Anomaly detection of 3D bioprinting process & optimization using machine learning
The field of bio printing has made remarkable progress in recent years, and it has great potential for creating complex biological constructs such as tissues and organs. However, achieving high printing accuracy, resolution, and consistency is still a major challenge.ML algorithms can analyze hug...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project |
| Language: | English |
| Published: |
Nanyang Technological University
2023
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/167418 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Nanyang Technological University |
| Language: | English |
| Summary: | The field of bio printing has made remarkable progress in recent years, and it has great potential
for creating complex biological constructs such as tissues and organs. However, achieving high
printing accuracy, resolution, and consistency is still a major challenge.ML algorithms can analyze
huge amount of data, learn from it, and make predictions that optimize the printing process.
However, despite the potential benefits of using ML for bio printing, there is a research gap in how
to effectively integrate ML into bio printing.
One of the challenges will be the lack of high-quality training data. The bio printing process
involves various parameters, such as printing speed, pressure, nozzle diameter, and cell viability,
which all affect the final outcome. Therefore it is important to develop effective methods for
collecting high-quality data, and enhancing the interpretability of ML models. We can optimize
the printing process, after study the results which leading to improved quality and efficiency.
Overall, this study demonstrates the potential of machine learning in improving the reliability and
performance of 3D bio printing, paving the way for the development of more complex and
functional tissues and organs for clinical use. |
|---|