Claim Missing Document
Check
Articles

Found 15 Documents
Search

Real-Time Retail Shelf-Stock Detection with YOLOv7 Alquratu SeptriaPS, Annies; Silvia Handayani, Ade; Nasron, Nasron
JURNAL TEKNIK INFORMATIKA Vol. 18 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.v18i2.46448

Abstract

This study developed a real-time shelf stock monitoring system for retail environments, leveraging the You Only Look Once version 7 (YOLOv7) deep learning-based object detection framework. The system effectively addresses the inefficiencies, delays, and errors inherent in manual stock auditing processes. The underlying model was trained on a comprehensive dataset comprising 15,397 annotated object labels across fifteen distinct retail product categories. The fully trained model was then integrated into a web-based platform designed to capture real-time shelf images via a webcam. These captured images undergo automated processing for product detection and counting. The detection results are dynamically displayed on an interactive dashboard and securely stored in a backend database. The system also incorporates voice alerts, which are triggered automatically when stock levels fall below predefined thresholds, thereby facilitating immediate restocking. Experimental validation indicates high performance, with both precision and recall exceeding 96%, and an average processing latency of less than one second per frame. The model achieved an mAP@0.5 of 0.996 and an mAP@0.5:0.95 of 0.86. These findings underscore the system's effectiveness in providing a rapid, accurate, and efficient monitoring solution specifically tailored for small to medium-sized retail businesses. The primary contribution of this research lies in its comprehensive, end-to-end system integration, combining robust YOLOv7-based object detection with real-time web visualization and automated voice alerts, successfully addressing existing gaps in prior implementations.
Perangkat Cerdas Deteksi Banjir Menggunakan Sensor Ultrasonik dan Sensor Curah Hujan dengan Metode Forecasting Rahmawati, Arma; Suroso, Suroso; Nasron, Nasron
Jurnal Teknologi Sistem Informasi dan Aplikasi Vol. 7 No. 3 (2024): Jurnal Teknologi Sistem Informasi dan Aplikasi
Publisher : Program Studi Teknik Informatika Universitas Pamulang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32493/jtsi.v7i3.42029

Abstract

Flooding is a natural disaster that most often affects Indonesia. South Sumatra is one of the areas that experienced recurrent flooding from 2023 to 2024. Monitoring of water levels at a point is often lacking, so that during high rainfall, water often overflows and causes flooding. Uncontrolled water discharge due to heavy rainfall can cause flooding and impact the local community due to lack of information. To solve this problem, machine learning technology can be used as a flood detection and early warning tool. The SVR (Support Vector Regression) algorithm is one example. This research classifies flood status into three categories: "Safe, Alert, and Danger." The flood status prediction model is built using SVR (Support Vector Regression) integrated with a flood detection device consisting of Arduino Uno, NodeMCU, and two sensors, namely an ultrasonic sensor and a rainfall sensor, which are installed above 1 metre from the ground. The test results show that this device can detect flood status based on the water level. When the distance between the water surface and the sensor is 80-100 cm and the rainfall is 0-20 mm, the status is safe, if the water distance is 50-80 cm and the rainfall is 21-30 mm, the status is alert, while if the water distance is 0-50 cm and the rainfall is 31-100 mm, the status is dangerous. The flood status detected by this tool will then be sent via the Telegram application as a notification to facilitate effective flood monitoring.
Macam-Macam Perkembangan Media Pembelajaran Dalam Proses Belajar Mengajar Di Indonesia Nasron, Nasron; Nurhasanah, Nurhasanah; Suranda, Novalyo; Khadafi, Muhammad
Innovative: Journal Of Social Science Research Vol. 4 No. 4 (2024): Innovative: Journal Of Social Science Research
Publisher : Universitas Pahlawan Tuanku Tambusai

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31004/innovative.v4i4.14744

Abstract

Media pembelajaran juga berfungsi sebagai sumber belajar, membantu guru dalam memudahkan pemahaman materi ajar oleh siswa dan memperkaya wawasan peserta didik. Menurut Levie dan Lentz (1982), media pembelajaran memiliki empat fungsi utama: menarik perhatian siswa (fungsi atensi), menggugah emosi dan sikap siswa (fungsi afektif), memperlancar tujuan untuk memahami dan mengingat informasi (fungsi kognitif), dan mengakomodasikan siswa yang lemah dan lambat menerima informasi (fungsi compensations) . Media pembelajaran berkembang dikelas tentu memudahkan dalam setiap laju pembelajaran, berbagai konsep serta gagasan pembelajaran dijadikan konkrit dengan adanya media pembelajaran. Siswa tidak semua mudah berfikir secara kritis, maka dai itu adanya media pembelajaran itu menjadi jembatannya. Guru menjadi media untuk penyampain materi atau ilmu dan media menjadi bagian yang sangat penting bagi guru, selain memudahkan itu dapat mengefisienkan waktu. Bagaimana media digunakan agar baik perlunya seorang guru mengetahui sejauh mana siswa membutuhkan, dan mana media yang pas dan relevan dengan apa yang di pelajari oleh murid tersebut. Guru juga harus mengoptimalkan bagaimana pelajaran tersampaikan dengan bantuan media yang sesuai dengan pelajaran tersebut. Jangan sampai media dan pelajaran yang disampaikan itu berlainan, karna akan mendapatkan kerancuan pemahaman kepada anak.
Pengembangan Server VOIP Menggunakan FREEPBX Dan Asterisk Berbasis Raspberry PI Nasron, Nasron; Mujur Rose, Martinus; Fadhilah, Darin
PROtek : Jurnal Ilmiah Teknik Elektro Vol 8, No 1 (2021): Protek : Jurnal Ilmiah Teknik Elektro
Publisher : Program Studi Teknik Elektro Universitas Khairun

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33387/protk.v8i1.2222

Abstract

Raspberry Pi is a single board computer that the author uses as a voip server based on asterisk. To use this voip network, each device must have a static IP as well as be connected to a stable network. The advantage of using raspberry pi is that it no longer costs money to make voice calls for both package and pulse costs. The purpose and benefits of this research to know how raspi works, know how to install voip server using freepbx and asterisk, know how to install voip client on smartphones and laptops dang know the topology of raspi-based voip network, and know how to test stages of searching for throughput, loss package, delay, and jitter using wireshark
Monitoring Of Household Electricity Usage Based On The Internet Of Things Fatin, Muhammad Hanif; Nasron, Nasron; Sarjana, Sarjana; Saputra, Muhammad Renaldy
MOTIVECTION : Journal of Mechanical, Electrical and Industrial Engineering Vol 7 No 2 (2025): Motivection : Journal of Mechanical, Electrical and Industrial Engineering
Publisher : Indonesian Mechanical Electrical and Industrial Research Society (IMEIRS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46574/motivection.v7i2.460

Abstract

The increasing demand for energy efficiency in the digital era has accelerated the adoption of Internet of Things (IoT)-based technologies in household electricity management. This study presents the design and implementation of an IoT-based real-time electricity monitoring system using the ESP32 microcontroller and PZEM-004T sensor, integrated with the Blynk application for remote access. The system measures voltage, current, power, energy consumption, and cost, displaying data on both an LCD and a mobile interface. Experimental testing involved household appliances such as fans and rice cookers under individual and combined usage, with measurements taken at 15-minute intervals. The results demonstrated strong agreement between theoretical calculations and real-time data, with the measured values slightly higher due to the dynamic nature of electrical loads. The system achieved a low average error rate of 0.17%, with a maximum error of 0.30%. These findings confirm the accuracy and reliability of the system, supporting its potential for enhancing user awareness, improving billing precision, and contributing to sustainable energy use in smart home applications.