Author name cluster

Nan Zhou

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

2 author rows

EAAI Journal 2026 Journal Article

A dual-stream regional feature learning and adaptive fusion method for electroencephalogram-based emotion recognition

Yong Yang
Wenhao Wang
Kaibo Shi
Yuanlun Xie
Nan Zhou
Shiping Wen
Ming Zhu
Badong Chen

Electroencephalogram (EEG) has become a research hotspot in emotion recognition due to its high temporal resolution and ability to truly reflect brain activity. However, few existing EEG-based emotion recognition methods integrate brain region information into the algorithm and do not fully extract the deep features of each region. Brain science has shown that different brain regions have different functions and are highly correlated with the production of emotions. In this paper, based on the division of brain regions, a dual-branch regional feature learning and adaptive fusion neural network (DRFNet) is proposed to extract the features of different brain regions and adaptively fuse regional features, thereby achieving accurate EEG emotion recognition. Specifically, DRFNet mainly consists of regional feature extraction modules (DB-CTFEM) and a feature fusion module (RFM). The DB-CTFEM extracts regional local and global features through the dual-branch structure of convolutional neural network (CNN) and Transformer, respectively, and then uses cross-attention to effectively fuse the two to obtain enhanced regional features. Considering the differences of brain regions, RFM uses the attention mechanism to fuse regional features and adaptively reconstruct global brain features. In addition, a region loss function based on the importance of region features is proposed to dynamically adjust the contribution weights of different brain regions, thereby guiding the model to pay more attention to key regions. This paper conducts subject-dependent experiments on the SJTU Emotion EEG Datasets (SEED, SEED-IV, SEED-V, and SEED-VII) to verify effectiveness and robustness of the proposed method.

Details DOI

EAAI Journal 2026 Journal Article

Correntropy meets cross-entropy: A robust loss against noisy labels

Nan Zhou
Qing Deng
Wenjun Luo
Xiuyu Huang
Yuanhua Du
Badong Chen
Witold Pedrycz

Noisy labels are a common challenge in real-world datasets, severely degrading the training of deep learning models. Enhancing the robustness of the loss function offers a flexible solution to mitigate this issue. This study first demonstrates that Categorical Cross-Entropy (CE), one of the most popular choices used to train a classification model, leads to significant performance degradation. To alleviate this issue, we innovatively propose a novel loss function called Correntropy-Inspired Cross-Entropy (CICE) loss, which utilizes the properties of correntropy and is robust to noisy labels. Compared with CE, CICE retains CE’s core functionality for linear class separation while automatically alleviating the adverse effects of noisy labels during training. Extensive experiments on four public datasets across multiple scenarios with varying noisy label rates validate CICE’s effectiveness. Results show that CICE outperforms 13 state-of-the-art loss functions in noise resilience and classification accuracy, establishing its superiority in noisy-label environments.

Details DOI

AAAI Conference 2026 Conference Paper

CrossCut: Cross-Patch Aware Interactive Segmentation for Remote Sensing Images

Zheng Lin
Nan Zhou
Yuhan Wang
Bojian Zhang

Interactive segmentation aims to delineate a user-specified target in an image by leveraging positive and negative clicks. While effective on natural images, existing methods often fail in remote sensing scenarios, where satellite imagery is characterized by ultra-high resolution, sparse object distribution, and significant scale variation. These factors hinder accurate segmentation of fine-grained targets like roads, buildings, and aircraft. To overcome these problems, we propose CrossCut, a novel interactive segmentation framework tailored for remote sensing imagery. Unlike previous approaches that either process the entire image or treat each patch independently, CrossCut enables simultaneous segmentation across multiple patches by propagating user click information to all patches. This design allows the model to fully utilize click guidance regardless of object location, effectively resolving the challenge of inter-patch information isolation. Furthermore, CrossCut supports flexible inference by allowing segmentation results from different patch configurations to be fused, enhancing both accuracy and robustness. Extensive evaluations across multiple remote sensing datasets demonstrate that CrossCut achieves state-of-the-art performance. Quantitative results and visualizations show that CrossCut significantly advances the field of interactive segmentation for remote sensing imagery.

PDF Details DOI

JBHI Journal 2026 Journal Article

Uncertainty-Aware Cross-Modal Retrieval for Medical Report Generation

Nan Zhou
Meng Liu
Linchao He
Mengting Luo
Yidi Chen
Yi Zhang
Ke Zou
Hu Chen

Automatic medical report generation (MRG) has advanced significantly with retrieval-augmented strategies. However, existing methods face two persistent challenges: 1) a largely reliance on single-modal retrieval, which limits multimodal semantic capture and cross-modal alignment; and 2) a lack of reliable information control, leading to irrelevant noisy content and potential hallucinations. To address these limitations, we propose Uncertainty-aware Cross-modal Alignment and Refinement, named U-CAR, a unified framework that enhances both semantic integration and retrieval reliability. First, a cross-modal alignment module explicitly learns fine-grained correspondences between visual and textual representations, ensuring consistent semantics across modalities. This alignment guides the construction of dual-path retrieval-aware memory banks, with one in the visual domain and one in the textual domain, enabling retrieval to capture complementary cues from both modalities. Second, we design a cross-modal retrieval-augmented generation strategy that jointly attends to the retrieved visual and textual context, thereby enriching semantic coverage and reinforcing the integration of multi-modal evidence in the generated reports. In parallel, we introduce an uncertainty-aware refinement mechanism that quantifies generation confidence to adaptively determine the necessity of retrieval. Experiments on the IU X-Ray and MIMIC-CXR datasets demonstrate that U-CAR outperforms the current state-of-the-art methods, achieving a 9% improvement in CIDEr on IU X-Ray. and a 4% gain in BLEU-4 on MIMIC-CXR. These results underscore U-CAR's effectiveness in generating accurate, coherent, and clinically relevant medical reports. Codes are available in https://github.com/Zhounan1222/U-CAR/tree/main.

Details DOI

EAAI Journal 2025 Journal Article

Digital twin-driven reinforcement learning-based operational management for customized manufacturing

Hao Tang
Minghao Cheng
Uzair Aslam Bhatti
Bo Xu
Nan Zhou
Rong Guo
Bing Wei

Due to the increasing complexity of customer demands for different batches and types of products, manufacturing operations management has been facing the challenge of uncertain product arrival times and resource processing times in customized manufacturing (CM). This paper proposes a dynamic scheduling method to solve the uncertainty in CM via the integration of the digital twin and fuzzy reinforcement learning methods. In this study, a digital twin-driven framework is first designed to describe the operation management system (OMS) hierarchies. Then a semi-Markov decision process (MDP) model with fuzzy definition is built by abstracting the stochastic scheduling process. To solve the semi-MDP model, an asynchronous multi-edge co-training method is presented to train a fuzzy deep neural network through closed-loop control of virtual commissioning, illustrating how the digital twin-driven OMS adapts to dynamic production requirements. Finally, the proposed method is verified by the performance of comparative experiment. Experimental results show that for randomly arriving products, the proposed method guarantees timely training and scheduling decisions and has the highest total system profit compared to other competing methods (Hybrid Multi-Agent System Negotiation and Ant Colony Optimization (HMA), Onto_MDP, and Deep Q Networks (DQN)). Also, the proposed method shows better scheduling performance in terms of average decision time, average training time and number of finished products when resources are abnormal.

Details DOI

NeurIPS Conference 2025 Conference Paper

Implicit Modeling for Transferability Estimation of Vision Foundation Models

Yaoyan Zheng
Huiqun Wang
Nan Zhou
Di Huang

Transferability estimation identifies the best pre-trained models for downstream tasks without incurring the high computational cost of full fine-tuning. This capability facilitates deployment and advances the pre-training and fine-tuning paradigm. However, existing methods often struggle to accurately assess transferability for emerging pre-trained models with diverse architectures, training strategies, and task alignments. In this work, we propose Implicit Transferability Modeling (ITM), a novel framework that implicitly models each model’s intrinsic transferability, coupled with a Divide-and-Conquer Variational Approximation (DVA) strategy to efficiently approximate embedding space evolution. This design enables generalization across a broader range of models and downstream tasks. Extensive experiments on a comprehensive benchmark—spanning extensive training regimes and a wider variety of model types—demonstrate that ITM consistently outperforms existing methods in terms of stability, effectiveness, and efficiency.

PDF Details

EAAI Journal 2025 Journal Article

MRTI-CR: A model based on multi-relationship and time-aware interest for personalized course recommendation

Shiyi Huang
Yongquan Dong
Ziyin Wang
Nan Zhou
Yuchao Ping

With the advancement of information technology, Massive Open Online Course (MOOC) platforms offer students a diverse selection of courses but also introduce the challenge of “course overload”. Most existing course recommendation methods primarily model students’ interactions with courses implicitly, overlooking the rich multi-relationships between different entities and also failing to account for the impact of students’ evolving learning interests, particularly the influence of time on course selection behavior. To address these limitations, we propose a model based on Multi-Relationship and Time-aware Interest for personalized Course Recommendation(MRTI-CR), which effectively integrates heterogeneous relationships and dynamic interest evolution. Our approach extracts global features of users and courses by constructing a heterogeneous information network and leveraging a meta-path-guided graph convolutional network, such as prerequisite relationship meta-paths. Furthermore, to enhance the utilization of temporal information, we design a dynamic interest extraction module based on a time-aware Transformer. This module incorporates time-interval-aware positional encoding and optimizes multi-head attention using temporal weights, enabling the dynamic modeling of students’ learning interests. Experiments conducted on the MOOCCube public dataset demonstrate that MRTI-CR outperforms existing baseline models across multiple evaluation metrics in the course recommendation task.

Details DOI

ICLR Conference 2025 Conference Paper

Progressive Parameter Efficient Transfer Learning for Semantic Segmentation

Nan Zhou
Huiqun Wang
Yaoyan Zheng
Di Huang 0001

Parameter Efficient Transfer Learning (PETL) excels in downstream classification fine-tuning with minimal computational overhead, demonstrating its potential within the pre-train and fine-tune paradigm. However, recent PETL methods consistently struggle when fine-tuning for semantic segmentation tasks, limiting their broader applicability. In this paper, we identify that fine-tuning for semantic segmentation requires larger parameter adjustments due to shifts in semantic perception granularity. Current PETL approaches are unable to effectively accommodate these shifts, leading to significant performance degradation. To address this, we introduce ProPETL, a novel approach that incorporates an additional midstream adaptation to progressively align pre-trained models for segmentation tasks. Through this process, ProPETL achieves state-of-the-art performance on most segmentation benchmarks and, for the first time, surpasses full fine-tuning on the challenging COCO-Stuff10k dataset. Furthermore, ProPETL demonstrates strong generalization across various pre-trained models and scenarios, highlighting its effectiveness and versatility for broader adoption in segmentation tasks. Code is available at: https://github.com/weeknan/ProPETL.

Details

YNIMG Journal 2024 Journal Article

Children's oppositional defiant disorder symptoms and neural synchrony in mother-child interactions: An fNIRS study

Wenrui Zhang
Ting He
Nan Zhou
Lian Duan
Peilian Chi
Xiuyun Lin

Interpersonal neural synchrony (INS) between mothers and children responds to the temporal similarity of brain signals in joint behavior between dyadic partners and is considered an important neural indicator of the formation of adaptive social interaction bonds. Parent-child interactions are particularly important for the development and maintenance of oppositional defiant disorder (ODD) in children, but the underlying neurocognitive mechanisms are unknown. Therefore, in the current study we measured INS between mothers and children in interactions by using simultaneous functional Near-infrared Spectroscopy (fNIRS), and explored its association with ODD symptoms in children. Seventy-two mother-child dyads were recruited to participate in the study, including 35 children with ODD and 37 healthy children to be used as a control. Each mother-child dyad was measured for neural activity in frontal, parietal, and temporal lobe regions while completing free-play as well as positive, and negative topic discussion tasks. We used Phase-locked value to calculate the synchrony strength and then used the K-means algorithm and k-space based alignment tests to confirm the specific patterns of parent-child synchrony in different brain areas. The results showed that, in free-play (right MFG and bilateral SFG), positive (left TPJ and bilateral SFGdor), and negative (bilateral SFGmed, right ANG, and left MFG) topic discussions, the mother-child pairs showed different patterns of INS. These specific INS patterns were significantly lower in the ODD group compared to the control group and were negatively associated with ODD symptoms in children. Network analyses showed that these INS patterns were connected to different nodes in the ODD symptom network. Our findings suggest that ODD mother-child dyads exhibit lower neural synchrony across a wide range of parent-child interactions. Neural synchrony in the context of interpersonal interactions provides new insights into understanding the neural mechanisms of ODD and can be used as an indicator of neural and socio-environmental factors in the network of psychological disorder symptoms.

Details DOI

AAAI Conference 2022 Short Paper

A Discriminative and Robust Feature Learning Approach for EEG-Based Motor Imagery Decoding (Student Abstract)

Xiuyu Huang
Nan Zhou
Kup-Sze Choi

Convolutional neural networks (CNNs) have been commonly applied in the area of the Electroencephalography (EEG)based Motor Imagery (MI) classification, significantly pushing the boundary of the state-of-the-art. In order to simultaneously decode the discriminative features and eliminate the negative effects of non-Gaussian noise and outliers in the motor imagery data, in this abstract, we propose a novel robust supervision signal, called Correntropy based Center Loss (CCL), for CNN training, which utilizes the correntropy induced distance as the objective measure. It is encouraging to see that the CNN model trained by the combination of softmax loss and CCL loss outperforms the state-of-the-art models on two public datasets.

PDF Details

TCS Journal 2022 Journal Article

Computational completeness of spiking neural P systems with inhibitory rules for generating string languages

Nan Zhou
Hong Peng
Jun Wang
Qian Yang
Xiaohui Luo

Spiking neural P systems with inhibitory rules (in short, SNP-IR systems) are a distributed parallel computing model, abstracted by the spiking and inhibitory mechanisms of biological neurons. Computational completeness of SNP-IR systems as number generating/accepting and function computing devices has been studied recently. However, computational completeness of SNP-IR systems as language generating devices still has not been investigated. We discuss the relationship of languages generated by SNP-IR systems with regular languages. Moreover, we prove that SNP-IR systems can generate recursively enumerable languages by means of a projection of inverse-morphic image.

Details DOI

I&C Journal 2021 Journal Article

Computational completeness of sequential spiking neural P systems with inhibitory rules

Tingting Bao
Nan Zhou
Hong Peng
Qian Yang
Jun Wang

Spiking neural P systems with inhibitory rules (in short, IR-SN P systems) are a kind of bio-inspired computing systems, which are abstracted by the inhibitory synaptic mechanism of biological neurons. IR-SN P systems work in synchronous mode. This paper investigates their sequential version, sequential IR-SN P systems (in short, IR-SSN P systems). In sequential mode, not only the rules in each neuron are applied sequentially, but also the neurons fire in a sequential manner. The maximum-spike-number strategy is considered in sequential mode, and two sub-modes are further distinguished: max-sequentiality strategy and max-pseudo-sequentiality strategy. Computational completeness of IR-SSN P systems as number generating/accepting devices and function computing devices are discussed. It is proven that IR-SSN P systems are Turing universal number generating/accepting devices. Moreover, a small universal IR-SSN P system for computing functions is established in max-sequential strategy.

Details DOI

I&C Journal 2021 Journal Article

Nonlinear neural P systems for generating string languages

Nan Zhou
Qian Yang
Hong Peng
Jun Wang
Xiaohui Luo

Nonlinear spiking neural P (NSNP) system is a distributed parallel computing model inspired from the mechanisms of spiking neurons. Computational completeness of NSNP systems as number generating/accepting devices and function computing devices has been already discussed. However, universality result of NSNP systems as language generating devices has not been established so far. This paper investigates computational power of NSNP systems as language generating devices. The relationships of languages generated by NSNP systems with regular languages are investigated. Moreover, we prove that recursively enumerable languages can be characterized by the projection of inverse-morphic images of languages generated by NSNP systems.

Details DOI

TIST Journal 2019 Journal Article

Short Text Analysis Based on Dual Semantic Extension and Deep Hashing in Microblog

Wanqiu Cui
Junping Du
Dawei Wang
Xunpu Yuan
Feifei Kou
Liyan Zhou
Nan Zhou

Short text analysis is a challenging task as far as the sparsity and limitation of semantics. The semantic extension approach learns the meaning of a short text by introducing external knowledge. However, for the randomness of short text descriptions in microblogs, traditional extension methods cannot accurately mine the semantics suitable for the microblog theme. Therefore, we use the prominent and refined hashtag information in microblogs as well as complex social relationships to provide implicit guidance for semantic extension of short text. Specifically, we design a deep hash model based on social and conceptual semantic extension, which consists of dual semantic extension and deep hashing representation. In the extension method, the short text is first conceptualized to achieve the construction of hashtag graph under conceptual space. Then, the associated hashtags are generated by correlation calculation based on the integration of social relationships and concepts to extend the short text. In the deep hash model, we use the semantic hashing model to encode the abundant semantic features and form a compact and meaningful binary encoding. Finally, extensive experiments demonstrate that our method can learn and represent the short texts well by using more meaningful semantic signal. It can effectively enhance and guide the semantic analysis and understanding of short text in microblogs.

Details DOI