Haitao Cheng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Haitao Cheng has a total of 28 co-authors. Here are the top co-authors by number of shared publications:
- He Xu
School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, China
3 shared publications Peng Li
3 shared publicationsKe Wang
2 shared publications- Peng Li
School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, China
2 shared publications - Qi Wang2 shared publications
Ruchuan Wang
School of Computer Science Nanjing University of Posts and Telecommunications Nanjing China
2 shared publications
Latest Publications
- 13 October 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 334
FinSA-MoE: A parameter-efficient mixture-of-experts framework for cross-domain Chinese financial sentiment analysis
- 13 October 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 334
FinSA-MoE: A parameter-efficient mixture-of-experts framework for cross-domain Chinese financial sentiment analysis
- 25 July 2025
- Published by Springer Nature in Earth Science Informatics
- Vol. 18 (3) , 1-20
Spatio-temporal aware graph convolution network for urban traffic speed prediction
- 25 July 2025
- Published by Springer Nature in Earth Science Informatics
- Vol. 18 (3) , 1-20
Spatio-temporal aware graph convolution network for urban traffic speed prediction
- Open Access
- 21 July 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 19 (6) , 1-19
Distributed Keyword-guided Topic Model with Lexical Knowledge Supervision
Topic models are often used to discover latent semantic patterns from document collections. However, existing unsupervised approaches have the following drawbacks: (1) The mined topics may not match user interests; (2) They are prone to extract semantically similar topics and sacrifice diversity; (3) The mined topics often have low interpretability, which does not meet common sense knowledge. To address these limitations, we propose the Distributed Keyword-guided Topic Model (DiskTM) that incorporates Gaussian-distributed keyword prior knowledge into the modeling process to mine user-interested topics. Furthermore, to inject common-sense knowledge and improve the topic’s interpretability, we extend DiskTM and propose the Distributed Keyword-guided Topic Model with Lexical Knowledge (DiskTM-LK). Experimental results on three publicly available text corpora show that our proposed approaches could extract topics that match user interests (keywords). Moreover, DiskTM and DiskTM-LK could also obtain more coherent and diverse topics, outperforming the state-of-the-art baseline approaches.
- 21 July 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 19 (6) , 1-19
Open AccessDistributed Keyword-guided Topic Model with Lexical Knowledge Supervision
Topic models are often used to discover latent semantic patterns from document collections. However, existing unsupervised approaches have the following drawbacks: (1) The mined topics may not match user interests; (2) They are prone to extract semantically similar topics and sacrifice diversity; (3) The mined topics often have low interpretability, which does not meet common sense knowledge. To address these limitations, we propose the Distributed Keyword-guided Topic Model (DiskTM) that incorporates Gaussian-distributed keyword prior knowledge into the modeling process to mine user-interested topics. Furthermore, to inject common-sense knowledge and improve the topic’s interpretability, we extend DiskTM and propose the Distributed Keyword-guided Topic Model with Lexical Knowledge (DiskTM-LK). Experimental results on three publicly available text corpora show that our proposed approaches could extract topics that match user interests (keywords). Moreover, DiskTM and DiskTM-LK could also obtain more coherent and diverse topics, outperforming the state-of-the-art baseline approaches.
- Top Cited Papers
- 1 May 2025
- Published by Elsevier in Applied Soft Computing
- Vol. 177
LLM-TFP: Integrating large language models with spatio-temporal features for urban traffic flow prediction
- 1 May 2025
- Published by Elsevier in Applied Soft Computing
- Vol. 177
Top Cited PapersLLM-TFP: Integrating large language models with spatio-temporal features for urban traffic flow prediction
- 24 April 2025
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 153
Enhancing diabetes complications prediction through knowledge graphs and convolutional networks
- 24 April 2025
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 153
Enhancing diabetes complications prediction through knowledge graphs and convolutional networks
- 29 June 2023
- Published by Springer Nature in World Wide Web
- Vol. 26 (5) , 1-28
A tractable temporal description logic for reasoning fuzzy spatiotemporal knowledge
- 29 June 2023
- Published by Springer Nature in World Wide Web
- Vol. 26 (5) , 1-28
A tractable temporal description logic for reasoning fuzzy spatiotemporal knowledge
- Open Access
- 12 August 2022
- Published by Wiley in Disease Markers
- Vol. 2022, 1-17
A Deep Learning Model Incorporating Knowledge Representation Vectors and Its Application in Diabetes Prediction
The deep learning methods for various disease prediction tasks have become very effective and even surpass human experts. However, the lack of interpretability and medical expertise limits its clinical application. This paper combines knowledge representation learning and deep learning methods, and a disease prediction model is constructed. The model initially constructs the relationship graph between the physical indicator and the test value based on the normal range of human physical examination index. And the human physical examination index for testing value by knowledge representation learning model is encoded. Then, the patient physical examination data is represented as a vector and input into a deep learning model built with self-attention mechanism and convolutional neural network to implement disease prediction. The experimental results show that the model which is used in diabetes prediction yields an accuracy of 97.18% and the recall of 87.55%, which outperforms other machine learning methods (e.g., lasso, ridge, support vector machine, random forest, and XGBoost). Compared with the best performing random forest method, the recall is increased by 5.34%, respectively. Therefore, it can be concluded that the application of medical knowledge into deep learning through knowledge representation learning can be used in diabetes prediction for the purpose of early detection and assisting diagnosis.
- 12 August 2022
- Published by Wiley in Disease Markers
- Vol. 2022, 1-17
Open AccessA Deep Learning Model Incorporating Knowledge Representation Vectors and Its Application in Diabetes Prediction
The deep learning methods for various disease prediction tasks have become very effective and even surpass human experts. However, the lack of interpretability and medical expertise limits its clinical application. This paper combines knowledge representation learning and deep learning methods, and a disease prediction model is constructed. The model initially constructs the relationship graph between the physical indicator and the test value based on the normal range of human physical examination index. And the human physical examination index for testing value by knowledge representation learning model is encoded. Then, the patient physical examination data is represented as a vector and input into a deep learning model built with self-attention mechanism and convolutional neural network to implement disease prediction. The experimental results show that the model which is used in diabetes prediction yields an accuracy of 97.18% and the recall of 87.55%, which outperforms other machine learning methods (e.g., lasso, ridge, support vector machine, random forest, and XGBoost). Compared with the best performing random forest method, the recall is increased by 5.34%, respectively. Therefore, it can be concluded that the application of medical knowledge into deep learning through knowledge representation learning can be used in diabetes prediction for the purpose of early detection and assisting diagnosis.
- 6 July 2020
- Published by Wiley in Concurrency and Computation: Practice and Experience
- Vol. 33 (22)
Dynamic spatio‐temporal logic based on RCC‐8
Summary: Qualitative spatio‐temporal reasoning is an important problem in artificial intelligence and has been widely and successfully applied in geographic information system and spatio‐temporal database. Currently, action features can be found in spatio‐temporal domain and the existing spatio‐temporal formalisms are not suitable for dealing with dynamic spatio‐temporal knowledge. Thus, how to represent and reason dynamic spatio‐temporal knowledge has become an important research issue. In this article, we present a dynamic spatio‐temporal logic for representing and reasoning dynamic spatio‐temporal knowledge. is a natural combination of spatio‐temporal logic ‐8 based on ‐8 and propositional dynamic logic. Timed actions of can be considered as temporal terms, moving the regions of topological space from one time point to another. can capture actions that change spatial relations between regions over time. For a formula from , we present a construction of a Büchi tree automaton. At the same time, we prove that deciding the satisfiability problem of is an EXPTIME‐complete problem.
- 6 July 2020
- Published by Wiley in Concurrency and Computation: Practice and Experience
- Vol. 33 (22)
Dynamic spatio‐temporal logic based on RCC‐8
Summary: Qualitative spatio‐temporal reasoning is an important problem in artificial intelligence and has been widely and successfully applied in geographic information system and spatio‐temporal database. Currently, action features can be found in spatio‐temporal domain and the existing spatio‐temporal formalisms are not suitable for dealing with dynamic spatio‐temporal knowledge. Thus, how to represent and reason dynamic spatio‐temporal knowledge has become an important research issue. In this article, we present a dynamic spatio‐temporal logic for representing and reasoning dynamic spatio‐temporal knowledge. is a natural combination of spatio‐temporal logic ‐8 based on ‐8 and propositional dynamic logic. Timed actions of can be considered as temporal terms, moving the regions of topological space from one time point to another. can capture actions that change spatial relations between regions over time. For a formula from , we present a construction of a Büchi tree automaton. At the same time, we prove that deciding the satisfiability problem of is an EXPTIME‐complete problem.