Feri Fahrianto
Department Of Informatics Engineering, Faculty Of Science And Technology, State Islamic University Syarif Hidayatullah Jakarta

Published : 10 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 10 Documents
Search

PUSH NOTIFICATION MONITORING SISTEM PINTU AIR BERBASIS ANDROID MENGGUNAKAN FIREBASE CLOUD MESSAGING Fernando, Frandia; Arini, Arini; Fahrianto, Feri
JURNAL TEKNIK INFORMATIKA Vol 13, No 1 (2020): JURNAL TEKNIK INFORMATIKA
Publisher : Prodi Teknik Informatika Universitas Islam Negeri Syarif Hidayatullah Jakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (809.704 KB) | DOI: 10.15408/jti.v13i1.15884

Abstract

Flood disaster is very common, especially in Jakarta City. One way to control water debit is to create a dam or reservoir. In each reservoir there is a water gate which serves to dispose of unwanted water gradually or continuously according to the water volume present in the dam. The Regional Disaster Management Agency (BPBD) Jakarta City needed a system that can monitor any existing water gates of the reservoir, this is to facilitate water gate inspectors to provide information. By using firebase cloud messaging technology that will be applied in the application of push-based android water doors. The application will provide notification and water gate data in real time, making it easier for users to get data in real time. Firebase Cloud Messaging is a cross platform solution that allows you to send messages reliably at no cost. In addition, the use of API as a processing medium to pull data from the web BPBD, optimize its function to mobile android. BPBD as the agency that tackling the disaster can know the state of the environment quickly and accurately. Applications created not only made for BPBD only but the general public can also to know the condition of the water gate. In addition, there are also ways of handling floods and what to do at each level of water level.For the next, this application can add other technollgy also IoT technology.
PENERAPAN END-TO-END ENCRYPTION DENGAN METODE SUPER ENCRYPTION UNTUK KERAHASIAAN CITRA DIGITAL PADA APLIKASI INSTANT MESSAGING Feri Fahrianto; Addinul Kitanggi
JURNAL TEKNIK INFORMATIKA Vol 9, No 1 (2016): Jurnal Teknik Informatika
Publisher : Department of Informatics, Universitas Islam Negeri Syarif Hidayatullah

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (873.124 KB) | DOI: 10.15408/jti.v9i1.5651

Abstract

ABSTRAK Instant Messaging merupakan media komunikasi pengiriman pesan yang marak digunakan untuk saat ini sebagai pengganti telepon dan SMS. Salah satu fitur pada layanan instant messaging yang populer adalah fitur pengiriman citra digital. Ada potensi ancaman keamanan pada instant messaging berbentuk pencurian data citra digital yang dikirim melalui jaringan layanan instant messaging dan juga pencurian data pada database yang tersimpan pada server pihak ketiga. Solusiyang dapat dilakukan untuk hal ini adalah dengan menggunakan end-to-end encryption (Andre 2009). End-to-end encryption (E2EE) adalah suatu mekanisme komunikasi dimana orang yang bisa membaca pesannya hanyalah orang yang sedang berkomunikasi tersebut. Algoritma enkripsi yang digunakan dalam implementasi E2EE bisa bervariasi. Dalam penelitian ini algoritma enkripsi yangdigunakan adalah super encryption dengan menggabungkan playfair cipher dengan Vigenere cipher yangcukup efektif untuk digunakan pada mobile phones (Setyaningsih et al. 2012). Untuk itu, penulis merancang dan membangung aplikasi instant messaging yang dapat berjalan pada platform mobile Android yang dapat mengenkripsi dan mengirim citra digital yang berguna untuk meningkatkan keamanan pada layananinstant messaging.  Kata Kunci:instant messaging, end-to-end encryption, super encryption, multiple encryption, vigenere cipher, playfair cipher, extreme programming
Penerapan Metode K-MEANS Clustering dan Support Vector Machine (SVM) dalam Identifikasi API pada Citra Warna Digital Amanda Febrianti; A Arini; Feri Fahrianto
Jurnal CoreIT: Jurnal Hasil Penelitian Ilmu Komputer dan Teknologi Informasi Vol 6, No 1 (2020): Juni 2020
Publisher : Fakultas Sains dan Teknologi, Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (132.639 KB) | DOI: 10.24014/coreit.v6i1.9001

Abstract

Banyak bencana yang telah terjadi akhir-akhir ini, mulai dari bencana alam maupun bencana yang disebabkan oleh manusia itu sendiri. Kebakaran adalah salah satu bencana yang paling sering terjadi dan memilki tingkat kerugian yang tidak sedikit. Salah satu upaya yang dapat dilakukan untuk mengenali api adalah pendeteksian pada citra digital, dikarenakan karakteristik api yang bisa langsung dilihat secara visual. Pada penelitian ini, penulis akan fokus pada salah satu karakteristik api, yaitu warna. Dalam segmentasi fitur warna, penulis menggunakan ruang warna YCbCr dan RGB. Ekstraksi data dilakukan dengan menggunakan metode K-Means Clustering. Hasil ekstraksi akan diklasifikasikan dengan Support Vector Machine (SVM), untuk mengelompokan citra yang mengandung api dengan citra biasa. Untuk data latih dan data uji, penulis akan menggunakan citra hutan agar dapat melakukan perbandingan hasil dengan penelitian sebelumnya. Selain itu, penulis juga akan menggunakan citra bangunan sebagai skenario tambahan untuk melihat hasil tingkat efektifitas algoritma yang penulis pakai pada kondisi citra selain hutan. Hasil penelitian menunjukan bahwa penggabungan mode warna RGB dan YCbCr dalam mendeteksi api pada citra digital hutan dan bangunan memiliki tingkat keberhasilan >90%, dengan tingkat akurasi yang lebih tinggi pada citra digital yang diambil pada siang hari.
Attendance Recognation by Using Smart Meter Based On IoT Study Case : FST UIN Jakarta Feri Fahrianto; Hendra Bayu Suseno; Alfatta Reza
JURNAL TEKNIK INFORMATIKA Vol 12, No 1 (2019): JURNAL TEKNIK INFORMATIKA
Publisher : Department of Informatics, Universitas Islam Negeri Syarif Hidayatullah

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (720.059 KB) | DOI: 10.15408/jti.v12i1.11043

Abstract

State Islamic University Syarif Hidayatullah Jakarta as rapidly growing university toward world-class research university placed in the edge of Jakarta has academic information centre running by Pustipanda (The Center of Information Technology and Database). The acadmic information system (AIS) has been used for recording an academic activity in university for almost a decade, this information system has a functionality for detecting the lecturer attandancity, but the attendance system needs to be input by admin. In this research, the system to detect attendancity from lecturer is build and synchronize to universisty academic information system.  Internet of Things, based on ITU-T 2015, some objects are able to transmit data among object by using Internet connection. It means by this technology the Internet used has been widely changed, from human to machine communication now also become machine-to-machine communications. By using this technology a small object or device is able to implement into electrical system to detect an activity occured in the room. Things implemented in the room are able to monitor which electronic device is active and motion of moving objects, also the position of objects. The communication connection between smart phones and acces point in the class room is also monitored in order to identify the lecturer identity.
Redesigning UI/UX of A Mobile Application Using Task Centered System Design Approach Mugi Praseptiawan; Meida Cahyo Untoro; Feri Fahrianto; Pungki Resti Prabandari; M. Syamsuddin Wisnubroto
Applied Information System and Management (AISM) Vol 6, No 1 (2023): Applied Information System and Management (AISM)
Publisher : Depart. of Information Systems, FST, UIN Syarif Hidayatullah Jakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15408/aism.v6i1.24665

Abstract

Digital transformation requires a software system development method to identify and analyze user needs. In this research, software system development uses the Task Centered System Design framework with several stages, including identification, needs analysis, design, and evaluation. The identification stage is carried out by conducting interviews with stakeholders, and then the results of the interviews are analyzed and approved by stakeholders. This study aims to obtain user needs to build an application interface by applying the steps of the Task Centered System Design method and usability evaluation and calculating the weight of the feasibility value by testing the Heuristics method and System Usability Scale on the solution application design. The evaluation phase aims to determine the value of the usability problem in the design that has been designed. The evaluation phase uses the Usability Heuristic method by involving experts in the field of software development and the System Usability Scale method involving end users. After conducting research from the identification to the evaluation stage, the average severity rating of the Heuristic Usability test component scored less than 1 (one) in the second iteration, and the System Usability Scale results scored 70.3 for admin and 73.75 for the customer application. This result is in grade C with an adjective rating of Good.  
Performance Analysis of Transfer Learning Models for Identifying AI-Generated and Real Images Arini Arini; Muhamad Azhari; Isnaieni Ijtima’ Amna Fitri; Feri Fahrianto
JURNAL TEKNIK INFORMATIKA Vol 17, No 2: JURNAL TEKNIK INFORMATIKA
Publisher : Department of Informatics, Universitas Islam Negeri Syarif Hidayatullah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15408/jti.v17i2.40453

Abstract

This study aims to analyze and compare the performance of three transfer learning methods, namely InceptionV3, VGG16, and DenseNet121, in detecting AI-generated and real images. The background of this research is the unknown performance of transfer learning methods for detecting AI-generated and real images. This study introduces innovation by conducting 54 experiments involving three types of transfer learning, three dataset split ratios (60:40, 70:30, and 80:20), three optimizers (Adam, SGD, and RMSprop), two numbers of epochs (20 and 50), and the addition of dense and flatten layers during fine tuning. Performance evaluation was conducted using binary cross entropy loss and confusion matrix. This research provides significant benefits in determining the most effective transfer learning model for detecting AI-generated and real images and offers practical guidance for further development. The results show that the InceptionV3 model with the Adam optimizer, an 80:20 split ratio, and 20 epochs achieved the highest accuracy of 84.26%, with a loss of 39.54%, precision of 81.33%, recall of 82.43%, and an F1-Score of 81.88%.
Investigating Synthetic Traffic Generators for Zipf Distribution Simulation Accuracy Feri Fahrianto; Viva Arifin; Imam Marzuki Shofi; Hendra Bayu Suseno; Victor Amrizal; Muhamad Azhari; Anggy Eka Pratiwi
JURNAL INFOTEL Vol 17 No 2 (2025): May
Publisher : LPPM INSTITUT TEKNOLOGI TELKOM PURWOKERTO

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20895/infotel.v17i2.1359

Abstract

Accurate traffic generation is essential for realistic network simulations in systems such as Content Delivery Networks (CDNs), Information-Centric Networks (ICNs), and the Internet of Things (IoT). These environments handle various types of data traffic—ranging from web pages and videos to sensor data and software updates—making it critical to model traffic patterns effectively. A well-designed traffic generator enables researchers and engineers to simulate real-world workloads, test scalability, and evaluate the performance of caching, routing, and resource allocation strategies under realistic conditions. Each traffic class has unique characteristics, including object size distributions, access patterns, and temporal dynamics. Capturing these differences is key to producing meaningful simulation results. For instance, CDNs require simulation of content popularity and delivery latency, ICNs focus on content retrieval and caching efficiency, while IoT simulations demand modeling of device behavior and intermittent communication. To support such complex scenarios, a traffic generator must not only mimic real user behavior but also allow for flexible scaling, combination, and modification of traffic patterns. This paper presents a method for evaluating synthetic traffic generators by comparing their output to the statistical properties of the Zipf distribution. The focus is on assessing whether synthetic traffic accurately reflects the heavy-tailed nature of real-world traffic as modeled by Zipf’s law. By analyzing the frequency distribution of requests generated by the traffic model and comparing it to theoretical Zipf curves, the study provides insights into the fidelity of the traffic generator. We measure the discrepancy between the simulated network traffic and the theoretical model to evaluate the accuracy and realism of the traffic generation approach.
Implementation of Federated Learning for Alzheimer's Disease Classification Using FedAdagrad Algorithm Arini Arini; Feri Fahrianto; Adil Ramadhan
IJID (International Journal on Informatics for Development) Vol. 14 No. 2 (2025): IJID December
Publisher : Faculty of Science and Technology, Universitas Islam Negeri (UIN) Sunan Kalijaga Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14421/ijid.2025.5045

Abstract

Federated Learning (FL) offers a promising solution for training machine learning models on decentralized data while preserving privacy, making it particularly valuable for sensitive applications such as healthcare. This study implements FL for the classification of Alzheimer’s disease using MRI images, addressing two critical challenges: data heterogeneity and class imbalance. The research evaluates the performance of the FedAdagrad optimization algorithm against the standard FedAvg approach under varying data distribution scenarios. The methodology employs a CNN trained on a dataset of 6,400 MRI images across four severity classes, partitioned non-IID using Dirichlet distributions (α = 0.1, 0.5, 0.9) to simulate real-world heterogeneity. Experiments were conducted using the Flower framework with four clients over ten communication rounds. Results indicate that FedAdagrad achieves a superior F1-score of 50.33% compared to FedAvg’s 48.14%, though both fall short of centralized CNN performance (55%). High data heterogeneity (α = 0.1) leads to a 13.35% accuracy decline, underscoring FL’s sensitivity to uneven data distributions. Class imbalance emerges as the primary bottleneck, affecting all models. The findings contribute to the growing body of research on adaptive optimization in federated settings, offering insights for future improvements in decentralized healthcare AI.
How Muslim Women in Jakarta Negotiate the ‘My Body, My Rules’ Narrative on Social Media: A Communication Perspective on Feminism and Islamic Values Naya Adisti Prameswari Putrie; Feri Fahrianto; Rino Febrianno Boer; Ajif Yunizar Pratama
Mimbar Agama Budaya Vol. 43 No. 1 (2026)
Publisher : Center for Research and Publication (PUSLITPEN), UIN Syarif Hidayatullah Jakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15408/mimbar.v43i1.51639

Abstract

A global wave of digital feminism has emerged, and the slogan “My Body, My Rules (abbreviated MBMR)” has spread widely across social platforms including TikTok and Instagram. However, after this discourse entered Indonesia’s Muslim communities, it required reinterpretation through integration with three core Islamic values: amanah, iffah, and maslahah, and the framing of bodily autonomy thus generated cross-cultural tensions. The author team of this paper centered their research on the core question of how Muslim women aged 20 to 40 in Jakarta negotiate and address this tension. Under a qualitative research framework, the study adopted a dual-path approach combining semi-structured interviews with digital discourse analysis. The study found that participants developed a form of negotiated agency, and that social media holds the dual attribute of being both an empowerment space and an arena for ideological contestation. This study supplements relevant research outcomes in the field of communication studies, proving that after localization, global feminist discourse can generate a hybrid agency that integrates individual empowerment and religious responsibility, and reshape the identity construction logic of contemporary digital communication.
Performance Comparison of LSTM, XGBoost, and Residual-Correction Hybrid LSTM–XGBoost Models for Bitcoin Price Forecasting Ihsan Maulana Anwas; Feri Fahrianto; Imam Marzuki Shofi; Ajif Yunizar Pratama
MATRIK : Jurnal Manajemen, Teknik Informatika dan Rekayasa Komputer Vol. 25 No. 2 (2026)
Publisher : Universitas Bumigora

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/matrik.v25i2.5983

Abstract

The objective of this study is to systematically compare the predictive performance of Long Short- Term Memory (LSTM), Extreme Gradient Boosting (XGBoost), and a Hybrid LSTM–XGBoost model for next-day Bitcoin (BTC–USD) closing-price forecasting. The research method employs a quantitative time-series modeling approach using a decade-long daily Bitcoin price dataset. A strictly chronological train–test split and a one-step-ahead forecasting scheme are applied to prevent lookahead bias and ensure experimental validity. Model performance is evaluated using Root Mean Square Error (RMSE), Mean Absolute Error (MAE), symmetric Mean Absolute Percentage Error (sMAPE), Mean Absolute Percentage Error (MAPE), and the coefficient of determination R2 on the original price scale. The results demonstrate that the Hybrid LSTM–XGBoost model consistently outperforms the standalone LSTM and XGBoost models across all evaluation metrics, indicating superior predictive accuracy and robustness under high market volatility. The contribution of this study lies in providing a controlled, uniform, and methodologically rigorous head-to-head comparison of deep learning, machine learning, and hybrid architectures for Bitcoin price forecasting, thereby enriching the empirical literature and offering a reliable foundation for the development of adaptive decision-support systemsin volatile cryptocurrency investment environments.