Penataan Potensi Pertanian Sektor Tanaman Pangan Menggunakan Algoritma Svm Dan Regresi Linear Dengan Data Historis Jawa Timur

Ibrohim, Huzaimi (2023) Penataan Potensi Pertanian Sektor Tanaman Pangan Menggunakan Algoritma Svm Dan Regresi Linear Dengan Data Historis Jawa Timur. Undergraduate Thesis thesis, Institut Teknologi Telkom Purwokerto.

	Text 1. Cover Asli.pdf Download (1MB)
	Text 3. ABSTRACT.pdf Download (7kB)
	Text 2. ABSTRAK.pdf Download (6kB)
	Text 4. BAB 1.pdf Download (16kB)
	Text 5. BAB2.pdf Download (227kB)
	Text 6. BAB3.pdf Download (518kB)
	Text 7. BAB4.pdf Restricted to Registered users only Download (962kB) | Request a copy
	Text 8. BAB5.pdf Download (10kB)
	Text 9. DAFPUS.pdf Download (88kB)
	Text 10. LAMPIRAN.pdf Restricted to Registered users only Download (220kB) | Request a copy

Abstract

The production of food crops in the agricultural sector plays a crucial role in providing food security and contributing to the economy. However, in 2021, the food crop sector in Indonesia experienced a decline of -1.56% in the Gross Domestic Product (GDP), influenced by various factors such as adverse weather conditions, suboptimal land management, and socio-economic challenges faced by farmers. One ongoing issue is the tendency of farmers to cultivate crops based on market demand without considering the climatic conditions that affect crop productivity. To address this problem, this research will employ the Support Vector Machines (SVM) algorithm for crop classification and the Linear Regression algorithm for predicting yield. The dataset required for this study consists of 252 records, encompassing crop yields and climate data such as rainfall and temperature. The modeling results using the SVM algorithm show an accuracy of 80% in the model scheme with outlier data, while the Linear Regression algorithm yields a Mean Absolute Error (MAE) value of 0.11 in the model scheme with outlier data. Keywords: Machine Learning, Food Crops, Linear Regression, SVM, Classification, Regression

Actions (login required)

View Item