Aiguo Chen

Prof. Dr. Aiguo Chen


Research Focus & Metrics

Academic Career Length

19Years (2008-Present)

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

Representative Publications

View All Publications
1 March 2012 in Information and Software Technology
Verified
Journal Article
Closed access
YMYing Ma
Ying Ma
GLGuangchun Luo
Guangchun Luo
XZXue Zeng
Xue Zeng
ACAiguo Chen
Aiguo Chen

11 April 2022 in Mathematics
Verified
Journal Article
Open access
PDF file
YLYi Luo
Yi Luo
GLGuangchun Luo
Guangchun Luo
KYKe Yan
Ke Yan
ACAiguo Chen
Aiguo Chen
Following the application of Deep Learning to graphic data, Graph Neural Networks (GNNs) have become the dominant method for Node Classification on graphs in recent years. To assign nodes with preset labels, most GNNs inherit the end-to-end way of Deep Learning in which node features are input to models while labels of pre-classified nodes are used for supervised learning. However, while these methods can make full use of node features and their associations, they treat labels separately and ignore the structural information of those labels. To utilize information on label structures, this paper proposes a method called 3ference that infers from references with differences. Specifically, 3ference predicts what label a node has according to the features of that node in concatenation with both features and labels of its relevant nodes. With the additional information on labels of relevant nodes, 3ference captures the transition pattern of labels between nodes, as subsequent analysis and visualization revealed. Experiments on a synthetic graph and seven real-world graphs proved that this knowledge about label associations helps 3ference to predict accurately with fewer parameters, fewer pre-classified nodes, and varying label patterns compared with GNNs.


8 December 2022 in Mathematics
Verified
Journal Article
Open access
PDF file
YLYi Lv
Yi Lv
QZQichen Zhang
Qichen Zhang
ZWZhenfei Wen
Zhenfei Wen
ACAiguo Chen
Aiguo Chen
All current deep learning-based prediction methods for remaining useful life (RUL) assume that training and testing data have similar distributions, but the existence of various operating conditions, failure modes, and noise lead to insufficient data with similar distributions during the training process, thereby reducing RUL prediction performance. Domain adaptation can effectively solve this problem by learning the cross-domain invariant features of the source domain and target domain to reduce the distribution difference. However, most domain adaptive methods extract the source domain and target domain features into a single space for feature alignment, which may leave out effective information and affect the accuracy of prediction. To address this problem, we propose a data-driven approach named long short-term memory network and multi-representation domain adaptation (LSTM-MRAN). We standardize and process the degraded sensor data with a sliding time window, use LSTM to extract features from the degraded data, and mine the time series information between the data. Then, we use multiple substructures in multi-representation domain adaptation to extract features of the source domain and target domain from different spaces and align features by minimizing conditional maximum mean difference (CMMD) loss functions. The effectiveness of the method is verified by the CMAPSS dataset. Compared with methods without domain adaptation and other transfer learning methods, the proposed method provides more reliable RUL prediction results under datasets with different operating conditions and failure modes.

1 October 2008
Verified
Conference Paper
Closed access
ACAiguo Chen
Aiguo Chen
GXGuoai Xu
Guoai Xu
YYYixian Yang
Yixian Yang
Mobile ad hoc network is a self-organized network made up of mobile devices. It is also often termed an infrastructure-less, spontaneous and dynamic network. Due to the temporary cooperation among nodes, and no enough knowledge between each node in advance, it is difficult to establish trust in ad hoc network. In this paper, a novel cluster-based trust model for ad hoc networks was presented and an inter-cluster recommendation trust concept was introduced. In our model, a network is divided into clusters with one special node each. It establishes trust relationship for internal clusters dynamically based on previous transactions result. From the experiment results, we can see that the model is dynamic and efficient enough to be applicable to in ad hoc networks. Uncertainty problem with nodes coming and going in spontaneous ad hoc environments can be solved well with this model.

1 August 2019 in Information Sciences
Verified
Journal Article
Closed access
XZXu Zheng
Xu Zheng
ACAiguo Chen
Aiguo Chen
GLGuangchun Luo
Guangchun Luo
LTLing Tian
Ling Tian
ZCZhipeng Cai
Zhipeng Cai