Teerawat Kamnardsiri | Chiang Mai University (original) (raw)

Conference Presentations by Teerawat Kamnardsiri

Electronic Journal of e-Learning, 2017

This paper investigated students’ achievement for learning American Sign Language (ASL), using tw... more This paper investigated students’ achievement for learning American Sign Language (ASL), using two different methods. There were two groups of samples. The first experimental group (Group A) was the game-based learning for ASL, using Kinect. The second control learning group (Group B) was the traditional face-to-face learning method, generally used in sign language skill training for students with hearing impairments. This study was separated into two phases. In Phase I: 3D trajectory matching measurement algorithm, the Euclidean distance algorithm was employed to present the similarity between teacher and student datasets. Then, Phase II: Effectiveness of the Game-Based Learning system, showed the proposed framework of the game-based learning for sign language. Moreover, knowledge of sign language together with the corresponding actions were captured from three sign language experts using the knowledge engineering method. Then, the proposed game-based system would be analysed to provide students immediate feedbacks and suggestions based on the knowledge transfer from ASL experts. In the experiment, the students (N=31) were divided into two groups. The first group, Group A (N=17), learnt with the game-based learning while the second group, Group B (N=14), learnt with the traditional face to face learning method. The study result showed a significant difference (p<0.05) on the mean score of the post-tests for both Group A and Group B. It also presented that the game-based learning approach provided a better performance of ASL vocabularies than the traditional face-to-face learning approach. Finally, in the section of Discussion and Conclusion, the effectiveness and the future work opportunity of the proposed game-based learning system were discussed for the improvement of sign language actions.

Sign Language (SL) is not a universal language, but diverse sign languages have been used in seve... more Sign Language (SL) is not a universal language, but diverse sign languages have been used in several countries, such as the UK, the US and Thailand. Sign Language is a visual language for communication between people with hearing impairment in everyday life. Nonetheless, standard sign language experts are rare and there is a lack of experts in the specification of standard sign languages. In this paper, we present the development of an intelligent game-based system for learning sign language with Kinect aiming at the practice of sign language for students with hearing impairment. The game-based learning provided learning activities that could suggest students to achieve an end goal. Moreover, knowledge capturing was employed by the knowledge engineering method from three sign language experts, as well as an action of sign language. After further analysis, immediate feedback and suggestions based on knowledge transfer from American Sign Language (ALS) experts were given. This experimental divided the students (N=31) into two groups. Group A (N=17) learnt with game-based learning while Group B (N=14) learnt with traditional face to face learning. As a result, this study provided a significant difference (p<0.05) on the mean score of the post-test of both Group A as well as Group B. The final result showed that the game-based learning approach provides a performance of ASL vocabularies higher than the traditional face to face learning approach.

Sign language is a visual language for communication among the deaf people around the world in ev... more Sign language is a visual language for communication among the deaf people around the world in everyday life. Sign language, however, is not a universal language but different sign languages have been used in many countries, for instance, there are several sign languages in the UK, the USA and Thailand. A sign language comprises two types; signs and finger-spellings. Signs are gestures of continuous hand motion as well as hand configurations, on the other hand, finger-spellings are a mixture of continuous hand configurations. Nevertheless, there is a lack of expertise in a specification of standard sign languages. In this paper, we present a framework of intelligent game-based learning using Kinect that aims at training sign language for the hearing-impaired students or deaf students. Game-based learning is not merely a constructive game for students to play but it provides activities to learn that can guide students to achieve an end goal. Besides, the game-based learning also supports the sign language teachers for sign language improvement to their students. Kinect is a composite device of an IR projector and an IR camera. Kinect delivers three outputs as IR image, RGB image and Depth image. The knowledge engineering method is used to capture knowledge from sign language experts. The idea is to capture an action of sign language, then analyse and give them immediate feedback and suggestion based on knowledge transfer from American Sign Language (ASL) experts. Additionally, the game-based learning is to facilitate positive student experience in order to maximise the impact of educational game.

Currently, corroborative tourist recommendation system is gaining its popularity with the social ... more Currently, corroborative tourist recommendation system is gaining its popularity with the social network era. The tourist knowledge (i.e., attractions) is mainly built deductively from information sharing. The drawback is that the system will take time to reach its maturity stage, also the accuracy is depending on the user background. For example, the recommendation will be useful if information sharer and information taker has similar background. This paper is aiming at proposing the domain centric tourist recommendation system. The concept is to build the system inductively starting from the atomic searching criteria. The paper deploys knowledge management tools such as typology, and ontology study to analyse tourist and tourism information. The paper also discuss the case study area Chiang Mai province, the north of Thailand.

The long jump is one of the standard events in modern Olympic Games. It is a part of track and fi... more The long jump is one of the standard events in modern Olympic Games. It is a part of track and field. The long jump comprises of four phases: Approach run phase, Takeoff phase, Flight phase and Landing phase. Each phase effects to construct the flight distance. If athletes execute right actions in each phase, it will increase their performance. Athletes need some coaches or experts to provide them suggestions. Nonetheless, there is a lack of experts in this field. In this paper, we demonstrate a new framework of a knowledge-based system for training long jumpers in order to support trainers or coaches in practising and monitoring the long jumping movement. The idea is to combine the knowledge engineering methods with computer vision techniques for constructing the expert system. The system will be able to capture movements of the long jump athletes in each phase, analyse and give the recommendation based on knowledge captured from experts.

—This paper presents the watermarking technique in order to protect copyright of Digital Art Imag... more —This paper presents the watermarking technique in order to protect copyright of Digital Art Images. The algorithm is based on combination method of Discrete Wavelet Transform (DWT) and Discrete Cosine Transform (DCT) for embedding. The embedding watermarking technique employs one level of decomposition of DWT coefficients at HL 1 sub band. After that, divides HL 1 sub band image to 8 × 8, blocks then operates DCT and inserts watermark into the middle frequency coefficients. In order to enhance the robustness of watermark from the compression attack such as JPEG standard compression, the standard JPEG quantization table is used in this proposed algorithm. The experimental results consist of two similarity measurements are imperceptibility and robustness. Perceptual quality results indicate that the maximum PSNR value is 37.1858(db) and NC value is 1.000. The average of PSNR value is 36.8852(db), Standard Deviation(SD) is 0.19347 and Confidence Level (95.0%) is 0.2402. The average of NC, moreover, is 0.9997, Standard Deviation(SD) is 0.0003 and Confidence Level (95%) is 0.0004. Besides, robustness evaluation results reveal that the proposed watermarking technique is able to construct good quality of watermarked image and also stronger robustness from degradation and distortion such as Compression (JPEG and JPEG 2000), Noise(Salt-and-Paper noise, Gaussian noise, Speckle noise, Filter (3 × 3) noise and Adjust contrast noise) and Cropping attacking.

Papers by Teerawat Kamnardsiri

PLOS ONE, Jan 18, 2024

Early signs of Mild Cognitive Impairment (MCI)-related gait deficits may be detected through the ... more Early signs of Mild Cognitive Impairment (MCI)-related gait deficits may be detected through the performance of complex walking tasks that require high gait control. Gait smoothness is a robust metric of overall body stability during walking. This study aimed to explore gait smoothness during complex walking tasks in older adults with and without MCI. Participants were 18 older adults with MCI (mean age = 67.89 ± 4.64 years) and 18 cognitively intact controls (mean age = 67.72 ± 4.63 years). Gait assessment was conducted under four complex walking tasks: walking a narrow path, walking around an obstacle, horizontal head turns while walking, and vertical head turns while walking. The index of harmonicity (IH), representing gait smoothness associated with overall body stability, was measured in anteroposterior, mediolateral, and vertical directions. A multivariate analysis was employed to compare the differences in IH between groups for each complex walking task. The MCI group demonstrated a reduction of IH in the mediolateral direction during the horizontal head turns than the control group (MCI group = 0.64 ± 0.16, Control group = 0.74 ± 0.12, p = 0.04). No significant differences between groups were found for the IH in other directions or walking conditions. These preliminary findings indicate that older adults with MCI have a decline in step regularity in the mediolateral direction during walking with horizontal head turns. Assessment of the smoothness of walking during head turns may be a useful approach to identifying subtle gait alterations in older adults with MCI, which may facilitate timely gait intervention.

This study aimed to propose the method of implementation of the Knowledge-Based System (KBS) in t... more This study aimed to propose the method of implementation of the Knowledge-Based System (KBS) in the case of approach-run phase. The proposed method was implemented for improving the long jump performance of athletes in the approach-run phase. Moreover, this study aimed to examine KBS concurrent validity in distinguishing between professional and amateur populations and then KBS convergent validity against a Tracker video analysis tool. Seven running professionals aged 19 to 42 years and five amateurs aged 18 to 38 years had captured with ten conditions of different movements (C1 to C10) using a standard video camera (60 fps, 10 mm lens). The camera was fixed on the tripod. The results showing an age-related difference in a speed measurement of ten conditions were evidently using the KBS. Good associations were found between KBS and Tracker 4.94 video analysis tool across various conditions of three variables that were the starting position (r=0.926 and 0.963), the maximum velocity (r=0.972 and 0.995) and the location of maximum velocity (r=0.574 and 0.919). In conclusion, the proposed method is a reliable tool for measuring the starting position, maximum speed and position of maximum speed. Furthermore, the proposed method can also distinguish speed performance between professional and amateur across multiple movement conditions.

Electronic Journal of e-Learning, Aug 1, 2017

This paper investigated students' achievement for learning American Sign Language (ASL), using tw... more This paper investigated students' achievement for learning American Sign Language (ASL), using two different methods. There were two groups of samples. The first experimental group (Group A) was the game-based learning for ASL, using Kinect. The second control learning group (Group B) was the traditional face-to-face learning method, generally used in sign language skill training for students with hearing impairments. This study was separated into two phases. In Phase I: 3D trajectory matching measurement algorithm, the Euclidean distance algorithm was employed to present the similarity between teacher and student datasets. Then, Phase II: Effectiveness of the Game-Based Learning system, showed the proposed framework of the game-based learning for sign language. Moreover, knowledge of sign language together with the corresponding actions were captured from three sign language experts using the knowledge engineering method. Then, the proposed game-based system would be analysed to provide students immediate feedbacks and suggestions based on the knowledge transfer from ASL experts. In the experiment, the students (N=31) were divided into two groups. The first group, Group A (N=17), learnt with the game-based learning while the second group, Group B (N=14), learnt with the traditional face to face learning method. The study result showed a significant difference (p<0.05) on the mean score of the post-tests for both Group A and Group B. It also presented that the game-based learning approach provided a better performance of ASL vocabularies than the traditional face-to-face learning approach. Finally, in the section of Discussion and Conclusion, the effectiveness and the future work opportunity of the proposed game-based learning system were discussed for the improvement of sign language actions.

Background: Declines in physical and cognitive functions are recognized as important risk factors... more Background: Declines in physical and cognitive functions are recognized as important risk factors for falls in older adults. Promising evidence suggests that interactive game-based systems that allow simultaneous physical and cognitive exercise are a potential approach to enhance exercise adherence and reduce fall risk in older adults. However, a limited number of studies have reported the development of a combined physical-cognitive game-based training system for fall risk reduction in older adults. Objective: The aim of this study is to develop and evaluate the usability of an interactive physical-cognitive game-based training system (game-based exercise) for older adults. Methods: In the development phase (Part I), a game-based exercise prototype was created by integrating knowledge and a literature review as well as brainstorming with experts on effective fall prevention exercise for older adults. The output was a game-based exercise prototype that covers crucial physical and cognitive components related to falls. In the usability testing (Part II), 5 games (ie, Fruits Hunter, Where Am I?, Whack a Mole, Sky Falls, and Crossing Poison River) with three difficulty levels (ie, beginner, intermediate, and advanced levels) were tested in 5 older adults (mean age 70.40 years, SD 5.41 years). After completing the games, participants rated their enjoyment level while engaging with the games using the Physical Activity Enjoyment Scale (PACES) and commented on the games. Descriptive statistics were used to describe the participants' characteristics and PACES scores. Results: The results showed that the average PACES score was 123 out of 126 points overall and between 6.66 and 7.00 for each item, indicating a high level of enjoyment. Positive feedback, such as praise for the well-designed interactions and user-friendly interfaces, was also provided. Conclusions: These findings suggest that it is promising to implement an interactive, physical-cognitive game-based exercise in older adults. The effectiveness of a game-based exercise program for fall risk reduction has yet to be determined.

Frontiers in sports and active living, Nov 27, 2020

As gait adaptation is vital for successful locomotion, the development of field-based tools to qu... more As gait adaptation is vital for successful locomotion, the development of field-based tools to quantify gait in challenging real-world environments are crucial. The aims of this study were to assess the reliability and validity of a smartphone-based gait and balance assessment while walking on unobstructed and obstructed terrains using two phone placements. Furthermore, age-related differences in smartphone-derived gait strategies when navigating different walking conditions and environments were evaluated. By providing a method for evaluating gait in the simulated free-living environment, results of this study can elucidate the strategies young and older adults utilize to navigate obstructed and unobstructed walking paths. A total of 24 young and older adults ambulated indoors and outdoors under three conditions: level walking, irregular surface walking, and obstacle crossing. Android smartphones placed on the body and in a bag computed spatiotemporal gait (i.e., velocity, step time, step length, and cadence) and balance (i.e., center of mass (COM) displacement), with motion capture and video used to validate parameters in the laboratory and free-living environments, respectively. Reliability was evaluated using the intraclass correlation coefficient and validity was evaluated using Pearson's correlation and Bland-Altman analysis. A three-way ANOVA was used to assess outcome measures across group, condition, and environment. Results showed that smartphones were reliable and valid for measuring gait across all conditions, phone placements, and environments (ICC 2,1 : 0.606-0.965; Pearson's r: 0.72-1.00). Although body and bag placement demonstrated similar results for spatiotemporal parameters, accurate vertical COM displacement could only be obtained from the body placement. Older adults demonstrated a longer step time and lower cadence only during obstacle crossing, when compared to young adults. Furthermore, environmental differences in walking strategy were observed only during irregular surface walking. In particular, participants utilized a faster gait speed and a longer step length in the free-living environment, compared to the laboratory environment. In conclusion, smartphones demonstrate the potential for remote patient monitoring and home health care. Along with being easy-to-use, inexpensive, and portable, smartphones can accurately evaluate gait during both unobstructed and obstructed walking, indoors and outdoors.

IEEE Journal of Biomedical and Health Informatics, Apr 1, 2020

As turns and walking speed modulation are crucial for functional mobility, development of a field... more As turns and walking speed modulation are crucial for functional mobility, development of a field-based tool to objectively evaluate non-steady-state gait is essential. This study aimed to quantify spatiotemporal gait using three Android smartphones during steady-state walking, turns, and gait speed modulation in laboratory and free-living environments. Twenty-four adults ambulated along a 10-m walkway in both environments under seven conditions: straight walking, 90-degree left or right turn, and modulating gait speed from usual-slow, usual-fast, slow-fast, and fast-slow. Two smartphones were attached to the body, with another phone placed in a shoulder bag. Gait velocity, step time, step length, cadence, and symmetry were computed from smartphone-based tri-axial accelerometers and validated with motion capture and video, in laboratory and free-living environments, respectively. Validity was assessed using Pearson's correlation and Bland-Altman analysis. Gait velocity results revealed moderate to very high validity across all walking conditions, smartphone models, smartphone locations, and environments. Correlations for gait velocity ranged between 0.87-0.91 and 0.79-0.83 for straight walking, 0.86-0.95 and 0.86-0.89 for turning, and 0.51-0.90 and 0.67-0.89 for speed modulation trials, in laboratory and free-living environments, respectively. Step time, step length, and cadence demonstrated high to very high correlations for straight walking and turns. However, symmetry results revealed high correlations only during straight walking in the laboratory. Conditions that included slow walking showed negligible to moderate validity with a high bias. In conclusion, smartphones can be employed as field-based devices to assess steady-state walking, turning, and speed modulation across environment, model, and placement when walking faster than 0.5m/s.

International Journal of Environmental Research and Public Health, Aug 21, 2020

Physical and cognitive declines are significant risk factors for falls. Promising evidence sugges... more Physical and cognitive declines are significant risk factors for falls. Promising evidence suggests that combined physical-cognitive training would be an effective fall risk reduction and cognitive improvement intervention. However, a limited number of studies have been conducted and findings have been inconclusive. This study investigated the effects of interactive physical-cognitive game-based training on the fall risk and cognitive performance of older adults. Forty participants were randomly allocated to the intervention (n = 20) and control (n = 20) groups. Participants in the intervention group performed a 1 h session, 3 times a week for 12 weeks of the interactive physical-cognitive game-based training program. Fall risk (Physiological Profile Assessment, PPA; and Timed Up and Go, TUG) and cognitive outcome (Montreal Cognitive Assessment, MoCA) were assessed at pre-and post-intervention. Thirty-nine participants (mean age = 69.81 ± 3.78 years) completed the study (97.5%). At the end of the trial, participants in the intervention group demonstrated significant improvement in the PPA fall risk score (p = 0.015), postural sway (p = 0.005), MoCA score (p = 0.001), and TUG-dual task (p = 0.045) compared to controls. In conclusion, the interactive physical-cognitive, game-based training was effective in reducing physiological fall risk and improving cognitive function in community-dwelling older adults.

Sensors, Nov 14, 2022

This article is an open access article distributed under the terms and conditions of the Creative... more This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY

Journal of Primary Care & Community Health, 2023

Introduction: Obesity in middle-aged women markedly increases the risk for non-communicable disea... more Introduction: Obesity in middle-aged women markedly increases the risk for non-communicable diseases, neurodegenerative diseases, and physical and cognitive problems. Exercise, particularly combined physical-cognitive exercise, has been demonstrated to have beneficial effects on both physical and cognitive health. However, middle-aged women often face barriers to engaging in exercise, which include time constraints, lack of motivation, and enjoyment. Incorporating an exercise program into a technology-based intervention in the home environment may help overcome these barriers and promote health benefits. Therefore, this study aimed to assess the feasibility of home-based, physical-cognitive internet-based exercise for middle-aged obese women. Methods: A total of 33 middle-aged obese women were enrolled in the study. Participants performed an intervention for 60 min/day, 3 days/week for 3 months. Feasibility outcomes (adherence, adverse events, physical performances, obesity parameters, and enjoyment of the program) were measured. Results: Average exercise adherence was 91.67%, and no adverse events were reported in this feasibility study. At the end of the training period, body weight and BMI were significantly decreased compared to baseline. As for physical performances, both cardiorespiratory fitness and lower limb muscle power were significantly improved at post-training when compared to baseline. Furthermore, the participants experienced a high level of exercise enjoyment, and it was maintained over the 3-month training period. Conclusion: These findings suggest that home-based, internet-based physical-cognitive exercise was safe and feasible for reducing obesity parameters, improving physical function, maintaining enjoyment over the course of training, and facilitating adherence to exercise in middle-aged obese women.

Musculoskeletal science and practice, Dec 1, 2022

Gait & Posture, Sep 1, 2022

PLOS ONE

The Timed Up and Go Test (TUG) is a simple fall risk screening test that covers basic functional ... more The Timed Up and Go Test (TUG) is a simple fall risk screening test that covers basic functional movement; thus, quantifying the subtask movement ability may provide a clinical utility. The video-based system allows individual’s movement characteristics assessment. This study aimed to investigate the concurrent validity and test-retest reliability of the video-based system for assessing the movement speed of TUG subtasks among older adults. Twenty older adults participated in the validity study, whilst ten older adults participated in the reliability study. Participant’s movement speed in each subtask of the TUG under comfortable and fast speed conditions over two sessions was measured. Pearson correlation coefficient was used to identify the validity of the video-based system compared to the motion analysis system. Intraclass correlation coefficient (ICC3,2) was used to determine the reliability of the video-based system. The Bland-Altman plots were used to quantify the agreement b...

Journal of Primary Care & Community Health

Electronic Journal of e-Learning, 2017

PLOS ONE, Jan 18, 2024

Electronic Journal of e-Learning, Aug 1, 2017

Frontiers in sports and active living, Nov 27, 2020

IEEE Journal of Biomedical and Health Informatics, Apr 1, 2020

International Journal of Environmental Research and Public Health, Aug 21, 2020

Sensors, Nov 14, 2022

Journal of Primary Care & Community Health, 2023

Musculoskeletal science and practice, Dec 1, 2022

Gait & Posture, Sep 1, 2022

PLOS ONE

Journal of Primary Care & Community Health

PLOS ONE

Gait speed modulation, including abruptly decreasing or increasing gait speed, is a challenging t... more Gait speed modulation, including abruptly decreasing or increasing gait speed, is a challenging task and prerequisite for safe mobility in the community. Older adults with Mild Cognitive Impairment (MCI) exhibit gait deficits under challenging walking conditions which may increase their risk of falls. The purpose of this study was to investigate spatiotemporal variability during slow and fast speed transitions in older adults with and without MCI. Twenty-five older adults with MCI (mean age = 68.56 ± 3.79 years) and 25 cognitively intact controls (mean age = 68.72 ± 4.67 years) participated. Gait performance during gait speed transitions was measured in two walking conditions: 1) a slow to fast speed transition in response to a randomly presented cue, and 2) a fast to slow speed condition in response to a randomly presented cue. Means and variability of spatiotemporal parameters during the transitions were measured and mixed model repeated measures ANOVAs were used to assess interac...

Sensors

Recent advancement in Deep Learning-based Convolutional Neural Networks (D-CNNs) has led research... more Recent advancement in Deep Learning-based Convolutional Neural Networks (D-CNNs) has led research to improve the efficiency and performance of barcode recognition in Supply Chain Management (SCM). D-CNNs required real-world images embedded with ground truth data, which is often not readily available in the case of SCM barcode recognition. This study introduces two invented barcode datasets: InventBar and ParcelBar. The datasets contain labeled barcode images with 527 consumer goods and 844 post boxes in the indoor environment. To explore the influential capability of the datasets that affect recognition process, five existing D-CNN algorithms were applied and compared over a set of recently available barcode datasets. To confirm the model’s performance and accuracy, runtime and Mean Average Precision (mAP) were examined based on different IoU thresholds and image transformation settings. The results show that YOLO v5 works best for the ParcelBar in terms of speed and accuracy. The s...

Musculoskeletal Science and Practice

Developmental Neurorehabilitation

AIMS To examine the reliability and validity of a simple device, the Swaymeter, for measuring tru... more AIMS To examine the reliability and validity of a simple device, the Swaymeter, for measuring trunk control in children with CP. METHODS Twenty children with spastic CP participated in this study. Trunk sway was measured while quietly sitting for 30s. Children lean forward or backward as far as possible for measuring dynamic balance range. Test-retest reliability was conducted. The concurrent and construct validity of the Swaymeter was assessed by comparison to the motion capture system and gross motor function measure (GMFM). RESULTS The reliability of the Swaymeter was moderate to excellent in measuring trunk sway and dynamic balance range (ICCs = 0.696-0.948). Concurrent validity showed good results (r = 0.818-0.997) and construct validity of dynamic balance in anterior direction showed moderate to high correlation with the GMFM (r = 0.599-0.849). CONCLUSION Assessment of trunk control in a sitting position using the Swaymeter in this study was valid and reliable in children with CP.

Journal of Advances in Information Technology, 2015

The long jump is a part of track and field event. Also, it has been a standard event in modern Ol... more The long jump is a part of track and field event. Also, it has been a standard event in modern Olympic Games. Athletes have to use their strength, skills and effort to make distance as far as possible from a jumping point. The long jump consists of 4 phases: run phase, takeoff phase, flight phase, and landing phase. The actions in each phase effect to the flight distance. If athletes perform right actions in each phase, their performance will be significantly improved prior. In order to have right actions, they need coaching from experts. However, due to the lack of experts in the field, coaching the right actions con not be proceeded widely. In this paper, we propose a framework of an expert system for training long jump athletes by combing computer vision techniques and knowledge management theory. The expert system will capture and learn the right actions of the long jump experts in each phase. Then it will be able to analyse and coach learner/jumper based on knowledge captured from the experts. 