Klasifikasi Citra Plankton dengan Algoritma Hibrida Convolutional Neural Network-Extreme Learning Machine Berbasis Web Flask

Shahab, Muhammad Syaugi (2024) Klasifikasi Citra Plankton dengan Algoritma Hibrida Convolutional Neural Network-Extreme Learning Machine Berbasis Web Flask. Undergraduate thesis, UPN Veteran Jawa Timur.

	Text (Cover) 20081010107.-cover.pdf Download (1MB)
	Text (Bab 1) 20081010107.-bab1.pdf Download (230kB)
	Text (Bab 2) 20081010107.-bab2.pdf Restricted to Repository staff only until 30 October 2026. Download (2MB) \| Request a copy
	Text (Bab 3) 20081010107.-bab3.pdf Restricted to Repository staff only until 30 October 2026. Download (1MB) \| Request a copy
	Text (Bab 4) 20081010107.-bab4.pdf Restricted to Repository staff only until 30 October 2026. Download (2MB) \| Request a copy
	Text (Bab 5) 20081010107.-bab5.pdf Download (220kB)
	Text (Daftar pustaka) 20081010107.-daftarpustaka.pdf Download (209kB)
	Text (Lampiran) 20081010107.-lampiran.pdf Restricted to Repository staff only Download (158kB) \| Request a copy

Abstract

The oceans, covering approximately 71% of the Earth's surface, are teeming with life, including plankton, which are microscopic organisms forming the base of the marine food chain. Phytoplankton and zooplankton, the two main categories of plankton, play a vital role in maintaining the balance of marine ecosystems. In early studies, plankton identification relied heavily on manual methods, which were costly and impractical for large-scale use. However, automatic plankton classification also faces several challenges, such as unclear plankton images due to low resolution, small dataset sizes, and data imbalance across some classes. Current plankton research is divided into two approaches: feature descriptors and deep learning. While these methods are related in terms of function and history, they are treated as separate approaches. Therefore, a hybrid approach is used, with Convolutional Neural Networks for feature extraction and Extreme Learning Machines for classification. Additionally, SMOTE is applied to address class imbalance, and Flask is chosen as the web framework for model implementation to ensure easy accessibility. The testing of the CNN-ELM model showed that the best model achieved an accuracy of 98.89% with a training-to-testing data ratio of 80:20, using 16 CNN filters and 1000 ELM hidden nodes. However, this model faced difficulties in classifying the Nitzschia, Pleurosigma, and Thalassiosira classes. This research aims to improve understanding and decision-making in the field of marine science.

Item Type:

Thesis (Undergraduate)

Contributors:

Contribution	Contributors	NIDN/NIDK	Email
Thesis advisor	Junaidi, Achmad	NIDN0710117803	achmadjunaidi.if@upnjatim.ac.id
Thesis advisor	Sihananto, Andreas Nugroho	NIDN0012049005	andreas.nugroho.jarkom@upnjatim.ac.id

Subjects:

Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Q Science > QA Mathematics > QA76.6 Computer Programming
Q Science > QR Microbiology
T Technology > T Technology (General)

Divisions:

Faculty of Computer Science > Departemen of Informatics

Depositing User:

Muhammad Syaugi Shahab

Date Deposited:

31 Oct 2024 03:15

Last Modified:

31 Oct 2024 03:15

URI:

https://repository.upnjatim.ac.id/id/eprint/31732