Random forest robustness, variable importance, and tree aggregation

Sage, Andrew J.

doi:10.31274/etd-180810-6083

Cited by 14 publications

(13 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Random Forest (RF) is a tree-based ML technique proposed by [122]. Theoretically, RF model is an ensemble of multiple decision trees and uses the majority vote/decision of the trees as the final RF model [123,124]. The algorithm becomes more robust when more decision trees are constructed.…”

Section: Machine Learning (Ml) For Pm 25 Estimationmentioning

confidence: 99%

Evaluation of Machine Learning Models for Estimating PM2.5 Concentrations across Malaysia

et al. 2021

View full text Add to dashboard Cite

Southeast Asia (SEA) is a hotspot region for atmospheric pollution and haze conditions, due to extensive forest, agricultural and peat fires. This study aims to estimate the PM2.5 concentrations across Malaysia using machine-learning (ML) models like Random Forest (RF) and Support Vector Regression (SVR), based on satellite AOD (aerosol optical depth) observations, ground measured air pollutants (NO2, SO2, CO, O3) and meteorological parameters (air temperature, relative humidity, wind speed and direction). The estimated PM2.5 concentrations for a two-year period (2018–2019) are evaluated against measurements performed at 65 air-quality monitoring stations located at urban, industrial, suburban and rural sites. PM2.5 concentrations varied widely between the stations, with higher values (mean of 24.2 ± 21.6 µg m−3) at urban/industrial stations and lower (mean of 21.3 ± 18.4 µg m−3) at suburban/rural sites. Furthermore, pronounced seasonal variability in PM2.5 is recorded across Malaysia, with highest concentrations during the dry season (June–September). Seven models were developed for PM2.5 predictions, i.e., separately for urban/industrial and suburban/rural sites, for the four dominant seasons (dry, wet and two inter-monsoon), and an overall model, which displayed accuracies in the order of R2 = 0.46–0.76. The validation analysis reveals that the RF model (R2 = 0.53–0.76) exhibits slightly better performance than SVR, except for the overall model. This is the first study conducted in Malaysia for PM2.5 estimations at a national scale combining satellite aerosol retrievals with ground-based pollutants, meteorological factors and ML techniques. The satisfactory prediction of PM2.5 concentrations across Malaysia allows a continuous monitoring of the pollution levels at remote areas with absence of measurement networks.

show abstract

Section: Machine Learning (Ml) For Pm 25 Estimationmentioning

confidence: 99%

Evaluation of Machine Learning Models for Estimating PM2.5 Concentrations across Malaysia

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Second, we consider potential cultural differences in the meaning of the studied constructs by establishing equivalence of factor scores through (partial) strong invariance (see ( 21 )). Finally, to determine the efficacy of our independent variables in explaining contact avoidance, hygiene maintenance, and COVID-19 policy support in each country, we applied random forest-based regression algorithms appropriate for complex data sets with possible nonlinear and interactive relationships between variables ( 22 , 23 ).…”

Section: Introductionmentioning

confidence: 99%

Predicting attitudinal and behavioral responses to COVID-19 pandemic using machine learning

Pavlović¹,

Azevedo

et al. 2022

PNAS Nexus

View full text Add to dashboard Cite

At the beginning of 2020, COVID-19 became a global problem. Despite all the efforts to emphasize the relevance of preventive measures, not everyone adhered to them. Thus, learning more about the characteristics determining attitudinal and behavioral responses to the pandemic is crucial to improving future interventions. In this study, we applied machine learning on the multi-national data collected by the International Collaboration on the Social and Moral Psychology of COVID-19 (N = 51,404) to test the predictive efficacy of constructs from social, moral, cognitive, and personality psychology, as well as socio-demographic factors, in the attitudinal and behavioral responses to the pandemic. The results point to several valuable insights. Internalized moral identity provided the most consistent predictive contribution—individuals perceiving moral traits as central to their self-concept reported higher adherence to preventive measures. Similar was found for morality as cooperation, symbolized moral identity, self-control, open-mindedness, collective narcissism, while the inverse relationship was evident for the endorsement of conspiracy theories. However, we also found a non-negligible variability in the explained variance and predictive contributions with respect to macro-level factors such as the pandemic stage or cultural region. Overall, the results underscore the importance of morality-related and contextual factors in understanding adherence to public health recommendations during the pandemic.

show abstract

“…In this study, the random forest regression method was employed to evaluate the importance of each LBSN feature. The calculating procedures were as follows [22]:…”

Section: Feature Selection Using Random Forest Regression Methodsmentioning

confidence: 99%

A Data-Driven Approach to Trip Generation Modeling for Urban Residents and Non-local Travelers

Yang

Ding

et al. 2020

Sustainability

View full text Add to dashboard Cite

Trip generation modeling is essential in transportation planning activities. Previous modeling methods that depend on traditional data collection methods are inefficient and expensive. This paper proposed a novel data-driven trip generation modeling method for urban residents and non-local travelers utilizing location-based social network (LBSN) data and cellular phone data and conducted a case study in Nanjing, China. First, the point of interest (POI) data of the LBSN were classified into various categories by the service type, then, four features of each category including the number of users, number of POIs, number of check-ins, and number of photos were aggregated by traffic analysis zones to be used as explanatory variables for the trip generation models. We used a random tree regression method to select the most important features as the model inputs, and the trip models were established based on the ordinary least square model. Then, an exploratory approach was used to test the performance of each combination of the variables with various test methods to identify the best model for residents’ and travelers’ trip generation functions. The results suggest land use compositions have significant impact on trip generations, and the trip generation patterns are different between urban residents and non-local travelers.

show abstract

Random forest robustness, variable importance, and tree aggregation

Cited by 14 publications

References 17 publications

Evaluation of Machine Learning Models for Estimating PM2.5 Concentrations across Malaysia

Evaluation of Machine Learning Models for Estimating PM2.5 Concentrations across Malaysia

Predicting attitudinal and behavioral responses to COVID-19 pandemic using machine learning

A Data-Driven Approach to Trip Generation Modeling for Urban Residents and Non-local Travelers

Contact Info

Product

Resources

About