ORCID Profile
0000-0001-8979-2224
Current Organisation
Queensland University of Technology
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.
Innovation and Technology Management | Manufacturing Engineering | Manufacturing Robotics and Mechatronics (excl. Automotive Mechatronics) | Control Systems, Robotics and Automation |
Expanding Knowledge in Engineering | Technological and Organisational Innovation
Publisher: IEEE
Date: 06-2013
Publisher: ACM
Date: 07-07-2007
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 09-2009
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 03-2008
Publisher: IEEE
Date: 07-2018
Publisher: Elsevier BV
Date: 02-2017
Publisher: Frontiers Media SA
Date: 22-01-2021
Publisher: Elsevier BV
Date: 2017
Publisher: ACM
Date: 11-07-2015
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 11-2023
Publisher: Elsevier BV
Date: 09-2005
Publisher: IEEE
Date: 06-2013
Publisher: Springer Science and Business Media LLC
Date: 29-01-2021
Publisher: ACM
Date: 15-07-2017
Publisher: IEEE
Date: 06-2019
Publisher: Springer Singapore
Date: 2017
Publisher: World Scientific Pub Co Pte Lt
Date: 06-2014
DOI: 10.1142/S1469026814500096
Abstract: Feature selection is a multi-objective problem, where the two main objectives are to maximize the classification accuracy and minimize the number of features. However, most of the existing algorithms belong to single objective, wrapper approaches. In this work, we investigate the use of binary particle swarm optimization (BPSO) and probabilistic rough set (PRS) for multi-objective feature selection. We use PRS to propose a new measure for the number of features based on which a new filter based single objective algorithm (PSOPRSE) is developed. Then a new filter-based multi-objective algorithm (MORSE) is proposed, which aims to maximize a measure for the classification performance and minimize the new measure for the number of features. MORSE is examined and compared with PSOPRSE, two existing PSO-based single objective algorithms, two traditional methods, and the only existing BPSO and PRS-based multi-objective algorithm (MORSN). Experiments have been conducted on six commonly used discrete datasets with a relative small number of features and six continuous datasets with a large number of features. The classification performance of the selected feature subsets are evaluated by three classification algorithms (decision trees, Naïve Bayes, and k-nearest neighbors). The results show that the proposed algorithms can automatically select a smaller number of features and achieve similar or better classification performance than using all features. PSOPRSE achieves better performance than the other two PSO-based single objective algorithms and the two traditional methods. MORSN and MORSE outperform all these five single objective algorithms in terms of both the classification performance and the number of features. MORSE achieves better classification performance than MORSN. These filter algorithms are general to the three different classification algorithms.
Publisher: Springer Netherlands
Date: 2008
Publisher: IEEE
Date: 11-07-2021
Publisher: ACM
Date: 06-07-2013
Publisher: Springer Berlin Heidelberg
Date: 2010
Publisher: IEEE
Date: 07-2010
Publisher: ACM
Date: 13-07-2019
Publisher: Springer International Publishing
Date: 2016
Publisher: IEEE
Date: 08-2013
Publisher: IEEE
Date: 11-2013
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 08-2014
Publisher: IEEE
Date: 2006
Publisher: World Scientific Pub Co Pte Lt
Date: 08-2013
DOI: 10.1142/S0218213013500243
Abstract: Feature selection is a multi-objective problem with the two main conflicting objectives of minimising the number of features and maximising the classification performance. However, most existing feature selection algorithms are single objective and do not appropriately reflect the actual need. There are a small number of multi-objective feature selection algorithms, which are wrapper based and accordingly are computationally expensive and less general than filter algorithms. Evolutionary computation techniques are particularly suitable for multi-objective optimisation because they use a population of candidate solutions and are able to find multiple non-dominated solutions in a single run. However, the two well-known evolutionary multi-objective algorithms, non-dominated sorting based multi-objective genetic algorithm II (NSGAII) and strength Pareto evolutionary algorithm 2 (SPEA2) have not been applied to filter based feature selection. In this work, based on NSGAII and SPEA2, we develop two multi-objective, filter based feature selection frameworks. Four multi-objective feature selection methods are then developed by applying mutual information and entropy as two different filter evaluation criteria in each of the two proposed frameworks. The proposed multi-objective algorithms are examined and compared with a single objective method and three traditional methods (two filters and one wrapper) on eight benchmark datasets. A decision tree is employed to test the classification performance. Experimental results show that the proposed multi-objective algorithms can automatically evolve a set of non-dominated solutions that include a smaller number of features and achieve better classification performance than using all features. NSGAII and SPEA2 outperform the single objective algorithm, the two traditional filter algorithms and even the traditional wrapper algorithm in terms of both the number of features and the classification performance in most cases. NSGAII achieves similar performance to SPEA2 for the datasets that consist of a small number of features and slightly better results when the number of features is large. This work represents the first study on NSGAII and SPEA2 for filter feature selection in classification problems with both providing field leading classification performance.
Publisher: Elsevier BV
Date: 08-2023
Publisher: ACM
Date: 15-07-2023
Publisher: ACM
Date: 20-07-2016
Publisher: Elsevier BV
Date: 03-2016
Publisher: World Scientific Pub Co Pte Lt
Date: 12-2009
Publisher: Elsevier BV
Date: 03-2021
Publisher: ACM
Date: 25-06-2005
Publisher: MIT Press - Journals
Date: 06-2017
DOI: 10.1162/EVCO_A_00167
Abstract: A main research direction in the field of evolutionary machine learning is to develop a scalable classifier system to solve high-dimensional problems. Recently work has begun on autonomously reusing learned building blocks of knowledge to scale from low-dimensional problems to high-dimensional ones. An XCS-based classifier system, known as XCSCFC, has been shown to be scalable, through the addition of expression tree–like code fragments, to a limit beyond standard learning classifier systems. XCSCFC is especially beneficial if the target problem can be ided into a hierarchy of subproblems and each of them is solvable in a bottom-up fashion. However, if the hierarchy of subproblems is too deep, then XCSCFC becomes impractical because of the needed computational time and thus eventually hits a limit in problem size. A limitation in this technique is the lack of a cyclic representation, which is inherent in finite state machines (FSMs). However, the evolution of FSMs is a hard task owing to the combinatorially large number of possible states, connections, and interaction. Usually this requires supervised learning to minimize inappropriate FSMs, which for high-dimensional problems necessitates subs ling or incremental testing. To avoid these constraints, this work introduces a state-machine-based encoding scheme into XCS for the first time, termed XCSSMA. The proposed system has been tested on six complex Boolean problem domains: multiplexer, majority-on, carry, even-parity, count ones, and digital design verification problems. The proposed approach outperforms XCSCFA (an XCS that computes actions) and XCSF (an XCS that computes predictions) in three of the six problem domains, while the performance in others is similar. In addition, XCSSMA evolved, for the first time, compact and human readable general classifiers (i.e., solving any n-bit problems) for the even-parity and carry problem domains, demonstrating its ability to produce scalable solutions using a cyclic representation.
Publisher: Springer Berlin Heidelberg
Date: 2008
Publisher: IEEE
Date: 07-12-2021
Publisher: Springer International Publishing
Date: 2020
Publisher: IEEE
Date: 06-2013
Publisher: IEEE
Date: 2006
Publisher: IEEE
Date: 06-2012
Publisher: ACM
Date: 07-07-2010
Publisher: IEEE
Date: 08-2020
Publisher: ACM
Date: 12-07-2014
Publisher: ACM
Date: 15-07-2023
Publisher: ACM
Date: 06-07-2013
Publisher: Springer International Publishing
Date: 2014
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 12-2013
Publisher: Elsevier BV
Date: 12-2021
Publisher: ACM
Date: 20-07-2016
Publisher: Elsevier BV
Date: 10-2003
Publisher: Springer International Publishing
Date: 2018
Publisher: Springer International Publishing
Date: 2014
Publisher: IEEE
Date: 06-2012
Publisher: Springer International Publishing
Date: 27-12-2016
Publisher: IEEE
Date: 11-2013
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 08-2021
Publisher: IEEE
Date: 07-2014
Publisher: ACM
Date: 02-07-2018
Publisher: IEEE
Date: 07-2016
Publisher: IEEE
Date: 07-2020
Publisher: ACM
Date: 25-06-2020
Publisher: ACM
Date: 07-2017
Publisher: Springer International Publishing
Date: 2017
Publisher: IEEE
Date: 11-0011
Publisher: Springer Science and Business Media LLC
Date: 11-07-2014
Publisher: ACM
Date: 25-06-2020
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 08-2023
Publisher: IEEE
Date: 28-06-2021
Publisher: Springer Berlin Heidelberg
Date: 2017
Publisher: ACM
Date: 15-07-2023
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 02-2021
Publisher: Springer Science and Business Media LLC
Date: 08-10-2013
Publisher: Elsevier BV
Date: 04-2006
Publisher: Springer International Publishing
Date: 2016
Publisher: Springer Science and Business Media LLC
Date: 15-05-2018
Publisher: ACM
Date: 12-07-2014
Publisher: Springer Berlin Heidelberg
Date: 2003
Publisher: IEEE
Date: 12-2019
Publisher: Springer Science and Business Media LLC
Date: 08-11-2017
Publisher: Elsevier BV
Date: 05-2014
Publisher: IEEE
Date: 07-2018
Publisher: Springer Berlin Heidelberg
Date: 2011
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 08-2023
Publisher: Springer Science and Business Media LLC
Date: 02-05-2020
DOI: 10.1007/S11119-020-09722-6
Abstract: Proximal and remote sensors have proved their effectiveness for the estimation of several biophysical and biochemical variables, including yield, in many different crops. Evaluation of their accuracy in vegetable crops is limited. This study explored the accuracy of proximal hyperspectral and satellite multispectral sensors (Sentinel-2 and WorldView-3) for the prediction of carrot root yield across three growing regions featuring different cropping configurations, seasons and soil conditions. Above ground biomass (AGB), canopy reflectance measurements and corresponding yield measures were collected from 414 s le sites in 24 fields in Western Australia (WA), Queensland (Qld) and Tasmania (Tas), Australia. The optimal sensor (hyperspectral or multispectral) was identified by the highest overall coefficient of determination between yield and different vegetation indices (VIs) whilst linear and non-linear models were tested to determine the best VIs and the impact of the spatial resolution. The optimal regression fit per region was used to extrapolate the point source measurements to all pixels in each s led crop to produce a forecasted yield map and estimate average carrot root yield (t/ha) at the crop level. The latter were compared to commercial carrot root yield (t/ha) obtained from the growers to determine the accuracy of prediction. The measured yield varied from 17 to 113 t/ha across all crops, with forecasts of average yield achieving overall accuracies (% error) of 9.2% in WA, 10.2% in Qld and 12.7% in Tas. VIs derived from hyperspectral sensors produced poorer yield correlation coefficients (R 2 0.1) than similar measures from the multispectral sensors (R 2 0.57, p 0.05). Increasing the spatial resolution from 10 to 1.2 m improved the regression performance by 69%. It is impossible to non-destructively estimate the pre-harvest spatial yield variability of root vegetables such as carrots. Hence, this method of yield forecasting offers great benefit for managing harvest logistics and forward selling decisions.
Publisher: IEEE
Date: 11-2015
Publisher: ACM
Date: 06-07-2013
Publisher: Elsevier BV
Date: 04-2022
Publisher: IEEE
Date: 04-2012
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2016
Publisher: Center for Open Science
Date: 02-06-2021
Abstract: Partial face coverings such as sunglasses and face masks unintentionally obscure facial expressions, causing a loss of accuracy when humans and computer systems attempt to categorise emotion. With the rise of soft computing techniques interacting with humans, it is important to know not just their accuracy, but also the confusion errors being made—do humans make less random/damaging errors than soft computing? We analyzed the impact of sunglasses and different face masks on the ability to categorize emotional facial expressions in humans and computer systems. Computer systems, represented by VGG19, ResNet50, and InceptionV3 deep learning algorithms, and humans assessed images of people with varying emotional facial expressions and with four different types of coverings, i.e. unmasked, with a mask covering the lower face, a partial mask with transparent mouth window, and with sunglasses. The first contribution of this work is that computer systems were found to be better classifiers (98.48%) than humans (82.72%) for faces without covering (& % difference). This difference is due to the significantly lower accuracy in categorizing anger, disgust, and fear expressions by humans (p's & .001). However, the most novel aspect of the work is identifying how soft computing systems make different mistakes to humans on the same data. Humans mainly confuse unclear expressions as neutral emotion, which minimizes affective effects. Conversely, soft techniques often confuse unclear expressions as other emotion categories, which could lead to opposing decisions being made, e.g. a robot categorizing a fearful user as happy. Importantly, the variation in the misclassification can be adjusted by variations in the balance of categories in the training set.
Publisher: Victoria University of Wellington Library
Date: 13-04-2021
DOI: 10.26686/WGTN.14405762.V1
Abstract: No description supplied
Publisher: Springer Berlin Heidelberg
Date: 2008
Publisher: Springer Berlin Heidelberg
Date: 2012
Publisher: Springer International Publishing
Date: 2021
Publisher: ACM
Date: 13-07-2019
Publisher: IEEE
Date: 07-2016
Publisher: IEEE
Date: 11-2010
Publisher: Springer Science and Business Media LLC
Date: 30-09-2012
Publisher: ACM
Date: 08-07-2009
Publisher: ACM
Date: 15-07-2023
Publisher: ACM
Date: 08-07-2020
Publisher: Springer International Publishing
Date: 09-11-2016
Publisher: Springer International Publishing
Date: 2014
Publisher: IEEE
Date: 06-2019
Publisher: Springer Berlin Heidelberg
Date: 2010
Publisher: ACM
Date: 13-07-2019
Publisher: IEEE
Date: 06-2013
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 02-2010
Publisher: ACM
Date: 07-07-2012
Publisher: ACM
Date: 07-07-2010
Publisher: MIT Press - Journals
Date: 12-2014
DOI: 10.1162/EVCO_A_00127
Abstract: Image pattern classification is a challenging task due to the large search space of pixel data. Supervised and subsymbolic approaches have proven accurate in learning a problem’s classes. However, in the complex image recognition domain, there is a need for investigation of learning techniques that allow humans to interpret the learned rules in order to gain an insight about the problem. Learning classifier systems (LCSs) are a machine learning technique that have been minimally explored for image classification. This work has developed the feature pattern classification system (FPCS) framework by adopting Haar-like features from the image recognition domain for feature extraction. The FPCS integrates Haar-like features with XCS, which is an accuracy-based LCS. A major contribution of this work is that the developed framework is capable of producing human-interpretable rules. The FPCS system achieved 91 [Formula: see text] 1% accuracy on the unseen test set of the MNIST dataset. In addition, the FPCS is capable of autonomously adjusting the rotation angle in unaligned images. This rotation adjustment raised the accuracy of FPCS to 95%. Although the performance is competitive with equivalent approaches, this was not as accurate as subsymbolic approaches on this dataset. However, the benefit of the interpretability of rules produced by FPCS enabled us to identify the distribution of the learned angles—a normal distribution around [Formula: see text]—which would have been very difficult in subsymbolic approaches. The analyzable nature of FPCS is anticipated to be beneficial in domains such as speed sign recognition, where underlying reasoning and confidence of recognition needs to be human interpretable.
Publisher: IEEE
Date: 05-2015
Publisher: World Scientific Pub Co Pte Lt
Date: 06-2015
DOI: 10.1142/S146902681550008X
Abstract: Feature selection is an important data preprocessing step in machine learning and data mining, such as classification tasks. Research on feature selection has been extensively conducted for more than 50 years and different types of approaches have been proposed, which include wrapper approaches or filter approaches, and single objective approaches or multi-objective approaches. However, the advantages and disadvantages of such approaches have not been thoroughly investigated. This paper provides a comprehensive study on comparing different types of feature selection approaches, specifically including comparisons on the classification performance and computational time of wrappers and filters, generality of wrapper approaches, and comparisons on single objective and multi-objective approaches. Particle swarm optimization (PSO)-based approaches, which include different types of methods, are used as typical ex les to conduct this research. A total of 10 different feature selection methods and over 7000 experiments are involved. The results show that filters are usually faster than wrappers, but wrappers using a simple classification algorithm can be faster than filters. Wrappers often achieve better classification performance than filters. Feature subsets obtained from wrappers can be general to other classification algorithms. Meanwhile, multi-objective approaches are generally better choices than single objective algorithms. The findings are not only useful for researchers to develop new approaches to addressing new challenges in feature selection, but also useful for real-world decision makers to choose a specific feature selection method according to their own requirements.
Publisher: IEEE
Date: 05-2015
Publisher: Springer Berlin Heidelberg
Date: 2011
Publisher: Elsevier BV
Date: 02-2000
Publisher: ACM
Date: 07-07-2012
Publisher: ACM
Date: 12-07-2011
Publisher: IEEE
Date: 07-2010
Publisher: Springer International Publishing
Date: 2015
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 02-2022
Publisher: ACM
Date: 07-07-2012
Publisher: ACM
Date: 25-06-2020
Publisher: ACM
Date: 06-07-2013
Publisher: IEEE
Date: 28-06-2021
Publisher: IEEE
Date: 09-2009
Publisher: Informa UK Limited
Date: 09-2012
Publisher: IEEE
Date: 04-2014
Publisher: Springer International Publishing
Date: 2018
Publisher: IEEE
Date: 02-08-2020
Publisher: Elsevier BV
Date: 04-2021
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 12-2021
Publisher: IEEE
Date: 07-2016
Publisher: Springer Berlin Heidelberg
Date: 2017
Publisher: IEEE
Date: 07-2016
Publisher: IEEE
Date: 04-2012
Publisher: Springer Berlin Heidelberg
Date: 2017
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 12-2022
Publisher: Springer Berlin Heidelberg
Date: 2017
Publisher: Springer Berlin Heidelberg
Date: 2017
Publisher: Elsevier BV
Date: 06-2017
Publisher: Springer Berlin Heidelberg
Date: 2017
Publisher: Springer Berlin Heidelberg
Date: 2013
Publisher: IEEE
Date: 07-2016
Publisher: Wiley
Date: 02-12-2022
DOI: 10.1002/ROB.22141
Abstract: Accounting for wheel–terrain interaction is crucial for navigation and traction control of mobile robots in outdoor environments and rough terrains. Wheel slip is one of the surface hazards that needs to be detected to mitigate against the risk of losing the robot's controllability or mission failure occurring. The open problems in the Terramechanics field addressed are (1) the need for in situ wheel‐slippage estimation in harsh environments using low‐cost ower and easy to integrate sensors, and (2) removing the need for prior information of the soil, which is not always available. This paper presents a novel slip estimation method that utilizes only two proprioceptive sensors (IMU and wheel encoder) to estimate the wheel slip using deep learning methods. It is experimentally shown to be real‐world feasible in outdoor, uneven terrains without prior soil information assumptions. Comparison with previously used machine learning algorithms for continuous and discrete slip estimation problems show more than 9% and 14% improvement in estimation performance, respectively.
Publisher: IEEE
Date: 09-2008
DOI: 10.1109/HIS.2008.86
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 08-2016
Publisher: ACM
Date: 12-07-2011
Start Date: 2019
End Date: 2019
Funder: United States Department of the Navy
View Funded ActivityStart Date: 08-2021
End Date: 08-2026
Amount: $4,879,415.00
Funder: Australian Research Council
View Funded Activity