Garuda - Garba Rujukan Digital

Pengenalan Personal Menggunakan Citra Tampak Atas pada Lingkungan Cashierless Strore Prastowo, Bambang Nurcahyo; Putro, Nur Achmad Sulistyo; Dhewa, Oktaf Agni; Yusuf, Ach Maulana Habibi
Jurnal Buana Informatika Vol 10, No 1 (2019): Jurnal Buana Informatika Volume 10 Nomor 1 April 2019
Publisher : Universitas Atma Jaya Yogyakarta

Abstract.Personal recognition with image processing techniques from the side view has the disadvantage of being applied to the cashierless store environment, namely inaccurate recognition or identification when personal collisions occur. To overcome this, the image capture method is used from the top-view. Personal recognition method through the top-view image using the Haar Cascade Classifier method. 1420 positive images and 2170 negative images are used to find features that are considered suitable for recognizing objects using the Adaptive Boosting (Adaboost) method. Tests were carried out on 100 test data by varying the parameters of min_neighbors (3.4, and 5) and the size of the dataset window (25x25, 35x35, 45x45 pixels). Personal recognition testing gets the highest accuracy of 89.9% with the parameters used are min_neighbors 5 and the size of the 25x25 pixel dataset in the detection parameter size of min_size 140x140 pixels.Keywords: Person recognition, image processing, cashierless storeAbstrak. Pengenalan personal dengan teknik pengambilan citra dari tampak samping memiliki kelemahan untuk diterapkan pada lingkungan cashierless store yaitu tidak akuratnya pengenalan atau identifikasi saat terjadi tubrukan antar personal. Untuk mengatasi hal tersebut maka dipakailah metode pengambilan citra dari tampak atas. Metode pengenalan personal melalui citra tampak atas menggunakan metode Haar Cascade Classifier. Digunakan 1420 citra positif dan 2170 citra negatif untuk menemukan fitur-fitur yang dianggap cocok untuk mengenali objek dengan menggunakan metode Adaptive Boosting (Adaboost). Pengujian dilakukan terhadap data tes sebanyak 100 citra dengan menvariasikan parameter min_neighbors (3,4, dan 5) dan ukuran window dataset (25x25, 35x35, 45x45 piksel). Pengujian pengenalan personal mendapatkan akurasi tertinggi sebesar 89,9% dengan parameter yang dipakai yaitu min_neighbors 5 dan ukuran window dataset 25x25 piksel pada parameter ukuran pengujian min_size 140x140 piksel.Kata Kunci: pengenalan personal, pengolahan citra, cashierless store

Low Cost Sensor Node Device for Monitoring Landslides Lukman Awaludin; Oktaf Agni Dhewa
IJEIS (Indonesian Journal of Electronics and Instrumentation Systems) Vol 8, No 2 (2018): October
Publisher : IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.

Landslides are one of the natural disasters that often occur in Indonesia. Therefore, this disaster cannot be eliminated, but it can minimize the disadvantage caused by an early warning mechanism. Early warning systems rely on a sensor node used to read soil conditions with specific parameters. Those parameters that are read lead to the detection of mass movements. With the tightness of the monitoring process, of course, a reliable sensor node is needed. However, there are challenges in how to minimize losses that occur due to damage to sensor nodes when landslides occur. Sensor nodes are made using IMU sensors to monitor mass movements and its use two processors, namely microcontroller and mini SBC, which are inexpensive to manufacture and do not require large space in the installation.

PLO User Interface based on Telegram Bot Bambang Nurcahyo Prastowo; Nur Achmad Sulistyo Putro; Oktaf Agni Dhewa
IJCCS (Indonesian Journal of Computing and Cybernetics Systems) Vol 13, No 1 (2019): January
Publisher : IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/ijccs.29089

Instant messaging services usually integrate a notification system on their users’ devices, as phone calls and short message service (SMS) systems do. Telegram is – as far as we are aware – the only popular instant messaging service that uses open source code. Telegram also provides APIs for their users, enabling the development of a bot system that allows instant messaging application to access information. Here, we study the potential use of Telegram bot as a user interface to a paperless office (PLO) system developed in our institution. We found that Telegram bot improves communication among the users; however, as the amount of messages increased, the server becomes overloaded. This limitation suggests that future works need to be directed to improving the efficiency of the bot

Pengenalan Personal Menggunakan Citra Tampak Atas pada Lingkungan Cashierless Strore Bambang Nurcahyo Prastowo; Nur Achmad Sulistyo Putro; Oktaf Agni Dhewa; Ach Maulana Habibi Yusuf
Jurnal Buana Informatika Vol. 10 No. 1 (2019): Jurnal Buana Informatika Volume 10 Nomor 1 April 2019
Publisher : Universitas Atma Jaya Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24002/jbi.v10i1.1779

Abstract.Personal recognition with image processing techniques from the side view has the disadvantage of being applied to the cashierless store environment, namely inaccurate recognition or identification when personal collisions occur. To overcome this, the image capture method is used from the top-view. Personal recognition method through the top-view image using the Haar Cascade Classifier method. 1420 positive images and 2170 negative images are used to find features that are considered suitable for recognizing objects using the Adaptive Boosting (Adaboost) method. Tests were carried out on 100 test data by varying the parameters of min_neighbors (3.4, and 5) and the size of the dataset window (25x25, 35x35, 45x45 pixels). Personal recognition testing gets the highest accuracy of 89.9% with the parameters used are min_neighbors 5 and the size of the 25x25 pixel dataset in the detection parameter size of min_size 140x140 pixels.Keywords: Person recognition, image processing, cashierless storeAbstrak. Pengenalan personal dengan teknik pengambilan citra dari tampak samping memiliki kelemahan untuk diterapkan pada lingkungan cashierless store yaitu tidak akuratnya pengenalan atau identifikasi saat terjadi tubrukan antar personal. Untuk mengatasi hal tersebut maka dipakailah metode pengambilan citra dari tampak atas. Metode pengenalan personal melalui citra tampak atas menggunakan metode Haar Cascade Classifier. Digunakan 1420 citra positif dan 2170 citra negatif untuk menemukan fitur-fitur yang dianggap cocok untuk mengenali objek dengan menggunakan metode Adaptive Boosting (Adaboost). Pengujian dilakukan terhadap data tes sebanyak 100 citra dengan menvariasikan parameter min_neighbors (3,4, dan 5) dan ukuran window dataset (25x25, 35x35, 45x45 piksel). Pengujian pengenalan personal mendapatkan akurasi tertinggi sebesar 89,9% dengan parameter yang dipakai yaitu min_neighbors 5 dan ukuran window dataset 25x25 piksel pada parameter ukuran pengujian min_size 140x140 piksel.Kata Kunci: pengenalan personal, pengolahan citra, cashierless store

Peningkatan Kestabilan Quadrotor menggunakan Kendali Linear Quadratic Regulator dengan Kompensasi Integrator dalam Mempertahankan Posisi Oktaf Agni Dhewa; Faisal Fajri Rahani
Buletin Ilmiah Sarjana Teknik Elektro Vol. 4 No. 2 (2022): Agustus
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/biste.v4i2.6808

The quadrotor's ability to maintain position is a major requirement for the completion of various current missions. However, the large steady-state error (SSE) and multiple overshoots due to environmental disturbances cause flight instability. This condition makes Quadrotor unable to complete the mission optimally. Therefore, in this study applying a linear quadratic regulator control method, this research contributes to the addition of integrator compensation in handling the translational movement of the quadrotor. System model design testing is carried out by comparing quadrotor control using the LQR method without an Integrator and LQR with an Integrator. The value of R=1 for all states and Q_x=0.87, Q_y=124.6, Q_(v_x)=1.77, Q_(v_y)=124.6 and Ki_x=0,004, Ki_y=0.002 makes the SSE tendency that occurs 0.10 meters for the x-axis and -0.28 for the y-axis, while the multi-overshoot that occurs is 0.41 m for the maximum deviation and -1.35 m for the minimum deviation on the x-axis and 0.40 m maximum deviation and 0.47 m minimum deviations on the y axis. The test results show that the LQR control method with Integrator compensation is able to minimize and improve SSE and multiple overshoots that occur in quadrotor flights. In addition, it is able to significantly increase accuracy to 100% from 71.38% and precision to 37.71% from 35.91%.Kemampuan quadrotor dalam mempertahankan posisi menjadi kebutuhan utama untuk penyelesaian berbagai misi saat ini. Namun, besarnya steady state error (SSE) dan multiple overshoot karena gangguan lingkungan menyebabkan ketidakstabilan gerak terbang. Kondisi tersebut menjadikan quadrotor tidak mampu menyelesaikan misi secara optimal. Maka dari itu, pada penelitian ini menerapkan sebuah metode kendali Linear Quadratic Regulator penelitian ini memiliki kontribusi dengan penambahan kompensasi Integrator dalam menangani pergerakan translasi quadrotor. Pengujian desain model sistem, dilakukan dengan membandingkan antara pengendalian quadrotor menggunakan metode LQR tanpa Integrator dan LQR dengan Integrator. Nilai R=1 untuk semua state serta Q_x=0,87; Q_y=124,6; Q_(v_x)=1,77; Q_(v_y)=124,6 dan Ki_x=0,004; Ki_y=0,002 menjadikan kecenderungan SSE yang terjadi sebesar 0,10 m untuk sumbu x dan -0,28 m untuk sumbu y, sedangkan multi overshoot yang terjadi sebesar 0,41 meter simpangan maksimal dan -1,35 m simpangan minimal pada sumbu x serta 0,40 m simpangan maksimal dan 0,47 meter simpangan minimal pada sumbu y. Hasil pengujian tersebut menunjukkan bahwa metode LQR dengan kompensasi Integrator mampu meminimalkan dan memperbaiki SSE maupun multiple overshoot yang terjadi pada penerbangan quadrotor. Selain itu juga mampu meningkatkan akurasi secara signifikan sebesar 100% dari 71,38% serta presisi sebesar 37,71% dari 35,91%.

Crowd Detection System Using Blimp Drones as an Effort to Mitigate the Spread of Covid-19 Based on Internet of Things Mashoedah Mashoedah; Oktaf Agni Dhewa; Zulhakim Seftiyana Roviyan; Dheni Leo; Silvia Larasatul Masyitoh
Elinvo (Electronics, Informatics, and Vocational Education) Vol 6, No 2 (2021): November 2021
Publisher : Department of Electronic and Informatic Engineering Education, Faculty of Engineering, UNY

The application of health protocols is a regulation that is applied to prevent the spread of Covid-19. Public awareness of the implementation of health protocols is still lacking. This study aims to determine the performance of the detection system using the Blimp Drone as an effort to mitigate the spread of Covid-19 based on the Internet of Things. The method used in system development consists of literature review, needs analysis, design, manufacture, and testing. This system uses the Blimp Drone as a vehicle to carry out flight missions. Raspberry pi camera as a component for distance detection in crowds and mask detection, and Flir Lepton 2.5 as a component for temperature detection. In addition, thealso used raspberry pi 4 is as a component for image processing of the distance detection system for crowd, mask, and temperature detection. The results of the tests carried out are: (1) the results of the analysis of the lifting power of the Blimp Drone using pure helium and a diameter of 0.91m capable of lifting a load of 0.45kg (2) the system can detect the distance of each person in the crowd (3) the system can detect everyone who using a mask and not wearing a mask (4) the system can detect the temperature of each person using image processing (5) an audio warning sounds when a person who is not wearing a mask is detected and the distance between 2 people in a crowd of less than 1 meter is detected (6) the advantages of this tool ie can work autonomous in flight missions to detect the distance the crowd, masks, and temperature, as well as integrated with system the Internet of Things so that data the results capturing can be accessed in real time for further action by the authorities.

Implementasi Integrasi Computer Vision dan Kendali PID untuk Robot Line Follower dengan Kendali Kecepatan Dinamis Priambodo, Ardy Seto; Nasuha, Aris; Dhewa, Oktaf Agni
Telekontran : Jurnal Ilmiah Telekomunikasi, Kendali dan Elektronika Terapan Vol. 12 No. 1 (2024): TELEKONTRAN vol 12 no 1 April 2024
Publisher : Program Studi Teknik Elektro, Fakultas Teknik dan Ilmu Komputer, Universitas Komputer Indonesia.

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34010/telekontran.v12i1.13323

This research aims to develop a dynamic speed control system for line follower robots by integrating computer vision technology and PID control. The main challenge in controlling line follower robots is maintaining stability and speed while navigating various types of turns and complex paths. This study proposes the use of computer vision to detect paths more accurately and responsively, and PID control to dynamically adjust the robot's speed based on detected errors. The research methods involve simulating the e-puck robot in a Webots environment, developing algorithms for black line detection and error calculation, and designing the PID control system. The test results show that in Arena 1, the completion time with fixed base speed is 58.08 seconds, while with dynamic base speed it is 50.386 seconds, indicating a 13.3% reduction in completion time. In Arena 2, the completion time with fixed base speed is 71.584 seconds, while with dynamic base speed it is 66.624 seconds, indicating a 6.9% reduction in completion time. Thus, this control system is more effective in keeping the robot on the desired path, reducing deviations and improving path tracking accuracy.

Benchmark Analysis of Sampling Methods for RRT Path Planning Pratama, Gilang Nugraha Putu; Dhewa, Oktaf Agni; Priambodo, Ardy Seto; Baktiar, Faris Yusuf; Prasetyo, Rizky Hidayat; Jati, Mentari Putri; Hidayatulloh, Indra
Control Systems and Optimization Letters Vol 2, No 2 (2024)
Publisher : Peneliti Teknologi Teknik Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59247/csol.v2i2.132

Path planning is a crucial aspect of mobile robot navigation, ensuring that robots can safely travel from their initial position to the goal. In real-world applications, path planning is essential for autonomous vehicles, drones, warehouse robots, and rescue robots to navigate complex environments efficiently and safely. One effective method for path planning is the Rapidly-exploring Random Tree (RRT) algorithm, which is particularly practical in maze-like environments. The performance of RRT depends on the sampling methods used to explore the maze. Sampling methods are important because they determine how the algorithm explores the search space, affecting the efficiency and success of finding an optimal path. Poor sampling can lead to suboptimal or infeasible paths. In this study, we investigate different sampling strategies for RRT, specifically focusing on uniform sampling, Gaussian sampling, and the Motion Planning Network (MPNet) sampling. MPNet leverages a neural network trained on past environments, allowing it to predict promising regions of the search space quickly, unlike traditional methods like RRT that rely on random exploration without prior knowledge. This makes MPNet much faster and more efficient, especially in complex or high-dimensional spaces. Through a benchmarking analysis, we compare these methods in terms of their effectiveness in generating feasible paths. The results indicate that while all three methods are effective, MPNet sampling outperforms uniform and Gaussian sampling, particularly in terms of path length. The mean path length generated, based on a sample size of 30, is 13.115 meters for MPNet, which is shorter compared to uniform and Gaussian sampling, which are 18.27 meters and 18.088 meters, respectively. These findings highlight the potential to enhance path planning algorithms using learning-based sampling methods.

Optimalisasi Potensi Dusun Terbah Serut Kulon Progo melalui Media Digital Berbasis Website Karyono, Tri Hadi; Dhewa, Oktaf Agni; Baktiar, Faris Yusuf; Priambodo, Ardy Seto; Hakim, Septian Rahman
Jurnal Abdi Masyarakat Indonesia Vol 4 No 6 (2024): JAMSI - November 2024
Publisher : CV Firmos

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54082/jamsi.1434

Keterbatasan akses informasi di Dusun Terbah dan Serut menghambat promosi potensi lokal. Teknologi digital, seperti website, menawarkan solusi untuk memperluas akses informasi. Melalui website, masyarakat dapat dengan mudah mengakses dan menyebarkan informasi. Kegiatan pengabdian ini bertujuan membangun sistem informasi berbasis website dan melakukan transfer pengetahuan untuk pengelolaannya. Website ini diharapkan mampu menyajikan informasi kegiatan dusun serta mempromosikan potensi lokal secara cepat dan akurat. Teknologi yang digunakan adalah CMS Wordpress dengan MySQL sebagai basis data, dan website di-hosting agar dapat diakses kapan saja. Pengabdian ini mencakup dua aktivitas utama: pengembangan aplikasi selama tiga bulan dan pelatihan melalui empat kali workshop di kantor dusun. Hasilnya, website berhasil meningkatkan visibilitas potensi lokal serta keterlibatan masyarakat. Pelatihan berjalan lancar dan mendapat respons positif dari peserta, termasuk kepala dukuh dan pengelola, yang kini lebih sadar bahwa website bukan hanya alat informasi, tetapi juga media promosi. Kegiatan ini mendorong pengelola dusun untuk lebih aktif dalam mengelola dan mempromosikan potensi lokal.

Chicken Cage Incubator Cooling Control System Using Fuzzy Logic Agni Dhewa, Oktaf; Aldiasa Pangestu Aji
Media of Computer Science Vol. 1 No. 1 (2024): June 2024
Publisher : CV. Digital Innovation

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.69616/mcs.v1i1.177

This research examines the impact of prolonged cooling time in the incubator of chicken coops on the well-being of chicks during the incubation process. Poorly maintained temperature conditions can jeopardize the health of chicks and diminish the overall productivity of poultry farming. To address this issue, the study develops an efficient temperature control system by integrating a peltier as the main cooling component and fuzzy logic control combined with a DC fan. Experimental results indicate that the developed system is capable of providing a robust response to temperature changes in the chicken coop incubator, with transient response values meeting the expected criteria. Consequently, this temperature control system holds the potential to enhance the performance of chicken coop incubators and reduce the risk of chick mortality during the incubation process. This research serves as an initial step in advancing better temperature control for chicken coop incubators in the future.

Title

Found 11 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 11 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 11 Documents
Search