Seasid: deep learning based microbiome monitoring system for early detection of seaweed disease through classification of microbes using submersible microscope via web interface with alert system/ Thricia Mae R. Aquino, Eduardo II D. Arceo, Daryll Stuart C. Pabilando, Aaron Edcel M. Pasaporte, and Danna Ericka S. Pili.--

By:

Aquino, Thricia Mae R [author]

Contributor(s):

Material type: Text

TextPublication details: Manila: Technological University of the Philippines, 2025.Description: vii, 156pages: 29cmContent type:

Media type:

Carrier type:

Subject(s):

LOC classification:

BTH TK 870 A68 2025

Dissertation note: College of Engineering.-- Bachelor of science in electronics engineering: Technological University of the Philippines, 2025. Summary: Seaweed farming is one of the major contributors to the health of marine ecosystems and aquaculture, especially in the Philippines, as it is a source of income and food for those living in coastal areas and a global food security contributor. Seaweed farms are, however, seriously threatened by diseases caused by pathogenic microorganisms, leading to huge economic losses. Conventional detection techniques using manual observation and laboratory testing are time-consuming, subjective, and inefficient, thus the necessity to develop early detection techniques. This paper introduces SEASID, a novel deep learning-based seaweed disease monitoring system for early and real-time seaweed disease detection. SEASID employs a submersible microscope to capture high-resolution underwater images of microbes and integrates environmental sensors for real-time salinity and temperature monitoring, which are critical parameters influencing microbial behavior. The system was tested in real seawater conditions. YOLOv8 detected harmful and non- harmful microbes with 76.2% precision, 73% recall, and 75.1% F1-score. The temperature sensor has an accuracy rate of ±0.8°C, while the salinity sensor has a small error rate of ±0.9 ppt in comparison to commercial counterparts. SEASID can provide real-time results. Traditional testing is more expensive too and has no continuous monitoring capability. It has also been shown by SEASID that microbial counts increase above 28°C and salinity changes greater than 3 ppt, thus predicting an early risk for diseases. It offers fast, accurate, and affordable seaweed health assessment compared with traditional methods.

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 A68 2025 (Browse shelf(Opens below))	c.1.	Not for loan		BTH0006435

Bachelor's thesis

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

Includes bibliographic references and index.

Seaweed farming is one of the major contributors to the health of marine
ecosystems and aquaculture, especially in the Philippines, as it is a source of income and
food for those living in coastal areas and a global food security contributor. Seaweed farms
are, however, seriously threatened by diseases caused by pathogenic microorganisms,
leading to huge economic losses. Conventional detection techniques using manual
observation and laboratory testing are time-consuming, subjective, and inefficient, thus the
necessity to develop early detection techniques. This paper introduces SEASID, a novel
deep learning-based seaweed disease monitoring system for early and real-time seaweed
disease detection. SEASID employs a submersible microscope to capture high-resolution
underwater images of microbes and integrates environmental sensors for real-time salinity
and temperature monitoring, which are critical parameters influencing microbial behavior.

The system was tested in real seawater conditions. YOLOv8 detected harmful and non-
harmful microbes with 76.2% precision, 73% recall, and 75.1% F1-score. The temperature

sensor has an accuracy rate of ±0.8°C, while the salinity sensor has a small error rate of
±0.9 ppt in comparison to commercial counterparts. SEASID can provide real-time results.
Traditional testing is more expensive too and has no continuous monitoring capability. It
has also been shown by SEASID that microbial counts increase above 28°C and salinity
changes greater than 3 ppt, thus predicting an early risk for diseases. It offers fast, accurate,
and affordable seaweed health assessment compared with traditional methods.

There are no comments on this title.

to post a comment.

Click on an image to view it in the image viewer