Article Per Year (5 Year)
p-Index From 2019 - 2024
1.152
P-Index
This Author published in this journals
All Journal Journal of Information Technology and Computer Science (JOINTECS) Produktif : Jurnal Ilmiah Pendidikan Teknologi Informasi ILKOM Jurnal Ilmiah Komputasi: Jurnal Ilmiah Ilmu Komputer dan Matematika Progresif: Jurnal Ilmiah Komputer INTI Nusa Mandiri
Muhammad Rafi Muttaqin
Sekolah Tinggi Teknologi Wastukancana
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Education Electrical & Electronics Engineering Engineering Languange, Linguistic, Communication & Media Library & Information Science Mathematics Social Sciences

Published : 6 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 6 Documents
Search

 1 
Penerapan K-Means Clustering dan Cross-Industry Standard Process For Data Mining (CRISP-DM) untuk Mengelompokan Penjualan Kue Muhammad Rafi Muttaqin; Teguh Iman Hermanto; Muhamad Agus Sunandar
Komputasi: Jurnal Ilmiah Ilmu Komputer dan Matematika Vol 19, No 1 (2022): Komputasi: Jurnal Ilmiah Ilmu Komputer dan Matematika
Publisher : Ilmu Komputer, FMIPA, Universitas Pakuan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33751/komputasi.v19i1.3976

Abstract

Cake is a food that doesn’t have long durability. This will cause the cake producer to suffer a losses if the product is not sold out at the expiration date. With the availability of cake sales data, the sales potential will be clustered according to the date of sale using K-Means method. The data mining process used in this study is Cross-Industry Standard Process for Data Mining (CRISP-DM). The results obtained are the formation of agroup of cake sales that man consumers buy on each date. This grouping is divided into three, namely low, medium, and high sales. This will help producers to prepare their products more effectively and efficiently so as to reduce wasteful production. If the cake is in the low sales group, the number of cake products is small. On the contrary, if there is a cake that goes into high sales group, then the producer will produce the cake in large quantities.
Algoritma K-Means untuk Pengelompokan Topik Skripsi Mahasiswa Muhammad Rafi Muttaqin; Meriska Defriani
ILKOM Jurnal Ilmiah Vol 12, No 2 (2020)
Publisher : Teknik Informatika Fakultas Ilmu Komputer Univeristas Muslim Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33096/ilkom.v12i2.542.121-129

Abstract

In helping to develop technology in the field of education as well as bringing about a major change in competitiveness between individuals and groups, to be able to do so requires sufficient information and data to be analyzed further. In this case STT Wastukancana Purwakarta is under the auspices of Bunga Bangsa Foundation, seeing that STT Wastukancana Purwakarta students have several obstacles in their final project, one of which is difficult in determining the topic of the thesis title to be made so that sometimes the topic of the thesis title taken is not in accordance with their abilities each student. This problem can be overcome by applying the clustering method. The analytical method used is Knowledge Discovery in Database (KDD). The method of grouping students uses the clustering method and the K-Means algorithm as a clustering calculation where the Clustering aims to divide students into clusters based on grades obtained from semester 1 to 7, so as to produce student recommendations in taking thesis topics. The tool used to implement the algorithm is Rapidminer. The results of this study are grouping students according to their expertise, which is obtained based on the cluster that has the highest score and is dominated by the most subjects according to the subjects that have been grouped by each expertise. So, the results of this cluster are used as a reference for students to take the thesis title topic.
SISTEM COMPUTER SUPPORTED COLLABORATIVE LEARNING UNTUK PENINGKATAN PEMBELAJARAN MAHASISWA Muhammad Rafi Muttaqin; Ismi Kaniawulan; Defryan Tri Gusman
Produktif : Jurnal Ilmiah Pendidikan Teknologi Informasi Vol. 3 No. 1 (2019): PRODUKTIF: Jurnal Ilmiah Pendidikan Teknologi Informasi
Publisher : Program Studi Pendidikan Teknologi Informasi

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

Abstract

Perubahan tata cara interaksi dalam proses pendidikan mengalami pergeseran dari konvensional menjadi online. Computer Supported Collaborative Learning merupakan cabang ilmu yang mempelajari bagaimana manusia dapat berinteraksi dan belajar bersama dengan menggunakan teknologi komputer. Permasalahan muncul ketika proses pembelajaran mahasiswa harus dilakukan secara kelompok namun terkendala oleh jarak dan waktu. Tujuan dari penelitian ini adalah merancang sebuah sistem computer supported collaborative learning sehingga dapat meningkatkan pembelajaran mahasiswa. Metoda pengembangan sistem dengan model waterfall. Hasil dari penelitian adalah sistem computer supported collaborative learning.
SISTEM PAKAR DIAGNOSA PENYAKIT PADA DOMBA DENGAN MENGGUNAKAN METODE FUZZY MAMDANI Cucu Kardila; Muhammad Rafi Muttaqin; Mochzen Gito Resmi
INTI Nusa Mandiri Vol 18 No 1 (2023): INTI Periode Agustus 2023
Publisher : Lembaga Penelitian dan Pengabdian Pada Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/inti.v18i1.4314

Abstract

Abstract—The decreasing sheep population has raised serious concerns regarding its impact on both the livestock industry and export opportunities. One of the main factors contributing to this decline is the prevalence of diseases among sheep. These illnesses present a significant problem as they can lead to reduced meat production, animal fatalities, and economic losses. The limited knowledge among farmers regarding these diseases and sheep care makes it challenging to diagnose and treat the conditions effectively. To address this issue and aid farmers in easily diagnosing diseases, a web-based expert system utilizing the fuzzy Mamdani method was developed. The selection of the fuzzy Mamdani method was based on its ability to handle uncertainty in disease diagnosis, providing reasonably accurate results by evaluating symptoms, determining disease severity, and recommending appropriate treatments. Through the fuzzy Mamdani method and the web-based platform, this system offers convenient access for farmers to diagnose diseases in their sheep online. According to the analysis results, reproductive health disorders are the primary cause of the decline in the sheep population. Consequently, the expert system for diagnosing sheep diseases serves as an alternative for early prevention and suitable treatment. System testing indicates an accuracy rate of 80%, signifying the system's capability to provide reasonably accurate diagnoses. The main goal of this research is to support the livestock and fisheries department in Purwakarta in diagnosing sheep diseases, preventing epidemic outbreaks, and implementing proper measures to mitigate the negative impacts on the livestock industry while promoting sustainable growth of the sheep population
Klasifikasi Citra Mutu Kemasan Menggunakan Metode Convolutional Neural Network Dengan Arsitektur MobileNetV2 Kus Irawan Indra Saputra; Muhammad Rafi Muttaqin; Teguh Iman Hermanto
Progresif: Jurnal Ilmiah Komputer Vol 19, No 2: Agustus 2023
Publisher : STMIK Banjarbaru

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35889/progresif.v19i2.1411

Abstract

Product packaging is an important component. Packaging has an impact on product identification, quality, and competitiveness. The outer appearance of the product’s packaging affects how consumers see it. Inspection and classification of packaging is an important factor in determining whether the packaging is good or not for the quality of the products, food, and beverages packaged. The packaging used to pack food and beverages is good packaging that requires inspection. This study uses MobileNetV2 architecture with Deep Learning techniques in the classification of packaging quality, which is grouped into two classes: Good and Not Good. Each class is divided into 3 parts: training, validation, and test data, with a ratio of 80:10:10. From the implementation of MobileNetV2 architecture in the classification of packaging quality, an accuracy of 98% was obtained. It was concluded that the classification of packaging quality with the architecture of MobileNetV2 has good and accurate accuracy. Kata kunci: Packaging; Inspection; Classification; MobileNetV2; Deep Learning AbstrakKemasan produk adalah komponen penting. Kemasan memiliki dampak pada identifikasi, kualitas, dan daya saing produk. Tampilan luar kemasan produk mempengaruhi bagaimana konsumen melihatnya. Inspeksi dan klasifikasi kemasan adalah faktor penting dalam menentukan kemasan tersebut bagus dan tidak bagus untuk menjaga kualitas produk dan makanan dan minuman yang dikemas. Kemasan yang digunakan untuk mengemas makanan dan minuman merupakan kemasan yang bagus sehingga diperlukan inspeksi terhadap kemasan tersebut. Pada penelitian ini menggunakan arsitektur MobileNetV2 dengan teknik Deep Learning dalam klasifikasi mutu kemasan yang dikelompokkan menjadi 2 kelas yaitu Good dan Not Good. Setiap kelas dibagi menjadi 3 data yaitu data latih, validasi dan test dengan rasio 80:10:10. Dari hasil implementasi arsitektur MobileNetV2 dalam mengklasifikasi mutu kemasan diperoleh nilai akurasi sebesar 98%. Didapatkan kesimpulan bahwa klasifikasi mutu kemasan dengan arsitektur MobileNetV2 memiliki akurasi yang baik dan akurat.Kata kunci: Kemasan; Inspeksi; Klasifikasi; MobileNetV2; Deep Learning 
Klasifikasi Penyakit Pada Daun dan Buah Jambu Menggunakan Convolutional Neural Network Fadlan Sayyidul Anam; Muhammad Rafi Muttaqin; Yudhi Raymond Ramadhan
JOINTECS (Journal of Information Technology and Computer Science) Vol 8, No 3 (2023)
Publisher : Universitas Widyagama Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31328/jointecs.v8i3.4823

Abstract

Jambu biji merupakan komoditas tanaman di Jawa Barat dengan jumlah produksi tahun 2021 mencapai 692.488 kuintal. Produksi ini mengalami penurunan sebesar -12,82% dibandingkan dengan tahun 2020 yang sebesar 794.345 kuintal. Penelitian menggunakan teknologi deep learning dengan algoritma Convolutional Neural Network (CNN) dan berarsitektur MobileNetV2 untuk melakukan klasifikasi citra digital daun dan buah jambu biji yang telah diberi label atau disebut supervised learning. Metode pengembangan yang digunakan dalam penelitian ini adalah Cross Industry Standard Process for Data Mining (CRISP-DM). Berdasarkan hasil penelitian ini, model daun jambu biji memiliki hasil evaluasi yang sangat baik, training accuracy sebesar 99,6%, validation accuracy 100%, training loss 3,2%, dan validation loss 3,1%. Confusion matrix model ini memiliki akurasi 100% dari 63 data validasi. Sementara itu, model buah jambu biji memerlukan dropout sebesar 0,2 dan kernel regularizers L2 sebesar 0,01 untuk mengurangi overfitting. Model ini memiliki training accuracy sebesar 98,8%, validation accuracy 91,6%, training loss 19,1%, dan validation loss 38,6%. Hasil confusion matrix menunjukkan akurasi model ini mencapai 91,6% dari 84 data validasi. Kemudian model berhasil diimplementasikan menjadi aplikasi berbasis mobile menggunakan bahasa pemrograman Kotlin.
Co-Authors Cucu Kardila Defryan Tri Gusman Fadlan Sayyidul Anam Ismi Kaniawulan, Ismi Kus Irawan Indra Saputra Meriska Defriani Mochzen Gito Resmi Muhamad Agus Sunandar Teguh Iman Hermanto Yudhi Raymond Ramadhan