Papers by Yunyong Punsawad
IEEE Access
This research work is financially supported in part by Walailak University This work involved hum... more This research work is financially supported in part by Walailak University This work involved human subjects in its research. All ethical and experimental procedures and protocols were conducted according to the guidelines of the Declaration of Helsinki and approved by the Office of the Human Research Ethics Committee of Walailak University (protocol code: WU-EC-EN-2-140-64) ABSTRACT In the case of paralysis with visual and tactile impairments, brain-computer interfaces (BCIs) based on auditory and mental imagery paradigms are alternative methods for controlling external devices. This study demonstrates the use of a hybrid BCI via auditory stimulation and speech imagination for assistive technology. The proposed auditory BCI using Thai vowel and numeral stimulus patterns as well as multiloudspeaker position settings for multi-command BCI are investigated. To avoid auditory stimulation during resting periods, a speech imagery method is used to enable an audio stimulator. We observe the classification efficiency of speech imagery and auditory BCIs from selected electroencephalogram channels using the proposed algorithms. We examine the efficiency of using the proposed BCI in the presence of background noise (speech). One command is created using the proposed speech-imagination paradigm. Four commands are created using the proposed auditory stimulation paradigm. We design an experiment to verify the proposed BCI paradigm and classification algorithms for real-time processing. The results show that the average classification accuracy of the proposed auditory BCI using numeral stimuli and scatter patterns without speech noise is 72.2% to 83.3%, respectively. The efficiency under background noise is approximately two times lower than that without background noise.
Review for "A comfortable steady state visual evoked potential stimulation paradigm using peripheral vision
A multi-command SSVEP-based BCI system based on single flickering frequency half-field steady-state visual stimulation
Medical & Biological Engineering & Computing
Abstract Steady-state visual evoked potentials (SSVEPs) are widely employed in brain–computer int... more Abstract Steady-state visual evoked potentials (SSVEPs) are widely employed in brain–computer interface (BCI) applications, especially to control machines. However, the use of SSVEPs leads to eye fatigue and causes lower accuracy over the long term, particularly when multi-commands are required. Therefore, this paper proposes a half-field steady-state visual stimulation pattern and paradigm to increase the limited number of commands that can be achieved with existing SSVEP-based BCI methods. Following the theory of vision perception and existing half-field SSVEP-based BCI systems, the new stimulation pattern generates four commands using only one frequency flickering stimulus and has an average classification accuracy of approximately 75 %. According to the proposed stimulus pattern, using only one frequency without requiring users to stare directly at the flickering stimulus allows users to easily focus on the system and experience less visual fatigue compared to existing systems. Furthermore, new half-field SSVEP-based BCI systems are proposed, incorporating our proposed feature extraction and decision-making algorithm. Extracting the signal from the occipital area and using a reference electrode position at the parietal area yielded better results compared to the central area. In addition, we recommend using an LED or LCD as the visual stimulus device (at the recommended size), which yielded comparable results to our proposed feature extraction and decision-making algorithm. Finally, an application of the proposed system is demonstrated for real-time television control.
Enhancement of steady-state visual evoked potential-based brain-computer interface systems via a steady-state motion visual stimulus modality
IEEJ Transactions on Electrical and Electronic Engineering
Steady-state visual evoked potential (SSVEP)-based brain–computer interface (BCI) systems are amo... more Steady-state visual evoked potential (SSVEP)-based brain–computer interface (BCI) systems are among the most accurate assistive devices for patients with severe disabilities. However, existing visual stimulation patterns lead to eye fatigue, which affects the system performance. Therefore, in this study, we propose two improvements to SSVEP-based BCI systems. First, we propose a novel visual stimulator that incorporates a visual motion stimulus for the steady-state visual stimulus to reduce eye fatigue while maintaining the advantages associated with SSVEPs. We also propose two corresponding feature extraction algorithms, i.e. SSVEP detection and visual attention detection, to capture the phenomena of steady-state motion visual stimulus responses. The accuracy of the test was ∼83.6%. Second, we propose a novel hybrid BCI-SSVEP system and a motion visual stimulus hybrid BCI system to enhance the SSVEP-based BCI system during a state of eye fatigue. Participants used the SSVEP system until reaching a fatigued state and then began using a hybrid motion visual stimulus. The accuracy of the proposed system was ∼85.6%. The proposed improvements can be incorporated into practical BCI systems for wheelchair control. © 2017 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.
Multi-command SSAEP-based BCI system with training sessions for SSVEP during an eye fatigue state
IEEJ Transactions on Electrical and Electronic Engineering
Real-time hybrid SSSEP-MI based brain computer interface system for upper limb rehabilitation
Brain-computer interface (BCI) system is currently utilized to provide the neuro-rehabilitation e... more Brain-computer interface (BCI) system is currently utilized to provide the neuro-rehabilitation especially for the stroke, brain injury, and cerebral palsy patients. In this work, we develop the prototype of the hybrid BCI system that simultaneously employs both motor imagery (MI) potential and steady-state somatosensory evoked potential (SSSEP) for motor and sensation of upper limbs rehabilitation. The MI potential can be observed from the event-related desynchonization (ERD) pattern when the user imagines the right or left hand movement. For the SSSEP-based BCI system, we attach the tactile stimulator at specific frequency of 23 Hz on the palm. The classification accuracy of our SSSEP-based and MI-based neuro-rehabilitation systems are approximately 82.5% and 75.27%, respectively. By systematically employ both systems simultaneously in one device; the rehabilitation process can be enhanced.
Steady-state visual evoked potential (SSVEP)-based brain computer interface (BCI) device is one o... more Steady-state visual evoked potential (SSVEP)-based brain computer interface (BCI) device is one of the most accurate assistive technologies for the persons with severe disabilities. However, for the existing systems, the persons with disabilities still need the assistance for the long period of time as well as the continuous time usages. In order to minimize this problem, we propose the SSVEP-based BCI system that the persons with disabilities can enable/disable the BCI device by alpha band EEG and control the electrical devices by SSVEP. A single-channel EEG (O1 or O2) is employed. Power spectral density via periodogram at the four stimulated frequencies (6, 7, 8, and 13 Hz) and their harmonics are used as the features of interest. Simple threshold-based decision rule is applied to the selected features. With the minimal need for assistance, the classification accuracy of the proposed system ranged from 75 to 100%.
Mental fatigue is another major cause of the seri-ous car accidents. Ability to early predict the... more Mental fatigue is another major cause of the seri-ous car accidents. Ability to early predict the men-tal fatigue phenomenon is hence one of the chal-lenging problems in brain-computer interface (BCI). In this paper, we propose the practical EEG-based mental fatigue alarm system including the weighted-frequency index of the linear combination among EEG theta, alpha and beta rhythms. The proposed system is tested with the simulated driving situations. By using only 1-channel EEG at the temporal area of the brain, more than 90% of prediction accuracies are reported compared to the opinion scores of the users.
Signal and Information Processing Association Annual Summit and Conference (APSIPA), 2014 Asia-Pacific, 2014
This paper proposes three main contributions. First contribution is on a study of brain activity ... more This paper proposes three main contributions. First contribution is on a study of brain activity during creativity task by the use of electroencephalogram (EEG). Second contribution is on a simply creativity task in art. Lastly, an information intervention for creative thinking activation is proposed. Quantitative EEG (QEEG) and brain connectivity are analytical methods for studying a phenomenon of creativity. Delta, theta, alpha and beta bands are the indicators of the brain activity. Moreover, phase of EEG is also employed. Prefrontal area of the brain is observed. Parietal area is considered to associate with the cognition. For the results, we can identify the creativity improvement in right frontal (Fp2 and F8) brain locations. Coherence analysis also reveals an effect of the intervention. We hope that this paper is useful for the neurological and cognitive science. The neurofeedback training system for creative thinking enhancement is listed as our future work.
Signal and Information Processing Association Annual Summit and Conference (APSIPA), 2014 Asia-Pacific, 2014
This paper proposes the relationship between user performance and luminance of visual stimulator ... more This paper proposes the relationship between user performance and luminance of visual stimulator in steady state visual evoked potential (SSVEP) based brain computer interface BCI system. The luminance conditions that relate to the environment used to study an eye or visual fatigue. The highlight of the work is the level of eye fatigue detection model in real time by using electroencephalogram (EEG) and skin temperature (SKT). We would like to invent a protocol and guideline of SSVEP based BCI system design. The results present the model that a number of trials leads to a low efficiency of user performance of SSVEP based BCI system. Visual stimulator is also a factor of an occurring of eye fatigue. Clearly, SSVEP is easily activated by high luminance, but it can also rapidly activate eye fatigue. This paper is useful for designing and enhancing the SSVEP based BCI system.
On the Performance Comparison of Using Checkerboard and Flash Ball Visual Stimulators for SSVEP-based BCI system
IFMBE Proceedings, 2013
Searching for the visual stimulators that can reduce eye-fatigue and enhance the performance of t... more Searching for the visual stimulators that can reduce eye-fatigue and enhance the performance of the steady state visual evoked potential (SSVEP)-based brain computer interface (BCI) system is one of the challenging problem in BCI research. In this paper, we compare the multi-command selection performance of the two visual stimulators, i.e. the proposed flash ball and the conventional checkerboard patterns, on the liquid crystal display (LCD) screen. Each visual stimulator consists of 12 commands with different flickering frequencies. These visual stimulators are evaluated with four subjects. Fast Fourier transform FFT is used to simply extract the features of interest. The results show that, by employing the flash ball pattern, the average accuracy is 76.67% which is higher than 60% accuracy of the checkerboard pattern.
On the Development of Using the Non-Invasive Blood Oxygen Level Sensor for Quantifying Hemoglobin Concentration
IFMBE Proceedings, 2013
In this paper, we propose the non-invasive method for detecting hemoglobin concentration. Our hyp... more In this paper, we propose the non-invasive method for detecting hemoglobin concentration. Our hypothesis is that, for the patients who have high hemoglobin concentration, the average pulse amplitudes should be different from their normal condition. To verify our assumption, we diluted the blood of normal subjects by letting them drink the water. According to our experiment, 80% of the subjects had higher pulse amplitude.
On the enhancement of training session performance via attention for single-frequency/multi-commands based steady state auditory evoked potential BCI
2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2012
To solve the eye fatigue problem on using the well known steady state visual evoked potential (SS... more To solve the eye fatigue problem on using the well known steady state visual evoked potential (SSVEP)-based brain-computer interface (BCI) system, the steady state auditory evoked potential (SSAEP) becomes one of the promising BCI modalities. However, SSAEP-based BCI system still suffers from the low accuracy. To increase the accuracy, in this paper, we propose the new training method to enhance the SSAEP training session. The training process is enhanced by making the users control their attention levels simultaneously with the detected auditory stimulus frequency. Furthermore, with the proposed training method, we also propose the corresponding single-frequency/multi-commands BCI paradigm. With the proposed paradigm, four commands can be detected by using only one auditory stimulus frequency. The proposed training system yields approximately 81% accuracy compared with 66% of the session without performing the proposed training.
Hybrid SSVEP-motion visual stimulus based BCI system for intelligent wheelchair
2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 2013
This paper proposes the hybrid BCI modalities for wheelchair control by taking into account weakn... more This paper proposes the hybrid BCI modalities for wheelchair control by taking into account weakness of the current BCI systems. The idea is to combine two hybrid BCI systems with the intelligent wheelchair for three states, i.e. normal, fatigue, and emergency states. First system is the hybrid steady state visual evoked potential (SSVEP) and alpha rhythm BCI which is designed to use in the normal state. Second system is the hybrid motion visual stimulus and alpha rhythm which can be employed during the fatigue state (after using the first system). For the experiment, subjects are asked to perform SSVEP system for 30 minutes (until the fatigue states occur). Then, the subjects will be asked to perform the hybrid motion visual stimulus and alpha rhythm testing. The accuracy of the proposed system during fatigue state is approximately 85.62%. With this idea, BCI controlled wheelchair can be efficiently employed in reality.
2013 7th International Symposium on Medical Information and Communication Technology (ISMICT), 2013
People who lost their limbs by injury or congenital missing need prosthesis to replace the missin... more People who lost their limbs by injury or congenital missing need prosthesis to replace the missing body part to assist or enhance the motor ability or for cosmetic purpose. In this paper, brain-computer interface (BCI) technology is proposed to assist the person with disability who has no arm. The proposed system includes two BCI algorithms, i.e. ERD/ERS algorithm and hybrid EEG-EOG algorithm. The designed assistive robot arm is light weight, low power consumption, user friendly and pleasing aesthetic. The ERD/ERS algorithm can achieve the accuracy of approximately 66% with 3 commands. Moreover, the accuracy of the hybrid EEG-EOG algorithm yields nearly 96%.
Hybrid EEG-EOG brain-computer interface system for practical machine control
2010 Annual International Conference of the IEEE Engineering in Medicine and Biology, 2010
Practical issues such as accuracy with various subjects, number of sensors, and time for training... more Practical issues such as accuracy with various subjects, number of sensors, and time for training are important problems of existing brain-computer interface (BCI) systems. In this paper, we propose a hybrid framework for the BCI system that can make machine control more practical. The electrooculogram (EOG) is employed to control the machine in the left and right directions while the electroencephalogram (EEG) is employed to control the forword, no action, and complete stop motions of the machine. By using only 2-channel biosignals, the average classification accuracy of more than 95% can be achieved.
Motion visual stimulus for SSVEP-based BCI system
2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2012
Steady-state visual evoked potential (SSVEP)- based brain-computer interface (BCI) system is one ... more Steady-state visual evoked potential (SSVEP)- based brain-computer interface (BCI) system is one of the most accurate assistive technologies for the persons with severe disabilities. However, the existing visual stimulation patterns still lead to the eyes fatigue. Therefore, in this paper, we propose a novel visual stimulator using the idea of the motion visual stimulus to reduce the eyes fatigue while maintaining the merit of the SSVEP phenomena. Two corresponding feature extractions, i.e. 1) attention detection and 2) SSVEP detection, are also proposed to capture the phenomena of the proposed motion visual stimulus. Two-class classification accuracy of both features is approximately 80%, where the maximum accuracy using the attention detection is 90%, and the maximum accuracy using the SSVEP detection is 100%.
The 5th 2012 Biomedical Engineering International Conference, 2012
This paper proposes an investigation on classification of the positive and negative emotions via ... more This paper proposes an investigation on classification of the positive and negative emotions via the use of electroencephalogram (EEG). EEG bandpowers are extracted as the feature of interest. Two simple decision rules to classify positive and negative emotions are proposed, i.e. 1) using both the left and right frontal information and 2) using only one side of the left or right frontal information. First decision reports low accuracy while the second decision rule can achieve higher accuracy between 80 to 90%. This can be concluded that the proposed method is possible for the realtime emotion classification in neuroeconomics.
2011 IEEE International Conference on Robotics and Biomimetics, 2011
In this paper, the utilization of Zigbee as wireless sensor network (WSN) for medical application... more In this paper, the utilization of Zigbee as wireless sensor network (WSN) for medical application is demonstrated. The combination of various topologies is used to configure wireless sensors network to achieve high efficiency network architecture in medicine. The network consists of center coordinator, routers and sensor nodes. Mesh network is used for the connection between coordinator and router for range expansion. A performance of the proposed modality is tested in the normal situation. Besides, the architecture of the smart room systems is also proposed for healthcare monitoring. Physiological data and signal are transmitted using Xbee which is a wireless device operated in unlicensed radio frequency bands. OWADAYS, healthcare technology is dramatically developed since there are many modern treatments and therapeutic techniques, medical device, and medical appliance. Seeking for technologies that can enhance the ability of the healthcare system for reducing human error, simplifying the treatment process as well as improving the quality of life for nurses and doctors is the challenging problems. Monitoring system is one of the essential systems in medicine that can help doctor diagnose and predict a symptom before making a plan for treatment. Furthermore, monitoring system can be set to alarm when patient has abnormal behavior, e.g. in the intensive care unit (ICU) and patient who needs special observation. In present, nurse usually goes to check a physiological data of patient such as temperature, heart rate or electrocardiography (ECG) [1-2], blood pressure (BP), oxygen saturation together with a drip and other devices. All of this is performed by following a schedule. For this existing system, there are many problems such as in case of many patients, nurses have an overload work and might yield some human error on losing the physiological data that are important for treatment.
2008 IEEE International Conference on Robotics and Biomimetics, 2009
This paper proposes the use of the phase congruency to enhance the palmprint image used for palmp... more This paper proposes the use of the phase congruency to enhance the palmprint image used for palmprint identification. By using phase congruency, the palmprint lines which act like the edges in the palmprint image are detected. The resulting phase image is shown as the enhanced palmprint image. Comparing with the previous palmprint enhancement method that uses the phase symmetry proposed by Kovesi et al. (1997), the proposed method is significantly less sensitive to the textures which are not the palmprint lines in the palmprint image.
Uploads
Papers by Yunyong Punsawad