Article Per Year (5 Year)
p-Index From 2021 - 2026
2.907
P-Index
This Author published in this journals
All Journal Jurnal CoreIT JITK (Jurnal Ilmu Pengetahuan dan Komputer) Pendas : Jurnah Ilmiah Pendidikan Dasar JURNAL PENDIDIKAN TAMBUSAI IJISTECH (International Journal Of Information System & Technology) EQIEN - JURNAL EKONOMI DAN BISNIS Jurnal Infortech IJISTECH Tridharmadimas: Jurnal Pengabdian Kepada Masyarakat Jayakarta SPEED - Sentra Penelitian Engineering dan Edukasi Jurnal Abdimas Dosma Jurnal Ilmiah Teknik Informatika dan Komunikasi Socius: Social Sciences Research Journal Jurnal Pengabdian Masyarakat Jurnal Pengabdian Masyarakat dan Riset Pendidikan Seminar Nasional Riset dan Teknologi (SEMNAS RISTEK) Jurnal Abdimas Dosma
Imam Budiawan
Universitas Nusa Mandiri
Religion Agriculture, Biological Sciences & Forestry Arts Humanities Chemical Engineering, Chemistry & Bioengineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Engineering Environmental Science Health Professions Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Library & Information Science Mathematics Nursing Public Health Social Sciences Other

Published : 25 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 25 Documents
Search

 1   2   3 
Komparasi Algoritma Machine Learning (SVM, Random Forest, dan Regresi Logistik) untuk Prediksi Tingkat Obesitas Achmad Rivai Syahputra; Rian Hidayat; Fathur Rismansyah; Sumanto Sumanto; Imam Budiawan; Roida Pakpahan
Jurnal Ilmiah Teknik Informatika dan Komunikasi Vol. 5 No. 3 (2025): November: Jurnal Ilmiah Teknik Informatika dan Komunikasi 
Publisher : Lembaga Pengembangan Kinerja Dosen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55606/juitik.v5i3.1716

Abstract

Obesity is a global health issue with a continuously increasing prevalence. Early prediction of obesity levels is crucial for designing more effective intervention strategies. This study aims to apply and analyze the performance of three machine learning classification methods: Support Vector Machine (SVM), Random Forest (RF), and Logistic Regression (LR), for predicting obesity levels. The research methodology utilizes a public dataset, ObesityLevels, downloaded from the Kaggle platform, which consists of 2111 medical and lifestyle records. The process includes data preprocessing to convert categorical features into numerical ones, splitting the data into training and testing sets with a 70:30 ratio, model training, and evaluation using accuracy, precision, recall, and F1-score metrics. The results indicate that the Random Forest (RF) algorithm achieved the highest performance, with an accuracy of 90.3%, precision of 90.3%, recall of 90.3%, and an F1-score of 90.3%. Based on these findings, it is concluded that the Random Forest model is the most effective choice for an obesity level prediction system based on the dataset used.
Klasifikasi Penyakit Daun Tanaman Berbasis Citra Menggunakan Convolutional Neural Network Data Augmentation Suci, Bintang Dyas; Musfiroh, Musfiroh; Sefriani, Shintia Putriayu; Sumanto, Sumanto; Pakpahan, Roida; Budiawan, Imam
Semnas Ristek (Seminar Nasional Riset dan Inovasi Teknologi) Vol 10, No 1 (2026): SEMNAS RISTEK 2026
Publisher : Universitas Indraprasta PGRI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30998/semnasristek.v10i1.8894

Abstract

Penelitian ini membahas penerapan Convolutional Neural Network (CNN) yang dikombinasikan dengan teknik augmentasi data untuk klasifikasi penyakit daun tanaman berbasis citra. Permasalahan utama penelitian ini adalah keterbatasan jumlah data latih yang dapat memengaruhi kinerja model klasifikasi. Tujuan penelitian adalah mengevaluasi efektivitas augmentasi data dalam meningkatkan performa model CNN pada dataset berskala terbatas. Dataset yang digunakan adalah Plant Disease Recognition Dataset yang terdiri dari 1.523 citra dengan tiga kelas, yaitu Healthy, Powdery Mildew, dan Rust. Penelitian ini menggunakan metode eksperimen dengan tahapan praproses data, augmentasi data, pelatihan model, serta evaluasi performa yang seluruhnya dilakukan menggunakan Google Colab. Teknik augmentasi yang diterapkan meliputi rotasi, zoom, dan horizontal flip. Hasil penelitian menunjukkan bahwa model CNN mampu mencapai akurasi validasi yang baik, meskipun performa klasifikasi antar kelas masih bervariasi, khususnya pada kelas Rust yang memiliki karakteristik visual kompleks, sebagaimana ditunjukkan melalui confusion matrix dan classification report. Selain itu, penelitian ini mengimplementasikan skema prediksi real-time sebagai proof-of-concept. Secara keseluruhan, hasil penelitian menunjukkan bahwa kombinasi CNN dan augmentasi data efektif untuk klasifikasi penyakit tanaman pada kondisi keterbatasan data dan sumber daya komputasi.
Analisis Klaster Tingkat Stres Generasi Z Berdasarkan Pola Tidur dan Aktivitas Media Sosial Menggunakan Metode K-Means Clustering Putra, Imam Hanif; Nurrahman, Alvin; Saputra, Sabita Abigail; Sumanto, Sumanto; Budiawan, Imam; Pakpahan, Roida
Semnas Ristek (Seminar Nasional Riset dan Inovasi Teknologi) Vol 10, No 1 (2026): SEMNAS RISTEK 2026
Publisher : Universitas Indraprasta PGRI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30998/semnasristek.v10i1.8898

Abstract

Penelitian ini bertujuan untuk mengidentifikasi pola kecenderungan stres pada Generasi Z melalui analisis klaster berbasis perilaku tidur dan penggunaan media sosial. Data yang digunakan berasal dari dataset kesehatan mental publik tahun 2025 yang terdiri dari 5.000 data responden, dengan dua variabel utama yaitu durasi tidur harian dan lama penggunaan media sosial. Pendekatan kuantitatif eksploratori diterapkan menggunakan metode unsupervised learning, tanpa melibatkan label kelas. Proses analisis dilakukan melalui tahap pembersihan data, normalisasi, dan klasterisasi menggunakan algoritma K-Means yang diimplementasikan pada aplikasi Orange Data Mining. Penentuan jumlah klaster optimal dilakukan dengan evaluasi Silhouette Score, yang menunjukkan bahwa konfigurasi enam klaster memberikan kualitas pemisahan terbaik dibandingkan variasi klaster lainnya. Hasil klasterisasi memperlihatkan perbedaan karakteristik yang jelas antar kelompok, mulai dari individu dengan durasi tidur rendah dan penggunaan media sosial tinggi hingga kelompok dengan pola tidur lebih seimbang dan aktivitas digital lebih terkendali. Temuan ini menunjukkan bahwa kombinasi pola tidur dan intensitas penggunaan media sosial dapat digunakan sebagai indikator awal dalam memetakan potensi stres pada Generasi Z, serta menjadi dasar bagi penelitian lanjutan terkait kesehatan mental berbasis perilaku digital.
Pelatihan Dasar Ms.Power Point dalam Peningkatan Kreatifitas Presentasi bagi Staf dan Pengajar TKQ-TPQ Kecamatan Tanjung Priok Jakarta Utara Ummu Radiyah; Astriana Mulyani; Sidik; Imam Budiawan
JURNAL ABDIMAS DOSMA (JAD) Vol. 2 No. 2 (2023): JUNI
Publisher : IKATAN ALUMNI DOSEN MAGANG KEMENRISTEKDIKTI TAHUN ANGKATAN 2017

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70522/jad.v2i2.28

Abstract

The staff and teachers of TKQ/TPQ Kec. Tanjung Priok in their work activities is not proficient in using technology or applications that make work easier. The problems experienced include not being able to make creative presentation material. Based on the problems experienced by TKQ/TPQ staff and teachers in Tanjung Priok District, basic Ms. Power Point training was carried out to help find solutions to the problems they faced. Ms. Power Point basic training is held to make it easier for staff and teachers to be more able to use and apply technology in the work activities carried out. Ms. Power Point training can also help prepare creative and interesting presentation materials so that teaching and learning activities become dynamic and material can be conveyed by attracting the interest and attention of students and can be timely in disseminating teaching materials. The service method consists of survey stages, training, and evaluation stages. The results of the service show that the TKQ/TPQ staff and teachers, kec. Tanjung Priok can make presentation materials or teaching media that are effective and interesting.
ANALISIS SEGMENTASI PENGUNJUNG MENGGUNAKAN K-MEANS CLUSTERING BERDASARKAN MODEL RFM: STUDI KASUS PEGASUS KARTING CABANG PLUIT VILLAGE Nurul Isnayni; Imam Budiawan; Yumi Novita Dewi
Pendas : Jurnal Ilmiah Pendidikan Dasar Vol. 11 No. 03 (2026): Volume 11 Nomor 03, September 2026 Publish
Publisher : Program Studi Pendidikan Guru Sekolah Dasar FKIP Universitas Pasundan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23969/jp.v11i03.63269

Abstract

The experience-based entertainment industry, such as indoor karting, faces challenges in understanding customer behavior through a data-driven approach. Pegasus Karting at Pluit Village Mall recorded 1,833 transactions from 892 unique customers during October-December 2025 via its Smart TAG cashier system, yet this data remained underutilized for strategic decision-making. This study aims to implement K-Means Clustering based on the RFM (Recency, Frequency, Monetary) model to generate customer segments, analyze the characteristics of each segment, and formulate Customer Relationship Management (CRM) strategy recommendations and operational efficiency improvements. The methodology encompasses RFM value computation, Min-Max normalization, optimal cluster determination using the Elbow Method and Silhouette Score, and K-Means execution with k-means++ initialization. Results indicate that k = 3 is the optimal configuration, yielding a Silhouette Score of 0.5453 (above the 0.5 threshold), thus rejecting H₀ and accepting H₁. Segmentation produced two main groups: Champions (655 customers, 73.4%) with an average Recency of 24.25 days, Frequency of 2.2 visits, and Monetary of IDR 333,829, contributing 76.7% of total revenue; and Lost Customers (237 customers, 26.6%) with an average Recency of 77.83 days, contributing 23.3% of revenue. These findings serve as the basis for loyalty retention strategies for the Champions segment and win-back campaigns for Lost Customers.
Co-Authors Achmad Rivai Syahputra Ade Setiawan Ahmad Yusuf Amas Sari Marthanti Arfhan Prasetyo - STMIK Nusa Mandiri Arfhan Prasetyo - UBSI Astriana Mulyani Astriana Mulyani, Mulyani Bella - STMIK Nusa Mandiri Bella - UBSI Belsana Butar Butar Desmulyati, Desmulyati Dwi Arum Ningtyas FAHRIZAL Fathur Rismansyah Firstianty Wahyuhening Fibriany Gata, Windu Hani Harafani Hani Harafani, Hani Hari, Raga Suhada Henny Leidiyana Hoiriah Hoiriah I Ispandi Ika Kurniawati Imam Sujarwo ispandi ispandi Ispandi Ispandi Ispandi Ispandi, Ispandi Kiswanto, Andi Diah Martua HamiSiregar Muhammad Nasrulloh Mulyadi Mulyadi Mulyani, Astriana Musfiroh Musfiroh, Musfiroh Mushliha Nurrahman, Alvin Nurul Isnayni Pakpahan, Roida Prasetya, Arfhan Putra, Imam Hanif Rian Hidayat Rizky, Fernando Jovanca Roida Pakpahan Romdonni, Achmad Roddi Rusli, Ahmad Rais Saputra, Sabita Abigail Sefriani, Shintia Putriayu Sidik Sidik Sidik Sidik Sidik Sidik Suci, Bintang Dyas Sulistyowati, Daning Nur Sumanto Sumanto Sungkar, Adam Andrea Susan Rachmawati Ummu Radiyah Ummu Radiyah Ummu Radiyah, Ummu Wati Erawati Yasin, Saeful Yumi Novita Dewi Yuris Alkhalifi