scholarly journals Development of Predictive Model for Radon-222 Estimation in the Atmosphere using Stepwise Regression and Grid Search Based-Random Forest Regression

2021 ◽  
pp. 132-139
Author(s):  
Omodele Olubi ◽  
Ebeneze Oniya ◽  
Taoreed Owolabi
Keyword(s):  
Random Forest ◽  
Stepwise Regression ◽  
Meteorological Parameters ◽  
Activity Concentration ◽  
Absolute Humidity ◽  
Grid Search ◽  
Random Forest Regression ◽  
Significant Interest ◽  
Polar Research Institute ◽  
Field Measuring

This work develops predictive models for estimating radon (222Rn) activity concentration in the atmosphere using novel grid search based random forest regression (GS-RFR) and stepwise regression (SWR). The developed models employ meteorological parameters which include the temperature, pressure, relative and absolute humidity, wind speed and wind direction as descriptors.  Experimental data of radon concentration and meteorological parameters from two observatories of the Korea Polar Research Institute in Antarctica (King Sejong and Jang Bogo) have been employed in this work.  The performance of the developed models was assessed using three different performance measuring parameters. On the basis of root mean square error (RMSE), the GS-RFR shows better performance over the SWR. An improvement of 64.09 % and 15.19 % was obtained on the training and test datasets, respectively at King Sejong station. At the Jang Bogo station, an improvement of 75.04 % and 28.04 % was obtained on the training and test datasets, respectively. The precision and robustness of the developed models would be of significant interest in determining the concentration of radon (222Rn) activity concentration in the atmosphere for various physical applications especially in regions where field measuring equipment for radon is not available or measurements have been interrupted.

scholarly journals Evaluation of Evaporation from Water Reservoirs in Local Conditions at Czech Republic

Hydrology ◽  
2021 ◽  
Vol 8 (4) ◽  
pp. 153
Author(s):  
Eva Melišová ◽  
Adam Vizina ◽  
Martin Hanel ◽  
Petr Pavlík ◽  
Petra Šuhájková
Keyword(s):  
Czech Republic ◽  
Random Forest ◽  
Linear Regression ◽  
Statistical Methods ◽  
Stepwise Regression ◽  
The Other ◽  
Water Reservoirs ◽  
Random Forest Regression ◽  
Local Conditions ◽  
The Difference

Evaporation is an important factor in the overall hydrological balance. It is usually derived as the difference between runoff, precipitation and the change in water storage in a catchment. The magnitude of actual evaporation is determined by the quantity of available water and heavily influenced by climatic and meteorological factors. Currently, there are statistical methods such as linear regression, random forest regression or machine learning methods to calculate evaporation. However, in order to derive these relationships, it is necessary to have observations of evaporation from evaporation stations. In the present study, the statistical methods of linear regression and random forest regression were used to calculate evaporation, with part of the models being designed manually and the other part using stepwise regression. Observed data from 24 evaporation stations and ERA5-Land climate reanalysis data were used to create the regression models. The proposed regression formulas were tested on 33 water reservoirs. The results show that manual regression is a more appropriate method for calculating evaporation than stepwise regression, with the caveat that it is more time consuming. The difference between linear and random forest regression is the variance of the data; random forest regression is better able to fit the observed data. On the other hand, the interpretation of the result for linear regression is simpler. The study introduced that the use of reanalyzed data, ERA5-Land products using the random forest regression method is suitable for the calculation of evaporation from water reservoirs in the conditions of the Czech Republic.

Evaluating Disease Severity in Chronic Pain Patients with and without Fibromyalgia: A Comparison of the Symptom Impact Questionnaire and the Polysymptomatic Distress Scale

2015 ◽  
Vol 42 (12) ◽  
pp. 2404-2411 ◽  
Author(s):  
Ronald Friend ◽  
Robert M. Bennett
Keyword(s):  
Chronic Pain ◽  
Random Forest ◽  
Disease Severity ◽  
Stepwise Regression ◽  
Short Form ◽  
Unique Contribution ◽  
Clinical Practices ◽  
Random Forest Regression ◽  
Sf 36 ◽  
Distress Scale

Objective.To compare the relative effectiveness of the Polysymptomatic Distress Scale (PSD) with the Symptom Impact Questionnaire (SIQR), the disease-neutral revision of the updated Fibromyalgia Impact Questionnaire (FIQR), in their ability to assess disease activity in patients with rheumatic disorders both with and without fibromyalgia (FM).Methods.The study included 321 patients from 8 clinical practices with some 16 different chronic pain disorders. Disease severity was assessed by the Medical Outcomes Study Short Form-36 (SF-36). Univariate analyses were used to assess the magnitude of PSD and SIQR correlations with SF-36 subscales. Hierarchical stepwise regression was used to evaluate the unique contribution of the PSD and SIQR to the SF-36. Random forest regression probed the relative importance of the SIQR and PSD components as predictors of SF-36.Results.The correlations with the SF-36 subscales were significantly higher for the SIQR (0.48 to 0.78) than the PSD (0.29 to 0.56; p < 0.001). Stepwise regression revealed that the SIQR was contributing additional unique variance on SF-36 subscales, which was not the case for the PSD. Random forest regression showed SIQR Function, Symptoms, and Global Impact subscales were more important predictors of SF-36 than the PSD. The single SIQR pain item contributed 55% of SF-36 pain variance compared to 23% with the 19-point WPI (the Widespread Pain Index component of PSD).Conclusion.The SIQR, the disease-neutral revision of the updated FIQ, has several important advantages over the PSD in the evaluation of disease severity in chronic pain disorders.

scholarly journals Influence of Meteorological Parameters on the Variations of Atmospheric Radionuclides Concentration in Dar es Salaam, Tanzania

2020 ◽  
pp. 1-18
Author(s):  
Dorice Rashid Seif ◽  
Yusuf Ismail Koleleni
Keyword(s):  
Regression Analysis ◽  
Meteorological Parameters ◽  
Activity Concentration ◽  
Absolute Humidity ◽  
Dar Es Salaam ◽  
The Other ◽  
Atmospheric Conditions ◽  
Activity Concentrations ◽  
The Mean ◽  
Atmospheric Concentrations

Atmospheric concentrations of 7Be and 212Pb were measured for 11 years (2008 – 2018) in Dar es Salaam, Tanzania. The mean activity concentrations of 7Be and 212Pb were found to be within the range of 1.29 – 5.71 mBq/m3 and 10.85 – 50.06 mBq/m3, respectively. The annual mean activity concentrations of 7Be and 212Pb were 4.72 ± 1.18 mBq/m3 and 29.76 ± 13.63 mBq/m3, respectively. Distinct annual trends were depicted on 7Be and 212Pb, suggesting that the two radionuclides were affected differently with atmospheric conditions. Monthly atmospheric concentrations of 7Be showed a strong seasonal variation trend with the highest in January and February and lowest in April. 212Pb depicted the highest concentration during June and July and lowest in January and December. The regression analysis for 7Be and 212Pb activity concentrations together with number of meteorological parameters revealed that the relative humidity, rainfall, air temperature, absolute humidity and wind speed are the most significant parameters affecting radionuclides activity concentrations in the atmosphere. The sunspot numbers show 66.7% of its variability with 7Be activity concentration which further suggesting that other parameters may influence its variation. 212Pb, on the other hand, shows only 27.3% of its variability which clearly indicates that the existence of cosmic rays does not affect its activity concentration in the atmosphere.

scholarly journals Optimized Hyperparameter Tuned Random Forest Regressor Algorithm in Predicting Resale Car Value based on Grid Search Method

2021 ◽  
pp. 106-113
Author(s):  
Aruna M ◽  
M Anjana ◽  
Harshita Chauhan ◽  
Deepa R
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Decision Trees ◽  
Search Method ◽  
Grid Search ◽  
Random Forest Regression ◽  
Prediction Rate ◽  
Grid Search Method ◽  
Randomized Search ◽  
The Cost

The price of a car depreciates right from the time it is bought. The resale value of cars is influenced by many factors and influences both buyers and sellers, making it a prominent problem in the machine learning field. Diverse methodologies in machine learning can help us use all the varied factors and process a large amount of data to predict the cost. For our dataset, the Random Forest Regression algorithm shows a significant increase in the prediction rate. In order to optimise the Random Forest Regressor model, best hyperparameters can be found using hyperparameter tuning strategies. On comparing Grid Search and Randomized Search, a better prediction rate is accounted for using the former. These parameters are then passed to the algorithm as hyperparameter tuning can help collect the best batch of decision trees in the random forest for the most optimised prediction rate.

scholarly journals A novel framework for designing a multi-DoF prosthetic wrist control using machine learning

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Chinmay P. Swami ◽  
Nicholas Lenhard ◽  
Jiyeon Kang
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Upper Limb ◽  
Daily Living ◽  
Machine Learning Algorithms ◽  
Data Sets ◽  
Random Forest Regression ◽  
Prosthetic Devices ◽  
Upper Limb Function ◽  
The Neural Network

AbstractProsthetic arms can significantly increase the upper limb function of individuals with upper limb loss, however despite the development of various multi-DoF prosthetic arms the rate of prosthesis abandonment is still high. One of the major challenges is to design a multi-DoF controller that has high precision, robustness, and intuitiveness for daily use. The present study demonstrates a novel framework for developing a controller leveraging machine learning algorithms and movement synergies to implement natural control of a 2-DoF prosthetic wrist for activities of daily living (ADL). The data was collected during ADL tasks of ten individuals with a wrist brace emulating the absence of wrist function. Using this data, the neural network classifies the movement and then random forest regression computes the desired velocity of the prosthetic wrist. The models were trained/tested with ADLs where their robustness was tested using cross-validation and holdout data sets. The proposed framework demonstrated high accuracy (F-1 score of 99% for the classifier and Pearson’s correlation of 0.98 for the regression). Additionally, the interpretable nature of random forest regression was used to verify the targeted movement synergies. The present work provides a novel and effective framework to develop an intuitive control for multi-DoF prosthetic devices.

Real-Time Moisture Ratio Study of Drying Date Fruit Chips Based on On-Line Image Attributes Using kNN and Random Forest Regression Methods

Measurement ◽  
2020 ◽  
pp. 108899
Author(s):  
Madi Keramat-Jahromi ◽  
Seyed Saeid Mohtasebi ◽  
Hossein Mousazadeh ◽  
Mahdi Ghasemi-Varnamkhasri ◽  
Maryam Rahimi-Movassagh
Keyword(s):  
Random Forest ◽  
Real Time ◽  
Moisture Ratio ◽  
Random Forest Regression ◽  
Regression Methods ◽  
Line Image ◽  
Date Fruit ◽  
On Line

scholarly journals Application of random forest regression to the calculation of gas-phase chemistry within the GEOS-Chem chemistry model v10

2019 ◽  
Vol 12 (3) ◽  
pp. 1209-1225 ◽  
Author(s):  
Christoph A. Keller ◽  
Mat J. Evans
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Gas Phase ◽  
Atmospheric Chemistry ◽  
Random Forest Regression ◽  
Data Set ◽  
Gas Phase Chemistry ◽  
Chemical Conditions ◽  
Phase Chemistry ◽  
The Impact

Abstract. Atmospheric chemistry models are a central tool to study the impact of chemical constituents on the environment, vegetation and human health. These models are numerically intense, and previous attempts to reduce the numerical cost of chemistry solvers have not delivered transformative change. We show here the potential of a machine learning (in this case random forest regression) replacement for the gas-phase chemistry in atmospheric chemistry transport models. Our training data consist of 1 month (July 2013) of output of chemical conditions together with the model physical state, produced from the GEOS-Chem chemistry model v10. From this data set we train random forest regression models to predict the concentration of each transported species after the integrator, based on the physical and chemical conditions before the integrator. The choice of prediction type has a strong impact on the skill of the regression model. We find best results from predicting the change in concentration for long-lived species and the absolute concentration for short-lived species. We also find improvements from a simple implementation of chemical families (NOx = NO + NO2). We then implement the trained random forest predictors back into GEOS-Chem to replace the numerical integrator. The machine-learning-driven GEOS-Chem model compares well to the standard simulation. For ozone (O3), errors from using the random forests (compared to the reference simulation) grow slowly and after 5 days the normalized mean bias (NMB), root mean square error (RMSE) and R2 are 4.2 %, 35 % and 0.9, respectively; after 30 days the errors increase to 13 %, 67 % and 0.75, respectively. The biases become largest in remote areas such as the tropical Pacific where errors in the chemistry can accumulate with little balancing influence from emissions or deposition. Over polluted regions the model error is less than 10 % and has significant fidelity in following the time series of the full model. Modelled NOx shows similar features, with the most significant errors occurring in remote locations far from recent emissions. For other species such as inorganic bromine species and short-lived nitrogen species, errors become large, with NMB, RMSE and R2 reaching >2100 % >400 % and <0.1, respectively. This proof-of-concept implementation takes 1.8 times more time than the direct integration of the differential equations, but optimization and software engineering should allow substantial increases in speed. We discuss potential improvements in the implementation, some of its advantages from both a software and hardware perspective, its limitations, and its applicability to operational air quality activities.

Sign in / Sign up

Export Citation Format

Share Document