Nasiroh, Nimas Rorun (2025) Classification Of Wild Plants As Medical Plants Using Convolutional Neural Network Method For Assisting Healthcare Professionals In Treatment. Undergraduate thesis, Politeknik Negeri Jember,.
![[img]](https://sipora.polije.ac.id/style/images/fileicons/text.png) |
Text (Abstract)
Abstract.pdf - Submitted Version Available under License Creative Commons Attribution Share Alike. Download (227kB) |
|
Text (Bab 1 Pendahuluan)
BAB 1.pdf Available under License Creative Commons Attribution Share Alike. Download (169kB) |
|
Text (Daftar Pustaka)
Daftar Pustaka.pdf - Submitted Version Available under License Creative Commons Attribution Share Alike. Download (190kB) |
|
Text (Laporan Lengkap)
Laporan Lengkap 1.pdf - Submitted Version Restricted to Registered users only Download (4MB) | Request a copy |
Abstract
This study presents the design and development of HerbaClass, a mobile application utilizing Convolutional Neural Networks (CNN) with DenseNet121 architecture to classify wild plants as medicinal plants, aimed at supporting healthcare in remote areas of Indonesia. Leveraging Indonesia’s rich biodiversity, HerbaClass addresses challenges in manual plant identification, including visual similarities among species, lack of processing guidance, and difficulties in real-time plant location. HerbaClass enables users to capture or upload leaf images, providing accurate classifications, step by step processing instructions, and geolocation-based plant detection. The DenseNet121 model, trained on a dataset of 1,370 leaf images from six medicinal plant species, achieved a classification accuracy of 95%. Usability tests and surveys with 51 respondents, including pharmacists and the general public, confirmed HerbaClass’s effectiveness, with 64.7% valuing its community-driven data collection potential. The system’s multilingual support (Indonesian, Malay, English) and offline capability enhance accessibility in low-connectivity environments, making it a practical tool for alternative healthcare.
| Item Type: | Thesis (Undergraduate) | ||||||
|---|---|---|---|---|---|---|---|
| Contributors: |
|
||||||
| Uncontrolled Keywords: | CNN, DenseNet121, Medicinal Plants, Mobile Application, Remote Healthcare | ||||||
| Subjects: | 140 - Rumpun Ilmu Tanaman > 150 - Ilmu Pertanian dan Perkebunan > 156 - Pemuliaan Tanaman 340 - Rumpun Ilmu Kesehatan > 350 - Ilmu Kesehatan Umum > 351 - Kesehatan Masyarakat 340 - Rumpun Ilmu Kesehatan > 400 - Ilmu Farmasi > 401 - Farmasi Umum dan Apoteker 410 - Rumpun Ilmu Teknik > 450 - Teknik Elektro dan Informatika > 458 - Teknik Informatika 340 - Rumpun Ilmu Kesehatan > 350 - Ilmu Kesehatan Umum > Sistem Informasi Kesehatan |
||||||
| Divisions: | Jurusan Teknologi Informasi > Prodi D4 Teknik Informatika > Tugas Akhir | ||||||
| Depositing User: | Nimas Rorun Nasiroh | ||||||
| Date Deposited: | 11 Sep 2025 07:09 | ||||||
| Last Modified: | 11 Sep 2025 07:09 | ||||||
| URI: | https://sipora.polije.ac.id/id/eprint/46833 |
Actions (login required)
 |
View Item |
