Tengtuo Chen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Tengtuo Chen has a total of 23 co-authors. Here are the top co-authors by number of shared publications:
- Jianchun Zhang
Hangzhou Innovation Institute, Beihang University, Hangzhou, China
3 shared publications - Guibin Peng
COMAC Beijing Aircraft Technology Research Institute, Beijing 102211, China
2 shared publications - Haotian Zhong
COMAC Beijing Aircraft Technology Research Institute, Beijing 102211, China
2 shared publications - Liang Zhao
Dalian University of Technology, Dalian, Liaoning, China
2 shared publications - Qi Shao
School of Reliability and Systems Engineering, Beihang University, Beijing, China
2 shared publications - Shunkun Yang
School of Reliability and Systems Engineering, Beihang University, Beijing 100191, China
2 shared publications
Latest Publications
- Open Access
- 13 May 2026
- Published by MDPI AG in Mathematics
- Vol. 14 (10) , 1652
An Interpretable Ensemble Learning Method for GPS Spoofing Detection with Feature Selection
Global Positioning System (GPS) spoofing poses severe threats to navigation safety, necessitating robust detection mechanisms with enhanced interpretability. While existing methods have been explored for GPS spoofing detection, algorithmic interpretability is rarely addressed and detection performance remains suboptimal. This study proposes Stack-TabNet, a stacked ensemble learning framework integrating various decision trees and the attentive transformer-based TabNet network. To address model opacity, an interpretable feature attribution mechanism is employed to quantify feature contributions and guide optimization. Experiments are conducted on a complex dataset comprising authentic and spoofed GPS signals across four classes, characterized by high-dimensional signal metrics and severe class imbalances. The initial model utilizing all available features demonstrates robust detection capability. Subsequently, an optimized variant employs a subset of top-ranked features identified by the interpretation mechanism, yielding further improved accuracy. Comparative analysis confirms that the proposed framework outperforms traditional baselines, achieving a maximum accuracy of 95.91% after SHAP-guided feature selection, which exceeds all baseline models by at least 3.54%. The analysis identifies Pseudorange and Time of Code Delay as the most important features, consistently ranking at the top across all base learners within the ensemble architecture.
- 13 May 2026
- Published by MDPI AG in Mathematics
- Vol. 14 (10) , 1652
Open AccessAn Interpretable Ensemble Learning Method for GPS Spoofing Detection with Feature Selection
Global Positioning System (GPS) spoofing poses severe threats to navigation safety, necessitating robust detection mechanisms with enhanced interpretability. While existing methods have been explored for GPS spoofing detection, algorithmic interpretability is rarely addressed and detection performance remains suboptimal. This study proposes Stack-TabNet, a stacked ensemble learning framework integrating various decision trees and the attentive transformer-based TabNet network. To address model opacity, an interpretable feature attribution mechanism is employed to quantify feature contributions and guide optimization. Experiments are conducted on a complex dataset comprising authentic and spoofed GPS signals across four classes, characterized by high-dimensional signal metrics and severe class imbalances. The initial model utilizing all available features demonstrates robust detection capability. Subsequently, an optimized variant employs a subset of top-ranked features identified by the interpretation mechanism, yielding further improved accuracy. Comparative analysis confirms that the proposed framework outperforms traditional baselines, achieving a maximum accuracy of 95.91% after SHAP-guided feature selection, which exceeds all baseline models by at least 3.54%. The analysis identifies Pseudorange and Time of Code Delay as the most important features, consistently ranking at the top across all base learners within the ensemble architecture.
- Open Access
- 16 April 2026
- Published by MDPI AG in Preprints.org
An Interpretable Ensemble Learning Method for GPS Spoofing Detection with Feature Selection
Global Positioning System (GPS) spoofing poses severe threats to navigation safety, necessitating robust detection mechanisms with enhanced interpretability. This study proposes Stack-TabNet, a novel stacked ensemble learning framework integrating XGBoost, Random Forest, and the attentive transformer-based TabNet network. To address model opacity, an interpretable feature attribution mechanism is employed to quantify feature contributions and guide optimization. Experiments are conducted on a complex dataset comprising authentic and spoofed GPS signals across four classes, characterized by high-dimensional signal metrics and severe class imbalance. The initial model utilizing all available features demonstrates robust detection capability. Subsequently, an optimized variant utilizes a subset of top-ranked features identified by the interpretation mechanism, yielding further improved accuracy. Comparative analysis confirms that the proposed framework surpasses all traditional machine learning and deep learning baselines. The analysis identifies Pseudorange and Time of Code Delay as the most discriminative features. These results indicate that combining ensemble learning with interpretable feature selection significantly enhances detection accuracy and training efficiency for GPS anti-spoofing applications.
- 16 April 2026
- Published by MDPI AG in Preprints.org
Open AccessAn Interpretable Ensemble Learning Method for GPS Spoofing Detection with Feature Selection
Global Positioning System (GPS) spoofing poses severe threats to navigation safety, necessitating robust detection mechanisms with enhanced interpretability. This study proposes Stack-TabNet, a novel stacked ensemble learning framework integrating XGBoost, Random Forest, and the attentive transformer-based TabNet network. To address model opacity, an interpretable feature attribution mechanism is employed to quantify feature contributions and guide optimization. Experiments are conducted on a complex dataset comprising authentic and spoofed GPS signals across four classes, characterized by high-dimensional signal metrics and severe class imbalance. The initial model utilizing all available features demonstrates robust detection capability. Subsequently, an optimized variant utilizes a subset of top-ranked features identified by the interpretation mechanism, yielding further improved accuracy. Comparative analysis confirms that the proposed framework surpasses all traditional machine learning and deep learning baselines. The analysis identifies Pseudorange and Time of Code Delay as the most discriminative features. These results indicate that combining ensemble learning with interpretable feature selection significantly enhances detection accuracy and training efficiency for GPS anti-spoofing applications.
- 19 June 2025
- Published by Springer Nature
- p. 227-239
YOLO_LSK: A Sintered Surface Defect Detection Model Based on Large Selective Kernel Network
- 19 June 2025
- Published by Springer Nature
- p. 227-239
YOLO_LSK: A Sintered Surface Defect Detection Model Based on Large Selective Kernel Network
- 25 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Control Systems Letters
- Vol. 8, 3434-3439
Reliability-Guaranteed Fault Observer Design for Systems With Stochastic Parametric Uncertainty
The existing observer-based fault estimation methods for dynamic systems rarely consider the internal stochastic parametric uncertainty, limiting the reliability in practical applications. This letter aims to design a reliability-guaranteed fault observer for systems with stochastic parametric uncertainty. The condition for the observer stability and performance robustness is first described by a stochastic linear matrix inequality (LMI). By introducing the structural reliability index and certain matrix inequality lemmas, the original stochastic LMI is transformed into a deterministic probabilistic LMI with a probabilistic parameter of the reliability index. The probabilistic parameter quantifies the likelihood of achieving fault estimation performance and can be intentionally given or optimized to design a reliable fault observer. Simulation results with Monte-Carlo verification demonstrate the capability of the designed fault observer to estimate the constant and slowly time-varying faults, outperforming conventional methods in reliability.
- 25 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Control Systems Letters
- Vol. 8, 3434-3439
Reliability-Guaranteed Fault Observer Design for Systems With Stochastic Parametric Uncertainty
The existing observer-based fault estimation methods for dynamic systems rarely consider the internal stochastic parametric uncertainty, limiting the reliability in practical applications. This letter aims to design a reliability-guaranteed fault observer for systems with stochastic parametric uncertainty. The condition for the observer stability and performance robustness is first described by a stochastic linear matrix inequality (LMI). By introducing the structural reliability index and certain matrix inequality lemmas, the original stochastic LMI is transformed into a deterministic probabilistic LMI with a probabilistic parameter of the reliability index. The probabilistic parameter quantifies the likelihood of achieving fault estimation performance and can be intentionally given or optimized to design a reliable fault observer. Simulation results with Monte-Carlo verification demonstrate the capability of the designed fault observer to estimate the constant and slowly time-varying faults, outperforming conventional methods in reliability.
- Open Access
From Segmentation to Classification: A Deep Learning Scheme for Sintered Surface Images Processing
Effectively managing the quality of iron ore is critical to iron and steel metallurgy. Although quality inspection is crucial, the perspective of sintered surface identification remains largely unexplored. To bridge this gap, we propose a deep learning scheme for mining the necessary information in sintered images processing to replace manual labor and realize intelligent inspection, consisting of segmentation and classification. Specifically, we first employ a DeepLabv3+ semantic segmentation algorithm to extract the effective material surface features. Unlike the original model, which includes a high number of computational parameters, we use SqueezeNet as the backbone to improve model efficiency. Based on the initial annotation of the processed images, the sintered surface dataset is constructed. Then, considering the scarcity of labeled data, a semi-supervised deep learning scheme for sintered surface classification is developed, which is based on pseudo-labels. Experiments show that the improved semantic segmentation model can effectively segment the sintered surface, achieving 98.01% segmentation accuracy with only a 5.71 MB size. In addition, the effectiveness of the adopted semi-supervised learning classification method based on pseudo-labels is validated in six state-of-the-art models. Among them, the ResNet-101 model has the best classification performance, with 94.73% accuracy for the semi-supervised strategy while only using 30% labeled data, which is an improvement of 1.66% compared with the fully supervised strategy.
Open AccessFrom Segmentation to Classification: A Deep Learning Scheme for Sintered Surface Images Processing
Effectively managing the quality of iron ore is critical to iron and steel metallurgy. Although quality inspection is crucial, the perspective of sintered surface identification remains largely unexplored. To bridge this gap, we propose a deep learning scheme for mining the necessary information in sintered images processing to replace manual labor and realize intelligent inspection, consisting of segmentation and classification. Specifically, we first employ a DeepLabv3+ semantic segmentation algorithm to extract the effective material surface features. Unlike the original model, which includes a high number of computational parameters, we use SqueezeNet as the backbone to improve model efficiency. Based on the initial annotation of the processed images, the sintered surface dataset is constructed. Then, considering the scarcity of labeled data, a semi-supervised deep learning scheme for sintered surface classification is developed, which is based on pseudo-labels. Experiments show that the improved semantic segmentation model can effectively segment the sintered surface, achieving 98.01% segmentation accuracy with only a 5.71 MB size. In addition, the effectiveness of the adopted semi-supervised learning classification method based on pseudo-labels is validated in six state-of-the-art models. Among them, the ResNet-101 model has the best classification performance, with 94.73% accuracy for the semi-supervised strategy while only using 30% labeled data, which is an improvement of 1.66% compared with the fully supervised strategy.
- 21 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 26 (15209210) , 8323-8332
Multi-Sentence Complementarily Generation for Text-to-Image Synthesis
Generating realistic images based on text descriptions remains challenging in computer vision. Existing multi-stage generation methods are sufficient to generate high-resolution images. However, these methods mainly use one sentence to synthesize images, which are difficult to extract adequate semantic features, resulting in the generated images being far apart from ground-truth images. In this paper, we propose a Multi-Sentence Complementary Generative Adversarial Network, MSCGAN, which assists in generating accurate images by fusing the same semantics from different sentences and preserving their unique semantics. More specifically, the latest BERT model is employed to identify semantic features and a multi-semantic fusion module (MSFM) is designed to fuse the semantic features of different sentences. Besides, a pre-trained cross-modal contrast similarity model (CCSM) is developed to explore fine-grained loss on generated images. Moreover, a multi-sentence joint discriminator is designed to ensure that the generated images match all sentences. Experiments and ablation studies on CUB and MS-COCO datasets demonstrate the significant superiority of the proposed method compared to state-of-the-art methods.
- 21 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 26 (15209210) , 8323-8332
Multi-Sentence Complementarily Generation for Text-to-Image Synthesis
Generating realistic images based on text descriptions remains challenging in computer vision. Existing multi-stage generation methods are sufficient to generate high-resolution images. However, these methods mainly use one sentence to synthesize images, which are difficult to extract adequate semantic features, resulting in the generated images being far apart from ground-truth images. In this paper, we propose a Multi-Sentence Complementary Generative Adversarial Network, MSCGAN, which assists in generating accurate images by fusing the same semantics from different sentences and preserving their unique semantics. More specifically, the latest BERT model is employed to identify semantic features and a multi-semantic fusion module (MSFM) is designed to fuse the semantic features of different sentences. Besides, a pre-trained cross-modal contrast similarity model (CCSM) is developed to explore fine-grained loss on generated images. Moreover, a multi-sentence joint discriminator is designed to ensure that the generated images match all sentences. Experiments and ablation studies on CUB and MS-COCO datasets demonstrate the significant superiority of the proposed method compared to state-of-the-art methods.
- 14 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 670-674
Defects Clustering for Mineral Sintering Surface Based on Multi-source Data Fusion
During sintering of minerals, multiple categories of defects often appear on the surface of material due to hysteresis of control. Fusion of data from multiple sources is considered in this paper in a bid to identify different types of defects and to improve the utilization of collected data. Specifically, this paper establishes a heterogeneous multi-source dataset based on sintering data. And a novel deep learning approach for multi-source data fusion is introduced and extended. Based on constructed multi-source dataset and associated algorithm, the downstream task of clustering is carried out. Affiliated experimental results show that the multi-source information clustering process for mineral sintered surface defects proposed in this paper outperforms unimodal approach, and relative performance metrics have reached the level of engineering applications.
- 14 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 670-674
Defects Clustering for Mineral Sintering Surface Based on Multi-source Data Fusion
During sintering of minerals, multiple categories of defects often appear on the surface of material due to hysteresis of control. Fusion of data from multiple sources is considered in this paper in a bid to identify different types of defects and to improve the utilization of collected data. Specifically, this paper establishes a heterogeneous multi-source dataset based on sintering data. And a novel deep learning approach for multi-source data fusion is introduced and extended. Based on constructed multi-source dataset and associated algorithm, the downstream task of clustering is carried out. Affiliated experimental results show that the multi-source information clustering process for mineral sintered surface defects proposed in this paper outperforms unimodal approach, and relative performance metrics have reached the level of engineering applications.