add anomaly score predictor

2_anomaly_detection_ecg.py

@@ -60,7 +60,7 @@
  score_predictor = SVR(C=1.0,epsilon=0.2)
  score_predictor.fit(torch.cat(hiddens,dim=0).numpy(),train_scores)
 
- scores, sorted_predictions,sorted_errors, _, predicted_scores = anomalyScore(args, model, test_dataset, mean, cov, endPoint,score_predictor=score_predictor)
+ scores, sorted_predictions,sorted_errors, _, predicted_scores = anomalyScore(args, model, test_dataset, mean, cov, endPoint,score_predictor=score_predictor,channel_idx=1)
 
  sorted_predictions = torch.cat(sorted_predictions, dim=0)
  sorted_errors = torch.cat(sorted_errors,dim=0)

README.md

@@ -31,8 +31,20 @@ __2D gesture__
 
 ## Implemented Algorithms
 * RNN based Multi-step predictor
+
+ - [Malhotra, Pankaj, et al. "Long short term memory networks for anomaly detection in time series." Proceedings. Presses universitaires de Louvain, 2015.](https://www.elen.ucl.ac.be/Proceedings/esann/esannpdf/es2015-56.pdf)
+
+
 * Multivariate Gaussian distribution based anomaly detector
 
+ - [Malhotra, Pankaj, et al. "LSTM-based encoder-decoder for multi-sensor anomaly detection." arXiv preprint arXiv:1607.00148 (2016).](https://arxiv.org/pdf/1607.00148.pdf)
+
+* Anomaly score predictor
+
+ - [Park, Daehyung, Yuuna Hoshi, and Charles C. Kemp. "A Multimodal Anomaly Detector for Robot-Assisted Feeding Using an LSTM-based Variational Autoencoder." IEEE Robotics and Automation Letters 3.3 (2018): 1544-1551.](https://arxiv.org/pdf/1711.00614.pdf)
+
+
+
 ## Example of usage
 __1. Time-series prediction:__
 Train and save RNN based time-series prediction model