Claim Missing Document
Check
Articles

Found 33 Documents
Search

Virtual Reality Headset Implementation on Parsec Cloud Gaming Platform Muhammad Fadhil Rahadiansyah; Ridha Muldina; Sussi Sussi
JOIN (Jurnal Online Informatika) Vol 5 No 1 (2020)
Publisher : Department of Informatics, UIN Sunan Gunung Djati Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15575/join.v5i1.578

Abstract

Virtual reality (VR) based games are a type of game that provides immersive gaming experience, allowing players to dive into the virtual world of the game being played. VR-based games require a high minimum computer specification, so thin clients cannot play VR-based games properly. This research aims to see how to enable thin computers to play VR-based games by utilizing cloud gaming technology. Using a high specification computer as a server, an android device as a VR headset, this Final Project implements a VR headset device so that it can be used in conjunction with cloud gaming services to be able to play VR-based games on thin computers and see how well the implementation by seeing the result from computer resources used and the Quality of Services. With Parsec cloud gaming services, the application carried out in this Final Project can run well on computers with low specifications. CPU usage on the client computer when the service is running is high at 91% usage, with 2818 MB RAM usage. Quality of Service is obtained when setting the highest quality preset, with a throughput of 16MB with a delay of about 2 ms. VR games that are played can run well with a minimum bandwidth of 15 Mbps selected from the Frame per Second (FPS) results obtained to reach 56 FPS with medium quality settings.
Sistem Informasi Pengukuran Kadar Hemoglobin Non-Invasif Berbasis Android Menggunakan Algoritma Extreme Gradient Boosting Syarifuddin, Sri Dewi Sartika; Khurniawan, Amri; Munadi, Rendy; Sussi, Sussi
Komputika : Jurnal Sistem Komputer Vol 12 No 1 (2023): Komputika: Jurnal Sistem Komputer
Publisher : Computer Engineering Departement, Universitas Komputer Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34010/komputika.v12i1.5049

Abstract

Measurement of hemoglobin levels nationally was carried out invasively using the sahli method of 27.9%. Measurement of invasive hemoglobin levels takes a long time due to the chemical analysis of patient blood samples in the blood laboratory. In general, blood sampling is done using a syringe, which can cause pain and increase the risk of spreading other diseases through needle-stick wounds. Measurement of hemoglobin levels can be done using multiwavelength oximetry technique. Therefore, in this study, a non-invasive real-time measurement system for hemoglobin levels based on the internet of things was created using the multiwavelength oximetry technique with the Extreme Gradient Boosting algorithm which is integrated with Real-time Database and an android-based information system capable of mapping users using QR Code. The test results using the RMSE parameter obtained a value of 0.801085 which indicates a high category level and an accuracy of 94.91%. The information system can display real-time measurement of hemoglobin levels with a delay of 317 ms and a throughput of 3138 bps. The results of testing the oxygen saturation functionality are 0.654% with the difference in the measurement value of the highest oxygen saturation level being 1.33% and the smallest being 0.08%.
Effect of dataset distribution on automatic road extraction in very high-resolution orthophoto using DeepLab V3+ Sussi, Sussi; Husni, Emir; Siburian, Arthur; Yusuf, Rahadian; Budi Harto, Agung; Suwardhi, Deni
IAES International Journal of Artificial Intelligence (IJ-AI) Vol 13, No 2: June 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijai.v13.i2.pp1650-1657

Abstract

Road extraction is one of the stages in the map-making process, which has been done manually, takes a long time, and costs a lot. Deep Learning is used to speed up the road extraction process by performing binary semantic segmentation on the image. We propose DeepLab V3+ to produce road extraction from very high-resolution orthophoto for Indonesia study area, which poses many challenges, such as road obstruction by trees, clouds, building shadows, dense traffic, and similarities to rivers and rice fields. We compared the distribution of datasets to obtain the optimal performance of the DeepLab V3+ model in relation to the dataset. The results showed that dataset ratio of 75:10:15 resulted in mean Intersection Over Union (mIoU) of 0.92 and Dice Loss of 0.042. Visually, the results of road extraction are more accurate when compared to the results obtained from different distributions of the dataset.