Smaqcloud 2.0: real-time monitoring system for smart aquaponics via lstm and yolov8 using nvidia jetson nano/ Cyra E. Abdon, Hanz U. Baga, James Kerby S. Descalso, Beanca A. Manaog, and Julian Gabrielo B. Sales.--

By:

Abdon, Cyra E [author]

Contributor(s):

Material type: Text

TextPublication details: Manila: Technological University of the Philippines, 2025.Description: xii, 143pages: 29cmContent type:

Media type:

Carrier type:

Subject(s):

LOC classification:

BTH TK 870 A23 2025

Dissertation note: College Of Engineering.-- Bachelor of science in electronics engineering: Technological University of the Philippines, 2025. Summary: Highly populated areas in urban locations produce a significant amount of wastes, with fair share coming from various sectors, including agriculture. There are various approaches to aid waste management, some of these are hydroponics and aquaculture. The study produced a sustainable system of agriculture combining the advantages of both hydroponics and aquaculture – aquaponics. SMAQCloud 2.0 is an IoT (Internet of Things)-based real-time monitoring system designed to gather sensor data to make the system respond accordingly to the needs of the subjects – Tilapia and Romaine Lettuce and monitor their growth. It utilized the processing power of NVIDIA Jetson Nano running YOLOv8 (You Only Look Once) for instance segmentation, MiDas (Monocular Depth Approximation System) dimension measurement, and LSTM (Long-Short Term Memory) for growth prediction. The YOLOv8 models showed 98.4% and 74.9% mAP (Mean Average Precision) for tilapia and lettuce, respectively, indicating a precise detection through validation and training datasets. The Root Mean Square Error Statistical Analysis done on the length, height, and weight of tilapia resulted to errors of 0.82 cm, 0.18 cm, and 0.89 g, respectively; while the error for the lettuce diameter was only 1.69 cm, and 1.12 cm for the height. This was to compare the error or difference of the average measurements gathered by the system to the manual measurements. In addition, the web application that displayed the sensor data and specimen measurements in real-time also received high remarks from evaluators. Such results prove the aid that the system can offer to existing problems in the agricultural sector, solid waste management and food shortage in urbanized areas.

Tags from this library: No tags from this library for this title. Log in to add tags.

Average rating: 0.0 (0 votes)

Holdings
Item type	Current library	Shelving location	Call number	Copy number	Status	Date due	Barcode
Bachelor's Thesis COE	TUP Manila Library	Thesis Section-2nd floor	BTH TK 870 A23 2025 (Browse shelf(Opens below))	c.1	Not for loan		BTH0006547

Bachelor's thesis

College Of Engineering.--
Bachelor of science in electronics engineering: Technological University of the Philippines,
2025.

Includes bibliographic references and index.

Highly populated areas in urban locations produce a significant amount of
wastes, with fair share coming from various sectors, including agriculture. There
are various approaches to aid waste management, some of these are hydroponics
and aquaculture. The study produced a sustainable system of agriculture
combining the advantages of both hydroponics and aquaculture – aquaponics.
SMAQCloud 2.0 is an IoT (Internet of Things)-based real-time monitoring system
designed to gather sensor data to make the system respond accordingly to the
needs of the subjects – Tilapia and Romaine Lettuce and monitor their growth. It
utilized the processing power of NVIDIA Jetson Nano running YOLOv8 (You Only
Look Once) for instance segmentation, MiDas (Monocular Depth Approximation
System) dimension measurement, and LSTM (Long-Short Term Memory) for
growth prediction. The YOLOv8 models showed 98.4% and 74.9% mAP (Mean
Average Precision) for tilapia and lettuce, respectively, indicating a precise
detection through validation and training datasets. The Root Mean Square Error
Statistical Analysis done on the length, height, and weight of tilapia resulted to
errors of 0.82 cm, 0.18 cm, and 0.89 g, respectively; while the error for the lettuce
diameter was only 1.69 cm, and 1.12 cm for the height. This was to compare the
error or difference of the average measurements gathered by the system to the
manual measurements. In addition, the web application that displayed the sensor
data and specimen measurements in real-time also received high remarks from
evaluators. Such results prove the aid that the system can offer to existing
problems in the agricultural sector, solid waste management and food shortage in
urbanized areas.

There are no comments on this title.

to post a comment.

Click on an image to view it in the image viewer