Arosha Dabarera
Research Subjects
Arosha Dabarera has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
Liang Li
3 shared publications- Vinh The Ngoc Dao
The University of Queensland
3 shared publications Kanako Mori
2 shared publicationsSomnuk Tangtermsirikul
2 shared publications- Warangkana Saengsoy
Thammasat University
2 shared publications Jiahang Li
The University of Queensland
1 shared publication
Latest Publications
- 14 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-8
Interpretable AI for Built Environment Digital Twins: The Role of Tsetlin Machines
Digital Twin (DT) is a growing concept in industries such as manufacturing, energy, smart cities, and built environments. To bridge the digital and physical worlds, DTs often rely on state-of-the-art Machine Learning (ML) models. However, many ML models, like Neural Networks, are considered black boxes, making their decision-making processes difficult to interpret. To address this, the explainable AI paradigm has introduced methods like SHAP and LIME. Despite their effectiveness, interpreting model outputs remains challenging. This paper explores the potential of using Tsetlin Machines in built environment DTs to explain the detection of structural properties. The Tsetlin Machine has demonstrated strong performance even with limited training data while offering both local and global interpretability. Its rule-based approach provides transparent decision-making, making it a promising alternative to traditional black-box models in DT applications.
- 14 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-8
Interpretable AI for Built Environment Digital Twins: The Role of Tsetlin Machines
Digital Twin (DT) is a growing concept in industries such as manufacturing, energy, smart cities, and built environments. To bridge the digital and physical worlds, DTs often rely on state-of-the-art Machine Learning (ML) models. However, many ML models, like Neural Networks, are considered black boxes, making their decision-making processes difficult to interpret. To address this, the explainable AI paradigm has introduced methods like SHAP and LIME. Despite their effectiveness, interpreting model outputs remains challenging. This paper explores the potential of using Tsetlin Machines in built environment DTs to explain the detection of structural properties. The Tsetlin Machine has demonstrated strong performance even with limited training data while offering both local and global interpretability. Its rule-based approach provides transparent decision-making, making it a promising alternative to traditional black-box models in DT applications.
- 3 August 2022
- Published by University of Queensland Library
Early-age cracking in concrete structures: Mechanisms and control
- 3 August 2022
- Published by University of Queensland Library
Early-age cracking in concrete structures: Mechanisms and control
- 1 March 2022
- Published by Elsevier in Cement and Concrete Composites
- Vol. 127
Assessing the zero-stress temperature in high performance concrete at early age
- 1 March 2022
- Published by Elsevier in Cement and Concrete Composites
- Vol. 127
Assessing the zero-stress temperature in high performance concrete at early age
- 2 June 2021
- Published by Springer Nature in Materials and Structures
- Vol. 54 (3) , 1-16
Experimental evaluation and modelling of early-age basic tensile creep in high-performance concrete
- 2 June 2021
- Published by Springer Nature in Materials and Structures
- Vol. 54 (3) , 1-16
Experimental evaluation and modelling of early-age basic tensile creep in high-performance concrete
- 19 May 2021
- Published by Springer Nature
- p. 3-12
Age-Adjusted Effective Elastic Modulus of High-Performance Concrete at Early Age
- 19 May 2021
- Published by Springer Nature
- p. 3-12
Age-Adjusted Effective Elastic Modulus of High-Performance Concrete at Early Age
- 15 June 2017
- Published by Faculty of Engineering, Chulalongkorn University in Engineering Journal
- Vol. 21 (3) , 157-171
Models for Predicting Hydration Degree and Adiabatic Temperature Rise of Mass Concrete containing Ground Granulated Blast Furnace Slag
- 15 June 2017
- Published by Faculty of Engineering, Chulalongkorn University in Engineering Journal
- Vol. 21 (3) , 157-171
Models for Predicting Hydration Degree and Adiabatic Temperature Rise of Mass Concrete containing Ground Granulated Blast Furnace Slag
- 4 July 2016
- Published by Trans Tech Publications, Ltd. in Materials Science Forum
- Vol. 860, 135-139
Models for Predicting Free Water and Specific Heat of Pastes Containing Ground Granulated Blast Furnace Slag
This paper aims to investigate early age behavior in terms of free water content and specific heat for hardening cement paste incorporating Ground Granulated Blast Furnace Slag. Experiments were conducted to obtain free water and specific heat of slag-cement pastes by varying water to binder ratios and slag replacement levels. Free water to total binder ratios for pastes with w/b of 0.40 and slag replacements of 45% and 75% are 0.23 and 0.25 at 3 days and 0.17 and 0.19 at 28 days, respectively. Specific heat values for similar mixtures are 0.26 and 0.30 at 3 days and 0.23 and 0.25 at 28 days. Results showed that specific heat decreases as the amount of free water decreases. The slag substitution resulted in high specific heat and free water at early age but tends to decrease in long term due to enhanced reaction kinetics. Models were proposed to compute free water and specific heat by modifying existing models. The model simulations can be used to predict the measured values accurately.
- 4 July 2016
- Published by Trans Tech Publications, Ltd. in Materials Science Forum
- Vol. 860, 135-139
Models for Predicting Free Water and Specific Heat of Pastes Containing Ground Granulated Blast Furnace Slag
This paper aims to investigate early age behavior in terms of free water content and specific heat for hardening cement paste incorporating Ground Granulated Blast Furnace Slag. Experiments were conducted to obtain free water and specific heat of slag-cement pastes by varying water to binder ratios and slag replacement levels. Free water to total binder ratios for pastes with w/b of 0.40 and slag replacements of 45% and 75% are 0.23 and 0.25 at 3 days and 0.17 and 0.19 at 28 days, respectively. Specific heat values for similar mixtures are 0.26 and 0.30 at 3 days and 0.23 and 0.25 at 28 days. Results showed that specific heat decreases as the amount of free water decreases. The slag substitution resulted in high specific heat and free water at early age but tends to decrease in long term due to enhanced reaction kinetics. Models were proposed to compute free water and specific heat by modifying existing models. The model simulations can be used to predict the measured values accurately.