检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Hou, Wenzheng Xu, Qianqian Yang, Zhiyong Bao, Shilong He, Yuan Huang, Qingming Key Laboratory of Intelligent Information Processing Institute of Computing Technology CAS Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China State Key Laboratory of Information Security Institute of Information Engineering CAS Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Alibaba Group Beijing China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China Artificial Intelligence Research Center Peng Cheng Laboratory Shenzhen China

It is well-known that deep learning models are vulnerable to adversarial examples. Existing studies of adversarial training have made great progress against this challenge. As a typical trait, they often assume that the class distribution is overall balanced. However, long-tail datasets are ubiquitous in a wide spectrum of applications, where the amount of head class instances is larger than the tail classes. Under such a scenario, AUC is a much more reasonable metric than accuracy since it is insensitive toward class distribution. Motivated by this, we present an early trial to explore adversarial training methods to optimize AUC. The main challenge lies in that the positive and negative examples are tightly coupled in the objective function. As a direct result, one cannot generate adversarial examples without a full scan of the dataset. To address this issue, based on a concavity regularization scheme, we reformulate the AUC optimization problem as a saddle point problem, where the objective becomes an instance-wise function. This leads to an end-to-end training protocol. Furthermore, we provide a convergence guarantee of the proposed algorithm. Our analysis differs from the existing studies since the algorithm is asked to generate adversarial examples by calculating the gradient of a min-max problem. Finally, the extensive experimental results show the performance and robustness of our algorithm in three long-tail datasets. © 2022, CC BY.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Spectrometric Characterization of Suspension Liquid and Light Extinction Model Update

SSRN

引用

SSRN 2022年

作者： Liu, Sheng Shen, Yang Gao, Zihui Gao, Hongwen School of Computer Science and Technology Huaibei Normal University Huaibei235000 China State Key Laboratory of Enviromental Pollution Control and Resource Reuse Tongji University Shanghai200092 China Shanghai GreenEmpire Environmental Science and Technology Corporation Shanghai200092 China Anhui Engineering Research Center for Intelligent Computing and Application on Cognitive Behavior Huaibei235000 China

On the basis of the classical light scattering models, the light extinction model is the first to establish as [[EQUATION]] (, N and γ – average diameter in μm, number and relative refractive index of the suspending particles, λ , A and δ – incident light wavelength in μm, absorbance and optical path in cm of the suspension liquid) by spectrometric characterization of ten standard suspension liquids. It has been used to determine the suspending particles in the calcium oxalate, Formazine, soil, milk and sewage suspension water samples. As the result, the light extinction model method brought out less than 12% error of and 18% error of the suspending particles’ quality by comparing with the conventional methods. It provides a simple and reliable spectroptometric determination of a suspension liquid. Also, it is very potential to in-situ monitor the growth and working state of the suspending particles using in synthesis of materials, culture of cells, treatment of wastewater and safety of drinking water and foods. © 2022, The Authors. All rights reserved.

关键词： Suspensions (fluids)

来源：评论

学校读者我要写书评

暂无评论

RCGA-Net: An Improved Multi-hybrid Attention Mechanism Network in Biomedical Image Segmentation

RCGA-Net: An Improved Multi-hybrid Attention Mechanism Netwo...

引用

2021 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2021

作者： Xiao, Feng Shen, Cong Chen, Yu Yang, Tian Chen, Shengyong Liao, Zhijun Tang, Jijun Tianjin University of Technology School of Computer Science and Engineering Tianjin China Engineering Research Center of Learning-Based Intelligent System Ministry of Education Tianjin China School of Basic Medical Sciences Fujian Medical University Fujian Fuzhou China College of Intelligence and Computing Tianjin University Tianjin China Key Laboratory of Systems Bioengineering Ministry of Education Tianjin China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Guangdong Shenzhen China Department of Computer Science and Engineering University of South Carolina ColumbiaSC United States

ISBN: (纸本)9781665401265

Drawing support from an effective Medical Image Segmentation (MIS) is conducive to a substantial diagnostic basis for the physicians to identify the focus lesion in the patient body and give the subsequent clinical assessment of the patient status. Although various works have tried the challenging quantitative analysis problem, it is still difficult to conduct precise automatic segmentation, especially the soft tissue organs. In this decade, with the increased amount of available datasets, deep learning-based networks have achieved remarkable performance in image processing. Inspired by the state-of-the-art deep learning works, in this paper, we propose an end-to-end multi-layer network named RCGA-Net. It consists of an encoder-decoder backbone that integrates a coordinate attention mechanism based on space and channel and a global context extraction module to highlight more valuable information. To evaluate the performance of RCGA-Net, we apply it to different kinds of clinical and experimental MIS tasks to testify its generalization ability. Extensive experiments represent that our schema has taken the outperform or compatible results among the comparison methods group. Specifically, the numeric result of RCGA-Net on the pulmonary dataset has achieved a 99.12% optimum F1-score. © 2021 IEEE.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Progressive Dual Priori Network for Generalized Breast Tumor Segmentation

arXiv

引用

arXiv 2023年

作者： Wang, Li Wang, Lihui Kuai, Zixiang Tang, Lei Ou, Yingfeng Ye, Chen Zhu, Yuemin Wu, Min Shi, Tianliang Engineering Research Center of Text Computing & Cognitive Intelligence Ministry of Education Key Laboratory of Intelligent Medical Image Analysis and Precise Diagnosis of Guizhou Province State Key Laboratory of Public Big Data College of Computer Science and Technology Guizhou University Guiyang550025 China Imaging Center Harbin Medical University Cancer Hospital Harbin150081 China Radiology Department Guizhou Provincial People’s Hospital Guiyang550002 China Radiology Department Tongren People’s Hospital Tongren554300 China Univ Lyon INSA Lyon CNRS Inserm CREATIS UMR 5220 U1206 LyonF-69621 France

To promote the generalization ability of breast tumor segmentation models, as well as to improve the segmentation performance for breast tumors with smaller size, low-contrast and irregular shape, we propose a progressive dual priori network (PDPNet) to segment breast tumors from dynamic enhanced magnetic resonance images (DCE-MRI) acquired at different centers. The PDPNet first cropped tumor regions with a coarse-segmentation based localization module, then the breast tumor mask was progressively refined by using the weak semantic priori and cross-scale correlation prior knowledge. To validate the effectiveness of PDPNet, we compared it with several state-of-the-art methods on multi-center datasets. The results showed that, comparing against the suboptimal method, the DSC and HD95 of PDPNet were improved at least by 5.13% and 7.58% respectively on multi-center test sets. In addition, through ablations, we demonstrated that the proposed localization module can decrease the influence of normal tissues and therefore improve the generalization ability of the model. The weak semantic priors allow focusing on tumor regions to avoid missing small tumors and low-contrast tumors. The cross-scale correlation priors are beneficial for promoting the shape-aware ability for irregular tumors. Thus integrating them in a unified framework improved the multicenter breast tumor segmentation performance. The source code and open data can be accessed at https://github. com/wangli100209/PDPNet. Copyright © 2023, The Authors. All rights reserved.

关键词： Magnetic resonance

来源：评论

学校读者我要写书评

暂无评论

Aligning Recommendation and Conversation via Dual Imitation

arXiv

引用

arXiv 2022年

作者： Zhou, Jinfeng Wang, Bo Huang, Minlie Zhao, Dongming Huang, Kun He, Ruifang Hou, Yuexian College of Intelligence and Computing Tianjin University Tianjin China State Key Laboratory of Communication Content Cognition People’s Daily Online Beijing China The CoAI Group DCST Institute for Artificial Intelligence State Key Lab of Intelligent Technology and Systems Beijing National Research Center for Information Science and Technology Tsinghua University Beijing100084 China AI Lab China Mobile Communication Group Tianjin Co. Ltd. China

Human conversations of recommendation naturally involve the shift of interests which can align the recommendation actions and conversation process to make accurate recommendations with rich explanations. However, existing conversational recommendation systems (CRS) ignore the advantage of user interest shift in connecting recommendation and conversation, which leads to an ineffective loose coupling structure of CRS. To address this issue, by modeling the recommendation actions as recommendation paths in a knowledge graph (KG), we propose DICR (Dual Imitation for Conversational Recommendation), which designs a dual imitation to explicitly align the recommendation paths and user interest shift paths in a recommendation module and a conversation module, respectively. By exchanging alignment signals, DICR achieves bidirectional promotion between recommendation and conversation modules and generates high-quality responses with accurate recommendations and coherent explanations. Experiments demonstrate that DICR outperforms the state-of-the-art models on recommendation and conversation performance with automatic, human, and novel explainability metrics. © 2022, CC BY.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Large language models for diabetes training:a prospective study

引用

Science Bulletin 2025年第6期70卷 934-942页

作者： Haoxuan Li Zehua Jiang Zhouyu Guan Yuqian Bao Yuexing Liu Tingting Hu Jiajia Li Ruhan Liu Liang Wu Di Cheng Hongwei Ji Yong Wang Ya-Xing Wang Carol Y.Cheung Yingfeng Zheng Jihong Wang Zhen Li Weibing Wu Cynthia Ciwei Lim Yong Mong Bee Hong Chang Tan Elif I.Ekinci David C.Klonoff Justin B.Echouffo-Tcheugui Nestoras Mathioudakis Leonor Corsino Rafael Simó Charumathi Sabanayagam Gavin Siew Wei Tan Ching-Yu Cheng Tien Yin Wong Huating Li Chun Cai Lijuan Mao Lee-Ling Lim Yih-Chung Tham Bin Sheng Weiping Jia Shanghai University of Sport Shanghai 200438China School of Clinical Medicine Beijing Tsinghua Changgung HospitalTsinghua MedicineTsinghua UniversityBeijing 100084China Beijing Visual Science and Translational Eye Research Institute(BERI) Tsinghua MedicineTsinghua UniversityBeijing 100084China Shanghai Belt and Road International Joint Laboratory of Intelligent Prevention and Treatment for Metabolic Diseases Department of Computer Science and EngineeringSchool of ElectronicInformationand Electrical EngineeringShanghai Jiao Tong UniversityDepartment of Endocrinology and MetabolismShanghai Sixth People’s Hospital Affiliated to Shanghai Jiao Tong University School of MedicineShanghai Diabetes InstituteShanghai Clinical Center for DiabetesShanghai 200240China MoE Key Lab of Artificial Intelligence Artificial Intelligence InstituteShanghai Jiao Tong UniversityShanghai 200240China Department of Cardiology the Affiliated Hospital of Qingdao UniversityQingdao 266011China CEMS NCMISHCMSMADISAcademy of Mathematics and Systems ScienceChinese Academy of SciencesBeijing 100190China School of Mathematics University of Chinese Academy of SciencesChinese Academy of SciencesBeijing 100049China Key Laboratory of Systems Health Science of Zhejiang Province School of Life ScienceHangzhou Institute for Advanced StudyUniversity of Chinese Academy of SciencesHangzhou 310024China Beijing Institute of Ophthalmology Beijing Tongren HospitalCapital Medical UniversityBeijing Ophthalmology and Visual Sciences Key LaboratoryBeijing 100730China k.Department of Ophthalmology and Visual Sciences The Chinese University of Hong KongHong Kong 999077China State Key Laboratory of Ophthalmology Zhongshan Ophthalmic CenterSun Yat-sen UniversityGuangdong Provincial Key Laboratory of Ophthalmology and Visual ScienceGuangdong Provincial Clinical Research Center for Ocular DiseasesGuangzhou 510060China Department of Renal Medicine Singapore General HospitalSingHealth-Duke Academic Medical CentreSingapore169

Diabetes poses a considerable global health challenge,with varying levels of diabetes knowledge among healthcare professionals,highlighting the importance of diabetes *** Language Models(LLMs)provide new insights into diabetes training,but their performance in diabetes-related queries remains uncertain,especially outside the English language like *** first evaluated the performance of ten LLMs:ChatGPT-3.5,ChatGPT-4.0,Google Bard,LlaMA-7B,LlaMA2-7B,Baidu ERNIE Bot,Ali Tongyi Qianwen,MedGPT,HuatuoGPT,and Chinese LlaMA2-7B on diabetes-related queries,based on the Chinese National Certificate Examination for Primary Diabetes Care in China(NCE-CPDC)and the English Specialty Certificate Examination in Endocrinology and Diabetes of Membership of the Royal College of Physicians of the United ***,we assessed the training of primary care physicians(PCPs)without and with the assistance of ChatGPT-4.0 in the NCE-CPDC examination to ascertain the reliability of LLMs as medical *** found that ChatGPT-4.0 outperformed other LLMs in the English examination,achieving a passing accuracy of 62.50%,which was significantly higher than that of Google Bard,LlaMA-7B,and *** the NCE-CPFC examination,ChatGPT-4.0,Ali Tongyi Qianwen,Baidu ERNIE Bot,Google Bard,MedGPT,and ChatGPT-3.5 successfully passed,whereas LlaMA2-7B,HuatuoGPT,Chinese LLaMA2-7B,and LlaMA-7B ***-4.0(84.82%)surpassed all PCPs and assisted most PCPs in the NCE-CPDC examination(improving by 1%–6.13%).In summary,LLMs demonstrated outstanding competence for diabetes-related questions in both the Chinese and English language,and hold great potential to assist future diabetes training for physicians globally.

关键词： Diabetes Diabetestraining Largelanguagemodels Primarydiabetescare Prospectivestudy

来源：评论

学校读者我要写书评

暂无评论

S4TP: Social-Suitable and Safety-Sensitive Trajectory Planning for Autonomous Vehicles

arXiv

引用

arXiv 2024年

作者： Wang, Xiao Tang, Ke Dai, Xingyuan Xu, Jintao Du, Quancheng Ai, Rui Wang, Yuxiao Gu, Weihao Engineering Research Center of Autonomous Unmanned System Technology Ministry of Education Anhui University Hefei230031 China Haomo Technology Co. Ltd. Beijing100192 China The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China Qingdao Academy of Intelligent Industries Qingdao266114 China The School of Computer and Communication Engineering University of Science and Technology Beijing Beijing100083 China The School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China

In public roads, autonomous vehicles (AVs) face the challenge of frequent interactions with human-driven vehicles (HDVs), which render uncertain driving behavior due to varying social characteristics among humans. To effectively assess the risks prevailing in the vicinity of AVs in social interactive traffic scenarios and achieve safe autonomous driving, this article proposes a social-suitable and safety-sensitive trajectory planning (S4TP) framework. Specifically, S4TP integrates the Social-Aware Trajectory Prediction (SATP) and Social-Aware Driving Risk Field (SADRF) modules. SATP utilizes Transformers to effectively encode the driving scene and incorporates an AV’s planned trajectory during the prediction decoding process. SADRF assesses the expected surrounding risk degrees during AVs-HDVs interactions, each with different social characteristics, visualized as two-dimensional heat maps centered on the AV. SADRF models the driving intentions of the surrounding HDVs and predicts trajectories based on the representation of vehicular interactions. S4TP employs an optimization-based approach for motion planning, utilizing the predicted HDVs’ trajectories as input. With the integration of SADRF, S4TP executes real-time online optimization of the planned trajectory of AV within low-risk regions, thus improving the safety and the interpretability of the planned trajectory. We have conducted comprehensive tests of the proposed method using the SMARTS simulator. Experimental results in complex social scenarios, such as unprotected left-turn intersections, merging, cruising, and overtaking, validate the superiority of our proposed S4TP in terms of safety and rationality. S4TP achieves a pass rate of 100% across all scenarios, surpassing the current state-of-the-art methods Fanta of 98.25% and Predictive-Decision of 94.75%. Copyright © 2024, The Authors. All rights reserved.

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

A Feedback-based Print Quality Improving Strategy for FDM 3D Printing: An Optimal Design Approach

Research Square

引用

research Square 2021年

作者： Tami, Tariku Sinshaw Xiong, Gang Fang, Qihang Dong, Xisong Shen, Zhen Wang, Fei-Yue The State Key Laboratory for Management and Control of Complex Systems Beijing Engineering Research Center of Intelligent Systems and Technology Institute of Automation Chinese Academy of Sciences Beijing100190 China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing Cloud Computing Center Chinese Academy of Sciences Dongguan523808 China

Fused deposition modelling (FDM) 3D printing, as a supporting technology in social manufacturing and cloud manufacturing, is a rapidly growing technology in the era of industry 4.0. It produces objects with the layer-by-layer material accumulation technique. However, qualitative uncertainties are the common challenges yet. In order to assure print quality, studying the error causing parameters and minimizing their effects is important. This paper presents a feedback-based error compensation strategy, which integrates fuzzy inference system and grey wolf optimization algorithm. The objectives are twofold. First, the possible errors in FDM 3D printing are discussed in detail and optimal error causing parameters are obtained in percentage. This is used to understand the effects of the printing errors in every phase of the 3D printing process. From the nine optimization configuration trials used, Config-6 that has 100 number of iterations and 60 wolves is selected due to its higher convergence speed and best fitness value. The integral absolute error (IAE) is used as an objective function and the global minimum is achieved in the iteration interval [86, 100]. The outputs of this optimization problem is used to achieve the next objective. Second, a closed-loop quality monitoring approach comprising of inner-loops and an outer-loop is utilized. The three inner-loops are used to monitor the errors during pre-printing, printing, and post-printing, respectively. The outer-loop, on the other hand, is responsible for monitoring the aggregated errors in all the three 3D printing phases. The error compensation system simulation in Matlab is run for 10 seconds, and the results show that the "normal" range deformation factors are reached within less than 2 seconds for the inner-loops, whereas the outer-loop deformation factor is achieved within 7 seconds. The responses are within the acceptable time range. © 2021, CC BY.

关键词： 3D printers

来源：评论

学校读者我要写书评

暂无评论

An IoT Edge computing System architecture and its Application

An IoT Edge Computing System Architecture and its Applicatio...

引用

2020 IEEE International Conference on Networking, Sensing and Control, ICNSC 2020

作者： Chen, Shichao Li, Qijie Zhang, Hua Zhu, Fenghua Xiong, Gang Tang, Ying Macau University of Science and Technology State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences China Beijing University of Technology State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Beijing Aerospace Smart Manufacturing Technology Development Co. Ltd Platform Research and Development Department Beijing China State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Engineering Research Center of Intelligent Systems and Technology Institute of Automation Cloud Computing Center Chinese Academy of Sciences Beijing China Rowan University Department of Electrical and Computer Engineering GlassboroNJ United States Institute of Smart Education Qingdao Academy of Intelligent Industries Qingdao China

ISBN: (纸本)9781728168531

As the number of devices connected to the Internet of things (IoT) surges, the amount of data explodes. Therefore it not only increases the bandwidth load of data transmission but also aggravates the computing and storage load of a cloud platform. At the same time, the traditional computing paradigm centered on cloud computing cannot meet the real-time requirements in many application scenarios. The emergence of edge computing can solve the problems of realtime data processing and network bandwidth occupation in the current IoT scene. In this paper, according to the characteristics of IoT, such as fragmented data, heterogeneous network, and limited energy consumption, the architecture of an IoT edge computing system is constructed to suit better an IoT scene. In addition, the application of edge computing key technologies such as virtualization, edge intelligence, computing offload, collaborative scheduling and micro-services in resource-constrained IoT scenarios is analyzed in detail. Finally, the functions and application of energy consumption monitoring and optimization to a central air-conditioning system are analyzed and summarized, which is a typical application of edge computing in the context of the IoT. © 2020 IEEE.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

Cyber-Physical -Social systems for Smart Cities: An Overview

Cyber-Physical -Social Systems for Smart Cities: An Overview

引用

Digital Twins and Parallel Intelligence (DTPI), IEEE International Conference on

作者： Noreen Anwar Gang Xiong Wanze Lu Peijun Ye Hongxia Zhao Qinglai Wei The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China The Beijing Engineering Research Center of Intelligent Systems and Technology Institute of Automation and with The Cloud Computing Center Chinese Academy of Sciences China School of Artificial Intelligence and Automation Beijing University of Technology Beijing China

Cyber-physical social systems (CPSS) include cyberspace, physical space, and social space. Since the introduction of CPSS, human relationships with machinery and the physical world have altered as a new paradigm. Recent estimates indicate that approximately 60 percent of the world's population will live in cities by 2030. Large, dense cities can be highly productive, innovative, and very green per capita, hence ideal for our future. However, the huge influx of new people poses enormous challenges to their administrations. Smart cities are becoming a reality, therefore, to achieve higher efficiency, optimum use of resources, management and to strengthen several features of modern towns, several elements of modern cities are automated and integrated into Information and Communications Technology (ICT). Cities and infrastructure are growing all over the world, in providing end-users with increased performance, comfort, visibility and convenience, the Smart Cities concept is critical. This paper will discuss smart cities and the CPSS concept intensively with some of its key technologies, challenges, and further development by using CPSS.

关键词： Smart cities Digital twin Sociology Information and communication technology Security Resource management Statistics

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：