Poriferal Vision: Using MobileNet to Classify Sponge Spicules through Transfer Learning
Global warming is an ongoing issue where the Earth is rapidly warming up. It negatively affects the growth of coral through ocean warming and ocean acidification. Many coral communities, home to a large variety of marine life, are expected to be severely impacted by these effects. Past evidence sugg...
Main Author: | |
---|---|
Format: | Text |
Language: | unknown |
Published: |
SJSU ScholarWorks
2023
|
Subjects: | |
Online Access: | https://scholarworks.sjsu.edu/etd_projects/1311 https://scholarworks.sjsu.edu/context/etd_projects/article/2307/viewcontent/tran_brian.pdf |
id |
ftsanjosestate:oai:scholarworks.sjsu.edu:etd_projects-2307 |
---|---|
record_format |
openpolar |
spelling |
ftsanjosestate:oai:scholarworks.sjsu.edu:etd_projects-2307 2024-01-14T10:09:37+01:00 Poriferal Vision: Using MobileNet to Classify Sponge Spicules through Transfer Learning Tran, Brian 2023-01-01T08:00:00Z application/pdf https://scholarworks.sjsu.edu/etd_projects/1311 https://scholarworks.sjsu.edu/context/etd_projects/article/2307/viewcontent/tran_brian.pdf unknown SJSU ScholarWorks https://scholarworks.sjsu.edu/etd_projects/1311 https://scholarworks.sjsu.edu/context/etd_projects/article/2307/viewcontent/tran_brian.pdf Master's Projects Convolutional Neural Networks (CNN) Transfer Learning Transformations Zero Padding Background Padding Other Computer Engineering text 2023 ftsanjosestate 2023-12-18T19:10:59Z Global warming is an ongoing issue where the Earth is rapidly warming up. It negatively affects the growth of coral through ocean warming and ocean acidification. Many coral communities, home to a large variety of marine life, are expected to be severely impacted by these effects. Past evidence suggests that sponges will take over as the primary reef builders since many species of sponges have skeletons made of silica or glass which is not affected by ocean acidification. More research is needed to determine which kinds of sponge will most likely be able to thrive in today’s climate. This can be done by sampling the seabed for the target era and identifying the spicules that are present in the sample. However, classifying the spicules by hand accurately and within a reasonable amount of time is not tractable with large amounts of spicules. Transfer learning with a pre-existing convolutional neural network (CNN) can be utilized to train a model with a small spicule dataset to classify spicules. In this project, I use transfer learning with MobileNet, a pre-existing CNN, to classify seven categories of spicules. I then use image transformations, zero padding, and background padding on the data before training the model to try to improve its performance on the data. Background padding had the best performance although none of the different iterations of the model could classify all categories well at once. Text Ocean acidification San José State University: SJSU ScholarWorks |
institution |
Open Polar |
collection |
San José State University: SJSU ScholarWorks |
op_collection_id |
ftsanjosestate |
language |
unknown |
topic |
Convolutional Neural Networks (CNN) Transfer Learning Transformations Zero Padding Background Padding Other Computer Engineering |
spellingShingle |
Convolutional Neural Networks (CNN) Transfer Learning Transformations Zero Padding Background Padding Other Computer Engineering Tran, Brian Poriferal Vision: Using MobileNet to Classify Sponge Spicules through Transfer Learning |
topic_facet |
Convolutional Neural Networks (CNN) Transfer Learning Transformations Zero Padding Background Padding Other Computer Engineering |
description |
Global warming is an ongoing issue where the Earth is rapidly warming up. It negatively affects the growth of coral through ocean warming and ocean acidification. Many coral communities, home to a large variety of marine life, are expected to be severely impacted by these effects. Past evidence suggests that sponges will take over as the primary reef builders since many species of sponges have skeletons made of silica or glass which is not affected by ocean acidification. More research is needed to determine which kinds of sponge will most likely be able to thrive in today’s climate. This can be done by sampling the seabed for the target era and identifying the spicules that are present in the sample. However, classifying the spicules by hand accurately and within a reasonable amount of time is not tractable with large amounts of spicules. Transfer learning with a pre-existing convolutional neural network (CNN) can be utilized to train a model with a small spicule dataset to classify spicules. In this project, I use transfer learning with MobileNet, a pre-existing CNN, to classify seven categories of spicules. I then use image transformations, zero padding, and background padding on the data before training the model to try to improve its performance on the data. Background padding had the best performance although none of the different iterations of the model could classify all categories well at once. |
format |
Text |
author |
Tran, Brian |
author_facet |
Tran, Brian |
author_sort |
Tran, Brian |
title |
Poriferal Vision: Using MobileNet to Classify Sponge Spicules through Transfer Learning |
title_short |
Poriferal Vision: Using MobileNet to Classify Sponge Spicules through Transfer Learning |
title_full |
Poriferal Vision: Using MobileNet to Classify Sponge Spicules through Transfer Learning |
title_fullStr |
Poriferal Vision: Using MobileNet to Classify Sponge Spicules through Transfer Learning |
title_full_unstemmed |
Poriferal Vision: Using MobileNet to Classify Sponge Spicules through Transfer Learning |
title_sort |
poriferal vision: using mobilenet to classify sponge spicules through transfer learning |
publisher |
SJSU ScholarWorks |
publishDate |
2023 |
url |
https://scholarworks.sjsu.edu/etd_projects/1311 https://scholarworks.sjsu.edu/context/etd_projects/article/2307/viewcontent/tran_brian.pdf |
genre |
Ocean acidification |
genre_facet |
Ocean acidification |
op_source |
Master's Projects |
op_relation |
https://scholarworks.sjsu.edu/etd_projects/1311 https://scholarworks.sjsu.edu/context/etd_projects/article/2307/viewcontent/tran_brian.pdf |
_version_ |
1788064161305985024 |