检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Zhang, Wenzhen Cheng, Debo Lu, Guangquan Zhou, Bo Li, Jiaye Zhang, Shichao School of Computer Science and Engineering Guangxi Normal University Guangxi Guilin541004 China Guangxi Key Lab of Multi-Source Information Mining & Security Guangxi Normal University Guangxi Guilin541004 China Key Lab of Education Blockchain and Intelligent Technology Ministry of Education Guangxi Normal University Guangxi Guilin541004 China UniSA STEM University of South Australia AdelaideSA5095 Australia Guangxi Collaborative Innovation Center of Modern Sericulture and Silk Hechi University Guangxi Hechi546300 China The State Key Laboratory of Blockchain and Data Security Zhejiang University Zhejiang Hangzhou310027 China

Deep neural networks are highly susceptible to overfitting noisy labels, which leads to degraded performance. Existing methods address this issue by employing manually defined criteria, aiming to achieve optimal partitioning in each iteration to avoid fitting noisy labels while thoroughly learning clean samples. However, this often results in overly complex and difficult-to-train models. To address this issue, we decouple the tasks of avoiding fitting incorrect labels and thoroughly learning clean samples and propose a simple yet highly applicable method called Adaptive Label Refinement (ALR). First, inspired by label refurbishment techniques, we update the original hard labels to soft labels using the model’s predictions to reduce the risk of fitting incorrect labels. Then, by introducing the entropy loss, we gradually ‘harden’ the high-confidence soft labels, guiding the model to better learn from clean samples. This approach is simple and efficient, requiring no prior knowledge of noise or auxiliary datasets, making it more accessible compared to Copyright © 2025, The Authors. All rights reserved.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Fusion of terahertz spectroscopy and Raman spectroscopy combined with support vector machine to distinguish different pericarpium citri reticulatae species

引用

Heliyon 2025年第6期11卷

作者： Yang, Qiyu Xia, Congzi Cui, Yuanwu Zhang, Xiaoqiuyan Zhang, Tianyu Huang, Yong Liu, Diwei Wei, Yanyu Gong, Yubin Fang, Guangyou Wang, Zhenyou Chen, Xuequan Hu, Min Terahertz Center School of Electronic Science and Engineering University of Electronic Science and Technology Sichuan 611731 China Key Laboratory of Terahertz Technology Ministry of Education Sichuan 611731 China Institute of Big Data for Vocational Education Guangdong Polytechnic of Science and Technology Zhuhai 519000 China GBA Branch of Aerospace Information Research Institute Chinese Academy of Sciences Guangzhou 510700 China Guangdong Provincial Key Laboratory of Terahertz Quantum Electromagnetics Guangzhou 510700 China Shenzhen Authentic Traditional Chinese Medicine Treatment Hospital Shenzhen 518100 China

Pericarpium citri reticulatae (PCR), or Chenpi, is a valuable medicinal and food resource in China, but its classification can be challenging due to variations in medicinal value and market price. Traditional methods for identifying PCR involve subjective sensory analysis or cumbersome chemical techniques. This paper explores a new approach by combining terahertz and Raman spectral data with machine learning to classify seven PCR species of different ages, origins, and artificial skins. We used K-nearest neighbor (KNN), convolutional neural networks (CNN), and support vector machines (SVM) for model selection. The best model achieved 96.8 % accuracy and high AUC metrics. An innovative Manhattan data preprocessing method improved model performance by addressing errors due to instrumental and environmental factors. The T-distributed stochastic neighbor embedding (t-SNE) algorithm visualized data connections, and recursive feature elimination identified key frequencies. The THz band achieved 94.1 % accuracy using just 5.4 % of the original data, and the Raman band reached 77.8 % accuracy with 10 feature frequencies. This study demonstrates the effectiveness of spectral fusion and machine learning for precise PCR classification, offering valuable applications for traditional Chinese medicine and the food industry. © 2025

关键词： Manhattan distance Pericarpium citri reticulatae Raman spectroscopy Support vector machine Terahertz frequency domain spectroscopy

来源：评论

学校读者我要写书评

暂无评论

Representation learning: serial-autoencoder for personalized recommendation

引用

Frontiers of Computer Science 2024年第4期18卷 61-72页

作者： Yi ZHU Yishuai GENG Yun LI Jipeng QIANG Xindong WU School of Information Engineering Yangzhou UniversityYangzhou 225127China Key Laboratory of Knowledge Engineering with Big Data(Ministry of Education of the People’s Republic of China) Hefei University of TechnologyHefei 230009China School of Computer Science and Information Engineering Hefei University of TechnologyHefei 230009China

Nowadays,the personalized recommendation has become a research hotspot for addressing information *** this,generating effective recommendations from sparse data remains a ***,auxiliary information has been widely used to address data sparsity,but most models using auxiliary information are linear and have limited *** to the advantages of feature extraction and no-label requirements,autoencoder-based methods have become quite ***,most existing autoencoder-based methods discard the reconstruction of auxiliary information,which poses huge challenges for better representation learning and model *** address these problems,we propose Serial-Autoencoder for Personalized Recommendation(SAPR),which aims to reduce the loss of critical information and enhance the learning of feature ***,we first combine the original rating matrix and item attribute features and feed them into the first autoencoder for generating a higher-level representation of the ***,we use a second autoencoder to enhance the reconstruction of the data representation of the prediciton rating *** output rating information is used for recommendation *** experiments on the MovieTweetings and MovieLens datasets have verified the effectiveness of SAPR compared to state-of-the-art models.

关键词： personalized recommendation autoencoder representation learning collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

FortisAVQA and MAVEN: a Benchmark dataset and Debiasing Framework for Robust Multimodal Reasoning

arXiv

引用

arXiv 2025年

作者： Ma, Jie Gao, Zhitao Chai, Qi Liu, Jun Wang, Pinghui Tao, Jing Su, Zhou Ministry of Education of Key Laboratory for Intelligent Networks and Network Security School of Cyber Science and Engineering Xi’an Jiaotong University Shaanxi Xi’an710049 China Shannxi Provincial Key Laboratory of Big Data Knowledge Engineering School of Computer Science and Technology Xi’an Jiaotong University Shaanxi Xi’an710049 China Guangdong Guangzhou510000 China

Audio-Visual Question Answering (AVQA) is a challenging multimodal reasoning task requiring intelligent systems to answer natural language queries based on paired audio-video inputs accurately. However, existing AVQA approaches often suffer from overfitting to dataset biases, leading to poor robustness. Moreover, current datasets may not effectively diagnose these methods. To address these challenges, we first introduce a novel dataset, FortisAVQA, constructed in two stages: (1) rephrasing questions in the test split of the public MUSIC-AVQA dataset and (2) introducing distribution shifts across questions. The first stage expands the test space with greater diversity, while the second enables a refined robustness evaluation across rare, frequent, and overall question distributions. Second, we introduce a robust Multimodal Audio-Visual Epistemic Network (MAVEN) that leverages a multifaceted cycle collaborative debiasing strategy to mitigate bias learning. Experimental results demonstrate that our architecture achieves state-of-the-art performance on FortisAVQA, with a notable improvement of 7.81%. Extensive ablation studies on both datasets validate the effectiveness of our debiasing components. Additionally, our evaluation reveals the limited robustness of existing multimodal QA methods. We also verify the plug-and-play capability of our strategy by integrating it with various baseline models across both datasets. Our dataset and code are available at https://***/reml-group/fortisavqa. Copyright © 2025, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Adaptive Perception for Unified Visual Multi-modal Object Tracking

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年

作者： Hu, Xiantao Zhong, Bineng Liang, Qihua Shi, Liangtao Mo, Zhiyi Tai, Ying Yang, Jian Guangxi Normal University Guangxi Key Lab of Multi-Source Information Mining Guilin541004 China Guangxi Normal University Security Guilin541004 China Guangxi Normal University Intelligent Technology Guilin541004 China Guangxi Normal University Ministry of Education Guilin541004 China Wuzhou University School of Data Science Wuzhou543002 China Wuzhou University Software Engineering Wuzhou543002 China Nanjing University State Key Laboratory for Novel Software Technology Suzhou215163 China Nanjing University of Science and Technology School of Computer Science Nanjing210094 China Nanjing University of Science and Technology Engineering Nanjing210094 China

Recently, many multi-modal trackers prioritize RGB as the dominant modality, treating other modalities as auxiliary, and fine-tuning separately various multi-modal tasks. This imbalance in modality dependence limits the ability of methods to dynamically utilize complementary information from each modality in complex scenarios, making it challenging to fully perceive the advantages of multi-modal. As a result, a unified parameter model often underperforms in various multi-modal tracking tasks. To address this issue, we propose APTrack, a novel unified tracker designed for multi-modal adaptive perception. Unlike previous methods, APTrack explores a unified representation through an equal modeling strategy. This strategy allows the model to dynamically adapt to various modalities and tasks without requiring additional fine-tuning between different tasks. Moreover, our tracker integrates an adaptive modality interaction (AMI) module that efficiently bridges cross-modality interactions by generating learnable tokens. Experiments conducted on five diverse multi-modal datasets (RGBT234, LasHeR, VisEvent, DepthTrack, and VOT-RGBD2022) demonstrate that APTrack not only surpasses existing state-of-the-art unified multi-modal trackers but also outperforms trackers designed for specific multi-modal tasks. © 2020 IEEE.

关键词： Multicarrier modulation

来源：评论

学校读者我要写书评

暂无评论

Joint extraction method for entity relations from mineral resources reports integrating dependency parsing and improved graph convolutional networks

引用

Ore Geology Reviews 2025年 182卷

作者： Qiu, Qinjun Jin, Xiangguo Tian, Miao Wu, Qirui Tao, Liufeng Chen, Jianguo Xie, Zhong Technology Innovation Center for Geological Data Intelligent Application Department of Natural Resources of Jiangsu Province 210012 China School of Computer and Science China University of Geosciences Hubei Wuhan430074 China National Engineering Research Center for Geographic Information System Hubei Wuhan430074 China Key Laboratory of Geological Survery and Evaluation of Ministry of Education Hubei Wuhan430074 China School of Future Technology China University of Geosciences Hubei Wuhan430074 China Wuhan University Hubei Wuhan430074 China

Geological reports, as crucial technical documents reflecting the outcomes of geological survey work, encapsulate extensive expert and domain knowledge. Geological knowledge graphs integrate vast amounts of data, facilitating efficient and rapid extraction of knowledge embedded within geoscientific data. The extraction of geological entity relations is a key method in creating these knowledge graphs. Existing techniques for extracting geological entities and their relations encounter difficulties such entity overlap, relation overlap, and the challenge of obtaining deep semantic information because of the vastness and complexity of geological data. Our study suggests a collaborative extraction model for entity relations that integrates dependency syntactic relations with a graph convolutional network (GCN) in order to address these problems. This model learns dependency syntactic structures and deep semantic information by building a GCN that includes dependency syntactic relations. A pointer network decoder is then added to increase entity relation extraction efficiency. Dependencies between words in a phrase, such as subject-verb and verb-object relations, are revealed via dependency syntactic analysis. By structuring these dependencies into a graph, the model captures syntactic structural information. Through operations involving adjacency matrices and feature matrices, the model effectively propagates and aggregates node information, thereby capturing the global dependency syntactic structure and deep semantic information of sentences. The integration of dependency syntactic relations with GCN processing enables the model to more accurately comprehend entity relations within sentences. Results from experiments show that this model successfully tackles problems like overlapping entity relations and the challenge of gleaning deep semantic information from geological texts. It achieves a 79.73% accuracy rate and a 77.98% F1 score on geological text datasets. © 2025

关键词： Geochemical surveys

来源：评论

学校读者我要写书评

暂无评论

Lightweight axiom pinpointing via replicated driver and customized SAT-solving

引用

Frontiers of Computer Science 2023年第2期17卷 121-133页

作者： Dantong OUYANG Mengting LIAO Yuxin YE College of Computer Science and Technology Jilin UniversityChangchun 130012China Key Laboratory of Symbolic Computation and Knowledge Engineering(Jilin University) Ministry of EducationChangchun 130012China

In description logic,axiom pinpointing is used to explore defects in ontologies and identify hidden justifications for a logical *** recent years,SAT-based axiom pinpointing techniques,which rely on the enumeration of minimal unsatisfiable subsets(MUSes)of pinpointing formulas,have gained increasing *** with traditional Tableau-based reasoning approaches,SAT-based techniques are more competitive when computing justifications for consequences in large-scale lightweight description logic *** this article,we propose a novel enumeration justification algorithm,working with a replicated *** replicated driver discovers new justifications from the explored justifications through cheap literals resolution,which avoids frequent calls of SAT ***,when the use of SAT solver is inevitable,we adjust the strategies and heuristic parameters of the built-in SAT solver of axiom pinpointing *** adjusted SAT solver is able to improve the checking efficiency of unexplored *** proposed method is implemented as a tool named *** experimental results show that RDMinA outperforms the existing axiom pinpointing tools on practical biomedical ontologies such as Gene,Galen,NCI and Snomed-CT.

关键词： axiom pinpointing description logic SAT solver

来源：评论

学校读者我要写书评

暂无评论

RDF partitioning for scalable SPARQL query processing

引用

Frontiers of Computer Science 2015年第6期9卷 919-933页

作者： Xiaoyan WANG Tao YANG Jinchuan CHEN Long HE Xiaoyong DU School of Information Renmin University of China Beijing 100872 China Key Laboratory of Data Engineering and Knowledge Engineering of Ministry of Education Renmin University Beijing 100872 China Information Center Supreme People's Court Beijing 100745 China State Key Laboratory of Software Development Environment Beihang University Beijing 100191 China

The volume of RDF data increases dramatically within recent years, while cloud computing platforms like Hadoop are supposed to be a good choice for processing queries over huge data sets for their wonderful scalability. Previous work on evaluating SPARQL queries with Hadoop mainly focus on reducing the number of joins through careful split of HDFS files and algorithms for generating Map/Reduce jobs. However, the way of partitioning RDF data could also affect system performance. Specifically, a good partitioning solution would greatly reduce or even to- tally avoid cross-node joins, and significantly cut down the cost in query evaluation. Based on HadoopDB, this work processes SPARQL queries in a hybrid architecture, where Map/Reduce takes charge of the computing tasks, and RDF query engines like RDF-3X store the data and execute join operations. According to the analysis of query workloads, this work proposes a novel algorithm for automatically parti- tioning RDF data and an approximate solution to physically place the partitions in order to reduce data redundancy. It also discusses how to make a good trade-off between query evaluation efficiency and data redundancy. All of these pro- posed approaches have been evaluated by extensive experiments over large RDF data sets.

关键词： RDF data data partitioning SPARQL query

来源：评论

学校读者我要写书评

暂无评论

Tuning the Learning Rate for Stochastic Variational Inference

引用

Journal of Computer Science & Technology 2016年第2期31卷 428-436页

作者： Xi-Ming Li Ji-Hong Ouyang College of Computer Science and Technology Jilin University Changchun 130000 China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun 130000 China

Stochastic variational inference （SVI） can learn topic models with very big corpora. It optimizes the variational objective by using the stochastic natural gradient algorithm with a decreasing learning rate. This rate is crucial for SVI; however, it is often tuned by hand in real applications. To address this, we develop a novel algorithm, which tunes the learning rate of each iteration adaptively. The proposed algorithm uses the Kullback-Leibler （KL） divergence to measure the similarity between the variational distribution with noisy update and that with batch update, and then optimizes the learning rates by minimizing the KL divergence. We apply our algorithm to two representative topic models： latent Dirichlet allocation and hierarchical Dirichlet process. Experimental results indicate that our algorithm performs better and converges faster than commonly used learning rates.

关键词： stochastic variational inference online learning adaptive learning rate topic model

来源：评论

学校读者我要写书评

暂无评论

Simultaneous Prediction for Multiple key Performance Indicators in Semiconductor Wafer Fabrication

引用

Chinese Journal of Electronics 2016年第6期25卷 1159-1165页

作者： CAO Zhengcai LIU Xuelian HAO Jinghua LIU Min College of Information Science and Technology Beijing University of Chemical Technology Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Department of Automation Tsinghua University

The prediction and key factors identification for lot Cycle time(CT) and Equipment utilization(EU) which remain the key performance indicators(KPI)are vital for multi-objective optimization in semiconductor manufacturing industry. This paper proposes a prediction methodology which predicts CT and EU simultaneously and identifies their key factors. Bayesian neural network(BNN) is used to establish the simultaneous prediction model for Multiple key performance indicators(MKPI),and Bayes theorem is key solution in model complexity controlling. The closed-loop structure is built to keep the stability of MKPI prediction model and the weight analysis method is the basis of identifying the key factors for CT and EU. Compared with Artificial neural network(ANN)and Selective naive Bayesian classifier(SNBC), the simulation results of the prediction method of BNN are proved to be more feasible and effective. The prediction accuracy of BNN has been obviously improved than ANN and SNBC.

关键词： Prediction for MKPI Cycle time Equipment utilization BNN key factors identification

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：