检索结果-内蒙古大学图书馆

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Qian Yang Lijun Liu Xiaobing Yang Li Liu Wei Peng Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming P. R. China Yunnan Key Laboratory of Computer Technology Application Kunming China P. R. China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

Medical Visual Question Answering (Med-VQA) aims at answering clinical questions related to medical imaging, providing important reference for medical imaging diagnosis. Gastrointestinal visual question answering can deeply understand and analyze gastrointestinal medical images, provides supporting information to answer questions about the diagnostic process, and improves diagnostic accuracy and efficiency. However, most existing Med-VQA can only handle simple and general questions, struggling to tackle visual question answering related to complex diseases. Therefore, this paper proposes a Med-VQA model called CACL, which uses cross-guidance and improved combined loss. The model focuses on gastrointestinal image analysis and achieves efficient and accurate feature extraction for gastrointestinal images. A cross-guided attention module is also designed to enhance the model’s reasoning ability when dealing with complex cross-modal tasks. In addition, a multi-task composite loss function is designed to balance the loss of segmentation task and classification task, and improve the overall performance. Experimental results show that the proposed method can effectively improve the accuracy of gastrointestinal visual question answering.

关键词： Visualization Image segmentation Accuracy Image analysis Feature extraction Multitasking Gastrointestinal tract Question answering (information retrieval) Medical diagnostic imaging Diseases

来源：评论

学校读者我要写书评

暂无评论

Multi-objective performance prediction based on a self-constructed Al-Si alloy dataset

Multi-objective performance prediction based on a self-const...

引用

Information Systems and Computing technology (ISCTech), International Conference on

作者： Dan Hu Yingli Liu Tao Shen Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming China Yunnan Key Laboratory of Computer Technologies Application Kunming University of Science and Technology Kunming China

The combination of data-driven approaches and machine learning techniques has changed the design approach for new materials, propelling materials science research into the realm of the fourth paradigm. Researchers in the field of materials science have increasingly focused on utilizing machine learning methods to uncover the underlying nonlinear relationships within material data. However, there is currently limited research in the field of aluminum-silicon alloys regarding the prediction of alloy performance based on the composition-process-structure relationship. Additionally, there is a lack of data sharing in the aluminum-silicon alloy domain. Therefore, this study proposes a methodology. Firstly, an aluminum-silicon alloy dataset is constructed by mining relevant information from materials literature. Then, high-dimensional features in the dataset are subjected to feature selection techniques for dimensionality reduction. Subsequently, a multilayer perceptron model is applied to investigate the relationship between input features such as alloy composition, preparation process, and microstructural parameters, and output features such as yield strength, ultimate tensile strength, and elongation, enabling performance prediction.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Inverse Markov Process Based Constrained Dynamic Graph Layout

引用

Journal of computer Science & technology 2021年第3期36卷 707-718页

作者： Shi-Ying Sheng Sheng-Tao Chen Xiao-Ju Dong Chun-Yuan Wu Xiao-Ru Yuan ParisTech Elite Institute of Technology Shanghai Jiao Tong UniversityShanghai 200240China Department of Computer Science and Engineering Shanghai Jiao Tong UniversityShanghai 200240China Key Laboratory of Machine Perception(Ministry of Education) National Engineering Laboratory for Big Data Analysis and ApplicationPeking UniversityBeijing 100080China

In online dynamic graph drawing,constraints over nodes and node pairs help preserve a coherent mental map in a sequence of *** the constraints is challenging due to the requirements of both preserving mental map and satisfying the visual aesthetics of a graph *** existing algorithms basically depend on local changes but fail to do proper evaluations on the global propagation when setting *** solve this problem,we introduce a heuristic model derived from PageRank which simulates the node movement as an inverse Markov process hence to give a global analysis of the layout's change,according to which different constraints can be *** constraints,along with stress function,generate layouts maintaining spatial positions and shapes of relatively stable substructures between adjacent *** demonstrate that our method preserves both structure and position similarity to help users track graph changes visually.

关键词： graph drawing data stream dynamic graph layout

来源：评论

学校读者我要写书评

暂无评论

ML-GOOD: Towards Multi-Label Graph Out-Of-Distribution Detection 39

ML-GOOD: Towards Multi-Label Graph Out-Of-Distribution Detec...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Cai, Tingyi Jiang, Yunliang Li, Ming Huang, Changqin Wang, Yi Huang, Qionghao School of Computer Science and Technology Zhejiang Normal University China Zhejiang Key Laboratory of Intelligent Education Technology and Application Zhejiang Normal University China School of Information Engineering Huzhou University China Zhejiang Institute of Optoelectronics China

ISBN: (纸本)157735897X

The out-of-distribution (OOD) detection on graph-structured data is crucial for deploying graph neural networks securely in open-world scenarios. However, existing methods have overlooked the prevalent scenario of multi-label classification in real-world applications. In this work, we investigate the unexplored issue of OOD detection within multi-label node classification tasks. We propose ML-GOOD, a simple yet sufficient approach that utilizes an energy function to gauge the OOD score for each label. We further develop a strategy for amalgamating multiple label energies, allowing for the comprehensive utilization of label information to tackle the primary challenges encountered in multi-label scenarios. Extensive experimentation conducted on seven diverse sets of real-world multi-label graph datasets, encompassing cross-domain scenarios. The results show that the AUROC of ML-GOOD is improved by 5.26% in intra-domain and 6.54% in cross-domain compared to the previous methods. These empirical validations not only affirm the robustness of our methodology but also illuminate new avenues for further exploration within this burgeoning field of research. 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

Communication-Efficient Distributed Learning with Local Immediate Error Compensation

arXiv

引用

arXiv 2024年

作者： Cheng, Yifei Shen, Li Xu, Linli Qian, Xun Wu, Shiwei Zhou, Yiming Zhang, Tie Tao, Dacheng Chen, Enhong The Anhui Province Key Lab of Big Data Analysis and Application State Key Laboratory of Cognitive Intelligence School of Data Science School of Computer Science University of Science and Technology China The JD Explore Academy China The Shanghai Artificial Intelligence Laboratory China

Gradient compression with error compensation has attracted significant attention with the target of reducing the heavy communication overhead in distributed learning. However, existing compression methods either perform only unidirectional compression in one iteration with higher communication cost, or bidirectional compression with slower convergence rate. In this work, we propose the Local Immediate Error Compensated SGD (LIEC-SGD) optimization algorithm to break the above bottlenecks based on bidirectional compression and carefully designed compensation approaches. Specifically, the bidirectional compression technique is to reduce the communication cost, and the compensation technique compensates the local compression error to the model update immediately while only maintaining the global error variable on the server throughout the iterations to boost its efficacy. Theoretically, we prove that LIEC-SGD is superior to previous works in either the convergence rate or the communication cost, which indicates that LIEC-SGD could inherit the dual advantages from unidirectional compression and bidirectional compression. Finally, experiments of training deep neural networks validate the effectiveness of the proposed LIEC-SGD algorithm. Copyright © 2024, The Authors. All rights reserved.

关键词： Error compensation

来源：评论

学校读者我要写书评

暂无评论

Cross Modal Training for ASR Error Correction with Contrastive Learning

Cross Modal Training for ASR Error Correction with Contrasti...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Jin Jiang Xiaojun Wan Wei Peng Rongjun Li Jingyuan Yang Yanquan Zhou Beijing University of Posts and Telecommunications Wangxuan Institute of Computer Technology Peking University The MOE Key Laboratory of Computational Linguistics Peking University Artificial Intelligence Application Research Center Huawei Technologies

ASR Error Correction (AEC) aims to post-process the output of ASR systems and further reduce the word error rate. In this paper, we propose a cross-modal training framework with contrastive learning on the AEC task. This framework enables a shared encoder-decoder model to learn text, pinyin (phoneme 1 ) and audio information simultaneously, which is trained by three subtasks: text correction, pinyin to text and ASR. On this basis, we introduce contrastive learning loss to shrink the distance between the three modalities and construct a unified representation. Experiments 2 on four AEC datasets show that our method effectively corrects a large number of ASR errors to state-of-the-art levels.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Long-range Brain Graph Transformer

arXiv

引用

arXiv 2025年

作者： Yu, Shuo Jin, Shan Li, Ming Sarwar, Tabinda Xia, Feng School of Computer Science and Technology Dalian University of Technology China Key Laboratory of Social Computing and Cognitive Intelligence Dalian University of Technology Ministry of Education China School of Software Dalian University of Technology China Zhejiang Institute of Optoelectronics China Zhejiang Key Laboratory of Intelligent Education Technology and Application Zhejiang Normal University China School of Computing Technologies RMIT University Australia

Understanding communication and information processing among brain regions of interest (ROIs) is highly dependent on long-range connectivity, which plays a crucial role in facilitating diverse functional neural integration across the entire brain. However, previous studies generally focused on the short-range dependencies within brain networks while neglecting the long-range dependencies, limiting an integrated understanding of brain-wide communication. To address this limitation, we propose Adaptive Long-range aware TransformER (ALTER), a brain graph transformer to capture long-range dependencies between brain ROIs utilizing biased random walk. Specifically, we present a novel long-range aware strategy to explicitly capture long-range dependencies between brain ROIs. By guiding the walker towards the next hop with higher correlation value, our strategy simulates the real-world brain-wide communication. Furthermore, by employing the transformer framework, ALERT adaptively integrates both short- and long-range dependencies between brain ROIs, enabling an integrated understanding of multilevel communication across the entire brain. Extensive experiments on ABIDE and ADNI datasets demonstrate that ALTER consistently outperforms generalized state-of-the-art graph learning methods (including SAN, Graphormer, GraphTrans, and LRGNN) and other graph learning based brain network analysis methods (including FBNETGEN, BrainNetGNN, BrainGNN, and BrainNETTF) in neurological disease diagnosis. Cases of long-range dependencies are also presented to further illustrate the effectiveness of ALTER. The implementation is available at https://***/yushuowiki/ALTER. Copyright © 2025, The Authors. All rights reserved.

关键词： Neurons

来源：评论

学校读者我要写书评

暂无评论

A Novel Approach with Fusion Edge Prediction Strategy for Table Structure Recognition

A Novel Approach with Fusion Edge Prediction Strategy for Ta...

引用

Information Systems and Computing technology (ISCTech), International Conference on

作者： Yingli Liu Guangtao Zhang Tao Shen Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming China Yunnan Key Laboratory of Computer Technologies Application Kunming University of Science and Technology Kunming China

Table, as an information carrier with high information density and direct display form, are widely used in scientific literature and social production documents. Accurately identifying tables from various documents will significantly promote the intelligent application of documents. The table’s structural information is crucial for comprehending how the text content in the table relates to one another, but teaching a computer to fully understand a table’s structure is still a very difficult undertaking. In this research work, we provided a unique edge-based method to recognize table structures. Specifically, we define the inter-cell relationships as an edge prediction problem and leverage graph convolutional networks to learn representations of the cells. These learned representations are then utilized to directly predict the connections between the cells. The experimental results conducted on three publicly available datasets for table structure recognition provide compelling evidence supporting the feasibility and usefulness of our presented methodology.

关键词：

来源：评论

学校读者我要写书评

暂无评论

: heterogeneous hypergraph attention network with counterfactual learning for multimodal sentiment analysis

引用

Complex & Intelligent Systems 2025年第4期11卷 1-16页

作者： Huang, Changqin Lin, Zhenheng Huang, Qionghao Huang, Xiaodi Jiang, Fan Chen, Jili Zhejiang Key Laboratory of Intelligent Education Technology and Application Zhejiang Normal University Jinhua China School of Education Zhejiang Normal University Jinhua China School of Computer Science and Technology Zhejiang Normal University Jinhua China School of Computing Mathematics and Engineering Charles Sturt University Albury Australia

Multimodal sentiment analysis (MSA) has garnered significant attention for its immense potential in human-computer interaction. While cross-modality attention mechanisms are widely used in MSA to capture inter-modality interactions, existing methods are limited to pairwise interactions between two modalities. Additionally, these methods can not utilize the causal relationship to guide attention learning, making them susceptible to bias information. To address these limitations, we introduce a novel method called Heterogeneous Hypergraph Attention Network with Counterfactual Learning $$(\text {H}^2\text {CAN}).$$ The method constructs a heterogeneous hypergraph based on sentiment expression characteristics and employs Heterogeneous Hypergraph Attention Networks (HHGAT) to capture interactions beyond pairwise constraints. Furthermore, it mitigates the effects of bias through a Counterfactual Intervention Task (CIT). Our model comprises two main branches: hypergraph fusion and counterfactual fusion. The former uses HHGAT to capture inter-modality interactions, while the latter constructs a counterfactual world using Gaussian distribution and additional weighting for the biased modality. The CIT leverages causal inference to maximize the prediction discrepancy between the two branches, guiding attention learning in the hypergraph fusion branch. We utilize unimodal labels to help the model adaptively identify the biased modality, thereby enhancing the handling of bias information. Experiments on three mainstream datasets demonstrate that $$\text {H}^2\text {CAN}$$ sets a new benchmark.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Independent Pitch Controller based on Fuzzy Adaptive Tuning PI for Load Mitigation of Large Land Wind Turbine 2

Independent Pitch Controller based on Fuzzy Adaptive Tuning ...

引用

2023 2nd International Conference on Energy Internet and Power Systems, ICEIPS 2023

作者： Li, Shengshan Du, Ming Li, Yanggui He, Jun Ma, Fuliang Chen, Qingyun Department of Computer Science Qinghai University Qinghai Xining China Geospatial and Natural Resources Big Data Center Qinghai Xining China Key Laboratory of Geospatial Information Technology and Application Qinghai Xining China College of Chemical Engineering Qinghai University Qinghai Xining China Qinghai Telecom Qinghai Xining China

With the development of wind power generation units towards the mega-scale, the blade root and tower have large load and vibration problems during the operation of wind turbines. In order to extend the operational life of wind turbines, a PI independent pitch control (IPC) strategy with fuzzy adaptive tuning (FAT) is introduced based on the existing wind turbine model and control strategy to achieve optimal control of wind turbine loads. Simulations are carried out by the FAST software of the US Renewable Energy laboratory to compare the independent pitch and the cooperative pitch. The results show that IPC reduces the load on the blade roots and improves the quality of the electrical energy. © 2023 Published under licence by IOP Publishing Ltd.

关键词： Wind turbines

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：