检索结果-内蒙古大学图书馆

2024 International Conference on Cyber-Physical Social intelligence, ICCSI 2024

作者： Yang, Yueteng Li, Bing Li, Weikai Chen, Haifeng Cao, Wenming Chongqing Jiaotong University Department of Mathematics China Miit Key Laboratory of Pattern Analysis and Machine Intelligence Nanjing China Nanjing University Nanjing Drum Tower Hospital Affiliated Hospital of Medical School Department of Neurology Nanjing China

ISBN: (纸本)9798350376739

Synthesizing Aβ-PET images from cross-modal neuroimaging for diagnosing Alzheimer's disease through multi-modal medical image fusion is highly significant. However, there are relatively few studies in this area. We propose a multi-modal fusion adversarial method for Aβ-PET medical image synthesis, named MultiMed, to generate Aβ-PET images by fusing features from T1 and Flair images. Our approach employs an end-to-end method for image generation, incorporating a Multi-Feature Fusion Stream module for feature fusion. Integrating multimodal features enhances the model's representation capability and preliminarily designed a visual domain classifier for Alzheimer's disease diagnosis. We constructed an internal dataset for model training and validated our model on two external validation sets, achieving notable performance. © 2024 IEEE.

关键词： Neuroimaging

来源：评论

学校读者我要写书评

暂无评论

Minimum Error Entropy High-Order Extended Kalman Filter

Minimum Error Entropy High-Order Extended Kalman Filter

引用

2023 International Conference on Cyber-Physical Social intelligence, ICCSI 2023

作者： Cheng, Zhi Chen, Xiaofeng Li, Hua Li, Weikai Lin, Dongyuan Chongqing Jiaotong University Department of Mathematics Chongqing China Miit Key Laboratory of Pattern Analysis and Machine Intelligence Nanjing China Southwest University College of Electronic and Information Engineering Chongqing China

ISBN: (纸本)9798350312492

The conventional extended Kalman filter(EKF) is proposed under the criterion of minimum mean square error(MMSE) and omits high-order information. This leads to poor estimation of the EKF in non-Gaussian and strongly nonlinear systems. In this paper, for a class of nonlinear non-Gaussian systems in polynomial form, Pseudo-linearizing the system while preserving the high-order information, a new filter is proposed based on the minimum error entropy(MEE) criterion called the minimum error entropy high-order extended Kalman filter (MEE-HEKF). In the MEE-HEKF algorithm, the state estimation problem is transformed into a recursive solution problem in the form of a Kalman filter by a fixed-point iterative approach based on the MEE cost function. The proposed algorithm has better robustness under strong nonlinearity and non-Gaussian noise. Finally, the effectiveness of the new algorithm is illustrated by an example. © 2023 IEEE.

关键词： Extended Kalman filters

来源：评论

学校读者我要写书评

暂无评论

All-around Neural Collapse for Imbalanced Classification

引用

IEEE Transactions on Knowledge and Data Engineering 2025年

作者： Zhang, Enhao Li, Chaohua Geng, Chuanxing Chen, Songcan MIIT Key Laboratory of Pattern Analysis and Machine Intelligence China College of Computer Science and Technology Nanjing211106 China

Neural Collapse (NC) presents an elegant geometric structure that enables individual activations (features), class means and classifier (weights) vectors to reach optimal inter-class separability during the terminal phase of training on a balanced dataset. Once shifted to imbalanced classification, such an optimal structure of NC can be readily destroyed by the notorious minority collapse, where the classifier vectors corresponding to the minority classes are squeezed. In response, existing works mainly optimize classifiers in an effort to recover NC. However, we discover that this squeezing phenomenon is not only confined to classifier vectors but also occurs with class means. Consequently, reconstructing NC solely at the classifier aspect may be futile, as the class means remain compressed, leading to the violation of inherent self-duality in NC (i.e., class means and classifier vectors converge mutually) and incidentally, an unsatisfactory collapse of individual activations towards the corresponding class means. To shake off these dilemmas, we present a unified All-around Neural Collapse framework (AllNC), aiming to comprehensively restore NC across multiple aspects including individual activations, class means and classifier vectors. We thoroughly analyze its effectiveness and verify its performance on multiple benchmark datasets as state-of-the-art in both balanced and imbalanced settings. © 1989-2012 IEEE.

关键词： Contrastive learning Imbalanced classification Long-tailed Neural collapse

来源：评论

学校读者我要写书评

暂无评论

uChecker: Masked Pretrained Language Models as Unsupervised Chinese Spelling Checkers 29

uChecker: Masked Pretrained Language Models as Unsupervised ...

引用

29th International Conference on Computational Linguistics, COLING 2022

作者： Li, Piji College of Computer Science and Technology Nanjing University of Aeronautics Astronautics MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Jiangsu Nanjing China

The task of Chinese Spelling Check (CSC) is aiming to detect and correct spelling errors that can be found in the text. While manually annotating a high-quality dataset is expensive and time-consuming, thus the scale of the training dataset is usually very small (e.g., SIGHAN151 only contains 2339 samples for training), therefore supervised-learning based models usually suffer the data sparsity limitation and over-fitting issue, especially in the era of big language models. In this paper, we are dedicated to investigating the unsupervised paradigm to address the CSC problem and we propose a framework named uChecker to conduct unsupervised spelling error detection and correction. Masked pretrained language models such as BERT are introduced as the backbone model considering their powerful language diagnosis capability. Benefiting from the various and flexible MASKing operations, we propose a Confusionset-guided masking strategy to fine-train the masked language model to further improve the performance of unsupervised detection and correction. Experimental results on standard datasets demonstrate the effectiveness of our proposed model uChecker in terms of character-level and sentence-level Accuracy, Precision, Recall, and F1-Measure on tasks of spelling error detection and correction respectively. © 2022 Proceedings - International Conference on Computational Linguistics, COLING. All rights reserved.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

A Multi-Scale Multi-Hop Graph Convolution Network for Predicting Fluid intelligence via Functional Connectivity

A Multi-Scale Multi-Hop Graph Convolution Network for Predic...

引用

2022 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2022

作者： Wen, Xuyun Cao, Qumei Zhang, Daoqiang Nanjing University of Aeronautics and Astronautics Nanjing College of Computer Science and Technology MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Jiangsu China

ISBN: (纸本)9781665468190

Predicting fluid intelligence via neuroimaging data is important to understand neural mechanisms underlying diverse complex cognitive tasks in human brain. Functional connectivity (FC) reflects interactions among brain regions providing rich information of brain organization, which has been widely used in various behavior predictions. With the success of deep neural networks, graph convolutional network (GCN) is regarded as a promising feature learning method in FC networks (FCNs). However, as a challenging task, the existing GCN models cannot achieve a satisfactory performance in fluid intelligence predication due to the insufficient information utilization of brain connectivity and the limitation of graph convolution layer. To tackle these problems, this paper developed a Multi-Scale Multi-Hop GCN (MS-MH-GCN) to estimate fluid intelligence score by using FC. In the proposed method, we considered the hierarchy of brain system and thus utilized FCs from multiple spatial scales as input for the subsequent feature learning to achieve a complete characterize of brain organization for each individual. We also designed a new multi-hop graph convolution layer that uses multi-hop neighbors instead of l-hop neighbor in traditional GCN to guide message passing of nodal feature at every step. The introduction of high-order graph information benefits to the model learning ability improvement. Additionally, it is also worth emphasizing that, during feature learning process, we added contrast constraint to multi-scale FCNs to improve the similarity of feature representations across different spatial scales within a subject. Experimental results showed that our proposed method performed much better than the other four art-of-the-state methods. © 2022 IEEE.

关键词： Brain

来源：评论

学校读者我要写书评

暂无评论

fMRI-based Decoding of Visual Information from Human Brain Activity: A Brief Review

引用

International Journal of Automation and computing 2021年第2期18卷 170-184页

作者： Shuo Huang Wei Shao Mei-Ling Wang Dao-Qiang Zhang College of Computer Science and Technology Nanjing University of Aeronautics and AstronauticsNanjing 211106China MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Nanjing 211106China

One of the most significant challenges in the neuroscience community is to understand how the human brain *** progress in neuroimaging techniques have validated that it is possible to decode a person′s thoughts,memories,and emotions via functional magnetic resonance imaging(i.e.,fMRI)since it can measure the neural activation of human brains with satisfied spatiotemporal ***,the unprecedented scale and complexity of the fMRI data have presented critical computational bottlenecks requiring new scientific analytic *** the increasingly important role of machine learning in neuroscience,a great many machine learning algorithms are presented to analyze brain activities from the fMRI *** this paper,we mainly provide a comprehensive and up-to-date review of machine learning methods for analyzing neural activities with the following three aspects,i.e.,brain image functional alignment,brain activity pattern analysis,and visual stimuli *** addition,online resources and open research problems on brain pattern analysis are also provided for the convenience of future research.

关键词： Functional magnetic resonance imaging(fMRI) functional alignment brain activity brain decoding visual stimuli reconstruction

来源：评论

学校读者我要写书评

暂无评论

TimeCHEAT: A Channel Harmony Strategy for Irregularly Sampled Multivariate Time Series analysis 39

TimeCHEAT: A Channel Harmony Strategy for Irregularly Sample...

引用

39th Annual AAAI Conference on Artificial intelligence, AAAI 2025

作者： Liu, Jiexi Cao, Meng Chen, Songcan College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics China MIIT Key Laboratory of Pattern Analysis and Machine Intelligence China

ISBN: (纸本)157735897X

Irregularly sampled multivariate time series (ISMTS) are prevalent in reality. Due to their non-uniform intervals between successive observations and varying sampling rates among series, the channel-independent (CI) strategy, which has been demonstrated more desirable for complete multivariate time series forecasting in recent studies, has failed. This failure can be further attributed to the sampling sparsity, which provides insufficient information for effective CI learning, thereby reducing its capacity. When we resort to the channel-dependent (CD) strategy, even higher capacity cannot mitigate the potential loss of diversity in learning similar embedding patterns across different channels. We find that existing work considers CI and CD strategies to be mutually exclusive, primarily because they apply these strategies to the global channel. However, we hold the view that channel strategies do not necessarily have to be used globally. Instead, by appropriately applying them locally and globally, we can create an opportunity to take full advantage of both strategies. This leads us to introduce the Channel Harmony ISMTS Transformer (TimeCHEAT), which utilizes the CD strategy locally and the CI strategy globally. Specifically, we segment the ISMTS into sub-series level patches. Locally, the CD strategy aggregates information within each patch for time embedding learning, maximizing the use of relevant observations while reducing long-range irrelevant interference. Here, we enhance generality by transforming embedding learning into an edge weight prediction task using bipartite graphs, eliminating the need for special prior knowledge. Globally, the CI strategy is applied across patches, allowing the Transformer to learn individualized attention patterns for each channel. Experimental results indicate our proposed TimeCHEAT demonstrates competitive state-of-the-art performance across three mainstream tasks including classification, forecasting and interpolation. Copyri

关键词：

来源：评论

学校读者我要写书评

暂无评论

Expand Horizon: Graph Out-of-Distribution Generalization via Multi-Level Environment Inference 39

Expand Horizon: Graph Out-of-Distribution Generalization via...

引用

39th Annual AAAI Conference on Artificial intelligence, AAAI 2025

作者： Zhang, Jiaqiang Chen, Songcan College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics China MIIT Key Laboratory of Pattern Analysis and Machine Intelligence China

ISBN: (纸本)157735897X

Graph neural networks (GNNs) are widely used for node classification tasks, but when encountering distribution shifts due to environmental change in real-world scenarios, they tend to learn unstable correlations between features and labels. To overcome this dilemma, a powerful class of approaches views the environment as the root cause of those unstable correlations, thereby their key focus is to infer the environment involved, enabling the model to avoid capturing environment-sensitive correlations. However, their inferences rely solely on the single-level information from one low-hop ego-graph, neglecting both global information and multi-granularity information in local ego-graphs with different hops. Although applying deeper GNNs on the high-hop ego-graph could capture global information, it will bring the side effect of over-smoothing node representations. To tackle these issues, we propose a novel Multi-Level Environment Inference model named MLEI, which effectively broadens the horizon of training GNNs under node-level distribution shifts. Specifically, MLEI first leverages a linear graph transformer to surpass the scope of ego-graph, efficiently enabling high-level global environment inference. This global environment is in turn used as an overview to assist layer-by-layer environment inference on local multi-hop ego-graphs. Finally, we combine the environment from global and local views and utilize the designed objective function to capture stable predictive patterns. Extensive experiments on real-world datasets demonstrate that our model achieves satisfactory performance compared with the state-of-the-art methods under various distribution shifts. Copyright © 2025, Association for the Advancement of Artificial intelligence (***). All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

A Survey on Incomplete Multi-label Learning: Recent Advances and Future Trends

arXiv

引用

arXiv 2024年

作者： Li, Xiang Liu, Jiexi Wang, Xinrui Chen, Songcan College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics MIIT Key Laboratory of Pattern Analysis and Machine Intelligence China

关键词： machine learning

来源：评论

学校读者我要写书评

暂无评论

Dirichlet-Based Prediction Calibration for Learning with Noisy Labels

arXiv

引用

arXiv 2024年

作者： Zong, Chen-Chen Wang, Ye-Wen Xie, Ming-Kun Huang, Sheng-Jun College of Computer Science and Technology/Artificial Intelligence Nanjing University of Aeronautics Astronautics MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Nanjing China

Learning with noisy labels can significantly hinder the generalization performance of deep neural networks (DNNs). Existing approaches address this issue through loss correction or example selection methods. However, these methods often rely on the model’s predictions obtained from the softmax function, which can be over-confident and unreliable. In this study, we identify the translation invariance of the softmax function as the underlying cause of this problem and propose the Dirichlet-based Prediction Calibration (DPC) method as a solution. Our method introduces a calibrated softmax function that breaks the translation invariance by incorporating a suitable constant in the exponent term, enabling more reliable model predictions. To ensure stable model training, we leverage a Dirichlet distribution to assign probabilities to predicted labels and introduce a novel evidence deep learning (EDL) loss. The proposed loss function encourages positive and sufficiently large logits for the given label, while penalizing negative and small logits for other labels, leading to more distinct logits and facilitating better example selection based on a large-margin criterion. Through extensive experiments on diverse benchmark datasets, we demonstrate that DPC achieves state-of-the-art performance. The code is available at https://***/chenchenzong/DPC. Copyright © 2024, The Authors. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：