Agus Pratondo
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Agus Pratondo has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Aldia Deponsa Judistira
School of Applied Science, Telkom University, Indonesia
1 shared publication Anang Sularsa
School of Applied Science, Telkom University, Indonesia
1 shared publicationApriyanti Putri Sujana
School of Applied Science, Telkom University, Indonesia
1 shared publication- Astri Novianty
Department of Computer Engineering, School of Electrical Engineering, Telkom University, Bandung, West Jawa, Indonesia
1 shared publication Chee-Kong Chui
Department of Mechanical Engineering, National University of Singapore, Singapore
1 shared publication- Chee-Kong Chui
National University of Singapore
1 shared publication
Latest Publications
- 30 July 2024
- Published by Springer Nature
- p. 360-369
Detection of Paddy Plant Diseases Using Google Teachable Machine
- 30 July 2024
- Published by Springer Nature
- p. 360-369
Detection of Paddy Plant Diseases Using Google Teachable Machine
- Open Access
- 9 June 2023
- Published by Telkom University in IJAIT (International Journal of Applied Information Technology)
- p. 11-21
Augmented Reality with Speech Recognition for Animal Recognition Applications
The advance of educational technology is significantly changing and is very effective in supporting education nowadays. However, technology to support education in Indonesia is not maximal; one of the cases occurred in the PGRI Sumedang Kindergarten. Teachers at PGRI Sumedang Kindergarten have difficulties providing material that can build students’ interest, especially general knowledge about animals. This study aims to design Augmented Reality (AR) technology features with Speech Recognition for an Android-based interactive multimedia application of animal knowledge to assist learning activities in PGRI Sumedang Kindergarten. AR is a computer technology that combines virtual objects with the real world. This AR feature uses a card-shaped marker with an image and speech recognition as a medium for interaction with animals. Speech recognition is a computer technology to process human speech into digital letters or words. The resulting interaction is that if the user pronounces the animal’s name displayed in AR, the animal animation will move. This AR feature can help to learn activities at Kindergarten PGRI Sumedang.
- 9 June 2023
- Published by Telkom University in IJAIT (International Journal of Applied Information Technology)
- p. 11-21
Open AccessAugmented Reality with Speech Recognition for Animal Recognition Applications
The advance of educational technology is significantly changing and is very effective in supporting education nowadays. However, technology to support education in Indonesia is not maximal; one of the cases occurred in the PGRI Sumedang Kindergarten. Teachers at PGRI Sumedang Kindergarten have difficulties providing material that can build students’ interest, especially general knowledge about animals. This study aims to design Augmented Reality (AR) technology features with Speech Recognition for an Android-based interactive multimedia application of animal knowledge to assist learning activities in PGRI Sumedang Kindergarten. AR is a computer technology that combines virtual objects with the real world. This AR feature uses a card-shaped marker with an image and speech recognition as a medium for interaction with animals. Speech recognition is a computer technology to process human speech into digital letters or words. The resulting interaction is that if the user pronounces the animal’s name displayed in AR, the animal animation will move. This AR feature can help to learn activities at Kindergarten PGRI Sumedang.
- 23 August 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 108-112
Classification of Longan Edibility using Machine Learning
Longan fruit (Dimocarpus longan) originating from Southeast Asia, is a fruit that is commonly consumed in the region. The fruit is susceptible to damage during the distribution process. The selection of fruit that is suitable for consumption and that which is not is still made manually. This study aims to build a model using machine learning that can automatically classify longan edibility. Two classification algorithms are used, namely the k-nearest neighbor and the support vector machine. The model is trained with a number of images consisting of two classes, namely, fit (accepted) and unfit (rejected) to eat. The experimental results show that the algorithm's accuracy for k- nearest neighbors and the support vector machine are 93% and 98%, respectively. These results indicate that the classification of longan using machine learning is quite promising.
- 23 August 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 108-112
Classification of Longan Edibility using Machine Learning
Longan fruit (Dimocarpus longan) originating from Southeast Asia, is a fruit that is commonly consumed in the region. The fruit is susceptible to damage during the distribution process. The selection of fruit that is suitable for consumption and that which is not is still made manually. This study aims to build a model using machine learning that can automatically classify longan edibility. Two classification algorithms are used, namely the k-nearest neighbor and the support vector machine. The model is trained with a number of images consisting of two classes, namely, fit (accepted) and unfit (rejected) to eat. The experimental results show that the algorithm's accuracy for k- nearest neighbors and the support vector machine are 93% and 98%, respectively. These results indicate that the classification of longan using machine learning is quite promising.
- Open Access
- 7 July 2020
- Published by Telkom University in IJAIT (International Journal of Applied Information Technology)
- p. 96-105
Zetcil: Game Mechanic Framework for Unity Game Engine
Games are interactive multimedia products that require programming logic and graphic design capabilities in the development process. Game development using Unity Game Engine has become a primary subject in the Multimedia Engineering Technology study program, School of Applied Sciences, Telkom University. In the initial observation, it was found that more than 33% of students have difficulties in making a game using the C# language for Unity. The students understand the Game Design Pattern logic but having difficulty when applying it into programming codes. This research proposes Zetcil, a Game Mechanic Framework that simplifies the game development process for the Unity Game Engine. This framework turned most of the text-based programming commands into visual properties. Based on research for two years, it concluded that the Zetcil could increase 36% of student's confidence to develop games prototype rapidly.
- 7 July 2020
- Published by Telkom University in IJAIT (International Journal of Applied Information Technology)
- p. 96-105
Open AccessZetcil: Game Mechanic Framework for Unity Game Engine
Games are interactive multimedia products that require programming logic and graphic design capabilities in the development process. Game development using Unity Game Engine has become a primary subject in the Multimedia Engineering Technology study program, School of Applied Sciences, Telkom University. In the initial observation, it was found that more than 33% of students have difficulties in making a game using the C# language for Unity. The students understand the Game Design Pattern logic but having difficulty when applying it into programming codes. This research proposes Zetcil, a Game Mechanic Framework that simplifies the game development process for the Unity Game Engine. This framework turned most of the text-based programming commands into visual properties. Based on research for two years, it concluded that the Zetcil could increase 36% of student's confidence to develop games prototype rapidly.
- Open Access
- 11 December 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 23 (2) , 222-226
Robust Edge-Stop Functions for Edge-Based Active Contour Models in Medical Image Segmentation
Edge-based active contour models are effective in segmenting images with intensity inhomogeneity but often fail when applied to images containing poorly defined boundaries, such as in medical images. Traditional edge-stop functions (ESFs) utilize only gradient information, which fails to stop contour evolution at such boundaries because of the small gradient magnitudes. To address this problem, we propose a framework to construct a group of ESFs for edge-based active contour models to segment objects with poorly defined boundaries. In our framework, which incorporates gradient information as well as probability scores from a standard classifier, the ESF can be constructed from any classification algorithm and applied to any edge-based model using a level set method. Experiments on medical images using the distance regularized level set for edge-based active contour models as well as the k-nearest neighbours and the support vector machine confirm the effectiveness of the proposed approach.
- 11 December 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 23 (2) , 222-226
Open AccessRobust Edge-Stop Functions for Edge-Based Active Contour Models in Medical Image Segmentation
Edge-based active contour models are effective in segmenting images with intensity inhomogeneity but often fail when applied to images containing poorly defined boundaries, such as in medical images. Traditional edge-stop functions (ESFs) utilize only gradient information, which fails to stop contour evolution at such boundaries because of the small gradient magnitudes. To address this problem, we propose a framework to construct a group of ESFs for edge-based active contour models to segment objects with poorly defined boundaries. In our framework, which incorporates gradient information as well as probability scores from a standard classifier, the ESF can be constructed from any classification algorithm and applied to any edge-based model using a level set method. Experiments on medical images using the distance regularized level set for edge-based active contour models as well as the k-nearest neighbours and the support vector machine confirm the effectiveness of the proposed approach.
- 1 January 2014
- Published by Springer Nature
- p. 112-115
Region Growing for Medical Image Segmentation Using a Modified Multiple-seed Approach on a Multi-core CPU Computer
- 1 January 2014
- Published by Springer Nature
- p. 112-115
Region Growing for Medical Image Segmentation Using a Modified Multiple-seed Approach on a Multi-core CPU Computer
- 1 December 2010
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 188-190
Fuzzy Rule Base for Analytical Demand Forecasting Enhancement
Demand data can be viewed as a number series from time to time. The series may be a pattern that can be analyzed for the next demand prediction if the slice of time is constant. The demand series which the time slice is constant can forecast the next demand valued by applying a formula. There are many methods to forecast the next demand. All formulas calculate the next demand by using the fact of demand as a pure number series. The next demand value is derived from analytical process using mathematics equation, from the simplest way to the complex one. In fact, the demand is influenced by environment factor, for example social and politics exchange, disaster, and mode. The demand forecasting must be reevaluated by considering the environment factors. The environment factor usually has uncertainty value which is good using fuzzy value. That is why the best way to enhance the demand forecasting is calculation using fuzzy rule base.
- 1 December 2010
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 188-190
Fuzzy Rule Base for Analytical Demand Forecasting Enhancement
Demand data can be viewed as a number series from time to time. The series may be a pattern that can be analyzed for the next demand prediction if the slice of time is constant. The demand series which the time slice is constant can forecast the next demand valued by applying a formula. There are many methods to forecast the next demand. All formulas calculate the next demand by using the fact of demand as a pure number series. The next demand value is derived from analytical process using mathematics equation, from the simplest way to the complex one. In fact, the demand is influenced by environment factor, for example social and politics exchange, disaster, and mode. The demand forecasting must be reevaluated by considering the environment factors. The environment factor usually has uncertainty value which is good using fuzzy value. That is why the best way to enhance the demand forecasting is calculation using fuzzy rule base.