Explorando a correlação espaço-temporal no agrupamento de sensores de cidades inteligentes

• Morgana Gabi Gomes UFMG
• Pedro H. Barros UFMG
• Heitor S. Ramos UFMG

DOI: https://doi.org/10.5753/sbrc.2022.221955

Abstract

We propose a similarity function called SMELL-TS, based on deep metric learning, for classification of time series in the context of Zero-shot Learning, i.e., we are able to classify objects of classes that have not yet been used in the training set. The data are pre-processed by the Short-Term Fourier Transform, and later, they are mapped into two new representation spaces, called latent space and S-Space. We tested our model on a real dataset of sensors distributed in an intelligent building, seeking to group sensors co-located in the same environment . Our method presented better results when compared to other techniques found in the literature, with a gain of 15 % in the Room Accuracy metric – percentage of correctly co-located sensors grouped by SMELL-TS.

References

Barros, P. H., Queiroz, F., Figueredo, F., dos Santos, J. A., and Ramos, H. S. (2020). A new similarity space tailored for supervised deep metric learning.

Berndt, D. J. and Clifford, J. (1994). Using dynamic time warping to find patterns in time series. In Proceedings of the 3rd International Conference on Knowledge Discovery and Data Mining, AAAIWS’94, page 359–370. AAAI Press.

Bromley, J., Guyon, I., LeCun, Y., Säckinger, E., and Shah, R. (1994). Signature verification using a”siamese”time delay neural network. Advances in neural information processing systems, pages 737–737.

Che, Z., He, X., Xu, K., and Liu, Y. (2017). Decade: a deep metric learning model for multivariate time series. In KDD workshop on mining and learning from time series. sn.

Cui, Y., Zhou, F., Lin, Y., and Belongie, S. (2016). Fine-grained categorization and dataset bootstrapping using deep metric learning with humans in the loop. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 1153–1162.

Daubechies, I. (1990). The wavelet transform, time-frequency localization and signal analysis. IEEE Transactions on Information Theory, 36(5):961–1005.

Globerson, A. and Roweis, S. (2005). Metric learning by collapsing classes. Advances in neural information processing systems, 18:451–458.

Grabocka, J. and Schmidt-Thieme, L. (2018). Neuralwarp: Time-series similarity with warping networks. CoRR, abs/1812.08306.

Han, Z., Fu, Z., Chen, S., and Yang, J. (2021). Contrastive embedding for generalized zero-shot learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 2371–2381.

Hong, D., Cai, R., Wang, H., and Whitehouse, K. (2019). Learning from correlated events for equipment relation inference in buildings. In Proceedings of the 6th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation, BuildSys ’19, page 203–212, New York, NY, USA. Association for Computing Machinery.

Hong, D., Ortiz, J., Whitehouse, K., and Culler, D. (2013). Towards automatic spatial verification of sensor placement in buildings. In Proceedings of the 5th ACM Workshop on Embedded Systems For Energy-Efficient Buildings, BuildSys’13, page 1–8, New York, NY, USA. Association for Computing Machinery.

KAYA, M. and BILGE, H. S. (2019). Deep metric learning: A survey. Symmetry, 11(9).

Li, S., Hong, D., and Wang, H. (2020). Relation inference among sensor time series in smart buildings with metric learning. Proceedings of the AAAI Conference on Artificial Intelligence, 34(04):4683–4690.

Li Zhang, Weida Zhou, and Licheng Jiao (2004). Wavelet support vector machine. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 34(1):34–39.

Masnadi-Shirazi, H. and Vasconcelos, N. (2008). On the design of loss functions for classification: theory, robustness to outliers, and savageboost. sign [f*(x)], 10:2.

Oh Song, H., Xiang, Y., Jegelka, S., and Savarese, S. (2016). Deep metric learning via lifted structured feature embedding. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 4004–4012.

Rabiner, L. and Juang, B. (1986). An introduction to hidden markov models. IEEE ASSP Magazine, 3(1):4–16.

Romera-Paredes, B. and Torr, P. (2015). An embarrassingly simple approach to zero-shot learning. In Bach, F. and Blei, D., editors, Proceedings of the 32nd International Conference on Machine Learning, volume 37 of Proceedings of Machine Learning Research, pages 2152–2161, Lille, France. PMLR.

Schroff, F., Kalenichenko, D., and Philbin, J. (2015). Facenet: A unified embedding for face recognition and clustering. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 815–823.

Sohn, K. (2016). Improved deep metric learning with multi-class n-pair loss objective. In Advances in Neural Information Processing Systems 29, pages 1857– 1865. Curran Associates, Inc.

Wang, J., Zhou, F., Wen, S., Liu, X., and Lin, Y. (2017). Deep metric learning with angular loss. In Proceedings of the IEEE International Conference on Computer Vision (ICCV), pages 2593–2601.

Wang, X., Han, X., Huang, W., Dong, D., and Scott, M. R. (2019). Multi-similarity loss with general pair weighting for deep metric learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 5022–5030.

Wang, Y. and Yao, Q. (2019). Few-shot learning: A survey. CoRR, abs/1904.05046.

Xing, E. P., Ng, A. Y., Jordan, M. I., and Russell, S. (2002). Distance metric learning, with application to clustering with side-information. In Proceedings of the 15th International Conference on Neural Information Processing Systems, NIPS’02, page 521–528, Cambridge, MA, USA. MIT Press.