Kar Ho Tso
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
Kar Ho Tso has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Ahadiyat Abadi Bin Rawi
Computing Science, University of Glasgow, United Kingdom
1 shared publication - Chin-Sean Sum
Singapore Institute of Technology, Singapore
1 shared publication - Dennis Wong
Macao Polytechnic University
1 shared publication - Peter ChunYu Yau
School of Computing Science, University of Glasgow, Glasgow, United Kingdom
1 shared publication - Tyne Ng
Computing Science, University of Glasgow, United Kingdom
1 shared publication
Latest Publications
- 24 October 2026
- Published by Real Sense Pty Ltd in Australian Journal of Business and Social Science
- Vol. 1 (5) , 69-76
Autonomous Coastal Litter Collection via SLAM-Based Navigation and Deep Learning: System Design, Field Validation, and Operational Impact
Coastal litter accumulation represents a significant environmental, economic, and public health challenge affecting thousands of beaches globally. Conventional manual cleaning is labour-intensive (5–10 hours per site) and inefficient (30 –50% recyclables re covery). This paper presents EZBeachbot, an autonomous robotic system integrating SLAM-based navigation with LiDAR-Radar sensor fusion, deep learning-based waste detection, and real-time ESG measurement. We establish theoretical foundations for navigation and perception in unstructured coastal environments and validate the system through 12 -day field deployment at Deep Water Bay Beach, Hong Kong. Key contributions include: (1) an Extended Kalman Filter -based SLAM-LiDAR-Radar fusion algorithm with <0.87% drift over 2 km traverses; (2) deep learni ng detector (Faster R -CNN) achieving 91.4% F1 -score on 102,400 -image training set; (3) comprehensive field validation demonstrating 50% time reduction, 60% labour reduction, 78% recyclables diversion, and 82% carbon emissions reduction. The system is production -ready for municipal deployment at single or multi - site scale. Results provide empirical evidence for technical feasibility and commercial viability of autonomous coastal remediation.
- 24 October 2026
- Published by Real Sense Pty Ltd in Australian Journal of Business and Social Science
- Vol. 1 (5) , 69-76
Autonomous Coastal Litter Collection via SLAM-Based Navigation and Deep Learning: System Design, Field Validation, and Operational Impact
Coastal litter accumulation represents a significant environmental, economic, and public health challenge affecting thousands of beaches globally. Conventional manual cleaning is labour-intensive (5–10 hours per site) and inefficient (30 –50% recyclables re covery). This paper presents EZBeachbot, an autonomous robotic system integrating SLAM-based navigation with LiDAR-Radar sensor fusion, deep learning-based waste detection, and real-time ESG measurement. We establish theoretical foundations for navigation and perception in unstructured coastal environments and validate the system through 12 -day field deployment at Deep Water Bay Beach, Hong Kong. Key contributions include: (1) an Extended Kalman Filter -based SLAM-LiDAR-Radar fusion algorithm with <0.87% drift over 2 km traverses; (2) deep learni ng detector (Faster R -CNN) achieving 91.4% F1 -score on 102,400 -image training set; (3) comprehensive field validation demonstrating 50% time reduction, 60% labour reduction, 78% recyclables diversion, and 82% carbon emissions reduction. The system is production -ready for municipal deployment at single or multi - site scale. Results provide empirical evidence for technical feasibility and commercial viability of autonomous coastal remediation.
- Open Access
- 24 August 2026
- Published by Real Sense Pty Ltd in Australian Journal of Business and Social Science
- Vol. 1 (4) , 529-557
AI Safety Guard: Design, Prototype Implementation, and Validation Roadmap for a Privacy-Preserving Multi-Sensory Edge-AI Driver Drowsiness System
Driver drowsiness is a persistent road -safety problem whose episodic and under -reported nature complicates both prevention and measurement. This paper presents AI Safety Guard, a low -cost edge- AI prototype that combines non -contact facial-landmark analysis with bounded auditory and optional olfactory alerts. The proposed artefact uses local camera processing to estimate sustained eye closure, mouth opening and yawn patterns, and head -pose deviation; temporal decision fusion then triggers an active warning through a speaker or buzzer and, when enabled, a short, atomised scent pulse. Unlike cloud-dependent monitoring, the prototype is designed to retain no video and to record only minimal local event information. The study adopts a design -science and safety -by-design methodology: it reconstructs system requirements, specifies the hardware and inference architecture, formalises the tri- channel decision logic, and evaluates the credibility and limits of preliminary prototype evidence. Project documentation reports operation on Raspberry Pi-class hardware at approximately 10-15 frames per second, local event logging, hard -coded ac tuator duration, cooldown lockout, manual acknowledgement, and a scent opt-out. A website event trace reports 116 ms from a detection event to alert activation, whereas a separate pitch document claims 0.001 s actuation latency; this discrepancy is treated as an unresolved measurement issue rather than evidence of validated performance. The paper therefore distinguishes artefact feasibility from safety efficacy. It proposes a five -phase validation programme covering bench metrology, public -dataset evaluation, simulator experiments, closed -track trials, and regulatory readiness against functional-safety, safety-of-the-intended-functionality, privacy, and human -machine-interface requirements. The principal con tribution is an evidence -bounded blueprint for translating a student -developed prototype into a testable driver -monitoring system while preserving privacy and explicitly managing intervention risk. The system is not positioned as a substitute for sleep, rest, or safe pull-over behaviour, but as a supplementary warning device requiring independent validation before road deployment.
- 24 August 2026
- Published by Real Sense Pty Ltd in Australian Journal of Business and Social Science
- Vol. 1 (4) , 529-557
Open AccessAI Safety Guard: Design, Prototype Implementation, and Validation Roadmap for a Privacy-Preserving Multi-Sensory Edge-AI Driver Drowsiness System
Driver drowsiness is a persistent road -safety problem whose episodic and under -reported nature complicates both prevention and measurement. This paper presents AI Safety Guard, a low -cost edge- AI prototype that combines non -contact facial-landmark analysis with bounded auditory and optional olfactory alerts. The proposed artefact uses local camera processing to estimate sustained eye closure, mouth opening and yawn patterns, and head -pose deviation; temporal decision fusion then triggers an active warning through a speaker or buzzer and, when enabled, a short, atomised scent pulse. Unlike cloud-dependent monitoring, the prototype is designed to retain no video and to record only minimal local event information. The study adopts a design -science and safety -by-design methodology: it reconstructs system requirements, specifies the hardware and inference architecture, formalises the tri- channel decision logic, and evaluates the credibility and limits of preliminary prototype evidence. Project documentation reports operation on Raspberry Pi-class hardware at approximately 10-15 frames per second, local event logging, hard -coded ac tuator duration, cooldown lockout, manual acknowledgement, and a scent opt-out. A website event trace reports 116 ms from a detection event to alert activation, whereas a separate pitch document claims 0.001 s actuation latency; this discrepancy is treated as an unresolved measurement issue rather than evidence of validated performance. The paper therefore distinguishes artefact feasibility from safety efficacy. It proposes a five -phase validation programme covering bench metrology, public -dataset evaluation, simulator experiments, closed -track trials, and regulatory readiness against functional-safety, safety-of-the-intended-functionality, privacy, and human -machine-interface requirements. The principal con tribution is an evidence -bounded blueprint for translating a student -developed prototype into a testable driver -monitoring system while preserving privacy and explicitly managing intervention risk. The system is not positioned as a substitute for sleep, rest, or safe pull-over behaviour, but as a supplementary warning device requiring independent validation before road deployment.
- 20 June 2026
- Published by Real Sense Pty Ltd in Australian Journal of Business and Social Science
- Vol. 1 (3) , 20-27
Gamification Fatigue and Continuance Intention in Technology‑Enhanced Learning Platforms: A Post‑Adoption Extension of TAM
Technology-Enhanced Learning (TEL) platforms have become infrastructure in higher education, yet many implementations fail to sustain students’ voluntary engagement over time. Gamification is widely adopted to increase participation through game design elements such as points, badges, leaderboards, and progress feedback. However, a growing body of work suggests that gamification’s benefits are temporally dynamic: early engagement gains may attenuate after an initial novelty window, and some designs may introduce psychological strain that contributes to disengagement and fatigue. Despite these practical concerns, most gamification-acceptance studies remain cross-sectional and focus on initial adoption rather than continuance. This paper reframes gamified TEL acceptance as a post-adoption phenomenon and proposes a continuance-oriented model that extends the Technology Acceptance Model (TAM) with two constructs that are theoretically central to sustained use: satisfaction and gamification fatigue. Gamification fatigue is conceptualised as a progressive decline in motivational value due to habituation, mechanic-goal misalignment, perceived unfairness, competitive pressure, or interaction overload. To ground the post-adoption framing, we report pilot evidence from a university student survey (N=71) containing TAM beliefs, perceived gamification features, and continuance-oriented intention items. The pilot results indicate strong positive associations among constructs; perceived gamification shows the strongest correlation with intention (r=.795), followed by perceived ease of use (r=.696) and perceived usefulness (r=.679). In multiple regression, perceived gamification and perceived ease of use significantly predict continuance-oriented intention, while perceived usefulness is not significant when controlling for the other predictors. Building on these findings and recent longitudinal evidence on novelty and fatigue dynamics, the paper contributes a post-adoption conceptual model, an operational definition of gamification fatigue, and a longitudinal protocol and measurement instrument for semester-scale evaluation.
- 20 June 2026
- Published by Real Sense Pty Ltd in Australian Journal of Business and Social Science
- Vol. 1 (3) , 20-27
Gamification Fatigue and Continuance Intention in Technology‑Enhanced Learning Platforms: A Post‑Adoption Extension of TAM
Technology-Enhanced Learning (TEL) platforms have become infrastructure in higher education, yet many implementations fail to sustain students’ voluntary engagement over time. Gamification is widely adopted to increase participation through game design elements such as points, badges, leaderboards, and progress feedback. However, a growing body of work suggests that gamification’s benefits are temporally dynamic: early engagement gains may attenuate after an initial novelty window, and some designs may introduce psychological strain that contributes to disengagement and fatigue. Despite these practical concerns, most gamification-acceptance studies remain cross-sectional and focus on initial adoption rather than continuance. This paper reframes gamified TEL acceptance as a post-adoption phenomenon and proposes a continuance-oriented model that extends the Technology Acceptance Model (TAM) with two constructs that are theoretically central to sustained use: satisfaction and gamification fatigue. Gamification fatigue is conceptualised as a progressive decline in motivational value due to habituation, mechanic-goal misalignment, perceived unfairness, competitive pressure, or interaction overload. To ground the post-adoption framing, we report pilot evidence from a university student survey (N=71) containing TAM beliefs, perceived gamification features, and continuance-oriented intention items. The pilot results indicate strong positive associations among constructs; perceived gamification shows the strongest correlation with intention (r=.795), followed by perceived ease of use (r=.696) and perceived usefulness (r=.679). In multiple regression, perceived gamification and perceived ease of use significantly predict continuance-oriented intention, while perceived usefulness is not significant when controlling for the other predictors. Building on these findings and recent longitudinal evidence on novelty and fatigue dynamics, the paper contributes a post-adoption conceptual model, an operational definition of gamification fatigue, and a longitudinal protocol and measurement instrument for semester-scale evaluation.
- Open Access
- 16 February 2026
- Published by Real Sense Pty Ltd in Australian Journal of Business and Social Science
- Vol. 1 (1) , 75-79
A block-chain-integrated framework for micro-credentialing: enhancing trust and engagement in vocational internship portfolios
This paper proposes a framework using blockchain technology to verify vocational micro-credentials. It aims to solve the issue of portfolio fraud while increasing student engagement in lifelong learning pathways.
- 16 February 2026
- Published by Real Sense Pty Ltd in Australian Journal of Business and Social Science
- Vol. 1 (1) , 75-79
Open AccessA block-chain-integrated framework for micro-credentialing: enhancing trust and engagement in vocational internship portfolios
This paper proposes a framework using blockchain technology to verify vocational micro-credentials. It aims to solve the issue of portfolio fraud while increasing student engagement in lifelong learning pathways.
- Open Access
- 1 January 2026
- Published by Real Sense Pty Ltd in Australian Journal of Business and Social Science
- Vol. 1 (2) , 75-81
Gamification and Student Acceptance of Technology-Enhanced Learning Platforms: Evidence from an Extended TAM Pilot Study
Technology-Enhanced Learning (TEL) platforms have become an operational default in higher education, yet student acceptance and sustained engagement vary considerably across cohorts and course designs. Gamification—the deliberate use of game-design elements such as points, badges, challenges, feedback, and narrative in non-game learning contexts—has been widely adopted to improve motivation and persistence, but its influence on technology acceptance is often reported inconsistently and is frequently evaluated without explicit theoretical grounding. Building on the Technology Acceptance Model (TAM), this study tests an extended acceptance model that positions perceived gamification features (GAM) as an additional predictor of behavioural intention to use (BIU), alongside perceived usefulness (PU) and perceived ease of use (PEOU). A cross-sectional survey of higher-education students (N = 71) with prior exposure to gamified TEL experiences was analysed using reliability tests, Pearson correlations, and multiple regression. All constructs met exploratory reliability thresholds. Correlations indicate strong positive associations between BIU and GAM, PEOU, and PU. In the regression model, GAM and PEOU significantly predicted BIU, while PU was not significant. The findings suggest that in contemporary TEL contexts where baseline functional utility is assumed, motivational and experience-oriented design may play a decisive role in acceptance and continuance intention. The paper contributes a transparent, pilot-evidence-based extension of TAM, offers actionable design implications, and provides instrument-level reporting to support replication. Limitations include non-probability sampling, self-reported measures, and cross-sectional design; future research should validate causal mechanisms using longitudinal and experimental designs and test alternative specifications.
- 1 January 2026
- Published by Real Sense Pty Ltd in Australian Journal of Business and Social Science
- Vol. 1 (2) , 75-81
Open AccessGamification and Student Acceptance of Technology-Enhanced Learning Platforms: Evidence from an Extended TAM Pilot Study
Technology-Enhanced Learning (TEL) platforms have become an operational default in higher education, yet student acceptance and sustained engagement vary considerably across cohorts and course designs. Gamification—the deliberate use of game-design elements such as points, badges, challenges, feedback, and narrative in non-game learning contexts—has been widely adopted to improve motivation and persistence, but its influence on technology acceptance is often reported inconsistently and is frequently evaluated without explicit theoretical grounding. Building on the Technology Acceptance Model (TAM), this study tests an extended acceptance model that positions perceived gamification features (GAM) as an additional predictor of behavioural intention to use (BIU), alongside perceived usefulness (PU) and perceived ease of use (PEOU). A cross-sectional survey of higher-education students (N = 71) with prior exposure to gamified TEL experiences was analysed using reliability tests, Pearson correlations, and multiple regression. All constructs met exploratory reliability thresholds. Correlations indicate strong positive associations between BIU and GAM, PEOU, and PU. In the regression model, GAM and PEOU significantly predicted BIU, while PU was not significant. The findings suggest that in contemporary TEL contexts where baseline functional utility is assumed, motivational and experience-oriented design may play a decisive role in acceptance and continuance intention. The paper contributes a transparent, pilot-evidence-based extension of TAM, offers actionable design implications, and provides instrument-level reporting to support replication. Limitations include non-probability sampling, self-reported measures, and cross-sectional design; future research should validate causal mechanisms using longitudinal and experimental designs and test alternative specifications.
- Open Access
- 23 February 2024
- Published by Association for Computing Machinery (ACM)
- p. 536-541
Migrating from Monolithic to Microservices with Hybrid Database Design Architecture
This paper explores the monolithic and microservice architecture, by proposing a migration strategy using the Domain-Driven Design, implementing a hybrid database design. By decomposing the legacy system's components and integrating microservice architecture, it improves system robustness, scalability, and flexibility. Additionally, enhancement strategies are proposed, such as reducing coupling through microservice decomposition, incorporating design patterns, handling distributed transactions, and implementing eventual consistency using the Saga pattern. This aims to improve system performance through enhanced fault tolerance, reduced service downtimes, and improved communication reliability.
- 23 February 2024
- Published by Association for Computing Machinery (ACM)
- p. 536-541
Open AccessMigrating from Monolithic to Microservices with Hybrid Database Design Architecture
This paper explores the monolithic and microservice architecture, by proposing a migration strategy using the Domain-Driven Design, implementing a hybrid database design. By decomposing the legacy system's components and integrating microservice architecture, it improves system robustness, scalability, and flexibility. Additionally, enhancement strategies are proposed, such as reducing coupling through microservice decomposition, incorporating design patterns, handling distributed transactions, and implementing eventual consistency using the Saga pattern. This aims to improve system performance through enhanced fault tolerance, reduced service downtimes, and improved communication reliability.