Article Per Year (5 Year)
p-Index From 2021 - 2026
3.673
P-Index
This Author published in this journals
All Journal Jurnal Informatika dan Teknik Elektro Terapan Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Information Management For Educators And Professionals (IMBI) JURSIMA (Jurnal Sistem Informasi dan Manajemen) E-Link: Jurnal Teknik Elektro dan Informatika Jurnal Ilmu Komputer dan Teknologi (IKOMTI) Prosiding Seminar Nasional Sisfotek (Sistem Informasi dan Teknologi Informasi) PROSISKO : Jurnal Pengembangan Riset dan observasi Rekayasa Sistem Komputer Journal of Artificial Intelligence and Engineering Applications (JAIEA) Journal of Student Research Jurnal Riset Manajemen, Bisnis, Akuntansi dan Ekonomi (JAMBAK) JURSIMA Sintek Kuwera
Irfan Ali
Unknown Affiliation
Humanities Automotive Engineering Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Energy Engineering Library & Information Science Mechanical Engineering Public Health Social Sciences Other

Published : 23 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 23 Documents
Search

 1   2   3 
ANALISIS DATA PENJUALAN MENGGUNAKAN ALGORITMA K-MEANS CLUSTERING PADA TOKO KECANTIKAN PUTRI Agung Prayogo Bagustio; Ade Irma Purnamasari; Irfan Ali
PROSISKO: Jurnal Pengembangan Riset dan Observasi Sistem Komputer Vol. 11 No. 2 (2024): Prosisko Vol. 11 No. 2 September 2024
Publisher : Pogram Studi Sistem Komputer Universitas Serang Raya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30656/prosisko.v11i2.7928

Abstract

Abstrak - Industri kecantikan mengalami pertumbuhan pesat dalam beberapa tahun terakhir, mendorong tingginya permintaan produk kecantikan. Toko Kecantikan Putri merupakan salah satu toko kecantikan yang berkembang pesat di wilayah Cirebon. Untuk meningkatkan strategi penjualan dan memahami pola pembelian pelanggan, Toko Kecantikan Putri perlu menganalisis data penjualan secara efektif. Analisis data penjualan tradisional tidak dapat memberikan insights yang mendalam mengenai pola pembelian pelanggan. Hal ini dapat menghambat Toko Kecantikan Putri dalam mengembangkan strategi penjualan yang tepat dan efektif. Penelitian ini menerapkan algoritma K-Means clustering untuk menganalisis data penjualan Toko Kecantikan Putri selama bulan Januari 2024. Data yang dianalisis terdiri dari 122 baris dengan 22 atribut. Data penjualan meliputi informasi produk, kategori produk, dan jumlah penjualan. Algoritma K-Means clustering digunakan untuk mengelompokkan data penjualan berdasarkan karakteristik produk. Teknik analisis menggunakan Knowledge Discovery in Database (KDD) merupakan proses untuk menemukan pengetahuan baru dari data yang dikumpulkan. Hasil analisis menunjukkan bahwa data penjualan Toko Kecantikan Putri dapat dilakukan menjadi menjadi 9 cluster, dari cluster k=2 sampai k=9. Masing-masing cluster memiliki karakteristik pola pembelian yang berbeda. Cluster terbaik terdapat pada cluster K=8 dengan Nilai DBI sebesar 0,021 yang berasal dari measure Types Mixed Measures nilai davies bouldin index 0.077, Numerical Measures nilai davies bouldin index 0.114, Bregman Divergences nilai davies bouldin index 0.114. Analisis data penjualan Toko Kecantikan Putri dengan Algoritma K-Means Clustering menghasilkan insights berharga mengenai pola pembelian pelanggan. Evaluasi menyeluruh terhadap berbagai parameter, jumlah cluster, dan nilai Davies Bouldin Index optimal, menunjukkan bahwa Algoritma K-Means Clustering menghasilkan pengelompokan data yang paling optimal dan informatif.Kata Kunci: Algoritma K-Means clustering, Analisis Data Penjualan, Toko Kecantikan Putri, Pola Pembelian Pelanggan, Strategi Penjualan
Convolutional Neural Networks for Classification Motives and the Effect of Image Dimensions Siti Aisyah; Rini Astuti; Fadhil M Basysyar; Odi Nurdiawan; Irfan Ali
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 8 No 1 (2024): February 2024
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v8i1.5623

Abstract

Although Indonesian batik patterns vary by location, they usually depict local customs and cultures. Each batik has a unique quality and, to correctly identify the batik designs, you need to understand the design patterns. However, many people struggle to identify and categorize these kinds of motivation because they don't have the requisite knowledge, understanding, or access to sufficient information. This study used photo data to classify batik patterns into 15 different groups. Batik Kawung, Megamendung, Lasem, Pole, Machete, Gills, Nutmeg, Karaswasih, Cendrawasih, Geblek Renteng, Bali, Betawi, and Dayak are all included in this category. 1,350 images were used in the research. Google supports the collection of data. To provide the highest level of precision and to evaluate how image dimensions affect the classification of batik designs, this study employs convolutional neural networks (CNNs). The results of this study show that Multi-Layer Perceptron (MLP) is a well-liked deep learning method for data classification, especially in domains where picture classification is involved. The size of the images utilized affects the accuracy of computational neural network (CNN) algorithms. The results showed that the test using training data comparisons of 60%, 30% and 10% resulted in a 01.89% loss of 1.18% and a 100% improvement in accuracy.
Optimizing the Social Assistance Recipient Model in CangkringVillage Using the Naïve Bayes Algorithm Rotika; Nana Suarna; Irfan Ali; Dendy Indriya Efendi
Journal of Artificial Intelligence and Engineering Applications (JAIEA) Vol. 4 No. 2 (2025): February 2025
Publisher : Yayasan Kita Menulis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59934/jaiea.v4i2.849

Abstract

Social assistance is one of the methods used by the government to help the underprivileged. Cangkring Village is a village in Cirebon Regency that has inaccurate data on recipients of social assistance or underprivileged people. The Naive Bayes algorithm is one of the most effective techniques in machine learning for classifying data, in determining the eligibility of recipients of social assistance. The method works with a probabilistic approach to analyze data efficiently and accurately, can group data based on attributes and produce high accuracy. The problem in Cangkring Village, namely the accuracy of data on recipients of social assistance, is still a problem that requires special attention. This inaccuracy not only reduces the effectiveness of social assistance programs but also creates injustice for people in need. Invalid and inappropriate data causes the distribution of social assistance to be suboptimal. The purpose of this study is to optimize the accuracy model of social security recipients using the Naive Bayes algorithm, which can help improve the accuracy in determining eligible recipients.The method used in the study is secondary data processing taken from social assistance recipient data in Cangkring Village. This process includes data preprocessing stages, training and testing data distribution, and implementation or application of the Naive Bayes algorithm to perform classification. The results of the study show that the Naive Bayes algorithm is able to increase the accuracy of the classification of social assistance recipients with an accuracy rate of 90%, compared to the conventional method used previously. This study contributes to providing a more efficient and targeted method in selecting social assistance recipients, so that it can improve the social assistance distribution system in the future. Thus, the Naive Bayes algorithm can be an effective method for data-based decision making in the context of social policy.
Improving the Voter List Clustering Model Fixed(DPT) using the K-Means Algorithm in Girinata Village Rizki Aldi; Nana Suarna2; Irfan Ali; Dendy Indriya Efendi
Journal of Artificial Intelligence and Engineering Applications (JAIEA) Vol. 4 No. 2 (2025): February 2025
Publisher : Yayasan Kita Menulis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59934/jaiea.v4i2.876

Abstract

Elections are one of the pillars of democracy that require accurate voter data to ensure transparency and fairness. The Permanent Voter List (DPT) is a crucial element in supporting the smooth running of elections, but there are often data validity problems such as duplicate data, voter location errors, or voter data that does not meet the requirements. This research focuses on the application of the K-Means algorithm to increase the accuracy and validity of the DPT at TPS 05, Girinata Village. The problem formulation in this research includes the accuracy level of the DPT, the effectiveness of the K-Means algorithm in identifying inaccuracies, as well as factors that influence the accuracy of voter data. This research aims to analyze the accuracy level of the DPT, evaluate the effectiveness of the K-Means algorithm in grouping data, and identify factors contributing to the validity of the DPT. The analysis results show that the K-Means algorithm succeeded in grouping voter data with good quality, with a Davies-Bouldin Index (DBI) value of 0.389, which indicates clearly defined clusters. The main factors that influence clustering are age, distance to TPS, and location (RT and TPS). This research shows that the K-Means algorithm can be used to detect inaccuracies in voter data, such as data that does not match the TPS location or age that does not meet the requirements as a voter. With these results, the K-Means algorithm makes a significant contribution to validating voter data, thereby supporting a more transparent and accountable election process.
Identify Rattan Sales Patterns Using the FP-Growth Algorithm on CV. Busaeri Rattan Robi; Nana Suarna; Irfan Ali; Dendy Indriya Efendi
Journal of Artificial Intelligence and Engineering Applications (JAIEA) Vol. 4 No. 2 (2025): February 2025
Publisher : Yayasan Kita Menulis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59934/jaiea.v4i2.877

Abstract

This research was conducted to recognize the pattern of purchasing rattan products at CV. Busaeri Rattan by utilizing the FP-Growth algorithm. The rattan industry is faced with the challenge of understanding consumer habits in order to improve marketing strategies. The FP-Growth algorithm was chosen for its ability to efficiently identify frequent itemset patterns without requiring a lot of memory. This research includes collecting rattan sales transaction data for one year, data preprocessing, FP-Tree structure formation, and frequent itemset analysis. The analysis was conducted using RapidMiner software with a minimum support setting of 0.005 and confidence of 0.1. The processed data was then used to find combinations of products that are often purchased together. The results revealed some significant patterns, such as the products “Mandola 3/4” and “Jawit 8/11,” which are often purchased together with a confidence level of 100%. These findings provide important insights for CV. Busaeri Rattan in increasing sales through promotional strategies such as bundling or discount offers. In addition, the FP-Growth algorithm proved to be faster and more resource-efficient than traditional methods such as Apriori. The discussion shows that the discovered purchasing patterns can help CV. Busaeri Rattan better manage stock, minimize the risk of running out of goods, and design data-driven marketing strategies. The combination of products that are often purchased together can be utilized to improve customer satisfaction as well as operational efficiency. The conclusion of this research is that the FP-Growth algorithm is an effective tool for analyzing large-scale transaction data. Further research is recommended to explore the application of this algorithm to other types of products or compare it with other data mining algorithms.
Analisis Peramalan Tingkat Pengangguran Terbuka di Jawa Barat: Pendekatan Time Series menggunakan Metode ARIMA Adi Pangestu; Ade Irma Purnamasari; Irfan Ali
Jurnal IT UHB Vol 5 No 1 (2024): Jurnal Ilmu Komputer dan Teknologi
Publisher : Universitas Harapan Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35960/ikomti.v5i1.1298

Abstract

Tingkat pengangguran menjadi indikator penting dalam mengukur stabilitas ekonomi suatu daerah. Penelitian ini membahas tentang analisis model dan peramalan tingkat pengangguran terbuka di Wilayah Jawa Barat menggunakan metode ARIMA (Autoregressive Integrated Moving Average). Penelitian ini menggunakan data deret waktu (time-series) 6 bulanan tingkat pengangguran terbuka dari tahun 2007 hingga 2023 yang bersumber dari Badan Pusat Statistik, Opendatajabar dan Dinas Ketenagakerjaan Provinsi Jawa Barat. Analisis dimulai dengan identifikasi model ARIMA, estimasi parameter, cek diagnostik, evaluasi model dan peramalan. Peramalan dilakukan untuk 3 tahun ke depan (2024 - 2026). Model ARIMA(1,0,0) dipilih berdasarkan evaluasi parameter seperti Root Mean Squared Error(RMSE), Mean Absolute Error(MAE) dan Mean Abs Percent Error(MAPE). Hasil peramalan menunjukkan peningkatan tingkat pengangguran pada Februari 2024 7,92% menjadi 8,40% pada Agustus 2026. Hasil menunjukkan pola tren naik yang berkelanjutan. Peningkatan tingkat pengangguran di Wilayah Jawa Barat dipengaruhi oleh faktor kebijakan ekonomi, struktur industri, dinamika teknologi, dan pendidikan. Peran pemerintah dalam menciptakan lapangan kerja, reformasi pendidikan, dan kebijakan investasi menjadi krusial dalam menanggulangi masalah ini. Penelitian ini memberikan kontribusi dalam pemahaman dan peramalan tingkat pengangguran terbuka di Wilayah Jawa Barat. Model ARIMA(1,0,0) dapat digunakan sebagai alat yang efektif untuk meramalkan perubahan tingkat pengangguran di masa mendatang. Oleh karena itu, perumusan kebijakan yang mendukung pertumbuhan ekonomi dan penciptaan lapangan kerja diperlukan untuk mengatasi tantangan ini.
Penerapan Algoritma FP-Growth Untuk Menentukan Pola Penjualan Toko Ellia Umami Lintang Mugi Lestari; Irfan Ali
Journal of Student Research Vol. 1 No. 3 (2023): Mei: Journal of Student Research
Publisher : Pusat Riset dan Inovasi Nasional

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55606/jsr.v1i3.1267

Abstract

Toko ellia umami berupaya meningkatkan produksi produknya agar lebih banyak orang mengetahuinya, mirip dengan berapa banyak orang yang membeli dan menjual produk yang sama secara bersamaan. Toko Ellia Umami menjual berbagai macam barang, yang menimbulkan kemungkinan data tidak konsisten dan tidak dapat disamakan. Beberapa produk mungkin lebih populer dari yang lain, oleh karena itu toko ellia umami harus mengetahui aturan yang mengatur penjualan dan transaksi serta produk itu sendiri. Algoritma FP-Growth adalah satu-satunya algoritma penambangan data yang digunakan untuk memeriksa persyaratan transaksi data. Di toko ellia umami, FP-Growth dapat digunakan untuk menganalisis data transaksi pembelian produk dan mengidentifikasi transaksi yang tertunda.Tujuan dari tugas akhir ini adalah mengimplementasikan algoritma FP-Growth untuk menginformasikan kepada toko ellia umami tentang rekomendasi produk dan layanan berdasarkan data dari transaksi yang melibatkan penjualan toko ellia umami. Berdasarkan hasil akhir, pola hubungan data dari toko ellia umami dengan tingkat minimum (support 0,1) dan (confiden 0,1) menunjukkan bahwa jika pelanggan membeli Libby M, pelanggan juga akan membeli Celpen dan anak.
Penerapan Algoritma Fp-Growth Untuk Menentukan Pola Penjualan Pada Toko Sheryl Cosmetic Dan Titanium Collection Ayunda Fitriyana; Irfan Ali
Journal of Student Research Vol. 1 No. 4 (2023): Juli: Journal of Student Research
Publisher : Pusat Riset dan Inovasi Nasional

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55606/jsr.v1i4.1483

Abstract

Skincare saat ini adalah barang yang sangat digemari oleh para remaja tidak hanya perempuan adapun laki-laki juga memakainya, dengan berbagai macam merk yang banyak sekali manfaat dan kandungan dari berbagai macam skincare. Toko Sheryl Cosmetic dan Titanium Collection sebuah toko online dan offline yang bergerak dibidang penjualan skincare dll. Dalam Bisnisnya ini aturan transaksi penjualan nya sangat tidak stabil dan tidak efektif. Agar aturan asosiasi menjadi lebih efektif dan efisien maka dilakukanlah analisis suatu transaksi penjualan karena analisis transaksi ini bertujuan untuk merancang strategi yang efektif untuk dengan cara memanfaatkann data transaksi penjualan produk skincare mana saja yang dibeli oleh konsumen. Toko Sheryl Cosmetic dan Titanium Collection dapat mengidentifikasi pembelian pola-pola yang paling sering terjadi di setiap toko dengan menggunakan algoritma FP-Growth. Informasi seperti ini dapat digunakan untuk meningkatkan efektivitas manajemen persediaan dan strategi pemasaran, serta memungkinkan toko untuk memberikan rekomendasi pembelian yang lebih disesuaikan dan efektif kepada pelanggan.
APLIKASI CARSECURE MENGGUNAKAN FRAMEWORK FLUTTER UNTUK MEMBANTU OPTIMALISASI SISTEM IOT CARSECURE Affan, Taryono Ibnu; Dian Ade Kurnia; Irfan Ali
Jurnal Informatika dan Teknik Elektro Terapan Vol. 14 No. 1 (2026)
Publisher : Universitas Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23960/jitet.v14i1.8412

Abstract

Perkembangan teknologi informasi memberikan pengaruh besar terhadap sistem keamanan kendaraan modern, khususnya melalui pemanfaatan Internet of Things (IoT) yang memungkinkan perangkat saling terhubung dan dikendalikan secara jarak jauh. Penelitian ini bertujuan mengembangkan aplikasi CarSecure berbasis Flutter untuk mengoptimalkan sistem keamanan kendaraan IoT dengan fitur utama seperti pemantauan lokasi real-time, pengendalian mesin jarak jauh, dan notifikasi keamanan. Pengembangan dilakukan menggunakan model Waterfall, mencakup analisis kebutuhan, perancangan, implementasi, pengujian, dan pemeliharaan. Aplikasi ini terintegrasi dengan perangkat ESP32, modul GPS, dan relay, serta menggunakan Firebase Realtime Database sebagai media komunikasi data dua arah. Hasil evaluasi menunjukkan bahwa aplikasi mampu mengeksekusi perintah “Matikan Mesin” dengan waktu respon rata-rata 2–3 detik, memberikan notifikasi keamanan dalam waktu kurang dari 5 detik, serta menampilkan akurasi GPS dengan deviasi ±7 meter. Koneksi antara aplikasi dan perangkat IoT juga terbukti stabil dengan tingkat kestabilan 100% selama 30 menit pengujian tanpa putus. Evaluasi kepuasan pengguna terhadap 20 responden menghasilkan skor rata-rata 4.46, dengan aspek kemudahan penggunaan (4.6), kecepatan respon sistem (4.5), tampilan antarmuka (4.5), dan keandalan sistem (4.3). Berdasarkan hasil tersebut, aplikasi CarSecure dinilai responsif, akurat, mudah digunakan, dan efektif dalam mendukung keamanan kendaraan berbasis IoT, serta memiliki potensi untuk dikembangkan lebih lanjut dengan fitur keamanan berbasis kecerdasan buatan.
Pengaruh Augmentasi Data dan Dropout terhadap Generalisasi Model Deteksi Kerusakan Panel Surya Irfan Ali; Rudi Kurniawan; Dadang Sudrajat; Saeful Anwar; Nining Rahaningsih
Prosiding SISFOTEK Vol 9 No 1 (2025): SISFOTEK IX 2025
Publisher : Ikatan Ahli Informatika Indonesia

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

Abstract

Automatic defect detection in photovoltaic (PV) panels is a crucial challenge for maintaining energy efficiency and reliability in renewable power systems. However, the limited availability of labeled datasets and high environmental variability often lead deep learning models to overfit and lose generalization capability. This study investigates the combined effects of data augmentation and dropout regularization on improving the generalization performance of transfer learning-based models for multi-class PV defect classification. Two pretrained architectures, VGG16 and InceptionV3, were fine-tuned using the Faulty Solar Panel dataset comprising six defect categories. Experiments were conducted under three main configurations: (1) baseline without regularization, (2) augmentation only, and (3) combined augmentation–dropout with dropout rates of 0.2, 0.3, and 0.5. Performance evaluation employed accuracy, precision, recall, macro-F1, and confusion matrix analysis for each defect class. The results demonstrate that the combination of data augmentation and moderate dropout (0.3) significantly enhances generalization, achieving 92.10% accuracy and 0.90 macro-F1 with the InceptionV3 architecture. Higher dropout values (0.5) caused slower convergence and decreased accuracy. These findings confirm that balanced integration of augmentation and dropout effectively mitigates overfitting and strengthens model robustness under limited and imbalanced data conditions. The proposed approach provides practical implications for implementing reliable, lightweight, and deployable deep learning-based inspection systems in real-world PV monitoring using edge computing devices.
Co-Authors Ade Irma Purnamasari Adi Pangestu Affan, Taryono Ibnu Agung Prayogo Bagustio agus bahtiar Aji Santoso Aji Santoso Arif Rinaldi Dikananda Ayunda Fitriyana Bagustio, Agung Prayogo Dadang Sudrajat Dendy Indriya Efendi Dian Ade Kurnia Fadhil M Basysyar Farid Ali Ma'ruf Gian Fitralisma Gifthera Dwilestari INAYATUL AFRIYANI Irma Purnamasari, Ade Jayawarsa, A.A. Ketut Lintang Mugi Lestari Martanto Mukhlisin Ilahudin Mulyawan Nana Suarna Nana Suarna2 Nining R Nining Rahaningsih Nur Alia Sumanti Odi Nurdiawan Purnamasari, Ade Irma Qosdu Sabil Rini Astuti Rizki Aldi Robi Rotika Rudi Kurniawan Rusbandi Rusbandi Saeful Anwar Saefullah Fasa Siti Aisyah Willy Prihartono Yudhistira Arie Wijaya Yuslia Devitri