Article Per Year (5 Year)
p-Index From 2021 - 2026
0.444
P-Index
This Author published in this journals
All Journal Prosiding Seminar Nasional Teknoka Jurnal Penelitian Teknologi Informasi dan Sains
Muhammad Fajar Nugroho
Unknown Affiliation
Computer Science & IT Engineering

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

Found 2 Documents
Search

 1 
Rancang Bangun Robot Beroda dengan Kemampuan Berjalan Pada Sudut Tanjakan Landai dan Transmisi Sinyal Kendali Berbasis Bluetooth Akhmad Rizal Dzikrillah; Muhammad Rafli Ardiansyah; Rizky Afif Afandi; Elvira Nur Rahma; Muhammad Fajar Nugroho; Muhammad Shafar Rahim; Ahmad Robi
Prosiding Seminar Nasional Teknoka Vol 8 (2023): Proceeding of TEKNOKA National Seminar - 8
Publisher : Fakultas Teknik, Universitas Muhammadiyah Prof. Dr. Hamka, Jakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

In the 2023 ABU-Robocon (KRAI) robot contest, robots were instructed to insert rings into the poles of an arena in the form of a stacked floor. To maximize the score, the robot is allowed to climb the level 2 temple floor. Connecting the level 2 temple floor and the base of the arena is a ramp board with an incline angle of 18,420 and an area of 600 x 975 mm2. Another rule is that athletes controlling manual robots are not allowed to enter the arena or must stay outside the arena. This research aims to design a wheeled robot that has the ability to traverse uphill roads in the KRAI robot arena as well. The robot can be controlled remotely so that athletes do not need to enter the arena which has an area of 12x6 m2. The use of 4 omniwheels which are given a total DC voltage of 14.8 V, is able to make the aluminum robot able to traverse uphill roads in the KRAI 2023 robot arena. By using Bluetooth transmission, the robot can be controlled wirelessly across the entire arena.
Integrasi Yolov11 dengan Large Language Model untuk Deteksi Makanan dan Estimasi Nilai Gizi pada Program Makan Bergizi Gratis Firdausi Nuzula; Reno Syaelendra; Zakaria Mujur Prasetyo; Muhammad Fajar Nugroho; Giraldo Stevanus
Jurnal Penelitian Teknologi Informasi dan Sains Vol. 4 No. 2 (2026): Juni: JURNAL PENELITIAN TEKNOLOGI INFORMASI DAN SAINS (JPTIS)
Publisher : Institut Teknologi dan Bisnis (ITB) Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54066/jptis.v4i2.4244

Abstract

Evaluating food portions and types in the Free Nutritious Meal (MBG) program is generally still performed manually, which is time-consuming and potentially subjective. This study aims to develop an automated deep learning-based system to efficiently detect food types and estimate their nutritional value. The method used is a quantitative experiment integrating the YOLOv11m architecture for real-time object detection and the Google Gemini 2.5 Flash Large Language Model (LLM) for contextual nutritional estimation reasoning. The model training utilized a dataset of 2,630 food tray images categorized into five classes (fruit, side dish, staple food, vegetable, milk) that had undergone an augmentation process. The results showed that the YOLOv11m model achieved excellent performance with a mean Average Precision (mAP@0.5) of 0.9727 and the highest F1-score of 0.9522 at a confidence threshold of 0.1. Furthermore, validation of the LLM integration demonstrated a high prediction agreement rate of 85%. In conclusion, the combination of the YOLOv11m algorithm and LLM reasoning is capable of detecting and validating nutritional classification quickly and precisely, showing strong potential as an objective nutritional evaluation monitoring solution for large-scale MBG program implementation.
Co-Authors Ahmad Robi Akhmad Rizal Dzikrillah Elvira Nur Rahma FIRDAUSI NUZULA Giraldo Stevanus Muhammad Rafli Ardiansyah Muhammad Shafar Rahim Reno Syaelendra Rizky Afif Afandi Zakaria Mujur Prasetyo