Chi-Man Vong

Chi-Man Vong

Auto-generated profile, based on publicly available information

Chi-Man Vong

University of Macau, Macau, China

Research Focus & Metrics

Academic Career Length

22Years (2005-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
3 September 2018 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
ZHZhizhong Han
Zhizhong Han
MSMingyang Shang
Mingyang Shang
ZLZhenbao Liu
Zhenbao Liu
CVChi-Man Vong
Chi-Man Vong
Yu-Shen LiuYu-Shen Liu
Yu-Shen Liu
CCC. L. Philip Chen
C. L. Philip Chen
Learning 3D global features by aggregating multiple views has been introduced as a successful strategy for 3D shape analysis. In recent deep learning models with end-to-end training, pooling is a widely adopted procedure for view aggregation. However, pooling merely retains the max or mean value over all views, which disregards the content information of almost all views and also the spatial information among the views. To resolve these issues, we propose Sequential Views To Sequential Labels (SeqViews2SeqLabels) as a novel deep learning model with an encoder-decoder structure based on recurrent neural networks (RNNs) with attention. SeqViews2SeqLabels consists of two connected parts, an encoder-RNN followed by a decoder-RNN, that aim to learn the global features by aggregating sequential views and then performing shape classification from the learned global features, respectively. Specifically, the encoder-RNN learns the global features by simultaneously encoding the spatial and content information of sequential views, which captures the semantics of the view sequence. With the proposed prediction of sequential labels, the decoder-RNN performs more accurate classification using the learned global features by predicting sequential labels step by step. Learning to predict sequential labels provides more and finer discriminative information among shape classes to learn, which alleviates the overfitting problem inherent in training using a limited number of 3D shapes. Moreover, we introduce an attention mechanism to further improve the discriminative ability of SeqViews2SeqLabels. This mechanism increases the weight of views that are distinctive to each shape class, and it dramatically reduces the effect of selecting the first view position. Shape classification and retrieval results under three large-scale benchmarks verify that SeqViews2SeqLabels learns more discriminative global features by more effectively aggregating sequential views than state-of-the-art methods.

12 March 2019 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
ZHZhizhong Han
Zhizhong Han
HLHonglei Lu
Honglei Lu
Zhenbao LiuZhenbao Liu
Zhenbao Liu
CVChi-Man Vong
Chi-Man Vong
Yu-Shen LiuYu-Shen Liu
Yu-Shen Liu
CCC.L. Philip Chen
C.L. Philip Chen
Learning 3D global features by aggregating multiple views is important. Pooling is widely used to aggregate views in deep learning models. However, pooling disregards a lot of content information within views and the spatial relationship among the views, which limits the discriminability of learned features. To resolve this issue, 3D to Sequential Views (3D2SeqViews) is proposed to more effectively aggregate the sequential views using convolutional neural networks with a novel hierarchical attention aggregation. Specifically, the content information within each view is first encoded. Then, the encoded view content information and the sequential spatiality among the views are simultaneously aggregated by the hierarchical attention aggregation, where view-level attention and class-level attention are proposed to hierarchically weight sequential views and shape classes. View-level attention is learned to indicate how much attention is paid to each view by each shape class, which subsequently weights sequential views through a novel recursive view integration. Recursive view integration learns the semantic meaning of view sequence, which is robust to the first view position. Furthermore, class-level attention is introduced to describe how much attention is paid to each shape class, which innovatively employs the discriminative ability of the fine-tuned network. 3D2SeqViews learns more discriminative features than the state-of-the-art, which leads to the outperforming results in shape classification and retrieval under three large-scale benchmarks.

20 February 2020 in IEEE Transactions on Cybernetics
Verified
Journal Article
Closed access
JDJie Du
Jie Du
CVChi-Man Vong
Chi-Man Vong
CCC.L. Philip Chen
C.L. Philip Chen
High accuracy of text classification can be achieved through simultaneous learning of multiple information, such as sequence information and word importance. In this article, a kind of flat neural networks called the broad learning system (BLS) is employed to derive two novel learning methods for text classification, including recurrent BLS (R-BLS) and long short-term memory (LSTM)-like architecture: gated BLS (G-BLS). The proposed two methods possess three advantages: 1) higher accuracy due to the simultaneous learning of multiple information, even compared to deep LSTM that extracts deeper but single information only; 2) significantly faster training time due to the noniterative learning in BLS, compared to LSTM; and 3) easy integration with other discriminant information for further improvement. The proposed methods have been evaluated over 13 real-world datasets from various types of text classification. From the experimental results, the proposed methods achieve higher accuracies than LSTM while taking significantly less training time on most evaluated datasets, especially when the LSTM is in deep architecture. Compared to R-BLS, G-BLS has an extra forget gate to control the flow of information (similar to LSTM) to further improve the accuracy on text classification so that G-BLS is more effective while R-BLS is more efficient.

29 December 2016 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
CWChi Man Wong
Chi Man Wong
CVChi Man Vong
Chi Man Vong
Pak Kin WongPak Kin Wong
Pak Kin Wong
JCJiuwen Cao
Jiuwen Cao
Recently, multilayer extreme learning machine (ML-ELM) was applied to stacked autoencoder (SAE) for representation learning. In contrast to traditional SAE, the training time of ML-ELM is significantly reduced from hours to seconds with high accuracy. However, ML-ELM suffers from several drawbacks: 1) manual tuning on the number of hidden nodes in every layer is an uncertain factor to training time and generalization; 2) random projection of input weights and bias in every layer of ML-ELM leads to suboptimal model generalization; 3) the pseudoinverse solution for output weights in every layer incurs relatively large reconstruction error; and 4) the storage and execution time for transformation matrices in representation learning are proportional to the number of hidden layers. Inspired by kernel learning, a kernel version of ML-ELM is developed, namely, multilayer kernel ELM (ML-KELM), whose contributions are: 1) elimination of manual tuning on the number of hidden nodes in every layer; 2) no random projection mechanism so as to obtain optimal model generalization; 3) exact inverse solution for output weights is guaranteed under invertible kernel matrix, resulting to smaller reconstruction error; and 4) all transformation matrices are unified into two matrices only, so that storage can be reduced and may shorten model execution time. Benchmark data sets of different sizes have been employed for the evaluation of ML-KELM. Experimental results have verified the contributions of the proposed ML-KELM. The improvement in accuracy over benchmark data sets is up to 7%.

17 January 2019 in IEEE Access
Verified
Journal Article
Open access
Zhen JiaZhen Jia
Zhen Jia
Zhenbao LiuZhenbao Liu
Zhenbao Liu
CVChi-Man Vong
Chi-Man Vong
Michael Gerard PechtMichael Gerard Pecht
Michael Gerard Pecht
Rotating machinery plays a vital role in industrial systems, in which unexpected mechanical faults during operation can lead to severe consequences. For fault prevention, many fault diagnostic methods based on vibration signals are available in the literature. However, vibration signals are obtained by using different types of sensors, which can cause sensor installation issues and damage the rotating machinery. In addition, this kind of data acquisition via vibration signal induces a large amount of signal noise during machine operation, which will challenge the later fault diagnosis. A recent fault detection method based on infrared thermography (IRT) for rotating machinery avoids these issues. However, the corresponding literature is limited by the fact that the characteristics of the manual design cannot fully characterize the fault, so that the diagnostic accuracy cannot exceed the diagnostic method based on the vibration signals. This paper introduces a popular image feature extraction method into the fault diagnosis of rotating machinery based on IRT for the first time. Capturing the IRT images of the rotating machinery in different states firstly, and then two popular feature extraction methods for IRT images, bag-of-visual-word (BoVW), and convolutional neural network (CNN), are tested in turn. Finally, the extracted features are classified to implement automatic fault diagnosis. The developed method is applied to analyze the experimental IRT images collected from bearings, and the results demonstrate that the developed method is more effective than the traditional methods based on vibration signals.

4 April 2017 in IEEE Transactions on Industrial Informatics
Verified
Journal Article
Closed access
ZLZhenbao Liu
Zhenbao Liu
ZJZhen Jia
Zhen Jia
CVChi-Man Vong
Chi-Man Vong
SBShuhui Bu
Shuhui Bu
JHJunwei Han
Junwei Han
XTXiaojun Tang
Xiaojun Tang
Fault detection and isolation (FDI) is very difficult for electronics-rich analog systems due to its sophisticated mechanism and variable operational conditions. Traditionally, FDI in such systems is done through the monitoring of deviation of output signals in voltage or current at system level, which commonly arises from the degradation of one or more critical components. Therefore, FDI can be transformed to a multiclass classification task given the extracted features of the output signals in voltage or current of the circuit. Traditional feature extraction on the circuit output is mostly based on time-domain, frequency-domain, or time-frequency signal processing, which collapse high-dimensional raw signals into a lower dimensional feature set. Such low-dimensional feature set usually suffers from information loss so as to affect the accuracy of the later fault diagnosis. In order to retain as much information as possible, deep learning is proposed which employs a hierarchical structure to capture the different levels of semantic representations of the signals. In this paper, a novel fault diagnostic application of Gaussian-Bernoulli deep belief network (GB-DBN) for electronics-rich analog systems is developed which can more effectively capture the high-order semantic features within the raw output signals. The novel fault diagnosis is validated experimentally on two typical analog filter circuits. Experimental results show the fault diagnosis based on GB-DBN is with superior diagnostic performance than the traditional feature extraction methods.