Claim Missing Document
Check
Articles

Found 2 Documents
Search
Journal : Intelmatics

A Web-Based Boarding Management Application Design Maulana, Muhamad Anggi; Syaifudin; Sari, Syandra; Najih, Muhammad
Intelmatics Vol. 4 No. 1 (2024): Januari-Juni
Publisher : Penerbitan Universitas Trisakti

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25105/itm.v4i1.17649

Abstract

In Indonesia, the rental business of temporary accommodations or boarding houses ('kost') has significantly grown due to the influx of individuals from various cities or regions seeking temporary residence for educational pursuits, work, entrepreneurship, or marriage. Boarding house owners often manage not just one or two rooms but can have dozens or even hundreds of rooms. This extensive scale makes it challenging for boarding house owners to efficiently handle payment data, accurately record information, and report room damages using conventional methods. To address these challenges, an application was developed to streamline data management for boarding house owners, enabling them to efficiently manage their businesses. The data collection methods employed for developing this application included observation, interviews, and literature review, following the waterfall model for software development. The obtained results from this application development facilitate better service management for boarding house owners, enhancing cost and time efficiency while improving the quantity and quality of managed information.
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.