Article Per Year (5 Year)
p-Index From 2021 - 2026
0.817
P-Index
This Author published in this journals
All Journal Indonesian Journal of Artificial Intelligence and Data Mining Specta Journal of Technology Prosiding Seminar Nasional Pengabdian Kepada Masyarakat Pengabdian Kepada Masyarakat Bidang Teknologi dan Sistem Informasi
Rizky Amelia
Institut Teknologi Kalimantan
Humanities Chemical Engineering, Chemistry & Bioengineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Energy Engineering Environmental Science Public Health Other

Published : 4 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 4 Documents
Search

 1 
PENERAPAN AUTOMATIC WATERING BERBASIS KELEMBABAN PADALAHAN PERTANIAN KELOMPOK TANI RT 8 TERITIP LAUT Rizky Amelia; Boby Mugi Pratama; Trifani Arella Putra; Alzarfandy Fadillah Uzlifad; Farhan Ramadhani; Muhammad Asfian; Muhammad Gozy Al Vaiz
Prosiding Seminar Nasional Pengabdian Kepada Masyarakat Vol 3 (2022): PROSIDING SEMINAR NASIONAL PENGABDIAN KEPADA MASYARAKAT - SNPPM2022
Publisher : Lembaga Penelitian dan Pengabdian kepada Masyarakat Universitas Negeri Jakarta

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

Abstract

Abstract Information technology in agriculture that developed now leads to the study of control and automation systems. Artificial irrigation techniques are vital in Indonesian agriculture. The main disadvantage of conventional irrigation systems is the incalculable amount of water supplied to the plants; as a result, the plants do not receive the optimal amount of water for growth. Teritip Laut Village in East Balikpapan is one of the areas with high potential for plantations and agriculture due to its proximity to the coast and favorable natural conditions. The RT 8 Farmers Group took advantage of this circumstance by creating agricultural land that was planted with a variety of plants. Farmers face challenges in the irrigation process and the pump control system, which is still manual, resulting in lower crop yields due to less-than-optimal plant growth rates. This study was conducted to assist farmers in automatically monitoring soil moisture content in order to optimize crop yields. By allowing farmers to automate the process of irrigating their plants, an Arduinobased automatic watering system with a variable soil moisture sensor is applied on agricultural media belonging to the Farmers Group RT 8. Three FC-28 soil moisture sensors put in the agricultural area are coupled to an Arduino UNO-based microcontroller, which controls the system. One of the humidity sensors will detect the soil moisture value at a specific threshold, which will cause the Arduino UNO to activate a relay, turn on the water pump, and switch on numerous sprinklers that have been installed. When the threshold value recorded on the analog data value of the FC-28 sensor module is greater than 400, the soil condition is considered to be dry. Although an analog data reading value of less than 400 is regarded as a damp soil condition, it doesn't call for spray irrigation. Abstrak Teknologi informasi dalam bidang pertanian saat ini mengarah pada studi tentang sistem kontrol dan otomatisasi. Teknik pengairan buatan memainkan peranan penting dalam pertanian di Indonesia. Kelemahan utama dari sistem irigasi konvensional adalah tidak terhitungnya jumlah air yang disuplai ke tanaman, akibatnya tanaman tidak menerima jumlah air yang optimal untuk pertumbuhan. Kelurahan Teritip Laut di Balikpapan Timur adalah salah satu wilayah dengan potensi perkebunan dan pertanian yang cukup baik, karena berdekatan dengan daerah pesisir pantai dan didukung dengan kondisi alam yang baik. Kondisi tersebut dimanfaatkan oleh Kelompok Tani RT 8 dengan membuat lahan pertanian yang ditanami berbagai jenis tanaman. Dalam prosesnya, petani mendapati kendala pada proses pengairan dan sistem kendali pompa yang masih manual sehingga berpengaruh terhadap hasil panen sebagai akibat laju pertumbuhan tanaman yang kurang optimal. Studi ini dilakukan untuk membantu para petani agar dapat memantau kadar air tanah untuk mengoptimalkan hasil panen secara otomatis. Diterapkan automaticwatering system berbasis Arduino UNO dengan variabel sensor kelembaban tanah pada media pertanian milik Kelompok Tani RT 8 dengan memungkinkan para petani dapat mengotomatisasikan proses pengairan tanaman yang dimiliki. Sistem dikendalikan oleh sebuah mikrokontroler berbasis Arduino UNO yang terhubung dengan tiga buah sensor kelembaban tanah FC-28 yang dipasang di area pertanian. Pembacaan nilai kelembaban tanah yang berada pada nilai ambang tertentu pada salah satu sensor kelembaban akan membuat Arduino UNO memicu relay yang akan menghidupkan pompa air untuk mengalirkan air menujuke beberapa sprinkler yang telah terpasang. Kondisi tanah dikatakan kering ketika nilai ambang batas yang diperoleh pada nilai data analog modul sensor FC-28 lebih dari 400, sementara nilai bacaan data analog kurang dari 400 dianggap sebagai kondisi tanah yang basah sehingga tidak butuh penyiraman melalui sprinkler.
A RAG-Based Academic Information Chatbot Using Lightweight LLaMA and Indo-Sencence-BERT Muhamad Saman; Gusti Ahmad Fanshuri Alfarisy; Rizky Amelia; Nisa Rizqiza Fadhliana
Indonesian Journal of Artificial Intelligence and Data Mining Vol. 8 No. 3 (2025): November 2025
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

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

Abstract

In the current digital era, Institut Teknologi Kalimantan (ITK) encounters challenges in delivering academic information that is fast, accurate, and easily accessible to students, lecturers, and academic staff. Access to important information such as administrative procedures, report writing guidelines, and academic policies remains largely reliant on manual systems and static handbooks. To address this issue, this study investigates a chatbot system utilizing the Retrieval-Augmented Generation (RAG) framework through LLaMA model. The chatbot combines semantic retrieval and natural language generation to provide relevant and accurate answers based on existing academic documents. Evaluation was conducted on two lightweight LlaMA models: 1.5 and 3B parameters. Furthermore, different embedding vector also evaluated along with Indo-Sentence-BERT as well as the chunking size. The most optimal configuration was achieved using LLaMA 3B as the generative model and Indo-Sentence-BERT as the retriever, with a chunk size of 200 tokens and an overlap of 10 tokens. This setup achieved a RAGAS score of approximately 0.9, a competitive MRR of 0.5, and response latency under 1 second. Although LLaMA 1B recorded a higher MRR (0.6), its low RAGAS score made it less favorable. Overall, the LLaMA 3B and Indo-Sentence-BERT configuration is recommended to enhance the efficiency of academic information retrieval at ITK.
Implementasi Pembelajaran Berbasis Augmented Reality, Simulasi Pemilahan Sampah, dan Kreasi Kapal di SDN 006 Balikpapan Nisa Rizqiya Fadhliana; Rizky Amelia; Mahardika Arka; Olivia Dafina; Galuh Juliviana Romanita; Jonathan Riocardo Rawung; Sabina Danuwijaya Sinta; Yoga Adhi Nugroho; M. Shadiq Al-Fatiy; Vevrianto Pasudi; Dwi Nur Anggraeni; Cindytiara
Pengabdian kepada Masyarakat Bidang Teknologi dan Sistem Informasi (PETISI) Vol. 4 No. 1 (2026): Pengabdian Kepada Masyarakat Bidang Teknologi dan Sistem Informasi
Publisher : Mulawarman University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30872/petisi.v4i1.4773

Abstract

Pembelajaran konvensional di sekolah dasar masih sering membatasi keterlibatan aktif siswa dalam memahami materi lingkungan, keanekaragaman hayati, kemaritiman, serta pengembangan kreativitas. Kegiatan pengabdian kepada masyarakat ini bertujuan untuk mengimplementasikan pembelajaran terpadu berbasis digital dan praktik langsung melalui penggunaan media Augmented Reality, simulasi permainan edukatif pemilahan sampah, serta pembuatan kapal dari barang bekas. Kegiatan dilaksanakan di SD Negeri 006 Balikpapan Timur dengan sasaran siswa kelas V. Metode pelaksanaan meliputi tahap persiapan media, pelaksanaan tiga program utama, serta evaluasi melalui perbandingan hasil pre-test dan post-test secara deskriptif. Hasil kegiatan menunjukkan adanya peningkatan pemahaman siswa terhadap hewan khas Indonesia, konsep kemaritiman, jenis-jenis sampah, serta cara memilah sampah sesuai kategorinya. Penggunaan game Augmented Reality membantu siswa memahami materi secara lebih visual dan interaktif, sedangkan simulasi game edukasi mendorong siswa untuk belajar memilah sampah melalui aktivitas yang menyenangkan. Selain itu, kegiatan pembuatan kapal dari barang bekas mampu melatih kreativitas, kerja sama, keterampilan motorik, dan kesadaran siswa terhadap pemanfaatan kembali bahan sederhana di lingkungan sekitar. Dengan demikian, integrasi teknologi digital, game edukasi, dan pembelajaran berbasis pengalaman langsung dapat menjadi model pembelajaran yang menarik, kontekstual, dan aplikatif bagi siswa sekolah dasa
Klasifikasi Penyakit Daun Tanaman Menggunakan MobileNetV4 Berbasis Transfer Learning: 116 - 131 Syifa Maulida; Tito Ariffianto Miftahul Huda; Wafiq Ajriyah; Rizky Amelia; Gusti Ahmad Fanshuri Alfarisy
SPECTA Journal of Technology Vol. 10 No. 2 (2026): Specta Journal of Technology
Publisher : LPPM ITK

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35718/specta.v10i2.8481436

Abstract

Image-based plant leaf disease classification has become an important focus in agriculture to reduce significant losses and improve crop quality. This study proposes the use of Convolutional Neural Network (CNN) with MobileNetV4 architecture for plant leaf disease classification using transfer learning. MobileNetV4 was chosen because of its efficient ability to recognize visual objects with a light number of parameters, making it suitable for implementation on devices with limited resources. The dataset used is PlantVillage, which contains 20,600 labeled images across 15 disease categories. By using MobileNetV4 pre-trained on ImageNet, and modifying the final layers, we achieved a classification accuracy of 99.47%. This approach shows high potential for practical implementation on mobile devices due to its computational efficiency.
Co-Authors Alzarfandy Fadillah Uzlifad Boby Mugi Pratama Cindytiara Dwi Nur Anggraeni Farhan Ramadhani Galuh Juliviana Romanita Gusti Ahmad Fanshuri Alfarisy Jonathan Riocardo Rawung M. Shadiq Al-Fatiy Mahardika Arka Muhamad Saman Muhammad Asfian Muhammad Gozy Al Vaiz Nisa Rizqiya Fadhliana Nisa Rizqiza Fadhliana Olivia Dafina Sabina Danuwijaya Sinta Syifa Maulida Tito Ariffianto Miftahul Huda Trifani Arella Putra Vevrianto Pasudi Wafiq Ajriyah Yoga Adhi Nugroho