Towards a framework for multiple artificial neural network topologies validation by means of statistics

This study reviews performance criteria adequate to validate simulation models through the comparison of two quantitative data sets, concerning historical and simulated data. The criteria reviewed were organized according to its characteristics into the groups: error‐based measures, information theory measures, information criteria, parametric tests, non‐parametric tests, distance‐based measures and combined measures. Each criterion is reviewed through its mathematic definition, its applications in literature and the identification of its advantages and drawbacks. The features assessed by each criterion are identified and discussed. This study provides a concise outline over the criteria reviewed, which can be used as a guide to help developers of simulation models into the decision on the most appropriate criteria to validate their models.

show abstract

“…An insightful application of AIC to assess the quality of machine learning classifiers is provided by Gonzalez Carrasco et al . ().…”

Section: Performance Criteria Overviewmentioning

confidence: 97%

“…The application of t ‐test to validate simulation models is suggested by Kleijnen (), and an example of its application concerning the assessment of outputs from artificial neural networks can be found in the study of Gonzalez Carrasco et al . ().

t_{N - 1} = \frac{\overset{Y}{true} - μ_{y}}{s_{y} true/ \sqrt{N}}

s_{y}^{2} = true {true\sum}_{i = 1}^{N} \frac{{((), y_{i} - \overset{Y}{true})}^{2}}{N - 1}

…”

Section: Performance Criteria Overviewmentioning

confidence: 97%

A review of performance criteria to validate simulation models

Hora

Campos

2015

Expert Systems

View full text Add to dashboard Cite

show abstract

“…The center lines within each box show the location of the sample medians. The whiskers extend from the box to the minimum and maximum values in each sample, except for any outside or far outside points, which will be plotted separately (Gonzalez-Carrasco et al, 2014;Molnar, 2019). The detection of these outliers is crucial for understanding possible causes and implications of their presence (Cousineau and Chartier, 2010;Leys et al, 2013).…”

Section: Pre-processing: Dataset Analysismentioning

confidence: 99%

Framework for the Classification of Emotions in People With Visual Disabilities Through Brain Signals

López-Hernández

González‐Carrasco

López-Cuadrado

et al. 2021

Front. Neuroinform.

View full text Add to dashboard Cite

Nowadays, the recognition of emotions in people with sensory disabilities still represents a challenge due to the difficulty of generalizing and modeling the set of brain signals. In recent years, the technology that has been used to study a person’s behavior and emotions based on brain signals is the brain–computer interface (BCI). Although previous works have already proposed the classification of emotions in people with sensory disabilities using machine learning techniques, a model of recognition of emotions in people with visual disabilities has not yet been evaluated. Consequently, in this work, the authors present a twofold framework focused on people with visual disabilities. Firstly, auditory stimuli have been used, and a component of acquisition and extraction of brain signals has been defined. Secondly, analysis techniques for the modeling of emotions have been developed, and machine learning models for the classification of emotions have been defined. Based on the results, the algorithm with the best performance in the validation is random forest (RF), with an accuracy of 85 and 88% in the classification for negative and positive emotions, respectively. According to the results, the framework is able to classify positive and negative emotions, but the experimentation performed also shows that the framework performance depends on the number of features in the dataset and the quality of the Electroencephalogram (EEG) signals is a determining factor.

show abstract

“…Hence, in this section, and following the ideas exposed in [74], a statistical validation has been performed for the determination of which is the better choice among comparable models (with similar results). To facilitate this task, different analyses have been included to evaluate and compare the generalization ability of neural models designed from the statistical point of view.…”

Section: Statistical Validationmentioning

confidence: 99%

Automatic Learning Framework for Pharmaceutical Record Matching

et al. 2020

Self Cite

View full text Add to dashboard Cite

Pharmaceutical manufacturers need to analyse a vast number of products in their daily activities. Many times, the same product can be registered several times by different systems using different attributes, and these companies require accurate and quality information regarding their products since these products are drugs. The central hypothesis of this research work is that machine learning can be applied to this domain to efficiently merge different data sources and match the records related to the same product. No human is able to do this in a reasonable way because the number of records to be matched is extremely high. This paper presents a framework for pharmaceutical record matching based on machine learning techniques in a big data environment. The proposed framework aims to explode the well-known rules for the matching of records from different databases for training machine learning models. Then the trained models are evaluated by predicting matches with records that do not follow these known rules. Finally, the production environment is simulated by generating a huge amount of combinations of records and predicting the matches. The obtained results show that, despite the good results obtained with the training datasets, in the production environment, the average accuracy of the best model is around 85%. That shows that matches which do not follow the known rules can be predicted and, considering that there is not a human way to process this amount of data, the results are promising.

show abstract

Towards a framework for multiple artificial neural network topologies validation by means of statistics

Cited by 8 publications

References 64 publications

A review of performance criteria to validate simulation models

A review of performance criteria to validate simulation models

Framework for the Classification of Emotions in People With Visual Disabilities Through Brain Signals

Automatic Learning Framework for Pharmaceutical Record Matching

Contact Info

Product

Resources

About