Article Per Year (5 Year)
p-Index From 2021 - 2026
5.945
P-Index
This Author published in this journals
All Journal Jurnal Algoritma JUITA : Jurnal Informatika JURNAL TEKNIK INFORMATIKA DAN SISTEM INFORMASI Journal of Community Development Jurnal Diksatrasia : Jurnal Ilmiah Pendidikan Bahasa dan Sastra Indonesia Jurnal Algoritma
Leni Fitriani
Institut Teknologi Garut
Computer Science & IT Education Languange, Linguistic, Communication & Media Nursing Public Health Social Sciences

Published : 126 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 126 Documents
Search

 9   10   11   12   13 
Transformer-Based Detection Model for Number Recognition on Electric kWh Meters Leni Fitriani; Ahmad Sanusi; Rita Rismala; Dewi Tresnawati
JUITA: Jurnal Informatika JUITA Vol. 13 Issue 2, July 2025
Publisher : Department of Informatics Engineering, Universitas Muhammadiyah Purwokerto

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30595/juita.v13i2.26161

Abstract

Manual recording of analog kWh meters frequently results in user complaints due to discrepancies between recorded and actual electricity usage. These issues stem from the continued reliance on manual data collection. This study proposes a model that automatically detects and extracts numerical values from kWh electricity meters using the Detection Transformer (DETR) for object detection and EasyOCR for optical character recognition (OCR). The model was developed using the Machine Learning Life Cycle (MLLC) methodology, comprising data acquisition, preprocessing, modeling, evaluation, and deployment. Evaluation using the Mean Average Precision (mAP) metric yielded a score of 96.83%, demonstrating high object detection accuracy. The trained model was integrated into a simple web application built with the Flask framework. While the model performed well on high-quality images, its effectiveness declined on low-quality images, such as blurry or distant captures. This study highlights the potential of DETR for object detection and OCR-based text extraction in analog meter reading, while also identifying challenges in handling suboptimal image conditions for future improvements
Pendampingan Kelompok UMKM di Garut Dalam Penggunaan Dompet Digital Untuk Mendukung Ekonomi Digital Rina Kurniawati; Leni Fitriani; Muhammad Rikza Nashrulloh
Journal of Community Development Vol. 5 No. 3 (2025): April
Publisher : Indonesian Journal Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47134/comdev.v5i3.1292

Abstract

The community service program aimed to enhance the competitiveness of Micro, Small, and Medium Enterprises (MSMEs) in Garut Regency through the implementation of digital wallet technology. Addressing the challenges of market access and financial management faced by MSMEs, the program developed an application called MitraREID. This application was designed to assist MSMEs in managing transactions, recording expenses, generating financial reports, and optimizing product management. The implementation process included socialization, intensive training, application deployment, and technical assistance involving the UMKM community, Mikromega, in Garut. The results indicated a significant improvement in the MSMEs' ability to utilize digital technology for daily operations. The MitraREID application facilitated business management, enhanced transaction efficiency, and allowed MSMEs to structure their financial management more effectively. The program's impact was quantitatively measured by pre- and post-test scores, which showed an increase from an average of 79/100 before training to 99/100 after training. This significant improvement demonstrated the enhanced digital skills and understanding of participants in utilizing digital wallet technology to support their business operations, enabling them to compete more effectively in local and national markets.
Melatih Cara Berfikir Komputasi Pada Siswa Sekolah Dasar dan Menengah di Kabupaten Garut Dewi Tresnawati; Detila Rostilawati; Ayu Latifah; Eri Satria; Asri Mulyani; Sri Rahayu; Leni Fitriani; Rinda Cahyana; Shopi Nurhidayanti; Cha Cha Nisya Asyah
Journal of Community Development Vol. 5 No. 2 (2024): December
Publisher : Indonesian Journal Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47134/comdev.v5i2.1373

Abstract

Technological advances in the 21st century demand Computational Thinking skills that are increasingly important in the digital era. However, the application of Computational Thinking (CT) at the primary and secondary education levels in Garut Regency is still limited. This study aims to improve the understanding of CT among students in elementary schools, junior high schools, and vocational high schools through a training program that includes pre-test, interactive training, and post-test. The training method was designed according to the educational level of the participants, using Bebras questions to train CT skills. The pre-test results showed an average initial score of 47.19, while the post-test results increased by an average of 25.75 points to 72.94. The findings show that the training successfully improved participants' understanding of CT through a structured approach, including introduction of concepts through sample Bebras problems, practice problems, as well as a comprehensive question and answer session.
Integrasi Flowise AI dan LLM Gemini Untuk Chatbot Wisata Berbasis Website dengan Dukungan API Fitri Nuraeni; Muhammad Ghopur; Rinda Cahyana; Leni Fitriani
Jurnal Algoritma Vol 23 No 1 (2026): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.23-1.2590

Abstract

Tourism destination information is often scattered across various unintegrated sources, making it difficult for visitors to obtain quick and accurate answers. This problem can be overcome by implementing chatbot technology that is capable of providing automated responses based on verified data. This study aims to implement a tourism information service chatbot using the open-source Flowise AI platform integrated with Google's Gemini Large Language Model (LLM). The system development method uses a waterfall approach, including analysis, design, implementation, testing, deployment, and maintenance. Tourism information data is converted into vector representations through GoogleGenerativeAI Embeddings and stored in a vector store. The question and answer process is carried out using Conversational Retrieval QA Chain to generate relevant responses based on source documents. Testing results show that the chatbot is capable of providing fast, accurate, and appropriate answers based on available data, covering historical information, facilities, rates, cuisine, routes, accommodations, and tourism regulations. The contribution of this research is to provide an AI-based digital solution that facilitates access to tourism information, enhances user experience, and supports efficient tourism destination promotion.
Aplikasi Monitoring Distribusi Buku Berbasis Web Menggunakan Metode RUP Adi Haddaryadi; Leni Fitriani
Jurnal Algoritma Vol 23 No 1 (2026): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.23-1.2827

Abstract

Monitoring is the process of continuously collecting data and information to objectively assess the results of activities and improve the efficiency and effectiveness of mapping. Book distribution is part of marketing activities that play an important role in facilitating distribution from producers to consumers. At CV. Fazza Media, which is engaged in the distribution of school books in Garut Regency, the data collection process is still carried out using Microsoft Excel, which is prone to duplication and is inefficient. This study aims to develop a web-based book distribution monitoring information system using the Rational Unified Process (RUP) methodology, which includes the Inception, Elaboration, Construction, and Transition phases. The results of this study are an information system that supports distribution recording, school location mapping, and real-time shipment status tracking. This system makes it easier for companies to manage book distribution data, improves the efficiency of searching for distribution location information, and helps manage data in a more structured manner. The academic contribution of this research lies in the application of RUP in the context of map-based logistics distribution, while in practical terms, this system can be an initial model for the development of monitoring applications in other logistics sectors outside of book distribution.
Penerapan Arsitektur VGG-16 dalam Pengenalan Wajah Bermasker untuk Sistem Presensi Leni Fitriani; Rinda Cahyana; Fauzan Abdurrahman
Jurnal Algoritma Vol 23 No 1 (2026): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.23-1.2845

Abstract

Covid-19 membatasi interaksi fisik dan mendorong penggunaan masker, sementara sejumlah sistem pengenalan wajah konvensional mengharuskan masker dilepas sehingga risiko paparan meningkat oleh karena itu penting adanya sistem pengenalan wajah bermasker dalam pencegahan penularan Covid-19. Tujuan dari penelitian ini membuat model Convolutional Neural Network (CNN) untuk pengenalan wajah bermasker yang dapat diterapkan pada sistem presensi. Metode yang digunakan Machine Learning Life Cycle dan model dibuat menggunakan arsitektur VGG-16. Hasil penelitian ini berupa model yang diterapkan pada prototype sistem presensi yang dapat mengindentifikasi pengguna bermasker. Model dilatih 40 epoch dengan hasil nilai training accuracy 0.9900 serta nilai training loss 0.2694 sedangkan nilai validation accuracy 0.9500 serta nilai validation loss 0.4065. Evaluasi model oleh confusion matrix dengan hasil rata-rata akurasi sebesar 0.95 atau 95%. Pada tahap akhir pengujian, model digunakan pada prototype sistem presensi dengan hasil deteksi tercepat yaitu 6 detik dan terlama 42 detik yang mana hal tersebut menjadi kontribusi utama penelitian ini dengan sistem realtime dan pipeline augmentasi yang relevan untuk skenario wajah bermasker. Keterbatasan terletak pada skala data dan lingkungan uji yang terbatas. Penelitian selanjutnya diharapkan mencakup evaluasi menggunakan Real World Masked Face Recognition Dataset (RMFRD) atau Simulated Masked Face Recognition Dataset (SMFRD), eksplorasi arsitektur yang lebih bervariasi, serta percepatan inferensi.
Co-Authors A.A. Ketut Agung Cahyawan W Abdurohman Iqbal Abi Abdurahim Ade Sutedi Adi Haddaryadi Agas Moch Fauzan Ahmad Ilham Maulana Ahmad Sanusi Aji Pangestu Aldy Rialdy Atmadja Annisa Ridha Ramadhani Asri Mulyani Ayu Latifah Ayu Latifah Azmi Inda Roby Bunyamin . Cecep Iqbal Hambali Cha Cha Nisya Asyah Dede Kurniadi Detila Rostilawati Dewi Tresnawati Dini Destiani Siti Fatimah Eri Satria Fakhrul Hawariyan Fassa Fauzan Abdurrahman Febriansyah Adli Ramadhan Fikri Zakaria Rahman Fitri Nuraeni Garnis Kirani Gema Semesta Sholihat Gilang Adi Pratama Husni Mubarok Ikbal Lukmanul Hakim Ilpad Mutaqin Intania Sintiani Isan Priana Ivan Muhammad Hanif M. Iqbal Ismail Safei Pamungkas Mohamad Fikri Haekal Mohamad Ramdan Nurul Falah Muhammad Bagja Sukriyansah Muhammad Dzulfi Muwaffaq Muhammad Ghopur Muhammad Rikza Nashrulloh Muhammad Rois Dien Nenden Zakiatinnufus Popi Maspupah Raden Erwin Gunadhi Rahayu Raden Erwin Gunadhi Rahayu Raden Nazar Labani Rendi Nurdian Ridwan Setiawan Rifan Miptah Purnama Rina Kurniawati Rina Kurniawati Rinda Cahyana Rinda Cahyana Risma Liyana Ulfa Rita Rismala Rival Firmansyah Sendra Ilham Mandala Sherine Valentin Margaretha Shopi Nurhidayanti Siti Hapsah Azizah Sri Rahayu ST Dini Nur Ismiyanti Taofik Faturochman Titin Rostini Tova Nanda Pratama Yoga Handoko Agustin Yosep Septiana