Convolutional Neural Networks for Structured Industrial Data

Luis Moles; Fernando Boto; Goretti Echegaray; Iván G. Torre

doi:10.1007/978-3-031-18050-7_35

Convolutional Neural Networks for Structured Industrial Data

Luis Moles
, Fernando Boto^*
, Goretti Echegaray
, Iván G. Torre

^*Corresponding author for this work

VICOMTech

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

2 Citations (Scopus)

Abstract

Regression methods aim to predict a numerical value of a target variable given some input variables by building a function f: Rⁿ→ R. In Industry 4.0 regression tasks, tabular data-sets are especially frequent. Decision Trees, ensemble methods such as Gradient Boosting and Random Forest, or Support Vector Machines are widely used for regression tasks with tabular data. However, Deep Learning approaches are rarely used with this type of data, due to, among others, the lack of spatial correlation between features. Therefore, in this research, we propose two Deep Learning approaches for working with tabular data. Specifically, two Convolutional Neural Networks architectures are tested against different state of the art regression methods. We perform an hyper-parameter tuning of all the techniques and compare the model performance in different industrial tabular data-sets. Experimental results show that both Convolutional Neural Network approaches can outperform the commonly used methods for regression tasks.

Original language	English
Title of host publication	17th International Conference on Soft Computing Models in Industrial and Environmental Applications, SOCO 2022, Proceedings
Editors	Pablo García Bringas, Hilde Pérez García, Francisco Javier Martinez-de-Pison, José Ramón Villar Flecha, Alicia Troncoso Lora, Enrique A. de la Cal, Alvaro Herrero, Francisco Martínez Álvarez, Giuseppe Psaila, Héctor Quintián, Emilio S. Corchado Rodriguez
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	361-370
Number of pages	10
ISBN (Print)	9783031180491
DOIs	https://doi.org/10.1007/978-3-031-18050-7_35
Publication status	Published - 2023
Event	17th International Conference on Soft Computing Models in Industrial and Environmental Applications, SOCO 2022 - Salamanca, Spain Duration: 5 Sept 2022 → 7 Sept 2022

Publication series

Name	Lecture Notes in Networks and Systems
Volume	531 LNNS
ISSN (Print)	2367-3370
ISSN (Electronic)	2367-3389

Conference

Conference	17th International Conference on Soft Computing Models in Industrial and Environmental Applications, SOCO 2022
Country/Territory	Spain
City	Salamanca
Period	5/09/22 → 7/09/22

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 9 Industry, Innovation, and Infrastructure

Access to Document

10.1007/978-3-031-18050-7_35

Cite this

Moles, L., Boto, F., Echegaray, G., & Torre, I. G. (2023). Convolutional Neural Networks for Structured Industrial Data. In P. García Bringas, H. Pérez García, F. J. Martinez-de-Pison, J. R. Villar Flecha, A. Troncoso Lora, E. A. de la Cal, A. Herrero, F. Martínez Álvarez, G. Psaila, H. Quintián, & E. S. Corchado Rodriguez (Eds.), 17th International Conference on Soft Computing Models in Industrial and Environmental Applications, SOCO 2022, Proceedings (pp. 361-370). (Lecture Notes in Networks and Systems; Vol. 531 LNNS). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-031-18050-7_35

Moles, Luis ; Boto, Fernando ; Echegaray, Goretti et al. / Convolutional Neural Networks for Structured Industrial Data. 17th International Conference on Soft Computing Models in Industrial and Environmental Applications, SOCO 2022, Proceedings. editor / Pablo García Bringas ; Hilde Pérez García ; Francisco Javier Martinez-de-Pison ; José Ramón Villar Flecha ; Alicia Troncoso Lora ; Enrique A. de la Cal ; Alvaro Herrero ; Francisco Martínez Álvarez ; Giuseppe Psaila ; Héctor Quintián ; Emilio S. Corchado Rodriguez. Springer Science and Business Media Deutschland GmbH, 2023. pp. 361-370 (Lecture Notes in Networks and Systems).

@inproceedings{05043ed7d522476d87b5744f17b3558b,

title = "Convolutional Neural Networks for Structured Industrial Data",

abstract = "Regression methods aim to predict a numerical value of a target variable given some input variables by building a function f: Rn→ R. In Industry 4.0 regression tasks, tabular data-sets are especially frequent. Decision Trees, ensemble methods such as Gradient Boosting and Random Forest, or Support Vector Machines are widely used for regression tasks with tabular data. However, Deep Learning approaches are rarely used with this type of data, due to, among others, the lack of spatial correlation between features. Therefore, in this research, we propose two Deep Learning approaches for working with tabular data. Specifically, two Convolutional Neural Networks architectures are tested against different state of the art regression methods. We perform an hyper-parameter tuning of all the techniques and compare the model performance in different industrial tabular data-sets. Experimental results show that both Convolutional Neural Network approaches can outperform the commonly used methods for regression tasks.",

author = "Luis Moles and Fernando Boto and Goretti Echegaray and Torre, \{Iv{\'a}n G.\}",

note = "Publisher Copyright: {\textcopyright} 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.; 17th International Conference on Soft Computing Models in Industrial and Environmental Applications, SOCO 2022 ; Conference date: 05-09-2022 Through 07-09-2022",

year = "2023",

doi = "10.1007/978-3-031-18050-7\_35",

language = "English",

isbn = "9783031180491",

series = "Lecture Notes in Networks and Systems",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "361--370",

editor = "\{Garc{\'i}a Bringas\}, Pablo and \{P{\'e}rez Garc{\'i}a\}, Hilde and Martinez-de-Pison, \{Francisco Javier\} and \{Villar Flecha\}, \{Jos{\'e} Ram{\'o}n\} and \{Troncoso Lora\}, Alicia and \{de la Cal\}, \{Enrique A.\} and Alvaro Herrero and \{Mart{\'i}nez {\'A}lvarez\}, Francisco and Giuseppe Psaila and H{\'e}ctor Quinti{\'a}n and \{Corchado Rodriguez\}, \{Emilio S.\}",

booktitle = "17th International Conference on Soft Computing Models in Industrial and Environmental Applications, SOCO 2022, Proceedings",

address = "Germany",

}

Moles, L, Boto, F, Echegaray, G & Torre, IG 2023, Convolutional Neural Networks for Structured Industrial Data. in P García Bringas, H Pérez García, FJ Martinez-de-Pison, JR Villar Flecha, A Troncoso Lora, EA de la Cal, A Herrero, F Martínez Álvarez, G Psaila, H Quintián & ES Corchado Rodriguez (eds), 17th International Conference on Soft Computing Models in Industrial and Environmental Applications, SOCO 2022, Proceedings. Lecture Notes in Networks and Systems, vol. 531 LNNS, Springer Science and Business Media Deutschland GmbH, pp. 361-370, 17th International Conference on Soft Computing Models in Industrial and Environmental Applications, SOCO 2022, Salamanca, Spain, 5/09/22. https://doi.org/10.1007/978-3-031-18050-7_35

Convolutional Neural Networks for Structured Industrial Data. / Moles, Luis; Boto, Fernando; Echegaray, Goretti et al.
17th International Conference on Soft Computing Models in Industrial and Environmental Applications, SOCO 2022, Proceedings. ed. / Pablo García Bringas; Hilde Pérez García; Francisco Javier Martinez-de-Pison; José Ramón Villar Flecha; Alicia Troncoso Lora; Enrique A. de la Cal; Alvaro Herrero; Francisco Martínez Álvarez; Giuseppe Psaila; Héctor Quintián; Emilio S. Corchado Rodriguez. Springer Science and Business Media Deutschland GmbH, 2023. p. 361-370 (Lecture Notes in Networks and Systems; Vol. 531 LNNS).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Convolutional Neural Networks for Structured Industrial Data

AU - Moles, Luis

AU - Boto, Fernando

AU - Echegaray, Goretti

AU - Torre, Iván G.

PY - 2023

Y1 - 2023

N2 - Regression methods aim to predict a numerical value of a target variable given some input variables by building a function f: Rn→ R. In Industry 4.0 regression tasks, tabular data-sets are especially frequent. Decision Trees, ensemble methods such as Gradient Boosting and Random Forest, or Support Vector Machines are widely used for regression tasks with tabular data. However, Deep Learning approaches are rarely used with this type of data, due to, among others, the lack of spatial correlation between features. Therefore, in this research, we propose two Deep Learning approaches for working with tabular data. Specifically, two Convolutional Neural Networks architectures are tested against different state of the art regression methods. We perform an hyper-parameter tuning of all the techniques and compare the model performance in different industrial tabular data-sets. Experimental results show that both Convolutional Neural Network approaches can outperform the commonly used methods for regression tasks.

AB - Regression methods aim to predict a numerical value of a target variable given some input variables by building a function f: Rn→ R. In Industry 4.0 regression tasks, tabular data-sets are especially frequent. Decision Trees, ensemble methods such as Gradient Boosting and Random Forest, or Support Vector Machines are widely used for regression tasks with tabular data. However, Deep Learning approaches are rarely used with this type of data, due to, among others, the lack of spatial correlation between features. Therefore, in this research, we propose two Deep Learning approaches for working with tabular data. Specifically, two Convolutional Neural Networks architectures are tested against different state of the art regression methods. We perform an hyper-parameter tuning of all the techniques and compare the model performance in different industrial tabular data-sets. Experimental results show that both Convolutional Neural Network approaches can outperform the commonly used methods for regression tasks.

UR - https://www.scopus.com/pages/publications/85141692719

U2 - 10.1007/978-3-031-18050-7_35

DO - 10.1007/978-3-031-18050-7_35

M3 - Conference contribution

AN - SCOPUS:85141692719

SN - 9783031180491

T3 - Lecture Notes in Networks and Systems

SP - 361

EP - 370

BT - 17th International Conference on Soft Computing Models in Industrial and Environmental Applications, SOCO 2022, Proceedings

A2 - García Bringas, Pablo

A2 - Pérez García, Hilde

A2 - Martinez-de-Pison, Francisco Javier

A2 - Villar Flecha, José Ramón

A2 - Troncoso Lora, Alicia

A2 - de la Cal, Enrique A.

A2 - Herrero, Alvaro

A2 - Martínez Álvarez, Francisco

A2 - Psaila, Giuseppe

A2 - Quintián, Héctor

A2 - Corchado Rodriguez, Emilio S.

PB - Springer Science and Business Media Deutschland GmbH

T2 - 17th International Conference on Soft Computing Models in Industrial and Environmental Applications, SOCO 2022

Y2 - 5 September 2022 through 7 September 2022

ER -

Moles L, Boto F, Echegaray G, Torre IG. Convolutional Neural Networks for Structured Industrial Data. In García Bringas P, Pérez García H, Martinez-de-Pison FJ, Villar Flecha JR, Troncoso Lora A, de la Cal EA, Herrero A, Martínez Álvarez F, Psaila G, Quintián H, Corchado Rodriguez ES, editors, 17th International Conference on Soft Computing Models in Industrial and Environmental Applications, SOCO 2022, Proceedings. Springer Science and Business Media Deutschland GmbH. 2023. p. 361-370. (Lecture Notes in Networks and Systems). doi: 10.1007/978-3-031-18050-7_35