Skripsi

PENGGOLONGAN KONDISI TANAH PADA HASIL MONITORING SMART FARMING MENGGUNAKAN ALGORITMA SVM

---

Penilaian

---

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.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2507003381	T175484	T1754842025	Central Library (Reference)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T1754842025

Publisher

Indralaya : Prodi Sistem Komputer, Fakultas Ilmu Komputer Universitas Sriwijaya., 2025

Collation

xv, 94 hlm., ilus., tab.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

004.07

Content Type

Text

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Sistem komputer

Specific Detail Info

-

Statement of Responsibility

MI

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment