检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Ding, Hu Huang, Ruomin Liu, Kai Yu, Haikuo Wang, Zixiu School of Computer Science and Technology University of Science and Technology of China Anhui China School of Data Science University of Science and Technology of China Anhui China

In this paper, we study the problem of k-center clustering with outliers. The problem has many important applications in real world, but the presence of outliers can significantly increase the computational complexity. Though a number of methods have been developed in the past decades, it is still quite challenging to design quality guaranteed algorithm with low complexity for this problem. Our idea is inspired by the greedy method, Gonzalez’s algorithm, that was developed for solving the ordinary k-center clustering problem. Based on some novel observations, we show that a simple randomized version of this greedy strategy actually can handle outliers efficiently. We further show that this randomized greedy approach also yields small coreset for the problem in doubling metrics (even if the doubling dimension is not given), which can greatly reduce the computational complexity. Moreover, together with the partial clustering framework proposed by Guha et al. (2019), we prove that our coreset method can be applied to distributed data with a low communication complexity. The experimental results suggest that our algorithms can achieve near optimal solutions and yield lower complexities comparing with the existing methods. Copyright © 2023, The Authors. All rights reserved.

关键词： Computational complexity

来源：评论

学校读者我要写书评

暂无评论

Cross-domain NER with Generated Task-Oriented Knowledge: An Empirical Study from Information Density Perspective

Cross-domain NER with Generated Task-Oriented Knowledge: An ...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Zhang, Zhihao Lee, Sophia Yat Mei Wu, Junshuang Zhang, Dong Li, Shoushan Cambria, Erik Zhou, Guodong School of Computer Science & Technology NLP Lab Soochow University China Department of Chinese and Bilingual Studies The Hong Kong Polytechnic University Hong Kong Beijing Jinghang Research Institute of Computing and Communication China College of Computing and Data Science Nanyang Technological University Singapore

ISBN: (纸本)9798891761643

Cross-domain Named Entity Recognition (CDNER) is crucial for Knowledge Graph (KG) construction and natural language processing (NLP), enabling learning from source to target domains with limited data. Previous studies often rely on manually collected entity-relevant sentences from the web or attempt to bridge the gap between tokens and entity labels across domains. These approaches are time-consuming and inefficient, as these data are often weakly correlated with the target task and require extensive pre-training. To address these issues, we propose automatically generating task-oriented knowledge (GTOK) using large language models (LLMs), focusing on the reasoning process of entity extraction. Then, we employ task-oriented pre-training (TOPT) to facilitate domain adaptation. Additionally, current cross-domain NER methods often lack explicit explanations for their effectiveness. Therefore, we introduce the concept of information density to better evaluate the model's effectiveness before performing entity recognition. We conduct systematic experiments and analyses to demonstrate the effectiveness of our proposed approach and the validity of using information density for model evaluation. © 2024 Association for Computational Linguistics.

关键词： Domain Knowledge

来源：评论

学校读者我要写书评

暂无评论

ERTool:A Python Package for Efffcient Implementation of the Evidential Reasoning Approach for Multi-Source Evidence Fusion

引用

Health data science 2024年第1期4卷 162-176页

作者： Tongyue Shi Liya Guo Zeyuan Shen Guilan Kong Institute of Medical Technology Peking University Health Science CenterBeijingChina National Institute of Health Data Science Peking UniversityBeijingChina Yau Mathematical Sciences Center Tsinghua UniversityBeijingChina Tandon School of Engineering New York UniversityNew YorkNYUSA Advanced Institute of Information Technology Peking UniversityHangzhouChina

Background:Multi-source evidence fusion aims to process and combine evidence from different sources to support rational and reliable *** evidential reasoning(ER)approach is a helpful method to deal with information from multiple sources with *** has been widely used in business analytics,healthcare management,and other ffelds for optimal ***,computerized implementation of the ER approach usually requires much expertise and *** present,some ER-based computerized tools,such as the intelligent decision system(IDS),have been developed by professionals to provide decision ***,IDS is not open source,and the user interfaces are a bit complicated for non-professional *** lack of a free-to-access and easy-to-use computerized tool limits the application of ***:We designed and developed a Python package that could efffciently implement the ER approach for multi-source evidence ***,based on it,we built an online webbased system,providing not only real-time evidence fusion but also visualized illustrations of combined ***,a comparison study between the Python package and IDS was ***:A Python package,ERTool,was developed to implement the ER approach automatically and *** online version of the ERTool provides a more convenient way to handle evidence fusion ***:ERTool,compatible with Python 3 and can be installed through the Python Package Index at https://***/project/ERTool/,was developed to implement the ER *** ERTool has advantages in easy accessibility,clean interfaces,and high computing efffciency,making it a key tool for researchers and practitioners in multiple evidence-based *** helps bridge the gap between the algorithmic ER and its practical application and facilitates its widespread adoption in general decision-making contexts.

关键词： Python handle illustration

来源：评论

学校读者我要写书评

暂无评论

Hybrid Multimodal Machine Learning Driven Android Malware Recognition and Classification Model 7

Hybrid Multimodal Machine Learning Driven Android Malware Re...

引用

7th International Conference on Electronics, Communication and Aerospace technology, ICECA 2023

作者： Arthi, A. Aggarwal, Kapil Karthikeyan, R. Kayalvili, S. Srimathi, S. Srivastava, Aviral Rajalakshmi Institute of Technology Department of Artificial Intelligence and Data Science Chennai India Department of Computer Science & Engineering Guntur Andhra Pradesh Vaddeswaram522302 India Dr NGP Institute of Technology Department of Artificial Intelligence and Data Science Coimbatore India Artificial Intelligence College Name & Address: Kongu Engineering College Perundurai India Saveetha School of Engineering SIMATS Department of Bio Technology Tamilnadu Chennai India Amity University Rajasthan Jaipur300202 India

ISBN: (纸本)9798350340600

Android mobile applications and devices can be extremely utilized and employed in industry and smart cities. Malware recognition is an efficient and powerful method for assurance security of Android schemes, mainly for industrial platforms and smart cities. In recent times, research utilizing machine learning (ML)-based approaches for Android malware recognition enhanced quickly. However, one of the performed methods to accomplish feature selection and analysis, so-called feature engineering is labour-intensive and depends on artificial knowledge. Therefore, this study presents a Hybrid Multimodal Machine Learning Driven Android Malware Recognition and Classification (HM3-AMRC) model. The proposed HM3-AMRC technique recognizes and categorizes the Android malware accurately and efficiently. In the presented HM3-AMRC technique, initial phase of data preprocessing is performed. Next, the classification process takes place using three ML techniques such as gradient boosting decision tree (GBDT), extreme learning machine (ELM), and multilayer perceptron (MLP). Moreover, Bayesian optimization (BO) technique is employed for optimal parameter selection of the ML approaches. The stimulation analysis of the HM3-AMRC method is tested on Android malware dataset. Extensive comparison analysis highlighted the betterment of the HM3-AMRC method over existing techniques. © 2023 IEEE.

关键词： Android malware

来源：评论

学校读者我要写书评

暂无评论

Joint-Motion Mutual Learning for Pose Estimation in Video 24

Joint-Motion Mutual Learning for Pose Estimation in Video

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Wu, Sifan Chen, Haipeng Yin, Yifang Hu, Sihao Feng, Runyang Jiao, Yingying Yang, Ziqi Liu, Zhenguang College of Computer Science and Technology Jilin University Changchun China A STAR Singapore Singapore Georgia Institute of Technology AtlantaGA United States School of Artificial Intelligence Jilin University Changchun China The State Key Laboratory of Blockchain and Data Security Zhejiang University Hangzhou China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun China Institute of Blockchain and Data Security Hangzhou China

ISBN: (纸本)9798400706868

Human pose estimation in videos has long been a compelling yet challenging task within the realm of computer vision. Nevertheless, this task remains difficult because of the complex video scenes, such as video defocus and self-occlusion. Recent methods strive to integrate multi-frame visual features generated by a backbone network for pose estimation. However, they often ignore the useful joint information encoded in the initial heatmap, which is a by-product of the backbone generation. Comparatively, methods that attempt to refine the initial heatmap fail to consider any spatio-temporal motion features. As a result, the performance of existing methods for pose estimation falls short due to the lack of ability to leverage both local joint (heatmap) information and global motion (feature) dynamics. To address this problem, we propose a novel joint-motion mutual learning framework for pose estimation, which effectively concentrates on both local joint dependency and global pixel-level motion dynamics. Specifically, we introduce a context-aware joint learner that adaptively leverages initial heatmaps and motion flow to retrieve robust local joint feature. Given that local joint feature and global motion flow are complementary, we further propose a progressive joint-motion mutual learning that synergistically exchanges information and interactively learns between joint feature and motion flow to improve the capability of the model. More importantly, to capture more diverse joint and motion cues, we theoretically analyze and propose an information orthogonality objective to avoid learning redundant information from multi-cues. Empirical experiments show our method outperforms prior arts on three challenging benchmarks. © 2024 ACM.

关键词： Motion estimation

来源：评论

学校读者我要写书评

暂无评论

Graph convolution network based recommender systems: learning guarantee and item mixture powered strategy 22

Graph convolution network based recommender systems: learnin...

引用

Proceedings of the 36th International Conference on Neural Information Processing Systems

作者： Leyan Deng Defu Lian Chenwang Wu Enhong Chen School of Data Science University of Science and Technology of China School of Data Science University of Science and Technology of China and School of Computer Science and Technology University of Science and Technology of China

ISBN: (纸本)9781713871088

Inspired by their powerful representation ability on graph-structured data, Graph Convolution Networks (GCNs) have been widely applied to recommender systems, and have shown superior performance. Despite their empirical success, there is a lack of theoretical explorations such as generalization properties. In this paper, we take a first step towards establishing a generalization guarantee for GCN-based recommendation models under inductive and transductive learning. We mainly investigate the roles of graph normalization and non-linear activation, providing some theoretical understanding, and construct extensive experiments to further verify these findings empirically. Furthermore, based on the proven generalization bound and the challenge of existing models in discrete data learning, we propose Item Mixture (IMix) to enhance recommendation. It models discrete spaces in a continuous manner by mixing the embeddings of positive-negative item pairs, and its effectiveness can be strictly guaranteed from empirical and theoretical aspects.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Vision Transformer Based Hash Coding for Efficient Image and Audio Retrieval with Global and Local Equilibrium Distance Constraints

Vision Transformer Based Hash Coding for Efficient Image and...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Ye Liu Yan Pan Jian Yin School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China Artificial Intelligence and Big Data Department Lizhi Inc. Beijing & Guangzhou China School of Artificial Intelligence Sun Yat-sen University Zhuhai China

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

With the application of efficient retrieval in information systems and retrieval augmented generation with vector database for large language models, hash coding algorithms have made progress in recent years. The rise of transformer technology in the field of deep learning has brought the possibility to further improve the effect of hash coding algorithms. We introduce the vision transformer framework to both images and audios, and propose a novel approach for the tasks of multi-label image retrieval and audio event retrieval. In the proposed hash coding model, global and local equilibrium distance constraints are integrated, so that the hash codes for images can be better obtained through the global hash centers and local similar samples. In order to realize end-to-end training and hash code generation for audios, we adopt the adapter of mel spectrogram, thus the proposed approach can be simply converted and applied to audio hash coding. Comparative experiments verify that better results can be achieved on multiple image and audio datasets.

关键词： Training Computer vision Image coding Codes Large language models Image retrieval Transformers Encoding Vectors Spectrogram

来源：评论

学校读者我要写书评

暂无评论

NVDS$^{\mathbf{+}}$+: Towards Efficient and Versatile Neural Stabilizer for Video Depth Estimation

引用

IEEE Transactions on Pattern Analysis and Machine Intelligence 2024年第1期47卷 583-600页

作者： Yiran Wang Min Shi Jiaqi Li Chaoyi Hong Zihao Huang Juewen Peng Zhiguo Cao Jianming Zhang Ke Xian Guosheng Lin School of AIA Huazhong University of Science and Technology Wuhan China College of Computing and Data Science Nanyang Technological University Singapore Adobe Research San Francisco CA USA School of EIC Huazhong University of Science and Technology Wuhan China

Video depth estimation aims to infer temporally consistent depth. One approach is to finetune a single-image model on each video with geometry constraints, which proves inefficient and lacks robustness. An alternative is learning to enforce consistency from data, which requires well-designed models and sufficient video depth data. To address both challenges, we introduce NVDS $^{\mathbf{+}}$ that stabilizes inconsistent depth estimated by various single-image models in a plug-and-play manner. We also elaborate a large-scale Video Depth in the Wild (VDW) dataset, which contains 14,203 videos with over two million frames, making it the largest natural-scene video depth dataset. Additionally, a bidirectional inference strategy is designed to improve consistency by adaptively fusing forward and backward predictions. We instantiate a model family ranging from small to large scales for different applications. The method is evaluated on VDW dataset and three public benchmarks. To further prove the versatility, we extend NVDS $^{\mathbf{+}}$ to video semantic segmentation and several downstream applications like bokeh rendering, novel view synthesis, and 3D reconstruction. Experimental results show that our method achieves significant improvements in consistency, accuracy, and efficiency. Our work serves as a solid baseline and data foundation for learning-based video depth estimation.

关键词： Estimation Streaming media Accuracy Solid modeling Semantic segmentation data models Semantics Real-time systems Predictive models Adaptation models

来源：评论

学校读者我要写书评

暂无评论

Implementing Parallel Computing to Enhance the Performance of K-mean Algorithm

Implementing Parallel Computing to Enhance the Performance o...

引用

2021 International Conference on data Analytics for Business and Industry, ICDABI 2021

作者： Taha, Ranyah Alshakrani, Sara Alqaddoumi, Abdallah University of Bahrain Big Data Science and Analytics College of Science Bahrain University of Bahrain College of Information Technology College of Science Bahrain

ISBN: (纸本)9781665416566

Clustering is a common tool in data science, and it is used in many areas, such as statistics and bioinformatics. Clustering has a number of algorithms. The most well-known is k-means, which is popular due to its simplicity and efficiency. Similarly, as a programming model, the Message Passing interface (MPI4py) improves performance by reducing the execution time and increasing the speedup. By applying the K-means clustering algorithm to the MPI4py library, the performance of the algorithm in a parallel setting improved. The efficiency of clustering data using K-means is examined in this study in terms of overhead expenditure and execution between running the K-means algorithm sequentially and running the K-means algorithms using a Message Passing Interface (MPI) parallel architecture. © 2021 IEEE.

关键词： Message passing

来源：评论

学校读者我要写书评

暂无评论

Cooperative engineering the multiple radio-frequency fields to reduce the X-junction barrier for ion trap chips

引用

Chip 2024年第1期3卷 55-63页

作者： Yarui Liu Zhao Wang Zixuan Xiang Qikun Wang Tianyang Hu Xu Wang College of Big Data and Information Engineering Guizhou UniversityGuiyang 550025China Shenzhen Institute for Quantum Science and Engineering Southern University of Science and TechnologyShenzhen 518055China International Quantum Academy Shenzhen 518048China Guangdong Provincial Key Laboratory of Quantum Science and Engineering Southern University of Science and TechnologyShenzhen 518055China

With the increasing number of ion qubits and improving performance of sophisticated quantum algorithms,more and more scalable complex ion trap electrodes have been developed and *** ion shuttling operations at the junction are more frequently used,such as in the areas of separation,merging,and *** studies have been conducted to optimize the geometries of the radio-frequency(RF)electrodes to generate ideal trapping electric fields with a lower junction barrier and an even ion height of the RF saddle ***,this iteration is time-consuming and commonly accompanied by complicated and sharp electrode ***,high-accuracy fabrication process and high electric breakdown voltage are *** the current work,an effective method was proposed to reduce the junction’s pseudo-potential barrier and ion height variation by setting several individual RF electrodes and adjusting each RF voltage amplitude without changing the geometry of the electrode *** simulation results show that this method shows the same effect on engineering the trapping potential and reducing the potential barrier,but requires fewer parameters and optimization *** combining this method with the geometrical shapeoptimizing,the pseudo-potential barrier and the ion height variation near the junction can be further *** addition,the geometry of the electrodes can be simplified to relax the fabrication precision and keep the ability to engineer the trapping electric field in real-time even after the fabrication of the electrodes,which provides a potential all-electric degree of freedom for the design and control of the two-dimensional ion crystals and investigation of their phase transition.

关键词： Ion trap Junction Ion shuttling Electrode optimization Pseudo-potential barrier

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：