检索结果-内蒙古大学图书馆

IEEE International Conference on Systems, Man and Cybernetics

作者： Zhuolin Tan Anyong Qin Yongqing Sun Yuan Yan Tang School of Communications and Information Engineering Chongqing University of Posts and Telecommunications Chongqing China Chongqing Key Laboratory of Signal and Information Processing Chongqing China NTT Media Intelligence Laboratories Yokosuka Japan Zhuhai UM Science & Technology Research Institute University of Macau Macau China

ISBN: (纸本)9781665442084

Deep semi-nonnegative matrix factorization can obtain the hidden hierarchical representations according to the unknown attributes of the given data. On the other hand, the inherent structure of the each data cluster can be described by the distribution of the intra-class data. Then one hopes to learn a new low dimensional representation which can preserve the intrinsic structure embedded in the original high dimensional data space perfectly. Here we propose a novel distribution preserving deep semi-nonnegative matrix factorization method (DPNMF) to achieve this goal. As a result, the manifold structures in the raw data are well preserved in the feature space being from the top layer. The experimental results on the real-world datasets show that the proposed algorithm has good performance in terms of cluster accuracy and normalized mutual information (NMI).

关键词： Manifolds Conferences Clustering algorithms Approximation algorithms Mutual information Cybernetics

来源：评论

学校读者我要写书评

暂无评论

Uncertainty estimation by boosting with Gaussian process for expensive optimization problems

引用

Applied Soft Computing 2025年 180卷

作者： Zou, Hanhua Zeng, Sanyou Li, Changhe Jiao, Ruwang Zhao, Fei School of Mechanical Engineering and Electronic Information China University of Geosciences Wuhan China School of Artificial Intelligence Anhui University of Science & Technology Hefei China School of Future Science and Engineering Soochow University Suzhou China National Key Laboratory of Blind Signal Processing Chengdu China

In surrogate-assisted evolutionary algorithms (SAEAs), uncertainty measures the confidence level of the predicted fitness and plays an important role in selecting candidate points for expensive evaluation, as evaluating those with a large degree of uncertainty can enhance the exploration ability of algorithms and significantly improve model reliability. Gaussian process (GP) gains great popularity with a predictive variance to estimate uncertainty. However, the performance of GP-assisted SAEAs is still limited with weakened predictions and underutilized uncertainty. In this paper, we propose a novel SAEA that leverages a boosting ensemble with GP as the base learner to enhance optimization performance. First, GP is leveraged to boost a weak learner that captures global trends, refining its prediction in guiding the search. Then, the uncertainty provided by GP is integrated into boosting ensemble model to estimate its overall ensemble uncertainty, enhancing the model reliability and promoting the exploration capabilities. Moreover, a mechanism study is performed through standardized residual and a distance-based metric to have deep insights into search behaviors, demonstrating that the migrated uncertainty basically covers the statistical boundary of Gaussian distribution and contributes to exploitation and exploration trade-off. Experimental results across multiple benchmark problems and an antenna design problem demonstrate that the proposed method significantly enhanced GP-assisted SAEAs in statistical results of the best fitness value and convergence profile without increasing too much running time, particularly in high-dimensional problems. © 2025 Elsevier B.V.

关键词： Gaussian distribution

来源：评论

学校读者我要写书评

暂无评论

Semantic knowledge transfer for semi-supervised medical image segmentation

引用

Engineering Applications of Artificial intelligence 2025年 158卷

作者： Shiwei Zhou Haifeng Zhao Leilei Ma Dengdi Sun Key Laboratory of Intelligent Computing & Signal Processing (ICSP) Ministry of Education Anhui University Hefei 230601 China Anhui Provincial Key Laboratory of Multimodal Cognitive Computation Anhui University Hefei 230601 China School of Computer Science and Technology Anhui University Hefei 230601 China School of Artificial Intelligence Anhui University Hefei 230601 China Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei 230026 China

In semi-supervised medical image segmentation, due to possible differences in information content and distribution between labeled and unlabeled data, dealing with the two separately usually prevents knowledge transfer from labeled to unlabeled data. This prevents the model from effectively sharing learned information between the two types of data. To alleviate this problem, we train labeled and unlabeled data as a whole. Semantic mixing of labeled and unlabeled data is achieved by selecting and exchanging some of the region images of both through a mask to generate complementary input views. In addition, due to the limited labeled data, the unlabeled data has a weak ability to distinguish categories in the feature space. Traditional methods rely on pixel positions to generate positive and negative samples for contrastive learning to solve this problem, but relying on pixel position sampling can easily lead to semantic inconsistency, which affects the effect of feature learning; therefore, to address this problem, we propose an innovative labeled data-guided inter-class contrastive learning strategy, which extracts the category features from labeled and unlabeled data and exploits the accurate category information in the labeled data to guide contrastive learning, while introducing a similarity-based ranking weighting mechanism. Combining the two designs, we propose a new semantic knowledge transfer framework for semi-supervised medical image segmentation. Experiments demonstrate a significant improvement in our model compared to State of the Art (SOTA) on the Automatic Cardiac Diagnosis Challenge (ACDC) dataset and the Left Atrium (LA) dataset.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Reliable Multi-Modal Object Re-Identification via Modality-Aware Graph Reasoning

arXiv

引用

arXiv 2025年

作者： Wan, Xixi Zheng, Aihua Wang, Zi Jiang, Bo Tang, Jin Ma, Jixin Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui Provincial Key Laboratory of Security Artificial Intelligence School of Artificial Intelligence Anhui University Hefei230601 China School of Biomedical Engineering Anhui Medical University Key Laboratory of Intelligent Computing & Signal Processing Ministry of Education Anhui University Hefei China Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University Hefei230601 China School of Computing and Mathematical Sciences University of Greenwich LondonSE10 9LS United Kingdom

Multi-modal data provides abundant and diverse object information, crucial for effective modal interactions in Re-Identification (ReID) tasks. However, existing approaches often overlook the quality variations in local features and fail to fully leverage the complementary information across modalities, particularly in the case of low-quality features. In this paper, we propose to address this issue by leveraging a novel graph reasoning model, termed the Modality-aware Graph Reasoning Network (MGRNet). Specifically, we first construct modality-aware graphs to enhance the extraction of fine-grained local details by effectively capturing and modeling the relationships between patches. Subsequently, the selective graph nodes swap operation is employed to alleviate the adverse effects of low-quality local features by considering both local and global information, enhancing the representation of discriminative information. Finally, the swapped modality-aware graphs are fed into the local-aware graph reasoning module, which propagates multimodal information to yield a reliable feature representation. Another advantage of the proposed graph reasoning approach is its ability to reconstruct missing modal information by exploiting inherent structural relationships, thereby minimizing disparities between different modalities. Experimental results on four benchmarks (RGBNT201, Market1501-MM, RGBNT100, MSVR310) indicate that the proposed method achieves state-of-the-art performance in multi-modal object ReID. The code for our method will be available upon acceptance. Copyright © 2025, The Authors. All rights reserved.

关键词： Modal analysis

来源：评论

学校读者我要写书评

暂无评论

Evidence sentence extraction for reading comprehension based on multi-module 19

Evidence sentence extraction for reading comprehension based...

引用

19th Chinese National Conference on computational Linguistic, CCL 2020

作者： Ji, Yu Wang, Xiaoyue Li, Ru Guo, Shaoru Guan, Yong School of Computer and Information Technology Shanxi University China Key Laboratory of Computational Intelligence Chinese Information Processing of Ministry of Education Shanxi University Taiyuan China

As a key task of natural language understanding, machine reading comprehension has been widely concerned by scholars at domestic and foreign. In order to solve the problem of multiple choice reading comprehension, which is difficult to extract evidence sentences due to the absence of clue annotation and questions involve multi-hop reasoning, we proposes a model of evidence sentence extraction based on multi-module combination. Firstly,we use some labeled data to fine-tune the pre-training model;secondly, the evidence sentences in the multi-hop reasoning problem are extracted recursively through TF-IDF;finally, the unsupervised method is combined to further filter the model prediction results to reduce redundancy. This paper is verified on the Chinese Gaokao and the RACE data set. In the extraction of evidence sentences, compared with the optimal baseline model, the F1 value of the method in this paper is increased by 3.44%. The accuracy of using evidence sentences as model input in downstream answer tasks is 3.68% and 3.6% respectively higher than that of full text input. The above results confirm the effectiveness of the proposed method. © 2020 China National Conference on computational Linguistics Published under Creative Commons Attribution 4.0 International License

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Fuzzy decision implications: interpretation within fuzzy decision context

引用

CAAI Transactions on intelligence Technology 2019年第4期4卷 231-236页

作者： Jing Zhang Yanhui Zhai Deyu Li School of Foreign Language Shanxi UniversityTaiyuan 030006ShanxiPeople’s Republic of China Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education School of Computer and Information TechnologyShanxi UniversityTaiyuan 030006ShanxiPeople’s Republic of China

Fuzzy decision implication is an extension of decision implication in the fuzzy setting,serving to uncover the dependencies of fuzzy *** study presents the interpretation of fuzzy decision implication in the fuzzy decision ***,they will show that from fuzzy decision contexts one can obtain a closed fuzzy set of fuzzy decision implications,and the semantical characteristic of the obtained fuzzy set can be interpreted by fuzzy decision context and can be represented by some operators of fuzzy decision ***,starting from a fuzzy set of fuzzy decision implications,they can form a fuzzy decision context,from which the given fuzzy set can be *** result actually implies that they have constructed a correspondence between closed fuzzy sets of fuzzy decision implications and fuzzy decision contexts,and thus shows the equivalence of two interpretations of fuzzy decision implications.

关键词： Fuzzy operators implies

来源：评论

学校读者我要写书评

暂无评论

A Robust Matching Method for Optical and SAR Images Based on Coarse-to-Fine Mechanism

A Robust Matching Method for Optical and SAR Images Based on...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Cong Li Shuxuan Chen Kun Sun Yi Liang National Laboratory of Radar Signal Processing Xidian University Xi'an China National Key Laboratory of Science and Technology on Aerospace Intelligence Control Beijing Aerospace Automatic Control Institute Beijing China

ISBN: (数字)9781728163741

ISBN: (纸本)9781728163758

Although image matching techniques have been developed in the last decades, automatic optical-synthetic aperture radar (SAR) image matching is still a challenging task due to significant nonlinear intensity differences between such images. In this paper, a new method of coarse-to-fine heterogeneous image matching based on contour features is proposed. After images preprocessing, a Canny operator is used to extract open-loop contour features, and the angle feature of local feature points is used to complete coarse matching. Finally, constructing contour tree descriptors of coarse matching pairs, and calculating the contour distance is proposed to obtain the fine matching result. The experimental results show the effectiveness and robustness of this method.

关键词： Radar polarimetry Optical imaging Adaptive optics Feature extraction Optical reflection Nonlinear optics Optical filters

来源：评论

学校读者我要写书评

暂无评论

Deep learning detection of anomalous patterns from bus trajectories for traffic insight analysis

引用

Knowledge-Based Systems 2021年 217卷 106833-106833页

作者： Zhang, Xiaocai Zheng, Yi Zhao, Zhixun Liu, Yuansheng Blumenstein, Michael Li, Jinyan Advanced Analytics Institute Faculty of Engineering and IT University of Technology Sydney UltimoNSW 2007 Australia National Key Laboratory of Science and Technology on Blind Signal Processing ChengduSichuan610041 China College of Information Science and Engineering Hunan University ChangshaHunan410082 China Australian Artificial Intelligence Institute & Faculty of Engineering and IT University of Technology Sydney UltimoNSW 2007 Australia

Existing data-driven methods for traffic anomaly detection are modeled on taxi trajectory datasets. The concern is that the data may contain much inaccuracy about the actual traffic situations, because taxi drivers often choose optimal routes to evade from the congestions caused by traffic anomalies. We use bus trajectory data in this work. Bus trajectories can capture real traffic conditions in the road networks without drivers’ preference, which are more objective and appropriate for accurately detecting anomalous patterns for a broad range of insight analyses on traffics. We proposed a deep learning-based feature visualization method to map 3-dimensional features into a red–green–blue (RGB) color space. A color trajectory (CT) is then derived by encoding a trajectory with the RGB colors. With the spatial and temporal properties extracted from the CT, spatio-temporal outliers are detected by a novel offline detection method. We then conduct GIS map fusion to obtain insights for better understanding the traffic anomaly locations, and more importantly the influences on the road affected by the corresponding anomalies. Extended from the offline detection, an online detection method is developed for real-time detection of anomalous patterns. Our proposed methods were tested on 3 real-world bus trajectory datasets to demonstrate the performance of high accuracies, high detection rates and relatively low false alarm rates. © 2021

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

Multi-Party dual learning

arXiv

引用

arXiv 2021年

作者： Gong, Maoguo Gao, Yuan Xie, Yu Qin, A.K. Pan, Ke Ong, Yew-Soon The School of Electronic Engineering Key Laboratory of Intelligent Perception and Image Understanding Ministry of Education Xidian University Xi'an Shaanxi Province710071 China The Key Laboratory of Computational Intelligence and Chinese Information Processing Ministry of Education Shanxi University Taiyuan030006 China The Department of Computer Science and Software Engineering Swinburne University of Technology Melbourne Australia The School of Computer Science and Engineering Nanyang Technological University Singapore639798 Singapore

The performance of machine learning algorithms heavily relies on the availability of a large amount of training data. However, in reality, data usually reside in distributed parties such as different institutions and may not be directly gathered and integrated due to various data policy constraints. As a result, some parties may suffer from insufficient data available for training machine learning models. In this paper, we propose a multi-party dual learning (MPDL) framework to alleviate the problem of limited data with poor quality in an isolated party. Since the knowledge sharing processes for multiple parties always emerge in dual forms, we show that dual learning is naturally suitable to handle the challenge of missing data, and explicitly exploits the probabilistic correlation and structural relationship between dual tasks to regularize the training process. We introduce a feature-oriented differential privacy with mathematical proof, in order to avoid possible privacy leakage of raw features in the dual inference process. The approach requires minimal modifications to the existing multi-party learning structure, and each party can build flexible and powerful models separately, whose accuracy is no less than non-distributed self-learning approaches. The MPDL framework achieves significant improvement compared with state-of-the-art multi-party learning methods, as we demonstrated through simulations on real-world datasets. Copyright © 2021, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Demand estimation of water resources based on algorithm comparison

引用

International Journal of Wireless and Mobile Computing 2019年第2期16卷 110-116页

作者： Wang, Junyan Zhang, Jiangjiang Cai, Xingjuan Ma, Yanyan Jiangxi Province Key Laboratory of Water Information Cooperative Sensing and Intelligent Processing Nanchang Institute of Technology Nanchang330099 China Complex System and Computational Intelligence Laboratory TaiYuan University of Science and Technology Taiyuan003024 China Shanxi Cloud Era TISCO Information Automation Technology Co. Ltd. Taiyuan030003 China

Water is the source of life and the correct assessment of water resources is an important prerequisite for the rational utilisation of water resources. In this paper, water resources are evaluated and predicted by three different algorithms, including Bat Algorithm (BA), Particle Swarm Optimisation (PSO) and Pigeon-Inspired Optimisation (PIO). Comparing the errors of water resources assessed for the three algorithms, we select an algorithm of the minimum error to predict the future water demand. In the experiments, firstly, the water data from 2003 to 2012 are used to find the optimal weights of the models. Then, the weight factor is combined with the given model to gain the error between predicted value and the remaining data (2013–2015). Finally, the simulation results show that PIO algorithm has a better performance compared with the BA and PSO algorithms. Copyright © 2019 Inderscience Enterprises Ltd.

关键词： Water resources

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：