The anomaly detection algorithms

These algorithms can be ran directly: (the datasets structure can be found in "Vae" directory)

BeatGAN: B. Zhou, S. Liu, B. Hooi, X. Cheng, and J. Ye, “Beatgan: anomalous rhythm detection using adversarially generated time series,” in IJCAI, 2019, pp. 4433–4439.

Dagmm: B. Zong, Q. Song, M. R. Min, W. Cheng, C. Lumezanu, D. Cho, and H. Chen, “Deep autoencoding gaussian mixture model for unsupervised anomaly detection,” in ICLR, 2018.

Encdec: P. Malhotra, A. Ramakrishnan, G. Anand, L. Vig, P. Agarwal, and G. Shroff, “Lstm-based encoder-decoder for multi-sensor anomaly detection,” arXiv preprint arXiv:1607.00148, 2016.

GANomaly: S. Akcay, A. Atapour-Abarghouei, and T. P. Breckon, “Ganomaly: Semisupervised anomaly detection via adversarial training,” in ACCV, 2018, pp. 622–637.

Vae: The variant of our algorithm.

These algorithms need to be updated: (in Huawei's Obs system)

Lstmndt: K. Hundman, V. Constantinou, C. Laporte, I. Colwell, and T. Soderstrom, “Detecting spacecraft anomalies using lstms and nonparametric dynamic thresholding,” in SIGKDD, 2018, pp. 387–395.

LSTM-VAE: D. Park, Y. Hoshi, and C. C. Kemp, “A multimodal anomaly detector for robot-assisted feeding using an lstm-based variational autoencoder,” IEEE Robotics and Automation Letters, vol. 3, no. 3, pp. 1544–1551, 2018.

OmniAnomaly: Y. Su, Y. Zhao, C. Niu, R. Liu, W. Sun, and D. Pei, “Robust anomaly detection for multivariate time series through stochastic recurrent neural network,” in SIGKDD, 2019, pp. 2828–2837.

Running steps

1. Using the data_preprocess.py to preprocess data.

2. Using main.py (in each directory) to run the code.