ORCID Profile
0000-0001-9722-9503
Current Organisations
Nanyang Technological University
,
Curtin University
Does something not look right? The information on this page has been harvested from data sources that may not be up to date. We continue to work with information providers to improve coverage and quality. To report an issue, use the Feedback Form.
In Research Link Australia (RLA), "Research Topics" refer to ANZSRC FOR and SEO codes. These topics are either sourced from ANZSRC FOR and SEO codes listed in researchers' related grants or generated by a large language model (LLM) based on their publications.
Civil Engineering | Structural Engineering | Pattern Recognition and Data Mining | Construction Materials
Expanding Knowledge in Engineering | Expanding Knowledge in Technology | Hydrogen-based Energy Systems (incl. Internal Hydrogen Combustion Engines) | Management of Solid Waste from Energy Activities | Civil Building Management and Services | Cement and Concrete Materials |
Publisher: IEEE
Date: 10-2013
DOI: 10.1109/CW.2013.40
Publisher: Springer Science and Business Media LLC
Date: 23-06-1998
Publisher: Elsevier BV
Date: 08-2019
Publisher: IEEE
Date: 08-2015
Publisher: Springer Berlin Heidelberg
Date: 2009
Publisher: IEEE
Date: 12-2008
Publisher: Elsevier
Date: 1995
Publisher: Elsevier BV
Date: 08-2017
Publisher: Springer Berlin Heidelberg
Date: 2014
Publisher: Springer Science and Business Media LLC
Date: 06-09-2018
Publisher: Elsevier BV
Date: 03-2010
Publisher: Springer Science and Business Media LLC
Date: 21-10-2019
Publisher: IEEE Comput. Soc
Date: 2001
Publisher: IEEE Comput. Soc
Date: 2001
Publisher: IEEE
Date: 11-2015
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 07-2021
Publisher: Institute of Electronics, Information and Communications Engineers (IEICE)
Date: 2014
Publisher: Elsevier BV
Date: 2024
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2023
Publisher: IEEE
Date: 11-2014
Publisher: IEEE
Date: 03-2014
Publisher: IEEE
Date: 12-2016
Publisher: Springer Science and Business Media LLC
Date: 09-05-2018
Publisher: ACM
Date: 12-2007
Publisher: Elsevier BV
Date: 02-1998
Publisher: IEEE
Date: 11-2013
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2010
Publisher: Elsevier BV
Date: 06-2000
Publisher: IEEE
Date: 11-2015
Publisher: IEEE
Date: 08-2014
Publisher: Zhejiang University Press
Date: 07-2006
Publisher: IEEE
Date: 04-2013
Publisher: Wiley
Date: 16-06-2004
DOI: 10.1002/CAV.44
Abstract: This paper proposed an optimization approach for human motion recovery from the un‐calibrated monocular images containing unlimited human movements. A 3D skeleton human model based on anatomy knowledge is employed with encoded biomechanical constraints for the joints. Energy Function is defined to represent the deviations between projection features and extracted image features. Reconstruction procedure is developed to adjust joints and segments of the human body into their proper positions. Genetic Algorithms are adopted to find the optimal solution effectively in the high dimensional parameter space by simultaneously considering all the parameters of the human model. The experimental results are analysed by Deviation Penalty. Copyright © 2004 John Wiley & Sons, Ltd.
Publisher: Springer Science and Business Media LLC
Date: 04-06-2016
Publisher: IEEE
Date: 12-2012
Publisher: Elsevier BV
Date: 11-2019
DOI: 10.1016/J.JENVMAN.2019.109530
Abstract: This work aimed at elucidating the role of bacteria present in the gut of the earthworm Metaphire posthuma in plant growth promotion and toxic trace elements (TTEs) bioremediation. We isolated and identified three bacterial strains Bacillus safensis (MF 589718), Bacillus flexus (MF 589717) and Staphylococcus haemolyticus (MF 589719) among which the Bacillus strains appeared to be significantly more potent than the Staphylococcus strain (P < 0.05) in promoting plant growth and removing TTE (Cr(VI), Cu(II) and Zn(II)) from aqueous media. These strains exhibited several plant growth promoting traits (e.g., indole acetic acid (IAA), gibberellic acid (GA) and ammonium ion production, 1-aminocyclopropane- 1-carboxylic acid (ACC) deaminase activity, and phosphate solubilizing potential). In a pot trial, the gut isolates improved Vigna radiata seed germination, and enhanced the leaf area (30-79%), total chlorophyll content (26-67%) and overall root-shoot biomass (32-83%) as compared to the control. Bacillus safensis and Bacillus flexus were equipotent in removing Cr(VI) (40.5 and 40.3%) from aqueous media the former triumphed for Zn(II) removal (52.8%), while the latter performed better for Cu(II) removal (43.5%). The gut isolates successfully solubilized phosphate even in TTE-contaminated conditions. The results demonstrate that the earthworm's enteric bacteria possess inherent plant growth promoting, TTE resistance and phosphate solubilization (even under TTE stress) properties which can be further explored for their application in sustainable crop production and environmental management.
Publisher: SAGE Publications
Date: 20-09-2019
Abstract: This article proposes a deep sparse autoencoder framework for structural damage identification. This framework can be employed to obtain the optimal solutions for some pattern recognition problems with highly nonlinear nature, such as learning a mapping between the vibration characteristics and structural damage. Three main components are defined in the proposed framework, namely, the pre-processing component with a data whitening process, the sparse dimensionality reduction component where the dimensionality of the original input vector is reduced while preserving the required necessary information, and the relationship learning component where the mapping between the compressed dimensional feature and the stiffness reduction parameters of the structure is built. The proposed framework utilizes the sparse autoencoders based deep neural network structure to enhance the capability and performance of the dimensionality reduction and relationship learning components with a pre-training scheme. In the final stage of training, both components are jointly optimized to fine-tune the network towards achieving a better accuracy in structural damage identification. Since structural damages usually occur only at a small number of elements that exhibit stiffness reduction out of the large total number of elements in the entire structure, sparse regularization is adopted in this framework. Numerical studies on a steel frame structure are conducted to investigate the accuracy and robustness of the proposed framework in structural damage identification, taking into consideration the effects of noise in the measurement data and uncertainties in the finite element modelling. Experimental studies on a prestressed concrete bridge in the laboratory are conducted to further validate the performance of using the proposed framework for structural damage identification.
Publisher: MDPI AG
Date: 12-03-2014
DOI: 10.3390/POLYM6030706
Publisher: Springer Science and Business Media LLC
Date: 12-01-2018
Publisher: IEEE
Date: 2015
DOI: 10.1109/WACV.2015.34
Publisher: Springer Science and Business Media LLC
Date: 03-2006
Publisher: Elsevier BV
Date: 10-2018
Publisher: Springer Science and Business Media LLC
Date: 29-04-2016
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2018
Publisher: American Institute of Mathematical Sciences (AIMS)
Date: 09-2016
DOI: 10.3934/NACO.2016011
Publisher: Emerald
Date: 02-2005
DOI: 10.1108/RJTA-09-01-2005-B006
Abstract: Significant progress has been achieved over the last decade in the realistic animation of garments. However it is still a very costly process in terms of computational resources. Since wrinkles and vast smooth areas co-exist commonly, it is tempting to reduce computational cost by avoiding redundant tessellation at the smooth areas. In this paper we present a method for dynamic adaptation of triangular meshes suitable for the most elaborated cloth simulation approaches, such as finite-element based or alike. We use bottom-up approach to mesh refinement, which does not require precomputation and storage of multiresolution hierarchy. The hierarchy is constructed in runtime using √3-refinement rule. The hierarchy is essential to allow reverting of the refinement locally. Local mesh refinement and simplification are triggered by curvature-induced criterion, where the curvature is estimated using methods of discrete differential geometry. In the existing literature of adaptive meshes only the formulas for estimating the discrete mean curvature at the inner mesh vertices can be found. We extend it to the triangulated 2-manifolds with boundary, such as cloth meshes. The results demonstrated are the realistic animation of garment worn by a walking mannequin generated with Baraff-Witkin type cloth solver enhanced with our mesh adaptation scheme.
Publisher: IEEE
Date: 11-2014
Publisher: Springer Berlin Heidelberg
Date: 2010
Publisher: Zhejiang University Press
Date: 07-2006
Publisher: Springer Science and Business Media LLC
Date: 03-03-2018
Publisher: IEEE
Date: 12-2012
Publisher: IEEE
Date: 11-2017
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2023
Publisher: IEEE
Date: 2003
Publisher: Institute of Electronics, Information and Communications Engineers (IEICE)
Date: 2014
Publisher: IEEE
Date: 11-2015
Publisher: IEEE
Date: 12-2008
Publisher: Elsevier BV
Date: 12-2018
Publisher: Elsevier BV
Date: 04-1999
Publisher: Elsevier BV
Date: 07-2019
Publisher: Springer Science and Business Media LLC
Date: 07-12-2011
Publisher: IEEE
Date: 11-2015
Publisher: Elsevier BV
Date: 05-2021
Publisher: Elsevier BV
Date: 04-2019
Publisher: Elsevier BV
Date: 02-2023
Publisher: ACM
Date: 29-11-2005
Publisher: Springer International Publishing
Date: 2019
Publisher: World Scientific Pub Co Pte Lt
Date: 04-2005
DOI: 10.1142/S021946780500180X
Abstract: The paper aims to propose a new approach towards human posture reconstruction and animation from monocular video sequences that contain any kind of human postures and movements. This is a way towards low cost motion capture and at the same time it avoids many limitations of those classical methods. A parameterized human skeleton model based on anatomy is adopted where the angular constraints are encoded in the joints. Criterion Function is defined to represent the residuals between feature points in the monocular image and the corresponding points resulted from projecting the human model to the projection plane. By transforming each segment of the human model to achieve the minimum value of the Criterion Function, the proper human posture that resembles the one represented by the monocular image can be generated. Different kinds of adjustments are utilized to adjust the body parts into the proper locations and orientations in 3D space without camera calibration. In order to find the optimal solution effectively in a high-dimensional parameter space by considering all the parameters simultaneously, the method of Genetic Algorithms is proposed. A procedure is developed to recover the whole body posture, and then a human animation system is developed to animate a series of human movements from monocular image sequences, during which information between consecutive frames is considered to improve the accuracy. Our technique makes it feasible to reconstruct any possible human postures, and experimental results from many monocular images and video sequences are encouraging.
Publisher: Elsevier BV
Date: 10-2023
Publisher: IEEE
Date: 10-2013
DOI: 10.1109/CW.2013.17
Publisher: Springer International Publishing
Date: 2019
Publisher: IEEE
Date: 11-2015
Publisher: IEEE
Date: 12-2012
Publisher: Wiley
Date: 12-2005
Publisher: Elsevier BV
Date: 1996
Publisher: IEEE
Date: 12-2012
Publisher: MDPI AG
Date: 27-07-2018
DOI: 10.3390/A11080112
Abstract: In this paper, damage detection/identification for a seven-storey steel structure is investigated via using the vibration signals and deep learning techniques. Vibration characteristics, such as natural frequencies and mode shapes are captured and utilized as input for a deep learning network while the output vector represents the structural damage associated with locations. The deep auto-encoder with sparsity constraint is used for effective feature extraction for different types of signals and another deep auto-encoder is used to learn the relationship of different signals for final regression. The existing SAF model in a recent research study for the same problem processed all signals in one serial auto-encoder model. That kind of models have the following difficulties: (1) the natural frequencies and mode shapes are in different magnitude scales and it is not logical to normalize them in the same scale in building the models with training s les (2) some frequencies and mode shapes may not be related to each other and it is not fair to use them for dimension reduction together. To tackle the above-mentioned problems for the multi-scale dataset in SHM, a novel parallel auto-encoder framework (Para-AF) is proposed in this paper. It processes the frequency signals and mode shapes separately for feature selection via dimension reduction and then combine these features together in relationship learning for regression. Furthermore, we introduce sparsity constraint in model reduction stage for performance improvement. Two experiments are conducted on performance evaluation and our results show the significant advantages of the proposed model in comparison with the existing approaches.
Publisher: Springer Berlin Heidelberg
Date: 2010
Start Date: 2021
End Date: 12-2023
Amount: $355,331.00
Funder: Australian Research Council
View Funded ActivityStart Date: 07-2021
End Date: 06-2024
Amount: $290,831.00
Funder: Australian Research Council
View Funded ActivityStart Date: 04-2021
End Date: 12-2024
Amount: $768,927.00
Funder: Australian Research Council
View Funded Activity