Claim Missing Document
Check
Articles

Found 2 Documents
Search
Journal : Journal of Applied Information, Communication and Technology (JAICT)

Classification System of Crystal Guava (Psidium Guajava) Using Convolutional Neural Network And Rectrified Linear Unit Method Based on Android Wiktasari, Wiktasari; Yudantoro, Tri Raharjo; Alifiansyah, Muhammad Fikry; Kurniangsih, Kurniangsih; Triyono, Liliek; Hasan, Abu
JAICT Vol 10, No 1 (2025)
Publisher : Politeknik Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32497/jaict.v10i1.6170

Abstract

These instructions Abstract - However, determining the ripeness of fruit is frequently done by hand, which presents problems with consistency and efficiency. In order to improve the sorting of crystal guava fruit maturity, this study suggests combining machine learning technology with the creation of digital image-based apps. Fruit ripeness is classified using a convolutional neural network (CNN), a deep learning model, based on the color of its skin. It is anticipated that the method will increase productivity and offer superior precision while sorting crystal guava fruit. The System Development Life Cycle (SDLC) with a Waterfall approach is the methodology employed. The system design formed from the deep learning model resulted in excellent performance in classifying images of crystal guava fruit by utilizing model training from the base models ResNet50V2, DenseNet121, NASNetMobile, and MobileNetV2 with a combination of training using K-fold cross-validation with a 5-fold configuration. The best-trained model achieved an average highest accuracy of 99.92% in model training using MobileNetV2 with the lowest average loss value of 0.0088. The system application was developed using mobile Android, leveraging the Flutter framework and Dart programming language. The research results demonstrate a comparison of testing on crystal guava and local guava fruits against ripeness classification parameters
Design and Development of a Monitoring and Controlling System for Automatic Watering and Filling in Fungi House's Internet of Things-Based Mushroom Cultivation Supriyanto, Eko; Rochmatika, Rizkha Ajeng; Oktaviani, Cantika Cakhya; Luqita, Syauqi Fajar; Hasan, Abu; Bramantyo, Hutama Arif; Yudantoro, Tri Raharjo
JAICT Vol 9, No 2 (2024)
Publisher : Politeknik Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32497/jaict.v9i2.5921

Abstract

Temperature and humidity are aspects that need to be considered in cultivating oyster mushrooms. Previously, Fungi House in Genting Village, Semarang, implemented an automatic temperature, humidity, and watering monitoring system, but manually filled the water. This new system's design and development aim to simplify the monitoring and control of temperature, humidity, and water level for managers. Managers determined temperature, humidity, and water level thresholds via the web page. This system used the agile scrum method. The test results showed that the temperature measurement accuracy was 96.85%, humidity 99.35%, and water level 98.99%. With this system, the quality of baglog (mushroom growing medium) increased by 4.62%, while dead baglog decreased by 99.01%. Black box testing demonstrates that all features perform well in web testing. In the load activity test, with low bandwidth (6.71 Mbps), the average load time was 1.32 seconds, and with high bandwidth (37.15 Mbps), it was 0.878 seconds. These two conditions indicate excellent system performance and provide optimal user experience.