• No results found

Comparison of artificial neural network, random forest and random perceptron forest for forecasting the spatial impurity distribution

N/A
N/A
Protected

Academic year: 2021

Share "Comparison of artificial neural network, random forest and random perceptron forest for forecasting the spatial impurity distribution"

Copied!
8
0
0

Loading.... (view fulltext now)

Full text

Loading

Figure

FIGURE 1. Sampling place: Tarko-Sale, Yamalo-Nenets Autonomous Okrug, Russia
TABLE 1. Descriptive statistics of modeled elements.
FIGURE 2. Root mean square error (RMSE) of a neural network (MPL)
FIGURE 3. Dependence of the RMSE index on the number of trees for the RF and RMLPF models for predicting chromium  concentration

References

Related documents

Since the transformed BD/TD variable has a weak, negative and no significant relationship with RATE, whereas the SDB/TD exhibits a positive relationship with it, these two

However, combining the saturated area and rain water contributions gives a runoff volume with similar timing and magnitude to the event water estimated with the two-component

The backward design approach encourages us to think about a unit or course in terms of the collected assessment evidence needed to document and validate that the desired learning

learning techniques (random forest, artificial neural network, and logistic regression) to predict surgical intervention for POAG (primary open-angle glaucoma) based

The term "OMIT Data" as used in this contract is defined as all technical data (including computer software documentation), development tools, graphics, and computer

This paper presents two case studies, EI Sherana airstrip (ESA) cover, Northern Territory, Australia and Whistle Mine Backfilled Open Pit Cover System, Ontario, Canada, focusing

- Any item in which the provider scores a 0, 1, and 2 will automatically be displayed on the plan along with a linking video or document to be used as a resource that the mentor