检索结果-内蒙古大学图书馆

Identification of Features in ANN's Black Box using Dimensional Reduction and Correlation Analysis: A Case Study of Cardiovascular Disease Dataset

Identification of Features in ANN's Black Box using Dimensio...

引用

International Conference on Advanced Mechatronics, Intelligent Manufacture, and Industrial Automation (ICAMIMIA)

作者： Boby Siswanto Yaya Heryadi Wayan Suparta Antoni Wibowo Haryono Soeparno Lukas Computer Science Department BINUS Graduate Program-Doctor of Computer Science Bina Nusantara University Jakarta Indonesia Cognitive Engineering Research Group (CERG) Atma Jaya University Jakarta Indonesia

ISBN: (纸本)9781665499705

Artificial Neural Network (ANN) is a machine learning algorithm that can perform classification. ANN has limitations; namely, it has a black box working principle, which is unsure which feature is the most influential. This study is to identify the most influential features inside the ANN's black box using a classification model by applying Principal Component Analysis (PCA) dimension reduction combined with Pearson correlation analysis. The result of the proposed model can identify the name of the main features of the data inside the ANN's black box. This study uses two public Kaggle cardiovascular datasets. The first dataset consists of 13 features, and the second dataset consists of 12 features. The result is height and gender are the most influential features in the first dataset with the correlation value of 0.734; sex and smoking are the most influential features in the second dataset with the correlation value of 0.728. Black box model result with 2 PCA's features against a model with height and gender features in the first dataset resulting from the same accuracy on the test dataset of the classification prediction results with the value of 49.90%, while on the second dataset 58.30%.

关键词： Dimensionality reduction Analytical models Correlation Mechatronics Machine learning algorithms Artificial neural networks Predictive models

来源：评论

学校读者我要写书评

暂无评论

Hunting axion dark matter signatures in low-frequency terrestrial magnetic fields

arXiv

引用

arXiv 2025年

作者： Taruya, Atsushi Nishizawa, Atsushi Himemoto, Yoshiaki Center for Gravitational Physics and Quantum Information Yukawa Institute for Theoretical Physics Kyoto University Kyoto606-8502 Japan Kavli Institute for the Physics and Mathematics of the Universe Todai Institutes for Advanced Study The University of Tokyo Kavli IPMU WPI Chiba Kashiwa277-8583 Japan Physics Program Graduate School of Advanced Science and Engineering Hiroshima University Hiroshima Higashi-Hiroshima739-8526 Japan Astrophysical Science Center Hiroshima University Hiroshima Higashi-Hiroshima739-8526 Japan Graduate School of Science The University of Tokyo Tokyo113-0033 Japan Department of Liberal Arts and Basic Sciences College of Industrial Technology Nihon University Chiba Narashino275-8576 Japan

We show that Earth’s natural environment can serve as a powerful probe for ultralight axion dark matter. In the presence of global geomagnetic fields, the axions with masses ranging from 10−15 eV–10−13 eV induce electromagnetic waves in the (sub-) extremely low-frequency band (0.3 − 30 Hz) through the axion-photon coupling. We predict the amplitude of induced magnetic fields in the Earth-ionosphere cavity, taking the finite conductivity of the atmosphere into account. This allows us to constrain the axion-photon coupling parameter, gaγ, from the long-term monitoring data of the low-frequency magnetic fields, resulting in a significant improvement from the previous constraints down to gaγ 4 × 10−13 GeV−1 for axion mass ∼ 3 × 10−14 eV. © 2025, CC BY-NC-ND.

关键词： Geomagnetism

来源：评论

学校读者我要写书评

暂无评论

Efficiency comparison of proactive approaches to deal with machine failures*

引用

IFAC-PapersOnLine 2022年第10期55卷 767-772页

作者： Fernanda F. Alves Martin G. Ravetti Graduate Program in Production Engineering Federal University of Minas Gerais Presidente Antonio Carlos Avenue 6627 30161-010 Belo Horizonte Minas Gerais Brazil Department of Computer Science Federal University of Minas Gerais Presidente Antonio Carlos Avenue 6627 Cep 30161-010 Belo Horizonte Minas Gerais Brazil

Due to the innovations brought by Industry 4.0, decision-makers must rethink the premisses and methods used to solve production planning problems. We study short-term production planning and scheduling problems subject to disruptions, incorporating characteristics of Industry 4.0 into the analyzed scenario. We propose and compare two proactive approaches for dealing with machine failures on the shop floor. The methods aim to find sequences with low probabilities of infeasibility at the scheduling level even with the occurrence of disruptions. One proactive approach performs simulations before the resolution of the planning problems to define slacks added to the capacity constraints of the short-term production planning problem. On the other hand, the second approach determines these slacks based on the probability distributions of the failures. According to the experiments, we conclude that the proposed approaches find similar results for most instance sets when comparing the averages and standard deviations. The results indicate that is not necessary to perform simulations before the resolution of the planning problems; a quick analysis of the probability distributions could be used by the decision-maker.

关键词： Production planning control Job activity scheduling Modeling of manufacturing operations Maintenance scheduling production planning Production activity control

来源：评论

学校读者我要写书评

暂无评论

Photoemission of the Upconverted Hot Electrons in Mn-doped CsPbBr3 Nanocrystals

arXiv

引用

arXiv 2022年

作者： Wang, Chih-Wei Liu, Xiaohan Qiao, Tian Khurana, Mohit Akimov, Alexey V. Son, Dong Hee Department of Chemistry Texas A&M University College StationTX77843 United States Department of Physics Texas A&M University College StationTX77843 United States Center for Nanomedicine Institute for Basic Science Graduate Program of Nano Biomedical Engineering Advanced Science Institute Yonsei University Seoul03722 Korea Republic of

Hot electrons play a crucial role in enhancing the efficiency of photon-to-current conversion or photocatalytic reactions. In semiconductor nanocrystals, energetic hot electrons capable of photoemission can be generated via the upconversion process involving the dopant-originated intermediate state, currently known only in Mn-doped cadmium chalcogenide quantum dots. Here, we report that Mn-doped CsPbBr3 nanocrystals are an excellent platform for generating hot electrons via upconversion that can benefit from various desirable exciton properties and the structural diversity of metal halide perovskites (MHP). 2-dimensional Mn-doped CsPbBr3 nanoplatelets are particularly advantageous for hot electron upconversion due to the strong exciton-dopant interaction mediating the upconversion process. Furthermore, nanoplatelets reveal evidence for the hot electron upconversion via long-lived dark exciton in addition to bright exciton that may enhance the upconversion efficiency. This study not only establishes the feasibility of hot electron upconversion in MHP host but also demonstrates the potential merits of 2-dimensional MHP nanocrystals in hot electron upconversion. © 2022, CC BY.

关键词： Hot electrons

来源：评论

学校读者我要写书评

暂无评论

Discovery of bis-thiourea derivatives as potent tyrosinase inhibitors: combined experimental and computational study

引用

Journal of enzyme inhibition and medicinal chemistry 2025年第1期40卷

作者： Sahachai Sabuakham Sutita Nasoontorn Napat Nuramrum Atit Silsirivanit Thanyada Rungrotmongkol Ratchanok Pingaew Panupong Mahalapbutr Department of Biochemistry Center for Translational Medicine Faculty of Medicine Khon Kaen University Khon Kaen Thailand. Program in Bioinformatics and Computational Biology Graduate School Chulalongkorn University Bangkok Thailand. Center of Excellence in Structural and Computational Biology Department of Biochemistry Faculty of Science Chulalongkorn University Bangkok Thailand. Department of Chemistry Faculty of Science Srinakharinwirot University Bangkok Thailand.

Tyrosinase, a key enzyme in melanin synthesis, serves as a primary target for developing depigmenting agents. The search for novel tyrosinase inhibitors is needed due to the adverse effects of current inhibitors. This study evaluated 16 -thiourea derivatives using and methods, identifying compound , with chlorine substituents, as the most potent inhibitor. Compound outperformed kojic acid in inhibiting mushroom tyrosinase activity and interacted with catalytic copper ions and active site residues, as revealed by molecular docking and copper-chelating assay. Molecular dynamics simulation and MM/PBSA-based free energy calculations confirmed the greater stability and binding affinity of the compound -tyrosinase complex in an aqueous environment compared to kojic acid-tyrosinase complex. Melanin assay revealed that compound significantly suppressed melanin production in B16F10 melanoma cells, showing stronger anti-melanogenic activity than kojic acid. Drug-likeness predictions confirmed its compliance with Lipinski's rule of five, supporting -thiourea derivatives as promising tyrosinase inhibitors.

关键词： Bis-thioureas computational biology molecular docking molecular dynamics simulations tyrosinase

来源：评论

学校读者我要写书评

暂无评论

Revisiting Near-Infrared Features of Kilonovae: The Importance of Gadolinium

arXiv

引用

arXiv 2024年

作者： Rahmouni, Salma Tanaka, Masaomi Domoto, Nanae Kato, Daiji Hotokezaka, Kenta Aoki, Wako Hirano, Teruyuki Kotani, Takayuki Kuzuhara, Masayuki Tamura, Motohide Astronomical Institute Tohoku University Aoba Sendai980-8578 Japan Division for the Establishment of Frontier Sciences Organization for Advanced Studies Tohoku University Sendai980-8577 Japan National Institute for Fusion Science 322-6 Oroshi-cho Toki509-5292 Japan Interdisciplinary Graduate School of Engineering Sciences Kyushu University Fukuoka Kasuga816-8580 Japan Research Center for the Early Universe Graduate School of Science University of Tokyo Bunkyo Tokyo113-0033 Japan National Astronomical Observatory of Japan 2-21-1 Osawa Mitaka Tokyo181-8588 Japan Astronomical Science Program The Graduate University for Advanced Studies SOKENDAI 2-21-1 Osawa Mitaka Tokyo181-8588 Japan Astrobiology Center 2-21-1 Osawa Mitaka Tokyo181-8588 Japan Department of Astronomy Graduate School of Science The University of Tokyo 7-3-1 Hongo Bunkyo-ku Tokyo113-0033 Japan

The observation of the kilonova AT2017gfo and investigations of its light curves and spectra confirmed that neutron star mergers are sites of r-process nucleosynthesis. However, the identification of elements responsible for the spectral features is still challenging, particularly at the near-infrared wavelengths. In this study, we systematically searched for all possible near-infrared transitions of heavy elements using experimentally calibrated energy levels. Our analysis reveals that most candidate elements with strong absorption lines are lanthanides (Z = 57−71) and actinides (Z = 89−103). This is due to their complex structures leading to many low-lying energy levels, which results in strong transitions in the near-infrared range. Domoto et al. (2022) have shown that La III and Ce III can explain the absorption features at λ ∼ 12, 000 − 15, 000 Å. While our results confirm that these two elements show strong infrared features, we additionally identify Gd III as the next most promising species. Due to its unique atomic structure involving the half-filled 4f and the outer 5d orbitals, Gd III has one of the lowest-lying energy levels, between which relatively strong transitions occur. We also find absorption lines caused by Gd III in the near-infrared spectrum of a chemically peculiar star HR 465, which supports their emergence in kilonova spectra. By performing radiative transfer simulations, we confirm that Gd III lines affect the feature at ∼ 12, 000 Å previously attributed to La III. Future space-based time-series observations of kilonova spectra will allow the identification of Gd III lines. © 2024, CC BY.

关键词： Radiative transfer

来源：评论

学校读者我要写书评

暂无评论

Molecular interaction volume model of mixing enthalpy for molten salt system: An integrated calorimetry-model case study of LaCl3-(LiCl-KCl)

arXiv

引用

arXiv 2024年

作者： Goncharov, Vitaliy G. Smith, William Li, Jiahong Eakin, Jeffrey A. Reinhart, Erik D. Boncella, James Gibson, Luke D. Bryantsev, Vyacheslav S. Gong, Rushi Shang, Shun-Li Liu, Zi-Kui Xu, Hongwu Clark, Aurora Guo, Xiaofeng Department of Chemistry Washington State University PullmanWA99164 United States Materials Science and Engineering Program Washington State University PullmanWA99164 United States Computational Sciences and Engineering Division Oak Ridge National Laboratory P.O. Box 2008 Oak RidgeTN37831 United States Chemical Science Division Oak Ridge National Laboratory P.O. Box 2008 Oak RidgeTN37831 United States Department of Materials Science and Engineering Pennsylvania State University University ParkPA16802 United States Earth and Environmental Sciences Division Los Alamos National Laboratory Los Alamos New MexicoNM87545 United States Arizona State University TempeAZ United States Department of Chemistry The University of Utah Salt Lake CityUT84112 United States

Calorimetric determination of enthalpies of mixing (ΔHmix) of multicomponent molten salts often employs empirical models that lack parameters with clear physical interpretation (e.g., coordination numbers, molar volumes, and pair potentials). Although such physics informed models are not always needed, a thermodynamic understanding of the relationships between excess energies of mixing and local to intermediate solvation structures is particularly important for pyrochemical separation, as is the case for lanthanides (Ln), which are common neutron poisons and critical industrial elements found in spent nuclear fuels. Here we implement the molecular interaction volume model (MIVM) to synthesize information from experimentally measured ΔHmix (using high temperature melt drop calorimetry) and the distribution of solvation structures from ab initio molecular dynamics (AIMD) simulations. This was demonstrated by a case study of molten salt system consisted of LaCl3 mixing with a eutectic LiCl-KCl (58mol% - 42mol%) at 873 K and 1133 K. The parameters modelled from MIVM were used to extrapolate excess Gibbs energy (ΔGmix), and compositional dependence of La3+ activity in the LaCl3-(LiCl-KCl) system. In contrast, by AIMD or polarizable ion model (PIM) simulations, a significant deviation regarding the predicted ΔHmix was seen if computed directly from the molecular dynamic trajectories. The integrated experimental and simulation data within the MIVM formalism are generalizable to a wide variety of molten salts and demonstrate a significant improvement over currently employed methods to study molten salts for nuclear and separations sciences. Copyright © 2024, The Authors. All rights reserved.

关键词： Enthalpy

来源：评论

学校读者我要写书评

暂无评论

Investigation of Cyanobacteria-Hosted Antibiotic Resistance in Drinking Water Sources from a Public Health Perspective

SSRN

引用

SSRN 2024年

作者： Volk, Abigail Mills, Molly Chae, Soryong Lee, Jiyoung Division of Environmental Health Sciences College of Public Health The Ohio State University ColumbusOH United States Environmental Sciences Graduate Program The Ohio State University ColumbusOH United States Department of Chemical and Environmental Engineering University of Cincinnati CincinnatiOH United States Department of Food Science & Technology The Ohio State University ColumbusOH United States Infectious Diseases Institute The Ohio State University ColumbusOH United States

Cyanobacterial blooms are intensifying worldwide due to eutrophication and climate change. While traditionally, the focus has been on cyanotoxins, recent studies suggest a potential link between cyanobacteria and antibiotic resistance (AR), including hosting AR genes (ARGs) or promoting gene transfer. However, the role of cyanobacteria as ARG hosts and their contribution to environmental AR in drinking water sources remains largely unexplored. In this study, we examined cyanobacteria as ARG hosts within the broader microbiome context. Samples of drinking water sources were collected from Lake Erie and Grand Lake St. Marys (GLSM) between May and October 2022, both sites afflicted historically by blooms. Cyanobacterial genes and ARGs were quantified with DropletDigital™ PCR (ddPCR), while microcystin concentrations were quantified with enzyme-linked immunosorbent assay (ELISA). Shotgun metagenomic sequencing was employed to analyze the microbiome, with ARGs annotated using DeepARG and Resistance Gene Identifier. Although the alpha diversity and composition of the microbial communities were similar at both locations, the ddPCR and sequencing revealed elevated levels of Microcystis in Lake Erie and Planktothrix in GLSM. The ELISA results showed high microcystin concentrations in GLSM. Cyanobacteria were identified as potential hosts for ARGs, including genes such as rpoB2 and arlR. However, upon further examination, these genes are likely annotated on housekeeping genes and are considered false positives spurious hits. In addition, qac and OXA genes were also annotated, consistent with previous findings on NCBI BLAST in Cyanobacteria. Although cyanobacteria do not appear to be significant contributors to the resistome in these contexts, they may confer some antibiotic resistance. This study underscores the importance of continued monitoring of cyanobacteria within the broader microbiome and resistome, especially in drinking water sources with high contamination levels.

关键词： Lakes

来源：评论

学校读者我要写书评

暂无评论

The 2020 power blackout in the brazilian state of amapá: Lessons learned and opportunities

The 2020 power blackout in the brazilian state of amapá: Le...

引用

2021 IEEE PES Innovative Smart Grid Technologies Conference - Latin America, ISGT Latin America 2021

作者： Do Prado, Josue Campos Santos, Marcos Vinicius Ramos, Lucas Feksa Canha, Luciane Neves Konzen, Gabriel School of Engineering Computer Science Washington State University VancouverWA98686 United States School of Engineering Newcastle University Newcastle Upon TyneNE1 7RU United Kingdom Federal University of Rondônia Department of Electrical Engineering Porto Velho Brazil Graduate Program in Electrical Engineering Federal University of Santa Maria Santa Maria Brazil Division of Energy Economics and Environmental Studies Rio de Janeiro Brazil

ISBN: (纸本)9781665444217

The Brazilian state of Amapa=-notable for having 70% of its area consisting of unexplored Amazonian forests-experienced a massive power blackout in November 2020. An internal short-circuit in a transformer led to an explosion followed by a fire at the Macapa substation. This event left about 90% of the Amapa's population without power for several days in the middle of the COVID-19 pandemic, disrupting the lives of hundreds of thousands of people and raising concerns from several electricity sector stakeholders. This paper discusses select lessons learned from the power blackout and presents future opportunities to improve power system reliability and resilience for the grids in Amapá, and other similar Brazilian states, with a special focus on the increasingly important role of of distributed energy resources and smart grid technologies. © 2021 IEEE.

关键词： Outages

来源：评论

学校读者我要写书评

暂无评论

Reliable extrapolation of deep neural operators informed by physics or sparse observations

arXiv

引用

arXiv 2022年

作者： Zhu, Min Zhang, Handi Jiao, Anran Karniadakis, George Em Lu, Lu Department of Chemical and Biomolecular Engineering University of Pennsylvania PhiladelphiaPA19104 United States Graduate Group in Applied Mathematics and Computational Science University of Pennsylvania PhiladelphiaPA19104 United States Department of Computer and Information Science University of Pennsylvania PhiladelphiaPA19104 United States Division of Applied Mathematics Brown University ProvidenceRI02912 United States School of Engineering Brown University ProvidenceRI02912 United States

Deep neural operators can learn nonlinear mappings between infinite-dimensional function spaces via deep neural networks. As promising surrogate solvers of partial differential equations (PDEs) for real-time prediction, deep neural operators such as deep operator networks (DeepONets) provide a new simulation paradigm in science and engineering. Pure data-driven neural operators and deep learning models, in general, are usually limited to interpolation scenarios, where new predictions utilize inputs within the support of the training set. However, in the inference stage of real-world applications, the input may lie outside the support, i.e., extrapolation is required, which may result to large errors and unavoidable failure of deep learning models. Here, we address this challenge of extrapolation for deep neural operators. First, we systematically investigate the extrapolation behavior of DeepONets by quantifying the extrapolation complexity via the 2-Wasserstein distance between two function spaces and propose a new behavior of bias-variance trade-off for extrapolation with respect to model capacity. Subsequently, we develop a complete workflow, including extrapolation determination, and we propose five reliable learning methods that guarantee a safe prediction under extrapolation by requiring additional information—the governing PDEs of the system or sparse new observations. The proposed methods are based on either fine-tuning a pre-trained DeepONet or multifidelity learning. We demonstrate the effectiveness of the proposed framework for various types of parametric PDEs. Our systematic comparisons provide practical guidelines for selecting a proper extrapolation method depending on the available information, desired accuracy, and required inference speed. © 2022, CC BY-NC-ND.

关键词： Extrapolation

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：