Kungan Zeng

Kungan Zeng

Auto-generated profile, based on publicly available information

Kungan Zeng

School of Automation, Guangdong University of Technology, Guangzhou, China

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
4 July 2024 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
KZKungan Zeng
Kungan Zeng
Zhenni LiZhenni Li
Zhenni Li
HZHaoli Zhao
Haoli Zhao
KXKan Xie
Kan Xie
SXShengli Xie
Shengli Xie
ZZZibin Zheng
Zibin Zheng
Global navigation satellite systems (GNSS) provide efficient positioning services for location-aware Internet of Things (IoT) devices. However, GNSS non-line-of-sight (NLOS) signals can result in severe positioning errors in urban canyon areas. Existing deep learning-based NLOS signal classification methods cannot appropriately model the spatiotemporal information of NLOS interference, resulting in limited accuracy across multiple locations. This study presents a spatiotemporal information-driven model that can capture environmental characteristics and signal temporal information simultaneously to improve NLOS classification accuracy across multiple locations. First, a visualization analysis of the signal distribution across multiple locations demonstrates the impact of environmental characteristics. In addition, the significance of both the spatial environmental features and the signal temporal features for NLOS classification is clarified by constructing a tree diagram of the dataset. Second, we propose an airspace attention mechanism module and a long short-term memory (LSTM)-based temporal feature extraction module to model both types of features, respectively. Third, the learnable sparse regularizer is utilized to reduce feature redundancy and thereby realize a sparse representation, which improves model generalization performance. Finally, the spatiotemporal information-driven cross-attention model is developed to perform NLOS classification, which uses a cross-attention fusion strategy to integrate the two modules. We use real-world datasets collected across multiple urban canyon locations to test our model. Experiments show that the proposed model can achieve 98% classification accuracy across multiple locations. Generalization performance in unknown environments can be improved over 7% compared to several state-of-the-art models.

7 November 2024 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
KZKungan Zeng
Kungan Zeng
QWQianming Wang
Qianming Wang
JTJianhao Tang
Jianhao Tang
Zhenni LiZhenni Li
Zhenni Li
KXKan Xie
Kan Xie
SXShengli Xie
Shengli Xie
The reception of nonline-of-sight (NLOS) signals in urban areas, such as urban canyons and overpasses, can cause severe errors in global navigation satellite system (GNSS) positioning. Machine learning-based NLOS mitigation methods have become increasingly popular. However, existing methods cannot obtain satisfactory NLOS recognition accuracy across multiple locations or scenarios. Furthermore, in scenarios with severe occlusion, directly removing recognized NLOS signals may reduce the number of available satellites for positioning algorithms, resulting in lower positioning precision. To address these issues, this study proposes a deep learning-based NLOS interference mitigation method to improve the precision of GNSS single-point positioning (SPP). First, to improve NLOS signal recognition across multiple locations, we propose the dual self-attention mechanism (DSN) model for NLOS recognition, which utilizes self-attention networks to construct both spatial and temporal channels for modeling spatial environmental characteristics and signal temporal features, respectively. Second, to mitigate the interference from NLOS signals, we design a novel weighting scheme using NLOS recognition results to revise the elevation angle-based scheme. Next, we propose the SPP-DSN algorithm by combining the DSN model and the designed weighting scheme to improve positioning precision in urban areas. Finally, we collected real-world data to conduct experiments to investigate the performance of our proposed method. The experimental results show that our proposed DSN model can effectively improve NLOS recognition accuracy across multiple locations. Compared to the regular SPP algorithm, our proposed SPP-DSN method can enhance positioning precision by over 29% in urban canyons and more than 10% under overpasses.

8 August 2024 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
KZKungan Zeng
Kungan Zeng
Zhenni LiZhenni Li
Zhenni Li
SXShengli Xie
Shengli Xie
QWQianming Wang
Qianming Wang
WCWuhui Chen
Wuhui Chen
ZZZibin Zheng
Zibin Zheng
Machine learning-based global navigation satellite system (GNSS) signal recognition has been considered an efficient way to mitigate multipath error in positioning estimation. However, because of the spatial heterogeneity of non-line-of-sight (NLOS) interference, existing NLOS signal recognition methods struggle to achieve satisfactory accuracy across multiple locations. In particular, current methods achieve limited recognition accuracy on target domains containing unfamiliar environments. This study proposes a few-shot learning-based semi-supervised GNSS NLOS recognition method using cross-spatiotemporal information, which can achieve high-precision recognition for multiple target domains containing unfamiliar environments only requiring a limited number of labeled samples. First, we propose a self-attention mechanism-based cross-spatiotemporal information (SAM-CSI) module that captures the environmental characteristics used to model the spatial heterogeneity of NLOS interference. Next, to avoid the need for numerous labeled samples in training the model, we introduce a Siamese neural network-based few-shot learning (SNN-FSL) architecture to perform NLOS recognition using a similarity metric instead of label prediction. We then develop a semi-supervised NLOS recognition method by integrating the SAM-CSI module with the SNN-FSL architecture to enable high-precision recognition in target domains containing unfamiliar environments. Finally, we conducted comparison and few-shot learning experiments using real-world datasets, which demonstrated that our proposed method could achieve over 90% recognition accuracy in target domains containing unfamiliar environments after 50-shot learning. It represented an improvement of over 19% compared with existing methods.

17 October 2023 in Expert Systems with Applications
Verified
Journal Article
Closed access
KZKungan Zeng
Kungan Zeng
Incheon PaikIncheon Paik
Incheon Paik

5 June 2025 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
QWQianming Wang
Qianming Wang
KXKan Xie
Kan Xie
Zhenni LiZhenni Li
Zhenni Li
KZKungan Zeng
Kungan Zeng
SXShengli Xie
Shengli Xie
B. T. G. Samantha KumaraB. T. G. Samantha Kumara
B. T. G. Samantha Kumara
As a representative technical approach in Global Navigation Satellite System (GNSS) high-precision positioning, Precise Point Positioning (PPP), using a single receiver, can obtain absolute positioning accuracy ranging from decimeter-level to centimeter-level. An accurate stochastic model of observations is crucial for enhancing the PPP positioning quality. Currently, the stochastic model of observation is mainly established through empirical formulas. However, in urban environments, due to the influence of Non-Line-of-Sight (NLOS) errors, empirical formulas cannot reliably characterize the actual error magnitudes of observations, thereby degrading the PPP positioning accuracy. To address this issue, this study develops a resilient stochastic model scheme based on the intelligent identification results of NLOS, aiming to enhance PPP positioning accuracy in complex scenarios. Firstly, a stochastic model based on intelligent recognition result of NLOS signals is developed. This model utilizes the recognition results to calculate the Position Dilution of Precision (PDOP) accurately, and dynamically adjusts the observation weights of LOS and NLOS signals according to the quantity ratio of LOS and NLOS signals and the corresponding satellite geometry. Secondly, a graph neural network (GNN)-based model for NLOS signal recognition is introduced. The model leverages a GNN to extract environmental features from sky satellite images, enabling accurate identification of NLOS signals across different scenarios. Next, by integrating the designed stochastic model method and the intelligent NLOS identification model, an Enhanced Precise Point Positioning (EPPP) algorithm is proposed to improve positioning accuracy in urban environments. Finally, four real-world datasets from the urban forest scenarios and two datasets from the overpass scenarios were selected to verify the effectiveness of the proposed method. The experimental results show that the proposed EPPP model outperforms empirical stochastic models, and the PPP static positioning accuracy is improved by 38.8%-78.44%, 45.31%-69.19%, 20.52%-71.0%, 31.77%-75.7% in the east, north, up and three-dimensional directions, respectively, and the PPP dynamic positioning accuracy is improved by 19.67%-58.02%, 14.43%-57.35%, 6.56%-34.80%, 10.96%-44.87% in the east, north, up and three-dimensional directions, respectively.

30 May 2025 in IEEE Sensors Journal
Verified
Journal Article
Closed access
Zhenni LiZhenni Li
Zhenni Li
JCJiajun Chen
Jiajun Chen
KZKungan Zeng
Kungan Zeng
RYRong Yuan
Rong Yuan
SXShengli Xie
Shengli Xie
DNDusit Niyato
Dusit Niyato
The reception of non-line-of-sight (NLOS) signals significantly degrades the positioning precision of the global navigation satellite system (GNSS) in urban canyons. Recently, deep learning-based methods have shown significant potential in NLOS detection. However, existing methods suffer significant performance degradation across different scenarios, primarily due to an insufficient understanding of multivariate dependencies within GNSS measurement sequences. To address the above challenge, we propose a multivariate time series learning-based NLOS intelligent detection method, which improves detection accuracy by treating nonlinear temporal changes in GNSS measurement sequences as a multivariate dependency issue. Firstly, a transformer-based multivariate time series learning (TMTSL) module is designed to capture multivariate dependency features from GNSS measurement sequences effectively. It utilizes a decoupling-to-aggregation mechanism to extract univariate temporal information and aggregate multivariate temporal information, enhancing the representation of multivariate dependency features. Moreover, a graph transformer-based environment information extraction (GTEIE) module is developed to capture diverse environmental information. Specifically, a sky satellite graph is constructed to represent the spatial geometric distribution of satellites at a given epoch. The graph transformer is then used to extract environmental representations from this graph. Consequently, a multivariate time series learning-based NLOS detection method is proposed using a cross-attention-based fusion network to combine the environment information and multivariate dependency features for accurate NLOS detection. Experimental results demonstrate that the proposed method outperforms existing approaches, achieving a detection accuracy of over 96% while also exhibiting enhanced generalization performance.