Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal Jurnal Sisfokom (Sistem Informasi dan Komputer) Neptunus: Jurnal Ilmu Komputer dan Teknologi Informasi
Stefani Hardiyanti Putri
Unknown Affiliation
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Penerapan Sistem Informasi Pemasaran Toko Oleh-Oleh Makanan Khas Danau Maninjau Berbasis WEB Wizra Aulia; Stefani Hardiyanti Putri; Imelda Juniarta Emin
Neptunus: Jurnal Ilmu Komputer Dan Teknologi Informasi Vol. 3 No. 3 (2025): Agustus : Neptunus : Jurnal Ilmu Komputer Dan Teknologi Informasi
Publisher : Asosiasi Riset Teknik Elektro dan Informatika Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61132/neptunus.v3i3.1035

Abstract

Lake Maninjau specialty food souvenir shop is one of the micro businesses that sells a variety of traditional regional food products. So far, the marketing process and transaction management are still done manually, which causes limited market reach, difficulty in recording sales, and lack of effectiveness in product promotion. This research aims to design a web-based marketing information system to support the sales process, promotion, and data management in a more efficient and integrated manner. The system development method uses the System Development Life Cycle (SDLC) approach of the waterfall model, which includes the planning, needs analysis, system design, implementation, and testing stages. Data collection was conducted through field observations, interviews with business owners, questionnaires to customers, and literature studies related to information systems and digital marketing strategies. The designed information system includes various main features such as product data management, sales transaction recording, automatic sales report generation, social media integration, and product promotion pages. In the marketing aspect, this system allows businesses to display product catalogs online, provide real-time promotional information, and establish direct interaction with customers through contact and ordering features. In addition, the use of this system allows stores to reach a wider market, including potential customers from outside the Lake Maninjau area, through an integrated digital marketing strategy. The implementation results show that this web-based system can increase the effectiveness of product promotion, speed up the transaction process, and improve the quality of customer service. With this system, souvenir shops can compete more competitively in the digital era, as well as strengthen brand image and customer loyalty through more structured and sustainable marketing.
ResNet50-Based Deep Learning Architecture with Focal Loss Optimization for Automated Fruit Ripeness Classification Stefani Hardiyanti Putri; Nasrullah; Fefi Maulana; Prilia Rahmayanti; Efmi Maiyana
Jurnal Sisfokom (Sistem Informasi dan Komputer) Vol. 15 No. 01 (2026): JANUARY
Publisher : ISB Atma Luhur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32736/sisfokom.v15i01.2449

Abstract

This study develops an Enhanced ResNet50 architecture with Focal Loss optimization for automated fruit ripeness classification. The research implements systematic modifications to the standard ResNet50 framework, incorporating attention mechanisms, strategic transfer learning with 20 trainable layers, and advanced class imbalance handling through Focal Loss function (α=[0.809, 1.904, 0.807], γ=2.0). The model processes RGB images (224×224×3) across three ripeness categories: Overripe, Ripe, and Unripe, utilizing the Kaggle Fruits Ripeness Classification Dataset containing 4,434 high-quality images. The Enhanced ResNet50 architecture achieves 97.22% classification accuracy with corresponding precision, recall, and F1-scores of 0.9722, demonstrating superior performance compared to standard ResNet50 (91.7%), VGG16 (89.2%), and EfficientNet-B0 (88.5%). The model exhibits efficient computational characteristics with 50-100ms inference time and 104.55 MB model size, while successfully addressing mild class imbalance (ratio 0.424) through systematic optimization techniques.
Co-Authors Efmi Maiyana Fefi Maulana Imelda Juniarta Emin Nasrullah Prilia Rahmayanti Wizra Aulia