检索结果-内蒙古大学图书馆

Fitness dependent optimizer with neural networks for COVID-19 patients

Computer Methods and Programs in Biomedicine Update 2023年 3卷 100090页

作者： Abdulkhaleq, Maryam T. Rashid, Tarik A. Hassan, Bryar A. Alsadoon, Abeer Bacanin, Nebojsa Chhabra, Amit Vimal, S. Department of Computer Science and Engineering University of Kurdistan Hewler KRI Iraq Kurdistan Institution for Strategic Studies and Scientific Research Sulaimani KRI Iraq Department of Computer Networks Technical College of Informatics Sulaimani Polytechnic University Sulaimani KRI Iraq School of Computing and Mathematics Charles Sturt University Sydney Australia Information Technology Department Asia Pacific International College (APIC) Sydney Australia Singidunum University Danijelova 32 Belgrade 11000 Serbia Department of Computer Engineering and Technology Guru Nanak Dev University Amritsar India Dept of CSE Ramco Institute of Technology Tamilnadu Rajapalayam India

The Coronavirus, known as COVID-19, which appeared in 2019 in China, has significantly affected the global health and become a huge burden on health institutions all over the world. These effects are continuing today. One strategy for limiting the virus's transmission is to have an early diagnosis of suspected cases and take appropriate measures before the disease spreads further. This work aims to diagnose and show the probability of getting infected by the disease according to textual clinical data. In this work, we used five machine learning techniques (GWO_MLP, GWO_CMLP, MGWO_MLP, FDO_MLP, FDO_CMLP) all of which aim to classify Covid-19 patients into two categories (Positive and Negative). Experiments showed promising results for all used models. The applied methods showed very similar performance, typically in terms of accuracy. However, in each tested dataset, FDO_MLP and FDO_CMLP produced the best results with 100% accuracy. The other models' results varied from one experiment to the other. It is concluded that the models on which the FDO algorithm was used as a learning algorithm had the possibility of obtaining higher accuracy. However, it is found that FDO has the longest runtime compared to the other algorithms. The link to the Covid 19 models is found here: https://***/Tarik4Rashid4/covid19models © 2022

关键词： COVID 19 FDO Fitness dependent optimizer Machine learning Swarm intelligence

来源：评论

学校读者我要写书评

暂无评论

FNBench: Benchmarking Robust Federated Learning against Noisy Labels

arXiv

引用

arXiv 2025年

作者： Jiang, Xuefeng Li, Jia Wu, Nannan Wu, Zhiyuan Li, Xujing Sun, Sheng Xu, Gang Wang, Yuwei Li, Qi Liu, Min Institute of Computing Technology Chinese Academy of Sciences Beijing China Institute of Information Engineering Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Huazhong University of Science and Technology Hubei province Wuhan China Institution for Network Sciences and Cyberspace Tsinghua University Beijing China Zhongguancun Laboratory Beijing China

Robustness to label noise within data is a significant challenge in federated learning (FL). From the data-centric perspective, the data quality of distributed datasets can not be guaranteed since annotations of different clients contain complicated label noise of varying degrees, which causes the performance degradation. There have been some early attempts to tackle noisy labels in FL. However, there exists a lack of benchmark studies on comprehensively evaluating their practical performance under unified settings. To this end, we propose the first benchmark study FNBench to provide an experimental investigation which considers three diverse label noise patterns covering synthetic label noise, imperfect human-annotation errors and systematic errors. Our evaluation incorporates eighteen state-of-the-art methods over five image recognition datasets and one text classification dataset. Meanwhile, we provide observations to understand why noisy labels impair FL, and additionally exploit a representation-aware regularization method to enhance the robustness of existing methods against noisy labels based on our observations. Finally, we discuss the limitations of this work and propose three-fold future directions. To facilitate related communities, our source code is open-sourced at https://***/Sprinter1999/FNBench. Copyright © 2025, The Authors. All rights reserved.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Pressure-induced Lifshitz transition in the type Ⅱ Dirac semimetal PtTe_2

引用

science China(Physics,Mechanics & Astronomy) 2019年第4期62卷 91-97页

作者： FengLiang Liu JiaHeng Li KeNan Zhang Shang Peng HuaQing Huang MingZhe Yan NaNa Li Qian Zhang SongHao Guo XuJie Lü Peng Cai LiFeng Yin ShuYun Zhou WenHui Duan Jian Shen WenGe Yang State Key Laboratory of Surface Physics and Department of Physics Fudan University Center for High Pressure Science and Technology Advanced Research (HPSTAR) State Key Laboratory of Low Dimensional Quantum Physics and Department of Physics Tsinghua University Institute for Nanoelectronic Devices and Quantum Computing Fudan University Collaborative Innovation Center of Advanced Microstructures High Pressure Synergetic Consortium (HPSynC) Geophysical Laboratory Carnegie Institution of Washington

Numerous exotic properties have been discovered in Dirac Semimetals(DSMs) and Weyl Semimetals(WSMs). In a given DSM/WSM, the Dirac/Weyl nodes usually coexist with other bulk states, making their respective contribution elusive. In this work, we distinguish the role of bulk states from the tilted Dirac nodes on the transport properties in DSMs. Specifically, we applied pressure to a type-II DSM material, PtTe2, and studied its pressure modified electronic and lattice structure systematically by using in situ transport measurements and X-ray diffraction(XRD). A pressure-induced transition at about 20 GPa is revealed in the transport properties, while the layered lattice structure is robust against pressure as illustrated in XRD measurement *** functional theory(DFT) calculations suggest that this is originated from the Lifshitz transition in the bulk states. Our findings provide evidence to identify the bulk states' influence on transport from the topologically-protected DSM states in the DSM material.

关键词： Dirac semimetals diamond anvil cells X-ray diffraction transport measurement band structure calculation

来源：评论

学校读者我要写书评

暂无评论

Co-pyrolysis of Chlorella vulgaris with plastic wastes: Thermal degradation, kinetics and Progressive Depth Swarm-Evolution (PDSE) neural network-based optimization

Green Technologies and Sustainability

引用

Green Technologies and Sustainability 2024年第2期2卷

作者： Tan, Isabel Jia Yen Loy, Adrian Chun Minh Chin, Bridgid Lai Fui Cheah, Kin Wai Teng, Sin Yong How, Bing Shen Alhazmi, Hatem Leong, Wei Dong Lim, Huei Yeong Lam, Man Kee Lam, Su Shiung Department of Chemical and Energy Engineering Faculty of Engineering and Science Curtin University Malaysia CDT 250 Miri Sarawak 98009 Malaysia Chemical Engineering Department Monash University Victoria 3180 Australia HICoE-Centre for Biofuel and Biochemical Research Institute of Self-Sustainable Building Department of Chemical Engineering Universiti Teknologi PETRONAS Perak Darul Ridzuan Bandar Seri Iskandar 32610 Malaysia School of Computing Engineering and Digital Technologies Teesside University Middlesbrough TS1 3BX United Kingdom Radboud University Institute for Molecules and Materials P.O. Box 9010 Nijmegen 6500 GL Netherlands Biomass Waste-to-Wealth Special Interest Group Research Centre for Sustainable Technologies Faculty of Engineering Computing and Science Swinburne University of Technology Jalan Simpang Tiga Sarawak Kuching 93350 Malaysia Carbon Management Technologies Institute (CMTI) King Abdulaziz City for Science and Technology (KACST) P.O. Box 6086 Riyadh 11442 Saudi Arabia Duriane Professionals Sdn Bhd 26-1 & 26-3 Jalan Puteri 2/4 Bandar Puteri Selangor Puchong 47100 Malaysia Higher Institution Centre of Excellence (HICoE) Institute of Tropical Aquaculture and Fisheries (AKUATROP) Universiti Malaysia Terengganu Terengganu Kuala Nerus 21030 Malaysia Energy and Environment Research Cluster Faculty of Engineering and Science Curtin University Malaysia CDT 250 Sarawak Miri 98009 Malaysia Sustainability Cluster School of Engineering University of Petroleum & Energy Studies Uttarakhand Dehradun 248007 India

The search of sustainable route for biofuel production from renewable biomass have garnered wide interest to seek for various routes without compromising the environment. Co-pyrolysis emerges as a promising thermochemical route that can improve the pyrolysis output from simultaneously processing more than two feedstocks in an inert atmosphere. This paper focuses on the kinetic modeling and neuro-evolution optimization in the application of catalytic co-pyrolysis of microalgae and plastic waste using HZSM-5 supported on limestone (HZSM-5/LS), in which co-pyrolysis of binary mixture of microalgae and plastic wastes (i.e. High-Density Polyethylene and Low-Density Polyethylene) was investigated over different heating rates. The results have shown a positive synergistic effect between the microalgae and polyethylene in which the apparent activation energies values have reduced significantly (∼20 kJ/mol) compared to that obtained by pyrolysis of individual microalgae component. The kinetic models reflect that the mixture of microalgae and Low-Density Polyethylene for use as co-pyrolysis feedstock requires activation energy that is 23% and 13% lower compared to that required by pure microalgae and the mixture of microalgae and High-Density Polyethylene, respectively. The Progressive Depth Swarm-Evolution (PDSE) was used for neural architecture search, which subsequently provided optimal reaction condition at 873 K can achieve 99.6 % of degradation rate using a tri-combination of LDPE (0.13 %) + HDPE (0.77 %) + MA (0.11 %) in the presence of HZSM-5/LS catalyst. © 2024 The Authors

关键词： Co-pyrolysis Distributed activation energy model (DAEM) Kinetic analysis Microalgae Neuro-evolution Plastic waste

来源：评论

学校读者我要写书评

暂无评论

Interacting dark energy constraints from the full-shape analyses of BOSS DR12 and DES Year 3 measurements

arXiv

引用

arXiv 2025年

作者： Tsedrik, M. Lee, S. Markovic, K. Carrilho, P. Pourtsidou, A. Moretti, C. Bose, B. Huff, E. Robertson, A. Taylor, P.L. Zuntz, J. Institute for Astronomy University of Edinburgh Royal Observatory Blackford Hill EdinburghEH9 3HJ United Kingdom Higgs Centre for Theoretical Physics School of Physics and Astronomy EdinburghEH9 3FD United Kingdom Jet Propulsion Laboratory California Institute of Technology 4800 Oak Grove Drive PasadenaCA91109 United States SISSA - International School for Advanced Studies Via Bonomea 265 Trieste34136 Italy Centro Nazionale ‘High Performance Computer Big Data and Quantum Computing’ Italy INAF Osservatorio Astronomico di Trieste Via Tiepolo 11 TriesteI-34143 Italy Observatories Carnegie Institution for Science 813 Santa Barbara Street PasadenaCA91101 United States The Ohio State University ColumbusOH43210 United States Department of Physics The Ohio State University ColumbusOH43210 United States Department of Astronomy The Ohio State University ColumbusOH43210 United States

Dark Scattering (DS) is an interacting dark energy model characterised by pure momentum exchange between dark energy and dark matter. It is phenomenologically interesting because it is unconstrained by CMB data and can alleviate the S8 tension. We derive constraints on cosmological and DS parameters using three two-point correlation functions (3×2pt) from the Dark Energy Survey third year data release (DES Y3). We then add information from the multipoles of the galaxy power spectrum combined with Baryonic Acoustic Oscillation (BAO) measurements using the twelfth data release of the Baryon Oscillation Spectroscopic Survey (BOSS DR12) and external BAO measurements. We compare results from the direct combination of the probes with the joint posterior distribution calculated with a normalising flow approach. Additionally, we run a CMB analysis with the Planck Public Release 4 (PR4) for comparison of the cosmological constraints. Overall, we find that the combination of probes allows minimising the projection effects and improves constraints without the need to include CMB information. It brings the marginalised posterior maxima closer to the corresponding best-fit values and weakens the sensitivity to the priors of the spectroscopic modelling nuisance parameters. These findings are highly relevant in light of forthcoming data of surveys like DESI, Euclid, and Rubin. © 2025, CC BY.

关键词： Dark energy

来源：评论

学校读者我要写书评

暂无评论

Chemical Abundances of the Typhon Stellar Stream

arXiv

引用

arXiv 2022年

作者： Ji, Alexander P. Naidu, Rohan P. Brauer, Kaley Ting, Yuan-Sen Simon, Joshua D. Department of Astronomy & Astrophysics University of Chicago 5640 S Ellis Avenue ChicagoIL60637 United States Kavli Institute for Cosmological Physics University of Chicago ChicagoIL60637 United States Center for Astrophysics Harvard & Smithsonian 60 Garden Street CambridgeMA02138 United States Department of Physics Kavli Institute for Astrophysics and Space Research Massachusetts Institute of Technology CambridgeMA02139 United States Research School of Astronomy & Astrophysics Australian National University Cotter Rd. WestonACT Australia School of Computing Australian National University ActonACT2601 Australia Observatories of the Carnegie Institution for Science 813 Santa Barbara Street PasadenaCA91101 United States

We present the first high-resolution chemical abundances of seven stars in the recently discovered high-energy stream Typhon. Typhon stars have apocenters 100 kpc, making this the first detailed chemical picture of the Milky Way's very distant stellar halo. Though the sample size is limited, we find that Typhon's chemical abundances are more like a dwarf galaxy than a globular cluster, showing a metallicity dispersion and no presence of multiple stellar populations. Typhon stars display enhanced α-element abundances and increasing r-process abundances with increasing metallicity. The high-α abundances suggest a short star formation duration for Typhon, but this is at odds with expectations for the distant Milky Way halo and the presence of delayed r-process enrichment. If the progenitor of Typhon is indeed a new dwarf galaxy, possible scenarios explaining this apparent contradiction include a dynamical interaction that increases Typhon's orbital energy, a burst of enhanced late-time star formation that raises [α/Fe], and/or group preprocessing by another dwarf galaxy before infall into the Milky Way. Alternatively, Typhon could be the high-energy tail of a more massive disrupted dwarf galaxy that lost energy through dynamical friction. We cannot clearly identify a known low-energy progenitor of Typhon in the Milky Way, but 70% of high-apocenter stars in cosmological simulations are from high-energy tails of large dwarf galaxies. Typhon's surprising combination of kinematics and chemistry thus underscores the need to fully characterize the dynamical history and detailed abundances of known substructures before identifying the origin of new substructures. © 2022, CC BY.

关键词： Stars

来源：评论

学校读者我要写书评

暂无评论

Toward an Organic computing Approach to Automated Design of Processing Pipelines 31

Toward an Organic Computing Approach to Automated Design of ...

引用

31st GI/ITG International Conference on Architecture of computing Systems, ARCS 2018

作者： Stein, Anthony Margraf, Andreas Moroskow, Jürgen Geinitz, Steffen Hähner, Jörg Organic Computing Group Institute of Computer Science University of Augsburg Germany Fraunhofer Igcv Institution for Casting Composite and Processing Technology Germany

ISBN: (纸本)9783800745593

This paper aims to propose a novel Organic computing concept to dealing with the overall issue of automated design of processing pipelines. It is outlined how several methods standing under the Artificial Intelligence umbrella are combined to form a technique that can be realized by Organic computing systems to strengthen their self-configuration property by im-plementing self-optimization and self-learning techniques. Three envisioned application scenarios are discussed which will serve as first testbeds for the proposed architecture in a future research project: The automated design of 1) a data pre-processing observer component for the refurbishment and the analysis of insufficient quality data to improve the learning ability of employed machine learning algorithms, 2) an image processing pipeline for industrial imaging systems, and, 3) production lines in manufacturing scenarios. © ARCS 2018.

关键词： Pipelines

来源：评论

学校读者我要写书评

暂无评论

RETRACTED ARTICLE: Investigation of finance industry on risk awareness model and digital economic growth

引用

Annals of Operations Research 2021年第1期326卷 15-15页

作者： Chen, Yanyu kumara, E. Kusuma Sivakumar, V. College of Economics and Management Zhejiang Normal University Jinhua China Ece Vasavi Engineering College Hyderabad India School of Computing Vel Tech Rangarajan Dr Saguthala R & D Institution of Science and Technology Chennai India

来源：评论

学校读者我要写书评

暂无评论

Correction: Current Studies and Applications of Shuffled Frog Leaping Algorithm: A Review

引用

Archives of Computational Methods in Engineering 2022年第5期30卷 3469-3469页

作者： Maaroof, Bestan B. Rashid, Tarik A. Abdulla, Jaza M. Hassan, Bryar A. Alsadoon, Abeer Mohammadi, Mokhtar Khishe, Mohammad Mirjalili, Seyedali Information Technology Department College of Commerce University of Sulaimani Sulaymaniyah Iraq Computer Science and Engineering University of Kurdistan Hewler Erbil Iraq Computer Science Department College of Science Komar University of Science and Technology Sulaymaniyah Iraq Information Technology College of Commerce University of Sulaimani Sulaymaniyah Iraq Kurdistan Institution for Strategic Studies and Scientific Research Sulaimani Iraq School of Computing and Mathematics Charles Sturt University Sydney Australia Information Technology Department Asia Pacific International College (APIC) Sydney Australia Department of Information Technology College of Engineering and Computer Science Lebanese French University Kurdistan Region Iraq Department of Marine Electronics and Communication Engineering Imam Khomeini Marine Science University Nowshahr Iran Centre for Artificial Intelligence Research and Optimization Torrens University Adelaide Australia Yonsei Frontier Lab Yonsei University Seoul Korea

来源：评论

学校读者我要写书评

暂无评论

International AI Safety Report

arXiv

引用

arXiv 2025年

作者： Bengio, Yoshua Mindermann, Sören Privitera, Daniel Besiroglu, Tamay Bommasani, Rishi Casper, Stephen Choi, Yejin Fox, Philip Garfinkel, Ben Goldfarb, Danielle Heidari, Hoda Ho, Anson Kapoor, Sayash Khalatbari, Leila Longpre, Shayne Manning, Sam Mavroudis, Vasilios Mazeika, Mantas Michael, Julian Newman, Jessica Ng, Kwan Yee Okolo, Chinasa T. Raji, Deborah Sastry, Girish Seger, Elizabeth Skeadas, Theodora South, Tobin Strubell, Emma Tramèr, Florian Velasco, Lucia Wheeler, Nicole Acemoglu, Daron Adekanmbi, Olubayo Dalrymple, David Dietterich, Thomas G. Felten, Edward W. Fung, Pascale Gourinchas, Pierre-Olivier Heintz, Fredrik Hinton, Geoffrey Jennings, Nick Krause, Andreas Leavy, Susan Liang, Percy Ludermir, Teresa Marda, Vidushi Margetts, Helen McDermid, John Munga, Jane Narayanan, Arvind Nelson, Alondra Neppel, Clara Oh, Alice Ramchurn, Gopal Russell, Stuart Schaake, Marietje Schölkopf, Bernhard Song, Dawn Soto, Alvaro Tiedrich, Lee Varoquaux, Gaël Yao, Andrew Zhang, Ya-Qin Université de Montréal Mila - Quebec AI Institute Canada Epoch AI United States KIRA Center Mila Quebec AI Institute Canada Stanford University United States Massachusetts Institute of Technology United States University of Oxford United Kingdom Carnegie Mellon University United States Princeton University United States Hong Kong University of Science and Technology Hong Kong Centre for the Governance of AI United Kingdom The Alan Turing Institute United Kingdom University of Illinois at Urbana-Champaign United States New York University United States University of California Berkeley United States Concordia AI China Brookings Institution United States Demos United Kingdom Humane Intelligence ETH Zurich Switzerland Maastricht University Netherlands University of Birmingham United Kingdom Advanced Research Invention Agency United Kingdom Oregon State University United States Research Department International Monetary Fund United States Linköping University Sweden University of Toronto Canada University of Loughborough United Kingdom University College Dublin Ireland Federal University of Pernambuco Brazil AI Collaborative University of York United Kingdom Carnegie Endowment for International Peace United States Institute for Advanced Study KAIST School of Computing Korea Republic of ELLIS Institute Tübingen Germany Pontificia Universidad Católica de Chile Chile Duke University United States Inria France Institute for Interdisciplinary Information Sciences Tsinghua University China Tsinghua University China

The first International AI Safety Report comprehensively synthesizes thecurrent evidence on the capabilities, risks, and safety of advanced AI *** report was mandated by the nations attending the AI Safety Summit inBletchley, UK. Thirty nations, the UN, the OECD, and the EU each nominated arepresentative to the report\'s Expert Advisory Panel. A total of 100 AI expertscontributed, representing diverse perspectives and disciplines. Led by thereport\'s Chair, these independent experts collectively had full discretion overthe report\'s content. © 2025, CC BY.

关键词： Safety engineering

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：