Yingjie Yang

Professor Yingjie Yang

Job: Professor of Computational Intelligence

Faculty: Computing, Engineering and Media

School/department: School of Computer Science and Informatics

Research group(s): Centre for Computational Intelligence (CCI) and 羞羞视频 Interdisciplinary Group in Intelligent Transport Systems (DIGITS)

Address: 羞羞视频, The Gateway, Leicester, LE1 9BH, United Kingdom

T: +44 (0)116 257 7939

E: yyang@dmu.ac.uk

W: /cci

Close all sections

Open all sections

Personal profile

Dr. Yingjie Yang was awarded his first PhD in Engineering from Northeastern University in 1994, and his second PhD in Computer Science in 2008. He has published more than 100 papers in international journals and conferences. He has been involved in more than 90 international conferences as a member of program committees and organised a number of international conferences and special sessions such as 2015 IEEE International Conference on Grey Systems and Intelligent Service, IEEE SMC 2014 and IEEE WCCI2008. As a senior member of IEEE, Dr. Yang serves as a co-chair of the Technical Committee on Grey Systems, IEEE Systems, Man and Cybernetics Society and the vice chair for the task force for competition in IEEE Fuzzy Systems Technical Committee. He is serving also as an associate editor for 5 international academic journals, including IEEE Transactions on Cybernetics. He had been invited to give plenary speech at a number of international confertences, such as the 2013, 2011 and 2009 IEEE Conferences on Grey Systems and Intelligent Services and the 2001 international conference on Airport Management.

Research group affiliations

Centre for Computational Intelligence (CCI)

羞羞视频 Interdisciplinary Group in Intelligent Transport Systems (DIGITS)

Publications and outputs

dc.title: Reservoir permeability prediction using integrated Grey-Fuzzy Gaussian Process Regression: A comprehensive framework for uncertainty quantification and interpretability dc.contributor.author: Lawal, Ahmad; Yang, Yingjie; Baisa, Nathanael L.; He, Hongmei dc.description.abstract: This study introduces an Integrated Grey-Fuzzy Gaussian Process Regression (IGF-GPR) framework for reservoir permeability prediction that integrates Gaussian Process Regression (GPR), Grey Relational Analysis (GRA), and fuzzy logic to address both prediction accuracy and interpretability challenges. Permeability prediction is crucial for reservoir characterization, but traditional machine learning approaches often lack robust uncertainty quantification and are considered 鈥渂lack boxes鈥�. The proposed framework enhances the probabilistic modeling capabilities of GPR through lengthscale parameters optimized by GRA and provides interpretable reliability assessments via fuzzy logic. The framework was validated using two distinct datasets: Nuclear Magnetic Resonance (NMR) logs from North Sea sandstones and conventional logs from central Australian basins. Results demonstrate that the integrated approach consistently outperforms alternative machine learning methods, specifically eXtreme Gradient Boosting (XGBoost), Least Squares Boosting (LSBoost), and K-Nearest Neighbors (KNN), across both datasets. The method achieved reliability scores of approximately 0.91 and significantly narrower prediction intervals, with a Prediction Interval Normalized Average Width (PINAW) as low as 0.0446 compared to 1.0 for the alternatives. Sensitivity analysis of the fuzzy reliability assessment revealed that triangular membership functions produce more distinct reliability categories, while Gaussian functions offer more gradual transitions. The IGF-GPR framework is adaptable across different geological settings and data types. Furthermore, it is combined with interpretable uncertainty quantification, making it particularly valuable for supporting decision-making in reservoir development and management. dc.description: The file attached to this record is the author's final peer reviewed version. The Publisher's final version can be found by following the DOI link.
dc.title: Interpretable temporal graph attention network and cross-modal fusion for early rumor detection dc.contributor.author: Ding, Kuiyuan; Mao, Shuhua; Yang, Yingjie dc.description.abstract: Amid the widespread popularity of social media, the rapid spread of rumors presents a serious threat to social stability. Therefore, developing efficient and accurate automated rumor detection systems has become a crucial task. Existing methods often overlook the dynamic temporal characteristics of propagation, employ rudimentary cross-modal fusion mechanisms, and lack decision interpretability. Addressing these challenges, we propose an interpretable Temporal Graph Attention Network with Cross-Modal Fusion (TGA-CMF) for early rumor detection, where 鈥漜ross-modal鈥� explicitly refers to the heterogeneous fusion of text semantics, propagation structure, and temporal dynamics. The core innovation of this model lies in an adaptive Temporal Decay Graph Attention Network (Temporal Decay GAT), which integrates 鈥漬ode-relative posting time鈥� as a dynamic attribute to capture the propagation lifecycle. In parallel, we design a global-structure-guided cross-modal fusion mechanism that utilizes the global graph structure representation as a query to selectively filter and aggregate the most discriminative textual evidence. Benefiting from its temporal-aware capability and transparent architecture supporting dual-channel decision analysis, our model achieves superior performance in early detection, as demonstrated by experiments on datasets such as PHEME. Furthermore, it significantly outperforms baseline models on key metrics, including accuracy and F1-score. dc.description: The file attached to this record is the author's final peer reviewed version. The Publisher's final version can be found by following the DOI link.
dc.title: Terminating the reliability growth test under small sample failure data set dc.contributor.author: Dong, Wenjie; Guo, Jinyan; Liu, Lianyi; Yang, Yingjie dc.description.abstract: Upon failure discovery, redesign or corrective measures are always implemented to eliminate the defects and improve system reliability in reliability growth management. The Crow Army Materiel Systems Analysis Activity (AMSAA) model (C-A model) is an effective model candidate in describing cumulative number of faults with respect to reliability growth testing time, in which large amount of recorded failure data are utilized to estimate the parameters in the C-A model. Under small sample size, however, it has been proven difficult to confidently obtain accurate parameter estimators and reliability growth test termination time. In this research, the grey forecasting method, an effective approach in disposing uncertainty especially for scenarios with small sample and poor information, is introduced to fit the limited failure data, predict the next failure time, and extend the original failure dataset. After which, failure dataset is supplemented and parameters in the C-A model are updated. Estimating the reliability metrics at the predicted failure time and comparing with the target requirement, we terminate the reliability growth test, otherwise, continue to predict the failure time with the metabolic grey model. It is shown from two reliability growth cases in the literature that the grey model with first order and one variable (GM(1,1)) possesses a strong data processing ability, makes up for the insufficiencies in circumstance of small sample size, and accelerates the termination time in a reliability growth test. dc.description: The file attached to this record is the author's final peer reviewed version. The Publisher's final version can be found by following the DOI link.
dc.title: Multiple uncertainty data fusion and holographic reliability growth evaluation model dc.contributor.author: Liu, S. F.; Tang, Wei; Xu, Hongpeng; Liu, Lianyi; Yang, Yingjie dc.description.abstract: Purpose 鈥� In the era of big data, the understanding of the complex and uncertain nature of reliability growth data has deepened. Beyond the well-known characteristic that failure data are random variables following specific probability distributions, expert judgments expressed linguistically constitute fuzzy data. Allowable values for critical parameters are often confined to specific ranges, representing typical grey data. Moreover, knowledge regarding specific components, materials, and processes frequently manifests as rough data. Effectively utilizing reliability growth data characterized by multiple uncertainties鈥攔andomness, fuzziness, greyness, and roughness鈥攊s therefore key to solving the modeling challenges for reliability growth of high end intelligent equipment. This paper proposes a novel model and associated new concepts for uncertainty representation and integration to address this gap. Design/methodology/approach 鈥� Guided by the core principles of big data鈥攚hich emphasize utilizing all available data beyond random sampling, eliminating confounding factors to discern general trends, and prioritizing correlation over strict causality鈥攖his research adopts a "full data utilization" perspective. It begins with the collection, identification, and analysis of reliability growth data. Through an in-depth examination of the characteristics and commonalities of data embodying various uncertainties (random, fuzzy, grey, rough), the concept of a Standard Uncertainty Number (SUN) is defined. The representation of SUNs, conversion rules for transforming diverse uncertainty data into SUNs, and a comprehensive operational framework for SUNs are developed. Subsequently, analytical and data mining models based on SUNs are established. These models facilitate multi-dimensional, multi-stage, and multi-level exploration of key factors influencing the reliability growth of high-end intelligent equipment, leading to the construction of a reliability growth evaluation index system. To overcome existing modeling bottlenecks, holographic reliability growth evaluation and prediction models are constructed by integrating big data technologies, complex uncertainty data analysis methods, sequence operators, spectrum analysis, and intelligent algorithms. Findings/Results 鈥揟he proposed novel concepts and framework demonstrate the feasibility of integrating diverse uncertainties to achieve high reliability for complex equipment. Originality/value 鈥� While numerous uncertainty models exist, effective frameworks for their integration remain scarce. The definitions, operational systems of SUNs, the various SUN-based data mining models, and the holographic reliability growth evaluation and prediction models presented here are original contributions of the authors dc.description: The file attached to this record is the author's final peer reviewed version. The Publisher's final version can be found by following the DOI link.
dc.title: A novel grey three-way decision model and its application dc.contributor.author: Qiao, Yu; Yang, Yingjie; Jian, Lirong; Yao, Yiyu dc.description.abstract: Decision problems in the real world often face challenges arising from incomplete information and the associated decision resulting risk. To address these issues, this paper develops a novel grey three-way decision model by leveraging grey system theory, which manages incomplete information, with three-way decision theory, which minimize the decision risk. First, within the context of grey sets, the study defines the fundamental concepts of grey kernel, grey sup port, and grey boundary by considering both the characteristic function value and the degree of greyness. These concepts establish the theoretical foundation for constructing a unified frame work that progresses from qualitative to quantitative modelling. Subsequently, a qualitative grey three-way decision model is proposed. This model employs the newly introduced concepts to achieve a highly reliable partition of the most definite components of the information; how ever, its partitioning rules remain overly rigid. To overcome this limitation, a more refined quantitative grey three-way decision model is further developed. Its core innovation lies in introducing a grey transformation function and the concept of grey three-way approximation, which convert grey information into a clear three-valued representation. Moreover, by incorporating adjustable threshold parameters and the principle of minimum cost, the proposed model enables a more flexible and adaptive decision-making process for grey information. Theoretical analysis shows that the qualitative model is a special case of the quantitative model, ensuring internal consistency within the theoretical system. Finally, a case study on enterprise green performance evaluation in an eco-industrial park is conducted. Multi-perspective analyses demonstrate the effectiveness, robustness, and advantages of the proposed model in complex and uncertain decision environments. dc.description: The file attached to this record is the author's final peer reviewed version. The Publisher's final version can be found by following the DOI link.
dc.title: Forecasting the Extreme Heat for Chongqing in China dc.contributor.author: Zeng, Bo; Du, Shiyi; Yu, Lean; Bai, Yun; Wang, Jianzhou; Yang, Yingjie dc.description.abstract: Under global warming, Chongqing, China has seen rising frequencies of extreme heat, severely impacting residents鈥� lives, production, and the urban ecosystem. Accurately predicting future extreme heat year (hereinafter referred to as extreme heat) is crucial for ecological protection, energy management, and infrastructure planning. Using historical temperature data, this study defines extreme heat via the quantile method, ensuring regional representativeness. To address the limitations of traditional forecasting methods in predicting extreme heat characterized by 鈥渟mall sample sizes and complex influencing factors,鈥� we have proposed a new grey disaster prediction model. The new model introduces a three-element adjacent mean generation operator and uses the particle swarm optimization (PSO) algorithm for global optimization of its key parameters. Applying this model to Chongqing, China鈥檚 1951鈥�2024 extreme heat, we predict the next three occurrences will be in 2026, 2029, and 2031. This model offers a new approach to extreme heat prediction and supports urban heatwave emergency response optimization, aiding high-temperature disaster prevention and sustainable ecological development. dc.description: The file attached to this record is the author's final peer reviewed version. The Publisher's final version can be found by following the DOI link.
dc.title: Three-stage medical few-shot classification based on adaptive regularization with HMCE loss dc.contributor.author: Chen, Yiming; Mao, Shuhua; Yang, Yingjie dc.description.abstract: In medical research, the scarcity of labeled data and the high cost of expert annotation present a significant challenge for developing robust classification models, particularly in the context of rare diseases or specialized imaging modalities. To overcome this issue, we propose a three-stage few-shot learning framework that integrates meta-learning with pretraining and fine-tuning. First, during the pretraining stage, we pretrain the feature backbone on labeled external data using supervised loss to learn general feature representations. In the meta-training stage, we replace the fully connected layers of the pretrained model with task-specific fully connected layers and fix the feature extraction parameters. We then meta-train the fully connected layers on labeled simulated tasks using an adaptive learning rate and adaptive regularization with Hard-Mining loss, enabling rapid adaptation to new tasks. Finally, during the target task, we fine-tune the model on the target data, adjusting model parameters to align with the task鈥檚 feature distribution. We conducted experiments on challenging medical benchmarks BreakHis and ISIC2018 for few-shot classification tasks. Our method achieves superior performance on medical datasets, significantly outperforming related works. Additionally, ablation studies have also been conducted to validate the effectiveness of each module within the model. dc.description: The file attached to this record is the author's final peer reviewed version. The Publisher's final version can be found by following the DOI link.
dc.title: Community detection in attributed networks based on deep attention autoencoder with block diagonal subspace constraint dc.contributor.author: Wu, Ling; Guo, Shuai; Cai, Ziqi; Chen, Jianguo; Yang, Yingjie; Guo, Kun dc.description.abstract: Community detection in attributed networks has become a hotspot in contemporary complex network research. It integrates topological structures and attribute features to uncover latent community structures, providing considerable value in practical applications like recommendation systems, social network analysis, and bioinformatics. Although neural network-based community detection methods have achieved decent performance, these methods demonstrate weak learning capabilities for spatial structural features and neglect to consider the clustering distribution in the embedding space. To address this issue, this paper proposes a subspace plugin strategy that utilizes subspace constraints to guide representation vectors to learn the clustering distribution in the embedding space, making it more appropriate for clustering tasks. Additionally, to overcome the challenges of insufficient capture of network spatial features and inadequate extraction of attribute information in subspace clustering for attributed network community detection, an attribute-topology fusion strategy and a subspace autoencoder strategy are devised. These strategies enable the representation vectors to capture network features better and solve the difficulty of extracting attribute information. Experimental results on real and synthetic networks demonstrated that DAEAS has higher accuracy than several state-of-the-art community detection algorithms. dc.description: The file attached to this record is the author's final peer reviewed version. The Publisher's final version can be found by following the DOI link.
dc.title: A novel time-varying Wiener process for adaptive RUL prediction under multiple uncertainties dc.contributor.author: Niu, Cuiping; Fang, Zhigeng; Yang, Yingjie; Dong, Wenjie dc.description.abstract: Remaining useful life (RUL) prediction for high-reliability complex systems is often challenged by scarce real degradation data and noise-contaminated simulated data, limiting the ability of existing methods to handle multiple uncertainties and time-varying characteristics, which in turn constrains the robustness and interpretability of predictions. This study proposes a time-varying Wiener process (TVWP) degradation model that incorporates the quantification of multiple uncertainties. First, a TVWP model is developed to characterize dynamic degradation patterns, taking into full account unit-to-unit variability and time-varying degradation behaviors. Second, a normal cloud model-based Bayesian parameter estimation method is designed to achieve adaptive updating of time-varying parameters and dynamic quantification of epistemic uncertainty. Finally, the probability distribution of the RUL is derived analytically, enabling adaptive prediction while simultaneously achieving real-time quantification of prediction errors and uncertainty. The proposed method is validated on a small-sample gyroscope drift dataset and the large-scale C-MAPSS benchmark. Results demonstrate its strong adaptability to different data volumes and significant superiority over conventional Wiener process models and state-of-the-art approaches in both prediction accuracy and robustness. dc.description: The file attached to this record is the author's final peer reviewed version. The Publisher's final version can be found by following the DOI link.
dc.title: Predicting the demand of elderly care beds by a novel recursive grey Gompertz model: case studies of Jiangsu and Shanghai, China dc.contributor.author: Guo, Xiaojun; Wang, Yueyue; Zhu, Xinyao; Wu, Ying; Yang, Yingjie; Jin, Jingliang dc.description.abstract: Background China is undergoing a rapid demographic transition, with a continuously expanding older adult population driving surging demand for elderly care services, particularly in institutional settings. However, the supply of care resources is marked by regional disparities and structural inefficiencies, failing to meet diverse elderly needs. Scientifically forecasting care resource demand and optimizing allocation are thus urgent priorities. Accurate prediction is crucial, yet often constrained by the limited data availability in this field. Methods The study developed a Recursive Grey Gompertz Model (RGGM) to address small-sample forecasting challenges by integrating grey system theory with the Gompertz growth curve. Using historical data on institutional care beds in China, Jiangsu Province, and Shanghai Municipality, the model was applied for fitting and trend projection. Its performance was compared against several established methods-Recursive Grey Model, Gompertz, GM(1,1), Exponential Smoothing, ARIMA, and MLP-using Mean Absolute Percentage Error (MAPE) and Root Mean Square Error (RMSE) as accuracy metrics. Results The comparative analysis demonstrated that the RGGM model achieved higher predictive accuracy and reliability than the other benchmark models. The forecast results for the number of elderly care beds using RGGM were associated with lower MAPE and RMSE values, confirming its superior suitability for this forecasting task. Subsequently, the validated RGGM model was used to project the development trend of elderly care beds in China, Jiangsu Province, and Shanghai for the coming years. Conclusions The RGGM model introduces a memory factor into its objective function, which assigns a greater weight to newer observations. This mechanism ensures the priority of new information during the modeling process, enhancing the model's adaptability. Furthermore, the model's structural parameters are solved recursively with each new observation, allowing the parameters to inherit information from previous data points. This recursive approach effectively improves prediction accuracy. Accurately predicting the supply of and demand for elderly care resources can assist governments and policymakers in formulating rational elderly service plans, optimizing resource allocation, and ensuring the sustainable development of the elderly care system. dc.description: open access article

Key research outputs

R-Fuzzy sets: a novel combination of fuzzy sets with rough sets with capability to represent some situations difficult with other extensions;
Grey sets: a formal formulation of the concept of grey sets and its operations;
Relative Strength of Effect: a factor analysis method based on trained neural networks;
Application of neural networks in overlay operation of GIS
Airport noise simulation using neural networks

Research interests/expertise

Dr. Yang’s research interests are mainly with uncertainty models and their applications. His theoretical work involves fuzzy sets, rough sets, grey systems and neural networks. In applications, his interests are transportation planning, environment evaluation and civil engineering simulation and analysis.

Areas of teaching

Databases
Data Warehousing
AI programming

Qualifications

PhD in Engineering (1994 from Northeastern University, China)
PhD in Computer Science (2008 from Loughborough University, UK)

Courses taught

IMAT5167
IMAT5118
IMAT5103
IMAT2427
PHAR5350

Honours and awards

Best Paper Award, the 2013 IEEE Conference on Computational Intelligenceand Computing Research.

Membership of external committees

Co-chair of the Technical Committee on Grey Systems of IEEE Systems, Man,and Cybernetics Society, 2012 -- present
Vice-chair of the Task Force on Competitions for Fuzzy Systems Technical Committeeof IEEE Computational Intelligence Society, 2011 -- present
PC members for over 90 international academic conferences

Membership of professional associations and societies

Senior Member of IEEE, 2013 -- present
Member of IEEE, Mar 2007 -- 2013
Member of the Rail Research UK Association, May 2013 -- present

Current research students

First supervisor for:

Manal Alghieth
Mohammad Al Azawi
Arjab Khuman
Nguyen Thi Mai Phuong
Tarjana Yagnik

Externally funded research grants information

"International Network on Grey Systems and its Applications", Leverhulme Trust, PI, £124997, 2015--2018.
"Grey Systems and Its Application to Data Mining and Decision Support", EU FP7 Marie Curie International IncomingFellowship, PI, €309235, 2015--2016.
"Modeling Conditions, Mechanism and Characters of Grey Prediction Model GM(1,1)", Leverhulme Trust InternationalVisiting Fellowship, PI, £25500, 2013--2014.
"Grey Systems and Computational Intelligence", Royal Society, PI, £12000, 2011-- 2013.
"ITRAQ: Integrated Traffic Management and Air Quality Control Using Space Services", Europe Space Agency, CI, €97834, 2011--2012.
"Conference grant", Royal Academy of Engineering, PI, £500, Oct 2007.

Internally funded research project information

"Project application on Grey Systems and Uncertainty", 羞羞视频 Research Leave scheme, PI, £7104, 2012--2013.
"Initial preparation for EU research network on grey systems", 羞羞视频 RIF Fund, PI, £7000, 2011--2012.
"Emerging uncertainty models and their applications", 羞羞视频 PhD scholarship, PI, £55080, 2012--2016.
"Conference grant", 羞羞视频 RITI Fund, PI, £1500, Jun 2009.
"Conference grant", 羞羞视频 RITI Fund, PI, £1500, Jun 2008.

Professional esteem indicators

Editorial board:

Associate Editor of IEEE Transaction on Cybernetics (Institute of Electrical and Electronics Engineers) ISSN: 1083-4419
Associate Editor of Scientific World Journal (Hindawi Publishing Corporation) ISSN: 2356-6140
Associate Editor of Journal of Intelligent and Fuzzy Systems (IOS Press) ISSN: 1064-1246
Assocaite Editor of Journal of Grey Systems (Research Information Ltd) ISSN: 0957-3720
Associated Editor of Grey Systems: Theory and Applications (Emerald) ISSN: 2043-9377

Plenary talks and academic seminars

Keynote speaker at the 2013 IEEE International Conference on Grey Systems and Intelligent Services, Macau, 2013
Seminar on grey numbers at Nanjing University of Aeronautics and Astronautics, Nanjing, 2012
Keynote speaker at the 2011 IEEE International Conference on Grey Systems and Intelligent Services, Nanjing,2011
Seminar on grey numbers at Nanjing University of Aeronautics and Astronautics, Nanjing, 2011
Seminar series on computational intelligence at Nanjing University of Aeronautics and Astronautics, full financialsupport from Nanjing University of Aeronautics and Astronautics, Nanjing, 2010
Keynote speaker at the 2009 IEEE International Conference on Grey Systems and Intelligent Services, Nanjing,2009
Seminar on grey systems at University of Hull, 2008
Keynote speaker at the Airport Environmental Management Workshop in Singapore, full financial support fromSingapore Aviation Academy (organisor), Singapore, 2001

Conference management

Chair of the Program Committee for the 2015 IEEE International Conference on Grey Systems and Intelligent Services,Leicester, 2015
Chair of the Program Committee for the 2015 International Conference on Advanced Computational Intelligence,Wuyi, 2015
Chair of the Program Committee for the 2013 IEEE International Conference on Grey Systems and Intelligent Services,Macau, 2013
Co-chair of the special session on grey systems at the 2014 IEEE International Conference on Systems, Man and Cybernetics, San Diego, 2014
Co-chair of the special session on grey systems at the 2012 IEEE International Conference on Systems, Man and Cybernetics, Seoul, 2012
Co-chair of the special session on grey systems at the 2011 IEEE International Conference on Systems, Man and Cybernetics, Anchorage, 2011
Co-chair of the Program Committee for the 2011 IEEE International Conference on Grey Systems and IntelligentServices, Nanjing, 2011
Co-chair of the Program Committee for the 2009 IEEE International Conference on Grey Systems and Intelligent Services, Nanjing, 2009
Session chair for 3 regular sessions at the 2008 IEEE World Congress of Computational Intelligence, Hong Kong,2008
Co-chair of the special session on grey systems at the 2008 IEEE World Congress of Computational Intelligence,Hong Kong, 2008
Member of the organising committee of the 2007 IEEE International Conference on Grey Systems and Intelligent Services, Nanjing, 2007