The rise of artifcial intelligence(AI)has brought breakthroughs in many areas of medicine.In ophthalmology,AI has delivered robust results in the screening and detection of diabetic retinopathy,age-related macular deg...The rise of artifcial intelligence(AI)has brought breakthroughs in many areas of medicine.In ophthalmology,AI has delivered robust results in the screening and detection of diabetic retinopathy,age-related macular degeneration,glaucoma,and retinopathy of prematurity.Cataract management is another feld that can beneft from greater AI application.Cataract is the leading cause of reversible visual impairment with a rising global clinical burden.Improved diagnosis,monitoring,and surgical management are necessary to address this challenge.In addition,patients in large developing countries often sufer from limited access to tertiary care,a problem further exacerbated by the ongoing COVID-19 pandemic.AI on the other hand,can help transform cataract management by improving automation,efcacy and overcoming geographical barriers.First,AI can be applied as a telediagnostic platform to screen and diagnose patients with cataract using slit-lamp and fundus photographs.This utilizes a deep-learning,convolutional neural network(CNN)to detect and classify referable cataracts appropriately.Second,some of the latest intraocular lens formulas have used AI to enhance prediction accuracy,achieving superior postoperative refractive results compared to traditional formulas.Third,AI can be used to augment cataract surgical skill training by identifying diferent phases of cataract surgery on video and to optimize operating theater workfows by accurately predicting the duration of surgical procedures.Fourth,some AI CNN models are able to efectively predict the progression of posterior capsule opacifcation and eventual need for YAG laser capsulotomy.These advances in AI could transform cataract management and enable delivery of efcient ophthalmic services.The key challenges include ethical management of data,ensuring data security and privacy,demonstrating clinically acceptable performance,improving the generalizability of AI models across heterogeneous populations,and improving the trust of end-users.展开更多
Nuclear medicine and molecular imaging plays a signifcant role in the detection and management of cardiovascular disease(CVD).With recent advancements in computer power and the availability of digital archives,artifci...Nuclear medicine and molecular imaging plays a signifcant role in the detection and management of cardiovascular disease(CVD).With recent advancements in computer power and the availability of digital archives,artifcial intelligence(AI)is rapidly gaining traction in the feld of medical imaging,including nuclear medicine and molecular imaging.However,the complex and time-consuming workfow and interpretation involved in nuclear medicine and molecular imaging,limit their extensive utilization in clinical practice.To address this challenge,AI has emerged as a fundamental tool for enhancing the role of nuclear medicine and molecular imaging.It has shown promising applications in various crucial aspects of nuclear cardiology,such as optimizing imaging protocols,facilitating data processing,aiding in CVD diagnosis,risk classifcation and prognosis.In this review paper,we will introduce the key concepts of AI and provide an overview of its current progress in the feld of nuclear cardiology.In addition,we will discuss future perspectives for AI in this domain.展开更多
Traditional design,manufacturing and maintenance are run and managed independently under their own rules and regulations in an increasingly time-and-cost inefective manner.A unifed platform for efcient and intelligent...Traditional design,manufacturing and maintenance are run and managed independently under their own rules and regulations in an increasingly time-and-cost inefective manner.A unifed platform for efcient and intelligent designmanufacturing-maintenance of mechanical equipment and systems is highly needed in this rapidly digitized world.In this work,the defnition of digital twin and its research progress and associated challenges in the design,manufacturing and maintenance of engineering components and equipment were thoroughly reviewed.It is indicated that digital twin concept and associated technology provide a feasible solution for the integration of design-manufacturingmaintenance as it has behaved in the entire lifecycle of products.For this aim,a framework for information-physical combination,in which a more accurate design,a defect-free manufacturing,a more intelligent maintenance,and a more advanced sensing technology,is prospected.展开更多
The numerical computation of nonlocal Schrödinger equations (SEs) on the whole real axis is considered. Based on the artifcial boundary method, we frst derive the exact artifcial nonrefecting boundary conditions....The numerical computation of nonlocal Schrödinger equations (SEs) on the whole real axis is considered. Based on the artifcial boundary method, we frst derive the exact artifcial nonrefecting boundary conditions. For the numerical implementation, we employ the quadrature scheme proposed in Tian and Du (SIAM J Numer Anal 51:3458-3482, 2013) to discretize the nonlocal operator, and apply the z-transform to the discrete nonlocal system in an exterior domain, and derive an exact solution expression for the discrete system. This solution expression is referred to our exact nonrefecting boundary condition and leads us to reformulate the original infnite discrete system into an equivalent fnite discrete system. Meanwhile, the trapezoidal quadrature rule is introduced to discretize the contour integral involved in exact boundary conditions. Numerical examples are fnally provided to demonstrate the efectiveness of our approach.展开更多
This study presents a novel method for optimizing parameters in urban flood models,aiming to address the tedious and complex issues associated with parameter optimization.First,a coupled one-dimensional pipe network r...This study presents a novel method for optimizing parameters in urban flood models,aiming to address the tedious and complex issues associated with parameter optimization.First,a coupled one-dimensional pipe network runoff model and a two-dimensional surface runoff model were integrated to construct an interpretable urban flood model.Next,a principle for dividing urban hydrological response units was introduced,incorporating surface attribute features.The K-means algorithm was used to explore the clustering patterns of the uncertain parameters in the model,and an artificial neural network(ANN)was employed to identify the sensitive parameters.Finally,a genetic algorithm(GA) was used to calibrate the parameter thresholds of the sub-catchment units in different urban land-use zones within the flood model.The results demonstrate that the parameter optimization method based on K-means-ANN-GA achieved an average Nash-Sutcliffe efficiency coefficient(NSE) of 0.81.Compared to the ANN-GA and K-means-deep neural networks(DNN) methods,the proposed method better characterizes the runoff generation and flow processes.This study demonstrates the significant potential of combining machine learning techniques with physical knowledge in parameter optimization research for flood models.展开更多
Facing the escalating effects of climate change,it is critical to improve the prediction and understanding of the hurricane evacuation decisions made by households in order to enhance emergency management.Current stud...Facing the escalating effects of climate change,it is critical to improve the prediction and understanding of the hurricane evacuation decisions made by households in order to enhance emergency management.Current studies in this area often have relied on psychology-driven linear models,which frequently exhibited limitations in practice.The present study proposed a novel interpretable machine learning approach to predict household-level evacuation decisions by leveraging easily accessible demographic and resource-related predictors,compared to existing models that mainly rely on psychological factors.An enhanced logistic regression model(that is,an interpretable machine learning approach) was developed for accurate predictions by automatically accounting for nonlinearities and interactions(that is,univariate and bivariate threshold effects).Specifically,nonlinearity and interaction detection were enabled by low-depth decision trees,which offer transparent model structure and robustness.A survey dataset collected in the aftermath of Hurricanes Katrina and Rita,two of the most intense tropical storms of the last two decades,was employed to test the new methodology.The findings show that,when predicting the households’ evacuation decisions,the enhanced logistic regression model outperformed previous linear models in terms of both model fit and predictive capability.This outcome suggests that our proposed methodology could provide a new tool and framework for emergency management authorities to improve the prediction of evacuation traffic demands in a timely and accurate manner.展开更多
This article proposed an angle measurement method based on second harmonic generation(SHG)using an artifcial neural network(ANN).The method comprises three sequential parts:SHG spectrum collection,data preprocessing,a...This article proposed an angle measurement method based on second harmonic generation(SHG)using an artifcial neural network(ANN).The method comprises three sequential parts:SHG spectrum collection,data preprocessing,and neural network training.First,the referenced angles and SHG spectrums are collected by the autocollimator and SHG-based angle sensor,respectively,for training.The mapping is learned by the trained ANN after completing the training process,which solves the inverse problem of obtaining the angle from the SHG spectrum.Then,the feasibility of the proposed method is verifed in multiple-peak Maker fringe and single-peak phase-matching areas,with an overall angle measurement range exceeding 20,000 arcseconds.The predicted angles by ANN are compared with the autocollimator to evaluate the measure-ment performance in all the angular ranges.Particularly,a sub-arcsecond level of accuracy and resolution is achieved in the phase-matching area.展开更多
Owing to their compactness,robustness,low cost,high stability,and difraction-limited beam quality,mode-locked fber lasers play an indispensable role in micro/nanomanufacturing,precision metrology,laser spectroscopy,Li...Owing to their compactness,robustness,low cost,high stability,and difraction-limited beam quality,mode-locked fber lasers play an indispensable role in micro/nanomanufacturing,precision metrology,laser spectroscopy,LiDAR,biomedi-cal imaging,optical communication,and soliton physics.Mode-locked fber lasers are a highly complex nonlinear optical system,and understanding the underlying physical mechanisms or the fexible manipulation of ultrafast laser output is chal-lenging.The traditional research paradigm often relies on known physical models,sophisticated numerical calculations,and exploratory experimental attempts.However,when dealing with several complex issues,these traditional approaches often face limitations and struggles in fnding efective solutions.As an emerging data-driven analysis and processing technology,artifcial intelligence(AI)has brought new insights into the development of mode-locked fber lasers.This review highlights the areas where AI exhibits potential in accelerating the development of mode-locked fber lasers,including nonlinear dynamics prediction,ultrashort pulse characterization,inverse design,and automatic control of mode-locked fber lasers.Furthermore,the challenges and potential future development are discussed.展开更多
The need for safe operation and effective maintenance of pipelines grows as oil and gas demand rises.Thereby,it is increasingly imperative to monitor and inspect the pipeline system,detect causes contributing to devel...The need for safe operation and effective maintenance of pipelines grows as oil and gas demand rises.Thereby,it is increasingly imperative to monitor and inspect the pipeline system,detect causes contributing to developing pipeline damage,and perform preventive maintenance in a timely manner.Currently,pipeline inspection is performed at pre-determined intervals of several months,which is not sufficiently robust in terms of timeliness.This research proposes a drone and artificial intelligence reconsolidated technological solution(DARTS) by integrating drone technology and deep learning technique.This solution is aimed to detect the targeted potential root problems-pipes out of alignment and deterioration of pipe support system-that can cause critical pipeline failures and predict the progress of the detected problems by collecting and analyzing image data periodically.The test results show that DARTS can be effectively used to support decision making for preventive pipeline maintenance to increase pipeline system s afety and resilience.展开更多
文摘The rise of artifcial intelligence(AI)has brought breakthroughs in many areas of medicine.In ophthalmology,AI has delivered robust results in the screening and detection of diabetic retinopathy,age-related macular degeneration,glaucoma,and retinopathy of prematurity.Cataract management is another feld that can beneft from greater AI application.Cataract is the leading cause of reversible visual impairment with a rising global clinical burden.Improved diagnosis,monitoring,and surgical management are necessary to address this challenge.In addition,patients in large developing countries often sufer from limited access to tertiary care,a problem further exacerbated by the ongoing COVID-19 pandemic.AI on the other hand,can help transform cataract management by improving automation,efcacy and overcoming geographical barriers.First,AI can be applied as a telediagnostic platform to screen and diagnose patients with cataract using slit-lamp and fundus photographs.This utilizes a deep-learning,convolutional neural network(CNN)to detect and classify referable cataracts appropriately.Second,some of the latest intraocular lens formulas have used AI to enhance prediction accuracy,achieving superior postoperative refractive results compared to traditional formulas.Third,AI can be used to augment cataract surgical skill training by identifying diferent phases of cataract surgery on video and to optimize operating theater workfows by accurately predicting the duration of surgical procedures.Fourth,some AI CNN models are able to efectively predict the progression of posterior capsule opacifcation and eventual need for YAG laser capsulotomy.These advances in AI could transform cataract management and enable delivery of efcient ophthalmic services.The key challenges include ethical management of data,ensuring data security and privacy,demonstrating clinically acceptable performance,improving the generalizability of AI models across heterogeneous populations,and improving the trust of end-users.
基金the Innovative Research Group Project of the National Natural Science Foundation of China(82271992).
文摘Nuclear medicine and molecular imaging plays a signifcant role in the detection and management of cardiovascular disease(CVD).With recent advancements in computer power and the availability of digital archives,artifcial intelligence(AI)is rapidly gaining traction in the feld of medical imaging,including nuclear medicine and molecular imaging.However,the complex and time-consuming workfow and interpretation involved in nuclear medicine and molecular imaging,limit their extensive utilization in clinical practice.To address this challenge,AI has emerged as a fundamental tool for enhancing the role of nuclear medicine and molecular imaging.It has shown promising applications in various crucial aspects of nuclear cardiology,such as optimizing imaging protocols,facilitating data processing,aiding in CVD diagnosis,risk classifcation and prognosis.In this review paper,we will introduce the key concepts of AI and provide an overview of its current progress in the feld of nuclear cardiology.In addition,we will discuss future perspectives for AI in this domain.
基金Supported by National Natural Science Foundation of China(Grant Nos.51922041,51835003).
文摘Traditional design,manufacturing and maintenance are run and managed independently under their own rules and regulations in an increasingly time-and-cost inefective manner.A unifed platform for efcient and intelligent designmanufacturing-maintenance of mechanical equipment and systems is highly needed in this rapidly digitized world.In this work,the defnition of digital twin and its research progress and associated challenges in the design,manufacturing and maintenance of engineering components and equipment were thoroughly reviewed.It is indicated that digital twin concept and associated technology provide a feasible solution for the integration of design-manufacturingmaintenance as it has behaved in the entire lifecycle of products.For this aim,a framework for information-physical combination,in which a more accurate design,a defect-free manufacturing,a more intelligent maintenance,and a more advanced sensing technology,is prospected.
基金Jiwei Zhang is partially supported by the National Natural Science Foundation of China under Grant No.11771035the NSAF U1530401+3 种基金the Natural Science Foundation of Hubei Province No.2019CFA007Xiangtan University 2018ICIP01Chunxiong Zheng is partially supported by Natural Science Foundation of Xinjiang Autonom ous Region under No.2019D01C026the National Natural Science Foundation of China under Grant Nos.11771248 and 91630205。
文摘The numerical computation of nonlocal Schrödinger equations (SEs) on the whole real axis is considered. Based on the artifcial boundary method, we frst derive the exact artifcial nonrefecting boundary conditions. For the numerical implementation, we employ the quadrature scheme proposed in Tian and Du (SIAM J Numer Anal 51:3458-3482, 2013) to discretize the nonlocal operator, and apply the z-transform to the discrete nonlocal system in an exterior domain, and derive an exact solution expression for the discrete system. This solution expression is referred to our exact nonrefecting boundary condition and leads us to reformulate the original infnite discrete system into an equivalent fnite discrete system. Meanwhile, the trapezoidal quadrature rule is introduced to discretize the contour integral involved in exact boundary conditions. Numerical examples are fnally provided to demonstrate the efectiveness of our approach.
基金supported by the National Natural Science Foundation of China (Grant Nos.42271483,42071364)the Postgraduate Research&Practice Innovation Program of Jiangsu Province (Grant No.KYCX23_1696).
文摘This study presents a novel method for optimizing parameters in urban flood models,aiming to address the tedious and complex issues associated with parameter optimization.First,a coupled one-dimensional pipe network runoff model and a two-dimensional surface runoff model were integrated to construct an interpretable urban flood model.Next,a principle for dividing urban hydrological response units was introduced,incorporating surface attribute features.The K-means algorithm was used to explore the clustering patterns of the uncertain parameters in the model,and an artificial neural network(ANN)was employed to identify the sensitive parameters.Finally,a genetic algorithm(GA) was used to calibrate the parameter thresholds of the sub-catchment units in different urban land-use zones within the flood model.The results demonstrate that the parameter optimization method based on K-means-ANN-GA achieved an average Nash-Sutcliffe efficiency coefficient(NSE) of 0.81.Compared to the ANN-GA and K-means-deep neural networks(DNN) methods,the proposed method better characterizes the runoff generation and flow processes.This study demonstrates the significant potential of combining machine learning techniques with physical knowledge in parameter optimization research for flood models.
基金supported by the National Science Foundation under Grant Nos.2303578,2303579, 05 27699,0838654,and 1212790by an Early-Career Research Fellowship from the Gulf Research Program of the National Academies of Sciences,Engineering,and Medicine
文摘Facing the escalating effects of climate change,it is critical to improve the prediction and understanding of the hurricane evacuation decisions made by households in order to enhance emergency management.Current studies in this area often have relied on psychology-driven linear models,which frequently exhibited limitations in practice.The present study proposed a novel interpretable machine learning approach to predict household-level evacuation decisions by leveraging easily accessible demographic and resource-related predictors,compared to existing models that mainly rely on psychological factors.An enhanced logistic regression model(that is,an interpretable machine learning approach) was developed for accurate predictions by automatically accounting for nonlinearities and interactions(that is,univariate and bivariate threshold effects).Specifically,nonlinearity and interaction detection were enabled by low-depth decision trees,which offer transparent model structure and robustness.A survey dataset collected in the aftermath of Hurricanes Katrina and Rita,two of the most intense tropical storms of the last two decades,was employed to test the new methodology.The findings show that,when predicting the households’ evacuation decisions,the enhanced logistic regression model outperformed previous linear models in terms of both model fit and predictive capability.This outcome suggests that our proposed methodology could provide a new tool and framework for emergency management authorities to improve the prediction of evacuation traffic demands in a timely and accurate manner.
基金supported by the Japan Society for the Promo-tion of Science(20H00211).
文摘This article proposed an angle measurement method based on second harmonic generation(SHG)using an artifcial neural network(ANN).The method comprises three sequential parts:SHG spectrum collection,data preprocessing,and neural network training.First,the referenced angles and SHG spectrums are collected by the autocollimator and SHG-based angle sensor,respectively,for training.The mapping is learned by the trained ANN after completing the training process,which solves the inverse problem of obtaining the angle from the SHG spectrum.Then,the feasibility of the proposed method is verifed in multiple-peak Maker fringe and single-peak phase-matching areas,with an overall angle measurement range exceeding 20,000 arcseconds.The predicted angles by ANN are compared with the autocollimator to evaluate the measure-ment performance in all the angular ranges.Particularly,a sub-arcsecond level of accuracy and resolution is achieved in the phase-matching area.
基金supported by the National Natural Science Foundation of China(62203473)Hunan Provincial Natural Science Foundation(2023JJ40778).
文摘Owing to their compactness,robustness,low cost,high stability,and difraction-limited beam quality,mode-locked fber lasers play an indispensable role in micro/nanomanufacturing,precision metrology,laser spectroscopy,LiDAR,biomedi-cal imaging,optical communication,and soliton physics.Mode-locked fber lasers are a highly complex nonlinear optical system,and understanding the underlying physical mechanisms or the fexible manipulation of ultrafast laser output is chal-lenging.The traditional research paradigm often relies on known physical models,sophisticated numerical calculations,and exploratory experimental attempts.However,when dealing with several complex issues,these traditional approaches often face limitations and struggles in fnding efective solutions.As an emerging data-driven analysis and processing technology,artifcial intelligence(AI)has brought new insights into the development of mode-locked fber lasers.This review highlights the areas where AI exhibits potential in accelerating the development of mode-locked fber lasers,including nonlinear dynamics prediction,ultrashort pulse characterization,inverse design,and automatic control of mode-locked fber lasers.Furthermore,the challenges and potential future development are discussed.
基金This project was partially supported by the Center for Midstream and Management Science at Lamar University,Beaumont,Texas,USA.
文摘The need for safe operation and effective maintenance of pipelines grows as oil and gas demand rises.Thereby,it is increasingly imperative to monitor and inspect the pipeline system,detect causes contributing to developing pipeline damage,and perform preventive maintenance in a timely manner.Currently,pipeline inspection is performed at pre-determined intervals of several months,which is not sufficiently robust in terms of timeliness.This research proposes a drone and artificial intelligence reconsolidated technological solution(DARTS) by integrating drone technology and deep learning technique.This solution is aimed to detect the targeted potential root problems-pipes out of alignment and deterioration of pipe support system-that can cause critical pipeline failures and predict the progress of the detected problems by collecting and analyzing image data periodically.The test results show that DARTS can be effectively used to support decision making for preventive pipeline maintenance to increase pipeline system s afety and resilience.
