Article Per Year (5 Year)
p-Index From 2021 - 2026
0.444
P-Index
This Author published in this journals
All Journal Journal of Systems Engineering and Information Technology
Mohammad Iqbal
Gunadarma University
Computer Science & IT

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Comparative Analysis of Deep Learning Models for Vehicle Detection Rendi Nurcahyo; Mohammad Iqbal
Journal of Systems Engineering and Information Technology (JOSEIT) Vol 1 No 1 (2022)
Publisher : Ikatan Ahli Informatika Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (610.663 KB) | DOI: 10.29207/joseit.v1i1.1960

Abstract

Deep Learning techniques are now widely used instead of traditional Computer Vision. There are many Deep Learning model algorithms for each use case such as Object Detection has several models, including Faster R-CNN, SSD, and YOLO v3. The performance and results of each Deep Learning model have advantages and disadvantages. Therefore, we must determine which model is suitable for the use cases and datasets that we have so that we can make the best Deep Learning model. Based on this need, this paper will make a comparative analysis of the Deep Learning model for Vehicle Detection (the spesific of Object Detection) from the models mentioned, namely, Faster R-CNN, SSD (Single Shot Detector), and YOLO v3 (You Only Look Once) to see the advantages and the disadvantages and which ones are the best. And after a comparison, it was concluded that of the three models mentioned only YOLO v3 model is able to be used as real time detection because it has low latency due to YOLO v3 only performs single convolution process so that it makes the process simpler and faster without reduce the accuracy.
Public IP Efficiency and Data Center Security Enhancement with Reverse Proxy Implementation Achmad Sandy Bukhari; Mohammad Iqbal
Journal of Systems Engineering and Information Technology (JOSEIT) Vol 2 No 3 (2024)
Publisher : Ikatan Ahli Informatika Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/joseit.v3i2.5948

Abstract

With the increasing frequency of cyber-attacks, the trend of national cybersecurity traffic anomalies reached 976,429,996 incidents in 2022. Additionally, the world is now facing the fact that the supply of Public IPv4 addresses available for allocation is diminishing. IPv4 uses 32-bit addressing, which provides only over 4 billion unique IP addresses. By conducting research using two methods, namely a server without a reverse proxy and a server with an applied reverse proxy, it was found that implementing NGINX with a reverse proxy can lead to savings in public IPv4 addresses. Regardless of the number of servers, only one public IPv4 address is needed, which reduces the number of IPs required and also prevents cyber-attacks on the server. Testing with DNSChecker and whatismyipaddress showed that after applying the reverse proxy with NGINX, the application server could not be identified or accessed by external parties. Only the reverse proxy server was accessible to outsiders. As the number of applications increases, which directly correlates with the need for public IPv4 addresses, the study's results show that applying a reverse proxy with NGINX in a data center can overcome the limitations of public IPv4 addresses. As the number of virtual machines and applications grows, a single public IPv4 address applied to the reverse proxy server suffices. Thus, implementing a reverse proxy with NGINX allows multiple servers to use just one public IPv4 address.
Co-Authors Achmad Sandy Bukhari Rendi Nurcahyo