Claim Missing Document
Check
Articles

Found 2 Documents
Search
Journal : Intelmatics

Application of IOT Technology in The Control of Organic Waste Processing Machines with PT100 Sensors and Heaters for Fertilizer Healing and Animal Feeding Dharma, Ricardo; Budi Santoso, Gatot; Mardianto, Is
Intelmatics Vol. 4 No. 2 (2024): Juli-Desember
Publisher : Penerbitan Universitas Trisakti

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25105/v4i2.20913

Abstract

Waste is one of the major problems in Indonesia that still has to be resolved, because it has many negative impacts on the environment and health. Waste can be divided into two types: organic and inorganic waste. The increase in waste and the limited capacity of the Integrated Waste Disposal Sites (TPST) will cause waste to accumulate. Therefore, organic waste will have a negative impact on the environment if not managed properly, one of the efforts to reduce its impact is to process organic waste into fertilizer and animal food with new innovations in Internet of Thing (IOT) technology that can be used as an improvement in the agricultural sector. The manufacture of waste processing machines into fertilizer and animal food uses PT100 sensors as temperature control sensors from waste, PLC as data processing integration, HMI cloud and HMI haiwell are used as hardware that displays visual temperature data. This research shows that the use of PT100 sensors in waste processing machines has a significant effect on machine performance. In the process of making fertilizer, the PT100 sensor can regulate the temperature accurately, for example, when the temperature is set at 80℃ and exceeds the limit, the heater will turn off and the temperature decreases to 60℃. IoT technology allows real-time monitoring and control of temperature through mobile phones and HMIs, as well as providing Telegram notifications for high or low temperature warnings.
Brain Tumor Detection System Based on Convolutional Neural Network Febrianto, Nanang Dwi; Mardianto, Is; Rochman, Abdul; Najih, Muhammad
Intelmatics Vol. 5 No. 1 (2025): January-June
Publisher : Penerbitan Universitas Trisakti

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25105/v5i1.22135

Abstract

Early detection of brain tumours is essential to improve the effectiveness of treatment. This study develops a Convolutional Neural Network (CNN) model to detect brain tumours from MRI images. Using a dataset of 4410 images, the model was trained and tested with several CNN architectures, such as EfficientNetB0, InceptionNetV3, ResNet, MobileNet, VGG16, Model 1. Results showed that the best model achieved 97.8% accuracy, thus being able to predict brain tumours with a high degree of reliability. These findings support the application of CNNs in medical detection systems to assist doctors in faster and more accurate diagnosis.