Sensitivity analysis of the artificial neural networks in a system for durability prediction of forging tools to forgings made of C45 steel

Mrzygłód, B.; Hawryluk, Marek; Janik, Marta; Olejarczyk-Wożeńska, I.

doi:10.1007/s00170-020-05641-y

Cited by 26 publications

(13 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Typical model sensitivity evaluations include ‘one-at-a-time’ simulations that individually evaluate the impact of each independent variable while overlooking the interactions with other independent variables [ 58 ]. In ANN, sensitivity analysis enables the evaluation of input variables in terms of the significance of their impact on the output variable and the identification of factors that could be omitted without compromising network quality and the critical key factors [ 59 ]. The mean importance of ANN sensitivity analysis ( Table 9 ) in this study dataset indicated that PT was the most important variable, followed by LC and HM.…”

Section: Methodsmentioning

confidence: 99%

Predicting the intention to adopt wearable payment devices in China: The use of hybrid SEM-Neural network approach

Mamun

Hayat

et al. 2022

PLoS ONE

View full text Add to dashboard Cite

Wearable payment devices (WPD) are gaining acceptance fast and transforming everyday life and commercial operations in China. Limited research works were conducted on customers’ adoption intentions to obtain a real image of the evolution of WPD in China. This study aims to investigate the effects of Performance Expectancy (PE), Effort Expectancy (EE), Social Influence (SI), Facilitating Conditions (FC), Hedonic Motivation (HM), Perceived Trust (PT), and Lifestyle Compatibility (LC) on the intention to adopt WPD among Chinese consumers by expanding unified theory of acceptance and use of technology with two impelling determinants (i.e. PT and LC). Using an online survey, empirical data were collected from 298 respondents in China. In a two-stage data analysis, partial least squares structural equation modelling (PLS-SEM) were employed to analyse the causal effects and associations between independent and dependent variables, whereas artificial neural networks (ANN) were used to evaluate the research model prediction capability. The (PLS-SEM) findings indicated that PE, SI, FC, HM, LC, and PT had substantial positive impacts on adoption intention, whilst EE had no impact on adoption intention among Chinese consumers. The ANN analysis proved the high prediction accuracy of data fitness, with ANN findings highlighting the importance of PT, FC, and PE on the intention to adopt WPD. It was suggested that the study findings assist WPD service providers and the smart wearable device industry practitioners in developing innovative products and implementing efficient marketing strategies to attract the existing and potential WPD users in China.

show abstract

Section: Methodsmentioning

confidence: 99%

Predicting the intention to adopt wearable payment devices in China: The use of hybrid SEM-Neural network approach

Mamun

Hayat

et al. 2022

PLoS ONE

View full text Add to dashboard Cite

show abstract

“…Sensitivity analysis is used to establish the contribution of each predictor variable in an artificial neural network [43]. There are techniques to perform sensitivity analysis in artificial neural networks, such as Garson's algorithm, partial derivatives, input perturbation, forward stepwise addition, backward stepwise elimination [44] and the quotient W [45]. The chosen sensitivity analysis was the connection weights algorithm [43] as it demonstrates the highest Gower's coefficient of similarity in 500 Monte Carlo simulations [44] and denotes the similarity between the true ranked importance and estimated ranked importance of the variables in the artificial neural network [46].…”

Section: Artificial Neural Network Statistical Analysismentioning

confidence: 99%

Viskositas: Viscosity Prediction of Multicomponent Chemical Systems

dos¹

2022

Preprint

View full text Add to dashboard Cite

Viscosity in the metallurgical and glass industry plays a fundamental role in its production processes, also in the area of geophysics. As its experimental measurement is financially expensive, also in terms of time, several mathematical models were built to provide viscosity results as a function of several variables, such as chemical composition and temperature, in linear and nonlinear models. A database was built in order to produce a nonlinear model by artificial neural networks by variation of hyperparameters to provide reliable predictions of viscosity in relation to chemical systems and temperatures. The model produced named Viskositas demonstrated better statistical evaluations of mean absolute error, standard deviation and coefficient of determination (R 2 ) in relation to the test database when compared to different models from literature and 1 commercial model, offering predictions with lower errors, less variability and less generation of outliers.

show abstract

“…A sensitivity analysis was performed to detect the effect of risk factors on the output by assessing their sensitivity to the output. Mrzygłód et al [40] stated that sensitivity analyses can be applied to identify the effects of the input factors of an ANN model on its output factor. The effects of the risk factors on the output was assessed in this study by improving the factors by 10%, 20%, 30%, and 40%.…”

Section: Sensitivity Analysismentioning

confidence: 99%

Construction Schedule Risk Assessment and Management Strategy for Foreign General Contractors Working in the Ethiopian Construction Industry

Cheng

Darsa

2021

Sustainability

View full text Add to dashboard Cite

Construction project schedule delay is a worldwide concern and especially severe in the Ethiopian construction industry. This study developed a Construction Schedule Risk Assessment Model (CSRAM) and a management strategy for foreign general contractors (FGCs). 94 construction projects with schedule delay were collected and a questionnaire survey of 75 domain experts was conducted to systematically select 22 risk factors. In CSRAM, the artificial neural network (ANN) inference model was developed to predict the project schedule delay. Integrating it with the Garson algorithm (GA), the relative weights of risk factors with rankings were calculated and identified. For comparison, the Relative Importance Index (RII) method was also applied to rank the risk factors. Management strategies were developed to improve the three highest-ranked factors identified using the GA (change order, corruption/bribery, and delay in payment), and the RII (poor resource management, corruption/bribery, and delay in material delivery). Moreover, the improvement results were used as inputs for the trained ANN to conduct a sensitivity analysis. The findings of this study indicate that improvements in the factors that considerably affect the construction schedule can significantly reduce construction schedule delays. This study acts as an important reference for FGCs who plan to enter or work in the Ethiopian construction industry.

show abstract

Sensitivity analysis of the artificial neural networks in a system for durability prediction of forging tools to forgings made of C45 steel

Cited by 26 publications

References 29 publications

Predicting the intention to adopt wearable payment devices in China: The use of hybrid SEM-Neural network approach

Predicting the intention to adopt wearable payment devices in China: The use of hybrid SEM-Neural network approach

Viskositas: Viscosity Prediction of Multicomponent Chemical Systems

Construction Schedule Risk Assessment and Management Strategy for Foreign General Contractors Working in the Ethiopian Construction Industry

Contact Info

Product

Resources

About