Article Per Year (5 Year)
p-Index From 2020 - 2025
1.347
P-Index
This Author published in this journals
All Journal Bulletin of Electrical Engineering and Informatics Jurnal Teknologi Informasi dan Ilmu Komputer JISKa (Jurnal Informatika Sunan Kalijaga) Indonesian Journal of Electrical Engineering and Computer Science Journal of Internet and Software Engineering Jurnal Informatika: Jurnal Pengembangan IT
Alfian, Ganjar
Unknown Affiliation
Computer Science & IT Electrical & Electronics Engineering Engineering Library & Information Science

Published : 8 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 8 Documents
Search

 1 
Application of the outlier detection method for web-based blood glucose level monitoring system Nurhaliza, Rachma Aurya; Octava, Muhammad Qois Huzyan; Hilmy, Farhan Mufti; Farooq, Umar; Alfian, Ganjar
Bulletin of Electrical Engineering and Informatics Vol 13, No 4: August 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/eei.v13i4.7717

Abstract

Recent advancements in biosensors have empowered individuals with diabetes to autonomously monitor their blood glucose levels through continuous glucose monitoring (CGM) sensors. Nevertheless, the data collected from these sensors may occasionally include outliers due to the inherent imperfections of the sensor devices. Consequently, the identification of these outliers is critical to determine whether blood glucose levels deviate significantly from the norm, necessitating further action. This study employs an outlier detection approach based on the 3-sigma method and the interquartile range (IQR), along with the application of the Winsorizing technique to correct the identified outliers. Additionally, a web-based system for visualizing blood glucose levels is developed, utilizing both outlier detection methods. In order to assess the system's performance, two types of testing are conducted: black box testing and load testing. The results of black box testing indicate that all test scenarios operate as anticipated. As for the load testing response times, it is observed that the 3-sigma visualization page loads an average of 606.75 milliseconds faster compared to the IQR visualization page. This study's outcomes are expected to enhance data quality, enhance the precision of analyses, and facilitate more informed decision-making by identifying and addressing extreme data points.
Perancangan Federated Learning Berbasis Homomorphic Encryption untuk Perangkat Internet of Things Saputra, Yuris Mulya; Alfian, Ganjar; Octava, Muhammad Qois Huzyan
Journal of Internet and Software Engineering Vol 4 No 1 (2023): Journal of Internet and Software Engineering
Publisher : Department of Electrical Engineering and Informatics, Vocational College, Universitas Gadjah Mada

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/jise.v4i1.6378

Abstract

Semakin berkembangnya pasar big data yang digunakan oleh pengguna khususnya Internet of Things (IoT) berbasis kecerdasan buatan telah menarik banyak pihak baik dari industri maupun akademisi. Melalui penggunaan data lokal dari berbagai perangkat IoT, pemberi layanan aplikasi dapat menghasilkan informasi berguna melalui pendekatan machine learning (ML) seperti centralized learning dengan menggunakan cloud server dan local learning pada perangkat IoT langsung. Namun, dengan adanya risiko bocornya privasi pengguna ketika mengirim data lokal ke cloud server dan sumber daya komputasi yang terbatas pada IoT, penggunaan federated learning (FL) dapat menjadi solusi efisien. Pendekatan FL merupakan sebuah pendekatan ML kolaboratif di mana setiap perangkat IoT dapat melakukan proses training secara independen dan kemudian hanya mengirimkan model local kepada cloud server tanpa melakukan data sharing. Secara khusus, penggunaan FL untuk layanan aplikasi pada perangkat IoT tidak hanya memperbaiki kinerja untuk proses training, namun juga dapat melindungi privasi data bagi penggunanya. Penelitian ini berfokus pada perancangan sistem FL dengan privacy-awareness yang dapat digunakan oleh para pengguna perangkat IoT. Dalam hal ini, teknik enkripsi yang berbasis homomorphic encryption untuk mengenkripsi data dari perangkat IoT ketika proses training dari FL dapat diimplementasikan sebagai bentuk perlindungan privasi pengguna IoT dari malicious attackers. Dari penelitian ini, dapat dianalisis perbandingan tingkat akurasi model dari berbagai pendekatan baik tanpa dan dengan teknik enkripsi tersebut.
Pemodelan Prediksi Kadar Gula Darah Pada Pasien Diabetes Menggunakan Metode Regresi Linear Hanafi, Hanan; Alfian, Ganjar; Widodo, Tri; Syafrudin, Muhammad
Journal of Internet and Software Engineering Vol 5 No 1 (2024): Journal of Internet and Software Engineering
Publisher : Department of Electrical Engineering and Informatics, Vocational College, Universitas Gadjah Mada

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/jise.v5i1.8480

Abstract

Mengetahui kadar gula darah di masa depan akan dapat membantu penderita diabetes dalam melakukan tindakan preventif lebih awal sehingga dapat mengontrol kadar gula darah dan penyakit diabetesnya. Penelitian ini mengusulkan pemodelan prediksi kadar gula darah pada pasien diabetes menggunakan metode regresi linear. Dataset yang digunakan adalah data time series dari kadar gula darah pada 30 anak penderita diabetes tipe 1. Dataset tersebut digunakan sebagai parameter input tunggal dengan tambahan pemanfaatan data statistik yang diuji menggunakan beberapa algoritma, yaitu Linear Regression, Lasso Regression, Ridge Regression, eXtreme Gradient Boosting (XGB), dan K-Nearest Neighbor (KNN). Pada tahap evaluasi performa model menunjukkan bahwa metode regresi linear lebih baik dari model prediksi lainnya. Hasilnya menunjukkan untuk Prediction Horizon (PH) pada 5 menit, 15 menit, dan 30 menit didapat nilai rata-rata Root Mean Squared Error (RMSE) dari 15 pasien yang diuji sebesar 5,024, 12,488, dan 20,635, nilai Mean Absolute Error (MAE) sebesar 2,891, 8,272, dan 14,926 serta nilai Coefficient of Determination (R2) sebesar 0,962, 0,741, dan 0,39. Hasil model prediksi pada penelitian ini diimplementasi dan divisualisasikan ke sistem informasi berbasis website. Dalam sistem tersebut pengguna dapat memprediksi kadar gula darah di masa depan dengan berdasarkan riwayat kadar gula darah pada waktu 30 menit sebelumnya. Pengguna juga dapat melihat visualisasi data pergerakan kadar gula darah berdasarkan rentang waktu tertentu. Sistem ini diharapkan dapat membantu pasien diabetes untuk memprediksi kadar gula darah di masa depan sehingga dapat mengontrol kadar gula darahnya dan menghindari kondisi kesehatan yang buruk di masa depan.
Segmentasi Pelanggan E-Commerce Menggunakan Fitur Recency, Frequency, Monetary (RFM) dan Algoritma Klasterisasi K-Means Fauzan, Reyhan Muhammad; Alfian, Ganjar
JISKA (Jurnal Informatika Sunan Kalijaga) Vol. 9 No. 3 (2024): September 2024
Publisher : UIN Sunan Kalijaga Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14421/jiska.2024.9.3.170-177

Abstract

The rapid growth in the e-commerce industry demands the development of smarter and more focused marketing strategies. One approach that can be applied is customer segmentation using various features such as Recency, Frequency, and Monetary (RFM), along with machine learning-based clustering methods. The objective of this study is to design and develop a web-based e-commerce customer segmentation application using a combination of RFM features and clustering methods. The study proposes the K-Means algorithm and compares it with K-Medoids and Fuzzy C Means using publicly available e-commerce datasets. Experimental results showed that the K-Means algorithm outperformed K-Medoids and Fuzzy C Means (FCM) based on the Silhouette Score of 0.67305, Davies Bouldin Index of 0.51435, and Calinski Harabasz Index of 5647.89. Through analysis and testing, the designed application has proven effective in grouping customers into relevant segments. These segments are divided into three categories: Loyal, Need Attention, and Promising, visualized in a web-based application dashboard using Streamlit. The developed application allows e-commerce business owners and users from the business, management, and marketing divisions to categorize customers based on transaction data. The results of this study are expected to provide valuable insights to e-commerce management and marketing professionals who are facing increasingly fierce competition.
Utilizing association rule mining for enhancing sales performance in web-based dashboard application Teja Nursasongka, Raden Mas; Fahrurrozi, Imam; Oktiawati, Unan Yusmaniar; Taufiq, Umar; Farooq, Umar; Alfian, Ganjar
Indonesian Journal of Electrical Engineering and Computer Science Vol 36, No 2: November 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v36.i2.pp1105-1113

Abstract

Data is increasingly recognized as a valuable asset for generating new insights and information. Given the importance of data, businesses must always look for ways to get more value from data generated from sales transactions. In data mining, association rule mining is a good standard technique and is widely used to find interesting relationships in databases. Association rule is closely related to market basket analysis to find items that often appear together in one transaction. This study proposes the frequent pattern growth (FP-Growth) algorithm in finding association rules on sales transaction data. Our methodology includes dataset preparation for modeling, evaluation of model performance, and subsequent integration into a web-based platform. We conducted a comparative analysis of the FP-Growth algorithm against the Apriori algorithm, finding that FP-Growth outperformed Apriori in efficiency. Using the same dataset and constraint level, both algorithms produce the same number of frequent itemsets. However, in terms of computation time, FP-Growth excels by taking 2.89 seconds while Apriori takes 5.29 seconds. We integrated trained FP-Growth algorithm into a web-based dashboard application using the streamlit framework. This system is anticipated to simplify the process for businesses to identify customer purchasing patterns and improve sales.
Rancang Bangun Aplikasi Monitor Kadar Gula Darah Berbasis Mobile Zuhri, Arief; Hardiyanti, Margareta; Fitriyani, Norma Latif; Alfian, Ganjar
Journal of Internet and Software Engineering Vol 5 No 2 (2024): Journal of Internet and Software Engineering
Publisher : Department of Electrical Engineering and Informatics, Vocational College, Universitas Gadjah Mada

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/jise.v5i2.9026

Abstract

Diabetes merupakan kondisi serius pada kesehatan masyarakat serta menjadi salah satu penyebab mortalitas tertinggi secara global. Tujuan perawatan diabetes adalah mencegah atau menunda komplikasi dan mengoptimalkan kualitas hidup. American Diabetes Association (ADA) menjabarkan pendekatan multifaktorial untuk mengurangi risiko komplikasi diabetes yang diterapkan melalui perubahan gaya hidup dan edukasi. Manajemen diabetes melalui aplikasi berbasis mobile terbukti membantu individu dalam keberhasilan melakukan manajemen diabetes secara mandiri. Meskipun aplikasi yang ada telah memberikan manfaat signifikan, masih terdapat ruang untuk pengembangan lebih lanjut dalam hal efektivitas manajemen diabetes dan keberlanjutan pengembangan sistem. Pada penelitian ini, sistem monitor kadar gula darah berbasis mobile dirancang berdasarkan pendekatan multifaktorial. Teknologi pengembangan mengadopsi pendekatan Modern Android development (MAD) dari Google. Tahapan pengembangan mencakup analisis, perancangan, implementasi, dan pengujian. Implementasi menerapkan enam komponen MAD: penargetan versi Android terbaru, penggunaan Android Studio, Kotlin, Jetpack Compose, Android Jetpack, dan penerapan praktik terbaik untuk arsitektur dan pengujian. Aplikasi berhasil dibangun dengan dua fitur utama: monitor kadar gula darah dan rekomendasi perawatan diabetes. Fitur monitor menyajikan grafik gula darah, pencatatan aktivitas yang dapat memengaruhi gula darah, dan alarm gula darah. Adapun rekomendasi perawatan diabetes memberikan edukasi dan dorongan kepada pasien untuk menerapkan gaya hidup sehat. Penerapan MAD menghasilkan sistem yang skalabel dan mudah dipelihara. Dari hasil pengujian, fungsi aplikasi berjalan sesuai dengan hasil analisis dan perancangan serta tidak ditemukan kerusakan. Hasil penelitian ini diharapkan agar sistem dapat membantu pasien dalam mencapai tujuan perawatan diabetes. Selain itu, sistem diharapkan dapat terus dikembangkan untuk memastikan relevansinya dan dampak yang berkelanjutan.
SCANOCULAR: Application for Early Detection of Eye Diseases Using AI and Blockchain Technology Pratomo, Dinar Nugroho; Alfian, Ganjar; Putri, Divi Galih Prasetyo; Kusnady, Rasyid; Pinandhita, Pudyasta Satria; Yusuf, Muhammad Abyan Farras; Dharmawan, Edeline Felicia; Zhafarizza, Ghifari Nafhan Muhammad
Jurnal Informatika: Jurnal Pengembangan IT Vol 10, No 2 (2025)
Publisher : Politeknik Harapan Bersama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30591/jpit.v10i2.8014

Abstract

Eye diseases such as cataracts, glaucoma, and diabetic retinopathy affect approximately 2.2 billion people globally, with 1 billion cases being preventable. In Indonesia, cataracts remain the leading cause of blindness. This research presents SCANOCULAR, a mobile application that integrates artificial intelligence (AI) and blockchain technology for early detection of eye diseases. The system utilizes a modified EfficientNetB4 Convolutional Neural Network (CNN) for analyzing eye images, achieving 95.50% accuracy, 95.92% precision, and 94.95% recall in cataract detection with an AUC of 0.9932. The blockchain implementation using Polygon Amoy platform ensures secure data transmission and storage while maintaining efficient transaction processing. Testing results demonstrate the system's capability in identifying various eye conditions while maintaining data integrity through blockchain verification. SCANOCULAR contributes to informatics by implementing a hybrid AI-blockchain architecture optimized for medical imaging applications, with a lightweight CNN model design that reduces computational requirements while maintaining diagnostic accuracy. This integration of technologies provides a potential solution for improving accessibility to eye disease screening and early intervention in Indonesia.
Visualisasi Segmentasi Pelanggan Berdasarkan Atribut RFM Menggunakan Algoritma K-Means Untuk Memahami Karakteristik Pelanggan pada Toko Retail Online Imanuel, Dennis Alfa; Alfian, Ganjar
Jurnal Teknologi Informasi dan Ilmu Komputer Vol 12 No 2: April 2025
Publisher : Fakultas Ilmu Komputer, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25126/jtiik.2025128619

Abstract

Meningkatnya minat belanja pelanggan toko retail online menimbulkan persaingan ketat antar retailer. Agar tetap unggul dan kompetitif, retailer perlu memahami karakteristik pelanggannya. Penerapan segmentasi pelanggan memberikan kemudahan pada retailer untuk memahami karakteristik pelanggan berdasarkan penilaian pada atribut yang dihitung dari data riwayat transaksi pelanggan. Hasil segmentasi pelanggan yang divisualisasikan dapat meningkatkan pemahaman retailer dalam memahami data dan membantu dalam proses pengambilan keputusan. Oleh karena itu, penelitian ini mengusulkan Visualisasi Segmentasi Pelanggan menggunakan Algoritma K-means berdasarkan Atribut RFM (Recency, Frequency, Monetary). Hasil segmentasi dapat digunakan untuk Memahami Karakteristik Pelanggan pada Toko Retail Online. Penelitian ini menggunakan algoritma k-means untuk menjalankan clustering yang performanya akan dibandingkan dengan algoritma k-medoids mengacu pada nilai silhouette, Calinski-Harabasz Index, dan DaviesBouldin Index dalam melakukan segmentasi pelanggan berdasarkan atribut RFM. Berdasarkan metrik tersebut, didapatkan nilai algoritma k-means berturut-turut adalah 0,6558, 0,7219, dan 3578,9, sedangkan nilai algoritma k-medoids adalah 0,4677, 0,8298, dan 1236,9. Dengan demikian, hasilnya menunjukkan bahwa kinerja clustering menggunakan k-means lebih baik daripada menggunakan k-medoids. Pada dashboard Looker Studio ditampilkan visualisasi data hasil segmentasi tersebut, kemudian diuji fungsionalitasnya dengan metode Blackbox Testing dan berhasil menyelesaikan semua skenario pengujian, kemudian dilakukan pengujian dengan metode UAT (User Acceptance Testing) dan mendapatkan predikat sangat layak.   Abstract The growing interest in online retail shopping among customers has resulted in intense competition among retailers. To sustain a competitiveness, retailers need to understand characteristics of their customer. Implementation of customer segmentation facilitates retailers in understanding customer characteristics through assessments based on attributes derived from customer transaction history data. Visualization of customer segmentation results can enhance the retailer's understanding of data and assist in the decision-making process. Therefore, this study proposes the Visualization of Customer Segmentation using the K-means Algorithm based on RFM Attributes (Recency, Frequency, Monetary). The segmentation results can be utilized to understand the characteristics of customers in an online retail store. This study explores the k-means algorithm to execute clustering, and its performance will be compared with the k-medoids algorithm, based of silhouette values, Calinski-Harabasz Index, and Davies Bouldin Index in customer segmentation based on RFM attributes. Based on given metrics, the consecutive performance values for k-means algorithm are 0.6558, 0.7219, and 3578.9, while k-medoids algorithm are 0.4677, 0.8298, and 1236.9. Thus, the results indicate that the clustering performance using k-means is better than using k-medoids. On the Looker Studio dashboard, the visualization of the segmentation data is displayed, and its functionality is tested using the Black Box Testing method, successfully completing all test scenarios. Subsequently, the system undergoes testing through the User Acceptance Testing (UAT) method and receives a highly satisfactory rating.
Co-Authors Dharmawan, Edeline Felicia Divi Galih Prasetyo Putri Fahrurrozi, Imam Farooq, Umar Fauzan, Reyhan Muhammad Fitriyani, Norma Latif Hanafi, Hanan Hardiyanti, Margareta Hilmy, Farhan Mufti Imanuel, Dennis Alfa Kusnady, Rasyid Muhammad Syafrudin Nurhaliza, Rachma Aurya Octava, Muhammad Qois Huzyan Oktiawati, Unan Yusmaniar Pinandhita, Pudyasta Satria Pratomo, Dinar Nugroho Saputra, Yuris Mulya Taufiq, Umar Teja Nursasongka, Raden Mas Tri Widodo Yusuf, Muhammad Abyan Farras Zhafarizza, Ghifari Nafhan Muhammad Zuhri, Arief