Zhang Xiangfei

Dr. Zhang Xiangfei

Hainan University, Haikou, Hainan, China

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

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

Representative Publications

View All Publications
27 October 2021 in IEEE Transactions on Biomedical Engineering
Verified
Journal Article
Closed access
Feng Feng ZhaoFeng Feng Zhao
Feng Feng Zhao
ZXZhang Xiangfei
Zhang Xiangfei
KTKim-Han Thung
Kim-Han Thung
NMNing Mao
Ning Mao
SLSeong-Whan Lee
Seong-Whan Lee
DSDinggang Shen
Dinggang Shen
Brain functional connectivity network (FCN) based on resting-state functional magnetic resonance imaging (rs-fMRI) has been widely used to identify neuropsychiatric disorders such as autism spectrum disorder (ASD). Most existing FCN-based methods only estimate the correlation between brain regions of interest (ROIs), without exploring more informative higher-level interactions among multiple ROIs which could be beneficial to disease diagnosis. To fully explore the discriminative information provided by different brain networks, a cluster-based multi-view high-order FCN (Ho-FCN) framework is proposed in this paper. Specifically, we first group the functional connectivity (FC) time series into different clusters and compute the multi-order central moment series for the FC time series in each cluster. Then we utilize the correlation of central moment series between different clusters to reveal the high-order FC relationships among multiple ROIs. In addition, to address the phase mismatch issue in conventional FCNs, we also adopt the central moments of the correlation time series as the temporal-invariance features to capture the dynamic characteristics of low-order dynamic FCN (Lo-D-FCN). Experimentalresults on the ABIDE dataset validate that: 1) the proposed multi-view Ho-FCNs is able to explore rich discriminative information for ASD diagnosis; 2) the phase mismatch issue can be well circumvented by using central moments; and 3) the combination of different types of FCNs can significantly improve the diagnostic accuracy of ASD (86.2%).

8 January 2023 in Mathematics
Verified
Journal Article
Open access
PDF file
ZXZhang Xiangfei
Zhang Xiangfei
FYFeng Yang
Feng Yang
YGYu Guo
Yu Guo
HYHang Yu
Hang Yu
ZWZhengxia Wang
Zhengxia Wang
FBFanyu Bu
Fanyu Bu
Recently, deep neural networks (DNNs) have achieved exciting things in many fields. However, the DNN models have been proven to divulge privacy, so it is imperative to protect the private information of the models. Differential privacy is a promising method to provide privacy protection for DNNs. However, existing DNN models based on differential privacy protection usually inject the same level of noise into parameters, which may lead to a balance between model performance and privacy protection. In this paper, we propose an adaptive differential privacy scheme based on entropy theory for training DNNs, with the aim of giving consideration to the model performance and protecting the private information in the training data. The proposed scheme perturbs the gradients according to the information gain of neurons during training, that is, in the process of back propagation, less noise is added to neurons with larger information gain, and vice-versa. Rigorous experiments conducted on two real datasets demonstrate that the proposed scheme is highly effective and outperforms existing solutions.

26 September 2022 in Frontiers in Neurology
Verified
Journal Article
Open access
YWYu Wang
Yu Wang
XDXiaohui Duan
Xiaohui Duan
XZXiao Zhou
Xiao Zhou
RWRenbin Wang
Renbin Wang
ZXZhang Xiangfei
Zhang Xiangfei
DPDantao Peng
Dantao Peng
Background: The Annexin A11 (ANXA11) gene has been newly identified as a causative gene of amyotrophic lateral sclerosis (ALS) with or without frontotemporal dementia (FTD). The current study aimed to investigate the ANXA11 mutations in a Chinese ALS–FTD or FTD cohort.Methods: We included ten probands/patients with suspected ALS–FTD or FTD. Mutational analysis of ANXA11 was performed through Next Generation Sequencing (NGS) and Sanger sequencing. We collected and reviewed clinical presentation, neuropsychology test results, brain-imaging findings, and electrophysiological examination findings.Results: In total, six probands presented with ALS–FTD, and four with behavior variant FTD (bv-FTD). We identified a non-synonymous heterozygous mutation (c.119A>G, p.D40G) of ANXA11 in proband 1, which is associated with ALS. However, this is the first report of the mutation causing ALS–FTD. Proband 1 started with abnormal behavior and progressed to classic upper motor nervous disease. Magnetic resonance imaging (MRI) showed significant bilateral temporal lobe atrophy and bilateral hyperintensities along the corticospinal tracts.18F-AV45-PET imaging showed negative amyloid deposits.Conclusion: ANXA11-related diseases have high clinical and genetic heterogeneity. Our study confirmed the contribution of ANXA11 mutations to ALS–FTD. The ANXA11 mutations established a complex genotype–phenotype correlation in ALS–FTD. Our research further elucidated the genetic mechanism of ALS–FTD and contributed to setting the foundation of future targeted therapy.

6 January 2023 in Diagnostics
Verified
Journal Article
Open access
PDF file
ZXZhang Xiangfei
Zhang Xiangfei
SSShayel Parvez Shams
Shayel Parvez Shams
HYHang Yu
Hang Yu
ZWZhengxia Wang
Zhengxia Wang
FBFanyu Bu
Fanyu Bu
Autism spectrum disorder (ASD) is a lifelong neurological disease, which seriously reduces the patients’ life quality. Generally, an early diagnosis is beneficial to improve ASD children’s life quality. Current methods based on samples from multiple sites for ASD diagnosis perform poorly in generalization due to the heterogeneity of the data from multiple sites. To address this problem, this paper presents a similarity measure-based approach for ASD diagnosis. Specifically, the few-shot learning strategy is used to measure potential similarities in the RS-fMRI data distributions, and, furthermore, a similarity function for samples from multiple sites is trained to enhance the generalization. On the ABIDE database, the presented approach is compared to some representative methods, such as SVM and random forest, in terms of accuracy, precision, and F1 score. The experimental results show that the experimental indicators of the proposed method are better than those of the comparison methods to varying degrees. For example, the accuracy on the TRINITY site is more than 5% higher than that of the comparison method, which clearly proves that the presented approach achieves a better generalization performance than the compared methods.

1 July 2017
Verified
Conference Paper
Closed access
TLTianfeng Liu
Tianfeng Liu
YDYongsheng Ding
Yongsheng Ding
Xin CaiXin Cai
Xin Cai
YZYifeng Zhu
Yifeng Zhu
ZXZhang Xiangfei
Zhang Xiangfei

21 August 2025 in Artificial Intelligence Review
Verified
Journal Article
Open access
PDF file
ZXZhang Xiangfei
Zhang Xiangfei
FBFanyu Bu
Fanyu Bu
Recently, we have witnessed the revolutionary development of deep learning. As the application domain of deep learning has expanded, its privacy risks have attracted attention since deep leaning methods often use private data for training. Some methods for attacking deep learning, such as membership inference attacks, increase the privacy risks of deep learning models. One risk-reducing defensive strategy with great potential is to apply some degree of random perturbation during the training (or other) phase. Therefore, differential privacy, as a privacy protection framework originally designed for publishing data, is widely used to protect the privacy of deep learning models due to its solid mathematical foundation. In this paper, we first introduce several attack methods that threaten deep learning. Then, we systematically review the cross-applications of differential privacy and deep learning to protect deep learning models. We encourage researchers to visually demonstrate the defense effects of their approaches in the literature rather than solely providing rigorous mathematical proofs. In addition to privacy, we also discuss and review the impact of differential privacy on the robustness, overfitting, and fairness of deep neural networks. Finally, we analyze some potential future research directions, highlighting the significant potential for differential privacy to make positive contributions to future deep learning systems.