Pub Date : 2026-02-09DOI: 10.1016/j.compind.2026.104447
Bin Liu, Changfeng Yan, Ming Lv, Yuan Huang, Lixiao Wu
Domain adaptation-based methods are extensively applied to predict the Remaining Useful Life (RUL) of rolling bearings under complex operating conditions. However, the nonlinear degradation process of bearings gives rise to markedly non-stationary characteristics in vibration signals throughout the full life cycle. Although significant differences in fault features arise across different degradation stages, clearly identifying the critical degradation information remains a challenge. In this paper, a Signal Knowledge-enhanced Domain Adaptation Network (SKDAN) is proposed to learn domain-invariant features from non-stationary degradation processes, thereby improving cross-domain RUL prediction. Specifically, an adaptive short-time Fourier transform layer with a variable window is introduced to analyze the raw vibration signals in the time domain. This differentiable layer extracts time–frequency physical information with high energy concentration, which enhances the representation of degradation features. Subsequently, a novel discrepancy metric, termed Multi-Stage Maximum Mean Discrepancy (MSMMD), is proposed to replace the global average discrepancy with multiple local discrepancies. The MSMMD metric effectively increases the inter-class distance between cluster centers, which enables cross-domain feature alignment. Finally, an uncertainty measurement mechanism is constructed via a step-by-step training strategy, with the objective of quantifying the uncertainty in RUL results by calculating confidence intervals for prediction points. Comparative tests with other methods are conducted on two different bearing datasets, and the results demonstrate that SKDAN achieves superior performance and reliability in cross-domain RUL prediction.
{"title":"SKDAN: A Signal Knowledge-enhanced Domain Adaptation Network for remaining useful life prediction and uncertainty quantification of rolling bearings","authors":"Bin Liu, Changfeng Yan, Ming Lv, Yuan Huang, Lixiao Wu","doi":"10.1016/j.compind.2026.104447","DOIUrl":"https://doi.org/10.1016/j.compind.2026.104447","url":null,"abstract":"Domain adaptation-based methods are extensively applied to predict the Remaining Useful Life (RUL) of rolling bearings under complex operating conditions. However, the nonlinear degradation process of bearings gives rise to markedly non-stationary characteristics in vibration signals throughout the full life cycle. Although significant differences in fault features arise across different degradation stages, clearly identifying the critical degradation information remains a challenge. In this paper, a Signal Knowledge-enhanced Domain Adaptation Network (SKDAN) is proposed to learn domain-invariant features from non-stationary degradation processes, thereby improving cross-domain RUL prediction. Specifically, an adaptive short-time Fourier transform layer with a variable window is introduced to analyze the raw vibration signals in the time domain. This differentiable layer extracts time–frequency physical information with high energy concentration, which enhances the representation of degradation features. Subsequently, a novel discrepancy metric, termed Multi-Stage Maximum Mean Discrepancy (MSMMD), is proposed to replace the global average discrepancy with multiple local discrepancies. The MSMMD metric effectively increases the inter-class distance between cluster centers, which enables cross-domain feature alignment. Finally, an uncertainty measurement mechanism is constructed via a step-by-step training strategy, with the objective of quantifying the uncertainty in RUL results by calculating confidence intervals for prediction points. Comparative tests with other methods are conducted on two different bearing datasets, and the results demonstrate that SKDAN achieves superior performance and reliability in cross-domain RUL prediction.","PeriodicalId":55219,"journal":{"name":"Computers in Industry","volume":"24 1","pages":""},"PeriodicalIF":10.0,"publicationDate":"2026-02-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146146507","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-02-06DOI: 10.1016/j.compind.2026.104448
Simone Barandoni, Lorenzo Cascone, Emiliano Marrale, Salvatore Puccio, Filippo Chiarello
{"title":"Automating customer needs analysis: A comparative study of large language models in the travel industry","authors":"Simone Barandoni, Lorenzo Cascone, Emiliano Marrale, Salvatore Puccio, Filippo Chiarello","doi":"10.1016/j.compind.2026.104448","DOIUrl":"https://doi.org/10.1016/j.compind.2026.104448","url":null,"abstract":"","PeriodicalId":55219,"journal":{"name":"Computers in Industry","volume":"33 1","pages":""},"PeriodicalIF":10.0,"publicationDate":"2026-02-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146134522","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-02-04DOI: 10.1016/j.compind.2026.104444
Haijian Wang, Han Mo, Zhishen Liang, Xuemei Zhao
{"title":"Elevator traction wheel groove wear recognition based on lightweight YOLOv8 and sub-pixel edge detection","authors":"Haijian Wang, Han Mo, Zhishen Liang, Xuemei Zhao","doi":"10.1016/j.compind.2026.104444","DOIUrl":"https://doi.org/10.1016/j.compind.2026.104444","url":null,"abstract":"","PeriodicalId":55219,"journal":{"name":"Computers in Industry","volume":"156 1","pages":""},"PeriodicalIF":10.0,"publicationDate":"2026-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146134525","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-02-03DOI: 10.1016/j.compind.2026.104445
Qixuan Li, Yangjian Ji, Linjin Sun, Nian Zhang, Tiannuo Yang
{"title":"Anomaly detection for industrial time series in process industry using informed machine learning with graph attention networks","authors":"Qixuan Li, Yangjian Ji, Linjin Sun, Nian Zhang, Tiannuo Yang","doi":"10.1016/j.compind.2026.104445","DOIUrl":"https://doi.org/10.1016/j.compind.2026.104445","url":null,"abstract":"","PeriodicalId":55219,"journal":{"name":"Computers in Industry","volume":"79 1","pages":""},"PeriodicalIF":10.0,"publicationDate":"2026-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146110201","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-30DOI: 10.1016/j.compind.2026.104440
Khuong Le Nguyen , Thong M. Pham , Khanh Nguyen , Saeed Banihashemi
This study presents an innovative method for the dynamic analysis and generative design of high-speed ballasted railway bridges subjected to High-Speed Locomotive Multiple Articulated (HSLM-A) train loads. Compliant with Eurocode standards, a comprehensive database of over 4 million data points was generated, including maximum vertical displacement and acceleration data for more than 10,000 bridges affected by ten HSLM-A models at speeds ranging from 150 to 350 km/h. The key contribution of this research lies in a novel surrogate model that incorporates semantic search and advanced decoding techniques, significantly enhancing the calculation time and accuracy of dynamic behaviour predictions for single-span high-speed railway bridges. The performance of the developed model was verified through case studies on existing 30 m and 50 m span bridges, evidenced by an R2 value of 0.999, highlighting the model's precision and rapid prediction capabilities. Additionally, the research introduces a cutting-edge framework for optimising the cross-sectional geometry of prestressed concrete railway bridges. A case study was then conducted for a typical box girder bridge to identify 25 feasible solutions better than the original design in terms of mass per unit length. This research showcases the synergy between advanced technology and structural optimisation, and it opens new avenues for future studies in this field.
{"title":"Automation in dynamic analysis and generative design of prestressed concrete railway bridge infrastructures","authors":"Khuong Le Nguyen , Thong M. Pham , Khanh Nguyen , Saeed Banihashemi","doi":"10.1016/j.compind.2026.104440","DOIUrl":"10.1016/j.compind.2026.104440","url":null,"abstract":"<div><div>This study presents an innovative method for the dynamic analysis and generative design of high-speed ballasted railway bridges subjected to High-Speed Locomotive Multiple Articulated (HSLM-A) train loads. Compliant with Eurocode standards, a comprehensive database of over 4 million data points was generated, including maximum vertical displacement and acceleration data for more than 10,000 bridges affected by ten HSLM-A models at speeds ranging from 150 to 350 km/h. The key contribution of this research lies in a novel surrogate model that incorporates semantic search and advanced decoding techniques, significantly enhancing the calculation time and accuracy of dynamic behaviour predictions for single-span high-speed railway bridges. The performance of the developed model was verified through case studies on existing 30 m and 50 m span bridges, evidenced by an R<sup>2</sup> value of 0.999, highlighting the model's precision and rapid prediction capabilities. Additionally, the research introduces a cutting-edge framework for optimising the cross-sectional geometry of prestressed concrete railway bridges. A case study was then conducted for a typical box girder bridge to identify 25 feasible solutions better than the original design in terms of mass per unit length. This research showcases the synergy between advanced technology and structural optimisation, and it opens new avenues for future studies in this field.</div></div>","PeriodicalId":55219,"journal":{"name":"Computers in Industry","volume":"176 ","pages":"Article 104440"},"PeriodicalIF":9.1,"publicationDate":"2026-01-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146079530","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-29DOI: 10.1016/j.compind.2026.104441
Hongmin Li , Shengpeng Zhang , Shuo Huang , Shuanglong Rong , Haifeng Gao
This study proposes a novel distributed collaborative surrogate modeling framework for structural reliability assessment. It integrates the least absolute shrinkage and selection operator for feature selection, gradient boosting regression for ensemble prediction, and an improved particle swarm optimization algorithm for hyperparameter tuning, forming a new surrogate modeling approach abbreviated as IPSLG. A distributed collaborative strategy is then applied to extend IPSLG into a collaborative modeling framework, hereafter referred to as distributed collaborative IPSLG (DCIPSLG). Validation through strength reliability analysis of cantilever tubes and creep deformation reliability assessment of missile bracket–cabin systems demonstrate the superior performance of DCIPSLG against some established surrogate modeling techniques. Comparative results confirm significant improvements in prediction accuracy and computational efficiency, establishing the proposed framework as an effective tool for complex engineering reliability analysis.
{"title":"An ensemble learning-enhanced collaborative surrogate modeling approach with improved particle swarm optimization for structural reliability assessment","authors":"Hongmin Li , Shengpeng Zhang , Shuo Huang , Shuanglong Rong , Haifeng Gao","doi":"10.1016/j.compind.2026.104441","DOIUrl":"10.1016/j.compind.2026.104441","url":null,"abstract":"<div><div>This study proposes a novel distributed collaborative surrogate modeling framework for structural reliability assessment. It integrates the least absolute shrinkage and selection operator for feature selection, gradient boosting regression for ensemble prediction, and an improved particle swarm optimization algorithm for hyperparameter tuning, forming a new surrogate modeling approach abbreviated as IPSLG. A distributed collaborative strategy is then applied to extend IPSLG into a collaborative modeling framework, hereafter referred to as distributed collaborative IPSLG (DCIPSLG). Validation through strength reliability analysis of cantilever tubes and creep deformation reliability assessment of missile bracket–cabin systems demonstrate the superior performance of DCIPSLG against some established surrogate modeling techniques. Comparative results confirm significant improvements in prediction accuracy and computational efficiency, establishing the proposed framework as an effective tool for complex engineering reliability analysis.</div></div>","PeriodicalId":55219,"journal":{"name":"Computers in Industry","volume":"176 ","pages":"Article 104441"},"PeriodicalIF":9.1,"publicationDate":"2026-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146071765","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-12DOI: 10.1016/j.compind.2025.104433
Hengyi Liu , Yangfan Liu , Yuhua Fu , Xuan Li , Xinyun Li , Shuhong Zhao , Xiaolei Liu , Xiong Xiong
Accurate prediction of pre-weaning piglet growth curves is essential for forecasting weaning weight, a pivotal indicator of piglets’ future development and genetic breeding potential. Traditionally, recording growth curves relies on daily manual weighing, which is labor-intensive, induces stress in piglets, and is unsuitable for continuous monitoring. To address these limitations, it is imperative to develop a system that enables non-contact individual weight monitoring and early-stage prediction of pre-weaning growth curves. This study introduces FarrowSight, an intelligent system integrated with a Red Green Blue-Depth (RGB-D) camera, designed to identify freely moving piglets non-contact and estimate each piglet’s instantaneous weight in farrowing stables. Concurrently, the AutoGluon-based Iterative Network (AG-IterNet) algorithm was developed to enable precise monitoring of individual piglet time-series growth dynamics based on instantaneous weight measurement, achieving the prediction of pre-weaning growth curves as early as possible. FarrowSight exhibited exceptional predictive accuracy for pre-weaning growth curves using only the first week of weight data, achieving a coefficient of determination (R2) of 0.827 (95 % confidence interval (CI): 0.816, 0.838) and a Mean Absolute Percentage Error (MAPE) of 10.833 % (95 % CI: 10.526 %, 11.139 %). Moreover, prediction performance demonstrated progressive enhancement with the incorporation of additional early-stage weight measurements, effectively advancing the assessment timeline from traditional 3–4 week weaning weights to the critical first post-birth week. This innovation holds significant potential for optimizing feeding management and selecting superior individuals within the swine industry.
{"title":"FarrowSight: An intelligent system for early-stage piglet growth performance prediction in farrowing stables","authors":"Hengyi Liu , Yangfan Liu , Yuhua Fu , Xuan Li , Xinyun Li , Shuhong Zhao , Xiaolei Liu , Xiong Xiong","doi":"10.1016/j.compind.2025.104433","DOIUrl":"10.1016/j.compind.2025.104433","url":null,"abstract":"<div><div>Accurate prediction of pre-weaning piglet growth curves is essential for forecasting weaning weight, a pivotal indicator of piglets’ future development and genetic breeding potential. Traditionally, recording growth curves relies on daily manual weighing, which is labor-intensive, induces stress in piglets, and is unsuitable for continuous monitoring. To address these limitations, it is imperative to develop a system that enables non-contact individual weight monitoring and early-stage prediction of pre-weaning growth curves. This study introduces FarrowSight, an intelligent system integrated with a Red Green Blue-Depth (RGB-D) camera, designed to identify freely moving piglets non-contact and estimate each piglet’s instantaneous weight in farrowing stables. Concurrently, the AutoGluon-based Iterative Network (AG-IterNet) algorithm was developed to enable precise monitoring of individual piglet time-series growth dynamics based on instantaneous weight measurement, achieving the prediction of pre-weaning growth curves as early as possible. FarrowSight exhibited exceptional predictive accuracy for pre-weaning growth curves using only the first week of weight data, achieving a coefficient of determination (R<sup>2</sup>) of 0.827 (95 % confidence interval (CI): 0.816, 0.838) and a Mean Absolute Percentage Error (MAPE) of 10.833 % (95 % CI: 10.526 %, 11.139 %). Moreover, prediction performance demonstrated progressive enhancement with the incorporation of additional early-stage weight measurements, effectively advancing the assessment timeline from traditional 3–4 week weaning weights to the critical first post-birth week. This innovation holds significant potential for optimizing feeding management and selecting superior individuals within the swine industry.</div></div>","PeriodicalId":55219,"journal":{"name":"Computers in Industry","volume":"176 ","pages":"Article 104433"},"PeriodicalIF":9.1,"publicationDate":"2026-01-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145950196","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Tracking systems are essential in various fields, such as health and manufacturing industries, enabling mapping between the real and digital worlds. Amongst others, Augmented Reality Tracking Systems (ARTS) are more recent and less explored. This work proposes a quantitative metrological methodology to evaluate ARTS tooltip tracking performance, facilitating benchmarking, parameter optimization, and system selection for specific tasks. A specific 3D-printed measuring artifact is proposed to guide tooltip positioning. Tracking accuracy and precision are estimated, highlighting the effects of influence factors. The methodology was tested with two commercial state-of-the-art ARTSs using marker-based tooltips, i.e., a Microsoft HoloLens 2 and a stereo camera system equipped with Intel RealSense SR305 cameras. Metrological characteristics are evaluated, and the Euclidean distance expanded uncertainty at a conventional 95% confidence level is estimated as for the HoloLens 2 and for the stereo system, resulting in a superior metrological performance of HoloLens 2 under the specified conditions. This study provides a standardized approach for quantitatively comparing AR tracking systems, offering valuable insights for optimizing their use in specific applications and, innovatively in the context of ARTS, associates measurement uncertainty with tracked distance values.
{"title":"A metrological approach for Augmented Reality tooltip tracking assessment","authors":"Federico Salerno, Luca Ulrich, Giacomo Maculotti, Sandro Moos, Gianfranco Genta, Enrico Vezzetti, Maurizio Galetto","doi":"10.1016/j.compind.2025.104430","DOIUrl":"10.1016/j.compind.2025.104430","url":null,"abstract":"<div><div>Tracking systems are essential in various fields, such as health and manufacturing industries, enabling mapping between the real and digital worlds. Amongst others, Augmented Reality Tracking Systems (ARTS) are more recent and less explored. This work proposes a quantitative metrological methodology to evaluate ARTS tooltip tracking performance, facilitating benchmarking, parameter optimization, and system selection for specific tasks. A specific 3D-printed measuring artifact is proposed to guide tooltip positioning. Tracking accuracy and precision are estimated, highlighting the effects of influence factors. The methodology was tested with two commercial state-of-the-art ARTSs using marker-based tooltips, i.e., a Microsoft HoloLens 2 and a stereo camera system equipped with Intel RealSense SR305 cameras. Metrological characteristics are evaluated, and the Euclidean distance expanded uncertainty at a conventional 95% confidence level is estimated as <span><math><mrow><mn>5</mn><mo>.</mo><mn>071</mn><mspace></mspace><mtext>mm</mtext></mrow></math></span> for the HoloLens 2 and <span><math><mrow><mn>6</mn><mo>.</mo><mn>800</mn><mspace></mspace><mtext>mm</mtext></mrow></math></span> for the stereo system, resulting in a superior metrological performance of HoloLens 2 under the specified conditions. This study provides a standardized approach for quantitatively comparing AR tracking systems, offering valuable insights for optimizing their use in specific applications and, innovatively in the context of ARTS, associates measurement uncertainty with tracked distance values.</div></div>","PeriodicalId":55219,"journal":{"name":"Computers in Industry","volume":"175 ","pages":"Article 104430"},"PeriodicalIF":9.1,"publicationDate":"2026-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145925645","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-05DOI: 10.1016/j.compind.2025.104432
Tianming Ni , Wen Jiang , Huaguo Liang , Xiaoqing Wen , Mu Nie
Accurate detection of a wide range of defect patterns on wafers is crucial for enhancing chip yield and ensuring the reliability of semiconductor manufacturing systems. As this process becomes increasingly complex, new types of defects — referred to as unknown defects — emerge on wafers. Traditional pattern recognition methods struggle in this setting because limited samples are insufficient to effectively train deep learning models. Moreover, these models are prone to catastrophic forgetting when incrementally trained on new defect classes. To address these challenges, this paper proposes a method termed Few-Shot Class Contrastive Incremental Learning (FCCIL) for unknown wafer map defect detection. FCCIL integrates a contrastive learning network for distinguishing novel defect types and an incremental learning model for dynamic knowledge updating—both designed to mitigate catastrophic forgetting, thereby enabling the detection of unknown defects in wafer maps with limited data. Experimental results demonstrate a 4% improvement in forgetting resistance over state-of-the-art approaches, confirming the effectiveness of FCCIL in real-world semiconductor manufacturing scenarios.
{"title":"Incremental learning strategies for improved detection of unknown defects in wafer maps with limited samples","authors":"Tianming Ni , Wen Jiang , Huaguo Liang , Xiaoqing Wen , Mu Nie","doi":"10.1016/j.compind.2025.104432","DOIUrl":"10.1016/j.compind.2025.104432","url":null,"abstract":"<div><div>Accurate detection of a wide range of defect patterns on wafers is crucial for enhancing chip yield and ensuring the reliability of semiconductor manufacturing systems. As this process becomes increasingly complex, new types of defects — referred to as unknown defects — emerge on wafers. Traditional pattern recognition methods struggle in this setting because limited samples are insufficient to effectively train deep learning models. Moreover, these models are prone to catastrophic forgetting when incrementally trained on new defect classes. To address these challenges, this paper proposes a method termed Few-Shot Class Contrastive Incremental Learning (FCCIL) for unknown wafer map defect detection. FCCIL integrates a contrastive learning network for distinguishing novel defect types and an incremental learning model for dynamic knowledge updating—both designed to mitigate catastrophic forgetting, thereby enabling the detection of unknown defects in wafer maps with limited data. Experimental results demonstrate a 4% improvement in forgetting resistance over state-of-the-art approaches, confirming the effectiveness of FCCIL in real-world semiconductor manufacturing scenarios.</div></div>","PeriodicalId":55219,"journal":{"name":"Computers in Industry","volume":"175 ","pages":"Article 104432"},"PeriodicalIF":9.1,"publicationDate":"2026-01-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145897225","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：