bi_add
BI_ADD detects anomalous diffusions along trajectories iteratively.
Science Score: 49.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
○CITATION.cff file
-
✓codemeta.json file
Found codemeta.json file -
✓.zenodo.json file
Found .zenodo.json file -
✓DOI references
Found 7 DOI reference(s) in README -
✓Academic publication links
Links to: arxiv.org, zenodo.org -
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (13.0%) to scientific vocabulary
Repository
BI_ADD detects anomalous diffusions along trajectories iteratively.
Basic Info
- Host: GitHub
- Owner: JunwooParkSaribu
- License: gpl-3.0
- Language: Python
- Default Branch: main
- Size: 575 MB
Statistics
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
- Releases: 11
Metadata Files
README.md
BI-ADD (Bottom-up Iterative Anomalous Diffusion Detector)
[!IMPORTANT]
Requirements - TensorFlow 2.14 or 2.17 - Python 3.10 or 3.12 - latest version of scikit-learn - latest version of scikit-image - Pre-trained models
BI-ADD detects changepoints at single molecular trajectory level which follows fBm with two properties, Anomalous exponent(alpha) and Generalized diffusion coefficient(K), on different scenarios. For the details of data and scenarios of trjaectories, please check Andi2 Challenge[^1][^2]. The trajectory prediction from video is performed with FreeTrace
| On simulated trajectories |
 |
To run the program on your device
- Clone the repository on your local device.
- Download pre-trained models, place the models folder inside of BI_ADD folder.
- Place trajectory csv files(traj_idx, frame, x, y) inside inputs folder.
- Run run.py via python.
Contacts
junwoo.park@sorbonne-universite.fr
If you use this software, please cite it as below.
@misc{bi_add, title={Bottom-up Iterative Anomalous Diffusion Detector (BI-ADD)}, author={Junwoo Park and Nataliya Sokolovska and Clment Cabriel and Ignacio Izeddin and Judith Min-Hattab}, year={2025}, eprint={2503.11529}, archivePrefix={arXiv}, primaryClass={cs.LG}, url={https://arxiv.org/abs/2503.11529}, }
References
[^1]: AnDi datasets [^2]: Quantitative evaluation of methods to analyze motion changes in single-particle experiments, Gorka Muoz-Gil et al. 2024 https://arxiv.org/abs/2311.18100 [^3]: Convolutional LSTM Network, A Machine Learning Approach for Precipitation Nowcasting, Xingjian Shi et al. 2015 https://arxiv.org/abs/1506.04214 [^4]: Chenouard, N., Smal, I., de Chaumont, F. et al. Objective comparison of particle tracking methods. Nat Methods 11, 281289 (2014).
Owner
- Login: JunwooParkSaribu
- Kind: user
- Repositories: 2
- Profile: https://github.com/JunwooParkSaribu
GitHub Events
Total
- Release event: 6
- Delete event: 1
- Push event: 41
- Create event: 6
Last Year
- Release event: 6
- Delete event: 1
- Push event: 41
- Create event: 6