Poonpong Boonbrahm
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Poonpong Boonbrahm has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
Charlee Kaewrat
4 shared publicationsSalin Boonbrahm
4 shared publications- Charlee Kaewrat
Informatics Innovation Center of Excellence (IICE), School of Informatics, Walailak University, Nakhon Si Thammarat 80160, Thailand
2 shared publications - Lanjakorn Sewata
Walailak University
1 shared publication Lanjkorn Sewata
School of Informatics, Walailak University, Nakorn si Thammarat, Thailand 80161
1 shared publication- Patiwat Katelertprasert
School of Informatics, Walailak University, Nakhon Si Thammarat 80160, Thailand
1 shared publication
Latest Publications
- Open Access
- 1 January 2021
- Published by Walter de Gruyter GmbH in International Journal on Smart Sensing and Intelligent Systems
- Vol. 14 (1) , 1-10
A face-machine interface utilizing EEG artifacts from a neuroheadset for simulated wheelchair control
Many people suffer from movement disabilities and would benefit from an assistive mobility device with practical control. This paper demonstrates a face-machine interface system that uses motion artifacts from electroencephalogram (EEG) signals for mobility enhancement in people with quadriplegia. We employed an Emotiv EPOC X neuroheadset to acquire EEG signals. With the proposed system, we verified the preprocessing approach, feature extraction algorithms, and control modalities. Incorporating eye winks and jaw movements, an average accuracy of 96.9% across four commands was achieved. Moreover, the online control results of a simulated power wheelchair showed high efficiency based on the time condition. The combination of winking and jaw chewing results in a steering time on the same order of magnitude as that of joystick-based control, but still about twice as long. We will further improve the efficiency and implement the proposed face-machine interface system for a real-power wheelchair.
- 1 January 2021
- Published by Walter de Gruyter GmbH in International Journal on Smart Sensing and Intelligent Systems
- Vol. 14 (1) , 1-10
Open AccessA face-machine interface utilizing EEG artifacts from a neuroheadset for simulated wheelchair control
Many people suffer from movement disabilities and would benefit from an assistive mobility device with practical control. This paper demonstrates a face-machine interface system that uses motion artifacts from electroencephalogram (EEG) signals for mobility enhancement in people with quadriplegia. We employed an Emotiv EPOC X neuroheadset to acquire EEG signals. With the proposed system, we verified the preprocessing approach, feature extraction algorithms, and control modalities. Incorporating eye winks and jaw movements, an average accuracy of 96.9% across four commands was achieved. Moreover, the online control results of a simulated power wheelchair showed high efficiency based on the time condition. The combination of winking and jaw chewing results in a steering time on the same order of magnitude as that of joystick-based control, but still about twice as long. We will further improve the efficiency and implement the proposed face-machine interface system for a real-power wheelchair.
- Open Access
- 1 December 2019
- Published by Insight Society in International Journal on Advanced Science, Engineering and Information Technology
- Vol. 9 (6) , 2193-2200
Identify the Object’s Shape using Augmented Reality Marker-based Technique.
Identify the Object’s Shape using Augmented Reality Marker-based Technique.
- 1 December 2019
- Published by Insight Society in International Journal on Advanced Science, Engineering and Information Technology
- Vol. 9 (6) , 2193-2200
Open AccessIdentify the Object’s Shape using Augmented Reality Marker-based Technique.
Identify the Object’s Shape using Augmented Reality Marker-based Technique.
- Open Access
- 27 November 2019
- Published by International Journal of Technology in International Journal of Technology
- Vol. 10 (7) , 1326-1334
Interactive Marker-based Augmented Reality for CPR Training
CPR, or Cardiopulmonary Resuscitation, is a lifesaving technique useful for the case in which someone’s heartbeat or breathing has stopped due to heart attack. Without proper CPR, nine out of ten patients die. The American Heart Association recommends CPR with chest compressions in the event of witnessing such an incident. For proper CPR training, taking a class with a CPR instructor is usually the best choice, but it is not practical and costly for mass training, especially in schools and universities. There are many new techniques available that can replace traditional CPR training and Augmented Reality (AR) is one of them. AR is the technology that integrates virtual objects or environments, created by digital technology, with the real world. Augmented Reality using marker-based technique is a good option, since a trainee can have a realistic look at the patient, know the position of the hand on the chest, identify the number of chest compressions per minute, and also know the pressure that he or she puts on the chest. Besides that, the status of the operation can be displayed along with a recording system for analysis. In this research, we chose marker-based AR due to its precision in distance measurement. For measuring the pressure on the chest, we use a marker-marker interaction technique. Unity 3D cross-platform game engine and Qualcomm's Vuforia—an augmented reality software development kit (SDK) for mobile devices that enables the creation of augmented reality applications—are required. The results from our experiment with a group of people with non-CPR training confirm that the configuration increases the speed and accuracy of CPR training.
- 27 November 2019
- Published by International Journal of Technology in International Journal of Technology
- Vol. 10 (7) , 1326-1334
Open AccessInteractive Marker-based Augmented Reality for CPR Training
CPR, or Cardiopulmonary Resuscitation, is a lifesaving technique useful for the case in which someone’s heartbeat or breathing has stopped due to heart attack. Without proper CPR, nine out of ten patients die. The American Heart Association recommends CPR with chest compressions in the event of witnessing such an incident. For proper CPR training, taking a class with a CPR instructor is usually the best choice, but it is not practical and costly for mass training, especially in schools and universities. There are many new techniques available that can replace traditional CPR training and Augmented Reality (AR) is one of them. AR is the technology that integrates virtual objects or environments, created by digital technology, with the real world. Augmented Reality using marker-based technique is a good option, since a trainee can have a realistic look at the patient, know the position of the hand on the chest, identify the number of chest compressions per minute, and also know the pressure that he or she puts on the chest. Besides that, the status of the operation can be displayed along with a recording system for analysis. In this research, we chose marker-based AR due to its precision in distance measurement. For measuring the pressure on the chest, we use a marker-marker interaction technique. Unity 3D cross-platform game engine and Qualcomm's Vuforia—an augmented reality software development kit (SDK) for mobile devices that enables the creation of augmented reality applications—are required. The results from our experiment with a group of people with non-CPR training confirm that the configuration increases the speed and accuracy of CPR training.
- Open Access
- 1 February 2019
- Published by Omnia Publisher SL in Journal of Technology and Science Education
- Vol. 9 (1) , 20-31
Game elements from literature review of gamification in healthcare context
Gamification is a conceptual framework to apply game elements and techniques to improve the interesting process in non-game context. Gamification offers the motivation approach to motivate the player to handle the challenge tasks with game mechanics, game dynamics, and components. Nowadays, To discover the set of game elements and techniques from evaluating the existing related research is more opportunity for success in the exciting process. The core objective of this paper is to review the literature by using descriptive statistics of game elements with the review methodology and evaluate the model with multi-label classification with a dataset from this literature examined. The reviewed literature was first coded author-centrally. After each paper was scrutinized for the analysis, the perspective was pivoted, and further analyses were conducted concept-centrally. A systematic review has been conducted that proves the wide variety of game elements, being retrieved a total of fifteen terms of game elements from twenty-two selected papers that were screened from a total of eighty-two documents. Only a few terms are used: points, feedback, levels, leaderboards, challenges, badges, avatars, competition, and cooperation. However, only some can be considered actual elements mechanics and that have not a similar abstraction level. Additionally, the authors examined the relationship between game elements and STD: Competence, Autonomy, and Relatedness with a Data mining technique, Multi-label classification to discovery knowledge of game elements. The results indicated that rFerns algorithm provides the lowest Hamming Loss with 4.17%. Furthermore, It shows that Multi-label Rain Forest (rfsrc) in Algorithm adaptation method and Rain Forest (RF) in Problem transformation method provide the same Hamming Loss with 29.17%. Moreover, rFerns algorithm provides the highest accuracy with 87.5% for Competence, and 100% for Autonomy and Relatedness. Furthermore, It shows that Multi-label Rain Forest (rfsrc) in Algorithm adaptation method and Rain Forest (RF) in Problem transformation method provide the same Accuracy with 87.5% for Competence, and 62.5% for Autonomy and Relatedness. The results from this study will be used to design a gamified system in a healthcare context to promote physical activity.
- 1 February 2019
- Published by Omnia Publisher SL in Journal of Technology and Science Education
- Vol. 9 (1) , 20-31
Open AccessGame elements from literature review of gamification in healthcare context
Gamification is a conceptual framework to apply game elements and techniques to improve the interesting process in non-game context. Gamification offers the motivation approach to motivate the player to handle the challenge tasks with game mechanics, game dynamics, and components. Nowadays, To discover the set of game elements and techniques from evaluating the existing related research is more opportunity for success in the exciting process. The core objective of this paper is to review the literature by using descriptive statistics of game elements with the review methodology and evaluate the model with multi-label classification with a dataset from this literature examined. The reviewed literature was first coded author-centrally. After each paper was scrutinized for the analysis, the perspective was pivoted, and further analyses were conducted concept-centrally. A systematic review has been conducted that proves the wide variety of game elements, being retrieved a total of fifteen terms of game elements from twenty-two selected papers that were screened from a total of eighty-two documents. Only a few terms are used: points, feedback, levels, leaderboards, challenges, badges, avatars, competition, and cooperation. However, only some can be considered actual elements mechanics and that have not a similar abstraction level. Additionally, the authors examined the relationship between game elements and STD: Competence, Autonomy, and Relatedness with a Data mining technique, Multi-label classification to discovery knowledge of game elements. The results indicated that rFerns algorithm provides the lowest Hamming Loss with 4.17%. Furthermore, It shows that Multi-label Rain Forest (rfsrc) in Algorithm adaptation method and Rain Forest (RF) in Problem transformation method provide the same Hamming Loss with 29.17%. Moreover, rFerns algorithm provides the highest accuracy with 87.5% for Competence, and 100% for Autonomy and Relatedness. Furthermore, It shows that Multi-label Rain Forest (rfsrc) in Algorithm adaptation method and Rain Forest (RF) in Problem transformation method provide the same Accuracy with 87.5% for Competence, and 62.5% for Autonomy and Relatedness. The results from this study will be used to design a gamified system in a healthcare context to promote physical activity.
- Open Access
- 8 November 2018
- Published by International Association of Online Engineering (IAOE) in International Journal of Interactive Mobile Technologies (iJIM)
- Vol. 12 (7) , 181-190
Study of the Hand Anatomy Using Real Hand and Augmented Reality
Anatomy is considered one of the foundation studies for all of the health science students especially medical and nursing students. Anatomy of the hand is complicated. It composes of bones, nerves, blood veins, muscles, and tendon. Memorising all the details about all those parts is tedious work and need much imagination. With the advances in computer graphics and human-computer interaction techniques, understanding how those body parts move is easy to understand in a visual presentation. Augmented Reality (AR) is the technique that allowed the computer-generated objects to overlay on top of the real world. In this study, we concentrate on studying the bones only. We have selected the Leap Motion, which is the device that can detect the hands and fingers, like a tracking device, and marker-based AR technique for displaying the computer generated bones on top of the real hand. Since the Leap Motion detects the hands and shows the bone in real time, so when a user moves the hands such as waving, all the 3D virtual bones move to the new position just like the real hand. Besides using this tool as the educational tool to help the students have better learning about anatomy, it can also be used as an assessment tool for anatomy class as well. Results from testing this tool with volunteer students indicate that it helps them to understand the hand anatomy better and faster than traditional ways.
- 8 November 2018
- Published by International Association of Online Engineering (IAOE) in International Journal of Interactive Mobile Technologies (iJIM)
- Vol. 12 (7) , 181-190
Open AccessStudy of the Hand Anatomy Using Real Hand and Augmented Reality
Anatomy is considered one of the foundation studies for all of the health science students especially medical and nursing students. Anatomy of the hand is complicated. It composes of bones, nerves, blood veins, muscles, and tendon. Memorising all the details about all those parts is tedious work and need much imagination. With the advances in computer graphics and human-computer interaction techniques, understanding how those body parts move is easy to understand in a visual presentation. Augmented Reality (AR) is the technique that allowed the computer-generated objects to overlay on top of the real world. In this study, we concentrate on studying the bones only. We have selected the Leap Motion, which is the device that can detect the hands and fingers, like a tracking device, and marker-based AR technique for displaying the computer generated bones on top of the real hand. Since the Leap Motion detects the hands and shows the bone in real time, so when a user moves the hands such as waving, all the 3D virtual bones move to the new position just like the real hand. Besides using this tool as the educational tool to help the students have better learning about anatomy, it can also be used as an assessment tool for anatomy class as well. Results from testing this tool with volunteer students indicate that it helps them to understand the hand anatomy better and faster than traditional ways.
- 27 September 2018
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 2016 (1) , 020102
Using ensemble algorithms for physical activity recognition prediction
This experiment examined the physical activity recognition model to access the relationship between sensors, the single tri-axial accelerometer and single tri-axial gyroscope, and fitness recognition (sitting, standing, walking, and running). We experimented with sixteen students (62.5% male and 37.5% female, age between eighteen through twenty- three year old) of the Informatics school at Walailak University. We had the experimental setup to evaluate model performance for baseline models, booting ensemble model, and begging ensemble model. When we measured model’s performance, we found the follows results. First, the baseline models performance has the highest accuracy level with KNN: k-Nearest Neighbor with k = 9 is 95.47%. Second, The Boosting ensemble models performance has the highest accuracy level with C5.0: C5.0 is 95.63%. Third, The Bagging ensemble models performance has the highest accuracy level with RF: Random Forest is 95.69%. Fourth, The Stacking ensemble models performance has the highest accuracy level with KNN is 95.52%. So, we concluded that RF has the highest performance with accuracy level at 95.69%. In the future work, we planned to get more accuracy model by adding more features from another sensor, heart rate. Mining data collected from sensors provide valuable result in the physical activity recognition area. The improvement in performance is required especially in the healthcare field. The more increasing of using the wearable device, the broader opportunity in the data mining research area can be.
- 27 September 2018
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 2016 (1) , 020102
Using ensemble algorithms for physical activity recognition prediction
This experiment examined the physical activity recognition model to access the relationship between sensors, the single tri-axial accelerometer and single tri-axial gyroscope, and fitness recognition (sitting, standing, walking, and running). We experimented with sixteen students (62.5% male and 37.5% female, age between eighteen through twenty- three year old) of the Informatics school at Walailak University. We had the experimental setup to evaluate model performance for baseline models, booting ensemble model, and begging ensemble model. When we measured model’s performance, we found the follows results. First, the baseline models performance has the highest accuracy level with KNN: k-Nearest Neighbor with k = 9 is 95.47%. Second, The Boosting ensemble models performance has the highest accuracy level with C5.0: C5.0 is 95.63%. Third, The Bagging ensemble models performance has the highest accuracy level with RF: Random Forest is 95.69%. Fourth, The Stacking ensemble models performance has the highest accuracy level with KNN is 95.52%. So, we concluded that RF has the highest performance with accuracy level at 95.69%. In the future work, we planned to get more accuracy model by adding more features from another sensor, heart rate. Mining data collected from sensors provide valuable result in the physical activity recognition area. The improvement in performance is required especially in the healthcare field. The more increasing of using the wearable device, the broader opportunity in the data mining research area can be.
- 17 May 2017
- Published by Springer Nature
- p. 3-11
Using Augmented Reality Interactive System to Support Digital Electronics Learning
- 17 May 2017
- Published by Springer Nature
- p. 3-11
Using Augmented Reality Interactive System to Support Digital Electronics Learning
- 21 July 2015
- Published by Springer Nature
- p. 162-171
3D Real Time Virtual Fitting Room for Women
- Open Access
- 1 January 2015
- Published by Elsevier in Procedia Computer Science
- Vol. 75, 28-33
Transforming 2D Human Data into 3D Model for Augmented Reality Applications
- 1 January 2015
- Published by Elsevier in Procedia Computer Science
- Vol. 75, 28-33
Open AccessTransforming 2D Human Data into 3D Model for Augmented Reality Applications
- 1 January 2015
- Published by Springer Nature
- p. 24-32
Using Augmented Reality Technology in Assisting English Learning for Primary School Students
- 1 January 2015
- Published by Springer Nature
- p. 24-32
Using Augmented Reality Technology in Assisting English Learning for Primary School Students