Garuda - Garba Rujukan Digital

Rancang Bangun Alat Cuci Tangan Nirsentuh sebagai Sarana Edukasi dan Pencegahan Covid-19 Gunawan Dewantoro; Ignatius Jody; Imaddudin Abdurrahman; Ferdi Yansen; Hoeko Setyawijaya
Magistrorum et Scholarium: Jurnal Pengabdian Masyarakat Vol 1 No 2 (2020)
Publisher : Universitas Kristen Satya Wacana Salatiga

As the confirmed Covid-19 cases increase, the health promotion and disease-preventing actions become more prevalent in the society, including the proper handwashing campaign. Thus, contactless handwashing machines were constructed to educate the society how to wash hands complying with WHO standards. This machine integrated all the steps of proper handwashing processes, starting from wetting the hands, applying soap, rinsing the hands, and drying the hands, automatically without the need of physical contact. For each handwashing step, an instructional voice is produced to guide the hand washer. The outcome of this community service is the availability of contactless handwashing machines in several spots in Salatiga city, which at the same time serves as educational tools for the society.

Ekstrakurikuler Robotika: Sarana Pengembangan Minat dan Bakat Siswa SD Negeri 02 Salatiga Aditya Bintang Sri Mukti; Paula Agrippina Ika Felixia; Gunawan Dewantoro
Magistrorum et Scholarium: Jurnal Pengabdian Masyarakat Vol 3 No 1 (2022)
Publisher : Universitas Kristen Satya Wacana Salatiga

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (796.758 KB)

Dalam rangka menunjang minat dan bakat siswa, maka kegiatan ekstrakurikuler di luar jam belajar formal diselenggarakan oleh sekolah-sekolah, termasuk ekstrakurikuler robotika di SD Negeri 2 Salatiga. Sebagai instansi yang belum pernah menyelenggarakan ekstrakurikuler robotika, maka SD Negeri 2 Salatiga belum memiliki bekal yang cukup untuk menyelenggarakan secara mandiri, baik dari sisi alat dan bahan maupun sumber daya manusianya. Untuk itulah kegiatan pengabdian masyarakat ini diselenggarakan sebagai jembatan bagi SD Negeri 2 Salatiga agar mampu menyelenggarakan ekstrakurikuler robotika yang berkelanjutan di masa mendatang. Metode yang digunakan dimulai dengan merancang topik pembelajaran, menyiapkan alat dan bahan, dan juga mengajar siswa-siswa peserta ekstrakurikuler seminggu sekali selama satu semester. Hasil dari kegiatan pengabdian masyarakat ini adalah meningkatnya minat siswa terhadap bidang robotika dan juga ketrampilan siswa. Selain itu, kegiatan pengabdian masyarakat ini menjadi bekal berharga bagi SD Negeri 2 Salatiga untuk menyelenggarakan kegiatan serupa di kemudian hari.

Real world design and implementation of pathfinding sewer inspection robot using a-star algorithm Atyanta Rumaksari; Adri Gabriel Sooai; Gloria Song Abimanyu; Gunawan Dewantoro; Hartanto Kusuma Wardana; Budihardja Murtianta; Lukas Bambang Setyawan
Jurnal Mantik Vol. 7 No. 1 (2023): May: Manajemen, Teknologi Informatika dan Komunikasi (Mantik)
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35335/mantik.v7i1.3702

This paper presents the design and implementation of a sewer inspection robot that utilizes the A-Star algorithm for pathfinding. The robot is intended to provide a more efficient solution for culvert workers in inspecting sewer pipes, particularly in hard-to-reach areas. The A-Star algorithm was chosen due to its ease of implementation and low computational resource requirements, making it suitable for real-time applications. The robot was designed with a modular approach, allowing for flexibility in adapting to different pipe sizes and configurations. It is equipped with various sensors and cameras, allowing for accurate inspection of pipe conditions and identification of potential issues. The A-Star algorithm was used to plan the robot's path through the sewer pipes, minimizing the time required for inspection and reducing the risk of damage to the pipes. The results of the implementation showed that the sewer inspection robot using the A-Star algorithm was able to efficiently navigate through the sewer pipes, reducing the time required for inspection and minimizing the need for manual labor. In order to check the performance, we performed experiments on six test models through simulation. On average, the proposed algorithm showed remarkable results, where all models can generate path planning to find the target from the start position. We obtained an average time completion from Models 1 to 6 with a maximum travel distance of 30 meters of 12.96, 4.47, 18.59, 20.71, 24.93, and 19.34 seconds.

Alat Optimasi Suhu dan Kelembaban untuk Inkubasi Fermentasi dan Pengeringan Pasca Fermentasi Gunawan Dewantoro; Sri Hartini; Agustinus Hery Waluyo
Jurnal Rekayasa Elektrika Vol 11, No 3 (2015)
Publisher : Universitas Syiah Kuala

Fermentation optimizer aids have been common around us in both laboratories and home industries. However, these aids only served as incubator and sometimes cannot optimize the fermentation process due to the increasing humidity in a closed box. Nevertheless, adding holes to the box will not lead to a better result since unwanted bacterias come into the box. Therefore, a fermentation optimizer aids has been realized with two separate functions, namely fermentation incubator and post-fermentation dryer. This kit works in the temperature ranging from 35 degree C – 120 degree C, and equipped with two exhaust fans to minimize the humidity in both fermentation and dryermodes. The SHT11 was utilized to measure the temperature and relative humidity. A ceramic heater was used to warm up the air inside the box as desired by users. As the user interface, keypad and character LCD were used. ArduinoMega2560 serves as the main controller of the whole system. Compared to the conventional fermentation process, this kit works 9 hours faster and the fermentation objects are perfectly fermented.

Comparative Study of Computer Vision Based Line Followers Using Raspberry Pi and Jetson Nano Gunawan Dewantoro; Jamil Mansuri; Fransiscus Dalu Setiaji
Jurnal Rekayasa Elektrika Vol 17, No 4 (2021)
Publisher : Universitas Syiah Kuala

The line follower robot is a mobile robot which can navigate and traverse to another place by following a trajectory which is generally in the form of black or white lines. This robot can also assist human in carrying out transportation and industrial automation. However, this robot also has several challenges with regard to the calibration issue, incompatibility on wavy surfaces, and also the light sensor placement due to the line width variation. Robot vision utilizes image processing and computer vision technology for recognizing objects and controlling the robot motion. This study discusses the implementation of vision based line follower robot using a camera as the only sensor used to capture objects. A comparison of robot performance employing different CPU controllers, namely Raspberry Pi and Jetson Nano, is made. The image processing uses an edge detection method which detect the border to discriminate two image areas and mark different parts. This method aims to enable the robot to control its motion based on the object captured by the webcam. The results show that the accuracies of the robot employing the Raspberry Pi and Jetson Nano are 96% and 98%, respectively.

An Embedded Convolutional Neural Network for Maze Classification and Navigation Gunawan Dewantoro; Dinar Rahmat Hadiyanto; Andreas Ardian Febrianto
JURNAL NASIONAL TEKNIK ELEKTRO Vol 12, No 2: July 2023
Publisher : Jurusan Teknik Elektro Universitas Andalas

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25077/jnte.v12n2.1091.2023

Traditionally, the maze solving robots employ ultrasonic sensors to detect the maze walls around the robot. The robot is able to transverse along the maze omnidirectionally measured depth. However, this approach only perceives the presence of the objects without recognizing the type of these objects. Therefore, computer vision has become more popular for classification purpose in robot applications. In this study, a maze solving robot is equipped with a camera to recognize the types of obstacles in a maze. The types of obstacles are classified as: intersection, dead end, T junction, finish zone, start zone, straight path, T–junction, left turn, and right turn. Convolutional neural network, consisting of four convolution layers, three pooling layers, and three fully-connected layers, is employed to train the robot using a total of 24,000 images to recognize the obstacles. Jetson Nano development kit is used to implement the trained model and navigate the robot. The results show an average training accuracy of 82% with a training time of 30 minutes 15 seconds. As for the testing, the lowest accuracy is 90% for the T-junction with the computational time being 500 milliseconds for each frame. Therefore, the convolutional neural network is adequate to serve as classifier and navigate a maze solving robot.

Alat Optimasi Suhu dan Kelembaban untuk Inkubasi Fermentasi dan Pengeringan Pasca Fermentasi Gunawan Dewantoro; Sri Hartini; Agustinus Hery Waluyo
Jurnal Rekayasa Elektrika Vol 11, No 3 (2015)
Publisher : Universitas Syiah Kuala

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.17529/jre.v11i3.2245

Fermentation optimizer aids have been common around us in both laboratories and home industries. However, these aids only served as incubator and sometimes cannot optimize the fermentation process due to the increasing humidity in a closed box. Nevertheless, adding holes to the box will not lead to a better result since unwanted bacterias come into the box. Therefore, a fermentation optimizer aids has been realized with two separate functions, namely fermentation incubator and post-fermentation dryer. This kit works in the temperature ranging from 35 degree C – 120 degree C, and equipped with two exhaust fans to minimize the humidity in both fermentation and dryermodes. The SHT11 was utilized to measure the temperature and relative humidity. A ceramic heater was used to warm up the air inside the box as desired by users. As the user interface, keypad and character LCD were used. ArduinoMega2560 serves as the main controller of the whole system. Compared to the conventional fermentation process, this kit works 9 hours faster and the fermentation objects are perfectly fermented.

Comparative Study of Computer Vision Based Line Followers Using Raspberry Pi and Jetson Nano Gunawan Dewantoro; Jamil Mansuri; Fransiscus Dalu Setiaji
Jurnal Rekayasa Elektrika Vol 17, No 4 (2021)
Publisher : Universitas Syiah Kuala

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.17529/jre.v17i4.21324

The line follower robot is a mobile robot which can navigate and traverse to another place by following a trajectory which is generally in the form of black or white lines. This robot can also assist human in carrying out transportation and industrial automation. However, this robot also has several challenges with regard to the calibration issue, incompatibility on wavy surfaces, and also the light sensor placement due to the line width variation. Robot vision utilizes image processing and computer vision technology for recognizing objects and controlling the robot motion. This study discusses the implementation of vision based line follower robot using a camera as the only sensor used to capture objects. A comparison of robot performance employing different CPU controllers, namely Raspberry Pi and Jetson Nano, is made. The image processing uses an edge detection method which detect the border to discriminate two image areas and mark different parts. This method aims to enable the robot to control its motion based on the object captured by the webcam. The results show that the accuracies of the robot employing the Raspberry Pi and Jetson Nano are 96% and 98%, respectively.

An Embedded Computer Vision using Convolutional Neural Network for Maze Classification and Robot Navigation Dewantoro, Gunawan; Hadiyanto, Dinar Rahmat; Febrianto, Andreas Ardian
Jurnal Teknologi dan Sistem Komputer [IN PRESS] Volume 10, Issue 4, Year 2022 (October 2022)
Publisher : Department of Computer Engineering, Engineering Faculty, Universitas Diponegoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14710/jtsiskom.2022.14474

Traditionally, the maze solving robots employ ultrasonic sensors to detect the maze walls around the robot. However, this approach only perceives the presence of the objects without recognizing the type of these objects. Therefore, computer vision has become more popular for classification purpose in robot applications. In this study, a maze solving robot is equipped with a camera to recognize the types of obstacles in a maze. The types of obstacles are classified as: intersection, dead end, T junction, finish zone, start zone, straight path, T–junction, left turn, and right turn. Convolutional neural network is employed to train the robot using a total of 24,000 images to recognize the obstacles. Jetson Nano development kit is used to implement the trained model and navigate the robot. The results shows an average training accuracy of 82% with a training time of 30 minutes 15 seconds. As for the testing, the lowest accuracy is 90% for the T-junction with the computational time being 500 milliseconds for each frame. Therefore, the convolutional neural network is adequate to serve as classifier and navigate a maze solving robot.

SELF-BALANCING ROBOT BERODA DUA DENGAN METODE PID Setiawan, Agus; Susilo, Deddy; Dewantoro, Gunawan
JST (Jurnal Sains dan Teknologi) Vol. 10 No. 1 (2021)
Publisher : Universitas Pendidikan Ganesha

Perkembangan teknologi membuat para peneliti berkeinginan mengembangkan robot lebih dari dua dekade ini, salah satu pengembangannya yaitu dengan menambahkan fitur self-balancing pada robot trainer untuk edukasi. Fitur ini menggunakan konsep pendulum terbalik yang harus menyeimbangkan pusat massa agar dapat berada di posisi seimbang. Untuk dapat membuat robot dapat berdiri dengan seimbang, maka dipakailah sebuah metode yaitu kendali PID. Metode ini bertujuan untuk membuat error sudut sekecil-kecilnya sehingga dapat membuat robot beroda dua pada posisi tegak. Robot yang digunakan merupakan robot Trainer Edukasi yang dirancang untuk media pembelajaran dan telah digunakan di beberapa sekolah yang terdapat di Kota Salatiga. Hasil pengujian menunjukkan bahwa robot dapat menyeimbangkan diri dan tahan terhadap gangguan luar dengan baik, dengan error kemiringan sebesar 1,14 derajat. Robot ini juga mampu bergerak dalam posisi tegak dengan kecepatan maksimal yang dapat ditangani robot adalah 15,07 cm/detik.

Title

Found 41 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 41 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 41 Documents
Search