Investigating the relationship between train speed and ground vibrations using random forest machine learning models

In the Netherlands, concerned citizens have proposed reducing train speed as an effective measure to mitigate annoyance caused by railway-induced vibrations. In the present study the relationship between train speed and other influencing parameters (e.g. axle load, wheel roughness), and ground vibrations was investigated using measurements, at different locations, of ground vibrations caused by the passage of regular freight trains and a test train at different speeds. Measurements have been analysed using multivariate regression models and a random decision forest model. The prevailing uncertainties have also been measured using normalized mean deviation between the model predicted value and the actual value. A comparison of results demonstrates that a 'trained and tested' random forest model has certain predictive advantages: i) mean deviation between predicted and actual value is found to be the lowest with random forest model; ii) the random forest model considers all available parameters in the dataset, thus simulating the real situation more closely. However, the model is very location-specific and must therefore be used with caution. In general it is observed that a decrease in train speed results in the reduction of measured vibration levels.

Download Full-text

Recruitment and Retention of Participant and Study Partner Dyads in Two Multinational Alzheimer’s Disease Registration Trials

10.21203/rs.3.rs-100842/v1 ◽

2020 ◽

Author(s):

Olivia M Bernstein ◽

Joshua D. Grill ◽

Daniel L. Gillen

Keyword(s):

Alzheimer’S Disease ◽

Alzheimer's Disease ◽

Random Forest ◽

Random Forest Model ◽

P Value ◽

Confounding Factors ◽

Forest Model ◽

Partner Type ◽

Study Partner ◽

The Relationship

Abstract Background: Early study exit is detrimental to statistical power and increases the risk for bias in Alzheimer’s disease clinical trials. Previous analyses in early phase academic trials demonstrated associations between rates of trial incompletion and participants’ study partner type, with participants enrolling with non-spouse study partners being at greater risk.Methods: We conducted secondary analyses of two multinational phase III trials of semagacestat, an oral gamma secretase inhibitor, for mild-to-moderate AD dementia. Cox’s proportional hazards regression model was used to estimate the relationship between study partner type and the risk of early exit from the trial after adjustment for a priori identified potential confounding factors. Additionally, we used a random forest model to identify top predictors of dropout.Results: Among participants with spousal, adult child, and other study partners, respectively, 35%, 38%, and 36% dropped out or died prior to protocol-defined study completion, respectively. In unadjusted models, the risk of trial incompletion differed by study partner type (unadjusted p-value=0.027 for test of differences by partner type), but in models adjusting for potential confounding factors the differences were not statistically significant (p-value=0.928). In exploratory modeling, participant age was identified as the primary characteristic to explain the relationship between study partner type and the risk of failing to complete the trial. Participant age was also the strongest predictor of trial incompletion in the random forest model.Conclusions: After adjustment for age, no qualitative differences in the risk of incompletion were observed when comparing participants with different study partner types in these trials. Differences between our findings and the findings of previous studies may be explained by differences in trial phase, size, geographic regions, or the composition of academic and non-academic sites.

Download Full-text

Recruitment and retention of participant and study partner dyads in two multinational Alzheimer’s disease registration trials

Alzheimer s Research & Therapy ◽

10.1186/s13195-020-00762-8 ◽

2021 ◽

Vol 13 (1) ◽

Author(s):

Olivia M. Bernstein ◽

Joshua D. Grill ◽

Daniel L. Gillen

Keyword(s):

Alzheimer’S Disease ◽

Alzheimer's Disease ◽

Random Forest ◽

Random Forest Model ◽

Phase Iii ◽

Confounding Factors ◽

Forest Model ◽

Partner Type ◽

Study Partner ◽

The Relationship

Abstract Background Early study exit is detrimental to statistical power and increases the risk for bias in Alzheimer’s disease clinical trials. Previous analyses in early phase academic trials demonstrated associations between rates of trial incompletion and participants’ study partner type, with participants enrolling with non-spouse study partners being at greater risk. Methods We conducted secondary analyses of two multinational phase III trials of semagacestat, an oral gamma secretase inhibitor, for mild-to-moderate AD dementia. Cox’s proportional hazards regression model was used to estimate the relationship between study partner type and the risk of early exit from the trial after adjustment for a priori identified potential confounding factors. Additionally, we used a random forest model to identify top predictors of dropout. Results Among participants with spousal, adult child, and other study partners, respectively, 35%, 38%, and 36% dropped out or died prior to protocol-defined study completion, respectively. In unadjusted models, the risk of trial incompletion differed by study partner type (unadjusted p value = 0.027 for test of differences by partner type), but in models adjusting for potential confounding factors, the differences were not statistically significant (p value = 0.928). In exploratory modeling, participant age was identified as the primary characteristic to explain the relationship between study partner type and the risk of failing to complete the trial. Participant age was also the strongest predictor of trial incompletion in the random forest model. Conclusions After adjustment for age, no differences in the risk of incompletion were observed when comparing participants with different study partner types in these trials. Differences between our findings and the findings of previous studies may be explained by differences in trial phase, size, geographic regions, or the composition of academic and non-academic sites.

Download Full-text

What Makes Underwriting and Non-Underwriting Clients of Brokerage Firms Receive Different Recommendations?

International Journal of Finance & Banking Studies (2147-4486) ◽

10.20525/ijfbs.v5i3.278 ◽

2016 ◽

Vol 5 (3) ◽

pp. 42-56

Author(s):

Shaowen Hua

Keyword(s):

Random Forest ◽

Regression Models ◽

Healthcare Research ◽

Random Forest Model ◽

Forest Model ◽

Prior Literature ◽

Book To Market Ratio ◽

The Difference ◽

Brokerage Firms ◽

To Receive

I explore company characteristics which explain the difference in analysts’ recommendations for companies that were underwritten (affiliated) versus non-underwritten (unaffiliated) by analysts’ brokerage firms. Prior literature documents that analysts issue more optimistic recommendations to underwriting clients of analysts’ brokerage employers. Extant research uses regression models to find general associations between recommendations and financial qualities of companies, with or without underwriting relationship. However, regression models cannot identify the qualities that cause the most difference in recommendations between affiliated versus unaffiliated companies. I adopt uplift random forest model, a popular technique in recent marketing and healthcare research, to identify the type of companies that earn analysts’ favor. I find that companies of stable earnings in the past, higher book-to-market ratio, smaller sizes, worsened earnings, and lower forward PE ratio are likely to receive higher recommendations if they are affiliated with analysts than if they are unaffiliated with analysts. With uplift random forest model, I show that analysts pay more attention on price-related than earnings-related matrices when they value affiliated versus unaffiliated companies. This paper contributes to the literature by introducing an effective predictive model to capital market research and shedding additional light on the usefulness of analysts’ reports.

Download Full-text

Prediction of the Strength of Rubberized Concrete by an Evolved Random Forest Model

Advances in Civil Engineering ◽

10.1155/2019/5198583 ◽

2019 ◽

Vol 2019 ◽

pp. 1-7 ◽

Cited By ~ 11

Author(s):

Yuantian Sun ◽

Guichen Li ◽

Junfei Zhang ◽

Deyu Qian

Keyword(s):

Random Forest ◽

Coarse Aggregate ◽

Construction Material ◽

Random Forest Model ◽

Significant Variable ◽

Rubberized Concrete ◽

Forest Model ◽

Environmental Friendly ◽

Key Variables ◽

The Relationship

Rubberized concrete (RC) has attracted more attention these years as it is an economical and environmental-friendly construction material. Normally, the uniaxial compressive strength (UCS) of RC needs to be evaluated before application. In this study, an evolutionary random forest model (BRF) combining random forest (RF) and beetle antennae search (BAS) algorithms was proposed, which can be used for establishing the relationship between UCS of RC and its key variables. A total number of 138 cases were collected from the literature to develop and validate the BRF model. The results showed that the BAS can tune the RF effectively, and therefore, the hyperparameters of RF were obtained. The proposed BRF model can accurately predict the UCS of RC with a high correlation coefficient (0.96). Furthermore, the variable importance was determined, and the results showed that the age of RC is the most significant variable, followed by water-cement ratio, fine rubber aggregate, coarse rubber aggregate, and coarse aggregate. This study provides a new method to access the strength of RC and can efficiently guide the design of RC in practice.

Download Full-text

Spatial modeling of gully head erosion on the Loess Plateau using a certainty factor and random forest model

The Science of The Total Environment ◽

10.1016/j.scitotenv.2021.147040 ◽

2021 ◽

Vol 783 ◽

pp. 147040

Author(s):

Chengcheng Jiang ◽

Wen Fan ◽

Ningyu Yu ◽

Enlong Liu

Keyword(s):

Random Forest ◽

Loess Plateau ◽

Spatial Modeling ◽

Random Forest Model ◽

Certainty Factor ◽

The Loess Plateau ◽

Forest Model ◽

Gully Head

Download Full-text

Clinical trial registries as Scientometric data: A novel solution for linking and deduplicating clinical trials from multiple registries

Scientometrics ◽

10.1007/s11192-021-04111-w ◽

2021 ◽

Author(s):

Christian Thiele ◽

Gerrit Hirschfeld ◽

Ruth von Brachel

Keyword(s):

Clinical Trials ◽

Random Forest ◽

Random Forest Model ◽

Scientometric Analysis ◽

Data Set ◽

The Public ◽

Forest Model ◽

Clinical Trial Registries ◽

Multiple Primary ◽

Clinical Trials Registry

AbstractRegistries of clinical trials are a potential source for scientometric analysis of medical research and serve important functions for the research community and the public at large. Clinical trials that recruit patients in Germany are usually registered in the German Clinical Trials Register (DRKS) or in international registries such as ClinicalTrials.gov. Furthermore, the International Clinical Trials Registry Platform (ICTRP) aggregates trials from multiple primary registries. We queried the DRKS, ClinicalTrials.gov, and the ICTRP for trials with a recruiting location in Germany. Trials that were registered in multiple registries were linked using the primary and secondary identifiers and a Random Forest model based on various similarity metrics. We identified 35,912 trials that were conducted in Germany. The majority of the trials was registered in multiple databases. 32,106 trials were linked using primary IDs, 26 were linked using a Random Forest model, and 10,537 internal duplicates on ICTRP were identified using the Random Forest model after finding pairs with matching primary or secondary IDs. In cross-validation, the Random Forest increased the F1-score from 96.4% to 97.1% compared to a linkage based solely on secondary IDs on a manually labelled data set. 28% of all trials were registered in the German DRKS. 54% of the trials on ClinicalTrials.gov, 43% of the trials on the DRKS and 56% of the trials on the ICTRP were pre-registered. The ratio of pre-registered studies and the ratio of studies that are registered in the DRKS increased over time.

Download Full-text

Discrimination of the geographic origins and varieties of wine grapes using high-throughput sequencing assisted by a random forest model

LWT ◽

10.1016/j.lwt.2021.111333 ◽

2021 ◽

pp. 111333

Author(s):

Feifei Gao ◽

Guihua Zeng ◽

Bin Wang ◽

Jing Xiao ◽

Liang Zhang ◽

...

Keyword(s):

Random Forest ◽

High Throughput ◽

High Throughput Sequencing ◽

Random Forest Model ◽

Wine Grapes ◽

Forest Model ◽

Geographic Origins

Download Full-text

Multi-Scenario Prediction of Intra-Urban Land Use Change Using a Cellular Automata-Random Forest Model

ISPRS International Journal of Geo-Information ◽

10.3390/ijgi10080503 ◽

2021 ◽

Vol 10 (8) ◽

pp. 503

Author(s):

Hang Liu ◽

Riken Homma ◽

Qiang Liu ◽

Congying Fang

Keyword(s):

Land Use ◽

Random Forest ◽

Cellular Automata ◽

Land Use Change ◽

Urban Land ◽

Urban Land Use ◽

Random Forest Model ◽

Growth Trend ◽

Related Factors ◽

Forest Model

The simulation of future land use can provide decision support for urban planners and decision makers, which is important for sustainable urban development. Using a cellular automata-random forest model, we considered two scenarios to predict intra-land use changes in Kumamoto City from 2018 to 2030: an unconstrained development scenario, and a planning-constrained development scenario that considers disaster-related factors. The random forest was used to calculate the transition probabilities and the importance of driving factors, and cellular automata were used for future land use prediction. The results show that disaster-related factors greatly influence land vacancy, while urban planning factors are more important for medium high-rise residential, commercial, and public facilities. Under the unconstrained development scenario, urban land use tends towards spatially disordered growth in the total amount of steady growth, with the largest increase in low-rise residential areas. Under the planning-constrained development scenario that considers disaster-related factors, the urban land area will continue to grow, albeit slowly and with a compact growth trend. This study provides planners with information on the relevant trends in different scenarios of land use change in Kumamoto City. Furthermore, it provides a reference for Kumamoto City’s future post-disaster recovery and reconstruction planning.

Download Full-text