检索结果-内蒙古大学图书馆

A Framework for Multiclass Contour Visualization

IEEE Transactions on Visualization and computer Graphics 2023年第1期29卷 353-362页

作者： Li, Sihang Yu, Jiacheng Li, Mingxuan Liu, Le Zhang, Xiaolong Luke Yuan, Xiaoru Laboratory of Machine Perception Ministry of Education School of AI Peking University China Center for Data Science Academy for Advanced Interdisciplinary Studies Peking University China National Engineering Laboratory for Big Data Analysis and Application Peking University China School of Computer Science Northwestern Polytechnical University China College of Information Sciences and Technology Pennsylvania State University United States

Multiclass contour visualization is often used to interpret complex data attributes in such fields as weather forecasting, computational fluid dynamics, and artificial intelligence. However, effective and accurate representations of underlying data patterns and correlations can be challenging in multiclass contour visualization, primarily due to the inevitable visual cluttering and occlusions when the number of classes is significant. To address this issue, visualization design must carefully choose design parameters to make visualization more comprehensible. With this goal in mind, we proposed a framework for multiclass contour visualization. The framework has two components: a set of four visualization design parameters, which are developed based on an extensive review of literature on contour visualization, and a declarative domain-specific language (DSL) for creating multiclass contour rendering, which enables a fast exploration of those design parameters. A task-oriented user study was conducted to assess how those design parameters affect users' interpretations of real-world data. The study results offered some suggestions on the value choices of design parameters in multiclass contour visualization. © 2022 IEEE.

关键词： data visualization

来源：评论

学校读者我要写书评

暂无评论

ImagineNet: Target Speaker Extraction with Intermittent Visual Cue Through Embedding Inpainting 48

ImagineNet: Target Speaker Extraction with Intermittent Visu...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Pan, Zexu Wang, Wupeng Borsdorf, Marvin Li, Haizhou Institute of Data Science Singapore Singapore Nus Department of Electrical and Computer Engineering Singapore Singapore University of Bremen Machine Listening Lab Germany The Chinese University of HongKong Shenzhen Research Institute of Big Data School of Data Science Shenzhen China

ISBN: (纸本)9781728163277

The speaker extraction technique seeks to single out the voice of a target speaker from the interfering voices in a speech mixture. Typically an auxiliary reference of the target speaker is used to form voluntary attention. Either a pre-recorded utterance or a synchronized lip movement in a video clip can serve as the auxiliary reference. The use of visual cue is not only feasible, but also effective due to its noise robustness, and becoming popular. However, it is difficult to guarantee that such parallel visual cue is always available in real-world applications where visual occlusion or intermittent communication can occur. In this paper, we study the audio-visual speaker extraction algorithms with intermittent visual cue. We propose a joint speaker extraction and visual embedding inpainting framework to explore the mutual benefits. To encourage the interaction between the two tasks, they are performed alternately with an interlacing structure and optimized jointly. We also propose two types of visual inpainting losses and study our proposed method with two types of popularly used visual embeddings. The experimental results show that we outperform the baseline in terms of signal quality, perceptual quality, and intelligibility. © 2023 IEEE.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

FedNorm: Optimised Federated Learning Strategy Using Hybrid Regularisation Norm 12th

FedNorm: Optimised Federated Learning Strategy Using Hybrid ...

引用

12th International Conference on Big data and Artificial Intelligence, BDA 2024

作者： John, Binu Menon, Varun Adhikari, Mainak Department of Computer Science and Engineering SCMS School of Engineering and Technology Kerala Ernakulam683576 India APJ Abdul Kalam Technological University Kerala Thiruvananthapuram695016 India School of Data Science Indian Institute of Science Education and Research Vithura Kerala Thiruvananthapuram695551 India

ISBN: (纸本)9783031818202

Federated Learning (FL) has emerged as a game-changing method for training machine learning (ML) models on decentralized data sources without centralizing the data itself. Conventional FL algorithms frequently exhibit performance instability and inefficiency, especially when working with non-Independent and Identically Distributed (non-IID) data distributions. To overcome these difficulties, we present FedNorm, a new FL method that uses hybrid regularisation approach to improve model stability and accuracy by balancing sparsity and smoothness, to increase generalization across varied data distributions. Our experimental setup uses the MNIST dataset to train models in both Independent and Identically Distributed (IID) and non-IID situations. The findings show that FedNorm routinely outperforms classic algorithms like FedAvg, FedSGD, FedNova and FedSAM, with minimal test loss and high accuracy. FedNorm has an exceptional accuracy rating of 0.98 on both IID and non-IID data. FedNorm addresses the constraints of conventional FL algorithms, resulting in a strong and dependable solution for FL in diverse situations. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Exploring the Role of Generative AI in Constructing Knowledge Graphs for Drug Indications with Medical Context 15

Exploring the Role of Generative AI in Constructing Knowledg...

引用

15th International Conference on Semantic Web Applications and Tools for Health Care and Life sciences, SWAT4HCLS 2024

作者： Alharbi, Reham Ahmed, Umair Dobriy, Daniil Lajewska, Weronika Menotti, Laura Saeedizade, Mohammad Javad Dumontier, Michel Department of Computer Science University of Liverpool Liverpool United Kingdom School of Science and Technology University of Camerino Camerino Italy Institute for Data Process and Knowledge Management Vienna University of Economics and Business Vienna Austria Department of Electrical Engineering and Computer Science University of Stavanger Stavanger Norway Department of Information Engineering University of Padua Padova Italy Department of Computer Science Linköping University Linköping Sweden Institute of Data Science Maastricht University Maastricht Netherlands

The medical context for a drug indication provides crucial information on how the drug can be used in practice. However, the extraction of medical context from drug indications remains poorly explored, as most research concentrates on the recognition of medications and associated diseases. Indeed, most databases cataloging drug indications do not contain their medical context in a machine-readable format. This paper proposes the use of a large language model for constructing DIAMOND-KG, a knowledge graph of drug indications and their medical context. The study 1) examines the change in accuracy and precision in providing additional instruction to the language model, 2) estimates the prevalence of medical context in drug indications, and 3) assesses the quality of DIAMOND-KG against NeuroDKG, a small manually curated knowledge graph. The results reveal that more elaborated prompts improve the quality of extraction of medical context;71% of indications had at least one medical context;63.52% of extracted medical contexts correspond to those identified in NeuroDKG. This paper demonstrates the utility of using large language models for specialized knowledge extraction, with a particular focus on extracting drug indications and their medical context. We provide DIAMOND-KG as a FAIR RDF graph supported with an ontology. Openly accessible, DIAMOND-KG may be useful for downstream tasks such as semantic query answering, recommendation engines, and drug repositioning research. © 2024 Copyright for this paper by its authors.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

PipeMoE: Accelerating Mixture-of-Experts through Adaptive Pipelining 42

PipeMoE: Accelerating Mixture-of-Experts through Adaptive Pi...

引用

42nd IEEE International Conference on computer Communications, INFOCOM 2023

作者： Shi, Shaohuai Pan, Xinglin Chu, Xiaowen Li, Bo Harbin Institute of Technology School of Computer Science and Technology Shenzhen China Hong Kong Baptist University Department of Computer Science Hong Kong Data Science and Analytics Thrust Hong Kong The Hong Kong University of Science and Technology Department of Computer Science and Engineering Hong Kong

ISBN: (纸本)9798350334142

Large models have attracted much attention in the AI area. The sparsely activated mixture-of-experts (MoE) technique pushes the model size to a trillion-level with a sub-linear increase of computations as an MoE layer can be equipped with many separate experts, but only one or two experts need to be trained for each input data. However, the feature of dynamically activating experts of MoE introduces extensive communications in distributed training. In this work, we propose PipeMoE to adaptively pipeline the communications and computations in MoE to maximally hide the communication time. Specifically, we first identify the root reason why a higher pipeline degree does not always achieve better performance in training MoE models. Then we formulate an optimization problem that aims to minimize the training iteration time. To solve this problem, we build performance models for computation and communication tasks in MoE and develop an optimal solution to determine the pipeline degree such that the iteration time is minimal. We conduct extensive experiments with 174 typical MoE layers and two real-world NLP models on a 64-GPU cluster. Experimental results show that our PipeMoE almost always chooses the best pipeline degree and outperforms state-of-the-art MoE training systems by 5%-77% in training time. © 2023 IEEE.

关键词： Pipelines

来源：评论

学校读者我要写书评

暂无评论

Improving Low-Resource Sequence Labeling with Knowledge Fusion and Contextual Label Explanations

arXiv

引用

arXiv 2025年

作者： Lai, Peichao Gan, Jiaxin Ye, Feiyang Wang, Yilei Cui, Bin School of Computer Science Peking University China College of Computer and Data Science Fuzhou University China

Sequence labeling remains a significant challenge in low-resource, domain-specific scenarios, particularly for character-dense languages like Chinese. Existing methods primarily focus on enhancing model comprehension and improving data diversity to boost performance. However, these approaches still struggle with inadequate model applicability and semantic distribution biases in domain-specific contexts. To overcome these limitations, we propose a novel framework that combines an LLM-based knowledge enhancement workflow with a span-based Knowledge Fusion for Rich and Efficient Extraction (KnowFREE) model. Our workflow employs explanation prompts to generate precise contextual interpretations of target entities, effectively mitigating semantic biases and enriching the model’s contextual understanding. The KnowFREE model further integrates extension label features, enabling efficient nested entity extraction without relying on external knowledge during inference. Experiments on multiple Chinese domain-specific sequence labeling datasets demonstrate that our approach achieves state-of-the-art performance, effectively addressing the challenges posed by low-resource settings. Copyright © 2025, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Context Interaction and Reasoning with Transformer for Emotion Recognition

Hierarchical Context Interaction and Reasoning with Transfor...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Wang, Wenxuan Wang, Chenglei Wang, Xiaomei Shen, Xuli Xu, Qing Qian, Xuelin School of Computer Science Northwestern Polytechnical University Xi'an China UniDT Co. Ltd. Shanghai China School of Data Science Fudan University Shanghai China School of Automation Northwestern Polytechnical University Xi'an China

ISBN: (纸本)9798350368741

Emotion recognition is an important task in computer vision. However, current approaches using hard associations (e.g., element-wise addition or concatenation) suffer from information pollution. To overcome these challenges and utilize information at different scales, we present a novel Transformer-based emotion recognition (TransEmo) framework utilizing only the RGB modality as input. TransEmo is a hierarchical feature fusion framework with soft-association to effectively realize contextual interaction and emotion reasoning. It comprises a top-down path and a bottom-up path with cross-attention layers. The top-down path enriches the features of the current hierarchy gradually by using information from a larger receptive field and interacts effectively with contexts to suppress redundant information and noise. The bottom-up path introduces a set of learnable prototypes to adaptively capture clues for various emotions by reasoning with hierarchical *** proposed approach achieves state-of-the-art performance on two benchmarks and provides an analysis to discuss the advantages of our modules. © 2025 IEEE.

关键词： context reasoning emotion recognition hierarchical interaction transformer

来源：评论

学校读者我要写书评

暂无评论

One-shot-but-not-degraded Federated Learning 24

One-shot-but-not-degraded Federated Learning

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Zeng, Hui Xu, Minrui Zhou, Tongqing Wu, Xinyi Kang, Jiawen Cai, Zhiping Niyato, Dusit School of Computer National University of Defense Technology Changsha China College of Computing and Data Science Nanyang Technological University Singapore Singapore School of Automation Guangdong University of Technology Guangzhou China

ISBN: (纸本)9798400706868

Transforming the multi-round vanilla Federated Learning (FL) into one-shot FL (OFL) significantly reduces the communication burden and makes a big leap toward practical deployment. However, we note that existing OFL methods all build on model lossy reconstruction (i.e., aggregating while partially discarding local knowledge in clients' models), which attains one-shot at the cost of degraded inference performance. By identifying the root cause of stressing too much on finding a one-fit-all model, this work proposes a novel one-shot FL framework by embodying each local model as an independent expert and leveraging a Mixture-of-Experts network to maintain all local knowledge intact. A dedicated self-supervised training process is designed to tune the network, where the sample generation is guided by approximating underlying distributions of local data and making distinct predictions among experts. Notably, the framework also fuels FL with flexible, data-free aggregation and heterogeneity tolerance. Experiments on 4 datasets show that the proposed framework maintains the one-shot efficiency, facilitates superior performance compared with 8 OFL baselines (+5.54% on CIFAR-10), and even attains over ×4 performance gain compared with 3 multi-round FL methods, while only requiring less than 85% trainable parameters. Our code will be available at https://***/zenghui9977/IntactOFL. © 2024 ACM.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

So Far Yet So Near: Time Series data Augmentation with Exploring non-Semantic Boundaries based on Reinforcement Learning

So Far Yet So Near: Time Series Data Augmentation with Explo...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Li, Haoran Zhang, Zhibo Kang, Jiarong Jiang, Xun Gong, Xiaoli Zhang, Jin Sun, Zhe Cichocki, Andrzej College of Computer Science Nankai University Tianjin China School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China Faculty of Medicine Faculty of Health Data Science Juntendo University Japan Systems Research Institute Polish Academy of Science Warsaw Poland

ISBN: (纸本)9798350368741

data augmentation effectively expands feature distribution in time series classification, enhancing downstream task performance. However, existing techniques often fail to maintain semantic consistency between augmented and original time series data, causing label noise and thereby degrading downstream task performance. We argue that data augmentation should preserve time series semantic consistency and expand the non-semantic information space. In this paper, we reformulate data augmentation as a semantic path planning problem between original data and augmented data, modeled as a Markov Decision Process (MDP). We propose a reinforcement learning-based algorithm (RL) named FreqSYN, where the action space is defined by a set of learnable Gaussian kernels that perturbs the frequency domain of the original data to generate augmented samples. The confidence coefficients of augmented data in semantically relevant classification tasks are used as a reward to iteratively refine the FreqSYN. Our method is validated across four datasets, achieving state-of-the-art performance, with a 2% improvement in F1 score over the SimPSI method. The code and models are available at https://***/NKU-EmbeddedSystem/FreqSYN. © 2025 IEEE.

关键词： data argumentation frequency domain augmentation Gaussian kernel prediction time series

来源：评论

学校读者我要写书评

暂无评论

Heart Disease Diagnosis Using the Brute Force Algorithm and Machine Learning Techniques

引用

computers, Materials & Continua 2022年第8期72卷 3195-3211页

作者： Junaid Rashid Samina Kanwal Jungeun Kim Muhammad Wasif Nisar Usman Naseem Amir Hussain Department of Computer Science and Engineering Kongju National UniversityCheonan31080Korea Department of Computer Science COMSATS University IslamabadWah Campus47040Pakistan School of Computer Science University of SydneySydneyNSW 2006Australia Centre of AI and Data Science Edinburgh Napier UniversityEdinburghEH114DYUK

Heart disease is one of the leading causes of death in the world *** of heart disease is a prominent topic in the clinical data *** increase patient survival rates,early diagnosis of heart disease is an important field of research in the medical *** are many studies on the prediction of heart disease,but limited work is done on the selection of *** selection of features is one of the best techniques for the diagnosis of heart *** this research paper,we find optimal features using the brute-force algorithm,and machine learning techniques are used to improve the accuracy of heart disease *** performance evaluation,accuracy,sensitivity,and specificity are used with split and cross-validation *** results of the proposed technique are evaluated in three different heart disease datasets with a different number of records,and the proposed technique is found to have superior *** selection of optimized features generated by the brute force algorithm is used as input to machine learning algorithms such as Support Vector Machine(SVM),Random Forest(RF),K Nearest Neighbor(KNN),and Naive Bayes(NB).The proposed technique achieved 97%accuracy with Naive Bayes through split validation and 95%accuracy with Random Forest through *** Bayes and Random Forest are found to outperform other classification approaches when accurately *** results of the proposed technique are compared with the results of the existing study,and the results of the proposed technique are found to be better than other ***,our proposed approach plays an important role in the selection of important features and the automatic detection of heart disease.

关键词： Heart disease brute force machine learning feature selection

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：