Garuda - Garba Rujukan Digital

Perancangan Sistem Pendeteksi Stok Berbasis Machine Learning dan Mikrokontroler Untuk Digitalisasi Usaha Mikro Kecil dan Menengah Gracia Novelly Krisantia Emor; Vina Sari Yosephine
Jurnal Serambi Engineering Vol. 9 No. 2 (2024): April 2024
Publisher : Faculty of Engineering, Universitas Serambi Mekkah

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

Improving operational efficiency and inventory management is a major challenge for micro, small and medium enterprises (MSMEs) in the digital era. This research develops a digital model that integrates a microcontroller-based Internet of Things (IoT) and machine learning to improve inventory management for MSMEs. The aim is to explore how digital technologies can improve the operational efficiency of MSMEs, with a particular focus on inventory management. The methodology employed includes prototyping, using IoT and deep learning techniques for remote detection of product inventory levels. The findings show that the synergistic integration of IoT sensors and machine learning algorithms can significantly improve the efficiency of inventory management, by enabling real-time detection of product stock levels and providing accurate inventory data. The adoption of IoT and machine learning offers significant potential to improve the operational efficiency and business growth of MSMEs through more efficient inventory management. This study contributes to the understanding of the application of digital technologies in MSME inventory management,

IoT-based inventory monitoring system for SMEs Lora Ristio Gultom; Vina Sari Yosephine
TEKNOSAINS : Jurnal Sains, Teknologi dan Informatika Vol 11 No 2 (2024): TEKNOSAINS: Jurnal Sains, Teknologi dan Informatika
Publisher : LPPMPK-Sekolah Tinggi Teknologi Muhammadiyah Cileungsi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37373/tekno.v11i2.1092

Industry 4.0's pervasive digital ideas have completely changed how businesses operate. A lot of big businesses have switched to digital systems. However, due to a lack of funding and digital infrastructure, SME sector digitalization issues still exist. Inventory management is one of the many manual methods that many SMEs still have to rely on, which makes it prone to error. To manage inventories more accurately and effectively, manual systems must be changed. The goal of this project is to improve inventory management efficiency by creating a dependable and affordable automated system. A cloud database is connected to the system to provide quick inventory monitoring on warehouse shelves. Prototyping and statistical testing are used in the study technique to evaluate the system's dependability. Using an Internet of Things-based single-board computer, the research creates an inventory monitoring system. With a daily implementation cost of IDR 642.92, the system is deemed cost-effective based on inventory monitoring results on warehouse shelves. Because the system's performance reached a Cronbach's alpha value greater than 0.8, the inventory management system used in the study is regarded as dependable for application in real-world systems to increase inventory management accuracy

Pemelajaran Mesin untuk Pengendalian Mutu pada Proses Produksi Tekstil Tradisional Yosephine, Vina Sari; Hanna, Tabitha; Setiawati, Marla; Setiawan, Ari
Jurnal Rekayasa Sistem Industri Vol. 13 No. 1 (2024): Jurnal Rekayasa Sistem Industri
Publisher : Universitas Katolik Parahyangan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26593/jrsi.v13i1.7173.165-174

This research is centered on the practical implementation of machine learning and computer vision technologies to enhance production quality control within the traditional textile industry. The traditional textile sector, known for labor-intensive practices, has slowly adapted to digital transformation. We present a practical case study from Bandung, Indonesia, to validate the effectiveness of our approach in real-world textile manufacturing. By emphasizing machine learning and computer vision, this research narrows the gap between traditional textile practices and digitalization, offering tailored solutions for manufacturers seeking to excel in today's rapidly changing global market. The findings provide valuable insights into the challenges and opportunities of using machine learning and computer vision for production quality control in traditional textile manufacturing. The machine learning models in the study showed good accuracy, ranging from 75% to 100% under various lighting conditions in real-world textile manufacturing environments, confirming their suitability for practical quality control applications.

Sistem manajemen gudang untuk UMKM dan pemanfaatan machine learning pada penjualan grosir minuman Raisa Nuraffifa Sudardjat; Vina Sari Yosephine
INFOTECH : Jurnal Informatika & Teknologi Vol 5 No 1 (2024): INFOTECH: Jurnal Informatika & Teknologi
Publisher : LPPMPK - Sekolah Tinggi Teknologi Muhammadiyah Cileungsi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37373/infotech.v5i1.1186

Di era industri 4.0, transformasi digital merupakan hal yang penting untuk meningkatkan fleksibilitas dan efisiensi operasional. Koneksi yang lebih baik dan teknologi seperti Internet of Things, artificial intelligence, dan robotika telah mengubah cara industri memproduksi, mengelola, dan berinteraksi dengan pelanggan. Usaha Mikro, Kecil, dan Menengah kini tengah menghadapi tantangan khusus dalam transformasi tersebut, terutama terkait dengan investasi yang signifikan untuk infrastruktur TI dan kebutuhan tenaga kerja yang mahir dalam keterampilan digital. Hambatan tersebut dapat menghambat adopsi dan integrasi penuh inovasi digital oleh UMKM. Meskipun demikian, transformasi digital sangat berpotensi bagi UMKM, terutama dalam pengembangan aplikasi manajemen gudang yang memanfaatkan teknologi digital. Inovasi tersebut dapat meningkatkan efisiensi secara signifikan dalam pemantauan stok, pelacakan inventory, dan pengelolaan logistik secara real-time, sehingga berdampak pada keberlanjutan bisnis UMKM di era digital. Penelitian ini bertujuan untuk mengembangkan model manajemen gudang yang terdiri dari sistem informasi dan teknologi machine learning yang disesuaikan untuk UMKM. Hasil pengujian laboratorium menunjukkan bahwa sistem ini memiliki tingkat akurasi yang tinggi, sehingga sesuai untuk digunakan oleh UMKM

Scalable and Affordable IoT-based Inventory Control with Real-Time Monitoring for Small and Medium Enterprises Yosephine, Vina Sari; Batara, Marco; Setiawati, Marla
Jurnal Teknik Industri: Jurnal Keilmuan dan Aplikasi Teknik Industri Vol. 27 No. 1 (2025): June 2025
Publisher : Institute of Research and Community Outreach - Petra Christian University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.9744/jti.27.1.121-136

Small and medium enterprises (SMEs) often struggle to adopt advanced inventory management systems due to high implementation costs and infrastructure complexity—barriers that are especially challenging in the context of Industry 4.0. This paper presents a scalable and affordable IoT-based stock monitoring and control system designed for small and medium enterprises. The proposed system integrates low-cost microcontrollers with ultrasonic sensors, enabling real-time stock tracking while reducing hardware expenses and complexity. Unlike existing solutions, it leverages a modular architecture for seamless scalability across different inventory sizes and environments. The system is validated through compliance with the Industry 4.0 Maturity Index and the ISA-95 standard, demonstrating its suitability for digital transformation in SME operations. Performance evaluation shows an accuracy rate exceeding 98% and response times under 10 seconds, ensuring reliable operation under varying environmental conditions. A comparative cost analysis highlights significant savings compared to conventional automated inventory systems. This approach provides an accessible entry point for SMEs seeking to enhance inventory visibility, operational efficiency, and readiness for Industry 4.0 integration.

Alat Pendeteksi Stok Barang Berbasis IoT untuk UMKM dengan Sensor Ultrasonik dan Inframerah Batara, Marco; Yosephine, Vina Sari
Journal of Integrated System Vol. 7 No. 1 (2024): Journal of Integrated System Vol. 7 No. 1 (June 2024)
Publisher : Universitas Kristen Maranatha

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.28932/jis.v7i1.8525

Di era Industri 4.0 UMKM Indonesia menghadapi tantangan dalam mengadopsi transformasi digital baik dari sisi pembiayaan maupun sumber daya manusia. Manajemen gudang merupakan contoh yang sering terabaikan. Pengelolaan inventori yang efisien menjadi penting untuk meningkatkan efisiensi operasional dan rantai pasok UMKM. Penelitian ini bertujuan untuk membangun model digitalisasi pemantauan stok untuk pemantauan operasi gudang secara real-time yang dikhususkan kepada UMKM. Sistem tersebut menggabungkan sistem informasi, single board computer, sensor ultrasonik, dan sensor inframerah dalam satu platform IoT untuk memberikan informasi inventori secara real-time. Analisis reliabilitas statistik pada pengujian menunjukkan tingkat konsistensi yang sangat tinggi yaitu nilai Cronbach's Alpha dan Intraclass Correlation Coefficient di atas 0.9. Hasil ini menunjukkan bahwa model tersebut dapat secara akurat memantau dan mengelola inventori, sehingga UMKM dapat membuat keputusan yang lebih tepat dan cepat. Nilai investasi sistem sebesar Rp103.350 sehingga model digital terjangkau dan mudah diimplementasikan bagi UMKM dalam mengadopsi teknologi digital khususnya dalam manajemen gudang.

Pemelajaran Mesin untuk Pengendalian Mutu pada Proses Produksi Tekstil Tradisional Yosephine, Vina Sari; Hanna, Tabitha; Setiawati, Marla; Setiawan, Ari
Jurnal Rekayasa Sistem Industri Vol. 13 No. 1 (2024): Jurnal Rekayasa Sistem Industri
Publisher : Universitas Katolik Parahyangan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26593/jrsi.v13i1.7173.165-174

This research is centered on the practical implementation of machine learning and computer vision technologies to enhance production quality control within the traditional textile industry. The traditional textile sector, known for labor-intensive practices, has slowly adapted to digital transformation. We present a practical case study from Bandung, Indonesia, to validate the effectiveness of our approach in real-world textile manufacturing. By emphasizing machine learning and computer vision, this research narrows the gap between traditional textile practices and digitalization, offering tailored solutions for manufacturers seeking to excel in today's rapidly changing global market. The findings provide valuable insights into the challenges and opportunities of using machine learning and computer vision for production quality control in traditional textile manufacturing. The machine learning models in the study showed good accuracy, ranging from 75% to 100% under various lighting conditions in real-world textile manufacturing environments, confirming their suitability for practical quality control applications.

A Cyber-Physical and AI-Based Digitalization Framework for Traditional Textile SMEs Tarigan, Amenda Septiala; Yosephine, Vina Sari; Dewi, Intan Novita Dewi; Mardhiyah, Wendy Febrianty Mardhiyah; Sarinindiyanti, Julin Arum Sarinindiyanti; Putra, Harditriyono Putra
JURNAL TEKNIK INDUSTRI Vol. 15 No. 3 (2025): November 2025
Publisher : Jurusan Teknik Industri, Fakultas Teknologi Indusri Universitas Trisakti

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25105/jti.v15i3.22880

Traditional textile SMEs still rely on manual processes, resulting in inefficiencies in production and data management. This study proposes a cost-conscious digitalization framework that integrates Cyber-Physical Systems (CPS), a lightweight information layer, and artificial intelligence (AI), specifically designed for labour-intensive textile operations. The framework adheres to the ISA-95 architecture, emphasizing affordability and scalability. Stakeholder interviews, business process reengineering, and a three-month field implementation were conducted in a textile hub in Bandung. Key digital tools, including e-kiosks for real-time logging, integrated digital scales for inventory management, and mobile vision-based quality control using convolutional neural networks (Xception and VGG), were evaluated through an immersion study and user acceptance testing. Evaluation results show improvements in workflow visibility, data reliability, and consistency of quality inspection compared to the pre-digitalized process, while maintaining ease of use for operators. Evaluation results indicate qualitative operational improvements—such as enhanced workflow visibility, more reliable data capture, and more consistent quality inspection—reflecting meaningful enhancements observed during the digitalization pilot. The study contributes a replicable CPS–AI model that enables traditional SMEs to enhance efficiency and quality through scalable digital transformation.

Title

Found 8 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 8 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 8 Documents
Search