Applying an interpretable machine learning framework to study mobility inequity in the recovery phase of COVID-19 pandemic

Li, Zihao; Wei, Zihang; Zhang, Yunlong; Kong, Xiaoqiang; Ma, Chaolun

doi:10.1016/j.tbs.2023.100621

Cited by 5 publications

(2 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These technologies have not only enhanced the accuracy and reliability of simulation models across diverse industries but have also proven effective in addressing numerous complex challenges [16]. They have been successfully applied in various fields such as healthcare [17][18][19], agriculture [20], transportation [21][22][23], clinical studies [24,25], medical imaging [26,27], civil engineering [28], industrial engineering [29,30], etc. The effectiveness of ML/AI methodologies in these domains demonstrates their versatility and offers valuable insights for our IUQ research in the nuclear energy sector.…”

Section: Introductionmentioning

confidence: 99%

Scalable Inverse Uncertainty Quantification by Hierarchical Bayesian Modeling and Variational Inference

Wang,

Wu,

Xie

et al. 2023

Energies

View full text Add to dashboard Cite

Inverse Uncertainty Quantification (IUQ) has gained increasing attention in the field of nuclear engineering, especially nuclear thermal-hydraulics (TH), where it serves as an important tool for quantifying the uncertainties in the physical model parameters (PMPs) while making the model predictions consistent with the experimental data. In this paper, we present an extension to an existing Bayesian inference-based IUQ methodology by employing a hierarchical Bayesian model and variational inference (VI), and apply this novel framework to a real-world nuclear TH scenario. The proposed approach leverages a hierarchical model to encapsulate group-level behaviors inherent to the PMPs, thereby mitigating existing challenges posed by the high variability of PMPs under diverse experimental conditions and the potential overfitting issues due to unknown model discrepancies or outliers. To accommodate computational scalability and efficiency, we utilize VI to enable the framework to be used in applications with a large number of variables or datasets. The efficacy of the proposed method is evaluated against a previous study where a No-U-Turn-Sampler was used in a Bayesian hierarchical model. We illustrate the performance comparisons of the proposed framework through a synthetic data example and an applied case in nuclear TH. Our findings reveal that the presented approach not only delivers accurate and efficient IUQ without the need for manual tuning, but also offers a promising way for scaling to larger, more complex nuclear TH experimental datasets.

show abstract

Section: Introductionmentioning

confidence: 99%

Scalable Inverse Uncertainty Quantification by Hierarchical Bayesian Modeling and Variational Inference

Wang,

Wu,

Xie

et al. 2023

Energies

View full text Add to dashboard Cite

show abstract

“…In addition, in order to visualize the spatial equality of elderly service facilities, scholars often use equality evaluation methods, mainly the Theil index, the Kakwani index, the Lorenz curve, and the Gini coefficient. Among them, the Lorenz curve and the Gini coefficient are some of the most commonly used indicators [37][38][39]. Therefore, we use the Lorenz curve and Gini coefficient to evaluate the spatial equality of elderly service facilities.…”

Section: Introductionmentioning

confidence: 99%

Spatial Equality of Urban Care Facilities from the Perspective of Refinement: An Example from Changchun, China

Zhang,

Chen,

et al. 2023

Land

View full text Add to dashboard Cite

Care facilities are the mainstay of social services for the elderly. As the trend of empty nesting among elderly families intensifies due to the aging population, it is becoming difficult for families to take on the responsibility of caring for the elderly on their own, and the elderly need more formal care to be provided by society. The contradiction between the lag in the construction of care facilities and the growth in the social demand for elderly care has been highlighted, and the spatial equality of care facilities is an important means of achieving an optimal allocation of resources for elderly care. In this paper, we use the two-step floating catchment method to measure the spatial accessibility of care facilities from a fine-grained perspective, using big data, including mobile phone signaling data and points of interest. Then, we use the Gini coefficient to analyze the equality of the spatial allocations of different types of urban care facilities. The results of the study show that, first, the spatial equality of care facilities is good in terms of the Gini coefficient, but the overall spatial accessibility of care facilities is at a relatively low level compared to that in developed cities. This means that the layout of Changchun’s care facilities is good, but there is insufficient service capacity. Second, the spatial accessibility of residential care facilities is characterized by a gradual decline, with high levels in the core and low levels in the periphery. Fewer facilities are located in the peripheral areas of the city, and spatial accessibility is at a lower level, a characteristic different from that seen in cities with a higher level of economic development, such as Beijing. Third, the spatial accessibility of community care facilities showed a polycentric, contiguous distribution. The effect of the study scale on the spatial accessibility of community care facilities was more pronounced, with large scales obscuring the high values of the spatial accessibility of community care facilities in peripheral areas. Fourth, Changchun has better overall equality of care facilities, with differences in the different types and areas of care provided. The spatial balance of care facilities in the core area is better than that observed in other regions. In conclusion, this paper underscores the value of big data, such as mobile phone signaling data, in supporting refined urban research. Furthermore, our comprehensive analysis of social care facility equality can inform policy making and spatial planning.

show abstract

Investigating Relationships Between Phone Use While Driving Behavior and Drivers’ Socio-demographic Characteristics: An Interpretable Machine Learning Approach

Kong,

Zhang,

Zhang

et al. 2024

Data Sci. Transp.

View full text Add to dashboard Cite

Applying an interpretable machine learning framework to study mobility inequity in the recovery phase of COVID-19 pandemic

Cited by 5 publications

References 47 publications

Scalable Inverse Uncertainty Quantification by Hierarchical Bayesian Modeling and Variational Inference

Scalable Inverse Uncertainty Quantification by Hierarchical Bayesian Modeling and Variational Inference

Spatial Equality of Urban Care Facilities from the Perspective of Refinement: An Example from Changchun, China

Investigating Relationships Between Phone Use While Driving Behavior and Drivers’ Socio-demographic Characteristics: An Interpretable Machine Learning Approach

Contact Info

Product

Resources

About