Tao Xue
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Tao Xue has a total of 39 co-authors. Here are the top co-authors by number of shared publications:
- Long Xi
School of Cybersecurity, Shaanxi Key Laboratory of Clothing Intelligence, Xi'an Polytechnic University, Xi'an, China
4 shared publications - Long Xi
Shaanxi Key Laboratory of Clothing Intelligence, School of Cybersecurity, Xi’an Polytechnic University, Xi’an 710048, China
3 shared publications - Wen Tang
Bournemouth University UK
3 shared publications - Wen Lv
School of Cybersecurity, Xi’an Polytechnic University, Xi’an, China
2 shared publications - Wen Lv
Shaanxi Key Laboratory of Clothing Intelligence, School of Cybersecurity, Xi’an Polytechnic University, Xi’an 710048, China
2 shared publications - Wen Lv
School of Cybersecurity, Xi'an Polytechnic University, Xi'an, China
2 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 11895-11903
CRFNet: Learning Energy-based Continuous Repulsion Field for Deformable 3D Clothing Dynamics
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 11895-11903
Open AccessCRFNet: Learning Energy-based Continuous Repulsion Field for Deformable 3D Clothing Dynamics
- Open Access
- 24 February 2026
- Published by MDPI AG in Electronics
- Vol. 15 (5) , 914
Tri-Stage Selective Reasoning for Rumor Source Detection via Graph Neural Networks and Large Language Models
Rumor source detection aims to identify the initial origin of misinformation diffusion in social networks. Accurate source localization is essential for effective rumor intervention and early mitigation in large-scale social media platforms. Existing rumor source detection methods often struggle to model complex propagation structures. However, applying mathematical models uniformly to all samples introduces unnecessary computational overhead and limits scalability. By leveraging GNN-based candidate ranking, our approach effectively narrows the source search space and provides a reliable structural foundation for subsequent reasoning. Prior studies typically perform end-to-end inference without considering prediction confidence, leading to inefficient processing of low-uncertainty samples. To address this issue, we introduce an entropy-based uncertainty filtering mechanism that selectively identifies high-uncertainty cases requiring further reasoning, significantly reducing redundant computation. Meanwhile, existing methods lack semantic interpretability when handling ambiguous propagation patterns, motivating the incorporation of large language model (LLM) reasoning. We employ LLM-based reasoning only on filtered samples to enhance semantic understanding while controlling inference cost. Based on these designs, we propose TSR-RSD, a tri-stage selective reasoning framework that integrates GNN-based structural modeling, uncertainty-driven sample selection, and LLM-based semantic reasoning. Experimental results on GossipCop, PolitiFact, and PHEME demonstrate that TSR-RSD consistently outperforms GNN-based baselines in terms of Hit@1, Hit@3, Hit@5, and Mean Reciprocal Rank (MRR), reflecting improved accuracy and stability in rumor source ranking. Furthermore, the entropy-based uncertainty filtering mechanism significantly reduces the LLM invocation ratio by approximately 40–60%, while maintaining comparable or improved ranking performance. As a result, TSR-RSD achieves an overall inference time reduction of 35–50%, effectively balancing localization accuracy, computational efficiency, and interpretability.
- 24 February 2026
- Published by MDPI AG in Electronics
- Vol. 15 (5) , 914
Open AccessTri-Stage Selective Reasoning for Rumor Source Detection via Graph Neural Networks and Large Language Models
Rumor source detection aims to identify the initial origin of misinformation diffusion in social networks. Accurate source localization is essential for effective rumor intervention and early mitigation in large-scale social media platforms. Existing rumor source detection methods often struggle to model complex propagation structures. However, applying mathematical models uniformly to all samples introduces unnecessary computational overhead and limits scalability. By leveraging GNN-based candidate ranking, our approach effectively narrows the source search space and provides a reliable structural foundation for subsequent reasoning. Prior studies typically perform end-to-end inference without considering prediction confidence, leading to inefficient processing of low-uncertainty samples. To address this issue, we introduce an entropy-based uncertainty filtering mechanism that selectively identifies high-uncertainty cases requiring further reasoning, significantly reducing redundant computation. Meanwhile, existing methods lack semantic interpretability when handling ambiguous propagation patterns, motivating the incorporation of large language model (LLM) reasoning. We employ LLM-based reasoning only on filtered samples to enhance semantic understanding while controlling inference cost. Based on these designs, we propose TSR-RSD, a tri-stage selective reasoning framework that integrates GNN-based structural modeling, uncertainty-driven sample selection, and LLM-based semantic reasoning. Experimental results on GossipCop, PolitiFact, and PHEME demonstrate that TSR-RSD consistently outperforms GNN-based baselines in terms of Hit@1, Hit@3, Hit@5, and Mean Reciprocal Rank (MRR), reflecting improved accuracy and stability in rumor source ranking. Furthermore, the entropy-based uncertainty filtering mechanism significantly reduces the LLM invocation ratio by approximately 40–60%, while maintaining comparable or improved ranking performance. As a result, TSR-RSD achieves an overall inference time reduction of 35–50%, effectively balancing localization accuracy, computational efficiency, and interpretability.
- Open Access
- 17 February 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 339
MCNet: Multi-3D point cloud completions with diverse latent shape prior
- 17 February 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 339
Open AccessMCNet: Multi-3D point cloud completions with diverse latent shape prior
- 6 February 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 313
Industrial anomaly detection via prompt learning with perturbation-based selective state memory units
- 6 February 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 313
Industrial anomaly detection via prompt learning with perturbation-based selective state memory units
- 3 November 2025
- Published by Springer Nature in Journal of Intelligent Information Systems
- Vol. 64 (1) , 325-347
GCN-diffusion and multi-view contrastive learning for enhanced knowledge recommendation
- 3 November 2025
- Published by Springer Nature in Journal of Intelligent Information Systems
- Vol. 64 (1) , 325-347
GCN-diffusion and multi-view contrastive learning for enhanced knowledge recommendation
- Open Access
- 7 June 2025
- Published by MDPI AG in Electronics
- Vol. 14 (12) , 2332
Parallel Ant Colony Algorithm for Sunway Many-Core Processors
Ant colony optimization (ACO) has garnered significant attention because of its wide application in route planning problems. Nevertheless, ACO requires a long time to calculate when tackling complex issues. Parallelization emerges as an effective strategy to improve algorithm execution efficiency, and especially in large-scale computations, parallelization technology can significantly reduce execution time. In this study, we propose an ant colony algorithm (Sunway ant colony optimization, SWACO) based on a second-level parallel strategy and tailored to the hardware characteristics of Sunway many-core processors. The first level involves process-level parallelism, in which the initial ant colony is divided into multiple child ant colonies according to the number of processors, with each child ant colony independently performing computations on each island. The second level is thread-level parallelism, utilizing the computing power of the slave core to accelerate path selection and pheromone updates of the ants, thereby effectively improving algorithm execution efficiency. The experimental results demonstrate that, across multiple TSP datasets, the SWACO algorithm significantly reduces computation time, achieving an overall speedup ratio by 3–6 times, and maintains the gap within 5%. A substantial acceleration effect was achieved.
- 7 June 2025
- Published by MDPI AG in Electronics
- Vol. 14 (12) , 2332
Open AccessParallel Ant Colony Algorithm for Sunway Many-Core Processors
Ant colony optimization (ACO) has garnered significant attention because of its wide application in route planning problems. Nevertheless, ACO requires a long time to calculate when tackling complex issues. Parallelization emerges as an effective strategy to improve algorithm execution efficiency, and especially in large-scale computations, parallelization technology can significantly reduce execution time. In this study, we propose an ant colony algorithm (Sunway ant colony optimization, SWACO) based on a second-level parallel strategy and tailored to the hardware characteristics of Sunway many-core processors. The first level involves process-level parallelism, in which the initial ant colony is divided into multiple child ant colonies according to the number of processors, with each child ant colony independently performing computations on each island. The second level is thread-level parallelism, utilizing the computing power of the slave core to accelerate path selection and pheromone updates of the ants, thereby effectively improving algorithm execution efficiency. The experimental results demonstrate that, across multiple TSP datasets, the SWACO algorithm significantly reduces computation time, achieving an overall speedup ratio by 3–6 times, and maintains the gap within 5%. A substantial acceleration effect was achieved.
- 20 May 2025
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 36 (6) , 066001
Lithium battery SOH prediction based on frequency-enhanced cross variable for short-term dependency recognition framework
Accurate and stable predictions of the state-of-health (SOH) of lithium-ion batteries are essential for effective battery management and extending battery lifespan. Two major issues exist in current lithium battery capacity prediction models. First the original data captured from temperature, voltage, and current sensors contains a large number of noises, which negatively impacts prediction accuracy. Second, the SOH of lithium-ion batteries is significantly influenced by factors such as current temperature, charge and discharge rates, and voltage. These rapid changing factors can be captured more effectively using short-term dependence rather than long-term dependence. However, the short-term dependence of capacity degradation is not fully captured, and the coupling relationships among multivariable sequences, along with the inaccurate capacity predictions resulting from frequency information, are not adequately addressed. In this paper, we propose a frequency-domain enhanced trans-variate short-term dependence recognition framework, FE-STDR, to solve these two problems and predict the SOH of lithium batteries. The FE-STDR framework comprises two modules including stacked denoising autoencoder (SDAE) and FEformer. SDAE module removes noise captured during the original battery data acquisition and capacity cycles, automatically extracting high-level features to capture complex battery state patterns through its multi-layer denoising structures. The FEformer module introduces a frequency enhanced channel attention mechanism to integrate frequency information into the framework while considering short-term frequency dependence in lithium battery data. The results indicate that the root mean square error of the proposed framework is reduced by 6.53%, 11.78%, and 7.34%, respectively, compared to the baseline models: long short-term memory, Transformer, and AE-GRU. The prediction accuracy proves that the proposed FE-STDR is superior, enabling accurate forecasting of the degradation trajectory of lithium battery SOH.
- 20 May 2025
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 36 (6) , 066001
Lithium battery SOH prediction based on frequency-enhanced cross variable for short-term dependency recognition framework
Accurate and stable predictions of the state-of-health (SOH) of lithium-ion batteries are essential for effective battery management and extending battery lifespan. Two major issues exist in current lithium battery capacity prediction models. First the original data captured from temperature, voltage, and current sensors contains a large number of noises, which negatively impacts prediction accuracy. Second, the SOH of lithium-ion batteries is significantly influenced by factors such as current temperature, charge and discharge rates, and voltage. These rapid changing factors can be captured more effectively using short-term dependence rather than long-term dependence. However, the short-term dependence of capacity degradation is not fully captured, and the coupling relationships among multivariable sequences, along with the inaccurate capacity predictions resulting from frequency information, are not adequately addressed. In this paper, we propose a frequency-domain enhanced trans-variate short-term dependence recognition framework, FE-STDR, to solve these two problems and predict the SOH of lithium batteries. The FE-STDR framework comprises two modules including stacked denoising autoencoder (SDAE) and FEformer. SDAE module removes noise captured during the original battery data acquisition and capacity cycles, automatically extracting high-level features to capture complex battery state patterns through its multi-layer denoising structures. The FEformer module introduces a frequency enhanced channel attention mechanism to integrate frequency information into the framework while considering short-term frequency dependence in lithium battery data. The results indicate that the root mean square error of the proposed framework is reduced by 6.53%, 11.78%, and 7.34%, respectively, compared to the baseline models: long short-term memory, Transformer, and AE-GRU. The prediction accuracy proves that the proposed FE-STDR is superior, enabling accurate forecasting of the degradation trajectory of lithium battery SOH.
- 2 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 37 (2) , 766-780
MC2LS: Towards Efficient Collective Location Selection in Competition
Collective Location Selection (CLS) has received significant research attention in the spatial database community due to its wide range of applications. The CLS problem selects a group of k preferred locations among candidate sites to establish facilities, aimed at collectively attracting the maximum number of users. Existing studies commonly assume every user is located in a fixed position, without considering the competition between peer facilities. Unfortunately, in real markets, users are mobile and choose to patronize from a host of competitors, making traditional techniques unavailable. To this end, this paper presents the first effort on a CLS problem in competition scenarios, called mc$^{2}$ ls, taking into account the mobility factor. Solving mc$^{2}$ ls is a non-trivial task due to its NP-hardness. To overcome the challenge of pruning multi-point users with highly overlapped minimum boundary rectangles (MBRs), we exploit a position count threshold and design two square-based pruning rules. We introduce IQuad-tree, a user-MBR-free index, to benefit the hierarchical and batch-wise properties of the pruning rules. We propose an$(1-\frac{1}{e})$ -approximate greedy solution to mc$^{2}$ ls and incorporate a candidate-pruning strategy to further accelerate the computation for handling skewed datasets. Extensive experiments are conducted on real datasets, demonstrating the superiority of our proposed pruning rules and solution compared to the state-of-the-art techniques.- 2 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 37 (2) , 766-780
MC2LS: Towards Efficient Collective Location Selection in Competition
Collective Location Selection (CLS) has received significant research attention in the spatial database community due to its wide range of applications. The CLS problem selects a group of k preferred locations among candidate sites to establish facilities, aimed at collectively attracting the maximum number of users. Existing studies commonly assume every user is located in a fixed position, without considering the competition between peer facilities. Unfortunately, in real markets, users are mobile and choose to patronize from a host of competitors, making traditional techniques unavailable. To this end, this paper presents the first effort on a CLS problem in competition scenarios, called mc$^{2}$ ls, taking into account the mobility factor. Solving mc$^{2}$ ls is a non-trivial task due to its NP-hardness. To overcome the challenge of pruning multi-point users with highly overlapped minimum boundary rectangles (MBRs), we exploit a position count threshold and design two square-based pruning rules. We introduce IQuad-tree, a user-MBR-free index, to benefit the hierarchical and batch-wise properties of the pruning rules. We propose an$(1-\frac{1}{e})$ -approximate greedy solution to mc$^{2}$ ls and incorporate a candidate-pruning strategy to further accelerate the computation for handling skewed datasets. Extensive experiments are conducted on real datasets, demonstrating the superiority of our proposed pruning rules and solution compared to the state-of-the-art techniques.- Open Access
- 14 November 2024
- Published by MDPI AG in Electronics
- Vol. 13 (22) , 4470
HCA-RFLA: A SAR Remote Sensing Ship Detection Based on Hierarchical Collaborative Attention Method and Gaussian Receptive Field-Driven Label Assignment Strategy
Ensuring safety at sea has become a primary focus of marine monitoring, driving the increasing adoption of ship detection technology in the maritime industry. Detecting small ship targets in SAR images presents challenges, as they occupy only a small portion of the image and exhibit subtle features, reducing detection efficiency. To address these challenges, we propose the HCA-RFLA algorithm for ship detection in SAR remote sensing. To better capture small targets, we design a hierarchical collaborative attention (HCA) mechanism that enhances feature representation by integrating multi-level features with contextual information. Additionally, due to the scarcity of positive samples for small targets under IoU and center sampling strategies, we propose a label assignment strategy based on Gaussian receptive fields, known as RFLA. RFLA assigns positive samples to small targets based on the Gaussian distribution between feature points and ground truth, increasing the model’s sensitivity to small samples. The HCA-RFLA was experimentally validated using the SSDD, HRSID, and SSD datasets. Compared to other state-of-the-art methods, HCA-RFLA improves detection accuracy by 6.2%, 4.4%, and 3.6%, respectively. These results demonstrate that HCA-RFLA outperforms existing algorithms in SAR remote sensing ship detection.
- 14 November 2024
- Published by MDPI AG in Electronics
- Vol. 13 (22) , 4470
Open AccessHCA-RFLA: A SAR Remote Sensing Ship Detection Based on Hierarchical Collaborative Attention Method and Gaussian Receptive Field-Driven Label Assignment Strategy
Ensuring safety at sea has become a primary focus of marine monitoring, driving the increasing adoption of ship detection technology in the maritime industry. Detecting small ship targets in SAR images presents challenges, as they occupy only a small portion of the image and exhibit subtle features, reducing detection efficiency. To address these challenges, we propose the HCA-RFLA algorithm for ship detection in SAR remote sensing. To better capture small targets, we design a hierarchical collaborative attention (HCA) mechanism that enhances feature representation by integrating multi-level features with contextual information. Additionally, due to the scarcity of positive samples for small targets under IoU and center sampling strategies, we propose a label assignment strategy based on Gaussian receptive fields, known as RFLA. RFLA assigns positive samples to small targets based on the Gaussian distribution between feature points and ground truth, increasing the model’s sensitivity to small samples. The HCA-RFLA was experimentally validated using the SSDD, HRSID, and SSD datasets. Compared to other state-of-the-art methods, HCA-RFLA improves detection accuracy by 6.2%, 4.4%, and 3.6%, respectively. These results demonstrate that HCA-RFLA outperforms existing algorithms in SAR remote sensing ship detection.
- Open Access
- 20 August 2024
- Published by Springer Nature in Research Square
CrossTransFuse:A Method for Colorectal Polyp Segmentation Incorporating Multi-Scale Cross-Attention and GiFusion Mechanisms.
Due to the varying sizes and shapes of colorectal polyps, along with their blurred textures and boundaries, segmenting the polyp boundary regions is challenging, thereby increasing the risk of misdiagnosis or missed diagnosis. This paper proposes a polyp segmentation method called CrossTransFuse, which effectively captures the subtle differences and complex features of polyps by designing a multi-scale interaction strategy. Additionally, the proposed GiFusion module integrates the interactive features of the Mask R-CNN and Transformer branches and connects them through residual blocks. The resulting interactive features can effectively capture both global and local contexts at the current spatial resolution,achieving finer polyp boundary segmentation and target localization. We test our model on five widely used polyp segmentation datasets, and the results show that, compared with advanced polyp segmentation networks, CrossTransFuse achieves more precise segmentation of polyp boundary regions on the datasets.
- 20 August 2024
- Published by Springer Nature in Research Square
Open AccessCrossTransFuse:A Method for Colorectal Polyp Segmentation Incorporating Multi-Scale Cross-Attention and GiFusion Mechanisms.
Due to the varying sizes and shapes of colorectal polyps, along with their blurred textures and boundaries, segmenting the polyp boundary regions is challenging, thereby increasing the risk of misdiagnosis or missed diagnosis. This paper proposes a polyp segmentation method called CrossTransFuse, which effectively captures the subtle differences and complex features of polyps by designing a multi-scale interaction strategy. Additionally, the proposed GiFusion module integrates the interactive features of the Mask R-CNN and Transformer branches and connects them through residual blocks. The resulting interactive features can effectively capture both global and local contexts at the current spatial resolution,achieving finer polyp boundary segmentation and target localization. We test our model on five widely used polyp segmentation datasets, and the results show that, compared with advanced polyp segmentation networks, CrossTransFuse achieves more precise segmentation of polyp boundary regions on the datasets.