Shihu Liu

Shihu Liu

Auto-generated profile, based on publicly available information

Shihu Liu

School of Mathematics and Computer Science, Yunnan Minzu University, Kunming 650504, China

Research Focus & Metrics

Academic Career Length

17Years (2010-Present)

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

Representative Publications

View All Publications
1 March 2021 in IEEE Transactions on Fuzzy Systems
Verified
Journal Article
Closed access
YTYuqing Tang
Yuqing Tang
FYFusheng Yu
Fusheng Yu
WPWitold Pedrycz
Witold Pedrycz
XYXiyang Yang
Xiyang Yang
JWJiayin Wang
Jiayin Wang
SLShihu Liu
Shihu Liu
The existing long-term time-series forecasting methods based on the neural networks suffer from multiple limitations, such as accumulated errors and diminishing temporal correlation, which compromise the prediction quality. To overcome these shortcomings, in this article, we build trend fuzzy granulation-based long short-term memory (LSTM) neural networks to carry out long-term forecasting, where data points with consistent trend characteristics, including trend change, fluctuation range, and trend persistence, are predicted in unison rather than individually. Noticing that these trend characteristics are more urgently needed than just magnitude information, a question on how to granulate a time series into a granular time series consists of meaningful granules containing trend information that comes to be a crucial step. Only if the established granules fit the varying patterns of time series at utmost, such a granulation can make sense for the improvement of the forecasting accuracy; thus, an optimization method of trend-oriented fuzzy granulation is proposed to meliorate the granulation results. With the built trend fuzzy granulation-based LSTM networks, the successive iterations of one-step forecasting are prevented, and the prediction errors of data within a granule will not further increase. This is the first attempt to build trend fuzzy granule-based LSTM to predict the trend characteristics. Experiments on publicly available time series show good performance of the proposed model.

23 October 2023 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
WZWuxia Zhang
Wuxia Zhang
YZYuhang Zhang
Yuhang Zhang
SGShiwen Gao
Shiwen Gao
XLXiaoqiang Lu
Xiaoqiang Lu
YTYi Tang
Yi Tang
SLShihu Liu
Shihu Liu
The multiple change detection (MCD) of hyperspectral images (HSIs) is the process of detecting change areas and providing “from–to” change information of HSIs obtained from the same area at different times. HSIs have hundreds of spectral bands and contain a large amount of spectral information. However, current deep-learning-based MCD methods do not pay special attention to the interspectral dependency and the effective spectral bands of various land covers, which limits the improvement of HSIs’ change detection (CD) performance. To address the above problems, we propose a spectrum-induced transformer-based feature learning (STFL) method for HSIs. The STFL method includes a spectrum-induced transformer-based feature extraction module (STFEM) and an attention-based detection module (ADM). First, the 3D-2D convolutional neural networks (CNNs) are used to extract deep features, and the transformer encoder (TE) is used to calculate self-attention matrices along the spectral dimension in STFEM. Then, the extracted deep features and the learned self-attention matrices are dot-multiplied to generate more discriminative features that take the long-range dependency of the spectrum into account. Finally, ADM mines the effective spectral bands of the difference features learned from STFEM by the attention block (AB) to explore the discrepancy of difference features and uses the softmax function to identify multiple changes. The proposed STFL method is validated on two hyperspectral datasets, and their experiments illustrate the superiority of the proposed STFL method over the currently existing MCD methods.

30 December 2012 in International Journal of Machine Learning and Cybernetics
Verified
Journal Article
Closed access
PDF file
SLShihu Liu
Shihu Liu
FYFusheng Yu
Fusheng Yu
Weihua XuWeihua Xu
Weihua Xu
WZWenxiu Zhang
Wenxiu Zhang

15 June 2023 in Entropy
Verified
Journal Article
Open access
PDF file
SLShihu Liu
Shihu Liu
HGHaiyan Gao
Haiyan Gao
Due to its wide application across many disciplines, how to make an efficient ranking for nodes in graph data has become an urgent topic. It is well-known that most classical methods only consider the local structure information of nodes, but ignore the global structure information of graph data. In order to further explore the influence of structure information on node importance, this paper designs a structure entropy-based node importance ranking method. Firstly, the target node and its associated edges are removed from the initial graph data. Next, the structure entropy of graph data can be constructed by considering the local and global structure information at the same time, in which case all nodes can be ranked. The effectiveness of the proposed method was tested by comparing it with five benchmark methods. The experimental results show that the structure entropy-based node importance ranking method performs well on eight real-world datasets.

1 August 2010
Verified
Conference Paper
Closed access
Weihua XuWeihua Xu
Weihua Xu
SLShihu Liu
Shihu Liu
QWQiaorong Wang
Qiaorong Wang
WZWenxiu Zhang
Wenxiu Zhang
The extension of classical rough set model is a very hot and interesting topic. In this paper, our aim is to present the first type of graded rough set (FGRS) based on rough membership function. The concepts of k-regions, k-rough degree, etc., are proposed firstly, and some of important properties are investigated in this rough set model. Moreover, the model has the corresponding properties with classical rough set model. In addition, relative k-reduction is considered and an example is used to illustrate its validity. By comparing, one can find that the model is a generalization of variable precision rough set model.

19 August 2022 in Entropy
Verified
Journal Article
Open access
PDF file
SLShihu Liu
Shihu Liu
YLYingjie Liu
Yingjie Liu
CYChunsheng Yang
Chunsheng Yang
LDLi Deng
Li Deng
Many similarity measure algorithms of nodes in weighted graph data have been proposed by employing the degree of nodes in recent years. Despite these algorithms obtaining great results, there may be still some limitations. For instance, the strength of nodes is ignored. Aiming at this issue, the relative entropy of the distance distribution based similarity measure of nodes is proposed in this paper. At first, the structural weights of nodes are given by integrating their degree and strength. Next, the distance between any two nodes is calculated with the help of their structural weights and the Euclidean distance formula to further obtain the distance distribution of each node. After that, the probability distribution of nodes is constructed by normalizing their distance distributions. Thus, the relative entropy can be applied to measure the difference between the probability distributions of the top d important nodes and all nodes in graph data. Finally, the similarity of two nodes can be measured in terms of this above-mentioned difference calculated by relative entropy. Experimental results demonstrate that the algorithm proposed by considering the strength of node in the relative entropy has great advantages in the most similar node mining and link prediction.