检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Cui, Yaodong Chen, Ren Chu, Wenbo Chen, Long Tian, Daxin Li, Ying Cao, Dongpu The Waterloo CogDrive Lab Department of Mechanical and Mechatronics Engineering University of Waterloo 200 University Ave West WaterlooONN2L3G1 Canada Research Institute Co. Ltd. Beijing100176 China School of Data and Computer Science Sun Yat-sen University Zhuhai519082 China Waytous Inc. Qingdao266109 China Beijing Advanced Innovation Center for Big Data and Brain Computing Beijing Key Laboratory for Cooperative Vehicle Infrastructure Systems and Safety Control School of Transportation Science and Engineering Beihang University Beijing100191 China

Autonomous vehicles were experiencing rapid development in the past few years. However, achieving full autonomy is not a trivial task, due to the nature of the complex and dynamic driving environment. Therefore, autonomous vehicles are equipped with a suite of different sensors to ensure robust, accurate environmental perception. In particular, the camera-LiDAR fusion is becoming an emerging research theme. However, so far there has been no critical review that focuses on deep-learning-based camera-LiDAR fusion methods. To bridge this gap and motivate future research, this paper devotes to review recent deep-learning-based data fusion approaches that leverage both image and point cloud. This review gives a brief overview of deep learning on image and point cloud data processing. Followed by in-depth reviews of camera-LiDAR fusion methods in depth completion, object detection, semantic segmentation, tracking and online cross-sensor calibration, which are organized based on their respective fusion levels. Furthermore, we compare these methods on publicly available datasets. Finally, we identified gaps and over-looked challenges between current academic researches and real-world applications. Based on these observations, we provide our insights and point out promising research directions. Copyright © 2020, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

The Minimum Information about CLinical Artificial Intelligence Checklist for Generative Modeling Research (MI-CLAIM-GEN)

arXiv

引用

arXiv 2024年

作者： Miao, Brenda Y. Chen, Irene Y. Williams, Christopher Y.K. Davidson, Jaysón Garcia-Agundez, Augusto Sun, Shenghuan Zack, Travis Saria, Suchi Arnaout, Rima Quer, Giorgio Sadaei, Hossein J. Torkamani, Ali Beaulieu-Jones, Brett Yu, Bin Gianfrancesco, Milena Butte, Atul J. Norgeot, Beau Sushil, Madhumita Bakar Computational Health Sciences Institute University of California San Francisco San FranciscoCA United States UCSF-UC Berkeley Joint Program in Computational Precision Health University of California Berkeley University of California San Francisco BerkeleyCA United States Department of Electrical Engineering and Computer Sciences University of California Berkeley BerkeleyCA United States Berkeley AI Research University of California Berkeley BerkeleyCA United States Department of Medicine Division of Rheumatology University of California San Francisco San FranciscoCA United States Helen Diller Family Comprehensive Cancer Center University of California San Francisco San FranciscoCA United States Center for Data-driven Insights and Innovation University of California Office of the President OaklandCA United States Bayesian Health New YorkNY10282 United States Department of Computer Science Johns Hopkins University Whiting School of Engineering BaltimoreMD United States Department of Health Policy & Management Johns Hopkins University Bloomberg School of Public Health BaltimoreMD United States Department of Medicine Johns Hopkins Medicine BaltimoreMD21205 United States Departments of Medicine Radiology and Pediatrics University of California San Francisco San FranciscoCA United States Scripps Research Translational Institute La Jolla CA United States Department of Integrative Structural and Computational Biology Scripps Research La Jolla CA92037 United States Department of Medicine University of Chicago ChicagoIL United States Department of Statistics University of California Berkeley BerkeleyCA United States Center for Computational Biology University of California Berkeley BerkeleyCA United States Qualified Health PBC Palo AltoCA United States

Recent advances in generative models, including large language models (LLMs), vision language models (VLMs), and diffusion models, have accelerated the field of natural language and image processing in medicine and marked a significant paradigm shift in how biomedical models can be developed and deployed. While these models are highly adaptable to new tasks, scaling and evaluating their usage presents new challenges not addressed in previous frameworks. In particular, the ability of these models to produce useful outputs with little to no specialized training data ("zero-" or "few-shot" approaches), as well as the open-ended nature of their outputs, necessitate the development of new guidelines for robust reporting of clinical generative model research. In response to gaps in standards and best practices for the development of clinical AI tools identified by US Executive Order 141103 and several emerging national networks for clinical AI evaluation, we begin to formalize some of these guidelines by building on the original MI-CLAIM checklist. The new checklist, MI-CLAIM-GEN (Table 1), aims to address differences in training, evaluation, interpretability, and reproducibility of new generative models compared to non-generative ("predictive") AI models. This MI-CLAIM-GEN checklist also seeks to clarify cohort selection reporting with unstructured clinical data and adds additional items on alignment with ethical standards for clinical AI research. © 2024, CC BY.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

A SURVEY OF AUTOMATIC GENERATION OF SOURCE CODE COMMENTS: ALGORITHMS AND TECHNIQUES

arXiv

引用

arXiv 2019年

作者： Song, Xiaotao Sun, Hailong Wang, Xu Yan, Jiafei School of Software Taiyuan University of Technology China SKLSDE Lab School of Computer Science and Engineering Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing China

As an integral part of source code files, code comments help improve program readability and comprehension. However, developers sometimes do not comment on their program code adequately due to the incurred extra efforts, lack of relevant knowledge, unawareness of the importance of code commenting or some other factors. As a result, code comments can be inadequate, absent or even mismatched with source code, which affects the understanding, reusing and the maintenance of software. To solve these problems of code comments, researchers have been concerned with generating code comments automatically. In this work, we aim at conducting a survey of automatic code commenting researches. First, we generally analyze the challenges and research framework of automatic generation of program comments. Second, we present the classification of representative algorithms, the design principles, strengths and weaknesses of each category of algorithms. Meanwhile, we also provide an overview of the quality assessment of the generated comments. Finally, we summarize some future directions for advancing the techniques of automatic generation of code comments and the quality assessment of comments. Copyright © 2019, The Authors. All rights reserved.

关键词： Surveys

来源：评论

学校读者我要写书评

暂无评论

Author Correction: Single-cell transcriptomics uncovers EGFR signaling-mediated gastric progenitor cell differentiation in stomach homeostasis

引用

Nature communications 2023年第1期14卷 6540页

作者： Hitomi Takada Yohei Sasagawa Mika Yoshimura Kaori Tanaka Yoshimi Iwayama Tetsutaro Hayashi Ayako Isomura-Matoba Itoshi Nikaido Akira Kurisaki Laboratory of Stem Cell Technologies Graduate School of Science and Technology Nara Institute of Science and Technology Takayama-cho Ikoma Nara Japan. Laboratory for Bioinformatics Research RIKEN Center for Biosystems Dynamics Research Wako Saitama Japan. Department of Functional Genome Informatics Biological Data Science Medical Research Institute Tokyo Medical and Dental University Bunkyo Tokyo Japan. Laboratory for Bioinformatics Research RIKEN Center for Biosystems Dynamics Research Wako Saitama Japan. itoshi.nikaido@riken.jp. Department of Functional Genome Informatics Biological Data Science Medical Research Institute Tokyo Medical and Dental University Bunkyo Tokyo Japan. itoshi.nikaido@riken.jp. Master's/Doctoral Program in Life Science Innovation (Bioinformatics) Degree Programs in Systems and Information Engineering Graduate School of Science and Technology University of Tsukuba Tsukuba Ibaraki Japan. itoshi.nikaido@riken.jp. Laboratory of Stem Cell Technologies Graduate School of Science and Technology Nara Institute of Science and Technology Takayama-cho Ikoma Nara Japan. akikuri@bs.naist.jp.

来源：评论

学校读者我要写书评

暂无评论

Time-varying formation control and disturbance rejection for UAV-UGV heterogeneous swarm system

引用

Hangkong Xuebao/Acta Aeronautica et Astronautica Sinica 2020年 41卷

作者： Zhou, Siquan Dong, Xiwang Li, Qingdong Ren, Zhang School of Automation Science and Electrical Engineering Beihang University Beijing100083 China Science and Technology on Aircraft Control Laboratory Beihang University Beijing100083 China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100083 China

This paper studies the time-varying formation control and disturbance rejection problems for heterogeneous UAV-UGV swarm system. The UAV-UGV swarm system is designed to achieve the desired time-varying output formation under unknown external disturbances. First, the kinetic and dynamic mathematical models of each UAV/UGV are established. In addition, the cooperative control models for heterogeneous swarm system are constructed by using the algebraic graph theory. Then, a distributed time-varying output formation controller is designed based on the internal model theory. The distributed formation center estimator and disturbance rejection compensator are designed and added to the formation controller. Third, an algorithm is presented to design the formation control parameters, where the feasibility conditions for achieving the time-varying output formation are given. The stability of the closed-loop UAV-UGV swarm system is proved. Finally, a simulation example is provided to demonstrate the effectiveness of the proposed formation control approach. © 2020, Beihang University Aerospace Knowledge Press. All right reserved.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Identification of Cognitive Dysfunction in Patients with T2DM Using Whole Brain Functional Connectivity

引用

Genomics, Proteomics & Bioinformatics 2019年第4期17卷 441-452页

作者： Zhenyu Liu Jiangang Liu Huijuan Yuan Taiyuan Liu Xingwei Cui Zhenchao Tang Yang Du Meiyun Wang Yusong Lin Jie Tian CAS Key Laboratory of Molecular Imaging Institute of AutomationChinese Academy of SciencesBeijing 100190China School of Computer and Information Technology Beijing Jiaotong UniversityBeijing 100044China Department of Endocrinology and Metabolism Henan Provincial People’s Hospital&the People’s Hospital of Zhengzhou UniversityZhengzhou 450003China Department of Radiology Henan Provincial People’s Hospital&the People’s Hospital of Zhengzhou UniversityZhengzhou 450003China Cooperative Innovation Center for Internet Healthcare&School of Software Zhengzhou UniversityZhengzhou 450003China School of Mechanical Electrical&Information EngineeringShandong University(Weihai)Weihai 264209China University of Chinese Academy of Sciences Beijing 100080China Beijing Advanced Innovation Center for Big Data-Based Precision Medicine School of MedicineBeihang UniversityBeijing 100191China Engineering Research Center of Molecular and Neuro Imaging of Ministry of Education School of Life Science and TechnologyXidian UniversityXi’an 710126China

Majority of type 2 diabetes mellitus(T2DM)patients are highly susceptible to several forms of cognitive impairments,particularly ***,the underlying neural mechanism of these cognitive impairments remains *** aimed to investigate the correlation between whole brain resting state functional connections(RSFCs)and the cognitive status in 95 patients with *** constructed an elastic net model to estimate the Montreal Cognitive Assessment(MoCA)scores,which served as an index of the cognitive status of the patients,and to select the RSFCs for further ***,we utilized a machine learning technique to evaluate the discriminative ability of the connectivity pattern associated with the selected *** estimated and chronological MoCA scores were significantly correlated with R=0.81 and the mean absolute error(MAE)=***,cognitive impairments of patients with T2DM can be identified using the RSFC pattern with classification accuracy of 90.54%and the area under the receiver operating characteristic(ROC)curve(AUC)of *** connectivity pattern not only included the connections between regions within the default mode network(DMN),but also the functional connectivity between the task-positive networks and the DMN,as well as those within the task-positive *** results suggest that an RSFC pattern could be regarded as a potential biomarker to identify the cognitive status of patients with T2DM.

关键词： Type 2 diabetes mellitus Resting state functional connectivity Elastic net Support vector machines MoCA

来源：评论

学校读者我要写书评

暂无评论

Workflow to Facilitate the Detection of New Psychoactive Substances and Drugs of Abuse in Influent Urban Wastewater

SSRN

引用

SSRN 2024年

作者： Bade, Richard van Herwerden, Denice Rousis, Nikolaos Adhikari, Sangeet Allen, Darren Baduel, Christine Bijlsma, Lubertus Boogaerts, Tim Burgard, Dan Chappell, Andrew Driver, Erin M. Sodre, Fernando Fabriz Fatta-Kassinos, Despo Gracia-Lor, Emma Gracia-Marín, Elisa Halden, Rolf U. Heath, Ester Jaunay, Emma Krotulski, Alex Lai, Foon Yin Löve, Arndís Sue Ching O’Brien, Jake W. Oh, Jeong-Eun Pasin, Daniel Castro, Marco Pineda Psichoudaki, Magda Salgueiro-Gonzalez, Noelia Gomes, Cezar Silvino Subedi, Bikram Thomas, Kevin V. Thomaidis, Nikolaos Wang, Degao Yargeau, Viviane Samanipour, Saer Mueller, Jochen The University of Queensland 20 Cornwall Street WoolloongabbaQLD4102 Australia University of Amsterdam Netherlands School of Sustainable Engineering and Built Environment Arizona State University TempeAZ85281 United States Biodesign Center for Environmental Health Engineering Biodesign Institute Arizona State University 1001 S. McAllister Ave. TempeAZ85281 United States Royal Brisbane and Women's Hospital HerstonQLD4029 Australia Grenoble France Environmental and Public Health Analytical Chemistry Research Institute for Pesticides and Water University Jaume I Avda Sos Baynat s/n CastellónE-12071 Spain Toxicological Centre Department of Pharmaceutical Sciences University of Antwerp Wilrijk2610 Belgium Department of Chemistry and Biochemistry University of Puget Sound TacomaWA98416 United States Christchurch Science Centre 27 Creyke Road Ilam Christchurch8041 New Zealand Institute of Chemistry University of Brasília DF Brasília70910-000 Brazil Nireas-International Water Research Centre Department of Civil and Environmental Engineering University of Cyprus P.O. Box 20537 Nicosia1678 Cyprus Department of Analytical Chemistry Faculty of Chemistry Complutense University of Madrid Avenida Complutense s/n Madrid28040 Spain OneWaterOneHealth Arizona State University Foundation 1001 S. McAllister Avenue TempeAZ85287-8101 United States Jožef Stefan Institute International Postgraduate School Jožef Stefan Jamova 39 Ljubljana1000 Slovenia Health and Biomedical Innovation UniSA: Clinical and Health Sciences University of South Australia AdelaideSA5001 Australia Center for Forensic Science Research and Education Fredric Rieders Family Foundation Willow GrovePA19090 United States UppsalaSE-75007 Sweden University of Iceland Department of Pharmacology and Toxicology Hofsvallagata 53 Reykjavik107 Iceland University of Iceland Faculty of Pharmaceutical Sciences Hofsvallagata 53 Reykjavik107 Iceland Department of Civil and Envir

The complexity around the dynamic markets for new psychoactive substances (NPS) forces researchers to develop and apply innovative analytical strategies to detect and identify them in influent urban wastewater. In this work a comprehensive suspect screening workflow following liquid chromatography – high resolution mass spectrometry analysis was established utilising the open-source InSpectra data processing platform and the HighResNPS library. In total, 278 urban influent wastewater samples from 47 sites in 16 countries were collected to investigate the presence of NPS and other drugs of abuse. A total of 50 compounds were detected in samples from at least one site. Most compounds found were prescription drugs such as gabapentin (detection frequency 79%), codeine (40%) and pregabalin (15%). However, cocaine was the most found illicit drug (83%), in all countries where samples were collected apart from the Republic of Korea and China. Eight NPS were also identified with this protocol: 3-methylmethcathinone 11%), eutylone (6%), etizolam (2%), 3-chloromethcathinone (4%), mitragynine (6%), phenibut (2%), 25I-NBOH (2%) and trimethoxyamphetamine (2%). The latter three have not previously been reported in municipal wastewater samples. The workflow employed allowed the prioritisation of features to be further investigated, reducing processing time and gaining in confidence in their identification. © 2024, The Authors. All rights reserved.

关键词： data handling

来源：评论

学校读者我要写书评

暂无评论

MemNetAR: Memory Network with Adversative Relation for Target-Level Sentiment Classification

MemNetAR: Memory Network with Adversative Relation for Targe...

引用

2019 IEEE Global Communications Conference (GLOBECOM)

作者： Yiwei Gao Jianwei Niu Xuefeng Liu Kaili Mao Shui Yu State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing China Beijing Advanced Innovation Center for Big Data and Brain Computing (BDBC) Beihang University Hangzhou Innovation Research Institute Beihang University School of Computer Science and Cyber Engineering Guangzhou University Guangdong China

ISBN: (数字)9781728109626

ISBN: (纸本)9781728109633

Target-level sentiment classification aims to identify the sentiment of multiple targets in a sentence. Although existing approaches based on neural network have achieved good performance in this task, we find that many approaches tend to give the same predictions for instances that have multiple targets, and this tendency can make a low accuracy for those instances that have different classes for different targets. Based on this observation, we propose MemNetAR, a memory network which can explicitly leverage the adversative relation among multiple targets in a sentence. Specifically, we add an adversative loss to the cross-entropy loss when there are adversative words between targets. The experimental results on public laptop and restaurant datasets prove that our model can improve 0.84% and 0.8% on total test dataset, and improve 2.97% and 2.68% on the dataset consisting of those instances with multiple targets but different classes by leveraging this new adversative information.

关键词： Task analysis Feature extraction Sentiment analysis Portable computers Machine learning Training Predictive models

来源：评论

学校读者我要写书评

暂无评论

Efficient Block Pruning Based on Kernel and Feature Stablization

Efficient Block Pruning Based on Kernel and Feature Stabliza...

引用

Proceedings of the Digital Image Computing: Technqiues and Applications (DICTA)

作者： Sheng Xu Hanlin Chen Kexin Liu Jinhu Lii Baochang Zhang School of Automatic Science and Electrical Engineering Beihang University China State Key Laboratory of Software Development Environment Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University China

With the development of computer vision research, the architecture of convolutional neural network becomes more and more complex to reach the state-of-the-art performance. Is the complexity of the model necessarily proportional to its accuracy? To answer this, the compression of the network has attracted much attention in the academy and industry. Existing network pruning methods mostly rely on the scoring mechanism of complexity or diversity of kernels to compress the network, and then build the network model after removing the kernels by tuning or training on the input data. These methods are cumbersome and depend on a well-trained pre-trained model. In this paper, we propose an end-to-end block pruning method based on kernel and feature stability by pruning blocks efficiently. To accomplish this, we firstly introduce a mask to scale the output of the blocks, and the L1 regularization term to monitor the mask update. Second, we introduce the center Loss to guarantee that the feature does not deviate greatly during learning. To converge fast, we introduce fast iterative shrinkage-thresholding algorithm (FISTA) to optimize the mask, by which a more fast and reliable pruning process is achieved. We implement experiments on different datasets, including CIFAR-10 and ImageNet ILSVRC2012. All the experiments have achieved the state-of-the-art accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An artificial intelligence system for predicting the deterioration of COVID-19 patients in the emergency department

arXiv

引用

arXiv 2020年

作者： Shamout, Farah E. Shen, Yiqiu Wu, Nan Kaku, Aakash Park, Jungkyu Makino, Taro Jastrzębski, Stanislaw Wang, Duo Zhang, Ben Dogra, Siddhant Cao, Meng Razavian, Narges Kudlowitz, David Azour, Lea Moore, William Lui, Yvonne W. Aphinyanaphongs, Yindalon Fernandez-Granda, Carlos Geras, Krzysztof J. Engineering Division NYU Abu Dhabi Center for Data Science New York University United States Sackler Institute of Graduate Biomedical Sciences NYU Grossman School of Medicine Department of Radiology NYU Langone Health Center for Advanced Imaging Innovation and Research NYU Langone Health Department of Population Health NYU Langone Health Department of Medicine NYU Langone Health Department of Mathematics Courant Institute New York University United States

During the COVID-19 pandemic, rapid and accurate triage of patients at the emergency department is critical to inform decision-making. We propose a data-driven approach for automatic prediction of deterioration risk using a deep neural network that learns from chest X-ray images, and a gradient boosting model that learns from routine clinical variables. Our AI prognosis system, trained using data from 3,661 patients, achieves an AUC of 0.786 (95% CI: 0.742-0.827) when predicting deterioration within 96 hours. The deep neural network extracts informative areas of chest X-ray images to assist clinicians in interpreting the predictions, and performs comparably to two radiologists in a reader study. In order to verify performance in a real clinical setting, we silently deployed a preliminary version of the deep neural network at NYU Langone Health during the first wave of the pandemic, which produced accurate predictions in real-time. In summary, our findings demonstrate the potential of the proposed system for assisting front-line physicians in the triage of COVID-19 patients. Copyright © 2020, The Authors. All rights reserved.

关键词： Deterioration

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：