SUWANDI, MUHAMMAD AFIF (2023) KOMPARASI ALGORITMA KLASIFIKASI UNTUK DETEKSI MANGROVE PADA AREA TERKENA ABRASI DENGAN MENGGUNAKAN SUPPORT VECTOR MACHINE (SVM) DAN NAÏVE BAYES (Studi Kasus: Pantai Muara Gembong Bekasi, Jawa Barat. S1 thesis, Universitas Mercu Buana Bekasi.
|
Text
41819210022-Muhammad Afif S-01 Cover.pdf Download (861kB) | Preview |
|
|
Text
41819210022-MUHAMMAD AFIF S-02 Abstrak.pdf Download (96kB) | Preview |
|
![[img]](https://repository.mercubuana.ac.id/style/images/fileicons/text.png) |
Text
41819210022-MUHAMMAD AFIF S-03 BAB 1.pdf Restricted to Registered users only Download (97kB) |
|
|
Text
41819210022-MUHAMMAD AFIF S-04 BAB 2.pdf Restricted to Registered users only Download (382kB) |
|
|
Text
41819210022-MUHAMMAD AFIF S-05 BAB 3.pdf Restricted to Registered users only Download (121kB) |
|
|
Text
41819210022-MUHAMMAD AFIF S-06 BAB 4.pdf Restricted to Registered users only Download (255kB) |
|
|
Text
41819210022-MUHAMMAD AFIF S-07 BAB 5.pdf Restricted to Registered users only Download (23kB) |
|
|
Text
41819210022-MUHAMMAD AFIF S-08 Daftar Pustaka.pdf Restricted to Registered users only Download (221kB) |
|
|
Text
41819210022-MUHAMMAD AFIF S-9 Lampiran.pdf Restricted to Registered users only Download (70kB) |
Abstract
Penelitian ini memperkenalkan pendekatan baru untuk pemrosesan gambar menggunakan Leveraging Naive Bayes untuk Seleksi Fitur dalam SVM dengan Kernel Polinomial. Fokusnya adalah pada ekstraksi fitur Normalized Difference Vegetation Index (NDVI), yang sangat penting untuk analisis vegetasi dan pemantauan lingkungan. Dengan menggabungkan Naive Bayes dan SVM dengan Polynomial Kernel, metode yang diusulkan dapat meningkatkan akurasi dan efisiensi tugas klasifikasi citra. Tinjauan literatur yang komprehensif menetapkan dasar-dasar teori dan metodologi yang terkait dengan pendekatan ini. Artikel penelitian utama dan makalah akademis dianalisis untuk mengidentifikasi keuntungan, tantangan, dan aplikasi potensial. Evaluasi eksperimental menggunakan dataset gambar dunia nyata menunjukkan keunggulan pendekatan yang diusulkan dalam hal akurasi klasifikasi dan efisiensi komputasi. Studi perbandingan dengan teknik tradisional dan algoritme alternatif semakin memvalidasi keefektifannya. Memasukkan Naive Bayes sebagai komponen pemilihan fitur dalam kerangka kerja SVM mengurangi kompleksitas komputasi dan memilih fitur yang relevan dari dataset NDVI. Pendekatan ini memiliki potensi yang signifikan untuk memajukan pemrosesan citra dan analisis vegetasi, berkontribusi pada pengembangan teknik inovatif di lapangan. Integrasi Naive Bayes dan SVM. Kata Kunci—Feature Selection, Image Processing, Leveraging Naive Bayes, NDVI Feature Extraction, SVM This paper introduces a novel approach for image processing using Leveraging Naive Bayes for Feature Selection in SVM with Polynomial Kernel. The focus is on extracting Normalized Difference Vegetation Index (NDVI) features, which are essential for vegetation analysis and environmental monitoring. By combining Naive Bayes and SVM with Polynomial Kernel, the proposed method enhances the accuracy and efficiency of image classification tasks. A comprehensive literature review establishes the theoretical foundations and methodologies related to this approach. Key research articles and academic papers are analyzed to identify advantages, challenges, and potential applications. Experimental evaluations using real-world image datasets demonstrate the superiority of the proposed approach in terms of classification accuracy and computational efficiency. Comparative studies with traditional techniques and alternative algorithms further validate its effectiveness. Incorporating Naive Bayes as a feature selection component within the SVM framework reduces computational complexity and selects relevant features from the NDVI dataset. This approach holds significant potential for advancing image processing and vegetation analysis, contributing to the development of innovative techniques in the field. The integration of Naive Bayes and SVM with Polynomial Kernel offers a promising solution for efficient feature selection, enhancing the overall performance of image classification systems. Further exploration and application in image analysis and environmental monitoring domains are encouraged. Keywords— Feature Selection, Image Processing, Leveraging Naive Bayes, NDVI Feature Extraction, SVM
| Item Type: | Thesis (S1) |
|---|---|
| Call Number CD: | FIK/SI 23 030 |
| NIM/NIDN Creators: | 41819210022 |
| Uncontrolled Keywords: | Feature Selection, Image Processing, Leveraging Naive Bayes, NDVI Feature Extraction, SVM |
| Subjects: | 000 Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 000. Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 000.01-000.09 Standard Subdivisions of Computer Science, Information and General Works/Subdivisi Standar Dari Ilmu Komputer, Informasi, dan Karya Umum |
| Divisions: | Fakultas Ilmu Komputer > Sistem Informasi |
| Depositing User: | siti maisyaroh |
| Date Deposited: | 04 Oct 2023 05:23 |
| Last Modified: | 04 Oct 2023 05:23 |
| URI: | http://repository.mercubuana.ac.id/id/eprint/81908 |
Actions (login required)
 |
View Item |
