检索结果-内蒙古大学图书馆

27th International Conference on Pattern Recognition, ICPR 2024

作者： Zhao, Xunda Wu, Xing Wang, Jianjia School of Computer Engineering and Science Shanghai University Shanghai China Engineering and Science Shanghai Institute for Advanced Communication and Data Science School of Computer Shanghai University Shanghai China School of AI and Advanced Computing Xi’an Jiaotong-Liverpool University Suzhou China

ISBN: (纸本)9783031783975

Complex network theory has been widely demonstrated as a powerful tool in modeling and characterizing various complex systems. In the past, complex network theory has focused on the behaviors as well as the characteristics of the network nodes and edges. However, with the continuous evolution of society, traditional graph theory faces challenges due to the emergence of extermely large network structures. Recently, complex network method based statistics has attracted much attention. The new approach effectively manages very large networks and uncovers their intrinsic properties. In this paper, we present a complex network analysis model for undirected, unweighted networks based on a statistical analysis approach. This model is inspired by the ensemble model in thermostatistical physics. Based on the established mathematical model, we derive physical measures that reflect the intrinsic properties of the network, including Entropy, Free Energy, Temperature, and so on. In the experimental part, we first explored the mathematical characterization of these metrics. Then, we observed the performance of various network categories under the same metric. Finally, we applied these measures to the field of graph classification. Extensive experiments demonstrate the effectiveness and superiority of the proposed method. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Undirected graphs

来源：评论

学校读者我要写书评

暂无评论

Remote Sensing Scene Classification Based on Hybrid Convolutional Neural Network and Attention Module

Remote Sensing Scene Classification Based on Hybrid Convolut...

引用

2025 International Conference on Advancement in data science, E-learning and Information System, ICADEIS 2025

作者： Kardawi, Muhammad Yusuf Gunawan, Alexander Agung Santoso Bina Nusantara University Profesional Engineer Program Faculty of Engineering Jakarta11480 Indonesia Faculty of Computer Science University of Indonesia Computer Science Department Jakarta Indonesia School of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9798331513320

Remote sensing images present classification challenges due to the complexity of their structural and spatial patterns. This research explores a hybrid approach that combines convolutional neural network (CNN) and attention through feature fusion to improve scene classification accuracy in remote sensing images. The proposed architecture utilizes EfficientNet and VGGNet to extract depth features separately. The extracted features are then integrated with Dynamic Selfattention (DSA), which dynamically focuses the model on the most relevant information in the image. DSA allows the model to adaptively assign weights to different parts of the image, thus improving the discriminative ability of the model. Furthermore, a feature fusion technique is applied to combine information from different layers of the CNN and DSA modules. Experiments conducted on the UC Merced dataset showed accuracies of 0.9181 and 0.9167. These results show that the combination of CNN, DSA, and feature fusion is an effective and robust approach for remote sensing image classification. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

An Empirical Study on Cross-lingual Vocabulary Adaptation for Efficient Language Model Inference

An Empirical Study on Cross-lingual Vocabulary Adaptation fo...

引用

2024 Findings of the Association for Computational Linguistics, EMNLP 2024

作者： Yamaguchi, Atsuki Villavicencio, Aline Aletras, Nikolaos School of Computer Science University of Sheffield United Kingdom Department of Computer Science Institute of Data Science and Artificial Intelligence University of Exeter United Kingdom The Alan Turing Institute United Kingdom

ISBN: (纸本)9798891761681

The development of state-of-the-art generative large language models (LLMs) disproportionately relies on English-centric tokenizers, vocabulary and pre-training data. Despite the fact that some LLMs have multilingual capabilities, recent studies have shown that their inference efficiency deteriorates when generating text in languages other than English. This results in increased inference time and costs. Cross-lingual vocabulary adaptation (CVA) methods have been proposed for adapting models to a target language aiming to improve downstream performance. However, the effectiveness of these methods on increasing inference efficiency of generative LLMs has yet to be explored. In this paper, we perform an empirical study of five CVA methods on four generative LLMs (including monolingual and multilingual models) across four typologically-diverse languages and four natural language understanding tasks. We find that CVA substantially contributes to LLM inference speedups of up to 271.5%. We also show that adapting LLMs that have been pre-trained on more balanced multilingual data results in downstream performance comparable to the original models. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Emotional Reactivity Classification Using Artificial Intelligence Based on Twitter in Bahasa Indonesia 3

Emotional Reactivity Classification Using Artificial Intelli...

引用

3rd IEEE International Conference on Social sciences and Intelligence Management, SSIM 2023

作者： Paramita, Greta V. Andangsari, Esther W. Kemala, Ade P. Ali, Moondore M. Putri, Trisa M. Puspita, Katarina I. Bina Nusantara University Faculty of Humanities Psychology Department Jakarta Indonesia Data Science Program School of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (纸本)9798350327786

Twitter is one of Indonesia's most widely used social media to express positive and negative emotions. Negative emotions are referred to as emotional reactivity, an example of which is depression. To detect emotional reactivity, Artificial Intelligence (AI) was used. With deep learning pretrained model methods (IndoBERT and IndoBERTweet), AI successfully classified emotional reactivity. AI satisfactorily detected emotional reactivity on Twitter. © 2023 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

On the Design of Cancer Tumor Type Prediction using Machine Learning Techniques for Efficient Diagnosis 2

On the Design of Cancer Tumor Type Prediction using Machine ...

引用

2nd International Conference on Advancements in Smart, Secure and Intelligent Computing, ASSIC 2024

作者： Thakkar, Hiren Kumar Kumar, Yogesh Kathirisetty, Nikhila School of Technology Pandit Deendayal Energy University Department of Computer Science and Engineering Gujarat 382007 India Vardhaman College of Engineering Department of Computer Science and Data Science Hyderabad Shamshabad India

ISBN: (纸本)9798350370188

In the recent past, cancer is designated as the life threatening disease causing significant deaths across the globe. Countries are putting efforts for early stage cancer detection, and mortality prediction. Machine Learning (ML) models are proven to efficiently find the correlation among the features for robust predictions over statistical approaches. In this paper, we used kaggle dataset that includes 569 cancer cells and around 30 features cancer cells' classification. The proposed study employs ML models (e.g., binary classifiers) for effective predictive analytics. The evaluation results indicate that Random Forest achieves better results with Area Under Curve (AUC) of 0.99 followed by Decision tree with AUC be 0.92. However, the Logistic Regression (LR) and Support Vector Machine (SVM) fails to capture the generalized behavior of the cancer data for predictive analysis. © 2024 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Tackling Non-Stationarity in Reinforcement Learning via Causal-Origin Representation 41

Tackling Non-Stationarity in Reinforcement Learning via Caus...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Zhang, Wanpeng Li, Yilin Yang, Boyu Lu, Zongqing School of Computer Science Peking University China Center for Statistical Science Peking University China School of Data Science Fudan University China Beijing Academy of Artificial Intelligence China

In real-world scenarios, the application of reinforcement learning is significantly challenged by complex *** existing methods attempt to model changes in the environment explicitly, often requiring impractical prior knowledge of *** this paper, we propose a new perspective, positing that non-stationarity can propagate and accumulate through complex causal relationships during state transitions, thereby compounding its sophistication and affecting policy *** believe that this challenge can be more effectively addressed by implicitly tracing the causal origin of *** this end, we introduce the Causal-Origin REPresentation (COREP) *** primarily employs a guided updating mechanism to learn a stable graph representation for the state, termed as causal-origin *** leveraging this representation, the learned policy exhibits impressive resilience to *** supplement our approach with a theoretical analysis grounded in the causal interpretation for non-stationary reinforcement learning, advocating for the validity of the causal-origin *** results further demonstrate the superior performance of COREP over existing methods in tackling non-stationarity *** code is available at https://***/PKURL/COREP. Copyright 2024 by the author(s)

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Discrete-Time Collaborative Neurodynamic Approach to Distributed Global Optimization 13

A Discrete-Time Collaborative Neurodynamic Approach to Distr...

引用

13th International Conference on Intelligent Control and Information Processing, ICICIP 2025

作者： Huang, Haoen Zeng, Zhigang Wang, Jun School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China Department of Computer Science Department of Data Science City University of HongKong Kowloon Hong Kong

ISBN: (纸本)9798331516147

In this paper, a discrete-time projection neural network with an adaptive step size (DPNN) is proposed for distributed global optimization. The DPNN is proven to be convergent to a Karush-Kuhn-Tucker point. Several DPNNs are utilized in a collaborative neurodynamic framework for solving distributed global optimization problem. The efficacy of the collaborative neurodynamic approach with DPNNs is demonstrated through simulation results. © 2025 IEEE.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

A Tutorial on Federated Learning from Theory to Practice:Foundations,Software Frameworks,Exemplary Use Cases,and Selected Trends

引用

IEEE/CAA Journal of Automatica Sinica 2024年第4期11卷 824-850页

作者： M.Victoria Luzón Nuria Rodríguez-Barroso Alberto Argente-Garrido Daniel Jiménez-López Jose M.Moyano Javier Del Ser Weiping Ding Francisco Herrera Department of Software Engineering Andalusian Research Institute in Data Science and Computational Intelligence(DaSCI)University of GranadaGranada 18071Spain Department of Computer Science and Artificial Intelligence Andalusian Research Institute in Data Science and Computational Intelligence(DaSCI)University of GranadaGranada 18071Spain Department of Communications Engineering University of the Basque Country(UPV/EHU)and also with TECNALIABasque Research&Technology Alliance(BRTA)Spain School of Information Science and Technology Nantong UniversityNantong 226019China

When data privacy is imposed as a necessity,Federated learning(FL)emerges as a relevant artificial intelligence field for developing machine learning(ML)models in a distributed and decentralized *** allows ML models to be trained on local devices without any need for centralized data transfer,thereby reducing both the exposure of sensitive data and the possibility of data interception by malicious third *** paradigm has gained momentum in the last few years,spurred by the plethora of real-world applications that have leveraged its ability to improve the efficiency of distributed learning and to accommodate numerous participants with their data *** virtue of FL,models can be learned from all such distributed data sources while preserving data *** aim of this paper is to provide a practical tutorial on FL,including a short methodology and a systematic analysis of existing software ***,our tutorial provides exemplary cases of study from three complementary perspectives:i)Foundations of FL,describing the main components of FL,from key elements to FL categories;ii)Implementation guidelines and exemplary cases of study,by systematically examining the functionalities provided by existing software frameworks for FL deployment,devising a methodology to design a FL scenario,and providing exemplary cases of study with source code for different ML approaches;and iii)Trends,shortly reviewing a non-exhaustive list of research directions that are under active investigation in the current FL *** ultimate purpose of this work is to establish itself as a referential work for researchers,developers,and data scientists willing to explore the capabilities of FL in practical applications.

关键词： data privacy distributed machine learning federated learning software frameworks

来源：评论

学校读者我要写书评

暂无评论

A survey for light field super-resolution

引用

High-Confidence Computing 2024年第1期4卷 118-129页

作者： Mingyuan Zhao Hao Sheng Da Yang Sizhe Wang Ruixuan Cong Zhenglong Cui Rongshan Chen Tun Wang Shuai Wang Yang Huang Jiahao Shen State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and EngineeringBeihang UniversityBeijing 100191China Key Laboratory of Data Science and Intelligent Computing International Innovation InstituteBeihang UniversityHangzhou 311115China State Key Laboratory of Software Development Environment School of Computer Science and EngineeringBeihang UniversityBeijing 100191China

Compared to 2D imaging data,the 4D light field(LF)data retains richer scene’s structure information,which can significantly improve the computer’s perception capability,including depth estimation,semantic segmentation,and LF ***,there is a contradiction between spatial and angular resolution during the LF image acquisition *** overcome the above problem,researchers have gradually focused on the light field super-resolution(LFSR).In the traditional solutions,researchers achieved the LFSR based on various optimization frameworks,such as Bayesian and Gaussian *** learning-based methods are more popular than conventional methods because they have better performance and more robust generalization *** this paper,the present approach can mainly divided into conventional methods and deep learning-based *** discuss these two branches in light field spatial super-resolution(LFSSR),light field angular super-resolution(LFASR),and light field spatial and angular super-resolution(LFSASR),***,this paper also introduces the primary public datasets and analyzes the performance of the prevalent approaches on these ***,we discuss the potential innovations of the LFSR to propose the progress of our research field.

关键词： Light field super-resolution Convolutional neural network Transformer Sub-aperture image Epipolar-plane image

来源：评论

学校读者我要写书评

暂无评论

Routing with Massive Trajectory data 40

Routing with Massive Trajectory Data

引用

40th IEEE International Conference on data Engineering, ICDE 2024

作者： Jensen, Christian S. Yang, Bin Guo, Chenjuan Hu, Jilin Torp, Kristian Aalborg University Department of Computer Science Aalborg Denmark School of Data Science & Engineering East China Normal University Shanghai China

ISBN: (纸本)9798350317152

The unprecedented availability of new types of data coupled with the invention of new technologies combine to enable entirely new or higher-resolution services that in turn enable more rational and data-driven processes. We consider the overall process of vehicular transportation and, more specifically, the process of deciding which route to follow when having to reach a destination. Early solutions modeled a road work as a graph, used sparse in-road sensor data to assign weights to graph edges, and then applied improved versions of Dijkstra's algorithm to find routes with the lowest sums of edge weights. Since then, massive vehicle trajectory data has become available. When coupled with new technologies, this data enables entirely new and higher-resolution routing services that in turn enable better routing. For more than a decade, the authors have engaged in research aimed at exploiting trajectory data to enable better routing. The resulting technologies were developed outside a DBMS. Here, we cover aspects of this research. Further, we challenge the community to develop DBMS support for these and other aspects of routing. © 2024 IEEE.

关键词： database 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：