检索结果-内蒙古大学图书馆

Effects of the urban landscape on heatwave-mortality associations in Hong Kong: comparison of different heatwave definitions

引用

Frontiers of Environmental science & Engineering 2024年第1期18卷 145-156页

作者： Jinglu Song Yi Lu Thomas Fischer Kejia Hu Department of Urban Planning and Design Xi’an Jiaotong-Liverpool UniversitySuzhou 215123China Department of Architecture and Civil Engineering City University of Hong KongKowloon TongHong Kong 999077China Environmental Assessment and Management Research Centre School of Environmental SciencesUniversity of LiverpoolLiverpool L35TRUK Research Unit for Environmental Sciences and Management Faculty of Natural and Agricultural SciencesNorth West UniversityPotchefstroom 31750South Africa Institute of Big Data in Health Science School of Public HealthZhejiang UniversityZijingang CampusHangzhou 310058China

Despite increased attention given to potential modifiers of temperature-mortality associations, evidence for variations between different urban landscape characteristics remains limited. It is in this context that in this paper effect modifications of multiple urban landscape characteristics are explored under different heatwave definitions for different age groups and gender in Hong Kong, China. Daily meteorological data and heatwave-related mortality counts from 2008 to 2017 were collected from the Hong Kong Census and Statistics Department, China. A case-only design was adopted, combined with logistic regression models to examine the modification effects of five urban landscape characteristics under six heatwave definitions. Stratified analyses were conducted to investigate age- and gender-specific effect modifications. It is found that individuals living in greener areas experienced lower levels of mortality during or immediately after heatwaves. In contrast, a higher building density and nighttime land surface temperature (LST) were associated with a higher heatwave-related mortality risk. Pronounced effect modifications of these urban landscape characteristics were observed under hotter and longer heatwaves, and in older adults (age ≥ 65 years) and males. The findings provide a scientific basis for policymakers and practitioners when considering measures for coping with hotter, longer, and more frequent heatwaves in the context of global climate change.

关键词： Urban landscape Heatwave Mortality Effect modification Intra-urban differences Health risk reduction

来源：评论

学校读者我要写书评

暂无评论

A Novel Two-step Sparse Learning Approach for Variable Selection and Optimal Predictive Modeling

引用

IFAC-PapersOnLine 2022年第7期55卷 57-64页

作者： Yiren Liu S. Joe Qin School of Data Science and Hong Kong Institute for Data Science City University of Hong Kong 83 Tat Chee Ave. Hong Kong Centre for Systems Informatics Engineering Shenzhen Research Institute of CityU Shenzhen China

In this paper, a two-step sparse learning approach is proposed for variable selection and model parameter estimation with optimally tuned hyperparameters in each step. In Step one, a sparse learning algorithm is applied on all data to produce a sequence of candidate subsets of selected variables by varying the hyperparameter value. In Step two, for each subset of the selected variables from Step one, Lasso, ridge regression, elastic-net, or adaptive Lasso is employed to find the optimal hyperparameters with the best cross-validation error. Among all subsets, the one with the overall minimum cross-validation error is selected as globally optimal. The effectiveness of the proposed approach is demonstrated using an industrial NOx emission dataset and the Dow challenge dataset to predict product impurity.

关键词： Inferential modeling sparse statistical learning variable selection regularization industrial applications

来源：评论

学校读者我要写书评

暂无评论

Target Networks and Over-parameterization Stabilize Off-policy Bootstrapping with Function Approximation

arXiv

引用

arXiv 2024年

作者： Che, Fengdi Xiao, Chenjun Mei, Jincheng Dai, Bo Gummadi, Ramki Ramirez, Oscar A. Harris, Christopher K. Mahmood, A. Rupam Schuurmans, Dale Department of Computing Science University of Alberta United States School of Data Science The Chinese University of Hong Kong Shenzhen China Google DeepMind United Kingdom School of Computational Science and Engineering Georgia Tech United States Figure Uber United States CIFAR AI Chair Amii Canada

We prove that the combination of a target network and over-parameterized linear function approximation establishes a weaker convergence condition for bootstrapped value estimation in certain cases, even with off-policy data. Our condition is naturally satisfied for expected updates over the entire state-action space or learning with a batch of complete trajectories from episodic Markov decision processes. Notably, using only a target network or an over-parameterized model does not provide such a convergence guarantee. Additionally, we extend our results to learning with truncated trajectories, showing that convergence is achievable for all tasks with minor modifications, akin to value truncation for the final states in trajectories. Our primary result focuses on temporal difference estimation for prediction, providing high-probability value estimation error bounds and empirical analysis on Baird’s counterexample and a Four-room task. 1 Furthermore, we explore the control setting, demonstrating that similar convergence conditions apply to Q-learning. © 2024, CC BY-NC-ND.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

A Novel Mode Selection-Based Fast Intra Prediction Algorithm for Spatial SHVC 48

A Novel Mode Selection-Based Fast Intra Prediction Algorithm...

引用

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

作者： Wang, Dayong Sun, Yu Li, Weisheng Xie, Lele Lu, Xin Dufaux, Frederic Zhu, Ce Chongqing Key Laboratory on Big Data for Bio Intelligence Department of Computer Science China University of Central Arkansas Computing Department of Computer Science United States Chongqing Key Laboratory of Image Cognition School of Information and Communication Engineering China Chongqing University of Posts and Telecommunications School of Information and Communication Engineering China United Kingdom Université Paris-Saclay Cnrs CentraleSupélec Laboratoire des Signaux et Systèmes France University of Electronic Science and Technology of China School of Information and Communication Engineering China

ISBN: (纸本)9781728163277

Due to multi-layer encoding and Inter-layer prediction, Spatial Scalable High-Efficiency Video Coding (SSHVC) has extremely high coding complexity. It is very crucial to improve its coding speed so as to promote widespread and cost-effective SSHVC applications. In this paper, we have proposed a novel Mode Selection-Based Fast Intra Prediction algorithm for SSHVC. We reveal the RD costs of Inter-layer Reference (ILR) mode and Intra mode have a significant difference, and the RD costs of these two modes follow Gaussian distribution. Based on this observation, we propose to apply the classic Gaussian Mixture Model and Expectation Maximization in machine learning to determine whether ILR is the best mode so as to skip the Intra mode. Experimental results demonstrate that the proposed algorithm can significantly improve the coding speed with negligible coding efficiency loss. © 2023 IEEE.

关键词： Gaussian distribution

来源：评论

学校读者我要写书评

暂无评论

Metadata as data Intelligence

引用

data Intelligence 2023年第1期5卷 1-5,F0004页

作者： Jane Greenberg Mingfang Wu Wei Liu Fenghong Liu Metadata Research Center College of Computing and InformaticsDrexel University3675 Market St 10th floor PhiladelphiaPA 19104USA Australian Research Data Commons MelbourneVictoria 3145Australia Shanghai Library(Institute of Scientific and Technical Information of Shanghai) No.1555 Huaihai Middle Road Xuhui DistrictShanghai200031China Department of Library Informationand ArchiveSchool of Economic ManagementUniversity of Chinese Academy of Sciences33 BeisihuanxiluHaidian DistrictBeijing 100190China Data Intelligence National Science LibraryChinese Academy of Sciences33 BeisihuanxiluHaidian DistrictBeijing 100190China

*** Metadata,as a type of data,describes content,provides context,documents transactions,and situates *** in metadata has steadily grown over the last several decades,motivated initially by the increase in digital information,open access,early data sharing policies,and interoperability *** foundation has accelerated in more recent times,due to the increase in research data management policies and advances in *** to research data management,one of the larger factors has been the global adoption of the FAIR(findable,accessible,interoperable,and reusable)data principles[1,2],which are highly ***,researchers across nearly every domain are interested in leveraging metadata for machine learning and other Al applications.

关键词： initially Metadata motivated

来源：评论

学校读者我要写书评

暂无评论

Retrieval-augmented diffusion models for time series forecasting 24

Retrieval-augmented diffusion models for time series forecas...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Jingwei Liu Ling Yang Hongyan Li Shenda Hong School of Intelligence Science and Technology Peking University and National Key Laboratory of General Artificial Intelligence Peking University Institute of Medical Technology Peking University Health Science Center Institute of Medical Technology Peking University Health Science Center and National Institute of Health Data Science Peking University and Institute for Artificial Intelligence Peking University

ISBN: (纸本)9798331314385

While time series diffusion models have received considerable focus from many recent works, the performance of existing models remains highly unstable. Factors limiting time series diffusion models include insufficient time series datasets and the absence of guidance. To address these limitations, we propose a Retrieval-Augmented Time series Diffusion model (RATD). The framework of RATD consists of two parts: an embedding-based retrieval process and a reference-guided diffusion model. In the first part, RATD retrieves the time series that are most relevant to historical time series from the database as references. The references are utilized to guide the denoising process in the second part. Our approach allows leveraging meaningful samples within the database to aid in sampling, thus maximizing the utilization of datasets. Meanwhile, this reference-guided mechanism also compensates for the deficiencies of existing time series diffusion models in terms of guidance. Experiments and visualizations on multiple datasets demonstrate the effectiveness of our approach, particularly in complicated prediction tasks. Our code is available at https://***/stanliu96/RATD

关键词：

来源：评论

学校读者我要写书评

暂无评论

Predicting visual acuity with machine learning in treated ocular trauma patients

引用

International Journal of Ophthalmology(English edition) 2023年第7期16卷 1005-1014页

作者： Zhi-Lu Zhou Yi-Fei Yan Jie-Min Chen Rui-Jue Liu Xiao-Ying Yu Meng Wang Hong-Xia Hao Dong-Mei Liu Qi Zhang Jie Wang Wen-Tao Xia Department of Forensic Medicine Guizhou Medical UniversityGuiyang 550009Guizhou ProvinceChina Shanghai Key Laboratory of Forensic Medicine Shanghai Forensic Service PlatformInstitute of Forensic ScienceMinistry of JusticeShanghai 200063China The SMART(Smart Medicine and AI-based Radiology Technology)Lab Shanghai Institute for Advanced Communication and Data ScienceShanghai UniversityShanghai 200444China School of Communication and Information Engineering Shanghai UniversityShanghai 200444China Basic Medical College Jiamusi UniversityJiamusi 154007Heilongjiang ProvinceChina

AIM:To predict best-corrected visual acuity(BCVA)by machine learning in patients with ocular trauma who were treated for at least ***:The internal dataset consisted of 850 patients with 1589 eyes and an average age of *** initial visual acuity was 0.99 log *** test dataset consisted of 60 patients with 100 eyes collected while the model was *** different machine-learning algorithms(Extreme Gradient Boosting,support vector regression,Bayesian ridge,and random forest regressor)were used to predict BCVA,and four algorithms(Extreme Gradient Boosting,support vector machine,logistic regression,and random forest classifier)were used to classify BCVA in patients with ocular trauma after treatment for 6mo or *** features were obtained from outpatient records,and ocular parameters were extracted from optical coherence tomography images and fundus *** features were put into different machine-learning models,and the obtained predicted values were compared with the actual BCVA *** best-performing model and the best variable selected were further evaluated in the test ***:There was a significant correlation between the predicted and actual values[all Pearson correlation coefficient(PCC)>0.6].Considering only the data from the traumatic group(group A)into account,the lowest mean absolute error(MAE)and root mean square error(RMSE)were 0.30 and 0.40 log MAR,*** the traumatic and healthy groups(group B),the lowest MAE and RMSE were 0.20 and 0.33 log MAR,*** sensitivity was always higher than the specificity in group A,in contrast to the results in group *** classification accuracy and precision were above 0.80 in both *** MAE,RMSE,and PCC of the test dataset were 0.20,0.29,and 0.96,*** sensitivity,precision,specificity,and accuracy of the test dataset were 0.83,0.92,0.95,and 0.90,***:Predicting BCVA using machine-learning models in patients wit

关键词： ocular trauma predicting visiual acuity best-corrected visual acuity visual dysfunction machine learning

来源：评论

学校读者我要写书评

暂无评论

SA-WavLM: Speaker-Aware Self-Supervised Pre-training for Mixture Speech

arXiv

引用

arXiv 2024年

作者： Lin, Jingru Ge, Meng Ao, Junyi Deng, Liqun Li, Haizhou Department of Electrical and Computer Engineering National University of Singapore Singapore Huawei Noah's Ark Lab Hong Kong School of Data Science Shenzhen Research Institute of Big Data The Chinese University of Hong Kong Shenzhen China

It was shown that pre-trained models with self-supervised learning (SSL) techniques are effective in various downstream speech tasks. However, most such models are trained on single-speaker speech data, limiting their effectiveness in mixture speech. This motivates us to explore pre-training on mixture speech. This work presents SA-WavLM, a novel pre-trained model for mixture speech. Specifically, SA-WavLM follows an "extract-merge-predict" pipeline in which the representations of each speaker in the input mixture are first extracted individually and then merged before the final prediction. In this pipeline, SA-WavLM performs speaker-informed extractions with the consideration of the interactions between different speakers. Furthermore, a speaker shuffling strategy is proposed to enhance the robustness towards the speaker absence. Experiments show that SA-WavLM either matches or improves upon the state-of-the-art pre-trained models. Copyright © 2024, The Authors. All rights reserved.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

FedX: Unsupervised Federated Learning with Cross Knowledge Distillation

arXiv

引用

arXiv 2022年

作者： Han, Sungwon Park, Sungwon Wu, Fangzhao Kim, Sundong Wu, Chuhan Xie, Xing Cha, Meeyoung School of Computing KAIST Korea Republic of Data Science Group Institute for Basic Science Korea Republic of Microsoft Research Asia China Tsinghua University China

This paper presents FedX, an unsupervised federated learning framework. Our model learns unbiased representation from decentralized and heterogeneous local data. It employs a two-sided knowledge distillation with contrastive learning as a core component, allowing the federated system to function without requiring clients to share any data features. Furthermore, its adaptable architecture can be used as an add-on module for existing unsupervised algorithms in federated settings. Experiments show that our model improves performance significantly (1.58-5.52pp) on five unsupervised algorithms. Copyright © 2022, The Authors. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Task Separation and Knowledge Sharing for Class Incremental Learning

Task Separation and Knowledge Sharing for Class Incremental ...

引用

Intelligent computing and Human-Computer Interaction (ICHCI), International Conference on

作者： Jiali Zhang Xiaoyan Qiao Yantai Key Laboratory of Big Data Modeling and Intelligent Computing Immersion Technology and Evaluation Shandong Engineering Research Center School of Computer Science and Technology Shandong Technology and Business University Yantai Shandong China Yantai Key Laboratory of Big Data Modeling and Intelligent Computing Immersion Technology and Evaluation Shandong Engineering Research Center School of Mathematics and Information Science Shandong Technology and Business University Yantai Shandong China

ISBN: (数字)9798350368284

ISBN: (纸本)9798350368291

Methods based on dynamically expanding architectures can effectively mitigate catastrophic forgetting in class incremental learning (CIL), but they often overlook information sharing and integration between subnetworks, leading to performance degradation and increased parameter count and memory consumption as the network expands. To address these complex issues, we introduce a new method called Task Separation and Knowledge Sharing (TSKS), which transfers knowledge at both the logical and feature levels through Hybrid Knowledge Distillation (HKD). In logical distillation, we combine Global Knowledge Distillation (GKD) and Task Knowledge Distillation (TKD) to establish connections between tasks. To prevent the model from favoring new classes, we design an Attention- Based Feature Fusion (ABFF) mechanism to capture important features. Additionally, we introduce a Soft-Margin Auxiliary Loss (SMAL) to help the model learn new concepts. Extensive experiments show that TSKS outperforms existing models on CIFAR100 and ImageNet100, regardless of whether memory samples are used. Notably, TSKS demonstrates superior performance in memory-free settings, indicating a reduced reliance on rehearsal memory.

关键词： Knowledge engineering Human computer interaction Degradation Incremental learning Computational modeling Memory management Information sharing Network architecture Feature extraction Knowledge transfer

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：