Claim Missing Document
Check
Articles

Found 34 Documents
Search

Braille Character Recognition Using Artificial Neural Network Joko Subur; Tri Arief Sardjono; Ronny Mardiyanto
IPTEK Journal of Proceedings Series No 1 (2015): 1st International Seminar on Science and Technology (ISST) 2015
Publisher : Institut Teknologi Sepuluh Nopember

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (320.825 KB) | DOI: 10.12962/j23546026.y2015i1.1048

Abstract

Braille letter is characters designed for the blind, consist of six embossed points, arranged in a standard braille character. Braille letters is touched and read using fingers, therefore the sensitivity of the fingers is important. Those characters need to be memorized, so it is very difficult to be learned. The aim of this research is to create a braille characters recognition system and translate it to alpha-numeric text. Webcam camera is used to capture braille image from braille characters on the paper sheet. Cropping, grayscale, thresholding, erotion, and dilation techniques are used for image preprocessing. Then, artificial neural network method are used to recognize the braille characters. The system can recognize braille characters with 99% accuracy even when the braille image is tilted up to 1 degrees.
Sistem Pelacakan Objek Menggunakan Kombinasi Algoritma Optical Flow dan Template Matching Ahmad Fahriannur; Ronny Mardiyanto; Meilana Siswanto
Jurnal Teknologi dan Sistem Komputer Volume 6, Issue 1, Year 2018 (January 2018)
Publisher : Department of Computer Engineering, Engineering Faculty, Universitas Diponegoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (530.347 KB) | DOI: 10.14710/jtsiskom.6.1.2018.13-17

Abstract

This study aimed to develop a tracking system algorithm by combining optical flow and template matching algorithms to strengthen tracking and minimize the resulting errors. The system has been tested on a football video game with the ball as a tracking object. The optical flow and template matching algorithms are used interchangeably based on the coordinates of both ranges calculated using the Euclidean distance equation. The result shows that the system is able to do tracking, although it is temporarily blocked by other objects, more stable and the distance error between the coordinates of the tracking result and the actual coordinates is not more than 110 pixels compared to using only optical flow or template matching algorithm.
Desain MPPT Berbasis Kontrol Logika Fuzzy Untuk Aplikasi Pesawat Terbang Heri Suryoatmojo; Fahad Al Hazmi; D C Riawan; Ronny Mardiyanto
Approach : Jurnal Teknologi Penerbangan Vol. 1 No. 2 (2017): Oktober 2017
Publisher : Politeknik Penerbangan Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (657.102 KB)

Abstract

Panel surya merupakan media untuk mengkonversi energi matahari menjadi energi listrik. Selaindigunakan secara konvensional sebagai sumber energi listrik, panel surya dapat diaplikasikan sebagaisumber utama energi listrik pada pesawat terbang tanpa awak. Panel surya menghasilkan energi listrikyang berfluktuasi mengikuti besarnya iradiansi dan temperatur sekitar. Berdasarkan karakteristik panelsurya, jika dioperasikan pada keadaan normal maka daya yang dibangkitkan dari panel surya tidakakan maksimal. Supaya daya yang dibangkitkan dari panel surya maksimal, maka diperlukanMaximum Power Point Tracking (MPPT). Pada pesawat tanpa awak, iradiansi matahari nilainyaberubah dengan sangat cepat, sehingga MPPT konvensional kurang efisien karena memiliki responyang lembat serta memiliki osilasi pada saat berada pada kondisi daya maksimal. Pada penelitian iniakan dirancang dan diimplementasikan sistem MPPT dengan kontrol logika fuzzy. Kontrol logikafuzzy dapat mempercepat respon sistem terhadap perubahan beban, serta mengurangi osilasi yangterjadi pada daya maksimum. Konverter, sebagai aktuator dari pengkondisi tegangan akan dipilih yangmemiliki berat seringan mungkin sehingga tidak akan menambah beban kerja dari pesawat. Dari hasilpercobaan menunjukan bahwa MPPT berbasis logika Fuzzy mempunyai respon yang lebih cepatdibandingkan dengan metode hill climbing.
Desain dan Implementasi Konverter DC-DC Topologi SEPIC Termodifikasi dengan Gain Statis yang Tinggi untuk Aplikasi pada Photovoltaic Heri Suryoatmojo; Indra Dilianto; Suwito Suwito; Ronny Mardiyanto; Eko Setijadi
Approach : Jurnal Teknologi Penerbangan Vol. 2 No. 1 (2018): April 2018
Publisher : Politeknik Penerbangan Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (411.242 KB)

Abstract

Dalam merancang sistem pembangkit photovoltaic terhubung jala-jala, diperlukan konverter DC-DC untuk meningkatkan tegangan keluaran photovoltaic. Dalam perancangan konverter DC-DC, biasanya digunakan konverter dengan gain statis yang tinggi dengan tujuan untuk meningkatkan tegangan keluaran photovoltaic dan memperoleh efisiensi konversi yang tinggi. Salah satu jenis konverter yang digunakan adalah konverter topologi SEPIC. Namun, konverter DC-DC konvensional seperti konverter topologi SEPIC memiliki gain statis dengan tegangan keluaran yang rendah. Konverter SEPIC konvensional hanya dapat meningkatkan tegangan keluaran sebesar 5 kali dari tegangan masukan ketika Duty Cycle bernilai 0.8182. Untuk memenuhi standard gain statis yang tinggi, maka diperlukan tegangan keluaran sebesar 10 kali dari tegangan masukan. Untuk mengatasi permasalahan tersebut, maka penulis mengusulkan menggunakan topologi konverter DC-DC SEPIC termodifikasi. Modifikasi pada konverter SEPIC konvensional dilakukan dengan menambahkan kapasitor dan dioda. Konverter DC-DC SEPIC termodifikasi dapat menaikkan tegangan keluaran hingga 10 kali dari tegangan masukan. Dengan diterapkannya topologi ini, maka diharapkan dapat diperoleh tegangan keluaran konverter yang tinggi untuk aplikasi pada photovoltaic.
Transformerless dc Converter for Distributed Solar Power Generation System Heri Suryoatmojo; Akbar Faiz; Mochamad Ashari; Ronny Mardiyanto
JAREE (Journal on Advanced Research in Electrical Engineering) Vol 1, No 1 (2017): April
Publisher : Department of Electrical Engineering ITS and FORTEI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12962/j25796216.v1.i1.7

Abstract

There are two types of distributed solar power generation system stand-alone system and grid-connected system. In grid-connected system usually are equiped with additional transformer to transfer the energy from solar power to the grid. However, it has resulted in considerable cost in providing these systems. Therefore in this reserach develops boost transformerless inverter system. The proposed system consists of a boost converter and transformerless inverter. Boost converter is used to increse the dc voltage yield by photovoltaic (PV) and delivered to the grid by mean of  transformerless inverter.In order to maximize the power from PV, the proposed system is also designed with Maximum Power Point Tracking (MPPT) by changing the value of modulation index in the transformerless inverters. From the simulation results show that the system can work effectively in a variety conditions such as light intensity changed and fluctuating in the grid  voltage side. Keywords: Inverter Transformerless, Boost Converter, MPPT, Photovoltaic.
Development of Water-Surface Robotic Vehicle to Assist Communication Between Remotely Operated Vehicle Underwater Robot and Control Station Badrut Tamam; Ronny Mardiyanto
JAREE (Journal on Advanced Research in Electrical Engineering) Vol 1, No 2 (2017): October
Publisher : Department of Electrical Engineering ITS and FORTEI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12962/j25796216.v1.i2.28

Abstract

This paper developed a water-surface robotic vehicle that act as repeater station to assist the communication between ROV (Remotely Operated Vehicle) underwater robot and control station. The key issue here is how the robot can relay the data communication between the ROV and the control station. The communication between repeater Station and control station is based on wireless, whereas the communication between repeater Station and ROV is based on wire. Data that have transmit from control station is received by Repeater Station and continued to the ROV through wire. The Power needed is suplied by photovoltaic (PV) to the Repeater Station and the ROV. The position of Repeater Station is controlled, so the position of Repeater Station and ROV always in parallel. In practices, there are two way directly communication between control station with ROV, that are based on wireless and through wire. Nevertheless, wireless communication system never used to observed on the ocean or the deep waters because there is a high attenuation of a signal when cross the air-water boundary. Based on these problems, we make a Repeater Station that used a buoyant communication system models. Communication from control station to Repeater Station in the form of motion control and data. Whereas, communication from Repeater Station to ROV in the form of motion control, data, and power supply. Communication frequency is at 5,8 GHz for audio video and 433 MHz for motion control and telemetry. The connection wire between Repeater Station and ROV can go along and shorten with automatically roll as feature. Electricity from PV is strorage to a battery in the Repeater Station. Charging of the battery occur when battery power is not full and will cease if battery power is being full. Power of the battery must be full if want to operated the Repeater Station. The availability of the Repeater Station is expected to assist the communication between ROV underwater robot with control station, so ROV can be controlled remotely and can increase range of the reach.Keywords: Water-Surface Robotic Vehicle; Communication; Position Control; Repeater Station; Self Charging
Autopilot Pesawat Tanpa Awak Menggunakan Algoritme Genetika untuk Menghilangkan Blank Spot Ronny Mardiyanto; Muhammad Ichlasul Salik; Djoko Purwanto
Jurnal Nasional Teknik Elektro dan Teknologi Informasi Vol 11 No 1: Februari 2022
Publisher : Departemen Teknik Elektro dan Teknologi Informasi, Fakultas Teknik, Universitas Gadjah Mada

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1669.33 KB) | DOI: 10.22146/jnteti.v11i1.2492

Abstract

This paper presents the autopilot of unmanned aerial vehicles (UAV) with the ability to minimize blank spots on aerial mapping using the genetic algorithm. The purpose of the developed autopilot is to accelerate the times required for aerial mapping and save battery consumption. Faster time in conducting aerial mapping saves operational costs, saves battery consumption, and reduces UAV maintenance costs. The proposed autopilot has the ability to analyze blank spots from aerial shots and optimize flight routes for re-photography. The genetic algorithm was applied to obtain the shortest distance, which was done to save battery consumption and flight time. When developing the autopilot, the operator would manually set the flight route, then the aircraft would fly according to that route. The unstable wind factor has caused a shift in the flight route, which correspondingly caused blank spots. After all flight routes were traversed, the system developed would analyze the location of the blank spots. The new flight route was calculated using the genetic algorithm to determine the shortest distance from all the blank spot locations. The system developed consisted of a UAV equipped with autopilot and a ground control station (GCS). At the time of flight, the UAV would send the coordinates of the path traversed to the GCS to calculate the blank spot analysis. After the flight mission has been completed, the GCS would create a new route and send it to the UAV. The test carried out was an aircraft with a height of 120m using a 4S 4,200 mAh 25C lipo battery, and the percentage of throttle when flying straight was 30%. The results obtained are that the developed autopilot saves 46.4% of the time and saves 41.18% of battery capacity compared to conventional autopilots.
DEVELOPMENT OF AUTONOMOUS UNDERWATER VEHICLE (AUV) BASED ON ROBOTIC OPERATING SYSTEM FOR FOLLOWING UNDERWATER CABLE Mardiyanto Ronny
Jurnal Ilmiah Kursor Vol 11 No 3 (2022)
Publisher : Universitas Trunojoyo Madura

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21107/kursor.v11i3.274

Abstract

In addition to satellites, the Marine Cable Communication Channel (SKKL) which is located under the sea is also one of the backbones of the communication network to connect from one island to another. However, there are often irresponsible parties who damage or commit acts of vandalism. This action resulted in the disruption of the communication process on the submarine cable network. So, it is necessary to periodically check the condition of the underwater communication network cables. Regular checking of underwater cables is very risky, so we propose an underwater robot to handle it. This paper presents the development of Autonomous Underwater Vehicle (AUV) based on Robotic Operating System (ROS) for Following Underwater Cable to monitor the condition of the cables automatically. The AUV is equipped with a camera, Nvidia Jetson Nano, Arduino, Flight Controller, ESC, and brushless DC motors that used to assist the tracking process on the cable. The camera is used as the main visual sensor. Visual image processing methods are carried out using thresholding and contours detection methods, then the obtained data are processed to drive the motors on the AUV so that they can move on the direction of the cable. The experiment results show that the object detection method can be used under conditions with light intensity more than 25 lux. It works optimally at speeds of 0.27 m/s to 0.42 m/s. In the horizontal motion control test, the overshoot parameter value is ±60%, rise time is 2s, settling time is 16s, and steady state error is ±20%. The AUV can track on a straight and winding path of 2 meters with a bright light intensity of ±493 lux, a dim light of ±107 lux and a dark light intensity of ±25 lux with the help of an LED beam with a light intensity of ±773 lux. The percentage of success of scoping experiments on a straight track and a winding track with three trials is 75%. This performance shows that the developed AUV works well to follow underwater cable.
Pengukuran Tingkat Kesiapan daan Pengembangan Model Kota Cerdas (Smart City) Kabupaten Pamekasan Eko Setijadi; Ronny Mardiyanto; Aang Kisnu Darmawan; Hoiriyah; Iwan Santosa
Sewagati Vol 4 No 2 (2020)
Publisher : Pusat Publikasi ITS

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (820.614 KB)

Abstract

Konsep kota cerdas (smart city) saat ini merupakan sebuah trend dan pilihan utama untuk pengolaan kota berbasis TIK yang terintegrasi. Konsep kota cerdas diharapkan menjadi solusi dari permasalan kota yang semakin kompleks dan multi dimensi. Tahun 2018, pemerintah Indonesia telah memulai Gerakan menuju 50 smart city, sebagai inisiasi untuk menyiapkan berbagai kota menjadi sebuah kota cerdas. Kabupaten Pamekasan telah memulai berbagai inisiasi untuk menjadi sebuah kota cerdas. Akan tetapi terdapat berbagai masalah dan kendala dalam hal penyiapan Masterplan, koordinasi antar stakeholder, penyiapan infrastruktur, teknostruktur, dan suprastruktur TIK. Program Abdimas berbasis penelitian ini bertujuan untuk melakukan kajian, pengukuran kesiapan dan pengembangan model kota cerdas di kabupaten Pamekasan. Pada program ini kegiatan ini di fokuskan pada pengukuran kesiapan dan koordinasi antar stakeholder smart city, yaitu pemerintah, masyarakat, sektor swasta/UKM dan sektor pendidikan yang terdampak pembangunan kota cerdas di kabupaten Pamekasan. Metode yang digunakan dalam kegiatan abdimas berbasis penelitian ini adalah Kajian kesiapan kota cerdas, sosialisasi, forum group discussion, kajian pengembangan masterplan/kerangka kerja kota cerdas dan kooordinasi antar dinas serta stake holder smart city. Hasil yang didapat dari kegiatan ini adalah analisis tingkat kesiapan kota cerdas kabupaten pamekasan dan peningkatan koordinasi antar stakeholder smart city kabupaten pamekasan. Kegiatan ini diharapkan bisa memberikan konstribusi dalam proses pembangunan smart city kabupaten pamekasan.
Peningkatan Akurasi Adaptive Monte Carlo Localization Menggunakan Convolutional Neural Network Riza Agung Firmansyah; Tri Arief Sardjono; Ronny Mardiyanto
Jurnal Nasional Teknik Elektro dan Teknologi Informasi Vol 12 No 3: Agustus 2023
Publisher : Departemen Teknik Elektro dan Teknologi Informasi, Fakultas Teknik, Universitas Gadjah Mada

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/jnteti.v12i3.7432

Abstract

This paper explains the increase in localization system accuracy of the adaptive Monte Carlo localization (AMCL) in robots utilizing a convolutional neural network (CNN). The localization system in robots is defined as the position recognition process of robots within their working environment. This system is essential as it allows robots to navigate and map efficiently and accurately. Without appropriate localization, robots cannot operate effectively and can encounter troubles such as losing direction or bumping into objects. AMCL is a popular localization system and is widely applied in robots. This method utilizes the changes in the robots’ position and light detection and ranging (LiDAR) sensor reading as input. Reading of robot position changes is susceptible to error due to slips or wheel deformations. The inaccuracy of reading the robots’ position change results in the inaccuracy of the robots’ position prediction by AMCL, so improvements are required. Novelty in this paper includes providing compensation values from AMCL results for the error to be small. These compensation values were obtained from the CNN training results; hence, the proposed method was dubbed AMCL+CNN. Inputs given to the CNN were the changes in wheel odometry values and distance reading by the LiDAR sensor. CNN outputs were compared to the target data in the form of the robots’ actual position from observation results. Network training was conducted for as many as 200 epochs to achieve the lowest validation loss. Testing was done on a robot installed with a robot operating system (ROS). Training and testing datasets were obtained from rosbag data when the robot traversed the testing area. In straight and turn scenarios, obtained AMCL+CNN algorithms had fewer errors than the regular AMCL and Monte Carlo localization (MCL). Results obtained are also superior in terms of positional error metrics when compared to several other comparison methods.