This project uses Python. Following packages are required:
- numpy
- scipy
- museval
- progressbar2
- ffmpeg
- librosa
These could be installed by conda install numpy scipy museval progressbar2 ffmpeg and conda install -c conda-forge librosa, if the environment is managed by Anaconda.
Testing setup can be done in pybss_example.py. Test results, including Separation Accuracy and Separation Time, are stored as .csv in the folder measurement/.
Please click and download the saxs.pkl as testing data set in dataset/.
If you like our repository, please cite our papers.
```
@INPROCEEDINGS{Wu2112:Network,
AUTHOR="Huanzhuo Wu and Yunbin Shen and Xun Xiao and Artur Hecker and Frank H.P. Fitzek",
TITLE="{In-Network} Processing Acoustic Data for Anomaly Detection in Smart Factory",
BOOKTITLE="2021 IEEE Global Communications Conference: IoT and Sensor Networks (Globecom2021 IoTSN)",
ADDRESS="Madrid, Spain",
DAYS=6,
MONTH=dec,
YEAR=2021
}
```
We are researchers at the Deutsche Telekom Chair of Communication Networks (ComNets) at TU Dresden, Germany. Our focus is on in-network computing.
- Huanzhuo Wu - huanzhuo.wu@tu-dresden.de or wuhuanzhuo@gmail.com
- Yunbin Shen - yunbin.shen@mailbox.tu-dresden.de or shenyunbin@outlook.com
This project is licensed under the MIT license.