Pub Date : 2024-08-27DOI: 10.1007/s13369-024-09508-2
Francisco de Arriba-Pérez, Silvia García-Méndez
Based on official estimates, 50 million people worldwide are affected by dementia, and this number increases by 10 million new patients every year. Without a cure, clinical prognostication and early intervention represent the most effective ways to delay its progression. To this end, artificial intelligence and computational linguistics can be exploited for natural language analysis, personalized assessment, monitoring, and treatment. However, traditional approaches need more semantic knowledge management and explicability capabilities. Moreover, using large language models (llms) for cognitive decline diagnosis is still scarce, even though these models represent the most advanced way for clinical–patient communication using intelligent systems. Consequently, we leverage an llm using the latest natural language processing (nlp) techniques in a chatbot solution to provide interpretable machine learning prediction of cognitive decline in real-time. Linguistic-conceptual features are exploited for appropriate natural language analysis. Through explainability, we aim to fight potential biases of the models and improve their potential to help clinical workers in their diagnosis decisions. More in detail, the proposed pipeline is composed of (i) data extraction employing nlp-based prompt engineering; (ii) stream-based data processing including feature engineering, analysis, and selection; (iii) real-time classification; and (iv) the explainability dashboard to provide visual and natural language descriptions of the prediction outcome. Classification results exceed 80% in all evaluation metrics, with a recall value for the mental deterioration class about 85%. To sum up, we contribute with an affordable, flexible, non-invasive, personalized diagnostic system to this work.
{"title":"Leveraging large language models through natural language processing to provide interpretable machine learning predictions of mental deterioration in real time","authors":"Francisco de Arriba-Pérez, Silvia García-Méndez","doi":"10.1007/s13369-024-09508-2","DOIUrl":"https://doi.org/10.1007/s13369-024-09508-2","url":null,"abstract":"<p>Based on official estimates, 50 million people worldwide are affected by dementia, and this number increases by 10 million new patients every year. Without a cure, clinical prognostication and early intervention represent the most effective ways to delay its progression. To this end, artificial intelligence and computational linguistics can be exploited for natural language analysis, personalized assessment, monitoring, and treatment. However, traditional approaches need more semantic knowledge management and explicability capabilities. Moreover, using large language models (<span>llm</span>s) for cognitive decline diagnosis is still scarce, even though these models represent the most advanced way for clinical–patient communication using intelligent systems. Consequently, we leverage an <span>llm</span> using the latest natural language processing (<span>nlp</span>) techniques in a chatbot solution to provide interpretable machine learning prediction of cognitive decline in real-time. Linguistic-conceptual features are exploited for appropriate natural language analysis. Through explainability, we aim to fight potential biases of the models and improve their potential to help clinical workers in their diagnosis decisions. More in detail, the proposed pipeline is composed of (i) data extraction employing <span>nlp</span>-based prompt engineering; (ii) stream-based data processing including feature engineering, analysis, and selection; (iii) real-time classification; and (iv) the explainability dashboard to provide visual and natural language descriptions of the prediction outcome. Classification results exceed 80% in all evaluation metrics, with a recall value for the mental deterioration class about 85%. To sum up, we contribute with an affordable, flexible, non-invasive, personalized diagnostic system to this work.</p>","PeriodicalId":8109,"journal":{"name":"Arabian Journal for Science and Engineering","volume":null,"pages":null},"PeriodicalIF":2.9,"publicationDate":"2024-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142194131","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}
Pub Date : 2024-08-27DOI: 10.1007/s13369-024-09519-z
Robiul Islam Rubel, Md Washim Akram, Md Mahmodul Alam, Afsana Nusrat, Raju Ahammad, Md Abdullah Al Bari
Thermal energy harvesting and its applications significantly rely on thermal energy storage (TES) materials. Critical factors include the material’s ability to store and release heat with minimal temperature differences, the range of temperatures covered, and repetitive sensitivity. The short duration of heat storage limits the effectiveness of TES. Phase change materials (PCMs) are a current global research focus due to their desirable thermal properties, which improve energy performance and thermal comfort. PCMs require relatively less synthesis effort while maintaining high efficiency and enhancing cost-effectiveness. However, limited temperature range and storage capacity restrict the application of conventional PCMs. Consequently, the demand for high-energy PCM storage with enhanced thermo-physical properties is high. It is essential to explore the potential of new PCMs to improve thermal storage performance and capacity while reducing energy consumption. This review article explores the classifications and applications of PCMs, addresses the challenges in enhancing their thermo-physical properties, and outlines the selection criteria for high-heat storage applications. Additionally, it provides an in-depth analysis of recent research and developments related to PCMs.
{"title":"Phase Change Materials in High Heat Storage Application: A Review","authors":"Robiul Islam Rubel, Md Washim Akram, Md Mahmodul Alam, Afsana Nusrat, Raju Ahammad, Md Abdullah Al Bari","doi":"10.1007/s13369-024-09519-z","DOIUrl":"https://doi.org/10.1007/s13369-024-09519-z","url":null,"abstract":"<p>Thermal energy harvesting and its applications significantly rely on thermal energy storage (TES) materials. Critical factors include the material’s ability to store and release heat with minimal temperature differences, the range of temperatures covered, and repetitive sensitivity. The short duration of heat storage limits the effectiveness of TES. Phase change materials (PCMs) are a current global research focus due to their desirable thermal properties, which improve energy performance and thermal comfort. PCMs require relatively less synthesis effort while maintaining high efficiency and enhancing cost-effectiveness. However, limited temperature range and storage capacity restrict the application of conventional PCMs. Consequently, the demand for high-energy PCM storage with enhanced thermo-physical properties is high. It is essential to explore the potential of new PCMs to improve thermal storage performance and capacity while reducing energy consumption. This review article explores the classifications and applications of PCMs, addresses the challenges in enhancing their thermo-physical properties, and outlines the selection criteria for high-heat storage applications. Additionally, it provides an in-depth analysis of recent research and developments related to PCMs.</p>","PeriodicalId":8109,"journal":{"name":"Arabian Journal for Science and Engineering","volume":null,"pages":null},"PeriodicalIF":2.9,"publicationDate":"2024-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142194154","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}
Pub Date : 2024-08-27DOI: 10.1007/s13369-024-09441-4
Bui Anh Duc, Tran Manh Hoang, Nguyen Thu Phuong, Xuan Nam Tran, Pham Thanh Hiep
In this study, we examine the downlink cell-free (CF) multiple aerial relay stations (ARSs) system, where ARSs are outfitted with several antennas, distributed randomly in entire responsible areas, and serve a large number of ground users. The application of the CF model is expected to not only improve the performance of the ARS system but also solve the problem of inconsistent throughput between users and the problem of near-far users in the current advanced networks, such as massive multiple-input multiple-output (mMIMO). Moreover, we propose two ARS selection strategies to cut off poor-quality transmission links in the original CF system, thereby reducing the power consumption of ARSs, reducing interference between users, and improving user throughput. We calculate a closed-form formulation for downlink user throughput under the condition of using conjugate beamforming technology. We optimize the pilot and downlink data transmission coefficients using the successive convex approximation (SCA) method and second-order cone programming (SOCP), respectively. The proposed optimization methods mitigate the problems of "pilot contamination" in channel estimation and inter-user interference in downlink data transmission of systems allowing multiple ARS to access the channel simultaneously. Our findings have assessed the downlink system throughput with pilot and data transmission power optimization for superior results based on a variety of selection strategies as well as the CF model (using all ARSs). In addition, the findings also indicate that the proposed novel ARS selection strategies have better user throughput than the CF technique with a specific number of selected ARS. Our proposed system is a promising technology and opens up various practical application scenarios for 6G networks.
在本研究中,我们探讨了下行链路无小区(CF)多空中中继站(ARS)系统,在该系统中,ARS 装有多个天线,随机分布在整个责任区,为大量地面用户提供服务。CF 模型的应用不仅有望提高 ARS 系统的性能,还能解决当前先进网络(如大规模多输入多输出(mMIMO)网络)中用户间吞吐量不一致的问题和用户距离过近的问题。此外,我们还提出了两种 ARS 选择策略,以切断原始 CF 系统中的劣质传输链路,从而降低 ARS 的功耗,减少用户间的干扰,提高用户吞吐量。在使用共轭波束成形技术的条件下,我们计算了下行用户吞吐量的闭式公式。我们分别使用逐次凸近似法(SCA)和二阶锥编程法(SOCP)优化了先导系数和下行链路数据传输系数。所提出的优化方法缓解了信道估计中的 "先导污染 "问题,以及允许多个 ARS 同时访问信道的系统在下行链路数据传输中的用户间干扰问题。我们的研究结果评估了下行链路系统的吞吐量,并根据各种选择策略和 CF 模型(使用所有 ARS)对先导和数据传输功率进行了优化,以获得更优的结果。此外,研究结果还表明,与采用特定数量 ARS 的 CF 技术相比,所提出的新型 ARS 选择策略具有更好的用户吞吐量。我们提出的系统是一项前景广阔的技术,为 6G 网络开辟了各种实际应用场景。
{"title":"Power Optimization and ARSs Selection Strategies in Downlink Cell-Free Multi-ARSs Communication Systems","authors":"Bui Anh Duc, Tran Manh Hoang, Nguyen Thu Phuong, Xuan Nam Tran, Pham Thanh Hiep","doi":"10.1007/s13369-024-09441-4","DOIUrl":"https://doi.org/10.1007/s13369-024-09441-4","url":null,"abstract":"<p>In this study, we examine the downlink cell-free (CF) multiple aerial relay stations (ARSs) system, where ARSs are outfitted with several antennas, distributed randomly in entire responsible areas, and serve a large number of ground users. The application of the CF model is expected to not only improve the performance of the ARS system but also solve the problem of inconsistent throughput between users and the problem of near-far users in the current advanced networks, such as massive multiple-input multiple-output (mMIMO). Moreover, we propose two ARS selection strategies to cut off poor-quality transmission links in the original CF system, thereby reducing the power consumption of ARSs, reducing interference between users, and improving user throughput. We calculate a closed-form formulation for downlink user throughput under the condition of using conjugate beamforming technology. We optimize the pilot and downlink data transmission coefficients using the successive convex approximation (SCA) method and second-order cone programming (SOCP), respectively. The proposed optimization methods mitigate the problems of \"pilot contamination\" in channel estimation and inter-user interference in downlink data transmission of systems allowing multiple ARS to access the channel simultaneously. Our findings have assessed the downlink system throughput with pilot and data transmission power optimization for superior results based on a variety of selection strategies as well as the CF model (using all ARSs). In addition, the findings also indicate that the proposed novel ARS selection strategies have better user throughput than the CF technique with a specific number of selected ARS. Our proposed system is a promising technology and opens up various practical application scenarios for 6G networks.\u0000</p>","PeriodicalId":8109,"journal":{"name":"Arabian Journal for Science and Engineering","volume":null,"pages":null},"PeriodicalIF":2.9,"publicationDate":"2024-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142194160","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}
Pub Date : 2024-08-26DOI: 10.1007/s13369-024-09411-w
O. S. J. Elham, S. K. Kamarudin, N. U. Saidin, L. K. Seng, M. R. Yusof
Direct methanol fuel cells (DMFCs) have great potential for use in portable electronics. However, obstacles such as methanol crossover, insufficient proton conductivity, and the high cost of Nafion hinder the broad commercialization of this technology. In line with the prevailing “waste-to-wealth” movement, eggshell powder was chosen as the filler for the Nafion matrix (rN-ES). Nano-calcium carbonate (nano-CaCO₃) was first produced from eggshell waste by a mechanochemical process before inclusion in the Nafion polymer matrix by the solution casting process. Cyclic voltammetry and electrochemical impedance spectroscopy were used to measure methanol permeability and proton conductivity. The composite membrane showed the highest value for ion exchange capacity of 1.25 mmol g⁻1 and water uptake of 46.54%. Remarkably, the through-plane method showed better proton conductivity (4.87 mS cm⁻1) compared to N117. The methanol permeability of the rN-ES composite membranes decreased to 3.3 times the permeability of N117. In the passive single-cell test of the DMFC, the use of a composite membrane with 5 wt.% nano-CaCO₃ resulted in a rise in the maximum power density from 9.5 to 12.37 mW cm⁻2. These results prove that the incorporation of nano-CaCO₃ as a filler in a Nafion matrix is practicable for DMFC applications.
{"title":"Performance Enhancement of Polymer Electrolyte Membrane with Nano-Calcium Carbonate Prepared by Mechanochemical for Direct Methanol Fuel Cell Applications","authors":"O. S. J. Elham, S. K. Kamarudin, N. U. Saidin, L. K. Seng, M. R. Yusof","doi":"10.1007/s13369-024-09411-w","DOIUrl":"https://doi.org/10.1007/s13369-024-09411-w","url":null,"abstract":"<p>Direct methanol fuel cells (DMFCs) have great potential for use in portable electronics. However, obstacles such as methanol crossover, insufficient proton conductivity, and the high cost of Nafion hinder the broad commercialization of this technology. In line with the prevailing “waste-to-wealth” movement, eggshell powder was chosen as the filler for the Nafion matrix (rN-ES). Nano-calcium carbonate (nano-CaCO₃) was first produced from eggshell waste by a mechanochemical process before inclusion in the Nafion polymer matrix by the solution casting process. Cyclic voltammetry and electrochemical impedance spectroscopy were used to measure methanol permeability and proton conductivity. The composite membrane showed the highest value for ion exchange capacity of 1.25 mmol g⁻<sup>1</sup> and water uptake of 46.54%. Remarkably, the through-plane method showed better proton conductivity (4.87 mS cm⁻<sup>1</sup>) compared to N117. The methanol permeability of the rN-ES composite membranes decreased to 3.3 times the permeability of N117. In the passive single-cell test of the DMFC, the use of a composite membrane with 5 wt.% nano-CaCO₃ resulted in a rise in the maximum power density from 9.5 to 12.37 mW cm⁻<sup>2</sup>. These results prove that the incorporation of nano-CaCO₃ as a filler in a Nafion matrix is practicable for DMFC applications.</p>","PeriodicalId":8109,"journal":{"name":"Arabian Journal for Science and Engineering","volume":null,"pages":null},"PeriodicalIF":2.9,"publicationDate":"2024-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142194162","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}
In two-dimensional axial symmetry finite element analyses, compressible clayey deposits improved by a large group of floating stone columns were performed using the unit cell idealization. The primary focus of this study is to assess the efficiency of floating stone columns in enhancing the consolidation rate of low-permeable soils. Additionally, it aims to evaluate the long-term stability of constructions built along marine coastal areas. To this end, two real case studies were investigated; the Béjaïa and Algiers Mediterranean harbors. Various geometric variables, pertaining to the design of floating stone columns, have been considered to analyze their effect in impacting the consolidation process and the long-term behavior emphasizing their fundamental importance in the design. Besides, a thorough comparison between the design in both short-term and long-term conditions, satisfying the admissible settlement, has been made, ultimately resulting in the optimized design selected. The results also indicate that increasing both the area improvement ratio and the floating column length leads to a speeding up of the consolidation rate. However, in contrast to the area substitution ratio, the column length has comparatively lesser importance in terms of reducing the settlement. Importantly, it is demonstrated that the design of floating stone columns for long-term conditions is significantly distinct from that for short-term conditions, requiring an approximate 40% increase in the area improvement ratio as designs based on the immediate settlement may not align with improved soft soil long-term behavior. Finally, the study reveals that the applied load ultimately governs the design of floating stone columns.
{"title":"Optimized Design of Floating Stone Columns for Enhanced Long-term Settlement Performance of Soft Soils","authors":"Khaoula Chenche, Meriem Fakhreddine Bouali, Jorge Castro","doi":"10.1007/s13369-024-09443-2","DOIUrl":"https://doi.org/10.1007/s13369-024-09443-2","url":null,"abstract":"<p>In two-dimensional axial symmetry finite element analyses, compressible clayey deposits improved by a large group of floating stone columns were performed using the unit cell idealization. The primary focus of this study is to assess the efficiency of floating stone columns in enhancing the consolidation rate of low-permeable soils. Additionally, it aims to evaluate the long-term stability of constructions built along marine coastal areas. To this end, two real case studies were investigated; the Béjaïa and Algiers Mediterranean harbors. Various geometric variables, pertaining to the design of floating stone columns, have been considered to analyze their effect in impacting the consolidation process and the long-term behavior emphasizing their fundamental importance in the design. Besides, a thorough comparison between the design in both short-term and long-term conditions, satisfying the admissible settlement, has been made, ultimately resulting in the optimized design selected. The results also indicate that increasing both the area improvement ratio and the floating column length leads to a speeding up of the consolidation rate. However, in contrast to the area substitution ratio, the column length has comparatively lesser importance in terms of reducing the settlement. Importantly, it is demonstrated that the design of floating stone columns for long-term conditions is significantly distinct from that for short-term conditions, requiring an approximate 40% increase in the area improvement ratio as designs based on the immediate settlement may not align with improved soft soil long-term behavior. Finally, the study reveals that the applied load ultimately governs the design of floating stone columns.</p>","PeriodicalId":8109,"journal":{"name":"Arabian Journal for Science and Engineering","volume":null,"pages":null},"PeriodicalIF":2.9,"publicationDate":"2024-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142194161","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}
Pub Date : 2024-08-26DOI: 10.1007/s13369-024-09460-1
Thanh Ngoc Tran
Peak load forecasting is a critical aspect of power system operations and planning. Accurate forecasting of peak loads significantly impacts the overall efficiency and reliability of a power system. Among the numerous load forecasting methods that are used, ensemble learning algorithms have emerged as a popular choice due to their high accuracy. In this research, the author proposes an innovative methodology that integrates the Differencing Operator with the Sliding Window procedure for training and predicting peak loads using commonly employed ensemble learning models such as GBDT, XGBoost, LightGBM, and CatBoost. The performance of the proposed approach was evaluated by analyzing the prediction error and execution time. The results obtained demonstrated improved accuracy in peak load forecasting, with no impact on execution time.
{"title":"Research on the Impact of the Differencing Operator on Ensemble Learning Algorithms in the Case of Peak Load Forecasting","authors":"Thanh Ngoc Tran","doi":"10.1007/s13369-024-09460-1","DOIUrl":"https://doi.org/10.1007/s13369-024-09460-1","url":null,"abstract":"<p>Peak load forecasting is a critical aspect of power system operations and planning. Accurate forecasting of peak loads significantly impacts the overall efficiency and reliability of a power system. Among the numerous load forecasting methods that are used, ensemble learning algorithms have emerged as a popular choice due to their high accuracy. In this research, the author proposes an innovative methodology that integrates the Differencing Operator with the Sliding Window procedure for training and predicting peak loads using commonly employed ensemble learning models such as GBDT, XGBoost, LightGBM, and CatBoost. The performance of the proposed approach was evaluated by analyzing the prediction error and execution time. The results obtained demonstrated improved accuracy in peak load forecasting, with no impact on execution time.</p>","PeriodicalId":8109,"journal":{"name":"Arabian Journal for Science and Engineering","volume":null,"pages":null},"PeriodicalIF":2.9,"publicationDate":"2024-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142194159","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}
Pub Date : 2024-08-25DOI: 10.1007/s13369-024-09471-y
Xinrong Cao, Jincai Wu, Jian Chen, Zuoyong Li
For recognizing small targets, fire-like objects in fire images, and detecting fires across various scenes, we propose a fire detection method based on feature fusion and channel attention. Most existing fire detection methods have specific application scenarios with poor speed or accuracy. To address the issues of poor accuracy when directly applying existing object detection models and the reduced detection speed when improving models for fire targets, our approach aims to balance accurate fire localization with real-time processing. In the backbone of the model, deformable convolution is used to capture rich image information, and channel attention is employed to enhance features. The feature fusion in the neck achieves better localization of small fire targets. The visualized heatmap results indicate the effectiveness of our improved measures. By simultaneously employing multiple improvement measures, our method achieved satisfactory fire detection performance. Experimental results on a self-annotated dataset demonstrate that the best AP@50 of the model can reach 63.9%, the fastest detection speed can reach 114 FPS, and the F1-score is stable at around 63%. Our method strikes a good balance between detection speed and accuracy.
{"title":"Complex Scenes Fire Object Detection Based on Feature Fusion and Channel Attention","authors":"Xinrong Cao, Jincai Wu, Jian Chen, Zuoyong Li","doi":"10.1007/s13369-024-09471-y","DOIUrl":"https://doi.org/10.1007/s13369-024-09471-y","url":null,"abstract":"<p>For recognizing small targets, fire-like objects in fire images, and detecting fires across various scenes, we propose a fire detection method based on feature fusion and channel attention. Most existing fire detection methods have specific application scenarios with poor speed or accuracy. To address the issues of poor accuracy when directly applying existing object detection models and the reduced detection speed when improving models for fire targets, our approach aims to balance accurate fire localization with real-time processing. In the backbone of the model, deformable convolution is used to capture rich image information, and channel attention is employed to enhance features. The feature fusion in the neck achieves better localization of small fire targets. The visualized heatmap results indicate the effectiveness of our improved measures. By simultaneously employing multiple improvement measures, our method achieved satisfactory fire detection performance. Experimental results on a self-annotated dataset demonstrate that the best AP@50 of the model can reach 63.9%, the fastest detection speed can reach 114 FPS, and the F1-score is stable at around 63%. Our method strikes a good balance between detection speed and accuracy.\u0000</p>","PeriodicalId":8109,"journal":{"name":"Arabian Journal for Science and Engineering","volume":null,"pages":null},"PeriodicalIF":2.9,"publicationDate":"2024-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142194163","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}
Pub Date : 2024-08-25DOI: 10.1007/s13369-024-09470-z
Kun Lin, Yazhen Sun, Jinchang Wang, Fengbin Zhu, Longyan Wang
In this paper, a comprehensive risk assessment system is proposed to evaluate the risk of collapse in mountain tunnels. This system integrates risk source identification, dynamic and static risk classification, deep learning prediction, and engineering risk evaluation. Firstly, risk events and sources are identified, and a risk evaluation method combines the fuzzy analytic hierarchy process (FAHP) and interval technique for order preference by similarity to ideal solution (TOPSIS). FAHP is used to calculate weights, and a risk classification table based on five classical values is derived using traditional TOPSIS. The actual project’s risk value is then calculated using Interval TOPSIS to determine the risk level. Secondly, six models (BP, SVM, CNN, LSTM, PSO-SLTM, and EPL) are trained and tested to predict surface settlement at the tunnel portal and using RMSE, MAE, and maximum (minimum and average) error values for comparison; the best model is determined. The study concludes that a two-stage model, which uses ensemble empirical mode decomposition to process raw data and particle swarm optimization to optimize long short-term memory hyperparameters, provides the best predictive results. Finally, static and dynamic risks are combined for a comprehensive risk evaluation. The Aktepe Tunnel Project in Xinjiang, China, serves as a case study to successfully and accurately forecast surface settlement and evaluate the safety of the tunnel portal. This assessment confirms that this section of the tunnel is at average risk and that the current building conditions ensure the safety of the tunnel, the case study validates the rationality of the comprehensive evaluation system, offering a reference for tunnel portal risk evaluation.
{"title":"Dynamic Risk Forecasting Based on Deep Learning and Collapse Risk Comprehensive Evaluation of Mountain Tunnel Portal Construction","authors":"Kun Lin, Yazhen Sun, Jinchang Wang, Fengbin Zhu, Longyan Wang","doi":"10.1007/s13369-024-09470-z","DOIUrl":"https://doi.org/10.1007/s13369-024-09470-z","url":null,"abstract":"<p>In this paper, a comprehensive risk assessment system is proposed to evaluate the risk of collapse in mountain tunnels. This system integrates risk source identification, dynamic and static risk classification, deep learning prediction, and engineering risk evaluation. Firstly, risk events and sources are identified, and a risk evaluation method combines the fuzzy analytic hierarchy process (FAHP) and interval technique for order preference by similarity to ideal solution (TOPSIS). FAHP is used to calculate weights, and a risk classification table based on five classical values is derived using traditional TOPSIS. The actual project’s risk value is then calculated using Interval TOPSIS to determine the risk level. Secondly, six models (BP, SVM, CNN, LSTM, PSO-SLTM, and EPL) are trained and tested to predict surface settlement at the tunnel portal and using RMSE, MAE, and maximum (minimum and average) error values for comparison; the best model is determined. The study concludes that a two-stage model, which uses ensemble empirical mode decomposition to process raw data and particle swarm optimization to optimize long short-term memory hyperparameters, provides the best predictive results. Finally, static and dynamic risks are combined for a comprehensive risk evaluation. The Aktepe Tunnel Project in Xinjiang, China, serves as a case study to successfully and accurately forecast surface settlement and evaluate the safety of the tunnel portal. This assessment confirms that this section of the tunnel is at average risk and that the current building conditions ensure the safety of the tunnel, the case study validates the rationality of the comprehensive evaluation system, offering a reference for tunnel portal risk evaluation.</p>","PeriodicalId":8109,"journal":{"name":"Arabian Journal for Science and Engineering","volume":null,"pages":null},"PeriodicalIF":2.9,"publicationDate":"2024-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142194164","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}
Pub Date : 2024-08-12DOI: 10.1007/s13369-024-09388-6
Malik Al-Abed Allah, Ihsan ulhaq Toor, Afaque Shams, Osman K. Siddiqui
This paper is focused on a comprehensive review related to the applications of machine learning (ML) and deep learning (DL) techniques for corrosion and crack detection in nuclear power plants (NPPs). NPPs require strict inspection and maintenance guidelines to ensure safety and efficiency, as the consequence of any such accident can be disastrous. Traditional methods of corrosion and crack detection often require substantial manual effort, even plant shutdown for inspection, and are limited in scalability. In recent years, ML and DL approaches have appeared as promising solutions to improve the accuracy and efficiency of corrosion and crack detection methods. The review begins by exploring the fundamental principles of ML and DL, providing insights into their adaptability for managing these challenges in NPPs. ML techniques such as support vector machines and decision trees (DT) as well as various DL architectures, including convolutional neural networks, recurrent neural networks, and autoencoders, are explored in the context of corrosion and crack detection. The paper highlights the dataset challenges related to NPPs, handling issues like imbalanced data, temporal dependencies, and multi-scale modeling. It focuses on case studies and research efforts utilizing ML techniques, highlighting notable advancements and potential breakthroughs in the field. Further, the challenges and future opportunities of integrating ML techniques into nuclear power plant inspection and maintenance are thoroughly scrutinized, underscoring the imperative need for standardized datasets, scalability, and model interpretability.
本文重点综述了机器学习(ML)和深度学习(DL)技术在核电站(NPP)腐蚀和裂纹检测中的应用。核电站需要严格的检查和维护准则来确保安全和效率,因为任何此类事故的后果都可能是灾难性的。传统的腐蚀和裂纹检测方法通常需要大量的人工操作,甚至需要关闭工厂进行检查,而且可扩展性有限。近年来,ML 和 DL 方法的出现为提高腐蚀和裂纹检测方法的准确性和效率带来了希望。本综述首先探讨了 ML 和 DL 的基本原理,并深入分析了它们在应对国家核电厂的这些挑战方面的适应性。在腐蚀和裂纹检测方面,探讨了支持向量机和决策树 (DT) 等 ML 技术以及卷积神经网络、递归神经网络和自动编码器等各种 DL 架构。论文强调了与核电厂相关的数据集挑战,处理了不平衡数据、时间依赖性和多尺度建模等问题。论文重点介绍了利用 ML 技术进行的案例研究和研究工作,强调了该领域的显著进步和潜在突破。此外,还深入探讨了将 ML 技术集成到核电站检查和维护中的挑战和未来机遇,强调了对标准化数据集、可扩展性和模型可解释性的迫切需求。
{"title":"Application of Machine Learning and Deep Learning Techniques for Corrosion and Cracks Detection in Nuclear Power Plants: A Review","authors":"Malik Al-Abed Allah, Ihsan ulhaq Toor, Afaque Shams, Osman K. Siddiqui","doi":"10.1007/s13369-024-09388-6","DOIUrl":"https://doi.org/10.1007/s13369-024-09388-6","url":null,"abstract":"<p>This paper is focused on a comprehensive review related to the applications of machine learning (ML) and deep learning (DL) techniques for corrosion and crack detection in nuclear power plants (NPPs). NPPs require strict inspection and maintenance guidelines to ensure safety and efficiency, as the consequence of any such accident can be disastrous. Traditional methods of corrosion and crack detection often require substantial manual effort, even plant shutdown for inspection, and are limited in scalability. In recent years, ML and DL approaches have appeared as promising solutions to improve the accuracy and efficiency of corrosion and crack detection methods. The review begins by exploring the fundamental principles of ML and DL, providing insights into their adaptability for managing these challenges in NPPs. ML techniques such as support vector machines and decision trees (DT) as well as various DL architectures, including convolutional neural networks, recurrent neural networks, and autoencoders, are explored in the context of corrosion and crack detection. The paper highlights the dataset challenges related to NPPs, handling issues like imbalanced data, temporal dependencies, and multi-scale modeling. It focuses on case studies and research efforts utilizing ML techniques, highlighting notable advancements and potential breakthroughs in the field. Further, the challenges and future opportunities of integrating ML techniques into nuclear power plant inspection and maintenance are thoroughly scrutinized, underscoring the imperative need for standardized datasets, scalability, and model interpretability.</p>","PeriodicalId":8109,"journal":{"name":"Arabian Journal for Science and Engineering","volume":null,"pages":null},"PeriodicalIF":2.9,"publicationDate":"2024-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141932734","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}
Pub Date : 2024-08-12DOI: 10.1007/s13369-024-09406-7
Aiman Jabeen, Shams ur Rahman, A. Shah, Sibghat Ullah Khan, Nasir Ali Siddiqui, Rabia Maryam, Afzal Hussain, Zainab Tariq, Rafaqat Hussain
Efficient removal of industrial effluents from wastewater is critical for a clean and sustainable water supply. In this study, novel nanosized SnO2/MnO2 photocatalysts with crystallite size between 34–40 nm were synthesized and evaluated for methylene blue (MB) degradation under visible light. The optimal percentage of MnO2 nanowires was explored for superior photocatalytic efficiency by varying its amount in the composites. The findings suggested that the SnO2/MnO2 composites exhibited enhanced photocatalytic performance compared to their individual components, which was attributed to the synergistic interaction between SnO2 and MnO2. Preliminary analysis by X-ray diffraction, Raman spectra, and EDX confirmed the crystalline structure and chemical composition of SnO2, MnO2 and their composites. Additionally, the morphology of MnO2 was observed to be of nanowires; while SnO2 was found to be comprised of agglomerated particles. Notably, the photocatalysts demonstrated a systematic reduction in the bandgap of the composites with increasing MnO2 content, leading to improved visible light utilization. Among all the prepared photocatalysts, the optimized SnO2/MnO2 composite with 75 wt. % MnO2 (denote as SM-3) revealed exceptional photocatalytic activity by degrading 93% of MB in 150 min of light exposure. Moreover, the catalytic process followed pseudo-first-order kinetics, highlighting the efficiency of the composites. The scavenger studies suggested that holes, hydroxyl and superoxide radicals are primarily responsible for the MB degradation. The composite SM-3 also exhibited impressive stability and reusability. This study demonstrates the potential of SnO2/MnO2 composites as effective photocatalysts for wastewater treatment under visible light.
{"title":"Tailoring Novel SnO2/α-MnO2 Composites for Photocatalytic Performance Under Visible-Light","authors":"Aiman Jabeen, Shams ur Rahman, A. Shah, Sibghat Ullah Khan, Nasir Ali Siddiqui, Rabia Maryam, Afzal Hussain, Zainab Tariq, Rafaqat Hussain","doi":"10.1007/s13369-024-09406-7","DOIUrl":"https://doi.org/10.1007/s13369-024-09406-7","url":null,"abstract":"<p>Efficient removal of industrial effluents from wastewater is critical for a clean and sustainable water supply. In this study, novel nanosized SnO<sub>2</sub>/MnO<sub>2</sub> photocatalysts with crystallite size between 34–40 nm were synthesized and evaluated for methylene blue (MB) degradation under visible light. The optimal percentage of MnO<sub>2</sub> nanowires was explored for superior photocatalytic efficiency by varying its amount in the composites. The findings suggested that the SnO<sub>2</sub>/MnO<sub>2</sub> composites exhibited enhanced photocatalytic performance compared to their individual components, which was attributed to the synergistic interaction between SnO<sub>2</sub> and MnO<sub>2</sub>. Preliminary analysis by X-ray diffraction, Raman spectra, and EDX confirmed the crystalline structure and chemical composition of SnO<sub>2</sub>, MnO<sub>2</sub> and their composites. Additionally, the morphology of MnO<sub>2</sub> was observed to be of nanowires; while SnO<sub>2</sub> was found to be comprised of agglomerated particles. Notably, the photocatalysts demonstrated a systematic reduction in the bandgap of the composites with increasing MnO<sub>2</sub> content, leading to improved visible light utilization. Among all the prepared photocatalysts, the optimized SnO<sub>2</sub>/MnO<sub>2</sub> composite with 75 wt. % MnO<sub>2</sub> (denote as SM-3) revealed exceptional photocatalytic activity by degrading 93% of MB in 150 min of light exposure. Moreover, the catalytic process followed pseudo-first-order kinetics, highlighting the efficiency of the composites. The scavenger studies suggested that holes, hydroxyl and superoxide radicals are primarily responsible for the MB degradation. The composite SM-3 also exhibited impressive stability and reusability. This study demonstrates the potential of SnO<sub>2</sub>/MnO<sub>2</sub> composites as effective photocatalysts for wastewater treatment under visible light.</p>","PeriodicalId":8109,"journal":{"name":"Arabian Journal for Science and Engineering","volume":null,"pages":null},"PeriodicalIF":2.9,"publicationDate":"2024-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141932735","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}