Author name cluster

Jun Jiang

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.

13 papers

2 author rows

JBHI Journal 2026 Journal Article

FEI-Hi: Federated Edge Intelligence for Healthcare Informatics

Chunjiong Zhang
Gaoyang Shan
Byeong-hee Roh
Fa Zhu
Jun Jiang

As the Internet of Things (IoT) and artificial intelligence (AI) technologies are rapidly evolving, smart healthcare has emerged as a transformative solution to enhance healthcare quality and optimize resource allocation. This study introduces FEI-Hi, a federated edge intelligence paradigm that integrates edge computing with federated learning (FL) to enable secure and efficient medical data processing. FEI-Hi comprises three principal layers: FL layer, which facilitates cross-device collaborative training through encrypted model updates; aggregation layer, which refines the global model by consolidating updates; and edge layer, which performs local data processing and model inference. FEI-Hi leverages distributed intelligent computation, model parameter compression, and efficient node clustering to enhance the accuracy and efficiency of medical data processing significantly. By employing Wasserstein distance for clustering and parameter selection, FEI-Hi ensures model convergence and stability. Experimental results on multiple medical datasets demonstrate a 30% improvement in the model training speed and an F1-score exceeding 90%, surpassing the state-of-the-art (SOTA) benchmarks in model parameter transfer efficiency, training speed, and accuracy.

Details DOI

JBHI Journal 2026 Journal Article

Interictal Epileptiform Discharge Detection Using Dual-Domain Features and GAN

Wenhao Rao
Jiayang Guo
Chunran Zhu
Meiyan Xu
Naian Xiao
Yijie Pan
Ling Zhang
Xiaowen Ye

Interictal Epileptiform Discharge is essential for identifying epilepsy. However, the unpredictable and non-stationary nature of electroencephalogram (EEG) patterns poses considerable challenges for reliable identification. Manual interpretation of EEG is subjective and time-consuming. With advancements in machine learning and deep learning, computer-aided approaches for automated IED detection have been rapidly developed. The state-of-the-art convolutional neural network (CNN)-based methods have shown promising results but struggle to capture long-term dependencies in time-series data. In contrast, Transformer excels at modeling sequential information through self-attention mechanisms, overcoming the CNN limitations. This study proposes an IED Detector (IEDD) that integrates convolutional layers and a Transformer to detect IEDs. The IEDD initially employs convolutional layers to extract local features of IEDs, followed by a Transformer to model long-term dependencies. To further extract spatial features, EEG data are represented as a three-dimensional tensor with embedded channel topology, where a CNN captures spatial features at each sampling point and a Long Short-Term Memory (LSTM) network models their temporal evolution. Additionally, due to the scarcity of IED data, a novel Transformer-based Generative Adversarial Network (GAN) is developed to augment the IED dataset. Experimental results show the proposed approach achieves an average accuracy of 96. 11% on the augmented Dataset 1 and 95. 25% on Dataset 2 for binary classification, with an average sensitivity of 87. 26% and precision of 89. 96% for multi-label classification. These findings provide valuable insights into advancing deep learning and Transformer-based approaches for automated IED detection.

Details DOI

NeurIPS Conference 2025 Conference Paper

PointTruss: K-Truss for Point Cloud Registration

Yue Wu
Jun Jiang
Yongzhe Yuan
Maoguo Gong
Qiguang Miao
Hao Li
Mingyang Zhang
Wenping Ma

Point cloud registration is a fundamental task in 3D computer vision. Recent advances have shown that graph-based methods are effective for outlier rejection in this context. However, existing clique-based methods impose overly strict constraints and are NP-hard, making it difficult to achieve both robustness and efficiency. While the k-core reduces computational complexity, which only considers node degree and ignores higher-order topological structures such as triangles, limiting its effectiveness in complex scenarios. To overcome these limitations, we introduce the $k$-truss from graph theory into point cloud registration, leveraging triangle support as a constraint for inlier selection. We further propose a consensus voting-based low-scale sampling strategy to efficiently extract the structural skeleton of the point cloud prior to $k$-truss decomposition. Additionally, we design a spatial distribution score that balances coverage and uniformity of inliers, preventing selections that concentrate on sparse local clusters. Extensive experiments on KITTI, 3DMatch, and 3DLoMatch demonstrate that our method consistently outperforms both traditional and learning-based approaches in various indoor and outdoor scenarios, achieving state-of-the-art results.

PDF Details

NeurIPS Conference 2025 Conference Paper

StegoZip: Enhancing Linguistic Steganography Payload in Practice with Large Language Models

Jun Jiang
Zijin Yang
Weiming Zhang
Nenghai Yu
Kejiang Chen

Generative steganography has emerged as an active research area, yet its practical system is constrained by the inherent secret payload limitation caused by low entropy in generating stego texts. This payload limitation necessitates the use of lengthy stego texts or frequent transmissions, which increases the risk of suspicion by adversaries. Previous studies have mainly focused on payload enhancement through optimized entropy utilization while overlooking the crucial role of secret message processing. To address this gap, we propose StegoZip, a framework that leverages large language models to optimize secret message processing. StegoZip consists of two core components: semantic redundancy pruning and index-based compression coding. The former dynamically prunes the secret message to extract a low-semantic representation, whereas the latter further compresses it into compact binary codes. When integrated with state-of-the-art steganographic methods under lossless decoding, StegoZip achieves 2. 5$\times$ the payload of the baselines while maintaining comparable processing time in practice. This enhanced payload significantly improves covertness by mitigating the risks associated with frequent transmissions while maintaining provable content security.

PDF Details

EAAI Journal 2025 Journal Article

Synthetic data enhancement using diffusion models for improved miscanthus identification and bioenergy extraction

Xinyue Wang
Xiangdong Chen
Jun Jiang
Ronggao Gong
Biao Wang

Miscanthus, a high-yielding perennial grass pivotal for bioenergy production, requires precise species identification to optimize bioenergy extraction. However, limited annotated spectral datasets hinder robust classification model development. To address this challenge, the paper proposes a novel diffusion probabilistic model tailored for near-infrared spectral synthesis. Unlike conventional generative approaches, the proposed model integrates a bidirectional gated recurrent unit-based temporal encoder and one dimension convolutional neural networks within a diffusion framework, augmented by a spectral attention module to prioritize critical absorption bands. This architecture uniquely addresses the sequential dependencies and subtle biochemical variations inherent in near-infrared spectral, enabling high-fidelity generation of diverse synthetic data. The diffusion process is optimized through a hybrid loss function combining variational lower bound training with mean squared error for pixel-level fidelity and maximum mean discrepancy for distributional alignment. Evaluated on 517 near-infrared spectral samples across three Miscanthus species, the proposed model outperforms traditional variational autoencoders, generative adversarial networks, and standard diffusion models in terms of sample authenticity and diversity. Incorporating synthetic data enhanced the accuracy, precision, and recall of downstream classifiers by 10%–15%, with the convolutional neural networks attaining 87% accuracy using hybrid real-synthetic training data. Remarkably, even with 50% synthetic data substitution, classification accuracy remained robust at 75%, demonstrating the model’s efficacy in mitigating data scarcity and advancing precision agriculture for bioenergy optimization.

Details DOI

JBHI Journal 2025 Journal Article

Towards Clinically Applicable Large-Model-Based Privacy-Preserving Polyp Segmentation: A Federated LoRA Approach to Colonoscopy

Xingchi Chen
Fa Zhu
Dazhou Li
Qing Li
Muhammad Shahid Anwar
Gaoyang Shan
Jun Jiang

Colonoscopy polyp segmentation is essential for accurate lesion detection and workflow optimization in clinical practice. However, deploying large foundation models in medical settings faces challenges related to patient privacy, computational overhead, and heterogeneous data distributions. In this study, we propose PolypSAMFL, a novel framework that integrates lowrank adaptation (LoRA) into the Segment Anything Model (SAM) within a federated learning paradigm to deliver privacypreserving, highprecision polyp segmentation. By freezing the majority of SAM's pretrained parameters and finetuning only compact LoRA modules in the image encoder and mask decoder, PolypSAMFL significantly reduces communication costs while maintaining robust feature extraction across distributed clinical datasets. We further propose a boundaryaware loss function and a multiresolution mask synthesis strategy to enhance delineation of irregular and lowcontrast polyp boundaries. Extensive evaluation on four public colonoscopy datasets demonstrates that our method yields a mean Dice score of 0. 987 and intersectionoverunion of 0. 976, outperforming stateoftheart approaches while fully preserving data locality. This translates directly to more reliable identification of polyp during colonoscopy. These results validate the clinical utility of PolypSAMFL for realworld, AIdriven colonoscopy workflows, offering a scalable solution that aligns with privacy regulations and resource constraints in modern healthcare environments.

Details DOI

JBHI Journal 2024 Journal Article

An Automatic Coronary Microvascular Dysfunction Classification Method Based on Hybrid ECG Features and Expert Features

Mingfeng Jiang
Feibiao Bian
Jucheng Zhang
Zhaoxia Pu
Huajun Li
Yuxuan Zhang
Yonghua Chu
Youqi Fan

Objective: In recent years, the early diagnosis and treatment of coronary microvascular dysfunction (CMD) have become crucial for preventing coronary heart disease. This paper aims to develop a computer-assisted autonomous diagnosis method for CMD by using ECG features and expert features. Approach: Clinical electrocardiogram (ECG), myocardial contrast echocardiography (MCE), and coronary angiography (CAG) are used in our method. Firstly, morphological features, temporal features, and T-wave features of ECG are extracted by multi-channel residual network with BiLSTM (MCResnet-BiLSTM) model and the multi-source T-wave features (MTF) extraction model, respectively. And these features are fused to form ECG features. In addition, the CFR $_\text{MCE}$ is calculated based on the parameters related to the MCE at rest and stress state, and the Angio-IMR is calculated based on CAG. The combination of CFR $_\text{MCE}$ and Angio-IMR is termed as expert features. Furthermore, the hybrid features, fused from the ECG features and the expert features, are input into the multilayer perceptron to implement the identification of CMD. And the weighted sum of the softmax loss and center loss is used as the total loss function for training the classification model, which optimizes the classification ability of the model. Result: The proposed method achieved 93. 36% accuracy, 94. 46% specificity, 92. 10% sensitivity, 95. 89% precision, and 93. 95% F1 score on the clinical dataset of the Second Affiliated Hospital of Zhejiang University. Conclusion: The proposed method accurately extracts global ECG features, combines them with expert features to obtain hybrid features, and uses weighted loss to significantly improve diagnostic accuracy. It provides a novel and practical method for the clinical diagnosis of CMD.

Details DOI

YNIMG Journal 2024 Journal Article

VAEEG: Variational auto-encoder for extracting EEG representation

Tong Zhao
Yi Cui
Taoyun Ji
Jiejian Luo
Wenling Li
Jun Jiang
Zaifen Gao
Wenguang Hu

The electroencephalogram (EEG) exhibits characteristics of complexity and strong randomness. Existing deep learning models for EEG typically target specific objectives and datasets, with their scalability constrained by the size of the dataset, resulting in limited perceptual and generalization abilities. In order to obtain more intuitive, concise, and useful representations of brain activity, we constructed a reconstruction-based self-supervised learning model for EEG based on Variational Autoencoder (VAE) with separate frequency bands, termed variational auto-encoder for EEG (VAEEG). VAEEG achieved outstanding reconstruction performance. Furthermore, we validated the efficacy of the latent representations in three clinical tasks concerning pediatric brain development, epileptic seizure, and sleep stage classification. We discovered that certain latent features: 1) correlate with adolescent brain developmental changes; 2) exhibit significant distinctions in the distribution between epileptic seizures and background activity; 3) show significant variations across different sleep cycles. In corresponding downstream fitting or classification tasks, models constructed based on the representations extracted by VAEEG demonstrated superior performance. Our model can extract effective features from complex EEG signals, serving as an early feature extractor for downstream classification tasks. This reduces the amount of data required for downstream tasks, simplifies the complexity of downstream models, and streamlines the training process.

Details DOI

JBHI Journal 2023 Journal Article

Bridging Feature Gaps to Improve Multi-Organ Segmentation on Abdominal Magnetic Resonance Image

Susu Kang
Muyuan Yang
X. Sharon Qi
Jun Jiang
Shan Tan

Accurate segmentation of abdominal organs on MRI is crucial for computer-aided surgery and computer-aided diagnosis. Most state-of-the-art methods for MRI segmentation employ an encoder-decoder structure, with skip connections concatenating shallow features from the encoder and deep features from the decoder. In this work, we noticed that simply concatenating shallow and deep features was insufficient for segmentation due to the feature gap between shallow features and deep features. To mitigate this problem, we quantified the feature gap from spatial and semantic aspects and proposed a spatial loss and a semantic loss to bridge the feature gap. The spatial loss enhanced spatial details in deep features, and the semantic loss introduced semantic information into shallow features. The proposed method successfully aggregated the complementary information between shallow and deep features by formulating and bridging the feature gap. Experiments on two abdominal MRI datasets demonstrated the effectiveness of the proposed method, which improved the segmentation performance over a baseline with nearly zero additional parameters. Particularly, the proposed method has advantages for segmenting organs with blurred boundaries or in a small scale, achieving superior performance than state-of-the-art methods.

Details DOI

ICRA Conference 2021 Conference Paper

A Novel Variable Resolution Torque Sensor Based on Variable Stiffness Principle

Xiantao Sun
Wenjie Chen
Jianbin Zhang
Jianhua Wang
Jun Jiang
Weihai Chen

High resolution and large range force/torque (F/T) measurements are usually required in many engineering tasks. However, most existing F/T sensors only have a fixed resolution over their whole ranges. The key lies in that it is difficult to well balance high resolution and large range in the sensor design. Taking the torque sensor for example, this paper presents a better compromise for this problem i. e. , a novel variable resolution torque sensor based on variable stiffness principle. From the structural points of view, the sensor is constructed with multiple radial flexures to achieve a pure rotational motion with negligible parasitic center motions. Two resistive strain gauges (RSGs) are selected as the measuring units of the sensor to detect the applied external torque and meanwhile provide variable resolutions in the two different measuring ranges (each RSG for one range). Static and dynamic models of the sensor are established in details and validated through finite element analysis (FEA) to evaluate its characteristics. A principle prototype is finally fabricated and tested to verify the effectiveness of the presented design. RSGs are calibrated through a commercial six-axis F/T sensor from ATI Industrial Automation, Inc. Experimental results show that the torque sensor can provide high and low resolutions in the small and large ranges respectively and possesses the first natural frequency of 67. 3 Hz. In addition, the proposed variable resolution method can also be applied to the development of multi-axis F/T sensors.

Details

YNIMG Journal 2018 Journal Article

The relationship between conflict awareness and behavioral and oscillatory signatures of immediate and delayed cognitive control

Jun Jiang
Camile M. Correa
Jesse Geerts
Simon van Gaal

Cognitive control over conflict, mediated by the prefrontal cortex, is an important skill for successful decision-making. Although it has been shown that cognitive control may operate unconsciously, it has recently been proposed that control operations may be driven by the metacognitive awareness of conflict, e. g. arising from the feeling of task difficulty or the ease of action selection, and therefore crucially depends on conflict awareness. Behavioral and electroencephalography (EEG) data are presented from 64 subjects performing a masked priming paradigm to test this hypothesis. Although the subjective experience of conflict elicited behavioral adaptation, this was also the case when conflict was present, but not experienced. In EEG, typical oscillatory markers of conflict processing in the theta-, alpha- and beta-band were observed (relative broadband), but these were differentially modulated by conflict experience. This demonstrates that conflict adaptation does not depend on conflict experience, but that conflict experience is associated with increased cognitive control.

Details DOI

YNIMG Journal 2015 Journal Article

Conflict awareness dissociates theta-band neural dynamics of the medial frontal and lateral frontal cortex during trial-by-trial cognitive control

Jun Jiang
Qinglin Zhang
Simon van Gaal

Recent findings have refuted the common assumption that executive control functions of the prefrontal cortex exclusively operate consciously, suggesting that many, if not all, cognitive processes could potentially operate unconsciously. However, although many cognitive functions can be launched unconsciously, several theoretical models of consciousness assume that there are crucial qualitative differences between conscious and unconscious processes. We hypothesized that the potential benefit of awareness in cognitive control mechanisms might become apparent when high control has to be maintained across time and requires the interaction between a set of distant frontal brain regions. To test this, we extracted oscillatory power dynamics from electroencephalographic data recorded while participants performed a task in which conflict awareness was manipulated by masking the conflict-inducing stimulus. We observed that instantaneous conflict as well as across trial conflict adaptation mechanisms were associated with medial frontal theta-band power modulations, irrespective of conflict awareness. However, and crucially, across-trial conflict adaptation processes reflected in increased theta-band power over dorsolateral frontal cortex were observed after fully conscious conflict only. This suggests that initial conflict detection and subsequent control adaptation by the medial frontal cortex are automatic and unconscious, whereas the routing of information from the medial frontal cortex to the lateral prefrontal cortex is a unique feature of conscious cognitive control.

Details DOI

YNIMG Journal 2014 Journal Article

Brain extraction based on locally linear representation-based classification

Meiyan Huang
Wei Yang
Jun Jiang
Yao Wu
Yu Zhang
Wufan Chen
Qianjin Feng

Brain extraction is an important procedure in brain image analysis. Although numerous brain extraction methods have been presented, enhancing brain extraction methods remains challenging because brain MRI images exhibit complex characteristics, such as anatomical variability and intensity differences across different sequences and scanners. To address this problem, we present a Locally Linear Representation-based Classification (LLRC) method for brain extraction. A novel classification framework is derived by introducing the locally linear representation to the classical classification model. Under this classification framework, a common label fusion approach can be considered as a special case and thoroughly interpreted. Locality is important to calculate fusion weights for LLRC; this factor is also considered to determine that Local Anchor Embedding is more applicable in solving locally linear coefficients compared with other linear representation approaches. Moreover, LLRC supplies a way to learn the optimal classification scores of the training samples in the dictionary to obtain accurate classification. The International Consortium for Brain Mapping and the Alzheimer's Disease Neuroimaging Initiative databases were used to build a training dataset containing 70 scans. To evaluate the proposed method, we used four publicly available datasets (IBSR1, IBSR2, LPBA40, and ADNI3T, with a total of 241 scans). Experimental results demonstrate that the proposed method outperforms the four common brain extraction methods (BET, BSE, GCUT, and ROBEX), and is comparable to the performance of BEaST, while being more accurate on some datasets compared with BEaST.

Details DOI