检索结果-内蒙古大学图书馆

Joint Sample Position Based Noise Filtering and Mean Shift Clustering for Imbalanced Classification Learning

Tsinghua science and technology 2024年第1期29卷 216-231页

作者： Lilong Duan Wei Xue Jun Huang Xiao Zheng School of Computer Science and Technology Anhui University of TechnologyMaanshan 243032China Institute of Artificial Intelligence Hefei Comprehensive National Science CenterHefei 230088China

The problem of imbalanced data classification learning has received much *** classification algorithms are susceptible to data skew to favor majority samples and ignore minority *** weighted minority oversampling technique(MWMOTE)is an effective approach to solve this problem,however,it may suffer from the shortcomings of inadequate noise filtering and synthesizing the same samples as the original minority *** this end,we propose an improved MWMOTE method named joint sample position based noise filtering and mean shift clustering(SPMSC)to solve these ***,in order to effectively eliminate the effect of noisy samples,SPMsC uses a new noise filtering mechanism to determine whether a minority sample is noisy or not based on its position and distribution relative to the majority *** that MWMOTE may generate duplicate samples,we then employ the mean shift algorithm to cluster minority samples to reduce synthetic replicate ***,data cleaning is performed on the processed data to further eliminate class *** on extensive benchmark datasets demonstrate the effectiveness of SPMsC compared with other sampling methods.

关键词： imbalanced data classification oversampling noise filtering clustering

来源：评论

学校读者我要写书评

暂无评论

Synthesis and hydrogen desorption kinetics of Mg_(2)FeH_(6)-and Mg_(2)CoH_(5)-based composites with in situ formed YH_(3)and Mg_(2)NiH_4 nanoparticles

引用

Rare Metals 2023年第7期42卷 2335-2343页

作者： Can Li Zhi-Wen Wu Qing-An Zhang School of Materials Science and Engineering Anhui University of TechnologyMaanshan243002China

Mg_(2)FeH_(6)-and Mg_(2)CoH_(5)-based composites with in situ formed YH_(3)and Mg_(2)NiH_4 nanoparticles were synthesized by ball milling of Mg_(10)YNi+4Fe(in mole ratio)and Mg_(10)YNi+4Co powders,respectively,at4 MPa H_(2)followed by hydrogenation at 673 K for 60 h under a hydrogen pressure of 7 *** is found that the nanocrystalline YH_(3)and Mg_(2)NiH_4 particles are indeed embedded in Mg_(2)FeH_(6)and Mg_(2)CoH_(5)*** hydrogen desorption rates of Mg_(2)FeH_(6)-and Mg_(2)CoH_(5)-based composites are enhanced compared to those undoped Mg_(2)FeH_(6)and Mg_(2)CoH_(5)hydrides,respectively,due to the synergetic catalysis of nanosized YH_(3)and Mg_(2)NiH_4 *** finding provides us with an efficient and simple approach for the improvement in hydrogen desorption kinetics of Mg-based hydrogen storage materials.

关键词： Hydrogen storage Mg-based hydride Kinetics Catalytic effect

来源：评论

学校读者我要写书评

暂无评论

Weakly-supervised instance co-segmentation via tensor-based salient co-peak search

引用

Frontiers of computer science 2024年第2期18卷 83-92页

作者： Wuxiu QUAN Yu HU Tingting DAN Junyu LI Yue ZHANG Hongmin CAI School of Computer Science Guangdong Polytechnic Normal UniversityGuangzhou 510665China School of Computer Science and Engineering South China University of TechnologyGuangzhou 510006China

Instance co-segmentation aims to segment the co-occurrent instances among two *** task heavily relies on instance-related cues provided by co-peaks,which are generally estimated by exhaustively exploiting all paired candidates in point-to-point ***,such patterns could yield a high number of false-positive co-peaks,resulting in over-segmentation whenever there are mutual *** tackle with this issue,this paper proposes an instance co-segmentation method via tensor-based salient co-peak search(TSCPS-ICS).The proposed method explores high-order correlations via triple-to-triple matching among feature maps to find reliable co-peaks with the help of co-saliency *** proposed method is shown to capture more accurate intra-peaks and inter-peaks among feature maps,reducing the false-positive rate of co-peak *** having accurate co-peaks,one can efficiently infer responses of the targeted *** on four benchmark datasets validate the superior performance of the proposed method.

关键词： weakly-supervised co-segmentation co-peak tensormatching deep network instance segmentation

来源：评论

学校读者我要写书评

暂无评论

OCRBench: on the hidden mystery of OCR in large multimodal models

引用

science China(Information sciences) 2024年第12期67卷 23-35页

作者： Yuliang LIU Zhang LI Mingxin HUANG Biao YANG Wenwen YU Chunyuan LI Xu-Cheng YIN Cheng-Lin LIU Lianwen JIN Xiang BAI School of Artificial Intelligence and Automation Huazhong University of Science and Technology School of Electronic and Information Engineering South China University of Technology Microsoft Research School of Computer & Communication Engineering University of Science and Technology Beijing Institute of Automation Chinese Academy of Sciences School of Software Engineering Huazhong University of Science and Technology

Large models have recently played a dominant role in natural language processing and multimodal vision-language learning. However, their effectiveness in text-related visual tasks remains relatively unexplored. In this paper, we conducted a comprehensive evaluation of large multimodal models, such as GPT4V and Gemini, in various text-related visual tasks including text recognition, scene text-centric visual question answering(VQA), document-oriented VQA, key information extraction(KIE), and handwritten mathematical expression recognition(HMER). To facilitate the assessment of optical character recognition(OCR) capabilities in large multimodal models, we propose OCRBench, a comprehensive evaluation benchmark. OCRBench contains 29 datasets, making it the most comprehensive OCR evaluation benchmark available. Furthermore, our study reveals both the strengths and weaknesses of these models, particularly in handling multilingual text, handwritten text, non-semantic text, and mathematical expression *** importantly, the baseline results presented in this study could provide a foundational framework for the conception and assessment of innovative strategies targeted at enhancing zero-shot multimodal *** evaluation pipeline and benchmark are available at https://***/Yuliang-Liu/Multimodal OCR.

关键词： large multimodal model OCR text recognition scene text-centric VQA document-oriented VQA key information extraction handwritten mathematical expression recognition

来源：评论

学校读者我要写书评

暂无评论

YC_(x)F_(y)nanosheets-supported Ni nanoparticles as a high-efficient catalyst for hydrogen desorption of MgH_(2)

引用

Nano Research 2023年第8期16卷 10938-10945页

作者： Cong Peng Qingan Zhang School of Materials Science and Engineering Anhui University of TechnologyMaanshan 243002China

Magnesium hydride(MgH_(2))has been considered as a promising hydrogen storage material,but the pressing issues including sluggish kinetics and poor cyclic stability hampered its practical ***,a high-efficient catalyst comprising of YC_(x)F_(y)nanosheets-supported Ni nanoparticles(Ni_(30)/YC_(x)F_(y))was designed and constructed aiming to resolve the abovementioned restrictions facing MgH_(2).After hybridizing with Ni_(30)/YC_(x)F_(y),the as-achieved MgH_(2)–10 wt.%Ni_(30)/YC_(x)F_(y)composite exhibits superior hydrogen desorption kinetics with an activation energy of 80.9 kJ·mol^(−1)and a high capacity retention of 97.6%after 50 *** is confirmed that the in situ formed Mg_(2)NiH_(4)and YH3 catalytic phases accelerate the hydrogen desorption kinetics,while the dispersed MgF_(2)and carbon species prevent the crystallite growth,particle aggregation,and catalyst redispersion,contributing an excellent cyclic *** work provides a new strategy to synthesize efficient catalysts for hydrogen desorption of MgH_(2).

关键词： hydrogen storage magnesium hydride catalyst kinetics cyclic stability

来源：评论

学校读者我要写书评

暂无评论

AsyCo: an asymmetric dual-task co-training model for partial-label learning

引用

science China(Information sciences) 2025年第5期68卷 332-347页

作者： Beibei LI Yiyuan ZHENG Beihong JIN Tao XIANG Haobo WANG Lei FENG College of Computer Science Chongqing University State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences University of Chinese Academy of Sciences School of Software Technology Zhejiang University School of Computer Science and Engineering Nanyang Technological University

Partial-label learning(PLL) is a typical problem of weakly supervised learning, where each training instance is annotated with a set of candidate labels. Self-training PLL models achieve state-of-the-art performance but suffer from error accumulation problems caused by mistakenly disambiguated instances. Although co-training can alleviate this issue by training two networks simultaneously and allowing them to interact with each other, most existing co-training methods train two structurally identical networks with the same task, i.e., are symmetric, rendering it insufficient for them to correct each other due to their similar limitations. Therefore, in this paper, we propose an asymmetric dual-task co-training PLL model called AsyCo,which forces its two networks, i.e., a disambiguation network and an auxiliary network, to learn from different views explicitly by optimizing distinct tasks. Specifically, the disambiguation network is trained with a self-training PLL task to learn label confidence, while the auxiliary network is trained in a supervised learning paradigm to learn from the noisy pairwise similarity labels that are constructed according to the learned label confidence. Finally, the error accumulation problem is mitigated via information distillation and confidence refinement. Extensive experiments on both uniform and instance-dependent partially labeled datasets demonstrate the effectiveness of AsyCo.

关键词： machine learning weakly supervised learning partial-label learning co-training models candidate label sets

来源：评论

学校读者我要写书评

暂无评论

Streaming Histogram Publication over Weighted Sliding Windows Under Differential Privacy

引用

Tsinghua science and technology 2024年第6期29卷 1674-1693页

作者： Xiujun Wang Lei Mo Xiao Zheng Zhe Dang School of Computer Science and Technology Anhui University of TechnologyMa’anshan 243032China Institute for Artificial Intelligence Hefei Comprehensive National Science CenterHefei 230088China Baosight Software(Anhui)Co.Ltd. Ma’anshan 243000China School of Electrical Engineering and Computer Science Washington State UniversityPullman 99164WAUSA

Continuously publishing histograms in data streams is crucial to many real-time applications,as it provides not only critical statistical information,but also reduces privacy leaking *** the importance of elements usually decreases over time in data streams,in this paper we model a data stream by a sequence of weighted sliding windows,and then study how to publish histograms over these windows *** existing literature can hardly solve this problem in a real-time way,because they need to buffer all elements in each sliding window,resulting in high computational overhead and prohibitive storage *** this paper,we overcome this drawback by proposing an online algorithm denoted by Efficient Streaming Histogram Publishing(ESHP)to continuously publish histograms over weighted sliding ***,our method first creates a novel sketching structure,called Approximate-Estimate Sketch(AESketch),to maintain the counting information of each histogram interval at every time instance;then,it creates histograms that satisfy the differential privacy requirement by smartly adding appropriate noise values into the sketching *** experimental results and rigorous theoretical analysis demonstrate that the ESHP method can offer equivalent data utility with significantly lower computational overhead and storage costs when compared to other existing methods.

关键词： differential privacy randomized algorithm streaming data publication weighted sliding window approximate statistics data usability computational complexity

来源：评论

学校读者我要写书评

暂无评论

Effect of Al(OH)_(3) prepared from fly ash on the structural and catalytic properties of g-C_(3)N_(4)-based materials

引用

Chinese Journal of Chemical engineering 2024年第10期74卷 44-51页

作者： Qingbo Yu Xianhua Li Qingping Wang The First Affiliated Hospital of Anhui University of Science and Technology(Huainan First People's Hospital) Anhui University of Science and TechnologyHuainan 232001China Anhui Industrial Generic Technology Research Center for New Materials from Coal-based Solid Wastes Huainan 232001China School of Materials Science and Engineering Anhui University of Science and TechnologyHuainan 232001China

In order to find the optimal combination method of secondary utilization of fly ash and graphite-phase carbon nitride(g-C_(3)N_(4))modification,an efficient composite photocatalyst of γ-Al_(2)O_(3)/g-C_(3)N_(4)was obtained by calcining the composite precursors of Al(OH)3/dicyandiamide(DCDA).The introduction of Al(OH)_(3)prepared by combining fly ash into the precursors causes hydrogen-bonding interactions between Al(OH)_(3)and DCDA,which facilitate the removal of N atoms from the edges of the CN framework of g-C_(3)N_(4)during condensation,and the composites prepared possess more cyano *** addition,γ-Al_(2)O_(3)and g-C_(3)N_(4)form a chemical bond at the interface,and this chemical bonding causes the density of the electron cloud in the vicinity of the N atoms to *** them,the strongest chemical bonding between Al_(2)O_(3)and g-C_(3)N_(4)was observed in ACN-1,whereas the most cyanine defects were formed in ACN-1,which made ACN-1 exhibit the best photocatalytic degradation of methylene blue,which is 2.48 times higher than that of the pristine g-C_(3)N_(4).

关键词： Precursors g-C_(3)N_(4) Waste treatment Catalyst Synthesis

来源：评论

学校读者我要写书评

暂无评论

When Software Security Meets Large Language Models:A Survey

引用

IEEE/CAA Journal of Automatica Sinica 2025年第2期12卷 317-334页

作者： Xiaogang Zhu Wei Zhou Qing-Long Han Wanlun Ma Sheng Wen Yang Xiang IEEE the School of Computer and Mathematical Sciences the University of Adelaide the School of Science Computing and Engineering Technologies Swinburne University of Technology

Software security poses substantial risks to our society because software has become part of our life. Numerous techniques have been proposed to resolve or mitigate the impact of software security issues. Among them, software testing and analysis are two of the critical methods, which significantly benefit from the advancements in deep learning technologies. Due to the successful use of deep learning in software security, recently,researchers have explored the potential of using large language models(LLMs) in this area. In this paper, we systematically review the results focusing on LLMs in software security. We analyze the topics of fuzzing, unit test, program repair, bug reproduction, data-driven bug detection, and bug triage. We deconstruct these techniques into several stages and analyze how LLMs can be used in the stages. We also discuss the future directions of using LLMs in software security, including the future directions for the existing use of LLMs and extensions from conventional deep learning research.

关键词： Large language models (LLMs) software analysis software security software testing

来源：评论

学校读者我要写书评

暂无评论

A Multi-Resolution Feature Fusion Method for Pedestrian Re-identification

IAENG International Journal of Computer Science

引用

IAENG International Journal of computer science 2024年第9期51卷 1393-1403页

作者： Qin, Haitian Xu, Yang Chen, Xupeng School of Computer Science and Software Engineering University of Science and Technology Liaoning Anshan114051 China School of Computer Science and Software Engineering University of Science and Technology Liaoning Anshan114051 China

Pedestrian re-identification technology enables accurate identification of individuals and is widely used in modern intelligent video surveillance systems to aid law enforcement, including criminal apprehension and locating missing persons. However, variations in lighting, background, resolution, and other imaging conditions captured by different cameras create significant challenges in pedestrian feature extraction, often leading to poor recognition accuracy. To overcome these challenges, this paper presents a Multi-resolution Feature Fusion (MRFF) method for pedestrian re-identification, based on the Pedestrian Re-identification Relational Network (RNFPR). This approach incorporates the Coordinate Attention (CA) module into the DenseNet161 network to enhance feature extraction capabilities. Improving the discriminative and recognition accuracy of features requires learning and fusing pedestrian features from multiple low-resolution images. This process enhances the expressive power of feature maps, ultimately improving pedestrian recognition performance. Additionally, this method introduces a multi-resolution feature fusion module that segments and integrates multi-resolution features from image data. This enables the model to effectively combine feature information from various resolution levels, resulting in a more comprehensive feature representation. Experimental results show that the MRFF method achieves a 1.3% increase in mean Average Precision (mAP) and a 1.0% improvement in Rank-1 accuracy on the Market1501 dataset. For the DukeMTMC-reID dataset, it provides a 0.2% increase in mAP and a 0.7% enhancement in Rank-1 accuracy. Consequently, the MRFF approach results in an overall mAP increase of 0.7% on the DukeMTMC-ReID dataset, significantly improving pedestrian gender re-identification accuracy. © (2024), (International Association of Engineers). All Rights Reserved.

关键词： Security systems

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：