PENGGOLONGAN KONDISI TANAH PADA HASIL MONITORING SMART FARMING MENGGUNAKAN ALGORITMA SVM

DAMAYANTI, AYU and Ubaya, Huda and Sukemi, Sukemi (2025) PENGGOLONGAN KONDISI TANAH PADA HASIL MONITORING SMART FARMING MENGGUNAKAN ALGORITMA SVM. Undergraduate thesis, Sriwijaya University.

Preview	Image RAMA_56201_09011482326005_cover.jpg - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (91kB) | Preview
	Text RAMA_56201_09011482326005.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_56201_09011482326005_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (6MB) | Request a copy
	Text RAMA_56201_09011482326005_0216068101_0003126604_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (580kB)
	Text RAMA_56201_09011482326005_0216068101_0003126604_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (5MB) | Request a copy
	Text RAMA_56201_09011482326005_0216068101_0003126604_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (6MB) | Request a copy
	Text RAMA_56201_09011482326005_0216068101_0003126604_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (4MB) | Request a copy
	Text RAMA_56201_09011482326005_0216068101_0003126604_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (265kB) | Request a copy
	Text RAMA_56201_09011482326005_0216068101_0003126604_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_56201_09011482326005_0216068101_0003126604_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (357kB) | Request a copy

Abstract

This research aims to develop a model capable of predicting soil condition classification based on datasets obtained from smart farming monitoring devices using the Support Vector Machine (SVM) algorithm. The dataset includes attributes such as air temperature, air humidity, soil moisture, soil higrow, light intensity, and battery level. The classification process utilizes the Kingma formula to categorize soil conditions into three classes: “dry,” “normal,” and “moist.” The modeling process involves several stages: data preprocessing, feature selection, handling of imbalanced data, model training using all SVM kernels (linear, polynomial, RBF, and sigmoid), and performance evaluation using accuracy, precision, recall, F1- score, and confusion matrix metrics. In addition, the learning curve is used to assess model performance as the training dataset size increases. The results show that the linear SVM model delivers the best performance, achieving an accuracy of 99.8952%, precision of 99.8955%, recall of 99.8952%, and an F1-score of 99.8952%. This model has the potential to support automated decision-making in irrigation management and crop selection based on soil conditions.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Support Vector Machine, Penggolongan Kondisi Tanah, Machine Learning, Kelembapan Tanah, Rumus Kingma
Subjects:	T Technology > T Technology (General) > T1-995 Technology (General)
Divisions:	09-Faculty of Computer Science > 56201-Computer Systems (S1)
Depositing User:	Ayu Damayanti
Date Deposited:	13 Jun 2025 05:42
Last Modified:	13 Jun 2025 05:42
URI:	http://repository.unsri.ac.id/id/eprint/175484

Actions (login required)

View Item