![](bg8.png)
7 CONCLUSION AND FUTURE
WORK
In this paper, we provide an approach for anomaly
detection which combines two state-of-the-art detec-
tion models, one based on stacked LSTM and another
one encoder-decoder based. TPSME-AD, in general,
outperforms the detection anomaly models from the
state-of-the-art techniques as already expected since
our ensemble model combines the best of models
(Malhotra et al., 2015; Malhotra et al., 2016) on de-
tecting anomalous time series. In the experiments, we
also show that, for a quasi-periodic time series data,
our model can outperform also standard ensemble fu-
sion approaches, such as simple average, damped av-
erage, and simple weighted average.
As a future direction, we aim at evaluating our
proposal with other datasets like the electrocardio-
gram, and the space-shuttle valve time-series (Keogh
et al., 2007). Another future improvement can be
added to a regularization of the combination function
so that we can mitigate the overfitting in the validation
dataset.
ACKNOWLEDGMENTS
This work is partially supported by the FUNCAP SPU
8789771/2017, and the UFC-FASTEF 31/2019.
REFERENCES
Aggarwal, C. C. (2013). Outlier ensembles: position paper.
ACM SIGKDD Explorations Newsletter, 14(2):49–58.
Chandola, V., Banerjee, A., and Kumar, V. (2009).
Anomaly detection: A survey. ACM computing sur-
veys (CSUR), 41(3):15.
Gao, J. and Tan, P.-N. (2006). Converting output scores
from outlier detection algorithms into probability es-
timates. In Sixth International Conference on Data
Mining (ICDM’06), pages 212–221. IEEE.
Gao, Y., Yang, T., Xu, M., and Xing, N. (2012). An un-
supervised anomaly detection approach for spacecraft
based on normal behavior clustering. In 2012 Fifth
International Conference on Intelligent Computation
Technology and Automation, pages 478–481. IEEE.
Hochreiter, S. and Schmidhuber, J. (1997). Long short-term
memory. Neural computation, 9(8):1735–1780.
Iverson, D. L. (2004). Inductive system health monitoring.
Keogh, E., Lin, J., Lee, S.-H., and Van Herle, H. (2007).
Finding the most unusual time series subsequence: al-
gorithms and applications. Knowledge and Informa-
tion Systems, 11(1):1–27.
Kieu, T., Yang, B., and Jensen, C. S. (2018). Outlier detec-
tion for multidimensional time series using deep neu-
ral networks. In 2018 19th IEEE International Con-
ference on Mobile Data Management (MDM), pages
125–134. IEEE.
Kittler, J., Hater, M., and Duin, R. P. (1996). Combining
classifiers. In Proceedings of 13th international con-
ference on pattern recognition, volume 2, pages 897–
901. IEEE.
Kong, X., Song, X., Xia, F., Guo, H., Wang, J., and Tolba,
A. (2018). Lotad: Long-term traffic anomaly detec-
tion based on crowdsourced bus trajectory data. World
Wide Web, 21(3):825–847.
Liu, F. T., Ting, K. M., and Zhou, Z.-H. (2012). Isolation-
based anomaly detection. ACM Transactions on
Knowledge Discovery from Data (TKDD), 6(1):3.
Malhotra, P., Ramakrishnan, A., Anand, G., Vig, L., Agar-
wal, P., and Shroff, G. (2016). Lstm-based encoder-
decoder for multi-sensor anomaly detection. arXiv
preprint arXiv:1607.00148.
Malhotra, P., Vig, L., Shroff, G., and Agarwal, P. (2015).
Long short term memory networks for anomaly detec-
tion in time series. In Proceedings, page 89. Presses
universitaires de Louvain.
Meng, F., Yuan, G., Lv, S., Wang, Z., and Xia, S. (2018).
An overview on trajectory outlier detection. Artificial
Intelligence Review.
Tariq, S., Lee, S., Shin, Y., Lee, M. S., Jung, O., Chung,
D., and Woo, S. S. (2019). Detecting anomalies in
space using multivariate convolutional lstm with mix-
tures of probabilistic pca. In Proceedings of the 25th
ACM SIGKDD International Conference on Knowl-
edge Discovery & Data Mining, pages 2123–2133.
ACM.
Wang, X., Lin, J., Patel, N., and Braun, M. (2018). Exact
variable-length anomaly detection algorithm for uni-
variate and multivariate time series. Data Mining and
Knowledge Discovery, 32(6):1806–1844.
Model-centered Ensemble for Anomaly Detection in Time Series
707