检索结果-内蒙古大学图书馆

H2-MARL: Multi-agent reinforcement learning for Pareto optimality in hospital capacity strain and human mobility during epidemic

引用

Expert Systems with Applications 2025年 291卷

作者： Xueting Luo Hao Deng Jihong Yang Yao Shen Huanhuan Guo Zhiyuan Sun Mingqing Liu Jiming Wei Shengjie Zhao School of Computer Science and Technology Tongji University Shanghai 201804 China Engineering Research Center of Key Software Technologies for Smart City Perception and Planning Ministry of Education Shanghai 201804 China China Land Surveying and Planning Institute Beijing 100035 China College of Architecture and Urban Planning Tongji University Shanghai 200092 China Chongqing Institute of Planning and Natural Resources Investigation and Monitoring Chongqing 401121 China College of Electronic and Information Engineering Tongji University Shanghai 201804 China Guangdong Urban-rural Planning and Design Research Institute Technology Group Co. Ltd. Guangzhou 510290 China

Effectively balancing the losses from mobility restrictions and hospital capacity strain has drawn significant attention in the aftermath of COVID-19. Reinforcement learning (RL)-based strategies for human mobility management have recently advanced in addressing the dynamic evolution of cities and epidemics; however, they still face challenges in achieving coordinated control at the township level and adapting to cities of varying scales. To address the above issues, we propose a multi-agent RL approach that achieves Pareto optimality in managing hospital capacity and human mobility (H2-MARL), applicable across cities of different population scales. We first develop a township-level infection model with online-updatable parameters to simulate disease transmission and construct a city-wide dynamic spatiotemporal epidemic simulator. On this basis, H2-MARL is designed to treat each division as an agent, with a trade-off dual-objective reward function formulated and an experience replay buffer enriched with expert knowledge built. To evaluate the effectiveness of the model, we construct a township-level human mobility dataset containing over one billion records from four representative cities of varying scales. Extensive experiments demonstrate that H2-MARL has the optimal dual-objective trade-off capability, which can simultaneously minimize hospital capacity strain and human mobility restriction loss. Meanwhile, the applicability of the proposed model to epidemic control in cities of varying scales is verified, which showcases its feasibility and versatility in practical applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Automatic Primary Gross Tumor Volume Segmentation for Nasopharyngeal Carcinoma using ResSE-UNet

Automatic Primary Gross Tumor Volume Segmentation for Nasoph...

引用

Annual IEEE Symposium on computer-Based Medical Systems

作者： Zhihao Jin XueChen Li Linlin Shen Jinyi Lang Jie Li Junxiang Wu Peng Xu Jiang Duan College of Computer Science and Software Engineering Shenzhen University Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ) Shenzhen University Shenzhen PR China Sichuan Cancer Hospital & Institute Sichuan Cancer Center School of Medicine University of Electronic Science and Technology of China Radiation Oncology Key Laboratory Of Sichuan Province Chengdu PR China School of economic information engineering Southwestern university of finance and economics Chengdu PR China

ISBN: (数字)9781728194295

ISBN: (纸本)9781728194301

Nasopharyngeal carcinoma (NPC) is an endemic disease within specific regions in the world. Radiotherapy is the standard treatment for NPC and accurate segmentation of primary gross tumor volume (GTV) is a critical process of continue therapy. In this paper we proposed a ResSE-UNet network and a Ternary Cross-Entropy (TCE) loss function for delineation of GTV. ResSE-UNet employed ResSE blocks to replace convolutional blocks in the original UNet to extract better features, and reduced the number of down-sampling processing to keep relatively high resolution of the images. TCE combined dice loss and Binary cross-entropy loss for larger gradient and better stability in training. The experimental results showed that among all combinations of networks and loss functions, the ResSE-UNet with TCE loss achieved the best segmentation performance, i.e. about 0.84 DSC can be obtained.

关键词： Image segmentation Computed tomography Convolution Feature extraction Tumors Task analysis Training

来源：评论

学校读者我要写书评

暂无评论

Identifying the Predictive Capability of Machine Learning Classifiers for Designing Heart Disease Detection System

Identifying the Predictive Capability of Machine Learning Cl...

引用

International Conference on Wavelet Active Media Technology and information Processing (ICWAMTIP)

作者： AMIN UL HAQ JIANPING LI JALALUDDIN KHAN MUHAMMAD HAMMAD MEMON SHADMA PARVEEN MORDECAI FOLARIN RAJI WASIF AKBAR TANVIR AHMAD SANA ULLAH LATIPOVA SHOISTA HAPPY N. MONDAY School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China School of Management Science and Economics University of Electronic Science and Technology of China School of Control and Computer Engineering North China Electric Power University Beijing China School of Information and Software Engineering University of Electronic Science and Technology of China

ISBN: (数字)9781728142425

ISBN: (纸本)9781728142432

The diagnosis of heart diseases through invoice based techniques as well as ordinary medical based methods are not reliable. On other hand, non-invoice based techniques are more effective for heart disease diagnosis. Therefore, we check the capability of various Machine Learning (ML) classifiers and deep learning classifier for heart disease identification in this paper. Six machine-learning classifiers and BPNN were used in order to check which one classifier is more effective for diagnosis the heart disease. The feature selection algorithm Relief was used for selection of important features and on these selected features, classifiers performances were also computed. Ensemble machine learning techniques (boosting, bagging, stacking) were used to further increase the classifiers performance. Furthermore, cross-validation techniques k-folds was also used. Additionally backward propagation neural network (BPNN) was also used for classification purpose because deep learning algorithm not need feature selection algorithms and it automatically select important features for good result. Based on model performance evaluation metrics the SVM (RBF) performed excellently on full features achieved accuracy 86%, and 88% accuracy on selected features as compared other classifiers. Through Ensemble learning techniques, SVM obtained the classification accuracy 92.30%. The BPNN achieved 93% classification accuracy. Thus the performance of deep neural networks learning algorithm is better than traditional machine learning algorithms. As per our experimental results shows that the performance of BPNN based diagnosis system is more effective for heart disease diagnosis.

关键词： Heart Classification algorithms Machine learning Diseases Machine learning algorithms Training Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Corrigendum to “Rational Protocols and Attacks in Blockchain System”

引用

Security and Communication Networks 2021年第1期2021卷

作者： Tao Li Yuling Chen Yanli Wang Yilei Wang Minghao Zhao Haojia Zhu Youliang Tian Xiaomei Yu Yixian Yang State Key Laboratory of Public Big Data Guizhou University Guiyang Guizhou 550025 *** College of Computer Science and Technology Guizhou University Guiyang Guizhou 550025 *** School of Information Science and Engineering Qufu Normal University Rizhao 276825 *** School of Software Tsinghua University Beijing 100084 *** School of Information Science and Engineering Shandong Normal University Jinan 250014 ***

来源：评论

学校读者我要写书评

暂无评论

Halal industry 4.0 model for SMEs

引用

AIP Conference Proceedings 2022年第1期2617卷

作者： Raja Mohd Tariqi Raja Lope Ahmad Wan Azlan Wan Hassan Suziyanti Marjudi Azhar Hamid Mohd Fahmi Mohamad Amran 1Computing Department Faculty of Communication Visual Art and Computing University Selangor 45600 Bestari Jaya Selangor Malaysia 2Software Engineering Department Faculty of Computer Science & Information Technology Universiti Tun Hussein Onn Malaysia 86400 Johor Malaysia 3Computer Science Department Faculty of Science and Defense Technology Universiti Pertahanan Nasional Malaysia Kem Sungai Besi 57000 Kuala Lumpur Malaysia

The commitment between SMEs and stakeholders is very important in coordinating interrelated Halal business functions. However, Halal SMEs players have major obstacles in integrating information that can support their stakeholders with operational and functional requirements. Moreover, there are scanty supply chain comprehensive models that can engage Halal SMEs participants for digitalization. Therefore, the purpose of this study is to construct the Halal Industry 4.0 Model (HI4.0) in order to improve business engagement among SMEs within the Halal Industry 4.0 supply chain. Analysis and evaluation were conducted based on application of previous research work by using systematic literature review and thematic analysis to identify the elements and processes involved in the implementation of Halal related businesses. The outcomes show that HI4.0 consists of five main components which are Halal Knowledge Repository, Halal Supply Chain Management Systems Implementation Framework, Halal Smart Application Ecosystem, Halal Infrastructure, and Halal Integrity Assurance System. The findings contribute to the Halal Industry 4.0 framework development in which the model can benefit stakeholders' engagement with governing bodies, consumers and SMEs.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Automatic and Robust Skull Registration Based on Discrete Uniformization

Automatic and Robust Skull Registration Based on Discrete Un...

引用

International Conference on computer Vision (ICCV)

作者： Junli Zhao Xin Qi Chengfeng Wen Na Lei Xianfeng Gu School of Data Science and Software Engineering Qingdao University Qingdao China Department of Computer Science Stony Brook University Stony Brook USA International School of Information Science and Engineering Dalian University of Technology Dalian China

ISBN: (数字)9781728148038

ISBN: (纸本)9781728148045

Skull registration plays a fundamental role in forensic science and is crucial for craniofacial reconstruction. The complicated topology, lack of anatomical features, and low quality reconstructed mesh make skull registration challenging. In this work, we propose an automatic skull registration method based on the discrete uniformization theory, which can handle complicated topologies and is robust to low quality meshes. We apply dynamic Yamabe flow to realize discrete uniformization, which modifies the mesh combinatorial structure during the flow and conformally maps the multiply connected skull surface onto a planar disk with circular holes. The 3D surfaces can be registered by matching their planar images using harmonic maps. This method is rigorous with theoretic guarantee, automatic without user intervention, and robust to low mesh quality. Our experimental results demonstrate the efficiency and efficacy of the method.

关键词： Three-dimensional displays Measurement Topology Robustness Iterative closest point algorithm Surface morphology Face

来源：评论

学校读者我要写书评

暂无评论

A Novel Steganography Scheme Combining Coverless information Hiding and Steganography

引用

Journal of information Hiding and Privacy Protection 2019年第1期1卷 43-48页

作者： Ruohan Meng Zhili Zhou Qi Cui Xingming Sun Chengsheng Yuan School of Computer and Software Nanjing University of Information Science and TechnologyNanjing210044China Jiangsu Engineering Centre of Network Monitoring Nanjing210044China Department of Electrical and computer Engineering University of WindsorWindsorONCanada N9B 3P4

At present,the coverless information hiding has been ***,due to the limited mapping relationship between secret information and feature selection,it is challenging to further enhance the hiding capacity of coverless information *** the same time,the steganography algorithm based on object detection only hides secret information in foreground objects,which contribute to the steganography capacity is *** object recognition contains multiple objects and location,secret information can be mapped to object categories,the relationship of location and so ***,this paper proposes a new steganography algorithm based on object detection and relationship mapping,which integrates coverless information hiding and *** this method,the coverless information hiding is realized by mapping the object type,color and secret information in object detection *** the same time,the object detection method is used to find the safe area to hide secret *** proposed algorithm can not only improve the steganographic capacity of the two information hiding methods but also make the coverless information hiding more secure and robust.

关键词： Steganography faster R-CNN coverless information hiding

来源：评论

学校读者我要写书评

暂无评论

Sustainable energy planning and integration for district heating systems: A case study in Nineveh Province, Iraq

引用

Journal of Building engineering 2024年 91卷

作者： Qusay Hassan Ali Khudhair Al-Jiboory Muna Al-Razgan Patrik Viktor Nouby M. Ghazaly Emad Mahrous Awwad Sameer Algburi Bashar Mahmood Ali I.B. Sapaev Imad Ibrahim Dawood Marek Jaszczur Aws Zuhair Sameen Maha Barakat Department of Mechanical Engineering University of Diyala Diyala Iraq Department of Software Engineering College of Computer and Information Sciences King Saud University Riyadh 11495 Saudi Arabia Keleti Károly Faculty of Business and Management Óbuda University H-1084 Budapest Hungary Technical College Imam Ja'afar Al-Sadiq University Baghdad Iraq Mechanical Engineering Faculty of Engineering South Valley University Egypt Department of Electrical Engineering College of Engineering King Saud University Riyadh 11421 Saudi Arabia College of Engineering Al-Kitab University Kirkuk 36015 Iraq Department of Construction Engineering and Project Management Al-Noor University College Nineveh Iraq Head of the Department Physics and Chemistry Tashkent Institute of Irrigation and Agricultural Mechanization Engineers National Research University Tashkent Uzbekistan Western Caspian University Scientific Researcher Baku Azerbaijan Mazaya University College Dhi Qar Iraq Faculty of Energy and Fuels AGH University of Science and Technology Krakow Poland College of Medical Techniques Al-Farahidi University Baghdad Iraq Business Administration Department Al-Turath University College Baghdad Iraq

The study explores the feasibility and benefits of implementing solar-based district heating systems in Nineveh Province of Iraq, prompted by an anticipated 10 % rise in heating demand by 2030. Geographic analysis reveals that over 74 % of the region is well-suited for solar district heating, emphasizing the province considerable potential for solar energy utilization. Employing a methodological approach, we devised five scenarios varying in sustainability and efficiency for the district heating system. The results highlight a significant potential for reducing the Total Primary Energy Supply (TPE) by 23.5 % and CO 2 emissions by 39.96 % under the optimal Scenario 5, in contrast to a Business as Usual (BAU) scenario. A sensitivity analysis further examines the influence of different parameters on system performance, reinforcing the importance of adaptive and sustainable energy planning. The main contribution of this study lies in its comprehensive evaluation of solar-based district heating in the province, offering a viable strategy for reducing energy consumption and greenhouse gas emissions. This study not only addresses the urgent need for efficient energy solutions in response to rising heating demands but also sets a precedent for integrating renewable energy systems in urban planning. The novelty of this work resides in its detailed analysis of the province solar heating potential and the practical implications of its findings, which are crucial for policymakers and urban planners committed to advancing sustainable energy initiatives.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Generating Approximate Ground States of Molecules Using Quantum Machine Learning

arXiv

引用

arXiv 2022年

作者： Ceroni, Jack Stetina, Torin F. Kieferová, Mária Marrero, Carlos Ortiz Arrazola, Juan Miguel Wiebe, Nathan Xanadu TorontoONM5G 2C8 Canada Department of Mathematics University of Toronto TorontoONM5S 3E1 Canada Simons Institute for the Theory of Computing BerkeleyCA94704 United States Berkeley Quantum Information and Computation Center University of California BerkeleyCA94720 United States Centre for Quantum Computation and Communication Technology Centre for Quantum Software and Information University of Technology SydneyNSW2007 Australia AI & Data Analytics Division Pacific Northwest National Laboratory RichlandWA99354 United States Department of Electrical & Computer Engineering North Carolina State University RaleighNC27607 United States Department of Computer Science University of Toronto ONM5S 1A1 Canada High Performance Computing Group Pacific Northwest National Laboratory RichlandWA99354 United States

The potential energy surface (PES) of molecules with respect to their nuclear positions is a primary tool in understanding chemical reactions from first principles. However, obtaining this information is complicated by the fact that sampling a large number of ground states over a high-dimensional PES can require a vast number of state preparations. In this work, we propose using a generative quantum machine learning model to prepare quantum states at arbitrary points on the PES. The model is trained using quantum data consisting of ground-state wavefunctions associated with different classical nuclear coordinates. Our approach uses a classical neural network to convert the nuclear coordinates of a molecule into quantum parameters of a variational quantum circuit. The model is trained using a fidelity loss function to optimize the neural network parameters. We show that gradient evaluation is efficient and numerically demonstrate our method’s ability to prepare wavefunctions on the PES of hydrogen chains, water, and beryllium hydride. In all cases, we find that a small number of training points are needed to achieve very high overlap with the groundstates in practice. From a theoretical perspective, we further prove limitations on these protocols by showing that if we were able to learn across an avoided crossing using a small number of samples, then we would be able to violate Grover’s lower bound. Additionally, we prove lower bounds on the amount of quantum data needed to learn a locally optimal neural network function using arguments from quantum Fisher information. This work further identifies that quantum chemistry can be an important use case for quantum machine learning. © 2022, CC BY.

关键词： Molecules

来源：评论

学校读者我要写书评

暂无评论

DPA-2: a large atomic model as a multi-task learner

arXiv

引用

arXiv 2023年

作者： Zhang, Duo Liu, Xinzijian Zhang, Xiangyu Zhang, Chengqian Cai, Chun Bi, Hangrui Du, Yiming Qin, Xuejian Peng, Anyang Huang, Jiameng Li, Bowen Shan, Yifan Zeng, Jinzhe Zhang, Yuzhi Liu, Siyuan Li, Yifan Chang, Junhan Wang, Xinyan Zhou, Shuo Liu, Jianchuan Luo, Xiaoshan Wang, Zhenyu Jiang, Wanrun Wu, Jing Yang, Yudi Yang, Jiyuan Yang, Manyi Gong, Fu-Qiang Zhang, Linshuang Shi, Mengchao Dai, Fu-Zhi York, Darrin M. Liu, Shi Zhu, Tong Zhong, Zhicheng Lv, Jian Cheng, Jun Jia, Weile Chen, Mohan Ke, Guolin Weinan, E. Zhang, Linfeng Wang, Han AI for Science Institute Beijing100080 China DP Technology Beijing100080 China Academy for Advanced Interdisciplinary Studies Peking University Beijing100871 China State Key Lab of Processors Institute of Computing Technology Chinese Academy of Sciences Beijing100871 China University of Chinese Academy of Sciences Beijing100871 China HEDPS CAPT College of Engineering Peking University Beijing100871 China Ningbo Institute of Materials Technology and Engineering Chinese Academy of Sciences Ningbo315201 China CAS Key Laboratory of Magnetic Materials and Devices Zhejiang Province Key Laboratory of Magnetic Materials and Application Technology Chinese Academy of Sciences Ningbo315201 China School of Electronics Engineering and Computer Science Peking University Beijing100871 China Shanghai Engineering Research Center of Molecular Therapeutics & New Drug Development School of Chemistry and Molecular Engineering East China Normal University Shanghai200062 China Laboratory for Biomolecular Simulation Research Institute for Quantitative Biomedicine Department of Chemistry and Chemical Biology Rutgers University PiscatawayNJ08854 United States Department of Chemistry Princeton University PrincetonNJ08540 United States College of Chemistry and Molecular Engineering Peking University Beijing100871 China Yuanpei College Peking University Beijing100871 China School of Electrical Engineering and Electronic Information Xihua University Chengdu610039 China State Key Laboratory of Superhard Materials College of Physics Jilin University Changchun130012 China Key Laboratory of Material Simulation Methods & Software of Ministry of Education College of Physics Jilin University Changchun130012 China International Center of Future Science Jilin University Changchun130012 China Key Laboratory for Quantum Materials of Zhejiang Province Department of Physics School of Science Westlake University Zhejiang Hangzhou310030 China Atomistic Simulations Italia

The rapid advancements in artificial intelligence (AI) are catalyzing transformative changes in atomic modeling, simulation, and design. AI-driven potential energy models have demonstrated the capability to conduct large-scale, long-duration simulations with the accuracy of ab initio electronic structure methods. However, the model generation process remains a bottleneck for large-scale applications. We propose a shift towards a model-centric ecosystem, wherein a large atomic model (LAM), pre-trained across multiple disciplines, can be efficiently fine-tuned and distilled for various downstream tasks, thereby establishing a new framework for molecular modeling. In this study, we introduce the DPA-2 architecture as a prototype for LAMs. Pre-trained on a diverse array of chemical and materials systems using a multi-task approach, DPA-2 demonstrates superior generalization capabilities across multiple downstream tasks compared to the traditional single-task pre-training and fine-tuning methodologies. Our approach sets the stage for the development and broad application of LAMs in molecular and materials simulation research. Copyright © 2023, The Authors. All rights reserved.

关键词： Multi-task 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：