewable energy sources. The approach relies on collecting real-time data from private and public EV charging stations connected to local distribution grids at the community/microgrid level in Europe. This infrastructure includes mixed residential chargers (Type-2/Type-3 AC) and community charging stations. Its hybrid renewable energy mix, which is supported by battery energy storage, primarily comes from solar energy. The local utility system supplies additional power. Grid data show low-voltage feeders that are constrained by capacity and pricing. In comparison to benchmark reinforcement learning and rule-based strategies, the results demonstrate the effectiveness and scalability of the proposed SRO-VRL framework for community-scale microgrids and regional smart grids, improving renewable energy utilization by approximately 4–5%, lowering peak grid load by approximately 7–8%, and reducing overall EV charging costs by approximately 5–6%. System states are then formulated to encompass EV state-of-charge (SoC), predicted renewable supply, and grid constraints, while charging power allocations constitute the action space. In comparison to benchmark reinforcement learning and rule-based strategies, the results demonstrate the effectiveness and scalability of the proposed SRO-VRL framework for community-scale microgrids and regional smart grids, improving renewable energy utilization by approximately 4–5%, reducing peak grid load by approximately 7–8%, and lowering overall EV charging costs by approximately 5–6%.</div></div>","PeriodicalId":48648,"journal":{"name":"Ain Shams Engineering Journal","volume":"17 3","pages":"Article 104040"},"PeriodicalIF":5.9,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146190846","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-03-01Epub Date: 2026-01-29DOI: 10.1016/j.asej.2026.103990
Qaisar Khan , Meraj Ali Khan , Ibrahim Al-Dayel , Majid Khan
This study reports the manipulation of photonic spin hall shift at the graphene medium that lies between two mirrors. The incoming probe light engages with a cavity filled with four levels graphene medium. The spin hall shift of the photons is tuned to positive or negative values, depending on the properties of the driving fields. The maximum spin hall shift which lies in is a function of incidence angle and independent of control field Rabi frequency. The minimum spin hall shift lies in the range against the control field Rabi frequency (= 0 G and 20 G). These findings have significant applications in areas such as sensing technology, quantum computing and optical communication.
{"title":"Photonic spin hall shift manipulation at the graphene atomic medium","authors":"Qaisar Khan , Meraj Ali Khan , Ibrahim Al-Dayel , Majid Khan","doi":"10.1016/j.asej.2026.103990","DOIUrl":"10.1016/j.asej.2026.103990","url":null,"abstract":"<div><div>This study reports the manipulation of photonic spin hall shift at the graphene medium that lies between two mirrors. The incoming probe light engages with a cavity filled with four levels graphene medium. The spin hall shift of the photons is tuned to positive or negative values, depending on the properties of the driving fields. The maximum spin hall shift which lies in <span><math><mo>−</mo><mn>50</mn><mi>λ</mi><mo>≤</mo><mi>S</mi><msubsup><mi>h</mi><mrow><mi>p</mi></mrow><mrow><mi>L</mi><mo>,</mo><mi>R</mi></mrow></msubsup><mo>≤</mo><mn>50</mn><mi>λ</mi></math></span> is a function of incidence angle and independent of control field Rabi frequency. The minimum spin hall shift lies in the range <span><math><mo>±</mo><mn>17.79</mn><mi>λ</mi><mo>≤</mo><mi>S</mi><msubsup><mi>h</mi><mrow><mi>p</mi></mrow><mrow><mi>L</mi><mo>,</mo><mi>R</mi></mrow></msubsup><mo>≤</mo><mo>±</mo><mn>17.83</mn><mi>λ</mi></math></span> against the control field Rabi frequency (<span><math><mo>|</mo><msub><mi>R</mi><mrow><mn>1</mn></mrow></msub><mo>|</mo></math></span>= 0 G and 20 G). These findings have significant applications in areas such as sensing technology, quantum computing and optical communication.</div></div>","PeriodicalId":48648,"journal":{"name":"Ain Shams Engineering Journal","volume":"17 3","pages":"Article 103990"},"PeriodicalIF":5.9,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146057587","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Flood prediction in data-scarce semi-arid regions presents significant challenges. This study develops an innovative artificial intelligence (AI) framework for the Jamash watershed, utilizing comprehensive daily data (2000–2023) of meteorological, hydrological, and remote sensing variables. We evaluated two feature selection methods—Random Forest (RF) and Wavelet Transform Coherence (WTC)—and employed Variational Mode Decomposition (VMD) to process non-stationary time series. Twelve modeling scenarios compared Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) architectures, both standalone and hybrid forms, with AI-based uncertainty assessment. Results demonstrated the superior performance of the hybrid VMD-WTC-GRU model, achieving a determination coefficient of 0.83 during testing. Uncertainty analysis confirmed this model as both the most accurate and reliable, exhibiting the narrowest uncertainty band (32.26) with satisfactory confidence probability coverage (0.95). This integrated AI framework effectively overcomes challenges of limited data and hydrological complexity in flood forecasting.
{"title":"An intelligent VMD-WTC-GRU hybrid framework with uncertainty quantification for forecasting extreme flood events in semi-arid regions","authors":"Rahele Ramezani , Abolhassan Gheiby , Hossein Malakooti , Ommolbanin Bazrafshan","doi":"10.1016/j.asej.2025.103960","DOIUrl":"10.1016/j.asej.2025.103960","url":null,"abstract":"<div><div>Flood prediction in data-scarce semi-arid regions presents significant challenges. This study develops an innovative artificial intelligence (AI) framework for the Jamash watershed, utilizing comprehensive daily data (2000–2023) of meteorological, hydrological, and remote sensing variables. We evaluated two feature selection methods—Random Forest (RF) and Wavelet Transform Coherence (WTC)—and employed Variational Mode Decomposition (VMD) to process non-stationary time series. Twelve modeling scenarios compared Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) architectures, both standalone and hybrid forms, with AI-based uncertainty assessment. Results demonstrated the superior performance of the hybrid VMD-WTC-GRU model, achieving a determination coefficient of 0.83 during testing. Uncertainty analysis confirmed this model as both the most accurate and reliable, exhibiting the narrowest uncertainty band (32.26) with satisfactory confidence probability coverage (0.95). This integrated AI framework effectively overcomes challenges of limited data and hydrological complexity in flood forecasting.</div></div>","PeriodicalId":48648,"journal":{"name":"Ain Shams Engineering Journal","volume":"17 3","pages":"Article 103960"},"PeriodicalIF":5.9,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146191327","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-02-01Epub Date: 2026-01-05DOI: 10.1016/j.asej.2025.103959
Zihan Zhang, Qihui Guo, Ivan Kholodilin, Maksim A. Grigorev
A method for structured light extraction and depth reconstruction, tailored to monocular omnidirectional vision systems, is proposed in this study to improve localization accuracy under wide field-of-view conditions with multiple objects and complex interferences such as reflections and occlusions. This method incorporates a multi-threshold fusion adjustment mechanism and introduces new algorithms for structured light clustering and discontinuity repair, aiming to improve the accuracy of centerline extraction. By integrating a neural network algorithm, the position of an object in the robot coordinate system can be accurately estimated from a single monocular omnidirectional image snapshot. The experimental results demonstrate that, compared with conventional extraction methods, the proposed method reduces the depth reconstruction error by 69.18 % in interference environments. By integrating the algorithm into the robotic system, multi-object recognition and localization were successfully achieved using a monocular camera. This provides a reference for the application of monocular omnidirectional vision in robotic systems.
{"title":"A monocular omnidirectional vision-based method for structured light strip extraction and robot target localization under complex interference","authors":"Zihan Zhang, Qihui Guo, Ivan Kholodilin, Maksim A. Grigorev","doi":"10.1016/j.asej.2025.103959","DOIUrl":"10.1016/j.asej.2025.103959","url":null,"abstract":"<div><div>A method for structured light extraction and depth reconstruction, tailored to monocular omnidirectional vision systems, is proposed in this study to improve localization accuracy under wide field-of-view conditions with multiple objects and complex interferences such as reflections and occlusions. This method incorporates a multi-threshold fusion adjustment mechanism and introduces new algorithms for structured light clustering and discontinuity repair, aiming to improve the accuracy of centerline extraction. By integrating a neural network algorithm, the position of an object in the robot coordinate system can be accurately estimated from a single monocular omnidirectional image snapshot. The experimental results demonstrate that, compared with conventional extraction methods, the proposed method reduces the depth reconstruction error by 69.18 % in interference environments. By integrating the algorithm into the robotic system, multi-object recognition and localization were successfully achieved using a monocular camera. This provides a reference for the application of monocular omnidirectional vision in robotic systems.</div></div>","PeriodicalId":48648,"journal":{"name":"Ain Shams Engineering Journal","volume":"17 2","pages":"Article 103959"},"PeriodicalIF":5.9,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145928429","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-02-01Epub Date: 2026-02-05DOI: 10.1016/j.asej.2026.104017
Ali Tugrul Albayrak
{"title":"Corrigendum to “The utilization of novel deep eutectic solvents in cement production and their impact on the physical and the mechanical properties of Portland cement” [Ain Shams Eng. J. 17(1) (2026) 103861]","authors":"Ali Tugrul Albayrak","doi":"10.1016/j.asej.2026.104017","DOIUrl":"10.1016/j.asej.2026.104017","url":null,"abstract":"","PeriodicalId":48648,"journal":{"name":"Ain Shams Engineering Journal","volume":"17 2","pages":"Article 104017"},"PeriodicalIF":5.9,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147395353","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-02-01Epub Date: 2026-01-21DOI: 10.1016/j.asej.2026.104003
Ping Guo, Jiwei Zhu
The renovation of urban old residential areas (UORA) is a crucial measure in urban stock renewal for improving the quality of residents’ lives. Scientifically understanding the multidimensional vulnerability of UORA is a prerequisite for implementing stock renewal. However, existing vulnerability assessment methods for UORA suffer from limitations such as subjective weight assignment, and insufficient handling of uncertain information, leading to inadequate support for precise renewal decisions. To address these gaps, this study proposes a novel multidimensional vulnerability evaluation framework. A vulnerability evaluation index system is constructed from physical space, infrastructure, functional adaptation, ecological environment, and social governance. A comprehensive evaluation model is established by integrating the combined entropy weight method and the unascertained measure theory. This methodological innovation enhances the objectivity of weight determination while effectively addressing unstructured data and uncertain factors in vulnerability assessment. The empirical results show that the vulnerability evaluation results of the six projects are clearly polarised. High-risk clusters need to prioritise the initiation of engineering interventions and social governance reconstruction; for medium-risk projects, dynamic monitoring and adaptive management should be strengthened. This study provides a priority standard and scientific support for renewal decisions and promotes the transformation of vulnerability assessment from a single diagnosis to a systematic governance paradigm..
{"title":"Vulnerability analysis of urban old residential areas for stock renewal: an unascertained measure theory approach","authors":"Ping Guo, Jiwei Zhu","doi":"10.1016/j.asej.2026.104003","DOIUrl":"10.1016/j.asej.2026.104003","url":null,"abstract":"<div><div>The renovation of urban old residential areas (UORA) is a crucial measure in urban stock renewal for improving the quality of residents’ lives. Scientifically understanding the multidimensional vulnerability of UORA is a prerequisite for implementing stock renewal. However, existing vulnerability assessment methods for UORA suffer from limitations such as subjective weight assignment, and insufficient handling of uncertain information, leading to inadequate support for precise renewal decisions. To address these gaps, this study proposes a novel multidimensional vulnerability evaluation framework. A vulnerability evaluation index system is constructed from physical space, infrastructure, functional adaptation, ecological environment, and social governance. A comprehensive evaluation model is established by integrating the combined entropy weight method and the unascertained measure theory. This methodological innovation enhances the objectivity of weight determination while effectively addressing unstructured data and uncertain factors in vulnerability assessment. The empirical results show that the vulnerability evaluation results of the six projects are clearly polarised. High-risk clusters need to prioritise the initiation of engineering interventions and social governance reconstruction; for medium-risk projects, dynamic monitoring and adaptive management should be strengthened. This study provides a priority standard and scientific support for renewal decisions and promotes the transformation of vulnerability assessment from a single diagnosis to a systematic governance paradigm..</div></div>","PeriodicalId":48648,"journal":{"name":"Ain Shams Engineering Journal","volume":"17 2","pages":"Article 104003"},"PeriodicalIF":5.9,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146023814","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号