This page is devoted to show the supplementary materials for the paper entitled "A Pattern-based Approach for Detecting Pneumatic Failures on Temporary Immersion Bioreactors" accepted as regular paper in Sensors journal since 2019.
Temporary Immersion Bioreactors (TIBs) are widely used for increasing plant quality and plant multiplication rates. These TIBs are actioned by mean of a pneumatic system. A failure in the pneumatic system could produce severe damages into the TIB. As a consequence, the whole biological process would be aborted, increasing the production cost. Therefore, an important task is to detect failures on a temporary immersion bioreactor system. In this paper, we propose to approach this task using a contrast pattern based classifier. We will show that our proposal, for detecting pneumatic failures in a TIB, outperforms other approaches reported on in the literature. Also, we introduce a new feature representationfor a new micropropagation pineapple database, which is used for detecting four new types of pneumatic failures on TIBs. Finally, we provide the result of an in-depth analysis of our experimental results; this analysis was carried out together with experts in both biotechnology and pneumatic devices.

Experimental Results and Extracted Contrast Patterns

  • AUC results considering all the databases ->
  • ZFP results considering all the databases ->
  • ROC and Accuracy results considering all the databases ->
  • All contrast patterns extracted by using the contrast pattern miner proposed in [3] ->

Statistical Tests

CD diagrams with a statistical comparison of the classification results and statistical results using Friedman's test (as a non-parametric test) and Shaffer static procedure (as a post-hoc procedure) [1]. The post hoc comparisons contain α = 0.05, α = 0.10, and adjusted p-values. ->


All partitions of the imbalanced databases that was introduced in this paper (using 5-fold and distribution optimally balanced stratified cross validation (DOB-SCV) [2]):

  • DB - Fault1.zip
  • DB - Fault2.zip
  • DB - Fault3.zip
  • DB - Fault4.zip
  • DB - Fault5.zip
  • DB - Fault6.zip


[1] J. Derrac, S. García, D. Molina, and F. Herrera, “A practical tutorial on the use of nonparametric statistical tests as a methodology for comparing evolutionary and swarm intelligence algorithms,” Swarm Evol. Comput., vol. 1, no. 1, pp. 3–18, 2011.

[2] J. G. Moreno-Torres, J. A. Saez, and F. Herrera, “Study on the Impact of Partition-Induced Dataset Shift on k-Fold Cross-Validation,” Neural Networks Learn. Syst. IEEE Trans., vol. 23, no. 8, pp. 1304–1312, Aug. 2012.

[3] O. Loyola-González, Miguel Angel Medina-Pérez, José Fco. Martínez-Trinidad, Jesús Ariel Carrasco-Ochoa, Raúl Monroy, Milton García-Borroto, PBC4cip: A new contrast pattern-based classifier for class imbalance problems, Knowledge-Based Systems, Volume 115, pp. 100-109, 2017.