2021
DOI: 10.3390/app11052314
|View full text |Cite
|
Sign up to set email alerts
|

Study on Accuracy Metrics for Evaluating the Predictions of Damage Locations in Deep Piles Using Artificial Neural Networks with Acoustic Emission Data

Abstract: Accuracy metrics have been widely used for the evaluation of predictions in machine learning. However, the selection of an appropriate accuracy metric for the evaluation of a specific prediction has not yet been specified. In this study, seven of the most used accuracy metrics in machine learning were summarized, and both their advantages and disadvantages were studied. To achieve this, the acoustic emission data of damage locations were collected from a pile hit test. A backpropagation artificial neural netwo… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

1
58
0
3

Year Published

2021
2021
2024
2024

Publication Types

Select...
5
4

Relationship

0
9

Authors

Journals

citations
Cited by 118 publications
(62 citation statements)
references
References 43 publications
1
58
0
3
Order By: Relevance
“…The purpose of this training is to optimized the output by minimizing the error between actual and predicted output. After every iteration k , the predicted outputs are compared with the actual outputs by computing the error according to Mean Absolute Percentage Error ( MAPE ) method as shown below [ 31 ]: …”
Section: Methodsmentioning
confidence: 99%
“…The purpose of this training is to optimized the output by minimizing the error between actual and predicted output. After every iteration k , the predicted outputs are compared with the actual outputs by computing the error according to Mean Absolute Percentage Error ( MAPE ) method as shown below [ 31 ]: …”
Section: Methodsmentioning
confidence: 99%
“…The performances of ANN and MLR models in predicting Saybolt color were determined through mean absolute error (MAE), root mean square error (RMSE), and coefficient of determination (R 2 ) as defined ( 9 )–( 11 ), respectively, as follows [ 40 , 41 ]: where and are actual and predicted data, and is the average value of . MAE represents the average of total model error and assesses how close the prediction is to the actual values.…”
Section: Materials and Methodsmentioning
confidence: 99%
“…After each iteration, the model calculates the cost function and accordingly adjusts the weights to minimize the error. In our model, we have used mean squared error (MSE), which is the default cost function for regression models, and calculated the average mean of squared differences between actual and predicted values [ 70 ]. The MSE ranges between 0 and infinity.…”
Section: Methodsmentioning
confidence: 99%
“…For a given model, the value of evaluation metrics determines how accurately the model is performing. The model performance is evaluated using percentage-dependent metric, mean absolute percentage error (MAPE) that measures the prediction accuracies, mainly in trend estimation [ 70 ]. The MAPE is calculated as follows: …”
Section: Methodsmentioning
confidence: 99%