Publications by authors named "Raymond Chiong"

11 Publications

  • Page 1 of 1

Low-Cost Pt Alloys for Heterogeneous Catalysis Predicted by Density Functional Theory and Active Learning.

J Phys Chem Lett 2021 Jul 28:7305-7311. Epub 2021 Jul 28.

Discipline of Chemistry, School of Environmental and Life Sciences, The University of Newcastle, Callaghan, New South Wales 2308, Australia.

Pt is a key high-performing catalyst for important chemical conversions, such as biomass conversion and water splitting. Limited Pt reserves, however, demand that we identify more sustainable alternative catalyst materials for these processes. Here, we combine state-of-the-art graph neural networks and crystal graph machine learning representations with active learning to discover new, low-cost Pt alloy catalysts for biomass reforming and hydrogen evolution reactions. We identify 12 Pt-based alloys which have comparable catalytic activity to that of the exemplar Pt(111) surface. Notably, CuPt and FeCuPt exhibit near identical catalytic performance as that of Pt(111). These results demonstrate the potential of machine learning for predicting new catalytic materials without recourse to expensive DFT geometry optimizations, the current bottleneck impeding high-throughput materials discovery. We also examine the performance of -band theory in elucidating trends in binary and ternary Pt alloys.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1021/acs.jpclett.1c01851DOI Listing
July 2021

Low-Cost Pt Alloys for Heterogeneous Catalysis Predicted by Density Functional Theory and Active Learning.

J Phys Chem Lett 2021 Jul 28:7305-7311. Epub 2021 Jul 28.

Discipline of Chemistry, School of Environmental and Life Sciences, The University of Newcastle, Callaghan, New South Wales 2308, Australia.

Pt is a key high-performing catalyst for important chemical conversions, such as biomass conversion and water splitting. Limited Pt reserves, however, demand that we identify more sustainable alternative catalyst materials for these processes. Here, we combine state-of-the-art graph neural networks and crystal graph machine learning representations with active learning to discover new, low-cost Pt alloy catalysts for biomass reforming and hydrogen evolution reactions. We identify 12 Pt-based alloys which have comparable catalytic activity to that of the exemplar Pt(111) surface. Notably, CuPt and FeCuPt exhibit near identical catalytic performance as that of Pt(111). These results demonstrate the potential of machine learning for predicting new catalytic materials without recourse to expensive DFT geometry optimizations, the current bottleneck impeding high-throughput materials discovery. We also examine the performance of -band theory in elucidating trends in binary and ternary Pt alloys.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1021/acs.jpclett.1c01851DOI Listing
July 2021

Deep sequence modelling for Alzheimer's disease detection using MRI.

Comput Biol Med 2021 07 1;134:104537. Epub 2021 Jun 1.

School of Electrical Engineering and Computing, The University of Newcastle, NSW 2308, Australia.

Background: Alzheimer's disease (AD) is one of the deadliest diseases in developed countries. Treatments following early AD detection can significantly delay institutionalisation and extend patients' independence. There has been a growing focus on early AD detection using artificial intelligence. Convolutional neural networks (CNNs) have proven revolutionary for image-based applications and have been applied to brain scans. In recent years, studies have utilised two-dimensional (2D) CNNs on magnetic resonance imaging (MRI) scans for AD detection. To apply a 2D CNN on three-dimensional (3D) MRI volumes, each MRI scan is split into 2D image slices. A CNN is trained over the image slices by calculating a loss function between each subject's label and each image slice's predicted output. Although 2D CNNs can discover spatial dependencies in an image slice, they cannot understand the temporal dependencies among 2D image slices in a 3D MRI volume. This study aims to resolve this issue by modelling the sequence of MRI features produced by a CNN with deep sequence-based networks for AD detection.

Method: The CNN utilised in this paper was ResNet-18 pre-trained on an ImageNet dataset. The employed sequence-based models were the temporal convolutional network (TCN) and different types of recurrent neural networks. Several deep sequence-based models and configurations were implemented and compared for AD detection.

Results: Our proposed TCN model achieved the best classification performance with 91.78% accuracy, 91.56% sensitivity and 92% specificity.

Conclusion: Our results show that applying sequence-based models can improve the classification accuracy of 2D and 3D CNNs for AD detection by up to 10%.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.compbiomed.2021.104537DOI Listing
July 2021

Group and Period-Based Representations for Improved Machine Learning Prediction of Heterogeneous Alloy Catalysts.

J Phys Chem Lett 2021 Jun 25;12(21):5156-5162. Epub 2021 May 25.

Discipline of Chemistry, School of Environmental and Life Sciences, The University of Newcastle, Callaghan, New South Wales 2308, Australia.

Machine learning has recently emerged as an efficient and powerful alternative to density functional theory for studying heterogeneous catalysis. Machine learning methods rely on a geometrical representation of the chemical environment around the catalytic adsorption site based on physical or chemical descriptors. Here, we show that replacing the atomic number in geometrical representations with elemental groups and periods (GP) yields significant improvements in predicted adsorption energies on bimetallic alloy surfaces. Notably, the GP-based Labeled Site Crystal Graph representation reported here achieves mean absolute error (MAE) ∼0.05 eV (near chemical accuracy) in predicting hydrogen adsorption and MAE ∼0.10 eV for other strong binding adsorbates such as carbon, nitrogen, oxygen, and sulfur. We also show GP-based representations to be robust in predicting adsorption on surface facets, elements, and alloys that are not included in the initial training set. This reliability makes GP-based representations an ideal basis for high-throughput approaches and materials discovery based on active learning techniques, which often involve limited training sets.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1021/acs.jpclett.1c01319DOI Listing
June 2021

Using an improved relative error support vector machine for body fat prediction.

Comput Methods Programs Biomed 2021 Jan 15;198:105749. Epub 2020 Sep 15.

Alice Springs Hospital, The Gap, NT 0870, Australia. Electronic address:

Background And Objective: The term 'obesity' refers to excessive body fat, and it is a chronic disease associated with various complications. Although a range of techniques for body fat estimation have been developed to assess obesity, they are typically associated with high-cost tests requiring special equipment. Accurate prediction of the body fat percentage based on easily accessed body measurements is thus important for assessing obesity and its related diseases. This paper presents an improved relative error support vector machine approach to predict body fat in a cost-effective manner.

Methods: Our proposed method introduces a bias error control term into its objective function to obtain an unbiased estimation. Feature selection is also utilised, by removing either redundant or irrelevant features without incurring much loss of information, to further improve the prediction accuracy. In addition, the Wilcoxon rank-sum test is used to validate if the performance of our proposed method is significantly better than other prediction models being compared.

Results: Experimental results based on four evaluation metrics show that the proposed method is able to outperform other prediction models under comparison. Considering the characteristics of different features (e.g., body measurements), we show that applying feature selection can further improve the prediction performance. Statistical analysis carried out confirms that our proposed method has obtained significantly better results than other compared methods.

Conclusions: We have proposed a new approach to predict the body fat percentage effectively. This approach can provide a good reference for people to know their body fat percentage with easily accessed measurements. Statistical test results based on the Wilcoxon rank-sum test not only show that our proposed method has significantly better performance than other prediction models being compared, but also confirm the usefulness of incorporating feature selection into the proposed method.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.cmpb.2020.105749DOI Listing
January 2021

An Evolutionary Game Model with Punishment and Protection to Promote Trust in the Sharing Economy.

Sci Rep 2019 12 24;9(1):19789. Epub 2019 Dec 24.

Einstein Center Digital Future, TU Berlin, 10587, Berlin, Germany.

In this paper, we present an evolutionary trust game, taking punishment and protection into consideration, to investigate the formation of trust in the so-called sharing economy from a population perspective. This sharing economy trust model comprises four types of players: a trustworthy provider, an untrustworthy provider, a trustworthy consumer, and an untrustworthy consumer. Punishment in the form of penalty for untrustworthy providers and protection in the form of insurance for consumers are mechanisms adopted to prevent untrustworthy behaviour. Through comprehensive simulation experiments, we evaluate dynamics of the population for different initial population setups and effects of having penalty and insurance in place. Our results show that each player type influences the 'existence' and 'survival' of other types of players, and untrustworthy players do not necessarily dominate the population even when the temptation to defect (i.e., to be untrustworthy) is high. Additionally, we observe that imposing a heavier penalty or having insurance for all consumers (trustworthy and untrustworthy) can be counterproductive for promoting trustworthiness in the population and increasing the global net wealth. Our findings have important implications for understanding trust in the context of the sharing economy, and for clarifying the usefulness of protection policies within it.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1038/s41598-019-55384-4DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC6930269PMC
December 2019

Deep learning to detect Alzheimer's disease from neuroimaging: A systematic literature review.

Comput Methods Programs Biomed 2020 Apr 27;187:105242. Epub 2019 Nov 27.

The University of Newcastle, University Drive, Callaghan 2308, Australia. Electronic address:

Alzheimer's Disease (AD) is one of the leading causes of death in developed countries. From a research point of view, impressive results have been reported using computer-aided algorithms, but clinically no practical diagnostic method is available. In recent years, deep models have become popular, especially in dealing with images. Since 2013, deep learning has begun to gain considerable attention in AD detection research, with the number of published papers in this area increasing drastically since 2017. Deep models have been reported to be more accurate for AD detection compared to general machine learning techniques. Nevertheless, AD detection is still challenging, and for classification, it requires a highly discriminative feature representation to separate similar brain patterns. This paper reviews the current state of AD detection using deep learning. Through a systematic literature review of over 100 articles, we set out the most recent findings and trends. Specifically, we review useful biomarkers and features (personal information, genetic data, and brain scans), the necessary pre-processing steps, and different ways of dealing with neuroimaging data originating from single-modality and multi-modality studies. Deep models and their performance are described in detail. Although deep learning has achieved notable performance in detecting AD, there are several limitations, especially regarding the availability of datasets and training procedures.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.cmpb.2019.105242DOI Listing
April 2020

Improved Representations of Heterogeneous Carbon Reforming Catalysis Using Machine Learning.

J Chem Theory Comput 2019 Dec 6;15(12):6882-6894. Epub 2019 Nov 6.

School of Information Management , Wuhan University , Wuhan 430072 , China.

Predicting adsorption energies of reaction intermediates is critical for determining catalytic reaction mechanisms. Here, we present three combined representations for predicting adsorption energies of carbon reforming species on transition-metal surfaces. Among the three combined representations, the Elemental Properties and Spectral London Axilrod-Teller-Muto (EP&SLATM) representation, which uses separate EP and SLATM representations for the surface and adsorbates, yields the lowest mean absolute error (MAE) of ∼0.18 eV with respect to density functional theory (DFT) adsorption formation energies for 68 adsorbates on four low-index metal facets (Cu(111), Pt(111), Pd(111), Ru(0001)). All three combined representations also have lower MAEs compared with linear scaling relations. Notably, two of the combined representations achieve their results using empirical/experimental molecular structures only (i.e., without recourse to structural optimization based on first-principles methods such as DFT). The combined representations enable improved efficiency for predicting heterogeneous catalytic mechanisms using machine learning approaches, largely bypassing expensive electronic structure calculations. Further, we show that the combined representations enable "cross-surface" training with regression and tree-based machine learning methods. That is, to predict adsorption formation energies on a particular catalyst metal, these methods only need a small amount of training samples (20%) on that metal.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1021/acs.jctc.9b00420DOI Listing
December 2019

Using support vector machine ensembles for target audience classification on Twitter.

PLoS One 2015 13;10(4):e0122855. Epub 2015 Apr 13.

School of Design, Communication and Information Technology, The University of Newcastle, Callaghan, NSW 2308, Australia.

The vast amount and diversity of the content shared on social media can pose a challenge for any business wanting to use it to identify potential customers. In this paper, our aim is to investigate the use of both unsupervised and supervised learning methods for target audience classification on Twitter with minimal annotation efforts. Topic domains were automatically discovered from contents shared by followers of an account owner using Twitter Latent Dirichlet Allocation (LDA). A Support Vector Machine (SVM) ensemble was then trained using contents from different account owners of the various topic domains identified by Twitter LDA. Experimental results show that the methods presented are able to successfully identify a target audience with high accuracy. In addition, we show that using a statistical inference approach such as bootstrapping in over-sampling, instead of using random sampling, to construct training datasets can achieve a better classifier in an SVM ensemble. We conclude that such an ensemble system can take advantage of data diversity, which enables real-world applications for differentiating prospective customers from the general audience, leading to business advantage in the crowded social media space.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://journals.plos.org/plosone/article?id=10.1371/journal.pone.0122855PLOS
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC4395415PMC
January 2016

A balance-evolution artificial bee colony algorithm for protein structure optimization based on a three-dimensional AB off-lattice model.

Comput Biol Chem 2015 Feb 22;54:1-12. Epub 2014 Nov 22.

College of Biomedical Engineering & Instrument Science, Zhejiang University, Hangzhou 310027, PR China. Electronic address:

Protein structure prediction is a fundamental issue in the field of computational molecular biology. In this paper, the AB off-lattice model is adopted to transform the original protein structure prediction scheme into a numerical optimization problem. We present a balance-evolution artificial bee colony (BE-ABC) algorithm to address the problem, with the aim of finding the structure for a given protein sequence with the minimal free-energy value. This is achieved through the use of convergence information during the optimization process to adaptively manipulate the search intensity. Besides that, an overall degradation procedure is introduced as part of the BE-ABC algorithm to prevent premature convergence. Comprehensive simulation experiments based on the well-known artificial Fibonacci sequence set and several real sequences from the database of Protein Data Bank have been carried out to compare the performance of BE-ABC against other algorithms. Our numerical results show that the BE-ABC algorithm is able to outperform many state-of-the-art approaches and can be effectively employed for protein structure optimization.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.compbiolchem.2014.11.004DOI Listing
February 2015

Incorporating feature ranking and evolutionary methods for the classification of high-dimensional DNA microarray gene expression data.

Australas Med J 2013 30;6(5):272-9. Epub 2013 May 30.

Department of Computing and Information Systems, The University of Melbourne, Victoria 3010, Australia ; IBM Research Australia, Carlton, Victoria 3053, Australia.

Background: DNA microarray gene expression classification poses a challenging task to the machine learning domain. Typically, the dimensionality of gene expression data sets could go from several thousands to over 10,000 genes. A potential solution to this issue is using feature selection to reduce the dimensionality.

Aims: The aim of this paper is to investigate how we can use feature quality information to improve the precision of microarray gene expression classification tasks.

Method: We propose two evolutionary machine learning models based on the eXtended Classifier System (XCS) and a typical feature selection methodology. The first one, which we call FS-XCS, uses feature selection for feature reduction purposes. The second model is GRD-XCS, which uses feature ranking to bias the rule discovery process of XCS.

Results: The results indicate that the use of feature selection/ranking methods is essential for tackling highdimensional classification tasks, such as microarray gene expression classification. However, the results also suggest that using feature ranking to bias the rule discovery process performs significantly better than using the feature reduction method. In other words, using feature quality information to develop a smarter learning procedure is more efficient than reducing the feature set.

Conclusion: Our findings have shown that extracting feature quality information can assist the learning process and improve classification accuracy. On the other hand, relying exclusively on the feature quality information might potentially decrease the classification performance (e.g., using feature reduction). Therefore, we recommend a hybrid approach that uses feature quality information to direct the learning process by highlighting the more informative features, but at the same time not restricting the learning process to explore other features.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.4066/AMJ.2013.1641DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3674418PMC
June 2013
-->