Rancang bangun sistem kontrol otomatis akuakultur untuk optimasi produksi pada budidaya ikan patin dengan algoritma random forest

Sumaryono, Rendy Febrian (2025) Rancang bangun sistem kontrol otomatis akuakultur untuk optimasi produksi pada budidaya ikan patin dengan algoritma random forest. Sarjana thesis, UIN Sunan Gunung Djati Bandung.

Preview	Text 1_COVER.pdf Download (23kB) | Preview
Preview	Text Surat Pernyataan Karya Sendiri (10).pdf Download (419kB) | Preview
Preview	Text 2_ABSTRAK.pdf Download (41kB) | Preview
Preview	Text 4_Daftar Isi.pdf Download (79kB) | Preview
Preview	Text 5_BAB 1.pdf Download (314kB) | Preview
	Text 6_BAB 2.pdf Restricted to Registered users only Download (1MB) | Request a copy
	Text 7_BAB 3.pdf Restricted to Registered users only Download (311kB) | Request a copy
	Text 8_BAB 4.pdf Restricted to Registered users only Download (2MB) | Request a copy
	Text 9_BAB 5.pdf Restricted to Registered users only Download (1MB) | Request a copy
	Text 10_BAB 6.pdf Restricted to Registered users only Download (43kB) | Request a copy
	Text 11_DAFTAR PUSTAKA.pdf Restricted to Registered users only Download (417kB) | Request a copy
	Text 12_LAMPIRAN.pdf Restricted to Repository staff only Download (2MB) | Request a copy

Abstract

Patin fish farming is one of the fisheries sectors that has great potential to be developed. However, non-optimal pond water quality is often a factor inhibiting fish growth and productivity. Therefore, this research aims to design and implement an aquaculture automatic control system based on water quality monitoring using random forest algorithm, in order to increase the growth of catfish production. The developed system utilizes pH (SEN 0601), temperature (DS18B20), TDS (Total Dissolved Solids) meter V1.0, and turbidity sensors to monitor water conditions in real-time. Data from the sensors is sent using ESP32 to an Express.js-based web application that is capable of displaying data in graphical form, performing automatic control actions such as feeding and water management, and saving data in Excel format. Random forest algorithm is applied to classify water quality conditions into three categories, namely good, normal, and bad, with the average accuracy reaching 96%, average precision 95.61%, average recall 96%, and average F1-score 95.55%. Testing was conducted for 3 months on two ponds (automatic and conventional). The results showed that fish in ponds using the IOT system experienced an increase in weight up to 310 grams with brighter body color. In contrast, fish in conventional ponds only reached a weight of 290 grams with a paler body color. With these results, the designed automatic control system proved effective in improving water quality, accelerating fish growth, and optimizing production in catfish farming.

Actions (login required)

View Item