ORCID Profile
0000-0001-5839-3765
Current Organisations
UNSW Sydney
,
Commonwealth Scientific and Industrial Research Organisation
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.
Publisher: IEEE
Date: 05-2015
Publisher: ACM
Date: 27-06-2020
Publisher: IEEE
Date: 06-2013
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 09-2020
Publisher: IEEE
Date: 11-2015
DOI: 10.1109/CCBD.2015.33
Publisher: IEEE
Date: 2005
Publisher: Springer Berlin Heidelberg
Date: 2013
Publisher: Association for Computing Machinery (ACM)
Date: 16-06-2020
DOI: 10.1145/3391613
Abstract: UI design is an integral part of software development. For many developers who do not have much UI design experience, exposing them to a large database of real-application UI designs can help them quickly build up a realistic understanding of the design space for a software feature and get design inspirations from existing applications. However, existing keyword-based, image-similarity-based, and component-matching-based methods cannot reliably find relevant high-fidelity UI designs in a large database alike to the UI wireframe that the developers sketch, in face of the great variations in UI designs. In this article, we propose a deep-learning-based UI design search engine to fill in the gap. The key innovation of our search engine is to train a wireframe image autoencoder using a large database of real-application UI designs, without the need for labeling relevant UI designs. We implement our approach for Android UI design search, and conduct extensive experiments with artificially created relevant UI designs and human evaluation of UI design search results. Our experiments confirm the superior performance of our search engine over existing image-similarity or component-matching-based methods and demonstrate the usefulness of our search engine in real-world UI design tasks.
Publisher: Springer International Publishing
Date: 2018
Publisher: No publisher found
Date: 2019
Publisher: IEEE
Date: 09-2008
Publisher: International Joint Conferences on Artificial Intelligence Organization
Date: 08-2019
Abstract: Growing awareness towards ethical use of machine learning (ML) models has created a surge for the development of fair models. Existing work in this regard assumes the presence of sensitive attributes in the data and hence can build classifiers whose decisions remain agnostic to such attributes. However, in the real world settings, the end-user of the ML model is unaware of the training data besides, building custom models is not always feasible. Moreover, utilizing a pre-trained model with high accuracy on certain dataset can not be assumed to be fair. Unknown biases in the training data are the true culprit for unfair models (i.e., disparate performance for groups in the dataset). In this preliminary research, we propose a different lens for building fair models by enabling the user with tools to discover blind spots and biases in a pre-trained model and augment them with corrective measures.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 04-2021
Publisher: IEEE
Date: 10-2017
DOI: 10.1109/LCN.2017.75
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2017
Publisher: IEEE
Date: 07-2007
Publisher: SPIE
Date: 20-05-2009
DOI: 10.1117/12.828598
Publisher: ACM
Date: 29-11-2010
Publisher: Springer Berlin Heidelberg
Date: 2008
Publisher: No publisher found
Date: 2008
Publisher: IEEE
Date: 04-2016
Publisher: IET
Date: 2012
DOI: 10.1049/IC.2012.0031
Publisher: Springer Berlin Heidelberg
Date: 2009
Publisher: ACM
Date: 14-05-2016
Publisher: No publisher found
Date: 2007
Publisher: Springer Berlin Heidelberg
Date: 2007
Publisher: Elsevier BV
Date: 12-2019
Publisher: Cambridge University Press (CUP)
Date: 03-2009
DOI: 10.1017/S0269888909000113
Abstract: This paper develops an ontological basis for evaluating software design methods, based on the situated function–behaviour–structure framework. This framework accounts for the situatedness of designing, viewing it as a dynamic activity driven by interactions between designers and the artefacts being designed. On the basis of this framework, we derive a general evaluation schema that we apply to five software design methods. The ideas presented in this work contribute to a better understanding of design methods, and uncover opportunities for method integration and development.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2019
Publisher: ACM
Date: 11-05-2008
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 12-2018
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 04-2016
Publisher: IEEE
Date: 08-2019
Publisher: IEEE
Date: 06-2014
DOI: 10.1109/DSN.2014.94
Publisher: IEEE
Date: 07-2018
Publisher: ACM
Date: 21-12-2020
Publisher: IET
Date: 2012
DOI: 10.1049/IC.2012.0002
Publisher: ACM
Date: 10-10-2022
Publisher: IEEE
Date: 03-2016
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 05-2016
DOI: 10.1109/MIC.2016.67
Publisher: Springer Science and Business Media LLC
Date: 22-06-2017
DOI: 10.1038/S41598-017-04323-2
Abstract: Strong anisotropic compression with pressure on the remarkable non-linear optical material KBe 2 BO 3 F 2 has been observed with the linear compression coefficient along the c axis found to be about 40 times larger than that along the a axis. An unusual non-monotonic pressure response was observed for the a lattice parameter. The derived bulk modulus of 31 ± 1 GPa indicates that KBe 2 BO 3 F 2 is a very soft oxide material yet with stable structure up to 45 GPa. A combination of high-pressure synchrotron powder X-ray diffraction, high-pressure Raman spectroscopy, and Density Functional Theory calculations points to the mechanism for the unusual pressure response being due to the competition between the K-F bond length and K-F-K bond angle and the coupling between the stretching and twisting vibration modes.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2015
Publisher: Springer International Publishing
Date: 2018
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 09-2020
Publisher: Springer International Publishing
Date: 2018
Publisher: IET
Date: 2012
DOI: 10.1049/IC.2012.0009
Publisher: No publisher found
Date: 2017
Publisher: IEEE
Date: 12-2012
Publisher: No publisher found
Date: 2008
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 03-2018
Publisher: IEEE
Date: 06-2017
DOI: 10.1109/ICWS.2017.54
Publisher: ACM
Date: 20-08-2020
Publisher: Elsevier BV
Date: 07-2006
Publisher: IEEE
Date: 05-2013
Publisher: No publisher found
Date: 2009
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 05-2016
DOI: 10.1109/MS.2016.81
Publisher: Springer Nature Switzerland
Date: 2022
Publisher: Elsevier BV
Date: 05-2019
Publisher: IEEE
Date: 09-2008
Publisher: AIP Publishing
Date: 07-11-2017
DOI: 10.1063/1.5002705
Abstract: Exotic phases of germanium, that form under high pressure but persist under ambient conditions, are of technological interest due to their unique optical and electrical properties. The thermal evolution and stability of two of these exotic Ge phases, the simple tetragonal (st12) and hexagonal diamond (hd) phases, are investigated in detail. These metastable phases, formed by high pressure decompression in either a diamond anvil cell or by nanoindentation, are annealed at temperatures ranging from 280 to 320 °C for st12-Ge and 200 to 550 °C for hd-Ge. In both cases, the exotic phases originated from entirely pure Ge precursor materials. Raman microspectroscopy is used to monitor the phase changes ex situ following annealing. Our results show that hd-Ge synthesized via a pure form of a-Ge first undergoes a subtle change in structure and then an irreversible phase transformation to dc-Ge with an activation energy of (4.3 ± 0.2) eV at higher temperatures. St12-Ge was found to transform to dc-Ge with an activation energy of (1.44 ± 0.08) eV. Taken together with results from previous studies, this study allows for intriguing comparisons with silicon and suggests promising technological applications.
Publisher: No publisher found
Date: 2004
Publisher: IEEE
Date: 09-2015
DOI: 10.1109/SRDS.2015.37
Publisher: No publisher found
Date: 2009
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 06-2018
Publisher: Elsevier BV
Date: 02-2007
Publisher: Springer International Publishing
Date: 2020
Publisher: Springer Science and Business Media LLC
Date: 27-01-2021
Publisher: American Chemical Society (ACS)
Date: 04-04-2017
Publisher: Elsevier BV
Date: 2014
Publisher: No publisher found
Date: 2012
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 06-2018
Publisher: ACM
Date: 10-2013
Publisher: ACM
Date: 27-06-2020
Publisher: ACM
Date: 04-05-2015
Publisher: Elsevier BV
Date: 11-2014
Publisher: ACM
Date: 19-09-2012
Publisher: IEEE
Date: 05-2009
Publisher: Association for Computing Machinery (ACM)
Date: 03-05-2020
DOI: 10.1145/3381833
Abstract: Sharing a pre-trained machine learning model, particularly a deep neural network via prediction APIs, is becoming a common practice on machine learning as a service (MLaaS) platforms nowadays. Although deep neural networks (DNN) have shown remarkable successes in many tasks, they are also criticized for the lack of interpretability and transparency. Interpreting a shared DNN model faces two additional challenges compared with interpreting a general model. (1) Limited training data can be disclosed to users. (2) The internal structure of the models may not be available. These two challenges impede the application of most existing interpretability approaches, such as saliency maps or influence functions, for DNN models. Case-based reasoning methods have been used for interpreting decisions however, how to select and organize the data points under the constraints of shared DNN models is not discussed. Moreover, simply providing cases as explanations may not be sufficient for supporting instance level interpretability. Meanwhile, existing interpretation methods for DNN models generally lack the means to evaluate the reliability of the interpretation. In this article, we propose a framework named Shared Model INTerpreter (SMINT) to address the above limitations. We propose a new data structure called a boundary graph to organize training points to mimic the predictions of DNN models. We integrate local features, such as saliency maps and interpretable input masks, into the data structure to help users to infer the model decision boundaries. We show that the boundary graph is able to address the reliability issues in many local interpretation methods. We further design an algorithm named hidden-layer aware p-test to measure the reliability of the interpretations. Our experiments show that SMINT is able to achieve above 99% fidelity to corresponding DNN models on both MNIST and ImageNet by sharing only a tiny fraction of training data to make these models interpretable. The human pilot study demonstrates that SMINT provides better interpretability compared with existing methods. Moreover, we demonstrate that SMINT is able to assist model tuning for better performance on different user data.
Publisher: IEEE
Date: 07-2010
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 12-2018
Publisher: American Chemical Society (ACS)
Date: 05-07-2017
Publisher: No publisher found
Date: 2015
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2018
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 04-2023
Publisher: Springer International Publishing
Date: 2018
Publisher: ACM
Date: 08-11-2020
Publisher: Springer Berlin Heidelberg
Date: 2007
Publisher: Springer Berlin Heidelberg
Date: 2012
Publisher: IEEE
Date: 2004
Publisher: Springer Berlin Heidelberg
Date: 2010
Publisher: No publisher found
Date: 2017
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 07-2021
Publisher: IEEE
Date: 11-2016
Publisher: Elsevier BV
Date: 03-2019
Publisher: IEEE
Date: 05-2007
DOI: 10.1109/REBSE.2007.2
Publisher: Springer Science and Business Media LLC
Date: 12-2005
Publisher: IEEE Comput. Soc
Date: 2004
Publisher: No publisher found
Date: 2007
Publisher: No publisher found
Date: 2008
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 11-2022
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 11-2016
Publisher: Springer International Publishing
Date: 2021
Publisher: AIP Publishing
Date: 10-07-2017
DOI: 10.1063/1.4993163
Publisher: ACM
Date: 04-07-2018
Publisher: ACM
Date: 21-05-2011
Publisher: American Chemical Society (ACS)
Date: 27-01-2021
Publisher: IEEE
Date: 2008
Publisher: IEEE
Date: 09-2015
DOI: 10.1109/EDCC.2015.15
Publisher: IEEE
Date: 06-2012
Publisher: Springer International Publishing
Date: 2018
Publisher: ACM
Date: 02-05-2010
Publisher: IEEE
Date: 04-2014
Publisher: No publisher found
Date: 2007
Publisher: Springer International Publishing
Date: 2019
Publisher: Springer International Publishing
Date: 2018
Publisher: Fuji Technology Press Ltd.
Date: 20-01-2019
DOI: 10.20965/JACIII.2019.P0146
Abstract: Although the present attendance management system, adopted by universities, determines students’ physical presence. It does not determine whether they perform physical activities. It is important to monitor students’ extracurricular physical exercise scientifically and effectively to solve the actual effect of extracurricular physical exercise attendance and exercise. Calorie management is one solution to this problem. Additionally, an extracurricular physical exercise monitoring and management system is developed to record the energy consumption of students during their physical activities. To realize the demand for the management of calories and the monitoring and analysis of the energy consumption of students through the two development of the energy consumption instrument. This plan has certain significance for solving the actual effect of extracurricular physical training.
Publisher: IEEE
Date: 05-2007
DOI: 10.1109/ULS.2007.6
Publisher: ACM Press
Date: 2005
Publisher: Springer Berlin Heidelberg
Date: 2007
Publisher: IEEE
Date: 09-2015
DOI: 10.1109/EDCC.2015.12
Publisher: IEEE
Date: 2004
Publisher: IEEE
Date: 06-2012
Publisher: Springer International Publishing
Date: 2017
Publisher: ACM
Date: 15-06-2017
Publisher: IEEE
Date: 06-2012
Publisher: No publisher found
Date: 2012
Publisher: International Joint Conferences on Artificial Intelligence Organization
Date: 08-2019
Abstract: Graph deep learning models, such as graph convolutional networks (GCN) achieve state-of-the-art performance for tasks on graph data. However, similar to other deep learning models, graph deep learning models are susceptible to adversarial attacks. However, compared with non-graph data the discrete nature of the graph connections and features provide unique challenges and opportunities for adversarial attacks and defenses. In this paper, we propose techniques for both an adversarial attack and a defense against adversarial attacks. Firstly, we show that the problem of discrete graph connections and the discrete features of common datasets can be handled by using the integrated gradient technique that accurately determines the effect of changing selected features or edges while still benefiting from parallel computations. In addition, we show that an adversarially manipulated graph using a targeted attack statistically differs from un-manipulated graphs. Based on this observation, we propose a defense approach which can detect and recover a potential adversarial perturbation. Our experiments on a number of datasets show the effectiveness of the proposed techniques.
Publisher: Springer Berlin Heidelberg
Date: 2009
Publisher: No publisher found
Date: 2010
Publisher: IEEE
Date: 05-2015
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2019
Publisher: No publisher found
Date: 2018
Publisher: Springer Berlin Heidelberg
Date: 2010
Publisher: IEEE
Date: 08-2016
Publisher: IEEE
Date: 12-2006
Publisher: ACM
Date: 10-05-2008
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2015
DOI: 10.1109/MS.2015.2
Publisher: No publisher found
Date: 2013
Publisher: Association for Computing Machinery (ACM)
Date: 26-02-2018
DOI: 10.1145/3183367
Abstract: Blockchain technology offers a sizable promise to rethink the way interorganizational business processes are managed because of its potential to realize execution without a central party serving as a single point of trust (and failure). To stimulate research on this promise and the limits thereof, in this article, we outline the challenges and opportunities of blockchain for business process management (BPM). We first reflect how blockchains could be used in the context of the established BPM lifecycle and second how they might become relevant beyond. We conclude our discourse with a summary of seven research directions for investigating the application of blockchain technology in the context of BPM.
Publisher: IEEE
Date: 05-2007
DOI: 10.1109/ICSE.2007.73
Publisher: IEEE
Date: 09-2008
DOI: 10.1109/ICWS.2008.74
Publisher: ACM
Date: 20-08-2012
Publisher: IEEE
Date: 09-2008
DOI: 10.1109/EDOC.2008.14
Publisher: ACM
Date: 21-10-2023
Publisher: IEEE
Date: 04-2018
Publisher: IEEE
Date: 09-2007
Publisher: IEEE
Date: 09-2009
Publisher: IEEE
Date: 12-2014
Publisher: Elsevier BV
Date: 08-2013
Publisher: Wiley
Date: 15-07-2016
DOI: 10.1002/SPE.2427
Publisher: No publisher found
Date: 2020
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 09-2018
Publisher: AICIT
Date: 30-11-2011
Publisher: No publisher found
Date: 2007
Publisher: MDPI AG
Date: 05-08-2020
DOI: 10.3390/EN13195179
Abstract: Prompted by rising concern about weak consumer switching and the practice of price discrimination, over the period of 2016–2019, the Office of Gas and Electricity Markets (Ofgem) undertook a series of trials on communication-based interventions to encourage consumer switching in the United Kingdom. The main purpose of this paper is to assess the experience of these Ofgem trials with a view to draw some lessons for policy makers. The analytical framework adopted for this purpose is informed by existing literature on the barriers for consumer switching. The results of the analysis suggest that while the Ofgem trials have made positive impacts on consumer switching, these impacts varied significantly across the trials, suggesting that some interventions were more effective than others. Further, the overall impacts of the Ofgem trials were moderate, as around 70% of participants did not switch suppliers even in the most impactful trial. This reflects a general lack of understanding in the literature about the behaviour-influencing factors, their impacts, and their context-connects. By implication, the difficulty in stimulating consumer switching, as demonstrated by the Ofgem trials, suggests that weak consumer switching and the practice of price discrimination may simply reflect significant competition, rather than a lack of it, especially if retail margins are not greater than the competitive level. In this case, the communication-based intervention aimed at encouraging consumer switching may lead to further price discrimination, especially for the most vulnerable consumers, who are more likely to stay with their incumbent suppliers.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 07-2018
Publisher: No publisher found
Date: 2018
Publisher: IEEE
Date: 04-2007
Publisher: ACM
Date: 21-06-2010
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 11-2023
Publisher: No publisher found
Date: 2000
Publisher: Wiley
Date: 09-11-2021
DOI: 10.1002/SPE.2931
Publisher: No publisher found
Date: 2007
Publisher: Elsevier BV
Date: 09-2011
Publisher: IEEE
Date: 06-2012
Publisher: No publisher found
Date: 2018
Publisher: IEEE
Date: 09-2015
Publisher: Springer Berlin Heidelberg
Date: 2004
Publisher: IEEE
Date: 08-2015
Publisher: IEEE
Date: 06-2016
DOI: 10.1109/DSN.2016.17
Publisher: IEEE
Date: 06-2015
Publisher: IEEE
Date: 09-2015
Publisher: IEEE
Date: 09-2009
Publisher: Springer Berlin Heidelberg
Date: 2008
Publisher: ACM
Date: 11-05-2008
Publisher: IEEE
Date: 2007
Publisher: ACM Press
Date: 2018
Publisher: International Joint Conferences on Artificial Intelligence Organization
Date: 08-2019
Abstract: Multimodal sentiment analysis combines information available from visual, textual, and acoustic representations for sentiment prediction. The recent multimodal fusion schemes combine multiple modalities as a tensor and obtain either the common information by utilizing neural networks, or the unique information by modeling low-rank representation of the tensor. However, both of these information are essential as they render inter-modal and intra-modal relationships of the data. In this research, we first propose a novel deep architecture to extract the common information from the multi-mode representations. Furthermore, we propose unique networks to obtain the modality-specific information that enhances the generalization performance of our multimodal system. Finally, we integrate these two aspects of information via a fusion layer and propose a novel multimodal data fusion architecture, which we call DeepCU (Deep network with both Common and Unique latent information). The proposed DeepCU consolidates the two networks for joint utilization and discovery of all-important latent information. Comprehensive experiments are conducted to demonstrate the effectiveness of utilizing both common and unique information discovered by DeepCU on multiple real-world datasets. The source code of proposed DeepCU is available at verma88/DeepCU-IJCAI19.
Publisher: IEEE
Date: 08-2012
Publisher: No publisher found
Date: 2010
Publisher: Springer International Publishing
Date: 2017
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 03-2015
DOI: 10.1109/MS.2015.23
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 05-2019
Publisher: ACM
Date: 06-07-2022
Publisher: IEEE
Date: 05-2018
Publisher: Elsevier BV
Date: 12-2019
Publisher: Tsinghua University Press
Date: 12-2013
Publisher: No publisher found
Date: 2007
Publisher: ACM
Date: 08-09-2016
Publisher: Springer Science and Business Media LLC
Date: 08-09-2018
Publisher: ACM
Date: 08-04-2019
Publisher: ACM
Date: 21-09-2006
Publisher: IEEE
Date: 11-2017
DOI: 10.1109/ESEM.2017.18
Publisher: ACM
Date: 09-12-2013
Publisher: IEEE
Date: 05-2007
Publisher: Springer Berlin Heidelberg
Date: 2008
Publisher: Elsevier BV
Date: 12-2015
Publisher: IEEE
Date: 2004
Publisher: Springer Berlin Heidelberg
Date: 2009
Publisher: No publisher found
Date: 2018
Publisher: Springer Berlin Heidelberg
Date: 2009
Publisher: Springer Berlin Heidelberg
Date: 2009
Publisher: No publisher found
Date: 2017
Publisher: Springer US
Date: 2007
Publisher: IEEE
Date: 06-2015
DOI: 10.1109/DSN.2015.23
Publisher: Springer Berlin Heidelberg
Date: 2012
Publisher: Springer Science and Business Media LLC
Date: 17-10-2007
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 06-2018
Publisher: Springer Berlin Heidelberg
Date: 2015
Publisher: Springer Berlin Heidelberg
Publisher: Springer Berlin Heidelberg
Date: 2011
Publisher: IEEE
Date: 06-2014
DOI: 10.1109/DSN.2014.63
Publisher: No publisher found
Date: 2007
Publisher: No publisher found
Date: 2008
Publisher: No publisher found
Date: 2010
Publisher: ACM
Date: 10-10-2022
Location: Australia
No related grants have been discovered for Liming Zhu.