Machine Learning-Driven Seaweed Genera Identification on a Web Application Using Teachable Machine
Riza Nur Azhar(1*), Ervia Yudiati(2), Sri Sedjati(3)
(1) Department of Marine Science, Faculty of Fisheries and Marine Sciences, Diponegoro University, Semarang, Indonesia
(2) Department of Marine Science, Faculty of Fisheries and Marine Sciences, Diponegoro University, Semarang, Indonesia
(3) Department of Marine Science, Faculty of Fisheries and Marine Sciences, Diponegoro University, Semarang, Indonesia
(*) Corresponding Author
Abstract
This study aims to evaluate the use of machine learning technology, particularly Teachable Machine, in identifying seaweed genus in Indonesia. The limitations of identification databases and the lack of previous research were the main drivers of this study. The research focused on Panjang Island with three representative field data collection stations. This field data became the basis for training machine learning models for identification. In addition to field data, information from the literature on seaweed visual characteristics was also taken to support the identification process. The machine learning model developed achieved 99.42% accuracy in identifying 13 classes of 9 seaweed genus. The implementation of the model on the web application showed satisfactory responsive performance, including in the speed test on Google PageSpeed. Overall, the integration of machine learning technology in a web application platform provides a practical solution for accurate and accessible seaweed identification. This invention has great potential in supporting research, conservation, and sustainable utilization of marine resources in Indonesia.
Keywords
Full Text:
PDFReferences
Annisaqois, M., Gerung, G. Wullur, S. Sumilat, B. Wagey & S. Mandagi. 2018. Analisis molekuler DNA alga merah (Rhodophyta) Kappaphycus sp. J. Pesisir dan Laut Tropis. 6(1): 107-112.https://doi.org/10.35800/jplt.6.1.2018.20589[M1]
Azora, P. 2021. Analisis quick count dengan menggunakan metode stratified random sampling studi kasus pemilu gubernur Kalimantan Barat 2018. Bimaster. 10(1): 43–50.
Baihaqi, M. B., Y. Litanianda & A. Triyanto, 2022. Implementasi tensor flow lite pada teachable untuk identifikasi tanaman aglonema berbasis android. KOMPUTEK. 6(1): 70-80.
Chazar, C & M. H. Rafsanjani. 2022. Penerapan Teachable Machine Pada Klasifikasi Machine Learning Untuk Identifikasi Bibit Tanaman. INOTEK. 2(1): 32-40.
Dodge, S & L. Karam. 2016. Understanding how image quality affects deep neural networks. QoMEX, 1-6.
Duarte, C. M., J. Wu , X. Xiao, A. Bruhn & D. Krause-Jensen. 2017. Can seaweed farming play a role in climate change mitigation and adaptation?. Front. Mar. Sci. 4(100): 1-8.
Eggertsen, M & C. Halling. 2021. Knowledge gaps and management recommendations for future paths of sustainable seaweed farming in the Western Indian Ocean. Ambio. 50(1): 60-73.
Islam, N., M. M. Rashid, S. Wibowo, C. Y. Xu, A. Morshed, S. A. Wasimi & S. M. Rahman. 2021. Early weed detection using image processing and machine learning techniques in an Australian chilli farm. Agriculture, 11(5): 387.
Javaid, A., M. Sadiq & F. Akram. 2021. Skin cancer classification using image processing and machine learning. IBCAST. 439-444.
Lobus, N. V & M. S. Kulikovskiy. 2023. The Co-Evolution Aspects of the Biogeochemical Role of Phytoplankton in Aquatic Ecosystems: A Review. Biology, 12(1): 92.
Madduppa, H. 2020. Perbandingan Hasil Metode Identifikasi Spesies: Morfologi dan Molekuler Pada Ikan Julung-Julung Di TPI (Tempat Pelelangan Ikan) Muara Angke, DKI Jakarta. Jurnal Kelautan: Indonesian Journal of Marine Science and Technology. 13(3): 168-175.
Malahina, E. A. U., R. P. Hadjon & F. Y. Bisilisin. 2022. Teachable Machine: Real-Time Attendance of Students Based on Open Source System. IJICS. 6(3): 140-146.
Pranata, B. A., A. Hijriani & A. Junaidi. 2018. Perancangan Application Programming Interface (API) Berbasis Web Menggunakan Gaya Arsitektur Representational State Transfer (Rest) Untuk Pengembangan Sistem Informasi Administrasi Pasien Klinik Perawatan Kulit. Jurnal Komputasi, 6(1): 33-89.
Pratiwi, H. A., M. Cahyanti dan M. Lamsani. 2021. Implementasi Deep Learning Flower Scanner Menggunakan Metode Convolutional Neural Network. Sebatik. 25(1): 124-130.
Rimmer, M. A., S. Larson, I. Lapong, A. H. Purnomo, P. R. Pong-Masak, L. Swanepoel & N. A. Paul. 2021. Seaweed aquaculture in Indonesia contributes to social and economic aspects of livelihoods and community wellbeing. Sustainability. 13(19): 10946. https://doi.org/10.3390/su131910946.
Rudzicz, F., P. A. Paprica & M. Janczarski. 2019. Towards international standards for evaluating machine learning. In SafeAI@ AAAI. 2301(10).
Saleh, H & E. Sebastian. 2020. Seaweed Nation: Indonesia’s New Growth Sector; Backgrounder, No. 02/2020. VIC. Australia—Indonesia Centre: Caulfield East, Australia. 18 pp.
Saputra, D. D., Ilhamsyah dan D. Prawira. 2020. Implementasi Framework Accelerated Mobile Pages Pada Pengembangan Website Program Studi Sistem Informasi. Jurnal Komputer dan Aplikasi. 8(2): 67-78.
Sinurat, E., D. Fransiska, B. S. B. Utomo, S. Subaryono & N. Nurhayati. 2023. Characteristics of Powder Agar Extracted from Different Seaweeds Species and Locations. J Appl Phycol.
Schölkopf, B., F. Locatello, S. Bauer, N. R. Ke, N. Kalchbrenner, A. Goyal & Y. Bengio. 2021. Toward causal representation learning. IEEE, 109(5), 612-634.
Yusup, I. M., M. Iqbal dan I. Jaya. 2020. Real-time reef fishes identification using deep learning. In IOP Conference Series: Earth and Environmental Science. 429(1): 012046.
DOI: https://doi.org/10.22146/jfs.92955
Article Metrics
Abstract views : 923 | views : 362Refbacks
- There are currently no refbacks.
Copyright (c) 2024 Jurnal Perikanan Universitas Gadjah Mada
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Jurnal Perikanan Universitas Gadjah Mada (print ISSN 0853-6384; online ISSN 2502-5066) is published by Department of Fisheries, Universitas Gadjah Mada in collaboration with Semnaskan UGM (Seminar Nasional Tahunan Hasil Perikanan dan Kelautan) and ISMFR (International Symposium on Marine and Fisheries Research).
View My Stats