This project is a part of the Avisa Project at ICRISAT.
The purpose of this project is determine the protein content from multiple grain cereals using near-infrared spectroscopy and machine learning/deep learning algorithms. Calibration models have been developed and will be deployed as rapid phenotyping tools for cereal breeders.
- Hone Ag Pty. Ltd.
- https://www.honeag.com/
- Partner contact: Felicity Fraser [felicity@honeag.com]
- Inferential Statistics
- Machine Learning
- Deep learning
- Data augmentation
- Data Visualization
- Predictive Modeling
- etc.
- Python
- Pandas, jupyter, Numpy
- Scipy, Matplotlib
- Scikit-Learn
- Keras
- Tensorflow
- etc.
- Measure protein content over 300 samples of peanut from wetlab analysis
- Scan the same samples using mobile and benchtop NIR sensors to record spectroscopic absorbance covering more than 1000 bands
- Preprocess the data (filtering, derivating, smoothing, etc)
- Develop ML/DL model architecture
- Train the model
- Make predictions
- Deploy the model
- frontend development for deployment
- data exploration/descriptive statistics
- data processing/cleaning
- statistical modeling
- writeup/reporting
- etc. (be as specific as possible)
-
Clone this repo (for help see this tutorial).
-
Raw Data is being kept here within this repo.
If using offline data mention that and how they may obtain the data from the froup)
-
Data processing/transformation scripts are being kept [here](Repo folder containing data processing scripts/notebooks)
-
etc...
If your project is well underway and setup is fairly complicated (ie. requires installation of many packages) create another "setup.md" file and link to it here
- Follow setup [instructions](Link to file)
Maintener: Adama Ndour
Others
| Name | Slack Handle |
|---|---|
| Adama Ndour | @adamavip |
| Krithika Anbazhagan | @krithika |
Reach out me
