Since its inception,Systems Engineering(SE)has developed as a distinctive discipline,and there has been significant progress in this field in the past two decades.Compared to other engineering disciplines,SE is not af...Since its inception,Systems Engineering(SE)has developed as a distinctive discipline,and there has been significant progress in this field in the past two decades.Compared to other engineering disciplines,SE is not affirmed by a set of underlying fundamental propositions,instead it has emerged as a set of best practices to deal with intricacies stemming from the stochastic nature of engineering complex systems and addressing their problems.Since the existing methodologies and paradigms(dominant patterns of thought and concepts)of SE are very diverse and somewhat fragmented.This appears to create some confusion regarding the design,deployment,operation,and application of SE.The purpose of this paper is 1)to delineate the development of SE from 1926-2017 based on insights derived from a histogram analysis,2)to discuss the different paradigms and school of thoughts related to SE,3)to derive a set of fundamental attributes of SE using advanced coding techniques and analysis,and 4)to present a newly developed instrument that could assess the performance of systems engineers.More than Two hundred and fifty different sources have been reviewed in this research in order to demonstrate the development trajectory of the SE discipline based on the frequency of publication.展开更多
Today’s rapid proliferation of information and technological advancements has led to complex and uncertain modern systems environments.The problems resulting from this increased complexity may surpass engineers’curr...Today’s rapid proliferation of information and technological advancements has led to complex and uncertain modern systems environments.The problems resulting from this increased complexity may surpass engineers’current capacity to perform effectively within the domain of complex systems.In response to this situation,the concept of Systems Thinking(ST)has been advanced as an aid to building a mental map that offers a robust conceptual understanding to offset the challenges of modern system of systems(SoS)problems.Although there has been some research regarding the effect of age and gender on ST preferences,there is still a lack of studies investigating how an individual’s ST skills preferences in system of systems(SoS)domain vary across educational qualifications.In addition,most of the extant literature focuses on one or two measures to assess the individual ST;thus,there is a need to include the full spectrum of ST measures to assess the ST skills preferences of an individual in the domain of complex systems.To address these gaps,this research uses an established ST skills preferences instrument to gauge an individual’s ST skills preferences in the SoS domain based on the educational qualifications.Two hundred and fifty-eight participants with educational qualifications ranging from non-degree to graduate degree participated in the research.The analysis of the responses was performed by a post-hoc test to show which groups differ significantly.From the results obtained through aggregate individual responses,we conclude that each group(i.e bachelor,masters and phD),possesses a different ST skills preference profile on average,and the educational qualifications in the SoS environment has a moderation impact on individuals’system skills preferences.展开更多
Accurate traffic forecasting is crucial for understanding and managing congestion for effi-cient transportation planning.However,conventional approaches often neglect epistemic uncertainty,which arises from incomplete...Accurate traffic forecasting is crucial for understanding and managing congestion for effi-cient transportation planning.However,conventional approaches often neglect epistemic uncertainty,which arises from incomplete knowledge across different spatiotemporal scales.This study addresses this challenge by introducing a novel methodology to establish dynamic spatiotemporal correlations that captures the unobserved heterogeneity in travel time through distinct peaks in probability density functions,guided by physics-based prin-ciples.We propose an innovative approach to modifying both prediction and correction steps of the Kalman filter(KF)algorithm by leveraging established spatiotemporal correla-tions.Central to our approach is the development of a novel deep learning(DL)model called the physics informed-graph convolutional gated recurrent neural network(PI-GRNN).Functioning as the state-space model within the KF,the PI-GRNN exploits estab-lished correlations to construct dynamic adjacency matrices that utilize the inherent struc-ture and relationships within the transportation network to capture sequential patterns and dependencies over time.Furthermore,our methodology integrates insights gained from correlations into the correction step of the KF algorithm that helps in enhancing its correctional capabilities.This integrated approach proves instrumental in alleviating the inherent model drift associated with data-driven methods,as periodic corrections through update step of KF refine the predictions generated by the PI-GRNN.To the best of our knowledge,this study represents a pioneering effort in integrating DL and KF algorithms in this unique symbiotic manner.Through extensive experimentation with real-world traf-fic data,we demonstrate the superior performance of our model compared to the bench-mark approaches.展开更多
基金We would like to personally thank anonymous reviewers for raising such questions that have transformed this manuscript into a muchimproved paper.
文摘Since its inception,Systems Engineering(SE)has developed as a distinctive discipline,and there has been significant progress in this field in the past two decades.Compared to other engineering disciplines,SE is not affirmed by a set of underlying fundamental propositions,instead it has emerged as a set of best practices to deal with intricacies stemming from the stochastic nature of engineering complex systems and addressing their problems.Since the existing methodologies and paradigms(dominant patterns of thought and concepts)of SE are very diverse and somewhat fragmented.This appears to create some confusion regarding the design,deployment,operation,and application of SE.The purpose of this paper is 1)to delineate the development of SE from 1926-2017 based on insights derived from a histogram analysis,2)to discuss the different paradigms and school of thoughts related to SE,3)to derive a set of fundamental attributes of SE using advanced coding techniques and analysis,and 4)to present a newly developed instrument that could assess the performance of systems engineers.More than Two hundred and fifty different sources have been reviewed in this research in order to demonstrate the development trajectory of the SE discipline based on the frequency of publication.
文摘Today’s rapid proliferation of information and technological advancements has led to complex and uncertain modern systems environments.The problems resulting from this increased complexity may surpass engineers’current capacity to perform effectively within the domain of complex systems.In response to this situation,the concept of Systems Thinking(ST)has been advanced as an aid to building a mental map that offers a robust conceptual understanding to offset the challenges of modern system of systems(SoS)problems.Although there has been some research regarding the effect of age and gender on ST preferences,there is still a lack of studies investigating how an individual’s ST skills preferences in system of systems(SoS)domain vary across educational qualifications.In addition,most of the extant literature focuses on one or two measures to assess the individual ST;thus,there is a need to include the full spectrum of ST measures to assess the ST skills preferences of an individual in the domain of complex systems.To address these gaps,this research uses an established ST skills preferences instrument to gauge an individual’s ST skills preferences in the SoS domain based on the educational qualifications.Two hundred and fifty-eight participants with educational qualifications ranging from non-degree to graduate degree participated in the research.The analysis of the responses was performed by a post-hoc test to show which groups differ significantly.From the results obtained through aggregate individual responses,we conclude that each group(i.e bachelor,masters and phD),possesses a different ST skills preference profile on average,and the educational qualifications in the SoS environment has a moderation impact on individuals’system skills preferences.
基金Funding for this research was provided by NSF[1910397,2106989]NCDOT[TCE2020-01].
文摘Accurate traffic forecasting is crucial for understanding and managing congestion for effi-cient transportation planning.However,conventional approaches often neglect epistemic uncertainty,which arises from incomplete knowledge across different spatiotemporal scales.This study addresses this challenge by introducing a novel methodology to establish dynamic spatiotemporal correlations that captures the unobserved heterogeneity in travel time through distinct peaks in probability density functions,guided by physics-based prin-ciples.We propose an innovative approach to modifying both prediction and correction steps of the Kalman filter(KF)algorithm by leveraging established spatiotemporal correla-tions.Central to our approach is the development of a novel deep learning(DL)model called the physics informed-graph convolutional gated recurrent neural network(PI-GRNN).Functioning as the state-space model within the KF,the PI-GRNN exploits estab-lished correlations to construct dynamic adjacency matrices that utilize the inherent struc-ture and relationships within the transportation network to capture sequential patterns and dependencies over time.Furthermore,our methodology integrates insights gained from correlations into the correction step of the KF algorithm that helps in enhancing its correctional capabilities.This integrated approach proves instrumental in alleviating the inherent model drift associated with data-driven methods,as periodic corrections through update step of KF refine the predictions generated by the PI-GRNN.To the best of our knowledge,this study represents a pioneering effort in integrating DL and KF algorithms in this unique symbiotic manner.Through extensive experimentation with real-world traf-fic data,we demonstrate the superior performance of our model compared to the bench-mark approaches.
