Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
RNN based Time-series Anomaly detector model implemented in Pytorch.
| Date | Stars |
|---|---|
| 2026-07-24 | 1306 |
| 2026-07-25 | 1306 |
| 2026-07-28 | 1306 |
| 2026-07-30 | 1306 |
| 2026-08-06 | 1306 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# RNN-Time-series-Anomaly-Detection
RNN based Time-series Anomaly detector model implemented in Pytorch.
This is an implementation of RNN based time-series anomaly detector, which consists of two-stage strategy of time-series prediction and anomaly score calculation.
## Requirements
* Ubuntu 16.04+ (Errors reported on Windows 10. see [issue](https://github.com/chickenbestlover/RNN-Time-series-Anomaly-Detection/issues/6#issue-358550020). Suggesstions are welcomed.)
* Python 3.5+
* Pytorch 0.4.0+
* Numpy
* Matplotlib
* Scikit-learn
## Dataset
__1. NYC taxi passenger count__
* The New York City taxi passenger data stream, provided by the [New
York City Transportation Authority](http://www.nyc.gov/html/tlc/html/about/trip_record_data.shtml )
* preprocessed (aggregated at 30 min intervals) by Cui, Yuwei, et al. in ["A comparative study of HTM and other neural network models for online sequence learning with streaming data." Neural Networks (IJCNN), 2016 International Joint Conference on. IEEE, 2016.](http://ieeexplore.ieee.org/abstract/document/7727380/)
, [code](https://github.com/numenta/htmresearch/tree/master/projects/sequence_prediction)
__2. Electrocardiograms (ECGs)__
* The ECG dataset containing a single anomaly corresponding to a pre-ventricular contraction
__3. 2D gesture (video surveilance)__
* X Y coordinate of hand gesture in a video
__4. Respiration__
* A patients respiration (measured by thorax extension, sampling rate 10Hz)
__5. Space shuttle__
* Space Shuttle Marotta Valve time-series
__6. Power demand__
* One years power demand at a Dutch research facility
The Time-series 2~6 are provided by E. Keogh et al. in
["HOT SAX: Efficiently Finding the Most Unusual Time Series Subsequence." In The Fifth IEEE International Conference on Data Mining. (2005)
](http://ieeexplore.ieee.org/abstract/document/1565683/)
, [dataset](http://www.cs.ucr.edu/~eamonn/discords/)
### **_DISCLAIMER_**:
_<U>The labels provided on this repository are unofficial and have not been verified. Labels were unofficially created by non-experts (annotated without any domain knowledge of the dataset or access to out-of-band data that could confirm the labels) and may contain mislabeled points (both false negatives, and false posatives).
We referred to other time-series anomaly detection papers using the datasets ([Malhotra et al., 2015.](https://www.elen.ucl.ac.be/Proceedings/esann/esannpdf/es2015-56.pdf),
[Malhotra et al., 2016.](https://arxiv.org/pdf/1607.00148.pdf))
and the author's dataset presentation slides to label anomaly points in this time series as accurately as possible. If you need accurate label information, you should refer to the official [dataset](http://www.cs.ucr.edu/~eamonn/discords/) [description](http://www.cs.ucr.edu/~eamonn/discords/ICDM05_discords.pdf) or contact the authors.</U>_
## RNN-based Multi-Step Prediction Model
__0. Architecture__
When the value of x_i is known from i=0 to i=t, the model recursively predicts the value of x_i from i=t+1 to i=T. In this figure, t=3, T=8. We first train this model with a trainset which contains no anomalies, then we use the trained model to detect anomalies in a testset, where anomalies are included.
__1. How to train this model__
Recursive multi-step prediction using RNNs is a rather difficult problem. As the prediction progresses, the prediction errors are accumulated and the predictions rapidly become inaccurate. To solve this problem, we need a model that is robust to input noise.
TODO
TODO
TODO
## RNN-based Multi-Step Prediction Model
TODO
## Example of usage
__0. Download the dataset:__
Download the five kinds of multivariate time-series dataset
(ecg, gesture,power_demand, respiration, space_shuttle),
and Label all the abnormality points in the dataset.
```
python 0_download_dataset.py
```
__1. Time-series predictExcerpt of 7,282 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:4a34a309dd80b8ae, topic:neural-network