Jurnal Ilmu Komputer dan Teknologi Informasi

Pengklasifikasian Jenis Sampah Berbasis Visi Komputer Dan Kecerdasan Buatan

Gusti Made Kresna Wijaya Wijaya, Daffa Khairul Ammar — Sat, 28 Mar 2026 00:00:00 +0000

Waste management presents a significant challenge in ensuring environmental sustainability, requiring an automated classification system to improve efficiency. This study designs a waste classification system (biological, electronic, glass, plastic) using a deep learning approach based on computer vision. The proposed method implements a custom Convolutional Neural Network (CNN) with MobileNet efficiency principles, consisting of Mobile Inverted Bottleneck Convolution (MBConv) and Squeeze-and-Excitation (SE) blocks. The model is developed from scratch using a four-class dataset and optimized with GPU processing and a batch size of 16. After fine-tuning the regularization and hyperparameters, the model achieved the highest accuracy of 75.59%.

Klasifikasi Kompleksitas Gameplay Berbasis Struktur Kalimat pada Deskripsi Game

Abdul Raihan, Mhd Arief Hasan, M Fadilah Azhim, Ilham Fadilah — Sat, 28 Mar 2026 00:00:00 +0000

Game descriptions on digital distribution platforms play a crucial role in conveying the characteristics of gameplay to players. However, the language complexity of these descriptions varies and may influence players' understanding of the gameplay being offered. This study aims to classify gameplay complexity based on sentence structure in game descriptions using a Natural Language Processing (NLP) approach. The dataset used is the 10k Most Popular Gaming 2025 dataset obtained from Kaggle, with a focus on the game description column. The description data is grouped into three complexity classes: simple, medium, and complex, based on the linguistic characteristics of the text. The research process includes text preprocessing, sentence-structure-based linguistic feature extraction, and data balancing using the balance rank method. Classification is performed using the Logistic Regression, Random Forest Classifier, and Support Vector Machine algorithms. Evaluation results show that the Random Forest Classifier achieves the highest accuracy of 0.85, while Logistic Regression and Support Vector Machine obtain accuracies of 0.81 each. Feature analysis reveals that word count and average sentence length are the most influential features in determining gameplay complexity. Visualization using Principal Component Analysis shows a clear distribution pattern of complexity classes, although some overlap between classes remains. The results of this study demonstrate that sentence-structure-based linguistic analysis is effective in representing gameplay complexity in game descriptions.

Implementasi Sistem Sensor Aliran Air Otomatis di Rumah dengan Notifikasi Telegram Berbasis Internet of Things (IoT)

Ahmad yoga Afiludin — Sat, 28 Mar 2026 00:00:00 +0000

Water is a highly valuable and limited natural resource. To increase awareness of the global water crisis, it is important to minimize water wastage. With a water flow monitoring system, water resource management can be carried out more efficiently while ensuring fair water distribution. In this research, problems are often encountered in accurately measuring, controlling, and monitoring water usage. These issues can be caused by excessive water consumption, which may lead to losses. Based on these problems, a system was designed to provide notifications of water usage, enabling users to control water consumption, including the ability to remotely turn the water tap on or off. This study presents an innovative solution in the form of an intelligent water monitoring system using a Water Flow Sensor capable of calculating water discharge and a Motorized Ball Valve to automatically control the water tap based on Internet of Things (IoT) technology. To determine the accuracy of the Water Flow Sensor, experiments were conducted by comparing the water volume measured by the sensor with the volume measured using a graduated cylinder.

Sistem Sistem Iot Untuk Pemantauan Suhu Dan Kelembaban Ruangan Secara Real-Time Sebagai Indikator Kualitas Udara

Melinda Novita Sari, Sujono — Sat, 28 Mar 2026 00:00:00 +0000

Indoor air quality is an important factor affecting human comfort, health, and productivity, especially in enclosed spaces with high usage intensity, where temperature and humidity serve as primary indicators of environmental conditions. This study aims to design and implement a real-time Internet of Things (IoT)-based temperature and humidity monitoring system using a DHT11 sensor and an ESP32 microcontroller integrated with the ThingSpeak cloud platform. The system is designed to collect environmental data, transmit it via a Wi-Fi network, and display the monitoring results in graphical form through a web dashboard. The research method includes hardware and software design, system implementation, and performance testing under normal indoor environmental conditions. The testing results indicate that the system is capable of displaying temperature and humidity data in real time with stable readings and deviations within the sensor’s tolerance limits, allowing consistent monitoring without significant interruptions. Practically, the system has potential applications in classrooms, offices, laboratories, and public facilities as a remote environmental monitoring solution. Furthermore, the system can be further developed by utilizing sensors with higher accuracy and incorporating additional air quality parameters to enhance its functionality and reliability.

Rancang Bangun Sistem E-Katalog Toko Bangunan Berbasis Web pada Platform KatalogQu di PT Era Cipta Digital

Muhammad Fauzy, Muhathir — Sat, 28 Mar 2026 00:00:00 +0000

The advancement of technology has driven the use of social media to promote products, including in the building materials industry. To address this, the author designed a website e-catalog as a solution for promoting building materials products. This website serves as a sub-website of the KatalogQU platform at PT. Era Cipta Digital, featuring a ready-to-sell template that can be customized through an admin dashboard. Store owners can adjust the website's appearance according to their needs. The site displays building materials products with various features and appealing layouts. The E-Catalog system is built using the Laravel framework, with key features such as CRUD for products and categories, appearance settings, and catalog content management. The outcome is a sub-website that can be used by various building material stores, making it easier for store owners to promote and sell their products online. This website allows building material stores to increase product visibility and expedite transactions, providing store owners with a more efficient way to run their business.