Garuda - Garba Rujukan Digital

Article Per Year (5 Year)

p-Index From 2020 - 2025

0.562

P-Index

This Author published in this journals

All Journal Prosiding Seminar Nasional Sains Teknologi dan Inovasi Indonesia (Senastindo)

Mohammed Ikrom Asysyakuur

Universitas Nurtanio, Bandung, Indonesia

Author-ID : 4257290

Computer Science & IT Control & Systems Engineering Engineering Mechanical Engineering Other

Published : 3 Documents Claim Missing Document

Claim Missing Document

Articles

Sistem Pendeteksi Pejalan Kaki di Lingkungan Terbatas Berbasis SSD Mobilenetv1 Menggunakan Gambar 360° Ternormalisasi Ni Nyoman Ayu Marlina; Denden Mohammad Ariffin; Arief Suryadi Satyawan; Mohammed Ikrom Asysyakuur; Muhammad Farhan Utamajaya; Raden Aditya Satria; Nafisun Nufus; Ema Ema
Prosiding Seminar Nasional Sains Teknologi dan Inovasi Indonesia (SENASTINDO) Vol 3 (2021): Prosiding Seminar Nasional Sains Teknologi dan Inovasi Indonesia (Senastindo)
Publisher : Akademi Angkatan Udara

Along with the times, every car manufacturer always creates its newest products that aremore sophisticated. This idea then gave birth to the concept of an autonomous electric vehicle (KLO .) This purpose is intended to always present vehicles that can meet consumers' growing tastes while also being environmentally friendly. The presence of autonomous electric vehicles will certainly be experienced by Indonesia, whose people have started to rely on car transportation. Therefore, this situation requires us to be prepared to face the era of Mobility in Society 5.0, where we must master the supporting technology. Autonomous electric vehicles can be realized if the system can detect objects properly. Therefore, a deep learning-based pedestrian detection system was developed and utilized 360° images in this study.The object detection software system was built using the Single Shot Multibox Detector (SSD)MobilenetV1, while the hardware used for this development is Jetson AGX Xavier. The development process started from taking a normalized 360° image containing pedestrian information in the Nurtanio University campus area which was then used as a dataset and test data, training the MobileNetV1 SSD with the dataset (19038), and testing the trained software model in real-time and offline. Offline test results on 735 360° images in daytime conditions show that 55.5% of images can be detected ideally, while of 595 360° images in afternoon conditions, 51.2% of images can be ideally detected. In real-time testing, 98% of pedestrians are inevitably seen during the day, while only 95% in the afternoon. The average processing time on an image in daytime conditions is 32.81283 ms if using the CPU, while if using the GPU, it is 32.79766 ms. For an image with the same information in the afternoon conditions, the processing time is 37.42598 ms if using the CPU, while if using the GPU, it is 37.45174 ms.

Simulasi Sistem Pendeteksi Objek Pada Pesawat Dengan Menggunakan Teknologi SAR (Synthetic Aperture Radar) Mohammed Ikrom Asysyakuur; Denden Mohammad Ariffin; Arief Suryadi Satyawan; Ni Nyoman Ayu Marlina; Nafisun Nufus; Raden Aditya Satria Nugraha; Ema Ema
Prosiding Seminar Nasional Sains Teknologi dan Inovasi Indonesia (SENASTINDO) Vol 3 (2021): Prosiding Seminar Nasional Sains Teknologi dan Inovasi Indonesia (Senastindo)
Publisher : Akademi Angkatan Udara

To map an object in the form of the contours of an area will be difficult if you use a passive sensor system such as a camera because of its limitations to penetrate clouds, fog, and erratic weather. Therefore, better technology is needed to map an object from above the earth's surface or the air. Synthetic Aperture Radar (SAR) is a mapping technique using radar to produce high-resolution maps of the earth's contours or describe an object and present information in the form of images or images. SAR can work in any weather conditions, whether in the rain, snow, or even fog. Another SAR capability is to be able to detect objects with a fairly good level of accuracy. Based on the above, research and development of SAR technology is very necessary. In this research, preliminary studies on SAR technology have been carried out. This research is intended to complement the capabilities of drones or unmanned aerial vehicles (UAVs) both for imaging the contours of the earth and activities related to society 5.0 so that the application can be used for modern agriculture, forestry, marine, and border observation activities. The goal is to simulate the detection of objects that are on the ground. There are two simulated SAR-based object detection methods, namely Range Migration Algorithm and Back Projection Algorithm. This simulation was built using a computer with an AMD A8 processor, 8 GB of memory, and MATLAB 2019 software. The simulation results show that the system design for both algorithms can work well at a frequency of 4 GHz with a resolution range of 3m. The image displayed in this simulation is in 2-D form. The average processing time of the two algorithms to be able to detect objects is 103.2 seconds. The image displayed in this simulation is in 2-D format. While the average processing time of the two algorithms to be able to detect objects is 103.2 seconds.

Sistem Pendeteksi Pejalan Kaki Di Lingkungan Terbatas Berbasis SSD MobileNet V2 Dengan Menggunakan Gambar 360° Ternormalisasi Nafisun Nufus; Denden Mohammad Ariffin; Arief Suryadi Satyawan; Raden Aditya Satria Nugraha; Mohammed Ikrom Asysyakuur; Ni Nyoman Ayu Marlina; Chandra Himawan Parangin; Ema Ema
Prosiding Seminar Nasional Sains Teknologi dan Inovasi Indonesia (SENASTINDO) Vol 3 (2021): Prosiding Seminar Nasional Sains Teknologi dan Inovasi Indonesia (Senastindo)
Publisher : Akademi Angkatan Udara

The growth of vehicular traffic in various areas such as urban and rural areas is gettinghigher due to the increasing need for transportation equipment. This condition causes many scientists to continuously improve the quality of the mode of transportation so that it is easier, safer, and more practical to use. As a result, the idea of driverless transportation has emerged to meet this need. The form of transportation is private vehicles, and it is expected to be in the form of mass vehicles such as buses or trains. Several aspects must be considered in designing autonomous transportation or autonomous electric vehicles so as not to cause accidents that can endanger the driver and the surrounding environment. Among them is the existence of a pedestrian detection system. This system is critical because, like conventional vehicles, autonomous vehicles must avoid pedestrians, but they work with no driver assistance. In this study, a software system that can detect pedestrians from all directions using a 360° camera was developed to overcome the above. This system also utilizes deep learning technology. The design and realization of this system went through several stages. The stages include installing supporting software on the NVIDIA Jetson AGX Xavier, capturing video data with a 360° camera for composing a dataset of 19,038 images, training the MobileNet V2 SSD with the dataset, and testing the trained model with the real-time and offline testing process. As a result, by testing 548 normalized 360° images offline for daytime conditions, 60.40% of images were perfectly detectable, while for 514 normalized 360° images for evening conditions, 62.25% of images were ideally detected.

Co-Authors Arief Suryadi Satyawan Arief Suryadi Satyawan Chandra Himawan Parangin Denden Mohammad Ariffin Ema Ema Muhammad Farhan Utamajaya Nafisun Nufus Ni Nyoman Ayu Marlina Raden Aditya Satria Raden Aditya Satria Nugraha

Title

Found 3 Documents
Search

Abstract

Abstract

Abstract

Title Search

Found 3 Documents Search

Abstract

Abstract

Abstract

Title

Found 3 Documents
Search