Author name cluster

Hao Yan

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

EAAI Journal 2026 Journal Article

An accurate, generalized, and efficient detection framework for steel surface defect inspection

Hao Yan
Lanxiang Chen
Hong Zhang
Shikun Chen
Shunwu Xu
Zhaowen Chen

Steel surface defect detection is crucial for ensuring product quality and process reliability in industrial manufacturing; however, existing methods often struggle to simultaneously achieve high accuracy, real-time efficiency, and strong cross-dataset generalization. This paper proposes AGE-YOLO (Accurate, Generalized, and Efficient YOLO (You Only Look Once)), an enhanced detection framework built upon the YOLO version 11 (YOLOv11) architecture. It is designed to address these challenges by incorporating three key components: (1) a Feature-Context Multi-Aggregation Network (FC-MANet) that integrates Convolutional Gated Linear Units (CGLU) and Partial Convolution (PConv) to capture irregular defect features while mitigating background artifacts through dynamic gating; (2) an Adaptive Cross-scale Fusion (ACF) module that dynamically aligns and fuses multi-level features via joint spatial–channel guidance, effectively suppressing irrelevant background responses; and (3) a Shared Insight Focus Head (SIFHead) employing lightweight shared convolutions with Group Normalization (GN) to enhance localization consistency, particularly for small defects. Experimental results on the GC10-DET dataset demonstrate that AGE-YOLO achieves a mean Average Precision (mAP) of 72. 8% at an Intersection over Union (IoU) threshold of 0. 5 (mAP@0. 5), outperforming YOLOv11n (nano) baseline by 5. 2% and recent YOLOv12n and YOLOv13n variants by 5. 8% and 5. 6%, respectively. The method also surpasses the Real-Time DEtection TRansformer (RT-DETR) by 3. 6% mAP while using only 10. 4% of its parameters. With 3. 41 million parameters and 7. 7 Giga Floating-Point Operations (GFLOPs), AGE-YOLO achieves a real-time inference speed of 189 frames per second (FPS) at 640 × 640 resolution on an NVIDIA RTX 4090D Graphics Processing Unit (GPU). Furthermore, hardware validation on the NVIDIA Jetson Orin Nano platform shows that, after optimization with the NVIDIA TensorRT inference engine using 16-bit floating-point (FP16) precision, the model attains a throughput of 74. 6 FPS, confirming its suitability for real-time edge deployment. Additional experiments on the Northeastern University steel defect dataset (NEU-DET) and the printed circuit board defect dataset released by the Peking University Open Laboratory on Human–Robot Interaction (HRIPCB) demonstrate mAP@0. 5 scores of 85. 4% and 95. 7%, respectively, yielding an average improvement of 4. 5% over representative lightweight detectors. The implementation of this work is publicly available at https: //github. com/gnmtdt/AGE-YOLO.

Details DOI

IJCAI Conference 2025 Conference Paper

A Relaxed Symmetric Non-negative Matrix Factorization Approach for Community Discovery (Extended Abstract)

Zhigang Liu
Hao Yan
Yurong Zhong
Weiling Li

Community discovery is a prominent issue in com-plex network analysis. Symmetric non-negative matrix factorization (SNMF) is frequently adopted to tackle this issue. The use of a single feature matrix can depict network symmetry, but it limits its ability to learn node representations. To break this limitation, we present a novel Relaxed Symmetric NMF (RSN) approach to boost an SNMF-based community detector. It works by 1) expanding the representational space and its degrees of freedom with multiple feature factors; 2) integrating the well-designed equality-constraints to make the model well-aware of the network’s intrinsic symmetry; 3) employing graph regularization to pre-serve the local geometric invariance of the network structure; and 4) separating constraints from decision variables for efficient optimization via the principle of alternating-direction-method of multi-pliers. RSN’s effectiveness is verified through empirical studies on six real social networks, show-casing superior precision in community discovery over existing models and baselines.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

Coherence-free Entrywise Estimation of Eigenvectors in Low-rank Signal-plus-noise Matrix Models

Hao Yan
Keith Levin

Spectral methods are widely used to estimate eigenvectors of a low-rank signal matrix subject to noise. These methods use the leading eigenspace of an observed matrix to estimate this low-rank signal. Typically, the entrywise estimation error of these methods depends on the coherence of the low-rank signal matrix with respect to the standard basis. In this work, we present a novel method for eigenvector estimation that avoids this dependence on coherence. Assuming a rank-one signal matrix, under mild technical conditions, the entrywise estimation error of our method provably has no dependence on the coherence under Gaussian noise (i. e. , in the spiked Wigner model), and achieves the optimal estimation rate up to logarithmic factors. Simulations demonstrate that our method performs well under non-Gaussian noise and that an extension of our method to the case of a rank-$r$ signal matrix has little to no dependence on the coherence. In addition, we derive new metric entropy bounds for rank-$r$ singular subspaces under $\ell_{2, \infty}$ distance, which may be of independent interest. We use these new bounds to improve the best known lower bound for rank-$r$ eigenspace estimation under $\ell_{2, \infty}$ distance.

PDF Details DOI

NeurIPS Conference 2023 Conference Paper

A Comprehensive Study on Text-attributed Graphs: Benchmarking and Rethinking

Hao Yan
Chaozhuo Li
Ruosong Long
Chao Yan
Jianan Zhao
Wenwen Zhuang
Jun Yin
Peiyan Zhang

Text-attributed graphs (TAGs) are prevalent in various real-world scenarios, where each node is associated with a text description. The cornerstone of representation learning on TAGs lies in the seamless integration of textual semantics within individual nodes and the topological connections across nodes. Recent advancements in pre-trained language models (PLMs) and graph neural networks (GNNs) have facilitated effective learning on TAGs, garnering increased research interest. However, the absence of meaningful benchmark datasets and standardized evaluation procedures for TAGs has impeded progress in this field. In this paper, we propose CS-TAG, a comprehensive and diverse collection of challenging benchmark datasets for TAGs. The CS-TAG datasets are notably large in scale and encompass a wide range of domains, spanning from citation networks to purchase graphs. In addition to building the datasets, we conduct extensive benchmark experiments over CS-TAG with various learning paradigms, including PLMs, GNNs, PLM-GNN co-training methods, and the proposed novel topological pre-training of language models. In a nutshell, we provide an overview of the CS-TAG datasets, standardized evaluation procedures, and present baseline experiments. The entire CS-TAG project is publicly accessible at \url{https: //github. com/sktsherlock/TAG-Benchmark}.

PDF Details

IS Journal 2023 Journal Article

Convolutional Neural Network-Assisted Adaptive Sampling for Sparse Feature Detection in Image and Video Data

Geet Lahoti
Chitta Ranjan
Jialei Chen
Hao Yan
Chuck Zhang

In this article, we propose a feature detection approach that employs an adaptive sampling technique coupled with a convolutional neural network (CNN) model, to detect sparse features of interest in high-dimensional input data. Adaptive sampling criterion smartly explores the high-dimensional input and exploits the regions of interest. The CNN model determines the likelihood of the presence of the desired features, which guides the exploitation component of the sampling strategy. The effectiveness of the approach is illustrated using case studies, where emotions in a candidate’s interview video are detected for evaluation purpose and anomalies in a product’s image are extracted for quality control. The approach reduces evaluation time and minimizes amount of input data to be accessed and processed while effectively identifying desired sparse features.

Details DOI

EAAI Journal 2023 Journal Article

CSCMOT: Multi-object tracking based on channel spatial cooperative attention mechanism

Fei Wang
Hao Yan
Libo Zhang
Ke Gao

Multi-object tracking has made good progress in recent years. Most mainstream methods use the fusion method of detection and Re-ID to complete the multi-target tracking technology. However, the current multi-tracking algorithm is slow and cannot meet the real-time requirements, which makes it difficult to implement in actual scenarios. In addition, the current mainstream multi-target tracking technology often has the problem of identity information jumping. Such frequent identity information hopping can lead to serious problems in some demanding practical applications, resulting in poor tracking performance. To solve these problems, we propose a simple framework CSCMOT. A non-parametric attention mechanism is adopted to focus on some feature points of the target without increasing the amount of computation, so as to reduce the amount of computation and improve the real-time performance of the algorithm. In addition, the jumping problem of identity information can be reduced by random simulation occlusion to improve tracking performance. Experiments show that the real-time performance of the proposed CSCMOT framework reaches 32. 5 FPS, which exceeds most of the mainstream methods. In addition, the ID-switch was reduced to 2493 on the MOT17 dataset. Made a great breakthrough, better to solve the problem of identity information jump. The tracking accuracy is also 71. 5, a competitive result that exceeds most of the mainstream methods. Effective data show that the framework improves the real-time performance of the algorithm, solves the problem of identity jump between targets, and is more conducive to experiment landing, which is easy to combine with the mobile robot platform.

Details DOI

EAAI Journal 2023 Journal Article

Open-circuit fault diagnosis in voltage source inverter for motor drive by using deep neural network

Hao Yan
Yumeng Peng
Wenjun Shang
Dongdong Kong

To increase the reliability of motor drive system, many fault diagnosis approaches have been reported with regard to three-phase Pulse Width Modulation Voltage Source Inverter (PWM-VSI). Based on feature engineering and deep neural network, this paper proposes a fault diagnosis approach for the VSI in three-phase Permanent-magnet Synchronous Motor (PMSM) drive. The three-phase current signals are used for the fault diagnosis of VSI. 10 typical signal features are extracted from the three-phase current signals and used as the input of deep neural network. To improve the diagnostic performance, the network structure of the presented deep neural network is designed like a pyramid. Experimental results show that the presented method can detect not only the single open-circuit faults but also the double open-circuit faults in power switches, with high diagnostic accuracy (more than 95%). Besides, comparison results show that the presented method has strong generalization performance. This paper provides theoretical guidance for the fault diagnosis of VSI in PMSM.

Details DOI

NeurIPS Conference 2023 Conference Paper

Train Once and Explain Everywhere: Pre-training Interpretable Graph Neural Networks

Jun Yin
Chaozhuo Li
Hao Yan
Jianxun Lian
Senzhang Wang

Intrinsic interpretable graph neural networks aim to provide transparent predictions by identifying the influential fraction of the input graph that guides the model prediction, i. e. , the explanatory subgraph. However, current interpretable GNNs mostly are dataset-specific and hard to generalize to different graphs. A more generalizable GNN interpretation model which can effectively distill the universal structural patterns of different graphs is until-now unexplored. Motivated by the great success of recent pre-training techniques, we for the first time propose the Pre-training Interpretable Graph Neural Network ($\pi$-GNN) to distill the universal interpretability of GNNs by pre-training over synthetic graphs with ground-truth explanations. Specifically, we introduce a structural pattern learning module to extract diverse universal structure patterns and integrate them together to comprehensively represent the graphs of different types. Next, a hypergraph refining module is proposed to identify the explanatory subgraph by incorporating the universal structure patterns with local edge interactions. Finally, the task-specific predictor is cascaded with the pre-trained $\pi$-GNN model and fine-tuned over downstream tasks. Extensive experiments demonstrate that $\pi$-GNN significantly surpasses the leading interpretable GNN baselines with up to 9. 98\% interpretation improvement and 16. 06\% classification accuracy improvement. Meanwhile, $\pi$-GNN pre-trained on graph classification task also achieves the top-tier interpretation performance on node classification task, which further verifies its promising generalization performance among different downstream tasks. Our code and datasets are available at https: //anonymous. 4open. science/r/PI-GNN-F86C

PDF Details

AAAI Conference 2023 Conference Paper

WSiP: Wave Superposition Inspired Pooling for Dynamic Interactions-Aware Trajectory Prediction

Renzhi Wang
Senzhang Wang
Hao Yan
Xiang Wang

Predicting motions of surrounding vehicles is critically important to help autonomous driving systems plan a safe path and avoid collisions. Although recent social pooling based LSTM models have achieved significant performance gains by considering the motion interactions between vehicles close to each other, vehicle trajectory prediction still remains as a challenging research issue due to the dynamic and high-order interactions in the real complex driving scenarios. To this end, we propose a wave superposition inspired social pooling (Wave-pooling for short) method for dynamically aggregating the high-order interactions from both local and global neighbor vehicles. Through modeling each vehicle as a wave with the amplitude and phase, Wave-pooling can more effectively represent the dynamic motion states of vehicles and capture their high-order dynamic interactions by wave superposition. By integrating Wave-pooling, an encoder-decoder based learning framework named WSiP is also proposed. Extensive experiments conducted on two public highway datasets NGSIM and highD verify the effectiveness of WSiP by comparison with current state-of-the-art baselines. More importantly, the result of WSiP is more interpretable as the interaction strength between vehicles can be intuitively reflected by their phase difference. The code of the work is publicly available at https://github.com/Chopin0123/WSiP.

PDF Details DOI

YNICL Journal 2021 Journal Article

Multisite schizophrenia classification by integrating structural magnetic resonance imaging data with polygenic risk score

Ke Hu
Meng Wang
Yong Liu
Hao Yan
Ming Song
Jun Chen
Yunchun Chen
Huaning Wang

Previous brain structural magnetic resonance imaging studies reported that patients with schizophrenia have brain structural abnormalities, which have been used to discriminate schizophrenia patients from normal controls. However, most existing studies identified schizophrenia patients at a single site, and the genetic features closely associated with highly heritable schizophrenia were not considered. In this study, we performed standardized feature extraction on brain structural magnetic resonance images and on genetic data to separate schizophrenia patients from normal controls. A total of 1010 participants, 508 schizophrenia patients and 502 normal controls, were recruited from 8 independent sites across China. Classification experiments were carried out using different machine learning methods and input features. We tested a support vector machine, logistic regression, and an ensemble learning strategy using 3 feature sets of interest: (1) imaging features: gray matter volume, (2) genetic features: polygenic risk scores, and (3) a fusion of imaging features and genetic features. The performance was assessed by leave-one-site-out cross-validation. Finally, some important brain and genetic features were identified. We found that the models with both imaging and genetic features as input performed better than models with either alone. The average accuracy of the classification models with the best performance in the cross-validation was 71.6%. The genetic feature that measured the cumulative risk of the genetic variants most associated with schizophrenia contributed the most to the classification. Our work took the first step toward considering both structural brain alterations and genome-wide genetic factors in a large-scale multisite schizophrenia classification. Our findings may provide insight into the underlying pathophysiology and risk mechanisms of schizophrenia.

Details DOI

YNIMG Journal 2020 Journal Article

A multi-model deep convolutional neural network for automatic hippocampus segmentation and classification in Alzheimer’s disease

Manhua Liu
Fan Li
Hao Yan
Kundong Wang
Yixin Ma
Li Shen
Mingqing Xu

Alzheimer's disease (AD) is a progressive and irreversible brain degenerative disorder. Mild cognitive impairment (MCI) is a clinical precursor of AD. Although some treatments can delay its progression, no effective cures are available for AD. Accurate early-stage diagnosis of AD is vital for the prevention and intervention of the disease progression. Hippocampus is one of the first affected brain regions in AD. To help AD diagnosis, the shape and volume of the hippocampus are often measured using structural magnetic resonance imaging (MRI). However, these features encode limited information and may suffer from segmentation errors. Additionally, the extraction of these features is independent of the classification model, which could result in sub-optimal performance. In this study, we propose a multi-model deep learning framework based on convolutional neural network (CNN) for joint automatic hippocampal segmentation and AD classification using structural MRI data. Firstly, a multi-task deep CNN model is constructed for jointly learning hippocampal segmentation and disease classification. Then, we construct a 3D Densely Connected Convolutional Networks (3D DenseNet) to learn features of the 3D patches extracted based on the hippocampal segmentation results for the classification task. Finally, the learned features from the multi-task CNN and DenseNet models are combined to classify disease status. Our method is evaluated on the baseline T1-weighted structural MRI data collected from 97 AD, 233 MCI, 119 Normal Control (NC) subjects in the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. The proposed method achieves a dice similarity coefficient of 87.0% for hippocampal segmentation. In addition, the proposed method achieves an accuracy of 88.9% and an AUC (area under the ROC curve) of 92.5% for classifying AD vs. NC subjects, and an accuracy of 76.2% and an AUC of 77.5% for classifying MCI vs. NC subjects. Our empirical study also demonstrates that the proposed multi-model method outperforms the single-model methods and several other competing methods.

Details DOI

AAAI Conference 2020 Conference Paper

Tensor Completion for Weakly-Dependent Data on Graph for Metro Passenger Flow Prediction

Ziyue Li
Nurettin Dorukhan Sergin
Hao Yan
Chen Zhang
Fugee Tsung

Low-rank tensor decomposition and completion have attracted signiﬁcant interest from academia given the ubiquity of tensor data. However, low-rank structure is a global property, which will not be fulﬁlled when the data presents complex and weak dependencies given speciﬁc graph structures. One particular application that motivates this study is the spatiotemporal data analysis. As shown in the preliminary study, weakly dependencies can worsen the low-rank tensor completion performance. In this paper, we propose a novel lowrank CANDECOMP / PARAFAC (CP) tensor decomposition and completion framework by introducing the L1-norm penalty and Graph Laplacian penalty to model the weakly dependency on graph. We further propose an efﬁcient optimization algorithm based on the Block Coordinate Descent for efﬁcient estimation. A case study based on the metro passenger ﬂow data in Hong Kong is conducted to demonstrate an improved performance over the regular tensor completion methods.

PDF Details

EAAI Journal 2019 Journal Article

Exploring eWOM in online customer reviews: Sentiment analysis at a fine-grained level

Qing Sun
Jianwei Niu
Zhong Yao
Hao Yan

Customer reviews in social media and electronic commerce Web sites contain valuable electronic word-of-mouth (eWOM) information of products, which facilitates firms’ business strategy and individual consumers’ comparison shopping. Exploring eWOM of products embedded in customer reviews has attracted interest from researchers in various fields. Coarse-grained and context-free sentiment analysis approaches have been used in existing researches, which however often fail to satisfy the firms’ demands of fine-grained extraction of market intelligence from social media. In this study, we propose an original method to explore eWOM of products based on sentiment analysis at fine-grained level from a large volume of online customer reviews. We illustrate a feature-based and context-sensitive sentiment analysis mechanism that can leverage the sheer volume of customer reviews in social media sites. A novel semi-supervised fuzzy product ontology mining algorithm is proposed to extract semantic knowledge from online customer reviews with positive or negative labels. Based on real-world online customer review data set, the proposed method shows remarkable performance improvement over baseline methods at exploring eWOM of product a fine-grained level. With the novel eWOM exploring method, firms can improve their product design and marketing strategies, and potential consumers can make better online purchase decisions.

Details DOI

TIST Journal 2015 Journal Article

Peacock

Yi Wang
Xuemin Zhao
Zhenlong Sun
Hao Yan
Lifeng Wang
Zhihui Jin
Liubin Wang
Yang Gao

Latent Dirichlet allocation (LDA) is a popular topic modeling technique in academia but less so in industry, especially in large-scale applications involving search engine and online advertising systems. A main underlying reason is that the topic models used have been too small in scale to be useful; for example, some of the largest LDA models reported in literature have up to 10 3 topics, which difficultly cover the long-tail semantic word sets. In this article, we show that the number of topics is a key factor that can significantly boost the utility of topic-modeling systems. In particular, we show that a “big” LDA model with at least 10 5 topics inferred from 10 9 search queries can achieve a significant improvement on industrial search engine and online advertising systems, both of which serve hundreds of millions of users. We develop a novel distributed system called Peacock to learn big LDA models from big data. The main features of Peacock include hierarchical distributed architecture, real-time prediction, and topic de-duplication. We empirically demonstrate that the Peacock system is capable of providing significant benefits via highly scalable LDA topic models for several industrial applications.

Details DOI

YNIMG Journal 2009 Journal Article

Hemispheric asymmetry in cognitive division of anterior cingulate cortex: A resting-state functional connectivity study

Hao Yan
Xi-Nian Zuo
Deyi Wang
Jue Wang
Chaozhe Zhu
Michael P. Milham
Dai Zhang
Yufeng Zang

The cognitive division of anterior cingulate cortex (ACC-cd) plays an important role in cognitive control via a distributed attention network. The structural hemispheric asymmetries of ACC have been revealed by several neuroimaging studies. However potential functional hemispheric asymmetries of ACC remain less clear. Investigating the functional hemispheric asymmetries of ACC helps for a better understanding of ACC function. The aim of this study was to use resting-state functional magnetic resonance imaging (fMRI) to examine hemispheric differences in the functional networks associated with ACC-cd in the two hemispheres. ROI-based functional connectivity analysis was performed on a group of 49 right-handed healthy volunteers. The left and right ACC-cd showed significant differences in their patterns of connectivity with a variety of brain regions, including the dorsolateral prefrontal cortex, inferior parietal lobule, superior parietal lobule and dorsal posterior cingulate cortex in their ipsilateral cerebral cortex, as well as cerebellar tonsil and inferior semilunar lobule in their contralateral cerebellar hemisphere. Specifically, for these areas, we found significantly greater connectivity strength with ACC-cd in the right hemisphere than the left, regardless of whether the connection was positive or negative. The current results highlight the presence of clear asymmetries in functional networks associated with ACC-cd. Future functional imaging studies are needed to give greater attention to the lateralized ACC functional networks which are observed.

Details DOI

YNIMG Journal 2007 Journal Article

Amplitude of low frequency fluctuation within visual areas revealed by resting-state functional MRI

Hong Yang
Xiang-Yu Long
Yihong Yang
Hao Yan
Chao-Zhe Zhu
Xiang-Ping Zhou
Yu-Feng Zang
Qi-Yong Gong

Most studies of resting-state functional magnetic resonance imaging (fMRI) have applied the temporal correlation in the time courses to investigate the functional connectivity between brain regions. Alternatively, the power of low frequency fluctuation (LFF) may also be used as a biomarker to assess spontaneous activity. The purpose of the current study is to evaluate whether the amplitude of the LFF (ALFF) relates to cerebral physiological states. Ten healthy subjects underwent four resting-state fMRI scanning sessions, two for eyes-open (EO) and two for eyes-closed (EC) conditions, with two sets of parameters (TR=400 ms and 2 s, respectively). After data preprocessing, ALFF was obtained by calculating the square root of the power spectrum in the frequency range of 0. 01–0. 08 Hz. Our results showed that the ALFF in EO was significantly higher than that in EC (P <0. 05, corrected) in the bilateral visual cortices. Furthermore, the ALFF in EO was significantly reduced in the right paracentral lobule (PCL) than in EC (P <0. 05, corrected). Region of interest (ROI) analysis showed that the ALFF differences between EO and EC were consistent for each subject. In contrast, no significant ALFF differences were found between EO and EC (P <0. 381) in the posterior cingulate cortex. All these results agree well with previous studies comparing EO and EC states. Our finding of the distinct ALFF difference between EO and EC in the visual cortex implies that the ALFF may be a novel biomarker for physiological states of the brain.

Details DOI