Xiaoqi Luo
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Xiaoqi Luo has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- Ge Song
College of Mathematics and Informatics, South China Agricultural University, Guangzhou 510642, China
2 shared publications - Jiaxin Chen
College of Mathematics and Informatics, College of Software Engineering, South China Agricultural University, Guangzhou, China
2 shared publications - Xiaofei Yang
School of Electronics and Communication Engineering, Guangzhou University, Guangzhou 510006, China
2 shared publications - Fei Zhao
Research Base of Guangzhou Agricultural Heritage Systems, South China Agricultural University, Guangzhou, China
1 shared publication Hua Zhang
College of Information Engineering Shanghai Maritime University Shanghai China
1 shared publication- Jin Deng
South China Agricultural University
1 shared publication
Latest Publications
- Open Access
- 23 October 2026
- Published by Springer Nature in Journal on Image and Video Processing
CFN: a cross-fusion network for hyperspectral image classification
- 23 October 2026
- Published by Springer Nature in Journal on Image and Video Processing
Open AccessCFN: a cross-fusion network for hyperspectral image classification
- Open Access
- 7 April 2025
- Published by MDPI AG in Electronics
- Vol. 14 (7) , 1477
MDFFN: Multi-Scale Dual-Aggregated Feature Fusion Network for Hyperspectral Image Classification
Employing the multi-scale strategy in hyperspectral image (HSI) classification enables the exploration of complex land-cover structures with diverse shapes. However, existing multi-scale methods still have limitations for fine feature extraction and deep feature fusion, which hinder the further improvement of classification performance. In this paper, we propose a multi-scale dual-aggregated feature fusion network (MDFFN) for both balanced and imbalanced environments. The network comprises two main core modules: a multi-scale convolutional information embedding (MCIE) module and a dual aggregated cross-attention (DACA) module. The proposed MCIE module introduces a multi-scale pooling operation to aggregate local features, which efficiently highlights discriminative spectral–spatial information and especially learns key features in small target samples in the imbalanced environment. Furthermore, the proposed DACA module employs a cross-scale interaction strategy to realize the deep fusion of multi-scale features and designs a dual aggregation mechanism to mitigate the loss of information, which facilitates further spatial–spectral feature enhancement. The experimental results demonstrate that the proposed method outperforms state-of-the-art methods on three classical HSI datasets, proving the superiority of the proposed MDFFN.
- 7 April 2025
- Published by MDPI AG in Electronics
- Vol. 14 (7) , 1477
Open AccessMDFFN: Multi-Scale Dual-Aggregated Feature Fusion Network for Hyperspectral Image Classification
Employing the multi-scale strategy in hyperspectral image (HSI) classification enables the exploration of complex land-cover structures with diverse shapes. However, existing multi-scale methods still have limitations for fine feature extraction and deep feature fusion, which hinder the further improvement of classification performance. In this paper, we propose a multi-scale dual-aggregated feature fusion network (MDFFN) for both balanced and imbalanced environments. The network comprises two main core modules: a multi-scale convolutional information embedding (MCIE) module and a dual aggregated cross-attention (DACA) module. The proposed MCIE module introduces a multi-scale pooling operation to aggregate local features, which efficiently highlights discriminative spectral–spatial information and especially learns key features in small target samples in the imbalanced environment. Furthermore, the proposed DACA module employs a cross-scale interaction strategy to realize the deep fusion of multi-scale features and designs a dual aggregation mechanism to mitigate the loss of information, which facilitates further spatial–spectral feature enhancement. The experimental results demonstrate that the proposed method outperforms state-of-the-art methods on three classical HSI datasets, proving the superiority of the proposed MDFFN.
- 4 February 2024
- Published by Wiley in Journal of Neuroscience Research
- Vol. 102 (2) , e25297
Identification of genetic features that are associated with amplitude of low‐frequency fluctuation changes in schizophrenia using omics analysis
Genetic risk for schizophrenia is thought to trigger variation in clinical features of schizophrenia, but biological processes associated with neuronal activity in brain regions remain elusive. In this study, gene expression features were mapped to various sub‐regions of the brain by integrating low‐frequency amplitude features and gene expression data from the schizophrenia brain and using gene co‐expression network analysis of the Allen Transcriptome Atlas of the human brain from six donors to identify genetic features of brain regions and important associations with neuronal features. The results indicate that changes in the dynamic amplitude of low‐frequency fluctuation (dALFF) are mainly associated with transcriptome signature factors such as cortical layer synthesis, immune response, and expanded membrane transport. Further modular disease enrichment analysis revealed that the same set of signature genes associated with dALFF levels was enriched for multiple neurological biological processes. Finally, genetic profiling of individual modules identified multiple core genes closely related to schizophrenia, also potentially associated with neuronal activity. Thus, this paper explores genetic features of brain regions in the schizophrenia closely related to low‐frequency amplitude ratio levels based on imaging genetics, which suggests structural endophenotypes associated with schizophrenia.
- 4 February 2024
- Published by Wiley in Journal of Neuroscience Research
- Vol. 102 (2) , e25297
Identification of genetic features that are associated with amplitude of low‐frequency fluctuation changes in schizophrenia using omics analysis
Genetic risk for schizophrenia is thought to trigger variation in clinical features of schizophrenia, but biological processes associated with neuronal activity in brain regions remain elusive. In this study, gene expression features were mapped to various sub‐regions of the brain by integrating low‐frequency amplitude features and gene expression data from the schizophrenia brain and using gene co‐expression network analysis of the Allen Transcriptome Atlas of the human brain from six donors to identify genetic features of brain regions and important associations with neuronal features. The results indicate that changes in the dynamic amplitude of low‐frequency fluctuation (dALFF) are mainly associated with transcriptome signature factors such as cortical layer synthesis, immune response, and expanded membrane transport. Further modular disease enrichment analysis revealed that the same set of signature genes associated with dALFF levels was enriched for multiple neurological biological processes. Finally, genetic profiling of individual modules identified multiple core genes closely related to schizophrenia, also potentially associated with neuronal activity. Thus, this paper explores genetic features of brain regions in the schizophrenia closely related to low‐frequency amplitude ratio levels based on imaging genetics, which suggests structural endophenotypes associated with schizophrenia.