Jingxuan Geng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Jingxuan Geng has a total of 20 co-authors. Here are the top co-authors by number of shared publications:
- Chunhua Yang
Central South University
5 shared publications - Lijuan Lan
School of Automation, Central South University, Changsha, China
4 shared publications - Yonggang Li
Central South University
4 shared publications Chunhua Yang
3 shared publicationsYonggang Li
3 shared publications- Fengxue Zhang
School of Automation, Central South University, Changsha, China
2 shared publications
Latest Publications
- 25 May 2026
- Published by Elsevier in Measurement
- Vol. 283
RDiGSr-GKAN: Pollutant dispersion prediction based on Gaussian prior and Kolmogorov–Arnold Networks
- 25 May 2026
- Published by Elsevier in Measurement
- Vol. 283
RDiGSr-GKAN: Pollutant dispersion prediction based on Gaussian prior and Kolmogorov–Arnold Networks
- Open Access
- 18 March 2026
- Published by Elsevier in SSRN Electronic Journal
RDiGSr-GKAN: Pollutant Dispersion Prediction based on Gaussian Prior and Kolmogorov-Arnold Networks
Pollutant leaks can cause significant environmental damage. Achieving rapid and accurate prediction of pollutant dispersion concentration is key to miti- gating the impact of such accidents. Bridging the gap between the environ- mental rigidity of mechanistic models and the physical opacity of data-driven methods, this paper presents RDiGSr-GKAN, a novel framework that fuses a Gaussian prior with Kolmogorov-Arnold Networks (KAN) for enhanced pollutant dispersion prediction. This model constructs Gaussian feature through the Gaussian plume model to embed physical relationships, em- ploys the RDiGSr algorithm to optimize sample selection, and subsequently utilizes KAN network to learn complex mappings between variables, thereby enhancing both prediction performance and interpretability. Experiments on seven datasets, including Project Prairie Grass, demonstrate that the proposed model outperforms traditional machine learning and deep learning methods across multiple evaluation metrics. For instance, on the Hanford- 64 and Cabauw datasets, which have vastly diferent concentration ranges (0–14.9 mg/m3 and 0–2838 mg/m3 , respectively), the RMSE values achieved are 0.049 and 11.468, significantly better than those of comparative mod- els. Ablation experiments confirm the crucial role of Gaussian feature in model performance. This research provides a physics-guided, data-driven, high-precision modeling method for pollutant dispersion prediction, demon- strating excellent generalization capability and application potential.
- 18 March 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessRDiGSr-GKAN: Pollutant Dispersion Prediction based on Gaussian Prior and Kolmogorov-Arnold Networks
Pollutant leaks can cause significant environmental damage. Achieving rapid and accurate prediction of pollutant dispersion concentration is key to miti- gating the impact of such accidents. Bridging the gap between the environ- mental rigidity of mechanistic models and the physical opacity of data-driven methods, this paper presents RDiGSr-GKAN, a novel framework that fuses a Gaussian prior with Kolmogorov-Arnold Networks (KAN) for enhanced pollutant dispersion prediction. This model constructs Gaussian feature through the Gaussian plume model to embed physical relationships, em- ploys the RDiGSr algorithm to optimize sample selection, and subsequently utilizes KAN network to learn complex mappings between variables, thereby enhancing both prediction performance and interpretability. Experiments on seven datasets, including Project Prairie Grass, demonstrate that the proposed model outperforms traditional machine learning and deep learning methods across multiple evaluation metrics. For instance, on the Hanford- 64 and Cabauw datasets, which have vastly diferent concentration ranges (0–14.9 mg/m3 and 0–2838 mg/m3 , respectively), the RMSE values achieved are 0.049 and 11.468, significantly better than those of comparative mod- els. Ablation experiments confirm the crucial role of Gaussian feature in model performance. This research provides a physics-guided, data-driven, high-precision modeling method for pollutant dispersion prediction, demon- strating excellent generalization capability and application potential.
- 31 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Imaging
- Vol. 12 (25730436) , 203-215
HEDU-Net: Improving Spectral Snapshot Compressive Imaging With Explicable Degradation Compensation
With the widespread adoption of utilizing coded aperture snapshot spectral imaging (CASSI) to acquire hyperspectral images (HSIs), reconstruction algorithms become increasingly important as one of the most critical parts of CASSI. By formulating the iterative optimization problem as a multistage end-to-end neural network, the deep unfolding framework has made gratifying progress in improving the reconstruction reliability and fidelity. Nevertheless, there still exist three knotty issues limiting the performance of current reconstruction algorithms: 1) predetermined sensing matrix ignoring the gap between real and ideal degradation procedure. 2) ill-structured feature extraction and fusion network making it difficult to effectively recover the spatial texture and ensure spectral consistency. 3) inadequate stage interaction module, which hinders the transmission of useful information. To address these issues, in this paper, we propose a hyperspectral explicable degradation-compensatory unfolding neural network (HEDUNet), which attempts to dynamically compensate for the differences between ideal and real degradation procedures using a residual network under the deep unfolding strategy. Moreover, a spatial-spectral interaction transformer is designed via plugging the Swin transformer under the framework of the MixS2 transformer to independently excavate spatial or spectral features and fuse them thoroughly. Finally, to mitigate the information loss between adjacent stages, stage interaction is also enhanced by proposing a specific feature aggregation module based on the multi-scale attention mechanism. Experiments on both simulation and practical datasets show the state-of-the-art (SOTA) performance and wide application prospects of our method.
- 31 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Imaging
- Vol. 12 (25730436) , 203-215
HEDU-Net: Improving Spectral Snapshot Compressive Imaging With Explicable Degradation Compensation
With the widespread adoption of utilizing coded aperture snapshot spectral imaging (CASSI) to acquire hyperspectral images (HSIs), reconstruction algorithms become increasingly important as one of the most critical parts of CASSI. By formulating the iterative optimization problem as a multistage end-to-end neural network, the deep unfolding framework has made gratifying progress in improving the reconstruction reliability and fidelity. Nevertheless, there still exist three knotty issues limiting the performance of current reconstruction algorithms: 1) predetermined sensing matrix ignoring the gap between real and ideal degradation procedure. 2) ill-structured feature extraction and fusion network making it difficult to effectively recover the spatial texture and ensure spectral consistency. 3) inadequate stage interaction module, which hinders the transmission of useful information. To address these issues, in this paper, we propose a hyperspectral explicable degradation-compensatory unfolding neural network (HEDUNet), which attempts to dynamically compensate for the differences between ideal and real degradation procedures using a residual network under the deep unfolding strategy. Moreover, a spatial-spectral interaction transformer is designed via plugging the Swin transformer under the framework of the MixS2 transformer to independently excavate spatial or spectral features and fuse them thoroughly. Finally, to mitigate the information loss between adjacent stages, stage interaction is also enhanced by proposing a specific feature aggregation module based on the multi-scale attention mechanism. Experiments on both simulation and practical datasets show the state-of-the-art (SOTA) performance and wide application prospects of our method.
- 18 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-13
A Low-Dimensional Space-Based Redundancy Minimization Semisupervised Modeling Method for Total Nitrogen Detection
To address the typical issue of insufficient labeled samples in the process of real time total nitrogen (TN) detection, a low-dimensional space-based redundancy minimization semi-supervised learning (LDSRM) framework is proposed. Unlike other graph-based semi-supervised algorithms, the proposed method performs semi-supervised modeling in a low-dimensional space, significantly reducing computational costs and improving algorithm performance. Firstly, sparse feature selection is integrated into the initial graph model construction to preliminarily select key features from the original space and construct a low-dimensional space. Secondly, by minimizing the redundancy of features through Pearson correlation coefficient, the negative impact of redundant features is reduced, and the most representative features are further selected in the low-dimensional space, thereby improving regression accuracy. Finally, we apply the proposed method to practical TN detection. The results demonstrate that this method can establish accurate detection models that meet national testing standards with a relative error below 10% even with limited labeled samples available.
- 18 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-13
A Low-Dimensional Space-Based Redundancy Minimization Semisupervised Modeling Method for Total Nitrogen Detection
To address the typical issue of insufficient labeled samples in the process of real time total nitrogen (TN) detection, a low-dimensional space-based redundancy minimization semi-supervised learning (LDSRM) framework is proposed. Unlike other graph-based semi-supervised algorithms, the proposed method performs semi-supervised modeling in a low-dimensional space, significantly reducing computational costs and improving algorithm performance. Firstly, sparse feature selection is integrated into the initial graph model construction to preliminarily select key features from the original space and construct a low-dimensional space. Secondly, by minimizing the redundancy of features through Pearson correlation coefficient, the negative impact of redundant features is reduced, and the most representative features are further selected in the low-dimensional space, thereby improving regression accuracy. Finally, we apply the proposed method to practical TN detection. The results demonstrate that this method can establish accurate detection models that meet national testing standards with a relative error below 10% even with limited labeled samples available.
- 30 May 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Electronics
- Vol. 72 (4) , 4041-4052
CSD: An Online Spectral Sensing Method for Wastewater Quality Monitoring Based on Compressed Sensing and Incremental Learning
The outstanding spectral resolution of full-spectrum detection (FSD) ensures excellent performance for complex scenarios in which target signals are affected by particle interference. However, FSD is limited by the cost of its measurement devices and demanding install requirements. Therefore, it is not always practical to utilize FSD for online water quality monitoring in wastewater treatment plants. In this article, we develop a novel detection approach entitled “compressive spectrum detection (CSD)” to overcome the hardware restrictions posed by FSD. An intelligent source-encoding laser is first developed to perform spectrum encoding, which avoids the utilization of sophisticated equipment and reduces the detection cost. Subsequently, a dual-stage compressive detection framework is proposed based on incremental learning to accurately reconstruct spectral signals with full-spectrum resolution, which consisted of three innovative algorithms and could solve difficulties brought about by sample insufficiency and changing environments in practical situations. Based on our constructed online detection prototype, the superiority of CSD is evaluated through practical application in which the training samples are reduced to a quarter of their original size with an overall improvement in detection precision greater than 50%.
- 30 May 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Electronics
- Vol. 72 (4) , 4041-4052
CSD: An Online Spectral Sensing Method for Wastewater Quality Monitoring Based on Compressed Sensing and Incremental Learning
The outstanding spectral resolution of full-spectrum detection (FSD) ensures excellent performance for complex scenarios in which target signals are affected by particle interference. However, FSD is limited by the cost of its measurement devices and demanding install requirements. Therefore, it is not always practical to utilize FSD for online water quality monitoring in wastewater treatment plants. In this article, we develop a novel detection approach entitled “compressive spectrum detection (CSD)” to overcome the hardware restrictions posed by FSD. An intelligent source-encoding laser is first developed to perform spectrum encoding, which avoids the utilization of sophisticated equipment and reduces the detection cost. Subsequently, a dual-stage compressive detection framework is proposed based on incremental learning to accurately reconstruct spectral signals with full-spectrum resolution, which consisted of three innovative algorithms and could solve difficulties brought about by sample insufficiency and changing environments in practical situations. Based on our constructed online detection prototype, the superiority of CSD is evaluated through practical application in which the training samples are reduced to a quarter of their original size with an overall improvement in detection precision greater than 50%.
- 19 July 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 71 (00189456) , 1-13
A Novel Semisupervised Regression Method for Online Total Nitrogen Detection Using Double Structural Sparse Feature Extraction
To solve the problem of insufficient labeled samples in online total nitrogen (TN) detection, a novel semisupervised learning (SSL) method called double regularized structure graph learning (DRSGL) was proposed, which can effectively extract useful features and support the TN detection equipment to establish accurate detection models with few labeled samples. Based on temporal and spectral informativity, a high-quality graph structure method was designed first, which utilizes the spectrum-temporal prior knowledge hidden in the spectrum and enhances the efficiency of the graph model. Then, considering the double sparsity of TN spectrum samples, a double structural sparse feature selection method (DS 2 FS) was invented accordingly, which can excavate useful information from both spectral and temporal dimensions. Finally, to address the insufficient problem of labeled samples, an adaptive SSL method was constructed by combining graph learning strategy and DS 2 FS and applied to the TN rapid detection prototype, which can iteratively select important features and update graph structure of samples correspondingly. According to the experimental results based on practical application, DRSGL can effectively solve the problem brought by the insufficiency of labeled samples, which can utilize only 20% labeled samples to establish an accurate detection model satisfied national detection standard with a relative error lower than 10%.
- 19 July 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 71 (00189456) , 1-13
A Novel Semisupervised Regression Method for Online Total Nitrogen Detection Using Double Structural Sparse Feature Extraction
To solve the problem of insufficient labeled samples in online total nitrogen (TN) detection, a novel semisupervised learning (SSL) method called double regularized structure graph learning (DRSGL) was proposed, which can effectively extract useful features and support the TN detection equipment to establish accurate detection models with few labeled samples. Based on temporal and spectral informativity, a high-quality graph structure method was designed first, which utilizes the spectrum-temporal prior knowledge hidden in the spectrum and enhances the efficiency of the graph model. Then, considering the double sparsity of TN spectrum samples, a double structural sparse feature selection method (DS 2 FS) was invented accordingly, which can excavate useful information from both spectral and temporal dimensions. Finally, to address the insufficient problem of labeled samples, an adaptive SSL method was constructed by combining graph learning strategy and DS 2 FS and applied to the TN rapid detection prototype, which can iteratively select important features and update graph structure of samples correspondingly. According to the experimental results based on practical application, DRSGL can effectively solve the problem brought by the insufficiency of labeled samples, which can utilize only 20% labeled samples to establish an accurate detection model satisfied national detection standard with a relative error lower than 10%.
- 1 August 2021
- Published by Elsevier in Analytica Chimica Acta
- Vol. 1171, 338635
iPCPA: Interval permutation combination population analysis for spectral wavelength selection
- 1 August 2021
- Published by Elsevier in Analytica Chimica Acta
- Vol. 1171, 338635
iPCPA: Interval permutation combination population analysis for spectral wavelength selection
- Open Access
- 4 March 2021
- Published by Copernicus GmbH
A rapid total nitrogen determination prototype for wastewater treatment plants online detection
The online automatic detection for the concentration of total nitrogen (TN) is a critical problem in wastewater treatment plants (WWTPs). The over-discharge of TN can cause severe environmental problems such as aquatic eutrophication and ecosystem dysfunction, and the TN concentration in each wastewater treatment process can also reflect the processing statement of WWTPs and ensure its stable operation. However, determining the TN concentration timely is always a difficult task. According to the traditional TN detection approach, the concentration of TN is determined after the oxidative digestion process, which is a complex chemical reaction process and usually requires 30 minutes to 1 hour. Considering the actual operation situation, this traditional method can hardly satisfy the real-time requirement of WWTPs, which can only be used as a kind of validation approach. To solve this problem, in this paper, we design a novel automatic detection prototype of TN. Instead of determining the concentration of TN after the process of oxidative digestion, the ultraviolet spectrum is used to non-destructive detect the concentration of nitrate during the whole oxidative digestion process. Based on the principle of competitive response and chemical reaction kinetics, for different water samples with different TN concentrations, their oxidative digestion processes are different even in the early reaction stage. Therefore, we can use the early reaction properties to determine the TN concentration, thereby shortening the necessary detection time. Based on experimental data collected from real water samples, our prototype can not only efficiently shorten the detection time of the TN concentration, but also ensure satisfactory detection accuracy.
- 4 March 2021
- Published by Copernicus GmbH
Open AccessA rapid total nitrogen determination prototype for wastewater treatment plants online detection
The online automatic detection for the concentration of total nitrogen (TN) is a critical problem in wastewater treatment plants (WWTPs). The over-discharge of TN can cause severe environmental problems such as aquatic eutrophication and ecosystem dysfunction, and the TN concentration in each wastewater treatment process can also reflect the processing statement of WWTPs and ensure its stable operation. However, determining the TN concentration timely is always a difficult task. According to the traditional TN detection approach, the concentration of TN is determined after the oxidative digestion process, which is a complex chemical reaction process and usually requires 30 minutes to 1 hour. Considering the actual operation situation, this traditional method can hardly satisfy the real-time requirement of WWTPs, which can only be used as a kind of validation approach. To solve this problem, in this paper, we design a novel automatic detection prototype of TN. Instead of determining the concentration of TN after the process of oxidative digestion, the ultraviolet spectrum is used to non-destructive detect the concentration of nitrate during the whole oxidative digestion process. Based on the principle of competitive response and chemical reaction kinetics, for different water samples with different TN concentrations, their oxidative digestion processes are different even in the early reaction stage. Therefore, we can use the early reaction properties to determine the TN concentration, thereby shortening the necessary detection time. Based on experimental data collected from real water samples, our prototype can not only efficiently shorten the detection time of the TN concentration, but also ensure satisfactory detection accuracy.