Gembong Edhi Setyawan
Fakultas Ilmu Komputer, Universitas Brawijaya

Published : 89 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Implementasi Algoritma Hough transform Pada Object Following Menggunakan Ar.Drone Quadcopter Muhammad Tri Buwana Zulfikar Ardi; Gembong Edhi Setyawan; Fitri Utaminingrum
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 4 No 1 (2020): Januari 2020
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (527.483 KB)

Abstract

Quadcopter is one type of unmanned aerial vehicle (UAV) or unmanned aircraft that has 4 rotors. At present the quadcopter control system still uses radio control. Along with the development of quadcopter technology at this time has been equipped with various features such as GPS and also a camera to take pictures or digital images from the quadcopter's point of view. Ar.Drone is an output quadcopter from the Parrot brand. Ar.Drone uses the Linux operating system so that it can be used to conduct research on quadcopter development. On the quadcopter an intelligent algorithm can be applied related to image processing so that it can be developed and one of them is object following or tracking. By using hough transform researchers are expected to be able to create an automatic navigation system for quadcopter that can be used to detect spherical objects as a basis for navigation. With the automatic navigation system can be petrified if you want to take a picture or video needed to record an object without having to do manual navigation using radio control. The navigation system automatically runs based on the position of the ball in the video streaming frame. for that frame streaming is divided into 9 frames to find out what movements the quadcopter has to do to be able to move along with the object. There are several things that must be done before the image from the front camera quadcopter can be used for the implementation of the hough transform algorithm. The process is image pre-processing, namely digital image processing including segmentation using HSV, blurring, and canny edge. In testing the position of the spherical coordinates on the frame, it can be concluded that the quadcopter can track the movement of the ball with reference to the sphere midpoint coordinate position. From the distance test, the maximum distance for detection is 4m with the percentage of successful detection of all colors at 85%.
Implementasi Low Power pada Sensor Node dengan Protokol Komunikasi Zigbee Frans Herbert Nainggolan; Mochammad Hannats Hanafi Ichsan; Gembong Edhi Setyawan
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 4 No 1 (2020): Januari 2020
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (531.857 KB)

Abstract

Changing times are increasingly rapid due to the development of information technology. It is estimated, the development of the use of market places from the Internet of Things will be more widespread. For this reason, the government itself has launched the Making Indonesia 4.0 program, where the component is the Internet of Things. The application of the Internet of Things in Indonesia can be done in aspects of transportation, health, the environment, and others. Not without negative impacts, the development of the Internet of Things (IoT) also brings negative impacts, one of which is huge energy consumption. Xbee is a module that is used as a radio communication media with the zigbee 802.15.4 protocol. Xbee can also be configured with several types of features, one of which is the active period where the device is transmitting and in the active period where all devices and microcontrollers can be turned off. From this problem, the implementation of low power sensor nodes in the zigbee communication protocol is designed.The system design with the xbee-s1 communication module is designed in 1 coordinator node, and 3 end nodes that are connected to the arduino uno microcontroller, the DHT-11 sensor, and the LDR sensor in charge of taking sensor data values ​​both temperature, humidity and light resistance value. After being tested to get the results the system can run as expected, with the result of a decrease in the value of the current of 0.031 A or 11.23%.
Navigasi Robot Beroda Berdasarkan Pengenalan Teks untuk Melakukan Pergerakan Menggunakan Metode Optical Character Recognition (OCR) M. Khanif Ashar; Gembong Edhi Setyawan; Eko Setiawan
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 4 No 4 (2020): April 2020
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (662.567 KB)

Abstract

The condition of an earthquake in a high-rise building often makes visitors panic when evacuating. This requires assistance to direct visitors to the evacuation route with voice commands or text written in the building. Therefore in this research a navigation system on wheeled robots is designed which aims to help the evacuation process at the time of an earthquake in a high-rise building by directing it to the evacuation route based on text orders. In the navigation system is designed to use a camera to recognize text. The camera detection results are used as input to be processed in the Raspberry Pi using the optical character recognition method. The output results are used as parameters to make the movement of the wheeled robot that is moving forward, turn right, turn left, walk backward and stop. Based on testing the detection accuracy obtained page segmentation modes value 6 with an average accuracy of 98.11%. The average result of time needed to detect an object is 48.5 seconds at a test distance of 3 meters and 185.75 seconds at a test meter of 6 meters. Wheeled robot speed obtained high percentage duty value of 13% and 14% with an average detection distance of 193.3cm. The accuracy of the motion results obtained by a percentage of 100% on all four objects except at the RUN object can make movements at a test distance of 50-250cm.
Perancangan Algoritma Jaringan Saraf Tiruan Backpropagation untuk Navigasi Robot Beroda Mohammad Riski Aprilianto; Gembong Edhi Setyawan; Eko Setiawan
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 4 No 5 (2020): Mei 2020
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

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

Abstract

Wheeled robot is a robot that moves using wheels under certain conditions so that a good navigation system is needed. Whether or not the robot navigation system is influenced by the software system and the algorithm that is running. Over time, artificial neural network algorithm is much in demand and developed because it has good flexibility to the nonlinear environment. Therefore, in this study a backpropagation artificial neural network algorithm is designed for navigation of wheeled robots. Artificial neural networks have advantages, among others, the level of accuracy is better than pattern recognition algorithms such as fuzzy and KNN. Besides artificial neural networks also have good flexibility in solving problems with multidimensional classes. Backpropagation artificial neural network is a supervised neural network in which there is a network training. In network training there are several factors that influence, including hidden layers, momentum, and learning rate. In addition to good training, robot speed regulation also needs to be considered so that the robot has good stability in its environment. Based on the time and error values ​​in the network training, the number of hidden layer nodes of 5 has the best results on input and output of 4 nodes. Whereas in the PWM motor 150 value setting obtained a fairly good movement stability for the wheeled robot used.
Kontrol Robot Manipulator Berdasarkan Pergerakan Lengan Manusia Menggunakan Electromyography Hanifa Nur Halimah; Rizal Maulana; Gembong Edhi Setyawan
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 4 No 6 (2020): Juni 2020
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

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

Abstract

One of the rapidly growing medical innovations is the surgical robot. Robotic technology will help doctors during a surgical procedure. The advantages of robotic surgery include faster recovery, minimal scarring, and smaller incisions, resulting in a reduced risk of infection. A surgical robot, in this case, is made in the form of a manipulator robot. The manipulator robot matches the doctor's movement by reading the electromyography (EMG) signal produced by muscle contraction through the electrodes. Myoware sensor detects EMG signals of arm muscles. Myoware output signal read by Arduino Nano so that the manipulator robot moves. Robot manipulator was designed to have 4 Degree of Freedom and implemented using servo dynamixel AX-12A. The EMG signal will be filtered exponentially so that the signal is smoother. The signals that have been processed will be analyzed the amplitude to determine the type of arm movement performed. The angles detected are 00, 450, 900, 1350 and 1450. Each angle has upper limit 0.89V; 1.59V; 2.29V; 3.49V; and 5V; lower limit 0V; 0.89V; 1.59V; 2.29V; and 3,49V. the system has an accuracy of 84% in determining the type of arm movement which had taken from 5 attempts each angle by 3 subjects.
Navigasi Robot Beroda menggunakan Algoritma SVM (Support Vector Mechines) Nengah Affan Riadi; Gembong Edhi Setyawan; Eko Setiawan
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 4 No 7 (2020): Juli 2020
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

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

Abstract

Wheeled robots need a navigation ability to operate properly. One of the navigation implementations of the wheeled robot is that the wheeled robot can help the SAR (Search and Rescue) team find victims. Wheeled robots need a navigation algorithm to do the job. This research will use one type of navigation algorithm, the SVM (Support Vector Machines) algorithm. In addition, the wheeled robot also requires a sensor and actuator that can support the performance of the wheeled robot. This research will use an Ultrasonic Sensor which is used to detect obstacles around the robot wheel and DC motor as the propulsion of the wheeled robot. The results of the tests conducted in this study, obtained the best PWM (Pulse Width Mudulation) motor value that will be used for operating robots is 150, Ultrasonic Sensors and DC Motors have a pretty good functionality and can be used in robots with wheels well, and accuracy SVM algorithm output that compares with the actual output is 87.5%.
Implementasi Sistem Otomasi Takaran Biji Kopi Pada Tempat Penyimpanan di Mesin Penggiling Kopi Fachrur Febriansyah Manangkalangi; Rizal Maulana; Gembong Edhi Setyawan
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 4 No 9 (2020): September 2020
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

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

Abstract

Entrepreneurs who have established small coffeeshop business for a long time, using coffee grinder machine which has no automatic scale tchnology inside, absolutely wish that kind of technology exist in their machines without replacing with the new ones. From that problem statement, the researcher will provide solution by creating coffee beans automatic measuring system in the storage of the grinder which there is not any automatic scale technology. This system will use load cell censor hardware with HX711 module as an object reader, in this case is coffee beans in the hopper. This system will also use stepper nema 17 motor whose end has already connected with artificial component in the form of auger and driver A4988 which is used as actuator to the coffee beans in the hopper. There is also 16x2 LCD with 12C module used as whole information display of the process, from the beginning until the end. It has three push buttons utilized by users to choose three mass measuring target of the system and it use servo motor as a open-close valve between the prototype tool and grinding machine. Then, the analysis result for this system testing can be concluded that there is 16,9% error to the digital scale tool, whereas for monitoring analysis, the whole information dislpayed on LCD monitor gain good system testing result in displaying all the system information. The next analysis is motor stepper actuator to the coffee beans capacity in the hopper and the result of motor stepper movement is 100%. It means that the movement towards the coffee beans capacity in the hopper is good. It moves very well. The conclusion of the final testing analysis to the entire system is the researcher gain 100% for accuracy of the entire system and it can be stated that it can work properly just as the purpose of this research.
Sistem Kendali Kecepatan Robot Beroda Pada Jalan Menanjak dan Menurun Menggunakan Metode Proportional Integral Derivative Muhammad Hanif Haikal; Dahnial Syauqy; Gembong Edhi Setyawan
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 4 No 10 (2020): Oktober 2020
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

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

Abstract

Abstract The development of the world of robotics is increasingly rapid, there is a human urge for all problems that arise around it so that it can be resolved quickly and efficiently. These problems are human limitation in processing control and a very long time, so that the more advanced the new technological era is, the more it is founds. For example in controlling speed on wheeled robots in terms of helping humans. The speed control system will be researched and applied to the skidsteering wheeled robot. This robot is equipped with an optocoupler sensor, Arduino UNO microcontroller and Motor Driver Shield L293D. this research method used is the Proportional Integral Derivative (PID). The access used is in the form of uphill and downhill roads on the slope of 10°, 15°,20° with the distance about 2m. From the simulation, the results are able to provide good control system performance criteria which can be seen from the comparison of the controller without using the PID controller and by using the PID control. PID contorl paramaters used to control DC motors are able to provide the most ideal control respone, with values of Kp = 0.2, Ki = 0.12 and Kd = 0.01. And when the robot run in the incline and descent area with an angle of 10°, 15°,20°, it has experienced a significant decrease in speed
Rancang Bangun Wearable System Klasifikasi Gerak Lari dan Jalan menggunakan Sensor MPU6050 dengan Metode Support Vector Machine Dilengkapi Tracking GPS Mahendra, I Gusti Putu Krisna Suaba; Syauqy, Dahnial; Setyawan, Gembong Edhi
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 8 No 13 (2024): Publikasi Khusus Tahun 2024
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

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

Abstract

Naskah dipublikasikan ke JITeCS (Journal of Information Technology and Computer Science)
Sistem Bantu Wearable pada Latihan Angkat Beban untuk Otot Biseps Menggunakan Sensor MPU6050 dengan Algoritma Decision Tree Raharja, Kahfi May; Syauqy, Dahnial; Setyawan, Gembong Edhi
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 8 No 2 (2024): Februari 2024
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

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

Abstract

Dalam era peningkatan kesadaran akan gaya hidup sehat dan idealisasi tubuh atletis, latihan angkat beban, terutama dengan dumbbell, menjadi pilihan utama bagi individu pemula yang berambisi mencapai kebugaran pribadi. Pada umumnya, individu ini mengadopsi teknik standing dumbbell curl, meskipun seringkali tanpa menyadari bahwa gerakan tersebut memfokuskan latihan pada otot biseps. Kesadaran yang minim terhadap teknik yang benar dapat menurunkan efektivitas latihan dan meningkatkan risiko cedera sehingga peran pelatih dalam memberikan panduan menjadi sangat penting. Namun, tidak semua orang memiliki akses terhadap seprang pelatih. Oleh karena itu, penelitian ini memperkenalkan sebuah sistem wearable yang memanfaatkan sensor MPU6050 terintegrasi dengan ESP32, yang menggunakan metode Decision Tree untuk mendeteksi gerakan benar dan salah dalam latihan berdasarkan pembacaan data akselerometer dan giroskop, sehingga diharapkan sistem dapat membantu menggantikan peran seorang pelatih. Penempatan sensor pada pergelangan tangan, lengan atas, dan dada mengoptimalkan pemantauan latihan. Algoritma Decision Tree mencapai akurasi 96,3%, sedangkan sistem dalam mengidentifikasi gerakan benar dan salah dengan memiliki akurasi 85% dengan waktu komputasi Decision Tree yang diterapkan pada sistem adalah rata-rata 2ms dalam 20 kali pengujian. Hasil klasifikasi ditampilkan melalui buzzer, memberikan umpan balik suara saat gerakan dilakukan dengan benar. Sistem wearable ini, dengan keleluasaan penggunaannya, dapat digunakan di berbagai tempat, memfasilitasi individu pemula dalam mencapai tujuan latihan angkat beban untuk otot biseps.
Co-Authors Abdurrahman Arif Kasim Achmad Baichuni Zain Adharul Muttaqin Adipratama, Ivan Rafli Aditya Rachmadi, Aditya Adiwijaya, Benny Adnan Mahfuzhon Agastya Bramanta Sanjaya Agung Setiabudi, Agung Alexandria, Syarifah ALFATH, ANASHRULLAH FAIZAL Amrin Rosada Amroy Casro Lumban Gaol Anata Tumonglo Andi Mohammad Rizki Andyan Bina Ardhana Ardandi, Haekal Fadhilah Arista Budi Setyawan Arycca Septian Mulyana Aryo Pinandito Ayang Setiyo Putri Ayu Dewi Khumairoh Ayu Samura Bagus Priyo Pangestu Barlian Henryranu Prasetio Cindy Lilian Dahnial Syauqy Didik Wahyu Saputra Dimas Angger Pribadi Dimas Bagus Jatmiko Edita Rosana Widasari, Edita Rosana Eko Setiawan Eko Setiawan Enno Roscitra Oktaria Eriq M. Adams Jonemaro Fachrur Febriansyah Manangkalangi Fahmi Farizal Faisal Natanael Lubis Faizal Andy Susilo Faizal Ardiansyah Fajar Miftakhul Ula Fajar Pradana Fajar, Sanhnai Fathirul Faviansyah Arianda Pallas Fikri, Aqil Dzakwanul Fitra Abdurrachman Bachtiar Fitriyah, Hurriyatul Frans Herbert Nainggolan Fungki Pandu Fantara Handi Handi Hanifa Nur Halimah Haqqi Rizqi Hendra Hendra Hurriyatul Fitriyah, Hurriyatul Irma Asri Kartika Sandy Irma Asri Kartika Sandy Issa Arwani Khurinika Cahyaning Susanty M. Khanif Ashar Mahendra, I Gusti Putu Krisna Suaba Maulidiah, Afifah Megananda, Muhammad Rifqi Mesra Diana Tamsar Mochammad Hannats Hanafi Ichsan Mochammad Hannats Hanafi Ichsan Moh. Zainur Rodhi Mohammad Kholili Adi Putra Mohammad Riski Aprilianto Muchamad Rafi Dharmawan Muhammad Alif Alfajra, Andi Muhammad Fajaruddin Akbar Muhammad Hanif Haikal Muhammad Rosyid Khulafa Muhammad Tri Buwana Zulfikar Ardi Muliyahati Sutejo Musada Teguh Andi Afandi Nawal Addufairi, M. Azkan Nengah Affan Riadi Okke Rizki Kurniawan Prahmono, Daffalino Purnama, Charrisma Dwi Mahardika Trisna Purnomo, Fawwaz Anrico Putra Wijaya Raharja, Kahfi May Rahmat Naharu Yanuar Rakhmadhany Primananda, Rakhmadhany Randy Maulana Rekyan Regasari Mardi Putri, Rekyan Regasari Mardi Reza Ridlo Nugraha Reza Tanjung Ahmad Fauzi Ricky Prasetya Santoso Riko Andianto Rimas Oktama Rinaldi Albert Soritua Riza Irfan, Muhammad Rizal Maulana Sabitha Wildani Hadi Sabriansyah Rizqika Akbar Simanjuntak, Eldon Parasian Sunu Dias Widhi Kurniadi Syarif Hidayatullah Tadya Adi Prana Tibyani Tibyani Utaminingrum, Fitri Wahyu Hari Suwito Wijaya Kurniawan Wijaya Kurniawan Wijaya Kurniawan Yasa Palaguna Umar, Yasa Palaguna Yusril Dewantara Zakky Ramadhan