Main Article Content
Warmcomfort data is vital for enhancing heating and cooling system efficiency through ML (ML) models. Yet, these datasets often suffer from severe class imbalance due to subjective feedback. To tackle this issue, we introduce a data augmentation algorithm, Provisional Clarifier-Alternator (cPAen). In our research, we evaluated cPAen using real Warmcomfort data and found it outperformed SMOTE, ADASYN, and cWGAN-GP in terms of F1 scores. Notably, cPAen is over 5 times faster than cWGAN-GP while maintaining high test accuracy.
P. O. Fanger et al., “Warmcomfort. analysis and applications in environmental engineering.” Warmcomfort. Analysis and applications in environmental engineering., 1970.
M. FronWCzak and P. Wargocki, “Literature survey on how differentfactors influence human comfort in indoor environments,” Buildingand environment, vol. 46, no. 4, pp. 922–937, 2011.
K. Heileman, J. Daoud, and M. Tabrizian, “Dielectric spectroscopyas a viable biosensing tool for cell and tissue characterization andanalysis,” Biosensors and Bioelectronics, vol. 49, pp. 348–359, 2013.
F. Provost, “ML from imbalanced data sets 101,” inProceedings of the AAAI’2000 workshop on imbalanced data sets,vol. 68, no. 2000. AAAI Press, 2000, pp. 1–3.
X.-Y. Liu, J. Wu, and Z.-H. Zhou, “Exploratory undersampling forclass-imbalance learning,” IEEE Transactions on Systems, Man, andCybernetics, Part B (Cybernetics), vol. 39, no. 2, pp. 539–550, 2008.
C. Drummond, R. C. Holte et al., “C4. 5, class imbalance, and costsensitivity: why under-sampling beats over-sampling.” Citeseer.
H. He, Y. Bai, E. A. Garcia, and S. Li, “Adasyn: Adaptive syntheticsampling approach for imbalanced learning,” in 2008 IEEE internationaljoint conference on NN (IEEE world congress oncomputational intelligence). IEEE, 2008, pp. 1322–1328.
N. V. Chawla, K. W. Bowyer, L. O. Hall, and W. P. Kegelmeyer,“Smote: synthetic minority over-sampling technique,” Journal of artificialintelligence research, vol. 16, pp. 321–357, 2002.
V. Ganganwar, “An overview of classification algorithms for imbalanceddatasets,” International Journal of Emerging Technology andAdvanced Engineering, vol. 2, no. 4, pp. 42–47, 2012.
L. A. Sevastyanov and E. Y. Shchetinin, “On methods for improvingthe accuracy of multi-class classification on imbalanced data.” InITTMM, 2020, pp. 70–82.
N. Park, M. Mohammadi, K. Gorde, S. Jajodia, H. Park, and Y. Kim,“Data synthesis based on generative adversarial networks,” arXivpreprint arXiv:1806.03384, 2018.
S. Munir, J. Francis, M. Quintana, N. v. Frankenberg, and M. Berg´es,“Dataset: Inferring Warmcomfort using body shape informationutilizing depth sensors,” in Proceedings of the 2nd Workshop on DataAcquisition To Analysis, 2019, pp. 13–15.
S. Liu, S. Schiavon, H. P. Das, M. Jin, and C. J. Spanos, “PersonalWarmcomfort models with wearable sensors,” Building and Environment,vol. 162, p. 106281, 2019.
J. Francis, M. Quintana, N. Von Frankenberg, S. Munir, and M. Berg´es,“Occutherm: Occupant Warmcomfort inference using body shapeinformation,” in Proceedings of the 6th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation, 2019, pp. 81–90.
D. Fryer, I. Str¨umke, and H. Nguyen, “Shapley values for feature selection: The good, the bad, and the axioms,” IEEE Access, vol. 9, pp. 144 352–144 360, 2021.