Early identification and treatment of stroke can greatly improve patient outcomes and quality of life.Although clinical tests such as the Cincinnati Pre-hospital Stroke Scale(CPSS)and the Face Arm Speech Test(FAST)are...Early identification and treatment of stroke can greatly improve patient outcomes and quality of life.Although clinical tests such as the Cincinnati Pre-hospital Stroke Scale(CPSS)and the Face Arm Speech Test(FAST)are commonly used for stroke screening,accurate administration is dependent on specialized training.In this study,we proposed a novel multimodal deep learning approach,based on the FAST,for assessing suspected stroke patients exhibiting symptoms such as limb weakness,facial paresis,and speech disorders in acute settings.We collected a dataset comprising videos and audio recordings of emergency room patients performing designated limb movements,facial expressions,and speech tests based on the FAST.We compared the constructed deep learning model,which was designed to process multi-modal datasets,with six prior models that achieved good action classification performance,including the I3D,SlowFast,X3D,TPN,TimeSformer,and MViT.We found that the findings of our deep learning model had a higher clinical value compared with the other approaches.Moreover,the multi-modal model outperformed its single-module variants,highlighting the benefit of utilizing multiple types of patient data,such as action videos and speech audio.These results indicate that a multi-modal deep learning model combined with the FAST could greatly improve the accuracy and sensitivity of early stroke identification of stroke,thus providing a practical and powerful tool for assessing stroke patients in an emergency clinical setting.展开更多
Detecting pavement cracks is critical for road safety and infrastructure management.Traditional methods,relying on manual inspection and basic image processing,are time-consuming and prone to errors.Recent deep-learni...Detecting pavement cracks is critical for road safety and infrastructure management.Traditional methods,relying on manual inspection and basic image processing,are time-consuming and prone to errors.Recent deep-learning(DL)methods automate crack detection,but many still struggle with variable crack patterns and environmental conditions.This study aims to address these limitations by introducing the Masker Transformer,a novel hybrid deep learning model that integrates the precise localization capabilities of Mask Region-based Convolutional Neural Network(Mask R-CNN)with the global contextual awareness of Vision Transformer(ViT).The research focuses on leveraging the strengths of both architectures to enhance segmentation accuracy and adaptability across different pavement conditions.We evaluated the performance of theMaskerTransformer against other state-of-theartmodels such asU-Net,TransformerU-Net(TransUNet),U-NetTransformer(UNETr),SwinU-NetTransformer(Swin-UNETr),You Only Look Once version 8(YoloV8),and Mask R-CNN using two benchmark datasets:Crack500 and DeepCrack.The findings reveal that the MaskerTransformer significantly outperforms the existing models,achieving the highest Dice SimilarityCoefficient(DSC),precision,recall,and F1-Score across both datasets.Specifically,the model attained a DSC of 80.04%on Crack500 and 91.37%on DeepCrack,demonstrating superior segmentation accuracy and reliability.The high precision and recall rates further substantiate its effectiveness in real-world applications,suggesting that the Masker Transformer can serve as a robust tool for automated pavement crack detection,potentially replacing more traditional methods.展开更多
为了解决大型工程项目中文件的传输时间与成本问题,提出一个基于文件工作流的工程项目文件管理优化方法。首先,构建了工程项目文件管理环境和具有逻辑顺序的文件工作流模型,分析了文件的传输和缓存。在此基础上,将文件管理优化问题建模...为了解决大型工程项目中文件的传输时间与成本问题,提出一个基于文件工作流的工程项目文件管理优化方法。首先,构建了工程项目文件管理环境和具有逻辑顺序的文件工作流模型,分析了文件的传输和缓存。在此基础上,将文件管理优化问题建模为马尔可夫过程,通过设计状态空间、动作空间及奖励函数等实现文件工作流的任务完成时间与缓存成本的联合优化。其次,采用对抗式双重深度Q网络(dueling double deep Q network,D3QN)来降低训练时间,提高训练效率。仿真结果验证了提出方案在不同参数配置下文件传输的有效性,并且在任务体量增大时仍能保持较好的优化能力。展开更多
The complex wiring,bulky data collection devices,and difficulty in fast and on-site data interpretation significantly limit the practical application of flexible strain sensors as wearable devices.To tackle these chal...The complex wiring,bulky data collection devices,and difficulty in fast and on-site data interpretation significantly limit the practical application of flexible strain sensors as wearable devices.To tackle these challenges,this work develops an artificial intelligenceassisted,wireless,flexible,and wearable mechanoluminescent strain sensor system(AIFWMLS)by integration of deep learning neural network-based color data processing system(CDPS)with a sandwich-structured flexible mechanoluminescent sensor(SFLC)film.The SFLC film shows remarkable and robust mechanoluminescent performance with a simple structure for easy fabrication.The CDPS system can rapidly and accurately extract and interpret the color of the SFLC film to strain values with auto-correction of errors caused by the varying color temperature,which significantly improves the accuracy of the predicted strain.A smart glove mechanoluminescent sensor system demonstrates the great potential of the AIFWMLS system in human gesture recognition.Moreover,the versatile SFLC film can also serve as a encryption device.The integration of deep learning neural network-based artificial intelligence and SFLC film provides a promising strategy to break the“color to strain value”bottleneck that hinders the practical application of flexible colorimetric strain sensors,which could promote the development of wearable and flexible strain sensors from laboratory research to consumer markets.展开更多
Neurodegenerative diseases cause great medical and economic burdens for both patients and society;however, the complex molecular mechanisms thereof are not yet well understood. With the development of high-coverage se...Neurodegenerative diseases cause great medical and economic burdens for both patients and society;however, the complex molecular mechanisms thereof are not yet well understood. With the development of high-coverage sequencing technology, researchers have started to notice that genomic repeat regions, previously neglected in search of disease culprits, are active contributors to multiple neurodegenerative diseases. In this review, we describe the association between repeat element variants and multiple degenerative diseases through genome-wide association studies and targeted sequencing. We discuss the identification of disease-relevant repeat element variants, further powered by the advancement of long-read sequencing technologies and their related tools, and summarize recent findings in the molecular mechanisms of repeat element variants in brain degeneration, such as those causing transcriptional silencing or RNA-mediated gain of toxic function. Furthermore, we describe how in silico predictions using innovative computational models, such as deep learning language models, could enhance and accelerate our understanding of the functional impact of repeat element variants. Finally, we discuss future directions to advance current findings for a better understanding of neurodegenerative diseases and the clinical applications of genomic repeat elements.展开更多
To fully leverage the advantages of mechanization and informatization in tunnel boring machine(TBM)operations,the authors aim to promote the advancement of tunnel construction technology toward intelligent development...To fully leverage the advantages of mechanization and informatization in tunnel boring machine(TBM)operations,the authors aim to promote the advancement of tunnel construction technology toward intelligent development.This involved exploring the deep integration of next-generation artificial intelligence technologies,such as sensing technology,automatic control technology,big data technology,deep learning,and machine vision,with key operational processes,including TBM excavation,direction adjustment,step changes,inverted arch block assembly,material transportation,and operation status assurance.The results of this integration are summarized as follows.(1)TBM key excavation parameter prediction algorithm was developed with an accuracy rate exceeding 90%.The TBM intelligent step-change control algorithm,based on machine vision,achieved an image segmentation accuracy rate of 95%and gripper shoe positioning error of±5 mm.(2)An automatic positioning system for inverted arch blocks was developed,enabling real-time perception of the spatial position and deviation during the assembly process.The system maintains an elevation positioning deviation within±3 mm and a horizontal positioning deviation within±10 mm,reducing the number of surveyors in each work team.(3)A TBM intelligent rail transportation system that achieves real-time human-machine positioning,automatic switch opening and closing,automatic obstacle avoidance,intelligent transportation planning,and integrated scheduling and command was designed.Each locomotive formation reduces one shunter and improves comprehensive transportation efficiency by more than 20%.(4)Intelligent analysis and prediction algorithms were developed to monitor and predict the trends of the hydraulic and gear oil parameters in real time,enhancing the proactive maintenance and system reliability.展开更多
Security and safety remain paramount concerns for both governments and individuals worldwide.In today’s context,the frequency of crimes and terrorist attacks is alarmingly increasing,becoming increasingly intolerable...Security and safety remain paramount concerns for both governments and individuals worldwide.In today’s context,the frequency of crimes and terrorist attacks is alarmingly increasing,becoming increasingly intolerable to society.Consequently,there is a pressing need for swift identification of potential threats to preemptively alert law enforcement and security forces,thereby preventing potential attacks or violent incidents.Recent advancements in big data analytics and deep learning have significantly enhanced the capabilities of computer vision in object detection,particularly in identifying firearms.This paper introduces a novel automatic firearm detection surveillance system,utilizing a one-stage detection approach named MARIE(Mechanism for Realtime Identification of Firearms).MARIE incorporates the Single Shot Multibox Detector(SSD)model,which has been specifically optimized to balance the speed-accuracy trade-off critical in firearm detection applications.The SSD model was further refined by integrating MobileNetV2 and InceptionV2 architectures for superior feature extraction capabilities.The experimental results demonstrate that this modified SSD configuration provides highly satisfactory performance,surpassing existing methods trained on the same dataset in terms of the critical speedaccuracy trade-off.Through these innovations,MARIE sets a new standard in surveillance technology,offering a robust solution to enhance public safety effectively.展开更多
BACKGROUND Patients with inflammatory bowel disease are at a 2-8-fold higher risk of deve-loping venous thromboembolism(VTE)as compared to the general population.Although the exact pathogenesis is unclear,the literatu...BACKGROUND Patients with inflammatory bowel disease are at a 2-8-fold higher risk of deve-loping venous thromboembolism(VTE)as compared to the general population.Although the exact pathogenesis is unclear,the literature suggests that increased risk of thromboembolic events in such patients occurs as a result of increased coagulation factors,inflammatory cytokines,and reduction in anticoagulants leading to a prothrombotic state.AIM To assess the prevalence,risk factors,management,and outcome of ulcerative colitis(UC)patients who develop VTE.METHODS This was a retrospective chart review done in The Gastroenterology Department of The Aga Khan University Hospital.Data was collected from medical records for all patients admitted with a diagnosis of UC from January 2012 to December 2022.RESULTS Seventy-four patients fulfilled the inclusion criteria.The mean±SD of age at presentation of all UC patients was 45 years±10 years whereas for those who developed VTE,it was 47.6 years±14.7 years.Hypertension and diabetes were the most common co-morbid seen among UC patients with a frequency of 17(22.9%)and 12(16.2%),respectively.A total of 5(6.7%)patients developed VTE.Deep venous thrombosis was the most common thromboembolic phenomenon seen in 3(60%)patients.All the patients with UC and concomitant VTE were discharged home(5;100%).CONCLUSION The prevalence of VTE with UC in Pakistani patients corresponds with the international literature.However,multi-centric studies are required to further explore these results.展开更多
Deep neural networks(DNNs)are effective in solving both forward and inverse problems for nonlinear partial differential equations(PDEs).However,conventional DNNs are not effective in handling problems such as delay di...Deep neural networks(DNNs)are effective in solving both forward and inverse problems for nonlinear partial differential equations(PDEs).However,conventional DNNs are not effective in handling problems such as delay differential equations(DDEs)and delay integrodifferential equations(DIDEs)with constant delays,primarily due to their low regularity at delayinduced breaking points.In this paper,a DNN method that combines multi-task learning(MTL)which is proposed to solve both the forward and inverse problems of DIDEs.The core idea of this approach is to divide the original equation into multiple tasks based on the delay,using auxiliary outputs to represent the integral terms,followed by the use of MTL to seamlessly incorporate the properties at the breaking points into the loss function.Furthermore,given the increased training dificulty associated with multiple tasks and outputs,we employ a sequential training scheme to reduce training complexity and provide reference solutions for subsequent tasks.This approach significantly enhances the approximation accuracy of solving DIDEs with DNNs,as demonstrated by comparisons with traditional DNN methods.We validate the effectiveness of this method through several numerical experiments,test various parameter sharing structures in MTL and compare the testing results of these structures.Finally,this method is implemented to solve the inverse problem of nonlinear DIDE and the results show that the unknown parameters of DIDE can be discovered with sparse or noisy data.展开更多
Titanium alloy has the advantages of high strength,strong corrosion resistance,excellent high and low temperature mechanical properties,etc.,and is widely used in aerospace,shipbuilding,weapons and equipment,and other...Titanium alloy has the advantages of high strength,strong corrosion resistance,excellent high and low temperature mechanical properties,etc.,and is widely used in aerospace,shipbuilding,weapons and equipment,and other fields.In recent years,with the continuous increase in demand for medium-thick plate titanium alloys,corresponding welding technologies have also continued to develop.Therefore,this article reviews the research progress of deep penetration welding technology for medium-thick plate titanium alloys,mainly covering traditional arc welding,high-energy beam welding,and other welding technologies.Among many methods,narrow gap welding,hybrid welding,and external energy field assistance welding all contribute to improving the welding efficiency and quality of medium-thick plate titanium alloys.Finally,the development trend of deep penetration welding technology for mediumthick plate titanium alloys is prospected.展开更多
Multimodal sensor fusion can make full use of the advantages of various sensors,make up for the shortcomings of a single sensor,achieve information verification or information security through information redundancy,a...Multimodal sensor fusion can make full use of the advantages of various sensors,make up for the shortcomings of a single sensor,achieve information verification or information security through information redundancy,and improve the reliability and safety of the system.Artificial intelligence(AI),referring to the simulation of human intelligence in machines that are programmed to think and learn like humans,represents a pivotal frontier in modern scientific research.With the continuous development and promotion of AI technology in Sensor 4.0 age,multimodal sensor fusion is becoming more and more intelligent and automated,and is expected to go further in the future.With this context,this review article takes a comprehensive look at the recent progress on AI-enhanced multimodal sensors and their integrated devices and systems.Based on the concept and principle of sensor technologies and AI algorithms,the theoretical underpinnings,technological breakthroughs,and pragmatic applications of AI-enhanced multimodal sensors in various fields such as robotics,healthcare,and environmental monitoring are highlighted.Through a comparative study of the dual/tri-modal sensors with and without using AI technologies(especially machine learning and deep learning),AI-enhanced multimodal sensors highlight the potential of AI to improve sensor performance,data processing,and decision-making capabilities.Furthermore,the review analyzes the challenges and opportunities afforded by AI-enhanced multimodal sensors,and offers a prospective outlook on the forthcoming advancements.展开更多
基金supported by the Ministry of Science and Technology of China,No.2020AAA0109605(to XL)Meizhou Major Scientific and Technological Innovation PlatformsProjects of Guangdong Provincial Science & Technology Plan Projects,No.2019A0102005(to HW).
文摘Early identification and treatment of stroke can greatly improve patient outcomes and quality of life.Although clinical tests such as the Cincinnati Pre-hospital Stroke Scale(CPSS)and the Face Arm Speech Test(FAST)are commonly used for stroke screening,accurate administration is dependent on specialized training.In this study,we proposed a novel multimodal deep learning approach,based on the FAST,for assessing suspected stroke patients exhibiting symptoms such as limb weakness,facial paresis,and speech disorders in acute settings.We collected a dataset comprising videos and audio recordings of emergency room patients performing designated limb movements,facial expressions,and speech tests based on the FAST.We compared the constructed deep learning model,which was designed to process multi-modal datasets,with six prior models that achieved good action classification performance,including the I3D,SlowFast,X3D,TPN,TimeSformer,and MViT.We found that the findings of our deep learning model had a higher clinical value compared with the other approaches.Moreover,the multi-modal model outperformed its single-module variants,highlighting the benefit of utilizing multiple types of patient data,such as action videos and speech audio.These results indicate that a multi-modal deep learning model combined with the FAST could greatly improve the accuracy and sensitivity of early stroke identification of stroke,thus providing a practical and powerful tool for assessing stroke patients in an emergency clinical setting.
文摘Detecting pavement cracks is critical for road safety and infrastructure management.Traditional methods,relying on manual inspection and basic image processing,are time-consuming and prone to errors.Recent deep-learning(DL)methods automate crack detection,but many still struggle with variable crack patterns and environmental conditions.This study aims to address these limitations by introducing the Masker Transformer,a novel hybrid deep learning model that integrates the precise localization capabilities of Mask Region-based Convolutional Neural Network(Mask R-CNN)with the global contextual awareness of Vision Transformer(ViT).The research focuses on leveraging the strengths of both architectures to enhance segmentation accuracy and adaptability across different pavement conditions.We evaluated the performance of theMaskerTransformer against other state-of-theartmodels such asU-Net,TransformerU-Net(TransUNet),U-NetTransformer(UNETr),SwinU-NetTransformer(Swin-UNETr),You Only Look Once version 8(YoloV8),and Mask R-CNN using two benchmark datasets:Crack500 and DeepCrack.The findings reveal that the MaskerTransformer significantly outperforms the existing models,achieving the highest Dice SimilarityCoefficient(DSC),precision,recall,and F1-Score across both datasets.Specifically,the model attained a DSC of 80.04%on Crack500 and 91.37%on DeepCrack,demonstrating superior segmentation accuracy and reliability.The high precision and recall rates further substantiate its effectiveness in real-world applications,suggesting that the Masker Transformer can serve as a robust tool for automated pavement crack detection,potentially replacing more traditional methods.
文摘为了解决大型工程项目中文件的传输时间与成本问题,提出一个基于文件工作流的工程项目文件管理优化方法。首先,构建了工程项目文件管理环境和具有逻辑顺序的文件工作流模型,分析了文件的传输和缓存。在此基础上,将文件管理优化问题建模为马尔可夫过程,通过设计状态空间、动作空间及奖励函数等实现文件工作流的任务完成时间与缓存成本的联合优化。其次,采用对抗式双重深度Q网络(dueling double deep Q network,D3QN)来降低训练时间,提高训练效率。仿真结果验证了提出方案在不同参数配置下文件传输的有效性,并且在任务体量增大时仍能保持较好的优化能力。
基金funded by the National Natural Science Foundation of China(52475580)the Special Foundation of the Taishan Scholar Project(tsqn202211077,tsqn202311077)+3 种基金Shandong Provincial Excellent Overseas Young Scholar Foundation(2023HWYQ-069)the Shandong Provincial Natural Science Foundation(ZR2023ME118,ZR2023QF080)the Natural Science Foundation of Qingdao City(23-2-1-219-zyyd-jch,23-2-1-111-zyyd-jch)the Fundamental Research Funds for the Central Universities(23CX06032A).
文摘The complex wiring,bulky data collection devices,and difficulty in fast and on-site data interpretation significantly limit the practical application of flexible strain sensors as wearable devices.To tackle these challenges,this work develops an artificial intelligenceassisted,wireless,flexible,and wearable mechanoluminescent strain sensor system(AIFWMLS)by integration of deep learning neural network-based color data processing system(CDPS)with a sandwich-structured flexible mechanoluminescent sensor(SFLC)film.The SFLC film shows remarkable and robust mechanoluminescent performance with a simple structure for easy fabrication.The CDPS system can rapidly and accurately extract and interpret the color of the SFLC film to strain values with auto-correction of errors caused by the varying color temperature,which significantly improves the accuracy of the predicted strain.A smart glove mechanoluminescent sensor system demonstrates the great potential of the AIFWMLS system in human gesture recognition.Moreover,the versatile SFLC film can also serve as a encryption device.The integration of deep learning neural network-based artificial intelligence and SFLC film provides a promising strategy to break the“color to strain value”bottleneck that hinders the practical application of flexible colorimetric strain sensors,which could promote the development of wearable and flexible strain sensors from laboratory research to consumer markets.
基金supported by the National Natural Science Foundation of China, No.61932008Natural Science Foundation of Shanghai, No.21ZR1403200 (both to JC)。
文摘Neurodegenerative diseases cause great medical and economic burdens for both patients and society;however, the complex molecular mechanisms thereof are not yet well understood. With the development of high-coverage sequencing technology, researchers have started to notice that genomic repeat regions, previously neglected in search of disease culprits, are active contributors to multiple neurodegenerative diseases. In this review, we describe the association between repeat element variants and multiple degenerative diseases through genome-wide association studies and targeted sequencing. We discuss the identification of disease-relevant repeat element variants, further powered by the advancement of long-read sequencing technologies and their related tools, and summarize recent findings in the molecular mechanisms of repeat element variants in brain degeneration, such as those causing transcriptional silencing or RNA-mediated gain of toxic function. Furthermore, we describe how in silico predictions using innovative computational models, such as deep learning language models, could enhance and accelerate our understanding of the functional impact of repeat element variants. Finally, we discuss future directions to advance current findings for a better understanding of neurodegenerative diseases and the clinical applications of genomic repeat elements.
文摘To fully leverage the advantages of mechanization and informatization in tunnel boring machine(TBM)operations,the authors aim to promote the advancement of tunnel construction technology toward intelligent development.This involved exploring the deep integration of next-generation artificial intelligence technologies,such as sensing technology,automatic control technology,big data technology,deep learning,and machine vision,with key operational processes,including TBM excavation,direction adjustment,step changes,inverted arch block assembly,material transportation,and operation status assurance.The results of this integration are summarized as follows.(1)TBM key excavation parameter prediction algorithm was developed with an accuracy rate exceeding 90%.The TBM intelligent step-change control algorithm,based on machine vision,achieved an image segmentation accuracy rate of 95%and gripper shoe positioning error of±5 mm.(2)An automatic positioning system for inverted arch blocks was developed,enabling real-time perception of the spatial position and deviation during the assembly process.The system maintains an elevation positioning deviation within±3 mm and a horizontal positioning deviation within±10 mm,reducing the number of surveyors in each work team.(3)A TBM intelligent rail transportation system that achieves real-time human-machine positioning,automatic switch opening and closing,automatic obstacle avoidance,intelligent transportation planning,and integrated scheduling and command was designed.Each locomotive formation reduces one shunter and improves comprehensive transportation efficiency by more than 20%.(4)Intelligent analysis and prediction algorithms were developed to monitor and predict the trends of the hydraulic and gear oil parameters in real time,enhancing the proactive maintenance and system reliability.
文摘Security and safety remain paramount concerns for both governments and individuals worldwide.In today’s context,the frequency of crimes and terrorist attacks is alarmingly increasing,becoming increasingly intolerable to society.Consequently,there is a pressing need for swift identification of potential threats to preemptively alert law enforcement and security forces,thereby preventing potential attacks or violent incidents.Recent advancements in big data analytics and deep learning have significantly enhanced the capabilities of computer vision in object detection,particularly in identifying firearms.This paper introduces a novel automatic firearm detection surveillance system,utilizing a one-stage detection approach named MARIE(Mechanism for Realtime Identification of Firearms).MARIE incorporates the Single Shot Multibox Detector(SSD)model,which has been specifically optimized to balance the speed-accuracy trade-off critical in firearm detection applications.The SSD model was further refined by integrating MobileNetV2 and InceptionV2 architectures for superior feature extraction capabilities.The experimental results demonstrate that this modified SSD configuration provides highly satisfactory performance,surpassing existing methods trained on the same dataset in terms of the critical speedaccuracy trade-off.Through these innovations,MARIE sets a new standard in surveillance technology,offering a robust solution to enhance public safety effectively.
文摘BACKGROUND Patients with inflammatory bowel disease are at a 2-8-fold higher risk of deve-loping venous thromboembolism(VTE)as compared to the general population.Although the exact pathogenesis is unclear,the literature suggests that increased risk of thromboembolic events in such patients occurs as a result of increased coagulation factors,inflammatory cytokines,and reduction in anticoagulants leading to a prothrombotic state.AIM To assess the prevalence,risk factors,management,and outcome of ulcerative colitis(UC)patients who develop VTE.METHODS This was a retrospective chart review done in The Gastroenterology Department of The Aga Khan University Hospital.Data was collected from medical records for all patients admitted with a diagnosis of UC from January 2012 to December 2022.RESULTS Seventy-four patients fulfilled the inclusion criteria.The mean±SD of age at presentation of all UC patients was 45 years±10 years whereas for those who developed VTE,it was 47.6 years±14.7 years.Hypertension and diabetes were the most common co-morbid seen among UC patients with a frequency of 17(22.9%)and 12(16.2%),respectively.A total of 5(6.7%)patients developed VTE.Deep venous thrombosis was the most common thromboembolic phenomenon seen in 3(60%)patients.All the patients with UC and concomitant VTE were discharged home(5;100%).CONCLUSION The prevalence of VTE with UC in Pakistani patients corresponds with the international literature.However,multi-centric studies are required to further explore these results.
文摘Deep neural networks(DNNs)are effective in solving both forward and inverse problems for nonlinear partial differential equations(PDEs).However,conventional DNNs are not effective in handling problems such as delay differential equations(DDEs)and delay integrodifferential equations(DIDEs)with constant delays,primarily due to their low regularity at delayinduced breaking points.In this paper,a DNN method that combines multi-task learning(MTL)which is proposed to solve both the forward and inverse problems of DIDEs.The core idea of this approach is to divide the original equation into multiple tasks based on the delay,using auxiliary outputs to represent the integral terms,followed by the use of MTL to seamlessly incorporate the properties at the breaking points into the loss function.Furthermore,given the increased training dificulty associated with multiple tasks and outputs,we employ a sequential training scheme to reduce training complexity and provide reference solutions for subsequent tasks.This approach significantly enhances the approximation accuracy of solving DIDEs with DNNs,as demonstrated by comparisons with traditional DNN methods.We validate the effectiveness of this method through several numerical experiments,test various parameter sharing structures in MTL and compare the testing results of these structures.Finally,this method is implemented to solve the inverse problem of nonlinear DIDE and the results show that the unknown parameters of DIDE can be discovered with sparse or noisy data.
基金financially supported by the Key Research and Development Program of Ningbo(Grant No.2023Z098)Natural Science Foundation of Inner Mongolia(Grant No.2023MS05040)+1 种基金Shenyang Collaborative Innovation Center Project for Multiple Energy Fields Composite Processing of Special Materials(Grant No.JG210027)Shenyang Key Technology Special Project of The Open Competition Mechanism to Select the Best Solution(Grant Nos.2022210101000827,2022-0-43-048).
文摘Titanium alloy has the advantages of high strength,strong corrosion resistance,excellent high and low temperature mechanical properties,etc.,and is widely used in aerospace,shipbuilding,weapons and equipment,and other fields.In recent years,with the continuous increase in demand for medium-thick plate titanium alloys,corresponding welding technologies have also continued to develop.Therefore,this article reviews the research progress of deep penetration welding technology for medium-thick plate titanium alloys,mainly covering traditional arc welding,high-energy beam welding,and other welding technologies.Among many methods,narrow gap welding,hybrid welding,and external energy field assistance welding all contribute to improving the welding efficiency and quality of medium-thick plate titanium alloys.Finally,the development trend of deep penetration welding technology for mediumthick plate titanium alloys is prospected.
基金supported by the National Natural Science Foundation of China(No.62404111)Natural Science Foundation of Jiangsu Province(No.BK20240635)+2 种基金Natural Science Foundation of the Jiangsu Higher Education Institutions of China(No.24KJB510025)Natural Science Research Start-up Foundation of Recruiting Talents of Nanjing University of Posts and Telecommunications(No.NY223157 and NY223156)Opening Project of Advanced Inte-grated Circuit Package and Testing Research Center of Jiangsu Province(No.NTIKFJJ202303).
文摘Multimodal sensor fusion can make full use of the advantages of various sensors,make up for the shortcomings of a single sensor,achieve information verification or information security through information redundancy,and improve the reliability and safety of the system.Artificial intelligence(AI),referring to the simulation of human intelligence in machines that are programmed to think and learn like humans,represents a pivotal frontier in modern scientific research.With the continuous development and promotion of AI technology in Sensor 4.0 age,multimodal sensor fusion is becoming more and more intelligent and automated,and is expected to go further in the future.With this context,this review article takes a comprehensive look at the recent progress on AI-enhanced multimodal sensors and their integrated devices and systems.Based on the concept and principle of sensor technologies and AI algorithms,the theoretical underpinnings,technological breakthroughs,and pragmatic applications of AI-enhanced multimodal sensors in various fields such as robotics,healthcare,and environmental monitoring are highlighted.Through a comparative study of the dual/tri-modal sensors with and without using AI technologies(especially machine learning and deep learning),AI-enhanced multimodal sensors highlight the potential of AI to improve sensor performance,data processing,and decision-making capabilities.Furthermore,the review analyzes the challenges and opportunities afforded by AI-enhanced multimodal sensors,and offers a prospective outlook on the forthcoming advancements.
