Claim Missing Document
Check
Articles

Found 26 Documents
Search

Colored object detection using 5 dof robot arm based adaptive neuro-fuzzy method Mujiarto Mujiarto; Asari Djohar; Mumu Komaro; Mohamad Afendee Mohamed; Darmawan Setia Rahayu; W. S. Mada Sanjaya; Mustafa Mamat; Aceng Sambas; Subiyanto Subiyanto
Indonesian Journal of Electrical Engineering and Computer Science Vol 13, No 1: January 2019
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v13.i1.pp293-299

Abstract

In this paper, an Adaptive Neuro Fuzzy Inference System (ANFIS) based on Arduino microcontroller is applied to the dynamic model of 5 DoF Robot Arm presented. MATLAB is used to detect colored objects based on image processing. Adaptive Neuro Fuzzy Inference System (ANFIS) method is a method for controlling robotic arm based on color detection of camera object and inverse kinematic model of trained data. Finally, the ANFIS algorithm is implemented in the robot arm to select objects and pick up red objects with good accuracy.
A new 2-D multi-stable chaotic attractor and its MultiSim electronic circuit design Sundarapandian Vaidyanathan; Aceng Sambas; Mohamad Afendee Mohamed; Mustafa Mamat; W. S. Mada Sanjaya; Sudarno Sudarno
Indonesian Journal of Electrical Engineering and Computer Science Vol 22, No 2: May 2021
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v22.i2.pp699-707

Abstract

A new multi-stable system with a double-scroll chaotic attractor is developed in this paper. Signal plots are simulated using MATLAB and multi-stability is established by showing two different coexisting double-scroll chaotic attractors for different states and same set of parameters. Using integral sliding control, synchronized chaotic attractors are achieved between drive-response chaotic attractors. A MultiSim circuit is designed for the new chaotic attractor, which is useful for practical engineering realizations.
Determining the arm's motion angle using inverse kinematics models and adaptive neuro-fuzzy interface system Endah Kinarya Palupi; Rofiqul Umam; Rahmad Junaidi; Yudha Satya Perkasa; W. S. Mada Sanjaya
International Journal of Electronics and Communications Systems Vol 1, No 1 (2021): International Journal of Electronics and Communications System
Publisher : Raden Intan State Islamic University of Lampung, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (503.392 KB) | DOI: 10.24042/ijecs.v1i1.9238

Abstract

Robotics technology is known as a great technology demand to be developed continuesly. One of the important things that need to be considered is the control of the motion of the robot. Movement predictions can be modeled in mathematical equations. Prediction based on learning logic is also very supportive of motion control systems, especially arm motion. In this study, the authors combined the two methods as the main study. The working principle of the arm is to take colored objects detected by the camera. In this study, we made arm four DOFs (Degree of Freedom), but only one DOF is controlled by ANFIS because the other three DOFs only move at two fixed angles. Two methods of determining the arm angle of motion used are inverse kinematics and ANFIS methods. The angle of motion and the position of the red object can be observed in real-time on the monitor with the interface in the MATLAB GUI. The angular output that appears in the MATLAB GUI is sent to Arduino in the form of characters, then, Arduino translates it into servo motion to the coordinates of the object detected by the camera. The results showed that the ANFIS method was more effective than the inverse kinematics model.
Design and Analysis Effect of Gantry Angle Photon Beam 4 MV on Dose Distributions using Monte Carlo Method EGSnrc Code System Uum Yuliani; Ridwan Ramdani; Freddy Haryanto; Yudha Satya Perkasa; Mada Sanjaya
Indonesian Journal of Physics Vol 27 No 1 (2016): Vol 27 No 1 (2016), July 2016
Publisher : Institut Teknologi Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (231.79 KB) | DOI: 10.5614/itb.ijp.2016.27.1.3

Abstract

Varian linac modeling has been carried out to obtain Percentage Depth Dose (PDD) and profiles using variations gantry angle 0o, 15o, 30o , 45o in the vertical axis of the surface, field size 10x10 cm2, photon beam 4 MV and Monte Carlo simulations. Percentage Depth Dose and profile illustrates dose distributions in a phantom water measuring 40x40x40 cm3, changes gantry is one of the factors that determine the distribution of the dose to the patient research shows changes in Dmax in the Percentage Depth Dose is affected by changes in the angle gantry resulted in the addition of the area build up so it can be used for therapy in the region and produce skin sparing effects that can be used to protect the skin from exposure to radiation. The graph result is profiles obtained show lack simetrisan in areas positive quadrant has a distribution of fewer doses than the quadrant of negative as well as the slope of the surface so that it can be used for some cases treatments that require a depth and a certain slope, dose calculations are more accurate and can minimize side effects.
Analysis of Effect of Change Source to Surface Distance (SSD) and the Field Size to Distribution Dose Using Monte Carlo Method-EGSnrc Intan Dillia Nurhadi; Ridwan Ramdani; Freddy Haryanto; Yudha Satya Perkasa; Mada Sanjaya
Indonesian Journal of Physics Vol 30 No 1 (2019): Vol 30 No 1 (2019)
Publisher : Institut Teknologi Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (693.89 KB) | DOI: 10.5614/itb.ijp.2019.30.1.3

Abstract

Research was conducted to analyze the effect of changes in the distance radiation source to the surface it is called the medium Source to Surface Distance (SSD) and wide exposure field (Field Size) on the distribution of the dose in linear air Accelerator (LINAC) using Monte Carlo - EGSnrc. Monte Carlo simulation is used for modeling and simulation head linac at BEAMnrc. Virtual model of the linac is made based on the data characteristics of the aircraft Linac Varian Clinac iX then its output obtained information characteristic photon beam using BEAMDP, while modeling and simulation phantom done on DOSXYZnrc with the size of the phantom is (40x40x40) cm3 , with the material in the form of water, using a beam of photons 6 MV, testing variation SSD at 80 cm, 90 cm, 100.1 cm, 110 cm, 120 cm and variation field size is (6x6) cm2, (10x10) cm2, (20x20) cm2 to obtain disribution of dosage form of curves Percentage Depth dose (PDD) and Profile dose. The results showed that the smaller distance radiation source to the surface of the medium (SSD) and the greater the broad field (field size), then increasing the dose distribution is obtained. In the SSD and Field Size variation, the radiation dose will continue to rise significantly from the surface of the medium 0 cm to a depth of maximum dose (Dmax), then the dose began to decline after passing the depth Dmax.
Early Study in Automatic Identification of Epilepsy in Neonatal Using EEGLAB and One Dimensional Convolutional Neural Network Through the EEG Signal Izaz Nadyah; Khoerun Nisa Syaja'ah; Mada Sanjaya Waryono Sunaryo
Jurnal Penelitian Fisika dan Aplikasinya (JPFA) Vol. 13 No. 1 (2023)
Publisher : Universitas Negeri Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26740/jpfa.v13n1.p1-15

Abstract

In detecting epileptic activity, medical experts examine the visual result of Electroencephalography signals. The visual analysis will take a lot of time and effort, due to a large amount of data. Furthermore, there are some errors in concluding the analysis result. One of the ways to analyze this quickly is to use Machine Learning (ML) methods. This study aims to evaluate the performance of 1D-CNN in identifying the given data. First, the signal will go through pre-processing using EEGLAB Toolbox which is then classified to identify epilepsy and non-epilepsy with the 1D-CNN algorithm. The results showed that the proposed method obtained high accuracy values, respectively 99,078% for the training data and 82,069% for the validation results. From the evaluation by a confusion matrix, an average accuracy of 99,31% was obtained. Based on this evaluation, the proposed model can be used as an efficient method in the process of automatic classification, detection, or identification of epileptic activity.