Artificial intelligence analysis for feed ratio optimization in precision aquaculture
Aquaculture products’ increasing demand emphasizes the importance of FCR (Feed Conversion Ratio) optimization. While efforts to improve FCR of specific species exist, a universal method is lacking. Therefore, we present a hunger detection method generalized for different aquaculture species by...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project (FYP) |
| Language: | English |
| Published: |
Nanyang Technological University
2024
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/176594 |
| _version_ | 1826124883586711552 |
|---|---|
| author | Galenius, Bryan Timothy |
| author2 | Ng Yin Kwee |
| author_facet | Ng Yin Kwee Galenius, Bryan Timothy |
| author_sort | Galenius, Bryan Timothy |
| collection | NTU |
| description | Aquaculture products’ increasing demand emphasizes the importance of FCR (Feed Conversion
Ratio) optimization. While efforts to improve FCR of specific species exist, a universal method is
lacking. Therefore, we present a hunger detection method generalized for different aquaculture
species by summarizing and combining the different behavioral parameters which has been found
to be useful in determining hunger into 5 parameters: Weighted Positional Index, Position
Variance, Average Speed, Lingering Count, and Average Swim Direction and Turning Angle.
We continuously recorded 21 Danio rerio (Zebrafish), a fish which has yet to be tested in hunger
detection, in a video for 7 days twice. The first 7-day recording is done with a twice-a-day feeding
regime, while the second recording is with only once-a-day feeding regime. The recordings are
then passed through DETR object detection algorithm and StrongSORT multi-object tracking
algorithm to extract the 5 proposed parameters, after which each parameter’s role in hunger
detection is evaluated through the comparison between the 2 different feeding regimes. Finally,
the twice-a-day feeding regime data is passed onto multiple different Machine Learning (ML)
algorithm. If the algorithm manages to find one or more clusters where all the values inside have
a high value of ‘time elapsed since the last feeding’ and with all clusters having a relatively large
number of datapoints each cluster (indicating the absence overfitting), then we can conclude that
the 5 parameters are indeed enough for the algorithm to find a cluster in which the fish is hungry.
The result shows that the proposed algorithm pipeline was indeed able to utilize the 5 proposed
parameters to identify a cluster showing fish hunger through Gaussian Mixture Model clustering
on PCA-transformed parameter data. It also shows that each parameter indeed contributes to the
hunger prediction. Therefore, the proposed algorithm pipeline can move forward to be tested on
multiple different species to ensure the generalization of the algorithm. Any other relevant
parameters found in the future can also be easily added. Afterwards, it can be further integrated
into the hardware system to create a holistic smart feeding system usable in aquaculture farms. |
| first_indexed | 2024-10-01T06:27:59Z |
| format | Final Year Project (FYP) |
| id | ntu-10356/176594 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T06:27:59Z |
| publishDate | 2024 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1765942024-05-18T16:53:32Z Artificial intelligence analysis for feed ratio optimization in precision aquaculture Galenius, Bryan Timothy Ng Yin Kwee School of Mechanical and Aerospace Engineering Wong Kei Fong, Mark MYKNG@ntu.edu.sg Computer and Information Science Engineering Aquaculture Computer vision Satiety Machine learning Hunger detection Aquaculture products’ increasing demand emphasizes the importance of FCR (Feed Conversion Ratio) optimization. While efforts to improve FCR of specific species exist, a universal method is lacking. Therefore, we present a hunger detection method generalized for different aquaculture species by summarizing and combining the different behavioral parameters which has been found to be useful in determining hunger into 5 parameters: Weighted Positional Index, Position Variance, Average Speed, Lingering Count, and Average Swim Direction and Turning Angle. We continuously recorded 21 Danio rerio (Zebrafish), a fish which has yet to be tested in hunger detection, in a video for 7 days twice. The first 7-day recording is done with a twice-a-day feeding regime, while the second recording is with only once-a-day feeding regime. The recordings are then passed through DETR object detection algorithm and StrongSORT multi-object tracking algorithm to extract the 5 proposed parameters, after which each parameter’s role in hunger detection is evaluated through the comparison between the 2 different feeding regimes. Finally, the twice-a-day feeding regime data is passed onto multiple different Machine Learning (ML) algorithm. If the algorithm manages to find one or more clusters where all the values inside have a high value of ‘time elapsed since the last feeding’ and with all clusters having a relatively large number of datapoints each cluster (indicating the absence overfitting), then we can conclude that the 5 parameters are indeed enough for the algorithm to find a cluster in which the fish is hungry. The result shows that the proposed algorithm pipeline was indeed able to utilize the 5 proposed parameters to identify a cluster showing fish hunger through Gaussian Mixture Model clustering on PCA-transformed parameter data. It also shows that each parameter indeed contributes to the hunger prediction. Therefore, the proposed algorithm pipeline can move forward to be tested on multiple different species to ensure the generalization of the algorithm. Any other relevant parameters found in the future can also be easily added. Afterwards, it can be further integrated into the hardware system to create a holistic smart feeding system usable in aquaculture farms. Bachelor's degree 2024-05-16T08:41:42Z 2024-05-16T08:41:42Z 2024 Final Year Project (FYP) Galenius, B. T. (2024). Artificial intelligence analysis for feed ratio optimization in precision aquaculture. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/176594 https://hdl.handle.net/10356/176594 en B208 application/pdf Nanyang Technological University |
| spellingShingle | Computer and Information Science Engineering Aquaculture Computer vision Satiety Machine learning Hunger detection Galenius, Bryan Timothy Artificial intelligence analysis for feed ratio optimization in precision aquaculture |
| title | Artificial intelligence analysis for feed ratio optimization in precision aquaculture |
| title_full | Artificial intelligence analysis for feed ratio optimization in precision aquaculture |
| title_fullStr | Artificial intelligence analysis for feed ratio optimization in precision aquaculture |
| title_full_unstemmed | Artificial intelligence analysis for feed ratio optimization in precision aquaculture |
| title_short | Artificial intelligence analysis for feed ratio optimization in precision aquaculture |
| title_sort | artificial intelligence analysis for feed ratio optimization in precision aquaculture |
| topic | Computer and Information Science Engineering Aquaculture Computer vision Satiety Machine learning Hunger detection |
| url | https://hdl.handle.net/10356/176594 |
| work_keys_str_mv | AT galeniusbryantimothy artificialintelligenceanalysisforfeedratiooptimizationinprecisionaquaculture |