Article Per Year (5 Year)
p-Index From 2021 - 2026
0.444
P-Index
This Author published in this journals
All Journal AMMA : Jurnal Pengabdian Masyarakat Journal of Mathematics, Computation and Statistics (JMATHCOS)
Eristia Arfi
Institut Teknologi Sumatera
Humanities Chemistry Law, Crime, Criminology & Criminal Justice Materials Science & Nanotechnology Mathematics Nursing

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Teknologi Smart Conservation Untuk Identifikasi Spesies Mangrove Di Kawasan Ekowisata Cuku Nyinyi, Lampung Triyana Muliawati; Fuji Lestari; Mika Alvionita Sitinjak; Eristia Arfi; Devia Gahana Cindi Alfian
AMMA : Jurnal Pengabdian Masyarakat Vol. 4 No. 1 : Februari (2025): AMMA : Jurnal Pengabdian Masyarakat
Publisher : CV. Multi Kreasi Media

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Mangroves are a type of forest ecosystem that grows in coastal areas along tropical and subtropical shores throughout Indonesia, particularly in Lampung Province. This ecosystem is found in regions influenced by tidal seawater. Mangroves consist of various species of trees, shrubs, and other plants that can survive in highly saline and muddy environments. Additionally, mangroves provide numerous benefits for environmental sustainability and human well-being. A healthy mangrove ecosystem contains diverse plant species with specific characteristics that help maintain ecological balance and ensure optimal ecological functions.Lampung Province has a mangrove ecotourism site located in Sidodadi Village, Teluk Pandan District, Pesawaran Regency, known as Cuku Nyinyi. Uniquely, Cuku Nyinyi is often used as a research and learning site for students, researchers, and the general public to study mangroves.One of the challenges faced by the ecotourism management team, the Bina Jaya Lestari Forest Farmers Group (KTH), is the difficulty in identifying and classifying mangrove species planted in the Cuku Nyinyi ecotourism area. Additionally, there is a lack of adequate information about mangroves, such as their age, anatomy, habitat, environmental adaptations, benefits, and other relevant details. To address this issue, researchers are developing an automatic identification system for mangrove species based on leaf morphology using a Convolutional Neural Network (CNN) approach. CNN is one of the most effective methods for pattern recognition in images and mangrove image processing. This technology is expected to be implemented in the form of a camera application that can automatically identify information from an image of mangrove leaf morphology captured in the Cuku Nyinyi ecotourism area.The Mangrove Camera Application provides new insights to KTH and the general public regarding the potential and importance of conserving natural resources.
Penerapan Algoritma K-Means Clustering dalam Memetakan Produktivitas Lokasi Perkebunan Nanas PT Great Giant Pineapple Anisa Fitriani; Eristia Arfi; Anwar Huda
Journal of Mathematics, Computations and Statistics Vol. 7 No. 2 (2024): Volume 07 Nomor 02 (Oktober 2024)
Publisher : Jurusan Matematika FMIPA UNM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35580/jmathcos.v7i2.4200

Abstract

Abstrak. PT Great Giant Pineapple (GGP) ialah perusahaan nanas terbesar di Indonesia. PT GGP memiliki tiga Plantation Group (PG) yang berfokus pada nanas proses. Pada PG terdapat lokasi-lokasi yang memiliki luas serta produktivitas yang berbeda-beda. Tujuan penelitian ini adalah untuk mengklaster lokasi pada PG dengan menggunakan algoritma k-means clustering kemudian menganalisis strategi untuk setiap klaster. Dalam menentukan jumlah klaster optimal penulis menerapkan metode elbow dan metode silhouette coefficient. Dari penerapan kedua metode diperoleh jumlah klaster yang optimal ketika . Dengan menggunakan diperoleh anggota untuk masing-masing PG secara berturut-turut, anggota klaster 1 sebanyak 134 lokasi, 166 lokasi, dan 115 lokasi kemudian anggota klaster 2 sebanyak 41 lokasi, 49 lokasi, dan 79 lokasi. Klaster lokasi yang memiliki produktivitas tinggi terdapat di klaster 1 pada PG 1 dan PG 2 kemudian klaster 2 pada PG 3. Kelompok lokasi yang memiliki produktivitas rendah terdapat di klaster 2 pada PG 1 dan PG 2 kemudian klaster 1 pada PG 3. Analisis strategi untuk klaster rendah yakni dengan melakukan manajemen air, pengendalian hama, pemupukan yang lebih efektif serta pengontrolan waktu forcing secara berkala serta pengawasan supaya tidak terjadi pencurian pada klaster yang memiliki produktivitas tinggi. Kata Kunci: Algoritma K-Means, Metode Elbow, Metode Silhouette Coefficient, PT GGP
Co-Authors Anisa Fitriani Anwar Huda Devia Gahana Cindi Alfian Fuji Lestari Mika Alvionita Sitinjak Muliawati