Author name cluster

Hua Zhang

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.

16 papers

1 author row

JBHI Journal 2026 Journal Article

Extraction of Seafarers’ Occupational Plasticity Brain Network Based on Effective Connectivity Lateralization

Lei Wang
Weiming Zeng
Baolong Li
Weifang Nie
Hua Zhang
Hongyu Chen
Yueyang Li
Yuhu Shi

Lateralization is an effective model for exploring changes in brain activity and is widely used to assess brain function. Seafarers, as an occupation working in marine environments, are subjected to long-term specialized occupational demands and experiences, which inevitably impact brain function. By utilizing lateralization, the influence of occupational experience on brain activity can be further explored. A novel Effective Connectivity Lateralization Analysis (ECLA) framework is proposed, which incorporates a Transformer-based Granger causality model (Transformer-GC) to analyze the effects of seafaring on brain plasticity. The Transformer-GC model constructs effective connectivity (EC) matrices, and lateralization indices are derived to investigate occupational influences on brain activity. Two control groups of non-seafarers are included to identify seafarers’ unique occupational plasticity brain networks. Results show that Transformer-GC achieves an accuracy improvement of nearly 16% and 19. 4% over the GRU-based and MVGC model, respectively, and a 5% gain over Pearson-based functional connectivity, confirming its superior performance. Moreover, the results of the ECLA showed significant differences in VentralAttention, Somatomotor, DorsalAttention in the seafarer, demonstrating that these brain networks are affected by the long-term work of seafarers. The findings demonstrate the effectiveness of ECLA in revealing the impact of long-term maritime work on brain plasticity, particularly in identifying the brain network of seafarers’ occupational plasticity. It is shown that occupational experience can reshape the lateralization of brain functional activity, offering new insights into neural plasticity across different professions.

Details DOI

AAAI Conference 2026 Conference Paper

The Emotional Baby Is Truly Deadly: Does Your Multimodal Large Reasoning Model Have Emotional Flattery Towards Humans?

Yuan Xun
Xiaojun Jia
Xinwei Liu
Simeng Qin
Hua Zhang

Multimodal large reasoning models (MLRMs) have advanced visual-textual integration, enabling sophisticated human-AI interaction. While prior work has exposed MLRMs to visual jailbreaks, it remains underexplored how their reasoning capabilities reshape the security landscape under adversarial inputs. To fill this gap, we conduct a systematic security assessment of MLRMs and uncover a security-reasoning paradox: although deeper reasoning boosts cross‑modal risk recognition, it also creates cognitive blind spots that adversaries can exploit. We observe that MLRMs oriented toward human-centric service are highly susceptible to users' emotional cues during the deep-thinking stage, often overriding safety protocols or built‑in safety checks under high emotional intensity. Inspired by this key insight, we propose EmoAgent, an autonomous adversarial emotion-agent that orchestrates exaggerated affective prompts to hijack reasoning pathways. Even when visual risks are correctly identified, models can still produce harmful completions through emotional misalignment. We further identify persistent high-risk failure modes in transparent deep-thinking scenarios, such as MLRMs generating harmful reasoning masked behind seemingly safe responses. These failures expose misalignments between internal inference and surface-level behavior, eluding existing content-based safeguards. To quantify these risks, we introduce three metrics: (1) Risk-Reasoning Stealth Score (RRSS) for harmful reasoning beneath benign outputs; (2) Risk-Visual Neglect Rate (RVNR) for unsafe completions despite visual risk recognition; and (3) Refusal Attitude Inconsistency (RAIC) for evaluating refusal unstability under prompt variants. Extensive experiments on advanced MLRMs demonstrate the effectiveness of EmoAgent and reveal deeper emotional cognitive misalignments in model safety.

PDF Details DOI

EAAI Journal 2025 Journal Article

Adaptive multimodal control of trans-media vehicle based on deep reinforcement learning

Jingkang Wang
Shuang Liang
Mingming Guo
Heng Wang
Hua Zhang

To solve the problem that the control system is prone to instability due to the sudden change of physical characteristics, strong interference, and nonlinear in the process of multimodal movement of trans-media vehicle, an adaptive control method combining the Deep Deterministic Policy Gradient (DDPG) and traditional Proportional-Integral-Derivative (PID) controller is proposed in this paper. In this approach, the upper-level DDPG controller continuously monitors the vehicle's state and environmental conditions, dynamically adjusting the PID parameters in real-time. The lower-level PID controller then utilizes these updated parameters to modulate the output thrust of the vehicle's motors, thereby achieving excellent control over the vehicle's entire movement. Firstly, according to the hydrodynamic analysis, the kinematics and dynamics mathematical model of the self-designed trans-media vehicle is constructed. This model includes the multi-stage motion modal process of aerial flight, underwater navigation, and cross-media motion, which is suitable for the simulation and verification of the control method. Then, an adaptive controller called RL-PID combining DDPG and PID is built, so that PID can adjust parameters in real-time according to the changes in the external environment. Finally, after theoretical stability proof, a comparison study is performed across three approaches, namely the novel RL-PID, Fuzzy PID, and PID. The experimental results illustrate the superiority of the proposed approach over the competing ones and the generalization of the proposed approach under different interference.

Details DOI

IJCAI Conference 2025 Conference Paper

Boosting Few-Shot Open-Set Object Detection via Prompt Learning and Robust Decision Boundary

Zhaowei Wu
Binyi Su
Qichuan Geng
Hua Zhang
Zhong Zhou

Few-shot Open-set Object Detection (FOOD) poses a challenge in many open-world scenarios. It aims to train an open-set detector to detect known objects while rejecting unknowns with scarce training samples. Existing FOOD methods are subject to limited visual information, and often exhibit an ambiguous decision boundary between known and unknown classes. To address these limitations, we propose the first prompt-based few-shot open-set object detection framework, which exploits additional textual information and delves into constructing a robust decision boundary for unknown rejection. Specifically, as no available training data for unknown classes, we select pseudo-unknown samples with Attribution-Gradient based Pseudo-unknown Mining (AGPM), which leverages the discrepancy in attribution gradients to quantify uncertainty. Subsequently, we propose Conditional Evidence Decoupling (CED) to decouple and extract distinct knowledge from selected pseudo-unknown samples by eliminating opposing evidence. This optimization process can enhance the discrimination between known and unknown classes. To further regularize the model and form a robust decision boundary for unknown rejection, we introduce Abnormal Distribution Calibration (ADC) to calibrate the output probability distribution of local abnormal features in pseudo-unknown samples. Our method achieves superior performance over previous state-of-the-art approaches, improving the average recall of unknown class by 7. 24% across all shots in VOC10-5-5 dataset settings and 1. 38% in VOC-COCO dataset settings. Our source code is available at https: //gitee. com/VR_NAVE/ced-food.

PDF Details DOI

AAAI Conference 2025 Short Paper

Efficient Unlearning for Spatio-temporal Graph (Student Abstract)

Qiming Guo
Chen Pan
Hua Zhang
Wenlu Wang

Machine unlearning is becoming increasingly important as deep models become more prevalent, particularly when there are frequent requests to remove the influence of specific training data due to privacy concerns or erroneous sensing signals. Spatial-temporal Graph Neural Networks, in particular, have been widely adopted in real-world applications that demand efficient unlearning, yet research in this area remains in its early stages. In this paper, we introduce STEPS, a framework specifically designed to address the challenges of spatio-temporal graph unlearning. Our results demonstrate that STEPS not only ensures data continuity and integrity but also significantly reduces the time required for unlearning, while minimizing the accuracy loss in the new model compared to a model with 0% unlearning.

PDF Details DOI

AAAI Conference 2025 Conference Paper

Fair Text-to-Image Diffusion via Fair Mapping

Jia Li
Lijie Hu
Jingfeng Zhang
Tianhang Zheng
Hua Zhang
Di Wang

In this paper, we address the limitations of existing text-to-image diffusion models in generating demographically fair results when given human-related descriptions. These models often struggle to disentangle the target language context from sociocultural biases, resulting in biased image generation. To overcome this challenge, we propose Fair Mapping, a flexible, model-agnostic, and lightweight approach that modifies a pre-trained text-to-image diffusion model by controlling the prompt to achieve fair image generation. One key advantage of our approach is its high efficiency. It only requires updating an additional linear network with few parameters at a low computational cost. By developing a linear network that maps conditioning embeddings into a debiased space, we enable the generation of relatively balanced demographic results based on the specified text condition. With comprehensive experiments on face image generation, we show that our method significantly improves image generation fairness with almost the same image quality compared to conventional diffusion models when prompted with descriptions related to humans. By effectively addressing the issue of implicit language bias, our method produces more fair and diverse image outputs.

PDF Details DOI

EAAI Journal 2025 Journal Article

Reading comprehension powered semantic fusion network for identification of N-ary drug combinations

Hua Zhang
Peiqian Zhan
Cheng Yang
Yongjian Yan
Zijing Cai
Guogen Shan
Bo Jiang
Bi Chen

The concurrent use of multiple medications to treat one or more diseases is prevalent. Identifying N-ary drug combinations from biomedical texts aids in uncovering significant pharmacological effects triggered by drug-drug interactions. Previous methods for this emerging task have primarily concentrated on representing drug entities using pre-trained language models, overlooking the comprehensive extraction of contextual and task-specific semantic information. To address these limitations, we develop a semantic fusion method grounded in machine reading comprehension (MRC) framework. Our model, termed Reading Comprehension powered semantic Fusion network for Identification of N-ary Drug combinations (RCFIND), first constructs relevant contexts and queries for each individual drug combination. Then, diverse information sources, including task-specific semantics, drug entity representations and contextual details, are fused by using a simplified Capsule network as well as incorporating contrastive learning. We assess RCFIND, achieving F1 scores ranging from 72. 0% to 83. 3% across four types of evaluations. Experimental results demonstrate significant performance enhancements over existing baselines, with at least a 5% F1 score improvement. Ablation studies and further analysis confirm the efficacy of the MRC framework and contrastive learning in accurately identifying N-ary drug combinations.

Details DOI

YNIMG Journal 2025 Journal Article

Subthalamic nucleus stimulation at high and low frequencies engages different brain networks to enhance gait performance in Parkinson's disease

Yin Jiang
Hutao Xie
Yutong Bai
Quan Zhang
Yu Diao
Houyou Fan
Xin Zhang
Hua Zhang

BACKGROUND: Subthalamic nucleus (STN) deep brain stimulation (DBS) is used to treat Parkinson's disease (PD), yet neither high-frequency stimulation (HFS) nor low frequency stimulation (LFS) fully resolves gait issues. Previous studies indicate that STN-DBS modulates motor-related brain networks. Given that PD patients with gait disturbances exhibit cognitive deficits-and considering the extensive projections between the STN and cerebral cortex-we hypothesized that varying STN stimulation frequencies may improve gait by modulating distinct brain networks. METHODS: We collected gait data, cortical electrophysiological signals, and resting-state fMRI from 44 PD patients and 32 healthy controls. Multi-network cortical activity and functional connectivity were c ompared under three conditions: DBS OFF, HFS, and LFS. Additionally, the connectivity values were correlated to the gait behaviors and clinical assessment scores. RESULTS: We found that: (1) HFS improved both motor and gait performance, while LFS enhanced gait but may not be optimal for long-term use; (2) STN-DBS induced widespread modulation across sensorimotor, frontoparietal, salience, dorsal attention, and default mode networks. HFS improved motor and gait functions via network modulation related to motor control, whereas LFS may enhance gait by boosting executive-related cortical activities and connections; (3) Relative to healthy controls, PD exhibited widespread reductions in functional connectivity, with DBS modulation trending toward normalization. CONCLUSIONS: These results reveal distinct brain network responses to different STN-DBS frequencies in PD, offering a theoretical basis for optimizing DBS treatment for gait impairments. These findings provide critical insights for tailoring DBS parameters to maximize both motor and cognitive benefits in PD patients.

Details DOI

EAAI Journal 2024 Journal Article

Evolution prediction of flame structure in a hydrogen-fueled scramjet combustor based on lightweight deformable convolutional residual neural network

Jiawen Deng
Mingming Guo
Erda Chen
Ye Tian
Chunmei Chen
Hua Zhang

Accurate prediction and fine feature identification of flame structure evolution within scramjet combustors are crucial for exploring stable combustion mechanisms and organizing efficient combustion. This study introduces an innovative method for predicting the dynamic evolution of supersonic flame structures. It presents a cross-temporal prediction model for the flame field that employs a lightweight, deformable convolutional residual neural network (DRCN). Ground-based pulse combustion wind tunnel tests are conducted at 2. 5 Mach with varying equivalence ratios. Synchronous measurements are taken to collect spatiotemporal multisource data, which is employed to compile a dataset of the combustion chamber wall pressure and flame field data. Pressure signals from sensors on the combustion chamber's upper and lower walls, along with signals spanning different time intervals, served as inputs to predict the evolution of the flame field structure. Experiments over multiple and extensive time spans are performed to compare and analyze performance differences between the different models. The experimental results demonstrated that the DRCN model surpasses other models in the test sets, achieving up to a 36. 11% increase in peak signal-to-noise ratio, a 33. 24% improvement in structural similarity index, and a 3. 81% enhancement in the correlation coefficient. Predictions on the dynamic evolution of initial flame kernels, flame contours, and flame distribution show superior performance. This research also investigates the network's lightweight design, achieving a model size of merely 1 MB to further enhance the model's inference speed. It presents significant engineering value for the real-time prediction of flame propagation in supersonic combustor.

Details DOI

EAAI Journal 2024 Journal Article

Query-induced multi-task decomposition and enhanced learning for aspect-based sentiment quadruple prediction

Hua Zhang
Xiawen Song
Xiaohui Jia
Cheng Yang
Zeqi Chen
Bi Chen
Bo Jiang
Ye Wang

A complete sentiment analysis of product and service reviews has attracted growing concerns from merchants to enhance personalized marketing activities. Aspect sentiment quadruple prediction (ASQP) is a demanding and challenging task with the objective to predict four sentiment elements from given reviews. Existing methods for ASQP face certain issues, with pipeline-based non-generative approaches prone to error propagation and generative models at the potential risk of producing unexpected outputs or longer inference times. To avoid these shortcomings, we develop a novel end-to-end non-generative model for ASQP involving multi-task decomposition within machine reading comprehension (MRC) framework. Specifically, the ASQP task is decomposed into six query-induced subtasks by introducing task-specific question templates. The proposed model, named MRC-CLRI, is trained with multi-task joint learning. It also incorporates contrastive learning for category identification and sentiment classification to enhance the correlation of the six subtasks. To further promote the quadruple prediction, we present a refined inference algorithm in a bidirectional multi-turn inference procedure to effectively match aspect and opinion terms and optimize two inference hyperparameters: distance threshold and probability threshold. Experimental results exhibit superior performance compared to existing two non-generative and seven generative baselines. Our proposed MRC-CLRI, as a novel non-generative model, outperforms the best existing generative method by an average F1 score improvement of 1. 69% and the best previous non-generative method by an average F1 score improvement of 15. 77% across four review datasets. Ablation experiments further validate the efficacy of the designed contrastive learning and the refined inference algorithm.

Details DOI

EAAI Journal 2024 Journal Article

Supersonic combustion flow field reconstruction based on multi-view domain adaptation generative network in scramjet combustor

Mingming Guo
Erda Chen
Ye Tian
Linjing Li
Mengqi Xu
Jialing Le
Hua Zhang

The efficient and precise reconstruction of supersonic combustion flow fields enables real-time sensing and control of hypersonic vehicles. However, current flow field reconstruction methodologies often suffer from limited prediction accuracy, poor generalization capabilities, and high model energy consumption. In this research, a robust and efficient multi-source data fusion framework for combustion flow field reconstruction based on a multi-view domain adaptation generative network (MV-DAGN) is developed and evaluated. In order to utilize multivariate flow field data, this study adopts a multi-view learning approach to thoroughly integrate various physical field data. It introduces an MV-DAGN framework for training models on multi-source data from supersonic combustor with a Mach 2. 5 low equivalence ratio derived from ground-based pulse combustion wind tunnels. The concept of transfer learning is incorporated, and the fusion of wall pressure and flame field data is utilized to validate the flow field reconstruction by including a limited set of high equivalence ratio data. Subsequently, to diminish the model's training duration and enhance the prediction speed of the combustion flow field, a lightweight MV-DAGN model is established.

Details DOI

AAAI Conference 2023 Conference Paper

Improving Dynamic HDR Imaging with Fusion Transformer

Rufeng Chen
Bolun Zheng
Hua Zhang
Quan Chen
Chenggang Yan
Gregory Slabaugh
Shanxin Yuan

Reconstructing a High Dynamic Range (HDR) image from several Low Dynamic Range (LDR) images with different exposures is a challenging task, especially in the presence of camera and object motion. Though existing models using convolutional neural networks (CNNs) have made great progress, challenges still exist, e.g., ghosting artifacts. Transformers, originating from the field of natural language processing, have shown success in computer vision tasks, due to their ability to address a large receptive field even within a single layer. In this paper, we propose a transformer model for HDR imaging. Our pipeline includes three steps: alignment, fusion, and reconstruction. The key component is the HDR transformer module. Through experiments and ablation studies, we demonstrate that our model outperforms the state-of-the-art by large margins on several popular public datasets.

PDF Details DOI

AAAI Conference 2018 Conference Paper

Audio Visual Attribute Discovery for Fine-Grained Object Recognition

Hua Zhang
Xiaochun Cao
Rui Wang

Current progresses on ﬁne-grained recognition are mainly focus on learning the discriminative feature representation via introducing the visual supervisions e. g. part labels. However, it is time-consuming and needs the professional knowledge to obtain the accuracy annotations. Different from these existing methods based on the visual supervisions, in this paper, we introduce a novel feature named audio visual attributes via discovering the correlations between the visual and audio representations. Speciﬁcally, our uniﬁed framework is training with video-level category label, which consists of two important modules, the encoder module and the attribute discovery module, to encode the image and audio into vectors and learn the correlations between audio and images, respectively. On the encoder module, we present two types of feed forward convolutional neural network for the image and audio modalities. While an attention driven framework based on recurrent neural network is developed to generate the audio visual attribute representation. Thus, our proposed architecture can be implemented end-to-end in the step of inference. We exploit our models for the problem of ﬁne-grained bird recognition on the CUB200-211 benchmark. The experimental results demonstrate that with the help of audio visual attribute, we achieve the superior or comparable performance to that of strongly supervised approaches on the bird recognition.

PDF Details

AAAI Conference 2018 Conference Paper

Group-Pair Convolutional Neural Networks for Multi-View Based 3D Object Retrieval

Zan Gao
Deyu Wang
Xiangnan He
Hua Zhang

In recent years, research interest in object retrieval has shifted from 2D towards 3D data. Despite many well-designed approaches, we point out that limitations still exist and there is tremendous room for improvement, including the heavy reliance on hand-crafted features, the separated optimization of feature extraction and object retrieval, and the lack of suf- ﬁcient training samples. In this work, we address the above limitations for 3D object retrieval by developing a novel endto-end solution named Group Pair Convolutional Neural Network (GPCNN). It can jointly learn the visual features from multiple views of a 3D model and optimize towards the object retrieval task. To tackle the insufﬁcient training data issue, we innovatively employ a pair-wise learning scheme, which learns model parameters from the similarity of each sample pair, rather than the traditional way of learning from sparse label–sample matching. Extensive experiments on three public benchmarks show that our GPCNN solution signiﬁcantly outperforms the state-of-the-art methods with 3% to 42% improvement in retrieval accuracy.

PDF Details

NeurIPS Conference 2018 Conference Paper

Multi-Class Learning: From Theory to Algorithm

Jian Li
Yong Liu
Rong Yin
Hua Zhang
Lizhong Ding
Weiping Wang

In this paper, we study the generalization performance of multi-class classification and obtain a shaper data-dependent generalization error bound with fast convergence rate, substantially improving the state-of-art bounds in the existing data-dependent generalization analysis. The theoretical analysis motivates us to devise two effective multi-class kernel learning algorithms with statistical guarantees. Experimental results show that our proposed methods can significantly outperform the existing multi-class classification methods.

PDF Details

AIIM Journal 2010 Journal Article

Development of traditional Chinese medicine clinical data warehouse for medical knowledge discovery and decision support

Xuezhong Zhou
Shibo Chen
Baoyan Liu
Runsun Zhang
Yinghui Wang
Ping Li
Yufeng Guo
Hua Zhang

Objective Traditional Chinese medicine (TCM) is a scientific discipline, which develops the related theories from the long-term clinical practices. The large-scale clinical data are the core empirical knowledge source for TCM research. This paper introduces a clinical data warehouse (CDW) system, which incorporates the structured electronic medical record (SEMR) data for medical knowledge discovery and TCM clinical decision support (CDS). Materials and methods We have developed the clinical reference information model (RIM) and physical data model to manage the various information entities and their relationships in TCM clinical data. An extraction-transformation-loading (ETL) tool is implemented to integrate and normalize the clinical data from different operational data sources. The CDW includes online analytical processing (OLAP) and complex network analysis (CNA) components to explore the various clinical relationships. Furthermore, the data mining and CNA methods are used to discover the valuable clinical knowledge from the data. Results The CDW has integrated 20, 000 TCM inpatient data and 20, 000 outpatient data, which contains manifestations (e. g. symptoms, physical examinations and laboratory test results), diagnoses and prescriptions as the main information components. We propose a practical solution to accomplish the large-scale clinical data integration and preprocessing tasks. Meanwhile, we have developed over 400 OLAP reports to enable the multidimensional analysis of clinical data and the case-based CDS. We have successfully conducted several interesting data mining applications. Particularly, we use various classification methods, namely support vector machine, decision tree and Bayesian network, to discover the knowledge of syndrome differentiation. Furthermore, we have applied association rule and CNA to extract the useful acupuncture point and herb combination patterns from the clinical prescriptions. Conclusion A CDW system consisting of TCM clinical RIM, ETL, OLAP and data mining as the core components has been developed to facilitate the tasks of TCM knowledge discovery and CDS. We have conducted several OLAP and data mining tasks to explore the empirical knowledge from the TCM clinical data. The CDW platform would be a promising infrastructure to make full use of the TCM clinical data for scientific hypothesis generation, and promote the development of TCM from individualized empirical knowledge to large-scale evidence-based medicine.

Details DOI