ORCID Profile
0000-0001-9582-3445
Current Organisation
University of Technology Sydney
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.
Information Systems | Database Management | Interorganisational Information Systems and Web Services | Pattern Recognition and Data Mining | Artificial Intelligence and Image Processing | Natural Language Processing
Application Software Packages (excl. Computer Games) | Electronic Information Storage and Retrieval Services | Wholesale and Retail Trade | Information Processing Services (incl. Data Entry and Capture) | Application Tools and System Utilities |
Publisher: Association for Computing Machinery (ACM)
Date: 15-06-2020
DOI: 10.1145/3397323
Abstract: Human activity recognition (HAR) plays an irreplaceable role in various applications and has been a prosperous research topic for years. Recent studies show significant progress in feature extraction (i.e., data representation) using deep learning techniques. However, they face significant challenges in capturing multi-modal spatial-temporal patterns from the sensory data, and they commonly overlook the variants between subjects. We propose a Discriminative Adversarial MUlti-view Network (DAMUN) to address the above issues in sensor-based HAR. We first design a multi-view feature extractor to obtain representations of sensory data streams from temporal, spatial, and spatio-temporal views using convolutional networks. Then, we fuse the multi-view representations into a robust joint representation through a trainable Hadamard fusion module, and finally employ a Siamese adversarial network architecture to decrease the variants between the representations of different subjects. We have conducted extensive experiments under an iterative left-one-subject-out setting on three real-world datasets and demonstrated both the effectiveness and robustness of our approach.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 03-2019
Publisher: Elsevier BV
Date: 2022
Publisher: ACM
Date: 06-07-2022
Publisher: Elsevier BV
Date: 2024
Publisher: Springer International Publishing
Date: 2022
Publisher: Springer International Publishing
Date: 2022
Publisher: IEEE
Date: 23-05-2022
Publisher: Elsevier BV
Date: 11-2020
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 08-2022
Publisher: IEEE
Date: 18-07-2021
Publisher: ACM
Date: 27-02-2023
Publisher: Springer International Publishing
Date: 2019
Publisher: IEEE
Date: 05-11-2020
Publisher: Oxford University Press (OUP)
Date: 19-05-2022
Abstract: Recommendation is a critical tool for developing and promoting the benefits of the Internet of Things (IoT). In recent years, recommender systems have attracted considerable attention in many IoT-related fields such as smart health, smart home, smart tourism and smart marketing. However, traditional recommender system approaches fail to exploit ever-growing, dynamic and heterogeneous IoT data in building recommender systems for the IoT (RSIoT). This article aims to provide a comprehensive review of state-of-the-art RSIoT, including the related techniques, applications and a discussion on the limitations of applying recommendation systems to IoT. Finally, we propose a reference framework for comparing existing studies to guide future research and practices.
Publisher: Springer International Publishing
Date: 2019
Publisher: Springer Science and Business Media LLC
Date: 29-09-2020
Publisher: Springer International Publishing
Date: 2018
Publisher: Springer Science and Business Media LLC
Date: 07-2018
Publisher: Springer Science and Business Media LLC
Date: 04-06-2018
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2023
Publisher: ACM
Date: 20-08-2020
Publisher: Springer International Publishing
Date: 2021
Publisher: ACM
Date: 16-10-2020
Publisher: ACM
Date: 18-07-2023
Publisher: ACM
Date: 17-10-2022
Publisher: IOP Publishing
Date: 05-03-2021
Abstract: Brain signals refer to the biometric information collected from the human brain. The research on brain signals aims to discover the underlying neurological or physical status of the in iduals by signal decoding. The emerging deep learning techniques have improved the study of brain signals significantly in recent years. In this work, we first present a taxonomy of non-invasive brain signals and the basics of deep learning algorithms. Then, we provide the frontiers of applying deep learning for non-invasive brain signals analysis, by summarizing a large number of recent publications. Moreover, upon the deep learning-powered brain signal studies, we report the potential real-world applications which benefit not only disabled people but also normal in iduals. Finally, we discuss the opening challenges and future directions.
Publisher: Springer Science and Business Media LLC
Date: 23-03-2018
Publisher: Elsevier BV
Date: 04-2020
Publisher: IEEE
Date: 02-05-2022
Publisher: MDPI AG
Date: 28-11-2021
DOI: 10.3390/FI13120305
Abstract: Recommendation systems are crucial in the provision of services to the elderly with Alzheimer’s disease in IoT-based smart home environments. In this work, a Reminder Care System (RCS) is presented to help Alzheimer patients live in and operate their homes safely and independently. A contextual bandit approach is utilized in the formulation of the proposed recommendation system to tackle dynamicity in human activities and to construct accurate recommendations that meet user needs without their feedback. The system was evaluated based on three public datasets using a cumulative reward as a metric. Our experimental results demonstrate the feasibility and effectiveness of the proposed Reminder Care System for real-world IoT-based smart home applications.
Publisher: Association for Computing Machinery (ACM)
Date: 05-02-2018
DOI: 10.1145/3134438
Abstract: Point-of-Interest (POI) recommendation is a new type of recommendation task that comes along with the prevalence of location-based social networks and services in recent years. Compared with traditional recommendation tasks, POI recommendation focuses more on making personalized and context-aware recommendations to improve user experience. Traditionally, the most commonly used contextual information includes geographical and social context information. However, the increasing availability of check-in data makes it possible to design more effective location recommendation applications by modeling and integrating comprehensive types of contextual information, especially the temporal information. In this article, we propose a collaborative filtering method based on Tensor Factorization, a generalization of the Matrix Factorization approach, to model the multi-dimensional contextual information. Tensor Factorization naturally extends Matrix Factorization by increasing the dimensionality of concerns, within which the three-dimensional model is the one most popularly used. Our method exploits a high-order tensor to fuse heterogeneous contextual information about users’ check-ins instead of the traditional two-dimensional user-location matrix. The factorization of this tensor leads to a more compact model of the data that is naturally suitable for integrating contextual information to make POI recommendations. Based on the model, we further improve the recommendation accuracy by utilizing the internal relations within users and locations to regularize the latent factors. Experimental results on a large real-world dataset demonstrate the effectiveness of our approach.
Publisher: IEEE
Date: 11-2019
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 09-2020
Publisher: Springer International Publishing
Date: 2022
Publisher: IGI Global
Date: 2012
Abstract: The web has undergone a tremendous shift from information repository to the provisioning capacity of services. As an effective means of constructing coarse-grained solutions by dynamically aggregating a set of services to satisfy complex requirements, traditional service composition suffers from dramatic decrease on the efficiency of determining the optimal solution when large scale services are available in the Internet based service market. Most current approaches look for the optimal composition solution by real-time computation, and the composition efficiency greatly depends on the adopted algorithms. To eliminate such deficiency, this paper proposes a semi-empirical composition approach which incorporates the extraction of empirical evidence from historical experiences to provide guidance to solution space reduction to real-time service selection. Service communities and historical requirements are further organized into clusters based on similarity measurement, and then the probabilistic correspondences between the two types of clusters are identified by statistical analysis. For each new request, its hosting requirement cluster would be identified and corresponding service clusters would be determined by leveraging Bayesian inference. Concrete services would be selected from the reduced solution space to constitute the final composition. Timing strategies for re-clustering and consideration to special cases in clustering ensures continual adaption of the approach to changing environment. Instead of relying solely on pure real-time computation, the approach distinguishes from traditional methods by combining the two perspectives together.
Publisher: ACM
Date: 05-11-2018
Publisher: IEEE
Date: 05-2022
Publisher: IEEE
Date: 12-2021
Publisher: Springer Science and Business Media LLC
Date: 28-04-2018
Publisher: Frontiers Media SA
Date: 03-05-2022
DOI: 10.3389/FDATA.2022.822783
Abstract: Adversarial attacks, e.g., adversarial perturbations of the input and adversarial s les, pose significant challenges to machine learning and deep learning techniques, including interactive recommendation systems. The latent embedding space of those techniques makes adversarial attacks challenging to detect at an early stage. Recent advance in causality shows that counterfactual can also be considered one of the ways to generate the adversarial s les drawn from different distribution as the training s les. We propose to explore adversarial ex les and attack agnostic detection on reinforcement learning (RL)-based interactive recommendation systems. We first craft different types of adversarial ex les by adding perturbations to the input and intervening on the casual factors. Then, we augment recommendation systems by detecting potential attacks with a deep learning-based classifier based on the crafted data. Finally, we study the attack strength and frequency of adversarial ex les and evaluate our model on standard datasets with multiple crafting methods. Our extensive experiments show that most adversarial attacks are effective, and both attack strength and attack frequency impact the attack performance. The strategically-timed attack achieves comparative attack performance with only 1/3 to 1/2 attack frequency. Besides, our white-box detector trained with one crafting method has the generalization ability over several other crafting methods.
Publisher: Elsevier BV
Date: 04-2020
Publisher: IEEE
Date: 07-2022
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2022
Publisher: IEEE
Date: 07-2020
Publisher: Springer Science and Business Media LLC
Date: 14-01-2022
Publisher: Institute of Electronics, Information and Communications Engineers (IEICE)
Date: 2019
Publisher: Elsevier BV
Date: 08-2022
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2021
Publisher: Association for the Advancement of Artificial Intelligence (AAAI)
Date: 17-07-2019
DOI: 10.1609/AAAI.V33I01.33018690
Abstract: Object detection is important in real-world applications. Existing methods mainly focus on object detection with sufficient labelled training data or zero-shot object detection with only concept names. In this paper, we address the challenging problem of zero-shot object detection with natural language description, which aims to simultaneously detect and recognize novel concept instances with textual descriptions. We propose a novel deep learning framework to jointly learn visual units, visual-unit attention and word-level attention, which are combined to achieve word-proposal affinity by an element-wise multiplication. To the best of our knowledge, this is the first work on zero-shot object detection with textual descriptions. Since there is no directly related work in the literature, we investigate plausible solutions based on existing zero-shot object detection for a fair comparison. We conduct extensive experiments on three challenging benchmark datasets. The extensive experimental results confirm the superiority of the proposed model.
Publisher: Elsevier BV
Date: 02-2020
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 03-2021
Publisher: IEEE
Date: 12-2021
Publisher: Springer Science and Business Media LLC
Date: 18-01-2018
Publisher: Elsevier BV
Date: 04-2020
Publisher: Elsevier BV
Date: 02-2021
Publisher: Elsevier BV
Date: 03-2017
Publisher: ACM
Date: 30-04-2023
Publisher: ACM
Date: 17-10-2022
Publisher: Elsevier BV
Date: 05-2022
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 02-2017
Publisher: Springer Science and Business Media LLC
Date: 27-01-2021
Publisher: Springer International Publishing
Date: 2022
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 10-2023
Publisher: Springer Science and Business Media LLC
Date: 22-08-2019
Publisher: Association for Computing Machinery (ACM)
Date: 11-09-2020
DOI: 10.1145/3411749
Abstract: Truth discovery has been widely studied in recent years as a fundamental means for resolving the conflicts in multi-source data. Although many truth discovery methods have been proposed based on different considerations and intuitions, investigations show that no single method consistently outperforms the others. To select the right truth discovery method for a specific application scenario, it becomes essential to evaluate and compare the performance of different methods. A drawback of current research efforts is that they commonly assume the availability of certain ground truth for the evaluation of methods. However, the ground truth may be very limited or even impossible to obtain, rendering the evaluation biased. In this article, we present CompTruthHyp , a generic approach for comparing the performance of truth discovery methods without using ground truth. In particular, our approach calculates the probability of observations in a dataset based on the output of different methods. The probability is then ranked to reflect the performance of these methods. We review and compare 12 representative truth discovery methods and consider both single-valued and multi-valued objects. The empirical studies on both real-world and synthetic datasets demonstrate the effectiveness of our approach for comparing truth discovery methods.
Publisher: Association for the Advancement of Artificial Intelligence (AAAI)
Date: 18-05-2021
DOI: 10.1609/AAAI.V35I10.17057
Abstract: Zero-shot learning (ZSL) refers to the problem of learning to classify instances from novel classes (unseen) that are absent in the training set (seen). Most ZSL methods infer the correlation between visual features and attributes to train the classifier for unseen classes. They may have a strong bias towards seen classes during training. Meta-learning has been introduced to mitigate the basis, but meta-ZSL methods are inapplicable when tasks used for training are s led from erse distributions. In this regard, we propose a novel Task-aligned Generative Meta-learning model for Zero-shot learning (TGMZ), aiming to mitigate the potentially biased training and to enable meta-ZSL to accommodate real-world datasets that contain erse distributions. Specifically, TGMZ incorporates an attribute-conditioned task-wise distribution alignment network that projects tasks into a unified distribution to deliver an unbiased model. Our experiments show TGMZ achieves a relative improvement of 2.1%, 3.0%, 2.5%, and 7.6% over state-of-the-art algorithms on AWA1, AWA2, CUB, and aPY datasets, respectively. Overall, TGMZ outperforms competitors by 3.6% in the generalized zero-shot learning (GZSL) setting and 7.9% in our proposed fusion-ZSL setting.
Publisher: IEEE
Date: 07-2020
Publisher: Springer International Publishing
Date: 2019
Publisher: Springer International Publishing
Date: 2020
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2021
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2019
Publisher: Springer International Publishing
Date: 2018
Publisher: Elsevier BV
Date: 08-2021
Publisher: Springer Science and Business Media LLC
Date: 06-03-2018
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2022
Publisher: International Joint Conferences on Artificial Intelligence Organization
Date: 08-2019
Abstract: Multi-step passenger demand forecasting is a crucial task in on-demand vehicle sharing services. However, predicting passenger demand is generally challenging due to the nonlinear and dynamic spatial-temporal dependencies. In this work, we propose to model multi-step citywide passenger demand prediction based on a graph and use a hierarchical graph convolutional structure to capture both spatial and temporal correlations simultaneously. Our model consists of three parts: 1) a long-term encoder to encode historical passenger demands 2) a short-term encoder to derive the next-step prediction for generating multi-step prediction 3) an attention-based output module to model the dynamic temporal and channel-wise information. Experiments on three real-world datasets show that our model consistently outperforms many baseline methods and state-of-the-art models.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 09-2022
Publisher: ACM
Date: 06-07-2022
Publisher: ACM
Date: 25-07-2020
Publisher: Springer Science and Business Media LLC
Date: 2022
DOI: 10.1007/S11280-021-00992-2
Abstract: The ability to explain why the model produced results in such a way is an important problem, especially in the medical domain. Model explainability is important for building trust by providing insight into the model prediction. However, most existing machine learning methods provide no explainability, which is worrying. For instance, in the task of automatic depression prediction, most machine learning models lead to predictions that are obscure to humans. In this work, we propose explainable Multi-Aspect Depression Detection with Hierarchical Attention Network MDHAN , for automatic detection of depressed users on social media and explain the model prediction. We have considered user posts augmented with additional features from Twitter. Specifically, we encode user posts using two levels of attention mechanisms applied at the tweet-level and word-level, calculate each tweet and words’ importance, and capture semantic sequence features from the user timelines (posts). Our hierarchical attention model is developed in such a way that it can capture patterns that leads to explainable results. Our experiments show that MDHAN outperforms several popular and robust baseline methods, demonstrating the effectiveness of combining deep learning with multi-aspect features. We also show that our model helps improve predictive performance when detecting depression in users who are posting messages publicly on social media. MDHAN achieves excellent performance and ensures adequate evidence to explain the prediction.
Publisher: IEEE
Date: 29-10-2021
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 10-2023
Publisher: Computers, Materials and Continua (Tech Science Press)
Date: 2019
Publisher: IEEE
Date: 11-2022
Publisher: Springer International Publishing
Date: 2019
Publisher: Springer Science and Business Media LLC
Date: 09-06-2022
DOI: 10.1007/S11280-022-01046-X
Abstract: Personalized decision-making can be implemented in a Federated learning (FL) framework that can collaboratively train a decision model by extracting knowledge across intelligent clients, e.g. smartphones or enterprises. FL can mitigate the data privacy risk of collaborative training since it merely collects local gradients from users without access to their data. However, FL is fragile in the presence of statistical heterogeneity that is commonly encountered in personalized decision making, e.g., non-IID data over different clients. Existing FL approaches usually update a single global model to capture the shared knowledge of all users by aggregating their gradients, regardless of the discrepancy between their data distributions. By comparison, a mixture of multiple global models could capture the heterogeneity across various clients if assigning the client to different global models (i.e., centers) in FL. To this end, we propose a novel multi-center aggregation mechanism to cluster clients using their models’ parameters. It learns multiple global models from data as the cluster centers, and simultaneously derives the optimal matching between users and centers. We then formulate it as an optimization problem that can be efficiently solved by a stochastic expectation maximization (EM) algorithm. Experiments on multiple benchmark datasets of FL show that our method outperforms several popular baseline methods. The experimental source codes are publicly available on the Github repository (GitHub repository: ingxuts/multi-center-fed-learning ).
Publisher: ACM
Date: 27-02-2023
Publisher: International Joint Conferences on Artificial Intelligence Organization
Date: 07-2020
Abstract: Zero-shot object detection (ZSD) has received considerable attention from the community of computer vision in recent years. It aims to simultaneously locate and categorize previously unseen objects during inference. One crucial problem of ZSD is how to accurately predict the label of each object proposal, i.e. categorizing object proposals, when conducting ZSD for unseen categories. Previous ZSD models generally relied on learning an embedding from visual space to semantic space or learning a joint embedding between semantic description and visual representation. As the features in the learned semantic space or the joint projected space tend to suffer from the hubness problem, namely the feature vectors are likely embedded to an area of incorrect labels, and thus it will lead to lower detection precision. In this paper, instead, we propose to learn a deep embedding from the semantic space to the visual space, which enables to well alleviate the hubness problem, because, compared with semantic space or joint embedding space, the distribution in visual space has smaller variance. After learning a deep embedding model, we perform $k$ nearest neighbor search in the visual space of unseen categories to determine the category of each semantic description. Extensive experiments on two public datasets show that our approach significantly outperforms the existing methods.
Publisher: Springer International Publishing
Date: 2021
Publisher: IEEE
Date: 29-10-2021
Publisher: Springer International Publishing
Date: 2021
Publisher: Scientific Research Publishing, Inc.
Date: 2009
Publisher: ACM
Date: 03-11-2019
Publisher: Springer Science and Business Media LLC
Date: 04-02-2019
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 07-2022
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 05-2019
Publisher: IEEE
Date: 07-2022
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 05-2019
Publisher: IEEE
Date: 07-2019
Publisher: Emerald
Date: 14-08-2017
Abstract: This paper aims to propose a system for generating actionable knowledge from Big Data and use this system to construct a comprehensive knowledge base (KB), called GrandBase. In particular, this study extracts new predicates from four types of data sources, namely, Web texts, Document Object Model (DOM) trees, existing KBs and query stream to augment the ontology of the existing KB (i.e. Freebase). In addition, a graph-based approach to conduct better truth discovery for multi-valued predicates is also proposed. Empirical studies demonstrate the effectiveness of the approaches presented in this study and the potential of GrandBase. The future research directions regarding GrandBase construction and extension has also been discussed. To revolutionize our modern society by using the wisdom of Big Data, considerable KBs have been constructed to feed the massive knowledge-driven applications with Resource Description Framework triples. The important challenges for KB construction include extracting information from large-scale, possibly conflicting and different-structured data sources (i.e. the knowledge extraction problem) and reconciling the conflicts that reside in the sources (i.e. the truth discovery problem). Tremendous research efforts have been contributed on both problems. However, the existing KBs are far from being comprehensive and accurate: first, existing knowledge extraction systems retrieve data from limited types of Web sources second, existing truth discovery approaches commonly assume each predicate has only one true value. In this paper, the focus is on the problem of generating actionable knowledge from Big Data. A system is proposed, which consists of two phases, namely, knowledge extraction and truth discovery, to construct a broader KB, called GrandBase.
Publisher: Springer Science and Business Media LLC
Date: 05-05-2022
DOI: 10.1007/S44230-022-00001-3
Abstract: The increasingly developed online platform generates a large amount of online reviews every moment, e.g., Yelp and Amazon. Consumers gradually develop the habit of reading previous reviews before making a decision of buying or choosing various products. Online reviews play an vital part in determining consumers’ purchase choices in e-commerce, yet many online reviews are intentionally created to confuse or mislead potential consumers. Moreover, driven by product reputations and merchants’ profits, more and more spam reviews were inserted into online platform. This kind of reviews can be positive, negative or neutral, but they had common features: misleading consumers or damaging reputations. In the past decade, many people conducted research on detecting spam reviews using statistical or deep learning method with various datasets. In view of that, this article first introduces the task of spam online reviews detection and makes a common definition of spam reviews. Then, we comprehensively conclude the existing method and available datasets. Third, we summarize the existing network-based approaches in dealing with this task and propose some direction for future research.
Publisher: IEEE
Date: 07-2020
Start Date: 12-2019
End Date: 12-2023
Amount: $600,000.00
Funder: Australian Research Council
View Funded ActivityStart Date: 11-2019
End Date: 11-2023
Amount: $368,446.00
Funder: Australian Research Council
View Funded ActivityStart Date: 03-2022
End Date: 03-2025
Amount: $405,000.00
Funder: Australian Research Council
View Funded ActivityStart Date: 04-2022
End Date: 02-2024
Amount: $538,350.00
Funder: Australian Research Council
View Funded Activity