Engineering Applications of Artificial Intelligence最新文献

{"title":"Hybrid optimization approach for syngas-fueled gas turbines: Integrating inverse problem solving and machine learning techniques","authors":"Hiago David Zogbi Silva Oliveira,&nbsp;Vítor Caldeira de Andrada Bastos,&nbsp;York Castillo Santiago,&nbsp;Isabela Florindo Pinheiro","doi":"10.1016/j.engappai.2025.112162","DOIUrl":"10.1016/j.engappai.2025.112162","url":null,"abstract":"<div><div>This study investigates the efficiency of gas turbines powered by syngas derived from gasification, combining a detailed thermodynamic model with a hybrid optimization approach that integrates inverse problem solving via the Levenberg-Marquardt (LM) algorithm and supervised machine learning using Gradient Boosted Trees (GBT). The LM method is used to estimate turbine and compressor performance parameters based on efficiency maps extracted through a custom image processing routine. These maps are applied to calibrate isentropic efficiencies and define the system's operational boundaries. The resulting performance curves enhance the accuracy of the thermodynamic cycle model. To identify optimal operating conditions that maximize thermal efficiency and minimize entropy generation, the inverse problem formulation is integrated with the GBT model, enabling data-driven optimization based on simulated system behavior. All modeling and simulations are conducted in Wolfram Mathematica version 14.0, while verification is performed with the commercial software Gasturb version 14.0, using syngas composition data available in the literature. As a case study to demonstrate the method's applicability, syngas obtained from sewage sludge gasification is analyzed. The findings after optimization indicated an average thermal efficiency of 40 % when using syngas. The analysis revealed that the fuel mass flow rate contributes approximately 45 % to the efficiency gains and more than 70 % to the exergy reduction, while the excess air ratio contributes around 50 % to the cycle's efficiency. The study demonstrates the value of integrating LM-based modeling and GBT optimization, indicating significant potential for enhancing the performance of syngas-fueled turbines. Moreover, it highlights syngas from sewage sludge as a promising sustainable energy source.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"161 ","pages":"Article 112162"},"PeriodicalIF":8.0,"publicationDate":"2025-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145046198","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A data-driven multi-stage stochastic optimization for sustainable humanitarian supply chain using machine learning algorithms","authors":"Farnaz Ansari ,&nbsp;Ali Bozorgi-Amiri ,&nbsp;Hossein Shakibaei","doi":"10.1016/j.engappai.2025.112133","DOIUrl":"10.1016/j.engappai.2025.112133","url":null,"abstract":"<div><div>The frequency and severity of natural disasters have intensified, resulting in significant human, financial, and emotional consequences. Earthquakes, in particular, have caused severe economic losses, deaths, and homelessness among millions. This study is designed to establish a comprehensive plan for managing pre- and post-disaster phases, including preparations, responses, and recovery efforts. It introduces a Multi-Stage Stochastic Programming (MSSP) model for sustainable humanitarian relief operations, optimizing location, allocation, and inventory management. The first and third stages concentrate on minimizing environmental impacts, while the second stage centers on enhancing social welfare. Simultaneously, economic cost reduction is consistently pursued in all three stages. The model's primary advantages include optimized inventory management to avoid shortages and flexible logistics strategies for timely and cost-effective delivery of relief items. Additionally, it ensures continuous aid, addressing both short-term and long-term needs to improve disaster management effectiveness and resilience. The multi-objective model is solved using Augmented Epsilon-Constraint (AEC). Furthermore, this paper employs Multi-Criteria Decision-Making (MCDM) methods to rank suppliers, leveraging Machine Learning (ML) algorithms to enhance ranking precision, thereby leading to a more responsive Supply Chain (SC). A real-world case study is then provided to illustrate the applicability and validity of the proposed model. Focusing on achieving balanced sustainability across all three stages, ensuring seamless logistics for all humanitarian supplies and affected individuals, and addressing uncertainties, the model determines the optimal quantities of all relief items to store. Through comprehensive analysis, the results provide key insights into the importance of MSSP in disaster management plans, enhancing understanding of the model's effectiveness.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"161 ","pages":"Article 112133"},"PeriodicalIF":8.0,"publicationDate":"2025-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145046201","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A search method for fractured-vuggy reservoir inter-well connectivity path based on multi-modal multi-agent","authors":"Wenbin Jiang ,&nbsp;Dongmei Zhang ,&nbsp;Hong Cao ,&nbsp;Xiaofeng Wang","doi":"10.1016/j.engappai.2025.112184","DOIUrl":"10.1016/j.engappai.2025.112184","url":null,"abstract":"<div><div>The complex geological structure of carbonate reservoirs and the intricate fracture-vuggy configurations obscure inter-well connectivity, making its evaluation challenging. Conventional studies primarily rely on seismic static data to delineate fracture-vuggy reservoirs, but the limited recognition accuracy hampers the precise characterization of inter-well connectivity and the spatial configuration of fractures and vugs. To address this, this study constructs a 3D (Three-Dimensional) search environment and use multi-modal static and dynamic data and proposes a multi-agent connected channel search model based on deep reinforcement learning. The model treats multiphase fluid as an agent and incorporates Swin Transformer (Shift Window Transformer) to extract large-scale fracture features from seismic data, providing global prior information for path search. A Graph Attention Network is established based on dynamic response relationships to extract spatial geological features, while a multi-head self-attention mechanism captures real-time fluid interactions in various directions. The model fuses multi-modal features, including seismic attributes and production data, to generate decisions and automatically search for inter-well connectivity channels. Experiments were conducted using the WE1 and WE5 well groups from the fault-controlled karst reservoirs in the Tahe oilfield, with results compared against tracer tests. The findings demonstrate that the proposed model's automatic search paths closely align with seismic data and tracer test results, effectively capturing the spatial distribution of fractures and vugs across different scales. This validates the model's effectiveness in evaluating inter-well connectivity in complex carbonate reservoirs.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"161 ","pages":"Article 112184"},"PeriodicalIF":8.0,"publicationDate":"2025-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145046191","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Optimizing mean conditional value-at-risk portfolios through deep neural network stock prediction","authors":"Jyotirmayee Behera ,&nbsp;Pankaj Kumar","doi":"10.1016/j.engappai.2025.112198","DOIUrl":"10.1016/j.engappai.2025.112198","url":null,"abstract":"<div><div>Portfolio optimization is essential in financial decision-making, requiring a balance between risk minimization and return maximization. Effective stock selection significantly influences portfolio performance. Traditional methods often struggle to effectively integrate advanced risk assessment techniques with stock selection. To enhance portfolio diversification and improve risk-adjusted returns, this study integrates deep learning-based stock selection with the mean conditional Value-at-Risk (MCVaR) model and entropy constraints to enhance portfolio diversification and risk-adjusted returns. Various deep neural networks, including Recurrent Neural Networks (RNN), Long Short-Term Memory (LSTM), Gated Recurrent Units (GRU), Multi-Layer Perceptrons (MLP), and Radial Basis Function Neural Networks (RBFN), are employed to rank stocks based on risk and return characteristics. The top-ranked stocks with the lowest risk are selected for portfolio construction. The entropy constraint is introduced to prevent excessive weight concentration, ensuring a well-diversified portfolio. Historical datasets from the Bombay Stock Exchange (BSE), India, B3 Stock Exchange, Brazil, and Shanghai Stock Exchange, China, are used for validation, with performance assessed on an out-of-sample dataset. Additionally, the efficacy of the suggested approach is evaluated by contrasting it with other machine learning and conventional portfolio optimization techniques. Experimental results demonstrate that the LSTM+MCVaR model with entropy constraint consistently outperforms other deep learning and conventional optimization methods, achieving superior cumulative returns and Sharpe ratios. The findings highlight the potential of combining LSTM forecasting with MCVaR optimization and entropy regularization for robust, diversified portfolio construction.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"161 ","pages":"Article 112198"},"PeriodicalIF":8.0,"publicationDate":"2025-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145046195","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Risk-response coupling in underground structures under liquefiable soil conditions: A causality-informed Dynamic Bayesian network integrated framework","authors":"Heqi Kong ,&nbsp;Xiaohua Bao ,&nbsp;Jun Shen ,&nbsp;Xiangcou Zheng ,&nbsp;Xiangsheng Chen","doi":"10.1016/j.engappai.2025.112171","DOIUrl":"10.1016/j.engappai.2025.112171","url":null,"abstract":"<div><div>Underground structures in liquefiable soils face complex seismic risks that can trigger cascading failures. This study proposes a Granger causality-informed Dynamic Bayesian network (G-DBN) framework to capture the temporal propagation of seismic risk in such systems. Firstly, a system risk assessment model integrates multiple performance indicators through Cloud Model (CM) to quantify overall risk levels, considering uncertainties associated with soil liquefaction and structural responses. Subsequently, a structural dynamic risk inference model is established using Dynamic Bayesian network (DBN), combining Granger Causality (GC) analysis with engineering-informed relationships to define the network structure. The input features include key structural state variables such as tunnel cross-section convergence (<em>T</em>₄), tunnel uplift displacement (<em>T</em>₆), station uplift displacement (<em>S</em>₅), and inter-story drift angle (<em>S</em>₆), and the aggregated structural risk indicator serves as the target variable. This framework enables the temporal propagation of risk across interconnected structural nodes, and elucidates the mechanisms by which liquefiable soil deformations and structural responses interact within the soil-structure system. Results showed that the risk characteristic value (Expectation<em>, E</em>_x) decreased from 29.12 % (percentage) to 5.21 % as the Peak Ground Acceleration (PGA, expressed in units of gravitational acceleration g) increased from 0.1 g to 0.7 g. The proposed G-DBN model demonstrates robust predictive capabilities, achieving coefficient of determination (<em>R</em>²) values exceeding 0.95 across multiple seismic intensity conditions. Additionally, tunnel cross-section convergence (<em>T</em>₄) was identified as the most critical factor affecting risk propagation in the coupled underground systems. By integrating holistic risk quantification with dynamic propagation analysis, this study offers a robust tool for understanding dynamic risk evolution and supports decision-making for seismic resilience of underground infrastructure in liquefiable soils.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"161 ","pages":"Article 112171"},"PeriodicalIF":8.0,"publicationDate":"2025-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145049132","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Spectrum prior-based and visibility fusion method for underwater image enhancement","authors":"Qifeng Liu ,&nbsp;Xin Yan ,&nbsp;Lu Shen ,&nbsp;Qiang Li","doi":"10.1016/j.engappai.2025.112203","DOIUrl":"10.1016/j.engappai.2025.112203","url":null,"abstract":"<div><div>When light propagates in water, it undergoes scattering and absorption phenomena, which typically result in haze, high blur, low contrast and color distortion, making it extremely challenging to obtain high-quality images. To address these issues, many existing methods target image enhancement by correcting specific aspects such as color shift or contrast. However, challenges like poor visibility and low-light conditions are often overlooked. In this paper, we proposed a spectrum prior-based and visibility fusion method (SPV) to enhance underwater images in terms of color, contrast, and visibility. Unlike existing methods, SPV complements the advantages of both physical and non-physical models, comprehensively addressing the problems of reduced visual visibility, color distortion, and low contrast caused by low-light environments, thereby significantly improving the overall image quality. We proposed a dehazing module based on spectral information priors, which reliably restores image quality under complex water conditions. Additionally, we introduced a color correction module based on human color perception and employed morphological operations, effectively solving the issues of color shift and unclear contours in underwater images. Furthermore, we proposed a visibility enhancement module based on the fuzzy c-means clustering method to improve image contrast and visibility, particularly under low-light conditions. Finally, through a detail enhancement fusion module, we simultaneously addressed problems related to color shift, low contrast, and low visibility. SPV showed excellent performance in application tests including feature point matching, geometric rotation estimation, and edge detection. Comparative experiments on four real underwater datasets against 14 advanced enhancement methods demonstrated promising results.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"161 ","pages":"Article 112203"},"PeriodicalIF":8.0,"publicationDate":"2025-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145049133","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Safety monitoring digital twin-based centralized model consolidation mechanism using dynamic node selection for multi-worker safety prediction","authors":"Sa Jim Soe Moe ,&nbsp;Atif Rizwan ,&nbsp;Anam Nawaz Khan ,&nbsp;Rongxu Xu ,&nbsp;Do Hyeun Kim","doi":"10.1016/j.engappai.2025.112186","DOIUrl":"10.1016/j.engappai.2025.112186","url":null,"abstract":"<div><div>The construction industry remains one of the most hazardous sectors, requiring innovative solutions to safeguard workers, especially in complex, dynamic outdoor environments. Digital Twin (DT) technology offers promising capabilities for real-time safety monitoring through virtual replicas of physical systems. However, existing DT frameworks rarely integrate comprehensive safety monitoring via a centralized model consolidation mechanism, such as Federated Learning (FL), which is explicitly tailored for multi-worker scenarios. Addressing this challenge, this paper proposes a FL-based Safety Monitoring Digital Twin (SMDT) framework designed to enhance multi-worker safety in resource-constrained settings. This enables real-time safety monitoring and control by representing on-site workers as virtual objects within a synchronized DT environment. A dynamic node selection mechanism based on client performance is employed to optimize global model convergence in FL. To validate the proposed approach, an edge computing-based experimental testbed using actual Raspberry Pi devices was implemented, using real-world construction safety data including worker status, weather conditions, and building structural parameters. Experimental results demonstrate the effectiveness of the proposed framework in significantly improving safety predictions and real-time monitoring efficiency. This research establishes a foundational work towards safer construction sites through intelligent, synchronized safety monitoring systems.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"161 ","pages":"Article 112186"},"PeriodicalIF":8.0,"publicationDate":"2025-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145049130","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Semantic analysis-based recommender system using sequential clustering and convolutional neural network","authors":"Yanjun Xu ,&nbsp;Chunqi Tian ,&nbsp;Wei Wang ,&nbsp;Lizhi Bai","doi":"10.1016/j.engappai.2025.112196","DOIUrl":"10.1016/j.engappai.2025.112196","url":null,"abstract":"<div><div>Accurate prediction of user preferences and generation of personalized recommendations remain as critical challenges in intelligent recommendation systems. In this study, we propose a novel recommendation model that transforms the rating prediction problem into a single-label multiclass classification task. The model integrates three key components: (1) ordered clustering information derived from user review text similarity, (2) rating rank similarity reflecting users’ behavioral tendencies, and (3) a convolutional neural network (CNN) to extract semantic representations from user textual data. First, user review embeddings are clustered to capture high-level semantic preferences, where cluster indices are utilized as ordered categorical features. Second, rating rank similarity features are constructed by comparing the relative ranking of items rated by similar users. These features are fused and fed into a CNN model, which outputs a predicted rating class (e.g., 1–5 stars) for each unobserved item, treated as a single-label classification target. To generate final Top-N recommendations, we further incorporate user-specific rating habits and item popularity to re-rank the classification outputs. The experimental results on public benchmark datasets indicate that our model substantially improves the prediction accuracy and recommendation quality compared with existing baselines. The proposed method offers a robust and interpretable approach to bridging textual review semantics, user behavior, and deep learning for rating-aware personalized recommendation.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"161 ","pages":"Article 112196"},"PeriodicalIF":8.0,"publicationDate":"2025-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145046192","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Contextual and orientation correction modules enhance weakly-supervised aerial object detection in remote sensing images","authors":"Le Yang ,&nbsp;Shunzhou Wang ,&nbsp;Xuerong Wang ,&nbsp;Shutong Wang ,&nbsp;Yuting Lu ,&nbsp;Binglu Wang","doi":"10.1016/j.engappai.2025.112110","DOIUrl":"10.1016/j.engappai.2025.112110","url":null,"abstract":"<div><div>This paper addresses the challenges of context and orientation ambiguity in weakly supervised aerial object detection. While current research focuses on improving detection accuracy and efficiency, it often encounters difficulties with contextual and rotational variations in aerial imagery. We propose a novel Context and Orientation Correction (COC) framework, which includes two innovative modules: a context correction module and an orientation correction module. The context correction module utilizes style normalization to guide the model in identifying atypical objects within specific contextual scenes by mitigating contextual disparities between instances and refining contextual information. Additionally, the orientation correction module aims to reduce feature distance between instances with varying orientations, leveraging contrastive learning to ensure consistent object representations. Furthermore, we introduce a category-aware aggregation loss to enhance similarity in feature representations of objects from the same category, thereby addressing the class collision issue commonly associated with contrastive learning. Our COC framework achieves 27.6% mean Average Precision and 59.8% mean Average Precision on the Detection in Optical Remote Sensing Image (DIOR) and Northwestern Polytechnical University Very High Resolution 10. v2 (NWPU VHR-10.v2) datasets, respectively, demonstrating its significant effectiveness.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"161 ","pages":"Article 112110"},"PeriodicalIF":8.0,"publicationDate":"2025-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145046193","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Emergency medical facility site selection in drone-based relief operations using an enhanced T-spherical fuzzy frank combined compromise solution method","authors":"Rajdip Mahajan ,&nbsp;Saptadeep Biswas ,&nbsp;Vladimir Simic ,&nbsp;Dragan Pamucar ,&nbsp;Abhijit Baidya ,&nbsp;Uttam Kumar Bera","doi":"10.1016/j.engappai.2025.112140","DOIUrl":"10.1016/j.engappai.2025.112140","url":null,"abstract":"<div><div>Unmanned aerial vehicles (UAVs) play a vital role in disaster response operations, emphasizing the need for efficient site selection for emergency medical facilities (EMFs). This study presents a structured framework for evaluating candidate sites and identifying critical criteria for establishing EMFs in drone-based relief operations. It proposes a novel T-spherical fuzzy (T-SF) multi-criteria group decision-making framework for EMF site selection. The framework integrates the T-SF-Entropy method and a hybrid subjective–objective weighting scheme that combines stepwise weight assessment ratio analysis and the method based on the removal effects of criteria. This integration enables a more reliable aggregation of expert opinions. The framework applies T-SF Frank aggregation operators in the modified combined compromise solution method to rank potential sites under multi-disaster conditions. A real-world case study evaluates alternative sites using the critical criteria and demonstrates the practical utility of the proposed model in the field of emergency engineering logistics. Quantitative analysis shows that the “urban logistics hub” achieves the highest compromise index due to its advantages in proximity, infrastructure, and supply chain access. Sensitivity analysis confirms that variations in parameters do not affect the stability of rankings. This study uses artificial intelligence to support intelligent decision-making in disaster response. It provides an effective engineering application that optimizes UAV-based healthcare deployment, enhances resource allocation, and improves the speed and accuracy of emergency medical responses.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"161 ","pages":"Article 112140"},"PeriodicalIF":8.0,"publicationDate":"2025-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145046194","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}