检索结果-内蒙古大学图书馆

SSRN 2022年

作者： Zhao, Zhonghui Chu, Jie Xu, Xiaohui Cao, Yanwen Schikowski, Tamara Geng, Mengjie Chen, Gongbo Bai, Guannan Hu, Kejia Xia, Jingjing Ma, Wei Liu, Qiyong Lu, Zilong Guo, Xiaolei Zhao, Qi Department of Epidemiology School of Public Health Shandong University Jinan250012 China Shandong University Climate Change and Health Center Jinan250012 China Shandong Center for Disease Control and Prevention Jinan250014 China Academy of Preventive Medicine Shandong University Jinan250014 China Department of Epidemiology IUF-Leibniz Research Institute for Environmental Medicine Düsseldorf Germany Chinese Center for Disease Control and Prevention Beijing102206 China Department of Occupational and Environmental Health School of Public Health Sun Yat-sen University Guangdong Guangzhou510080 China Department of Child Health Care The Children’s Hospital National Clinical Research Center for Child Health Zhejiang University School of Medicine China Department of Big Data in Health Science School of Public Health Zhejiang University Zijingang Campus Hangzhou310058 China School of Life Sciences Fudan University China

An increasing number of studies report the modification of air pollution such as particulate matter (PMs) on the association between cold temperature and health. However, it remains uncertain whether the modifying effect may vary by size of PMs. This study aimed to examine various interactive effects of cold exposure and ambient PMs with diameters ≤1/2.5/10 µm (PM 1/2.5/10 ) on premature deaths in Shandong Province, China. In the 2013-2018 cold seasons (November-February), data on daily mortality, PM 1/2.5/10, and weather were collected from the 1822 sub-districts of Shandong Province. A time-stratified case-crossover study design was performed to quantify the cumulative association between ambient cold and mortality over a lag of 0-12 days, with a linear interactive term between temperature and PM 1/2.5/10 . The extreme cold effect was defined as the cumulative odds ratio (OR) at the 1.0 th percentile of the temperature range compared to the minimum mortality temperature (MMT). We found that the mortality risk increased with ambient temperature decline, with the MMT located at 18.5 °C and the cumulative OR of extreme cold (-16.9°C) being 1.83 (95% CI: 1.66, 2.02). The cold-related mortality risk increased on days with higher PMs, with a smaller size of PM showing greater additive effect. For example, for each 60μg/m 3 increase in PM 1/2.5/10 , the extreme cold effect (i.e. cumulative OR) was 1.67 (95% CI: 1.14, 2.43), 1.19(95% CI: 0.99, 1.44), and 1.50(95% CI: 1.23, 1.83), respectively. The modifying effect of PMs also varied by population subgroups, which was stronger in the elderly aged over 75 years and individuals with middle school education and below. © 2022, The Authors. All rights reserved.

关键词： Cold effects

来源：评论

学校读者我要写书评

暂无评论

Benchmarking in Optimization: Best Practice and Open Issues

arXiv

引用

arXiv 2020年

作者： Bartz-Beielstein, Thomas Doerr, Carola Bossek, Jakob Chandrasekaran, Sowmya Eftimov, Tome Fischbach, Andreas Kerschke, Pascal López-Ibáñez, Manuel Malan, Katherine M. Moore, Jason H. Naujoks, Boris Orzechowski, Patryk Volz, Vanessa Wagner, Markus Weise, Thomas Institute for Data Science Engineering and Analytics TH Köln Germany Sorbonne Université CNRS LIP6 Paris France Optimisation and Logistics School of Computer Science University of Adelaide Adelaide Australia Computer Systems Department Jožef Stefan Institute Ljubljana Slovenia Statistics and Optimization Group University of Münster Münster Germany School of Computer Science and Engineering University of Málaga Málaga Spain Department of Decision Sciences University of South Africa Pretoria South Africa Institute for Biomedical Informatics University of Pennsylvania PhiladelphiaPA United States Department of Automatics AGH University of Science and Technology Krakow Poland modl.ai Copenhagen Denmark Institute of Applied Optimization School of Artificial Intelligence and Big Data Hefei University Hefei China

This survey compiles ideas and recommendations from more than a dozen researchers with different backgrounds and from different institutes around the world. Promoting best practice in benchmarking is its main goal. The article discusses eight essential topics in benchmarking: clearly stated goals, well-specified problems, suitable algorithms, adequate performance measures, thoughtful analysis, effective and efficient designs, comprehensible presentations, and guaranteed reproducibility. The final goal is to provide well-accepted guidelines (rules) that might be useful for authors and reviewers. As benchmarking in optimization is an active and evolving field of research this manuscript is meant to co-evolve over time by means of periodic *** Codes 68W50. Copyright © 2020, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MRI-based multimodal AI model enables prediction of recurrence risk and adjuvant therapy in breast cancer

引用

Pharmacological Research 2025年 216卷 107765页

作者： Yu, Yunfang Ren, Wei Mao, Luhui Ouyang, Wenhao Hu, Qiugen Yao, Qinyue Tan, Yujie He, Zifan Ban, Xiaohua Hu, Huijun Lin, Ruichong Wang, Zehua Chen, Yongjian Wu, Zhuo Chen, Kai Ouyang, Jie Li, Tang Zhang, Zebang Liu, Guoying Chen, Xiuxing Li, Zhuo Duan, Xiaohui Wang, Jin Yao, Herui Guangdong Provincial Key Laboratory of Malignant Tumor Epigenetics and Gene Regulation Guangdong-Hong Kong Joint Laboratory for RNA Medicine Department of Medical Oncology Breast Tumor Centre Phase I Clinical Trial Centre Sun Yat-sen Memorial Hospital Sun Yat-sen University Guangzhou China Guangdong Provincial Key Laboratory of Cancer Pathogenesis and Precision Diagnosis and Treatment Joint Big Data Laboratory Department of Medical Oncology Shenshan Medical Center Memorial Hospital of Sun Yat-sen University Shanwei China Institute for AI in Medicine and faculty of Medicine Macau University of Science and Technology Macao Taipa China Department of Breast Surgery The First Affiliated Hospital Jinan University Guangzhou China Department of Radiology Shunde Hospital Southern Medical University Foshan China Cells Vision (Guangzhou) Medical Technology Inc Guangzhou China Imaging Diagnostic and Interventional Center Sun Yat-sen University Cancer Center State Key Laboratory of Oncology in South China Collaborative Innovation Center for Cancer Medicine Guangzhou China Department of Radiology Sun Yat-sen Memorial Hospital Sun Yat-sen University Guangzhou China Faculty of Innovation Engineering Macau University of Science and Technology Macao Taipa China UMedEVO and UMedREVO Artificial Intelligence Technology (Guangzhou) Co. Ltd Dermatology and Venereology Division Department of Medicine Solna Center for Molecular Medicine Karolinska Institutet Stockholm Sweden Department of Breast Surgery Tungwah Hospital Dongguan China

Timely intervention and improved prognosis for breast cancer patients rely on early metastasis risk detection and accurate treatment predictions. This study introduces an advanced multimodal MRI and AI-driven 3D deep learning model, termed the 3D-MMR-model, designed to predict recurrence risk in non-metastatic breast cancer patients. We conducted a multicenter study involving 1199 non-metastatic breast cancer patients from four institutions in China, with comprehensive MRI and clinical data retrospectively collected. Our model employed multimodal-data fusion, utilizing contrast-enhanced T1-weighted imaging (T1 + C) and T2-weighted imaging (T2WI) volumes, processed through a modified 3D-UNet for tumor segmentation and a DenseNet121-based architecture for disease-free survival (DFS) prediction. Additionally, we performed RNA-seq analysis to delve further into the relationship between concentrated hotspots within the tumor region and the tumor microenvironment. The 3D-MR-model demonstrated superior predictive performance, with time-dependent ROC analysis yielding AUC values of 0.90, 0.89, and 0.88 for 2-, 3-, and 4-year DFS predictions, respectively, in the training cohort. External validation cohorts corroborated these findings, highlighting the model's robustness across diverse clinical settings. Integration of clinicopathological features further enhanced the model's accuracy, with a multimodal approach significantly improving risk stratification and decision-making in clinical practice. Visualization techniques provided insights into the decision-making process, correlating predictions with tumor microenvironment characteristics. In summary, the 3D-MMR-model represents a significant advancement in breast cancer prognosis, combining cutting-edge AI technology with multimodal imaging to deliver precise and clinically relevant predictions of recurrence risk. This innovative approach holds promise for enhancing patient outcomes and guiding individualized treatment plan

关键词： Breast cancer Deep learning Magnetic resonance imaging Multimodal data fusion Postoperative risk stratification

来源：评论

学校读者我要写书评

暂无评论

PathoGraph: A Graph-Based Method for Standardized Representation of Pathology Knowledge

引用

Scientific data 2025年第1期12卷 872页

作者： Peiliang Lou Yuxin Dong Caixia Ding Chunbao Wang Ruifeng Guo XiaoBo Pang Chen Wang Chen Li School of Computer Science and Technology Xi'an Jiaotong University Xi'an Shaanxi 710049 China. Division of Computational Biology Mayo Clinic Rochester MN USA. Department of Pathology Shaanxi Provincial Tumor Hospital Xi'an Jiaotong University 309 Yanta West Road Xi'an Shaanxi China. Department of Pathology The First Affiliated Hospital of Xi'an Jiaotong University 277 West Yanta Road Xi'an Shaanxi China. Division of Anatomic Pathology Department of Laboratory Medicine and Pathology Mayo Clinic Jacksonville Florida USA. Division of Computational Biology Mayo Clinic Rochester MN USA. wang.chen@mayo.edu. National Engineering Lab for Big Data Analytics Xi'an Jiaotong University Xi'an Shaanxi China. cli@***.

Pathology data, primarily consisting of slides and diagnostic reports, inherently contain knowledge that is pivotal for advancing data-driven biomedical research and clinical practice. However, the hidden and fragmented nature of this knowledge across various data modalities not only hinders its computational utilization, but also impedes the effective integration of AI technologies within the domain of pathology. To systematically organize pathology knowledge for its computational use, we propose PathoGraph, a knowledge representation method that describes pathology knowledge in a graph-based format. PathoGraph can represent: (1) pathological entities' types and morphological features; (2) the composition, spatial arrangements, and dynamic behaviors associated with pathological phenotypes; and (3) the differential diagnostic approaches used by pathologists. By applying PathoGraph to neoplastic diseases, we illustrate its ability to comprehensively and structurally capture multi-scale disease characteristics alongside pathologists' expertise. Furthermore, we validate its computational utility by demonstrating the feasibility of large-scale automated PathoGraph construction, showing performance improvements in downstream deep learning tasks, and presenting two illustrative use cases that highlight its clinical potential. We believe PathoGraph opens new avenues for AI-driven advances in the field of pathology.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Domain Knowledge Guided Deep Learning with Electronic Health Records

Domain Knowledge Guided Deep Learning with Electronic Health...

引用

IEEE International Conference on data Mining (ICDM)

作者： Changchang Yin Rongjian Zhao Buyue Qian Xin Lv Ping Zhang School of Computer Science and Technology Xi’an Jiaotong University Xi’an China National Engineering Lab for Big Data Analytics Xi’an Jiaotong University Xi’an China The Ohio State University Columbus Ohio USA

Due to their promising performance in clinical risk prediction with Electronic Health Records (EHRs), deep learning methods have attracted significant interest from healthcare researchers. However, there are 4 challenges: (i) data insufficiency. Many methods require large amounts of training data to achieve satisfactory results. (ii) Interpretability. Results from many methods are hard to explain to clinicians (e.g., why the models make particular predictions and which events cause clinical outcomes). (iii) Domain knowledge integration. No existing method dynamically exploits complicated medical knowledge (e.g., relations such as cause and is-caused-by between clinical events). (iv) Time interval information. Most existing methods only consider the relative order of visits from EHRs, but ignore the irregular time intervals between neighboring visits. In the study, we propose a new model, Domain Knowledge Guided Recurrent Neural Networks (DG-RNN), by directly introducing domain knowledge from the medical knowledge graph into an RNN architecture, as well as taking the irregular time intervals into account. Experimental results on heart failure risk prediction tasks show that our model not only outperforms state-of-the-art deep-learning based risk prediction models, but also associates individual medical events with heart failure onset, thus paving the way for interpretable accurate clinical risk predictions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Adaptive gradient methods with dynamic bound of learning rate

arXiv

引用

arXiv 2019年

作者： Luo, Liangchen Xiong, Yuanhao Liu, Yan Sun, Xu MOE Key Lab of Computational Linguistics School of EECS Peking University College of Information Science and Electronic Engineering Zhejiang University Department of Computer Science University of Southern California Center for Data Science Beijing Institute of Big Data Research Peking University

Adaptive optimization methods such as ADAGRAD, RMSPROP and ADAM have been proposed to achieve a rapid training process with an element-wise scaling term on learning rates. Though prevailing, they are observed to generalize poorly compared with SGD or even fail to converge due to unstable and extreme learning rates. Recent work has put forward some algorithms such as AMSGRAD to tackle this issue but they failed to achieve considerable improvement over existing methods. In our paper, we demonstrate that extreme learning rates can lead to poor performance. We provide new variants of ADAM and AMSGRAD, called ADABOUND and AMSBOUND respectively, which employ dynamic bounds on learning rates to achieve a gradual and smooth transition from adaptive methods to SGD and give a theoretical proof of convergence. We further conduct experiments on various popular tasks and models, which is often insufficient in previous work. Experimental results show that new variants can eliminate the generalization gap between adaptive methods and SGD and maintain higher learning speed early in training at the same time. Moreover, they can bring significant improvement over their prototypes, especially on complex deep networks. The implementation of the algorithm can be found at https://***/Luolc/AdaBound. Copyright © 2019, The Authors. All rights reserved.

关键词： Gradient methods

来源：评论

学校读者我要写书评

暂无评论

Gated recurrent neural network approach for multilabel emotion detection in microblogs

arXiv

引用

arXiv 2019年

作者： Rathnayaka, Prabod Abeysinghe, Supun Samarajeewa, Chamod Manchanayake, Isura Walpola, Malaka J. Nawaratne, Rashmika Bandaragoda, Tharindu Alahakoon, Damminda Department of Computer Science and Engineering University of Moratuwa Sri Lanka Sri Lanka Research Centre for Data Analytics and Cognition La Trobe University Victoria

People express their opinions and emotions freely in social media posts and online reviews that contain valuable feedback for multiple stakeholders such as businesses and political campaigns. Manually extracting opinions and emotions from large volumes of such posts is an impossible task. Therefore, automated processing of these posts to extract opinions and emotions is an important research problem. However, human emotion detection is a challenging task due to the complexity and nuanced nature. To overcome these barriers, researchers have extensively used techniques such as deep learning, distant supervision, and transfer learning. In this paper, we propose a novel Pyramid Attention Network (PAN) based model for emotion detection in microblogs. The main advantage of our approach is that PAN has the capability to evaluate sentences in different perspectives to capture multiple emotions existing in a single text. The proposed model was evaluated on a recently released dataset and the results achieved the state-of-the-art accuracy of 58.9%. Copyright © 2019, The Authors. All rights reserved.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Emergence and Dynamics of Regional Species Pools

引用

Global Ecology and Biogeography 2025年第5期34卷

作者： Jarzyna, Marta A. Ohyama, Leo Economo, Evan P. Gill, Jacquelyn L. Mascarenhas, Rilquer Okie, Jordan G. Qin, Clara Rabosky, Daniel L. Staniczenko, Phillip P. A. Hickerson, Michael J. Gillespie, Rosemary G. McGill, Brian J. Department of Evolution Ecology and Organismal Biology The Ohio State University Columbus OH United States Translational Data Analytics Institute The Ohio State University Columbus OH United States Institute for Global Change Biology University of Michigan Ann Arbor MI United States Biodiversity Institute University of Florida Gainesville FL United States Biodiversity and Biocomplexity Unit Okinawa Institute of Science and Technology Graduate University Okinawa Japan School of Biology and Ecology University of Maine Orono ME United States Climate Change Institute University of Maine Orono ME United States Department of Biology The City College of New York New York NY United States Graduate Center City University of New York New York NY United States School of Earth and Space Exploration Arizona State University Tempe AZ United States Department of Environmental Studies University of California Santa Cruz Santa Cruz CA United States Society for the Protection of Underground Networks Dover DE United States Department of Ecology and Evolutionary Biology University of Michigan Ann Arbor MI United States Department of Biology Brooklyn College City University of New York Brooklyn NY United States Division of Invertebrate Zoology American Museum of Natural History New York NY United States Department of Environmental Science Policy and Management University of California Berkeley Berkeley CA United States Mitchell Center for Sustainability Solutions University of Maine Orono ME United States

The Importance of the Regional Species Pool: The regional species pool—the set of species capable of entering a local community—is a foundational concept for understanding ecological processes that occur between local and extensive (biogeographic) spatial scales. However, the lack of precise definitions for the regional species pool, coupled with limited research into the dynamics of regional biodiversity, has impeded the development of a comprehensive framework to explain the mechanisms shaping these pools. Processes Governing Regional Species Pools: Although ecological processes at local and extensive scales are relatively well understood, the mechanisms shaping regional biota remain less clear. Regional species pools are likely shaped by a unique set of processes that often overlap minimally with those operating at local or extensive scales. Despite their significance, our understanding of the specific mechanisms driving the dynamics of regional species pools remains incomplete. The Need for a Theory of Regional Species Pools: We argue that it is essential to prioritise the study of the regional species pool for two reasons. First, the regional species pool bridges spatial and temporal scales from ecological dynamics in landscapes to the long-term processes shaping the biotas of entire biogeographic provinces. As such, understanding the dynamics of species pools addresses fundamental questions about the origin, maintenance, and dynamics of biodiversity. Second, effective biodiversity conservation in the Anthropocene hinges on understanding the processes that operate at regional scales. © 2025 The Author(s). Global Ecology and Biogeography published by John Wiley & Sons Ltd.

关键词： biotic interactions colonisation demographic stochasticity dispersal diversification environmental filtering environmental stochasticity local community regional species pool speciation

来源：评论

学校读者我要写书评

暂无评论

One single deep bidirectional LSTM network for word sense disambiguation of text data 31st

One single deep bidirectional LSTM network for word sense di...

引用

31st Canadian Conference on Artificial Intelligence, Canadian AI 2018

作者： Pesaranghader, Ahmad Pesaranghader, Ali Matwin, Stan Sokolova, Marina Institute for Big Data Analytics Dalhousie University Halifax Canada School of Computer Science University of Ottawa Ottawa Canada School of Epidemiology and Public Health University of Ottawa Ottawa Canada

ISBN: (纸本)9783319896557

Due to recent technical and scientific advances, we have a wealth of information hidden in unstructured text data such as offline/online narratives, research articles, and clinical reports. To mine these data properly, attributable to their innate ambiguity, a Word Sense Disambiguation (WSD) algorithm can avoid numbers of difficulties in Natural Language Processing (NLP) pipeline. However, considering a large number of ambiguous words in one language or technical domain, we may encounter limiting constraints for proper deployment of existing WSD models. This paper attempts to address the problem of one-classifier-per-one-word WSD algorithms by proposing a single Bidirectional Long Short-Term Memory (BLSTM) network which by considering senses and context sequences works on all ambiguous words collectively. Evaluated on SensEval-3 benchmark, we show the result of our model is comparable with top-performing WSD algorithms. We also discuss how applying additional modifications alleviates the model fault and the need for more training data. © Springer International Publishing AG, part of Springer Nature 2018.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

TV White Space Spectrum Analysis Based on Machine Learning

引用

Journal of Communications and Information Networks 2019年第2期4卷 68-80页

作者： Yuan Ma Yue Gao Chen Fu Wenge Rong Zhang Xiong Shuguang Cui College of Information Engineering Shenzhen UniversityShenzhen 518060China School of Electronic Engineering and Computer Science Queen Mary University of LondonLondon E14NSUnited Kingdom School of Computer Science and Engineering Beihang UniversityBeijing 100191China Shenzhen Research Institute of Big Data and School of Science and Engineering the Chinese University of Hong KongShenzhenChina Department of Electrical and Computer Engineering University of CaliforniaDavisCA95616

Exploration of TV white space(TVWS)is a promising solution to mitigate the spectrum shortage and provide opportunities for new *** this paper,we present a detailed analysis of spectrum utilisation over TVWS at different locations in *** short-term and long-term outdoor measurement campaigns are conducted over large scales to better understand the spectrum features and variations across multiple locations and time *** from most fixed-location-only measurements,we also drive along the main streets of London with a portable moving node to measure the on-route spectrum density along with the corresponding geographical information,which allows us to study the features and variations of spectrum use through a continuous *** better analyse the dynamic spectrum utilisation,a machine learning based analysis algorithm is developed over the real-world *** approach allows us to characterise the similarity and variability in spectrum usage within and among different channels,locations,and time instances,which is critical for the secondary system deployment to efficiently exploit the white space.

关键词： TV white space spectrum utilisation features RFeye node self organising mapping machine learning

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：