Tong Liu

Tong Liu

Auto-generated profile, based on publicly available information

Tong Liu

Department of Computer Science, University of Sheffield, Sheffield, U.K.

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

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

Representative Publications

View All Publications
21 July 2023 in IEEE Transactions on Industrial Electronics
Verified
Journal Article
Closed access
ZZZhonglin Zuo
Zhonglin Zuo
HZHao Zhang
Hao Zhang
LMLi Ma
Li Ma
TLTong Liu
Tong Liu
LSLiang Shan
Liang Shan
Real-time leak detection for natural gas gathering pipelines is critical to guarantee the safe transportation of energy in the source of production. Since leak samples are scarce in real pipelines, modeling healthy data becomes one of the mainstream solutions. However, due to the lack of prior knowledge of leaks, more effective feature learning for multivariate time series (MTS) of pipeline data is a prerequisite for reliable leak detection. Moreover, in-service gathering pipelines usually involve multiple operating conditions (MOCs), where the leak characteristics of MOCs could be significantly different. This poses a serious challenge to accurate leak detection. To address the abovementioned problems, we propose a hybrid leak detection method for gathering pipelines under MOCs. First, anomaly processing and long–short sequence construction are designed to provide high-quality data for leak detection. Then, reconstruction- and prediction-one-dimensional convolutional long short-term memory autoencoder is proposed to enhance the feature learning for MTS. Based on the learned features, a multimodel decision scheme with one-class support vector machine is developed to deal with leak detection under MOCs. Finally, experimental results on supervisory control and data acquisition data obtained from real-world natural gas gathering pipelines demonstrate the effectiveness of the proposed method.

21 February 2024 in Energy and Buildings
Verified
Journal Article
Closed access
DYDie Yu
Die Yu
TLTong Liu
Tong Liu
KWKai Wang
Kai Wang
Kang LiKang Li
Kang Li
MMMehmet Mercangöz
Mehmet Mercangöz
RZRuoFan Zhao
RuoFan Zhao

23 April 2024 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
XKXiangyin Kong
Xiangyin Kong
YHYimeng He
Yimeng He
ZSZhihuan Song
Zhihuan Song
TLTong Liu
Tong Liu
Zhiqiang GeZhiqiang Ge
Zhiqiang Ge
Probabilistic latent variable models (PLVMs), such as probabilistic principal component analysis (PPCA), are widely employed in process monitoring and fault detection of industrial processes. This article proposes a novel deep PPCA (DePPCA) model, which has the advantages of both probabilistic modeling and deep learning. The construction of DePPCA includes a greedy layer-wise pretraining phase and a unified end-to-end fine-tuning phase. The former establishes a hierarchical deep structure based on cascading multiple layers of the PPCA module to extract high-level features. The latter builds an end-to-end connection between the raw inputs and the final outputs to further improve the representation of the model to high-level features. After constructing the model structure of DePPCA, we first present the detailed training processes of the pretraining and fine-tuning stages, then clarify the theoretical merits of the proposed model from the perspective of variational inference. For process monitoring purposes, we develop two statistics based on the established DePPCA. The monitoring performance of these two statistics can remain superior even if the features extracted by DePPCA are significantly compressed to univariate. This makes the feature extraction process and online monitoring procedure of DePPCA quite fast. In other words, the proposed DePPCA can achieve accurate and efficient process monitoring by only extracting one feature for each sample. Finally, the effectiveness of DePPCA is evaluated on the Tennessee Eastman (TE) process and the multiphase flow (MPF) facility.

9 April 2024 in IEEE Transactions on Knowledge and Data Engineering
Verified
Journal Article
Closed access
MZMenghui Zhou
Menghui Zhou
XWXulong Wang
Xulong Wang
TLTong Liu
Tong Liu
YYYun Yang
Yun Yang
PYPo Yang
Po Yang
Alzheimer's disease (AD), the most prevalent dementia, gradually reduces the cognitive abilities of patients while also posing a significant financial burden on the healthcare system. A variety of multi-task learning methods have recently been proposed in order to identify potential MRI-related biomarkers and accurately predict the progression of AD. These methods, however, all use a predefined task relation structure that is rigid and insufficient to adequately capture the intricate temporal relations among tasks. Instead, we propose a novel mechanism for directly and automatically learning the temporal relation and constructing it as an Automatic Temporal relation Graph (AutoTG). We use the sparse group Lasso to select a universal MRI feature set for all tasks and particular sets for various tasks in order to find biomarkers that are useful for predicting the progression of AD. To solve the biconvex and non-smooth objective function, we adopt the alternating optimization and show that the two related sub-optimization problems are amenable to closed-form solution of the proximal operator. To solve the two problems efficiently, the accelerated proximal gradient method is used, which has the fastest convergence rate of any first-order method. We have preprocessed three latest AD datasets, and the experimental results verify our proposed novel multi-task approach outperforms several baseline methods. To demonstrate the high interpretability of our approach, we visualise the automatically learned temporal relation graph and investigate the temporal patterns of the important MRI features.

15 January 2024 in Ocean Engineering
Verified
Journal Article
Closed access
ZLZechen Li
Zechen Li
TLTong Liu
Tong Liu
XPXing Peng
Xing Peng
JRJinxin Ren
Jinxin Ren
LSLiang Shan
Liang Shan

2 February 2023 in IEEE Transactions on Cybernetics
Verified
Journal Article
Closed access
TLTong Liu
Tong Liu
SCSheng Chen
Sheng Chen
Kang LiKang Li
Kang Li
HSHuixia Shi
Huixia Shi
CHChris J. Harris
Chris J. Harris
Multioutput regression of nonlinear and nonstationary data is largely understudied in both machine learning and control communities. This article develops an adaptive multioutput gradient radial basis function (MGRBF) tracker for online modeling of multioutput nonlinear and nonstationary processes. Specifically, a compact MGRBF network is first constructed with a new two-step training procedure to produce excellent predictive capacity. To improve its tracking ability in fast time-varying scenarios, an adaptive MGRBF (AMGRBF) tracker is proposed, which updates the MGRBF network structure online by replacing the worst performing node with a new node that automatically encodes the newly emerging system state and acts as a perfect local multioutput predictor for the current system state. Extensive experimental results confirm that the proposed AMGRBF tracker significantly outperforms existing state-of-the-art online multioutput regression methods as well as deep-learning-based models, in terms of adaptive modeling accuracy and online computational complexity.