Article Per Year (5 Year)
p-Index From 2021 - 2026
2.517
P-Index
This Author published in this journals
All Journal PIKSEL : Penelitian Ilmu Komputer Sistem Embedded and Logic Jurnal Ilmiah Kursor Jurnal Teknologi Informasi dan Ilmu Komputer Knowledge Engineering and Data Science Jurnal Nasional Komputasi dan Teknologi Informasi Indonesian Journal of Electrical Engineering and Computer Science Jurnal Teknologi Sistem Informasi dan Sistem Komputer TGD Indexia IJCOSIN : Indonesian Journal of Community Service and Innovation Jurnal Riset Rumpun Ilmu Teknik (JURRITEK) Kohesi: Jurnal Sains dan Teknologi Jupiter: Publikasi Ilmu Keteknikan Industri, Teknik Elektro dan Informatika Merkurius: Jurnal Riset Sistem Informasi dan Teknik Informatika
Mar'i, Farhanna
Unknown Affiliation
Aerospace Engineering Agriculture, Biological Sciences & Forestry Automotive Engineering Biochemistry, Genetics & Molecular Biology Chemical Engineering, Chemistry & Bioengineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Education Electrical & Electronics Engineering Energy Engineering Environmental Science Languange, Linguistic, Communication & Media Neuroscience Social Sciences Transportation Other

Published : 17 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 17 Documents
Search

 1   2 
A conceptual approach of optimization in federated learning Mar’i, Farhanna; Supianto, Ahmad Afif
Indonesian Journal of Electrical Engineering and Computer Science Vol 37, No 1: January 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v37.i1.pp288-299

Abstract

Federated learning (FL) is an emerging approach to distributed learning from decentralized data, designed with privacy concerns in mind. FL has been successfully applied in several fields, such as the internet of things (IoT), human activity recognition (HAR), and natural language processing (NLP), showing remarkable results. However, the development of FL in real-world applications still faces several challenges. Recent optimizations of FL have been made to address these issues and enhance the FL settings. In this paper, we categorize the optimization of FL into five main challenges: Communication Efficiency, Heterogeneity, Privacy and Security, Scalability, and Convergence Rate. We provide an overview of various optimization frameworks for FL proposed in previous research, illustrated with concrete examples and applications based on these five optimization goals. Additionally, we propose two optional integrated conceptual frameworks (CFs) for optimizing FL by combining several optimization methods to achieve the best implementation of FL that addresses the five challenges.
Clustering Credit Card Holder Berdasarkan Pembayaran Tagihan Menggunakan Improved K-Means dengan Particle Swarm Optimization Mar'i, Farhanna; Supianto, Ahmad Afif
Jurnal Teknologi Informasi dan Ilmu Komputer Vol 5 No 6: Desember 2018
Publisher : Fakultas Ilmu Komputer, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (3093.112 KB) | DOI: 10.25126/jtiik.201856858

Abstract

AbstrakKartu kredit merupakan salah satu bentuk media bagi nasabah untuk melakukan kredit dalam sebuah proses transaksi yang telah disetujui oleh bank bersangkutan. Bank harus selektif dalam menganalisa nasabah yang ingin mengajukan penerbitan kartu kredit untuk menghindari adanya kredit macet yang dapat menimbulkan kerugian pada bank, sehingga sangat penting untuk mengetahui karakteristik nasabah dengan melakukan  clustering. Bank akan dapat mengambil keputusan untuk pertimbangan penerbitan kartu kredit dengan mencocokkan nasabah baru kedalam cluster-cluster yang telah dibentuk dan mengetahui kelayakan nasabah untuk diberikan akses kartu kredit dalam melakukan transaksi. K-Means adalah salah satu metode populer yang digunakan untuk clustering. Tetapi, metode K-Means tidak dapat memberikan solusi optimum karena keterbatasannya dalam penentuan titik centroid yang optimal, sehingga untuk memperbaiki metode K-Means dalam penelitian ini digunakan salah satu algoritma evolusi yaitu Particle Swarm Optimization (PSO) untuk generate titik centroid optimum yang digunakan dalam proses perhitungan K-Means. Hasil pengujian dilakukan dengan membandingkan nilai Silhouette Coefficient dari cluster yang dibentuk menggunakan K-Means murni dan Improved K-Means dengan PSO yang menghasilkan nilai masing–masing yaitu 0,3312 dan 0,3730. AbstractCredit card is one form of media for customers to credit in a transaction process that has been approved by the bank concerned. Banks should be selective in analyzing customers who want to apply for credit card issuance to avoid bad debts that can cause losses to banks, so it is very important to know the characteristics of customers by clustering. The Bank will be able to take decisions for credit card issuance by matching new customers into the established clusters and knowing the eligibility of customers to be granted credit card access in making transactions. K-Means is a popular method that is applied in the clustering process. However, the K-Means method can not provide the optimum solution because of its limitation in determining the optimal centroid point, so to improve the K-Means method in this research is used one of the evolution algorithm namely Particle Swarm Optimization (PSO) to generate optimum centroid point used in k-means calculation process. The test results were performed by comparing the coefficient silhouette values of the clusters formed using pure K-Means and Improved K-Means with PSO which yielded respective values of  0,31614 and 0,39484, respectively. 
Sistem Rekomendasi Profesi Berdasarkan Dimensi Big Five Personality Menggunakan Fuzzy Inference System Tsukamoto Mar'i, Farhanna; Mahmudy, Wayan Firdaus; Yusainy, Cleoputri
Jurnal Teknologi Informasi dan Ilmu Komputer Vol 6 No 5: Oktober 2019
Publisher : Fakultas Ilmu Komputer, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (4012.459 KB) | DOI: 10.25126/jtiik.201965942

Abstract

Sistem rekomendasi dapat dimanfaatkan sebagai alat bantu untuk pengambilan keputusan. Pada sebuah perusahaan, sistem rekomendasi profesi bisa digunakan untuk menempatkan seorang karyawan pada posisi yang tepat. Pada penelitian ini diusulkan sistem rekomendasi profesi berdasarkan Big Five Personality traits yang meliputi Extraversion, Aggreableness, Conscentiousness, Neuroticm, dan Opennes. Input yang digunakan ialah parameter dimensi Big Five Personality yang dirumuskan oleh John. Metode yang digunakan adalah Fuzzy Inference System (FIS) Tsukamoto. Keakuratan sistem dihitung dengan membandingkan output sistem dengan dengan acuan Top Ranked Personality - Based Work Styles for 22 Job Families yang menghasilkan nilai akurasi sebesar 63%.AbstractRecommendation systems can be used as a tool for decision making. In a company, a professional recommendation system can be used to place an employee in the right position. In this study proposed system of professional recommendation based on Big Five Personality traits which includes Extraversion, Aggreableness, Conscentiousness, Neuroticm, and Opennes. The input used is the Big Five Personality dimension parameter formulated by John. The method used is Fuzzy Inference System (FIS) Tsukamoto. The accuracy of the system is calculated by comparing the output of the system with the reference Top Personality - Based Work Styles for 22 Job Families that produce an accuracy score of 63%.
Perancangan Sistem Informasi Pengarsipan Surat Berbasis Web Di UPT SMPN 34 Gresik Ananda Hafiz Syawala; Farhanna Mar`i
JURAL RISET RUMPUN ILMU TEKNIK Vol. 3 No. 1 (2024): April : Jurnal Riset Rumpun Ilmu Teknik
Publisher : Lembaga Pengembangan Kinerja Dosen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55606/jurritek.v3i1.2795

Abstract

One of the educational institutions that is involved in managing correspondence is UPT SMPN 34 Gresik. Because UPT SMPN 34 Gresik still applies manual accounting methods, it requires a lot of paper for recording and as a result there is a buildup of archival data. Researchers propose the use of a MySQL database and a design process to create a web-based letter filing system to overcome these problems. Fall out. After this research is completed, a web-based letter filing system will be developed at UPT SMPN 34 Gresik with the aim of increasing efficiency, speeding up the archiving process, and ensuring accurate and safe document storage. The web-based technology letter filing system is expected to simplify administrative tasks and improve school policy and human resource management, based on insights from observation, interview and literature study methodologies. The aim of this research is to be able to provide UPT SMPN 34 Gresik with comprehensive and long-term answers to its demands.
Comparation of Federated and Centralized Learning for Image Classification Farhanna Mar'i; Ahmad Afif Supianto; Fitra Abdurrachman Bachtiar
PIKSEL : Penelitian Ilmu Komputer Sistem Embedded and Logic Vol. 11 No. 2 (2023): September 2023
Publisher : LPPM Universitas Islam 45 Bekasi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33558/piksel.v11i2.7367

Abstract

Federated Learning (FL) is a new approach in machine learning or it can also be called collaborative learning, which is a machine learning method that includes client devices to carry out the training process, so that clients do not need to send training data to the server but directly conduct training on their respective devices. respectively. The models generated from local training will be sent to the server for further global aggregation. Therefore, FL is referred to as machine learning which can maintain the privacy of the data owner, because the data is not submitted to the server and is still stored in each client's device. In this study, a performance comparison will be carried out to prove whether the latest approach which is Federated Learning, can produce the same accuracy performance as the traditional approach, that is Centralized Machine Learning, in the case of Image Classification. The comparison of two approaches would be conducted by using the Open Source Image Classification dataset, namely MNIST. The performance of two approaches would be presented by evaluation that is Accuracy. The result shows that Federated Learning almost overcome the performance of Centralized Learning in the case of Image Classification by provided Accuracy 76%.
Hybrid Artificial Bee Colony and Improved SimulatedAnnealing for the Capacitated Vehicle Routing Problem Mar'i, Farhanna; Ubaidillah, Hafidz; Mahmudy, Wayan Firdaus; Supianto, Ahmad Afif
Knowledge Engineering and Data Science
Publisher : citeus

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

Abstract

Capacitated Vehicle Routing Problem (CVRP) is a type of NP-Hard combinatorial problem that requires a high computational process. In the case of CVRP, there is an additional constraint in the form of a capacity limit owned by the vehicle, so the complexity of the problem from CVRP is to find the optimum route pattern for minimizing travel costs which are also adjusted to customer demand and vehicle capacity for distribution. One method of solving CVRP can be done by implementing a meta-heuristic algorithm. In this research, two meta-heuristic algorithms have been hybridized: Artificial Bee Colony (ABC) with Improved Simulated Annealing (SA). The motivation behind this idea is to complete the excess and the lack of two algorithms when exploring and exploiting the optimal solution. Hybridization is done by running the ABC algorithm, and then the output solution at this stage will be used as an initial solution for the Improved SA method. Parameter testing for both methods has been carried out to produce an optimal solution. In this study, the test was carried out using the CVRP benchmark dataset generated by Augerat (Dataset 1) and the recent CVRP dataset from Uchoa (Dataset 2). The result shows that hybridizing the ABC algorithm and Improved SA could provide a better solution than the basic ABC without hybridization.
Pengembangan Sistem Presensi Guru UPT SMPN 34 Gresik Berbasis Web Muhammad Ibnu Rosikhin; Farhanna Mar’i
Jupiter: Publikasi Ilmu Keteknikan Industri, Teknik Elektro dan Informatika Vol. 2 No. 1 (2024): Januari : Publikasi Ilmu Keteknikan Industri, Teknik Elektro dan Informatika
Publisher : Asosiasi Riset Ilmu Teknik Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61132/jupiter.v2i1.59

Abstract

UPT SMPN 34 Gresik is one of the educational institutions that faces challenges in managing teacher attendance and salaries efficiently. Because UPT SMPN 34 Gresik currently still uses manual recording of teacher attendance, so it takes quite a long time. To overcome this problem, the researcher proposes creating a web-based Teacher Attendance System using the Waterfall design methodology with a MySQL database. The aim of establishing this web-based teacher attendance system is to assist teachers in carrying out attendance attendance efficiently and assist educators and teaching staff in managing teacher salaries based on attendance better. The need for an inclusive teacher attendance system, and the need for optimal salary calculations at UPT SMPN 34 Gresik are resolved through this research. From the conclusions obtained from the process of observation, interviews and literature study, this web-based teacher attendance system is expected to increase the efficiency of human resource management in the education sector. Researchers hope to provide comprehensive and sustainable answers to the needs of UPT SMPN 34 Gresik.
Co-Authors Ade Nur Kurnia Rizqi Ananda Agung Gumilang Ahmad Afif Supianto Ahmad Afif Supianto Ahmad Afif Supianto Ananda Hafiz Syawala Bariza Nurus Shobah Choridatul Bahiyyah Cleoputri Yusainy Desiyarotur Risykiyana Fitra Abdurrachman Bachtiar Hafidz Ubaidillah Hafidz Ubaidillah Harunur Rosyid Hendry Y. Nanlohy Henny Dwi Bhakti Irvi Oktanisa Marianingsih, susi Muhammad Al Amin Muhammad Ibnu Rosikhin Nadya Husenti Purnomo Budi Santoso Rakhmadhan Rizki Brilian Ubaidillah, Hafidz Ullump Pratiwi Umi Chotijah Wayan Firdaus Mahmudy