Author name cluster

Zhe Sun

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

14 papers

1 author row

EAAI Journal 2026 Journal Article

Complex parameter estimation based on adaptive population renewal-based differential evolution algorithm and its application

Zhe Sun
Junlong Sun
Jiajia Cheng
Kai Yuan
Yunrui Bi
Zhixin Sun

Complex parameter estimation is widely used in system control, its accuracy plays a crucial role in system performance improvement. Therefore, to address the complex parameter estimation problem, this paper proposes an adaptive population renewal-based differential evolution (APRDE) algorithm. Inspired by the theory of natural selection, a population renewal strategy is designed before each iteration to steer the population towards the quest for the global optimum. Meanwhile, adaptive scaling factor and adaptive crossover factor are further proposed respectively, increasing the population diversity and enhancing the algorithm's global search capability. When compared to other algorithms evaluated on benchmark functions, the APRDE algorithm excels in terms of both convergence accuracy and speed. In recent years, research on proton exchange membrane fuel cell (PEMFC) systems has gained significant attention. Based on this, the APRDE algorithm is used to estimate parameters for the PEMFC model. Experimental results reveal that, in contrast to existing algorithms, the proposed approach offers greater dynamism and efficiency in PEMFC model parameter estimation.

Details DOI

YNIMG Journal 2025 Journal Article

Hippocampal subfields in aging: Sex-specific trajectories in structure and hemodynamics

Jiaqi Wen
Chenyang Li
Zhe Sun
Chao Wang
Jiangyang Zhang
Xiaojun Guan
Xiaojun Xu
Thomas Wisniewski

Sex differences in hippocampal aging have been increasingly recognized, with females showing greater vulnerability to neurodegeneration, particularly after menopause. However, the underlying neurobiological mechanisms remain unclear, especially at the level of hippocampal subfields. Leveraging high-resolution T1-, T2-weighted, and multi-delay arterial spin labeling MRI from 650 adults in the Human Connectome Project-Aging dataset, we examined sex-specific alterations in hippocampal subfield volume, arterial transit time (ATT), and cerebral blood flow (CBF) across the adult lifespan. All hippocampal subfields showed age-related atrophy and ATT prolongation. An age × sex interaction effect on ATT was observed in CA1 and CA2, indicating that age-related increases in ATT were more pronounced in females than in males in these subfields. Moreover, females exhibited more pronounced hippocampal subfields CBF reductions with aging and atrophy, while males showed relatively preserved CBF, with an increase in subiculum perfusion. Furthermore, CA1 showed the lowest perfusion and the strongest association with atrophy among hippocampal subfields. To investigate the potential impact of menopausal hormonal changes on sex-specific patterns, we explored the hypothalamic structure and hemodynamic alterations during aging and their effects on the hippocampus, given that hypothalamus regulates gonadal hormone secretion through the hypothalamic-pituitary-gonadal axis. We found significant hypothalamic atrophy during aging in both sexes, accompanied by ATT prolongation exclusively in females, which was associated with hippocampal atrophy and impaired hemodynamics. Our study highlights the intricate interplay between hippocampal structure and vascular function, revealing sex- and subfield-specific aging trajectories. These findings provide a normative quantitative imaging reference to age-related neurodegenerative diseases such as Alzheimer's Disease.

Details DOI

TCS Journal 2024 Journal Article

A new McEliece-type cryptosystem using Gabidulin-Kronecker product codes

Zhe Sun
Jincheng Zhuang
Zimeng Zhou
Fang-Wei Fu

This paper presents a new McEliece-type cryptosystem using Gabidulin-Kronecker product codes in the rank metric. The contributions of this paper are as follows. Firstly, we propose a new Gabidulin-Kronecker product code which is a kind of block circulant code, and give an efficient decoding algorithm. Secondly, we design a one-way secure public key encryption scheme based on the Gabidulin-Kronecker product codes. Thirdly, we obtain an IND-CCA2 secure public key encryption scheme by converting our one-way secure public key encryption scheme under the hardness assumption of the RSD Dual Problem. In terms of efficiency, our scheme has a smaller public key size by taking advantage of the block circulant structure. For 128-bit security, the public key size of our proposal is 13% of Lau-Tan's cryptosystem (in the rank metric), and 19% of BIKE (in the Hamming metric). In terms of security, our scheme can resist Overbeck attack, Coggia-Couvreur attack and Sendrier attack.

Details DOI

EAAI Journal 2024 Journal Article

An meta-cognitive based logistics human resource modeling and optimal scheduling

Zhe Sun
Zhenlong Tian
Xiangpeng Xie
Zhixin Sun
Xu Zhang
Gangfu Gong

Resource allocation in logistics poses intricate challenges due to its complexity and non-linearity. This paper presents a novel warehouse human resource scheduling model that combines queuing theory and integer programming. We introduce the Adaptive Quantum Differential Evolution (AQDE) algorithm, inspired by quantum computation, to address the optimization complexities. Our approach demonstrates superior global convergence accuracy and speed compared to other DE variants and evolutionary algorithms. The efficacy of AQDE is validated through experiments using real logistics warehouse data, showcasing its efficiency in allocating logistics resources.

Details DOI

EAAI Journal 2024 Journal Article

Cross-domain facial expression recognition based on adversarial attack fine-tuning learning

Yingrui Zhang
Zhe Sun

Expression recognition is important in artificial intelligence research and has broad application prospects in medical care and transportation. However, owing to differences in lighting, culture, ethnicity, etc. , cross-domain expression recognition is difficult. Analysis of the mechanism related to graph error discrimination is critical for improving cross-domain expression recognition performance. However, effective methods for expression error prediction and model performance analysis are lacking. In this study, an adversarial attack method is proposed to realise the analysis and adversarial attack fine-tuning learning is used to improve cross-domain expression recognition. To implement this method, the adversarial attack dataset must include domain differences in brightness, contrast, grayscale, Gaussian perturbation, and geometric perturbation. The critical graph feature fusion network, constructed using a residual network, local features, and prior graph-learning techniques, guarantees the realisation of this method. An adversarial attack expression recognition experiment revealed the influence of the attribute parameters of the database on graph error discrimination and illustrated that fine-tuning learning can prevent graph error discrimination. In the adversarial attack fine-tuning cross-domain expression recognition experiment, an average improvement of 7. 09% in the recognition accuracy was achieved on the four datasets, even without introducing any information about the target dataset. It can be concluded that the model achieved significant improvement in feature extraction performance and expression recognition range. Adversarial attack fine-tuning learning was integrated into the two best-performing cross-domain recognition methods, achieving an average accuracy improvement of no less than 6. 93% on four datasets, demonstrating the universality of the proposed method.

Details DOI

EAAI Journal 2024 Journal Article

Enabling temporal–spectral decoding in multi-class single-side upper limb classification

Hao Jia
Shuning Han
Cesar F. Caiafa
Feng Duan
Yu Zhang
Zhe Sun
Jordi Solé-Casals

This manuscript presents a novel approach for decoding pre-movement patterns from brain signals using a two-stage-training temporal–spectral neural network (TTSNet). The TTSNet employs a combination of filter bank task-related component analysis (FBTRCA) and convolutional neural network (CNN) techniques to enhance the classification of single-upper limb movements in non-invasive brain–computer interfaces (BCIs). In our previous work, we introduced the FBTRCA method which utilized filter banks and spatial filters to handle spectral and spatial information, respectively. However, we observed limitations in the temporal decoding phase, where correlation features failed to effectively utilize temporal information because of misaligned onset and noisy spikes. To address this issue, our proposed method focuses on analyzing multi-channel signals in the temporal–spectral domain. The TTSNet first divides the signals into various filter banks, employing task-related component analysis to reduce dimensionality and eliminate noise, respectively. Subsequently, a CNN is employed to optimize the temporal characteristics of the signals and extract class-related features. Finally, the class-related features from all filter banks are concatenated and classified using the fully connected layer. To evaluate the effectiveness of our proposed method, we conducted experiments on two publicly available datasets. In binary classification tasks, the TTSNet achieved an improved accuracy of 0. 7707 ± 0. 1168, surpassing the performance of EEGNet (accuracy: 0. 7340 ± 0. 1246) and FBTRCA (accuracy: 0. 7487 ± 0. 1250). In multi-class tasks, TTSNet achieved an accuracy of 0. 4588 ± 0. 0724, exhibiting a 4. 27% and 3. 95% accuracy increase over EEGNet and FBTRCA, respectively. The findings of this study suggest that the proposed TTSNet method holds promise for detecting limb movements and assisting in the rehabilitation of stroke patients. The classification of single-side limb movements is expected to facilitate the interaction between patients and external environment by increasing the number of control commands in BCIs.

Details DOI

YNIMG Journal 2024 Journal Article

In vivo mapping of hippocampal venous vasculature and oxygenation using susceptibility imaging at 7T

Chenyang Li
Sagar Buch
Zhe Sun
Marco Muccio
Li Jiang
Yongsheng Chen
E. Mark Haacke
Jiangyang Zhang

Mapping the small venous vasculature of the hippocampus in vivo is crucial for understanding how functional changes of hippocampus evolve with age. Oxygen utilization in the hippocampus could serve as a sensitive biomarker for early degenerative changes, surpassing hippocampal tissue atrophy as the main source of information regarding tissue degeneration. Using an ultrahigh field (7T) susceptibility-weighted imaging (SWI) sequence, it is possible to capture oxygen-level dependent contrast of submillimeter-sized vessels. Moreover, the quantitative susceptibility mapping (QSM) results derived from SWI data allow for the simultaneous estimation of venous oxygenation levels, thereby enhancing the understanding of hippocampal function. In this study, we proposed two potential imaging markers in a cohort of 19 healthy volunteers aged between 20 and 74 years. These markers were: 1) hippocampal venous density on SWI images and 2) venous susceptibility ( Δ χ vein ) in the hippocampus-associated draining veins (the inferior ventricular veins (IVV) and the basal veins of Rosenthal (BVR) using QSM images). They were chosen specifically to help characterize the oxygen utilization of the human hippocampus and medial temporal lobe (MTL). As part of the analysis, we demonstrated the feasibility of measuring hippocampal venous density and Δ χ vein in the IVV and BVR at 7T with high spatial resolution (0. 25 × 0. 25 × 1 mm3). Our results demonstrated the in vivo reconstruction of the hippocampal venous system, providing initial evidence regarding the presence of the venous arch structure within the hippocampus. Furthermore, we evaluated the age effect of the two quantitative estimates and observed a significant increase in Δ χ vein for the IVV with age (p = 0. 006, r2 = 0. 369). This may suggest the potential application of Δ χ vein in IVV as a marker for assessing changes in atrophy-related hippocampal oxygen utilization in normal aging and neurodegenerative diseases such as AD and dementia.

Details DOI

EAAI Journal 2024 Journal Article

The evolution of object detection methods

Yibo Sun
Zhe Sun
Weitong Chen

Object detection is one of the most important domains in computer vision tasks, which is an important branch of artificial intelligence. It aims at finding and locating the accurate position of objects in given pictures or videos. With the development of deep learning techniques, more powerful and robust algorithms have emerged to deal with multi-scale, high-level features to overcome the limitations of traditional pipeline of object detectors. The popularity of transformer framework enables larger capacity datasets by processing self-attention mechanism, and the object detection methods have evolved into a new era. This paper first reviews traditional object detection pipeline and brief history of deep learning, afterwards it focuses on the classification of deep learning-based object detection methods covering Convolution Neural Network based and transformer-based methods. Commonly used datasets and metrics are also covered in the next part. The Convolution Neural Network based methods mainly contain two-stage and one-stage detectors, Convolution Neural Network is the underlying structure of these methods convolutional stages are fundamental parts. Transformer-based models convert traditional object detection issues into end-to-end detection, which is widely used in dealing with images. Finally, the promising future of object detection areas are listed to show guidance on future work.

Details DOI

JBHI Journal 2023 Journal Article

Multi-Class Classification of Upper Limb Movements With Filter Bank Task-Related Component Analysis

Hao Jia
Fan Feng
Cesar F. Caiafa
Feng Duan
Yu Zhang
Zhe Sun
Jordi Solé-Casals

The classification of limb movements can provide with control commands in non-invasive brain-computer interface. Previous studies on the classification of limb movements have focused on the classification of left/right limbs; however, the classification of different types of upper limb movements has often been ignored despite that it provides more active-evoked control commands in the brain-computer interface. Nevertheless, few machine learning method can be used as the state-of-the-art method in the multi-class classification of limb movements. This work focuses on the multi-class classification of upper limb movements and proposes the multi-class filter bank task-related component analysis (mFBTRCA) method, which consists of three steps: spatial filtering, similarity measuring and filter bank selection. The spatial filter, namely the task-related component analysis, is first used to remove noise from EEG signals. The canonical correlation measures the similarity of the spatial-filtered signals and is used for feature extraction. The correlation features are extracted from multiple low-frequency filter banks. The minimum-redundancy maximum-relevance selects the essential features from all the correlation features, and finally, the support vector machine is used to classify the selected features. The proposed method compared against previously used models is evaluated using two datasets. mFBTRCA achieved a classification accuracy of 0. 4193 $\pm$ 0. 0780 (7 classes) and 0. 4032 $\pm$ 0. 0714 (5 classes), respectively, which improves on the best accuracies achieved using the compared methods (0. 3590 $\pm$ 0. 0645 and 0. 3159 $\pm$ 0. 0736, respectively). The proposed method is expected to provide more control commands in the applications of non-invasive brain-computer interfaces.

Details DOI

JBHI Journal 2023 Journal Article

Privacy-Preserving Multi-Source Domain Adaptation for Medical Data

Tianyi Han
Xiaoli Gong
Fan Feng
Jin Zhang
Zhe Sun
Yu Zhang

Great progress has been made in diagnosing medical diseases based on deep learning. Large-scale medical data are expected to improve deep learning performance further. It is almost impossible for a single institution to collect so much data due to the time-consuming and costly collection and labeling of medical data. Many studies have turned attention to data sharing among multiple medical institutions. However, due to different data acquiring and processing procedures, multiple institutions' medical data is characterized by distribution heterogeneity. Besides, the protection of patient privacy in medical data sharing has also been a common concern. To simultaneously address the problems of heterogeneous data distribution and privacy protection, we propose a novel multi-source source free domain adaptation. When aligning distributed heterogeneous data, our method only require to transfer the pre-trained source models rather than the direct source domain data, thus protecting patients' privacy. In addition, it has the advantages of being efficient and less costly in network resources. The proposed method is evaluated on the multi-site fMRI database Autism Brain Imaging Data Exchange (ABIDE) and yields an average accuracy of 69. 37%. We also analyzed its effectiveness on network resource-saving and conducted additional experiments on Camelyon17 to validate the generalization.

Details DOI

AAAI Conference 2021 Conference Paper

Generalized Relation Learning with Semantic Correlation Awareness for Link Prediction

Yao Zhang
Xu Zhang
Jun Wang
Hongru Liang
Wenqiang Lei
Zhe Sun
Adam Jatowt
Zhenglu Yang

Developing link prediction models to automatically complete knowledge graphs has recently been the focus of significant research interest. The current methods for the link prediction task have two natural problems: 1) the relation distributions in KGs are usually unbalanced, and 2) there are many unseen relations that occur in practical situations. These two problems limit the training effectiveness and practical applications of the existing link prediction models. We advocate a holistic understanding of KGs and we propose in this work a unified Generalized Relation Learning framework GRL to address the above two problems, which can be plugged into existing link prediction models. GRL conducts a generalized relation learning, which is aware of semantic correlations between relations that serve as a bridge to connect semantically similar relations. After training with GRL, the closeness of semantically similar relations in vector space and the discrimination of dissimilar relations are improved. We perform comprehensive experiments on six benchmarks to demonstrate the superior capability of GRL in the link prediction task. In particular, GRL is found to enhance the existing link prediction models making them insensitive to unbalanced relation distributions and capable of learning unseen relations.

PDF Details

AAAI Conference 2021 Short Paper

LAMS: A Location-aware Approach for Multimodal Summarization (Student Abstract)

Zhengkun Zhang
Jun Wang
Zhe Sun
Zhenglu Yang

Multimodal summarization aims to refine salient information from multiple modalities, among which texts and images are two mostly discussed ones. In recent years, many fantastic works have emerged in this field by modeling imagetext interactions; however, they neglect the fact that most of multimodal documents have been elaborately organized by their writers. This means that a critical organized factor has long been short of enough attention, that is, image locations, which may carry illuminating information and imply the key contents of a document. To address this issue, we propose a location-aware approach for multimodal summarization (LAMS) based on Transformer. We investigate image locations for multimodal summarization via a stack of multimodal fusion block, which can formulate the high-order interactions among images and texts. An extensive experimental study on an extended multimodal dataset validates the superior summarization performance of the proposed model.

PDF Details

AAAI Conference 2021 Conference Paper

News Content Completion with Location-Aware Image Selection

Zhengkun Zhang
Jun Wang
Adam Jatowt
Zhe Sun
Shao-Ping Lu
Zhenglu Yang

News, as one of the fundamental social media types, typically contains both texts and images. Image selection, which involves choosing appropriate images according to some specified contexts, is crucial for formulating good news. However, it presents two challenges: where to place images and which images to use. The difficulties associated with this wherewhich problem lie in the fact that news typically contains linguistically rich text that delivers complex information and more than one image. In this paper, we propose a novel endto-end two-stage framework to address these issues comprehensively. In the first stage, we identify key information in news by using location embeddings, which represent the local contextual information of each candidate location for image insertion. Then, in the second stage, we thoroughly examine the candidate images and select the most context-related ones to insert into each location identified in the first stage. We also introduce three insertion strategies to formulate different scenarios influencing the image selection procedure. Extensive experiments demonstrate the consistent superiority of the proposed framework in image selection.

PDF Details

AIIM Journal 2020 Journal Article

Real-world data medical knowledge graph: construction and applications

Linfeng Li
Peng Wang
Jun Yan
Yao Wang
Simin Li
Jinpeng Jiang
Zhe Sun
Buzhou Tang

Objective Medical knowledge graph (KG) is attracting attention from both academic and healthcare industry due to its power in intelligent healthcare applications. In this paper, we introduce a systematic approach to build medical KG from electronic medical records (EMRs) with evaluation by both technical experiments and end to end application examples. Materials and Methods The original data set contains 16, 217, 270 de-identified clinical visit data of 3, 767, 198 patients. The KG construction procedure includes 8 steps, which are data preparation, entity recognition, entity normalization, relation extraction, property calculation, graph cleaning, related-entity ranking, and graph embedding respectively. We propose a novel quadruplet structure to represent medical knowledge instead of the classical triplet in KG. A novel related-entity ranking function considering probability, specificity and reliability (PSR) is proposed. Besides, probabilistic translation on hyperplanes (PrTransH) algorithm is used to learn graph embedding for the generated KG. Results A medical KG with 9 entity types including disease, symptom, etc. was established, which contains 22, 508 entities and 579, 094 quadruplets. Compared with term frequency - inverse document frequency (TF/IDF) method, the normalized discounted cumulative gain (NDCG@10) increased from 0. 799 to 0. 906 with the proposed ranking function. The embedding representation for all entities and relations were learned, which are proven to be effective using disease clustering. Conclusion The established systematic procedure can efficiently construct a high-quality medical KG from large-scale EMRs. The proposed ranking function PSR achieves the best performance under all relations, and the disease clustering result validates the efficacy of the learned embedding vector as entity’s semantic representation. Moreover, the obtained KG finds many successful applications due to its statistics-based quadruplet. where N c o m i n is a minimum co-occurrence number and R is the basic reliability value. The reliability value can measure how reliable is the relationship between Si and Oij. The reason for the definition is the higher value of N co(Si, Oij ), the relationship is more reliable. However, the reliability values of the two relationships should not have a big difference if both of their co-occurrence numbers are very big. In our study, we finally set N c o m i n = 10 and R = 1 after some experiments. For instance, if co-occurrence numbers of three relationships are 1, 100 and 10000, their reliability values are 1, 2. 96 and 5 respectively.

Details DOI