检索结果-内蒙古大学图书馆

Future Glycemic Events Prediction Model Based On Artificial Neural Network

学校读者我要写书评

暂无评论

Future Glycemic Events Prediction Model Based On Artificial ...

2022 International Conference on Innovation and Intelligence for Informatics, Computing, and Technologies, 3ICT 2022

作者： Syafrudin, Muhammad Alfian, Ganjar Fitriyani, Norma Latif Hadibarata, Tony Rhee, Jongtae Anshari, Muhammad Sejong University Department of Artificial Intelligence Seoul Korea Republic of Universitas Gadjah Mada Department of Electrical Engineering and Informatics Vocational College Yogyakarta Indonesia Sejong University Department of Data Science Seoul Korea Republic of Curtin University Environmental Engineering Program Miri Malaysia Dongguk University Department of Industrial and Systems Engineering Seoul Korea Republic of Universiti Brunei Darussalam School of Business and Economics Brunei

ISBN: (数字)9781665451932

ISBN: (纸本)9781665451932

Predicting future glycemic events such as hypoglycemia, hyperglycemia, and normal for type 1 diabetes (T1D) remains a significant and challenging issue. In this study, an artificial neural network (ANN)-based model is proposed to predict the future glycemic events of T1D patients. We utilized five T1D patient datasets to build the models and predict future glycemic events with a prediction horizon (PH) of 30 and 60 minutes ahead of time. We applied the data preprocessing method based on the sliding window approach by sliding the blood glucose time-series data from the past 60 minutes (the last 12 data points) as input and using the next 30 and 60 minutes (the next 6 and 12-th data points) as output. All the numeric blood glucose output data are then transformed into a multi-class classification label, such as hypoglycemia, hyperglycemia, and normal. Our proposed model is then used to learn and create the prediction model from the preprocessed blood glucose dataset. Four performance metrics such as accuracy, precision, recall, and f-1 score were utilized to measure the performance of the classification models used in this study, such as Naïve Bayes (NB), Decision Tree (DT), Support Vector Machine (SVM), and K-Nearest Neighbour (KNN). The results showed that our proposed ANN-based model performed better at predicting future glycemic events than other models, with an average accuracy, precision, recall, and f-1 score of 88.649%, 76.661%, 71.731%, 72.609%, and 83.364%, 60.437%, 61.345%, 60.62% for the PH of 30 and 60 minutes, respectively. As a result, knowing this future glycemic event sooner can help patients avoid potentially dangerous conditions and can eventually be used to improve diabetes management. © 2022 IEEE.

关键词： Decision trees

Quantifying material stocks in long-lived products: Challenges and improvements for informing sustainable resource use strategies

学校读者我要写书评

暂无评论

Resources, Conservation and Recycling 2025年 221卷

作者： Jan Streeck André Baumgart Helmut Haberl Fridolin Krausmann Bowen Cai Tomer Fishman Maud Lanau Peter Berrill Zhi Cao Sebastiaan Deetman David Frantz Volker Krey Alessio Mastrucci Alessio Miatto Stefan Pauliuk Lola Sylvie Annie Rousseau Shoshanna Saxe Danielle Densley Tingley Gamze Ünlü Dominik Wiedenhofer BOKU University Institute of Social Ecology Department of Economics and Social Sciences Schottenfeldgasse 29 1070 Vienna Austria Wuhan University School of Remote Sensing and Information Engineering Wuhan Hubei Province 430079 China Leiden University Institute of Environmental Sciences (CML) 2333 CC Leiden Netherlands Chalmers University of Technology Department of Architecture and Civil Engineering Research Area Sustainable Built Environments Gothenburg 412 96 Sweden Universität Berlin Sustainability Economics of Human Settlements Berlin 10623 Germany College of Environmental Science and Engineering Nankai University Tianjin 300350 China School of Earth System Science Tianjin University Tianjin 300072 China Trier University Geoinformatics -Spatial Data Science Trier Rhineland-Palatinate 54296 Germany International Institute for Applied Systems Analysis (IIASA) Energy Climate and Environment (ECE) Program Schlossplatz 1 2361 Laxenburg Austria Commonwealth Scientific and Industrial Research Organisation (CSIRO) Canberra 2601 ACT Australia University of Freiburg Faculty of Environment and Natural Resources Freiburg Baden-Wuerttemberg D-79102 Germany Norwegian University of Science and Technology (NTNU) Industrial Ecology Programme Department of Energy and Process Engineering Trondheim 7034 Norway University of Toronto Department of Civil and Mineral Engineering Toronto Ontario M5S 1A1 Canada University of Sheffield School of Mechanical Aerospace and Civil Engineering Mappin Street Sheffield S1 3JD United Kingdom

Material stocks in long-lived products require over half of the annual global resource extraction for their construction and maintenance, and lock in energy use through their technical and geospatial characteristics. A thorough understanding of material stocks is therefore essential to inform sustainable resource use strategies. However, despite substantial advances in material stock research in recent decades, their robust quantification remains challenging and bears considerable uncertainties. We assess the (dis)agreement of material stock estimates from 32 recent studies across global, national, and urban scales, and propose recommendations for future work. Overall, we observe medium to high divergences between studies estimating the same material stocks. For end-use categories that aggregate multiple material stocks (e.g., buildings), most global-level estimates show divergences within 140 %. At the national level, most estimates for the USA diverge by <210 %, while those for China by <550 %. At the urban level, most estimates for Beijing fall within 90 %, and for Vienna, within 70 %. For low-income countries, non-residential buildings, and individual materials, the differences are often substantially higher, highlighting the need for an improved scientific basis for policy and planning. These disparities arise from differences in system boundaries, methodology, data sources, definitions, and lack of data to capture the diversity of material stock types. To robustly inform sustainable resource use strategies, the scientific community and practitioners should systematically assess and report sensitivity and uncertainty, and reduce the latter through transparent documentation, model intercomparisons, consensus and open-access databases, enhanced data collection, and comprehensive quantification of material stocks.

关键词： Material flow analysis Sustainable resource management Uncertainty analysis Socioeconomic metabolism Material stocks

A unified scheme to accelerate adaptive cubic regularization and gradient methods for convex optimization

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Jiang, Bo Lin, Tianyi Zhang, Shuzhong Research Center for Management Science and Data Analytics School of Information Management and Engineering Shanghai University of Finance and Economics Shanghai200433 China Department of Industrial Engineering and Operations Research UC Berkeley BerkeleyCA94720 United States Department of Industrial and Systems Engineering University of Minnesota MinneapolisMN55455 United States

In this paper we propose a unified two-phase scheme for convex optimization to accelerate: (1) the adaptive cubic regularization methods with exact/inexact Hessian matrices, and (2) the adaptive gradient method, without any knowledge of the Lipschitz constants for the gradient or the Hessian. This is achieved by tuning the parameters used in the algorithm adaptively in its process of progression, which can be viewed as a relaxation over the existing algorithms in the literature. Under the assumption that the sub-problems can be solved approximately, we establish overall iteration complexity bounds for three newly proposed algorithms to obtain an ϵ-optimal solution. Specifically, we show that the adaptive cubic regularization methods with the exact/inexact Hessian matrix both achieve an iteration complexity in the order of O(1/ϵ 1/3), which matches that of the original accel-erated cubic regularization method presented in [24] assuming the availability of the exact Hessian information and the Lipschitz constants, and the global solution of the sub-problems. Under the same two-phase adaptive acceleration framework, the gradient method achieves an iteration complexity in the order of O(1/ϵ 1/2), which is known to be best possible (cf. [26]). Our numerical experiment results show a clear effect of acceleration displayed in the adaptive Newton's method with cubic regularization on a set of regularized logistic regression instances. Copyright © 2017, The Authors. All rights reserved.

关键词： Convex optimization

Reynosin protects neuronal cells from microglial neuroinflammation by suppressing NLRP3 inflammasome activation mediated by NADPH oxidase

学校读者我要写书评

暂无评论

Chinese Journal of Natural Medicines 2024年第6期22卷 486-500页

作者： YANG Yanqiu CHE Yue FANG Mingxia YAO Xiaohu ZHOU Di WANG Feng CHEN Gang LIANG Dong LI Ning HOU Yue Key Laboratory of Bioresource Research and Development of Liaoning Province College of Life and Health SciencesNorth-eastern UniversityShenyang 110000China National Frontiers Science Center for Industrial Intelligence and Systems Optimization Key Laboratory of Data Analytics and Optimization for Smart IndustryMinistry of EducationNortheastern UniversityShenyang 110000China School of Traditional Chinese Materia Medica Key Laboratory of Innovative Traditional Chinese Medicine for Major Chronic Diseases of Liaoning provinceKey Laboratory for TCM Material Basis Study and Innovative Drug Development of Shenyang CityShenyang Pharmaceutical UniversityShenyang 110000China State Key Laboratory for Chemistry and Molecular Engineering of Medicinal Resources School of Chemistry and Pharmaceutical SciencesGuangxi Normal UniversityGuilin 541000China

Neuroinflammation,mediated by the nucleotide-binding oligomerization domain-like receptor family pyrin domain-containing-3(NLRP3)inflammasome,is a significant contributor to the pathogenesis of neurodegenerative diseases(NDDs).Reynos-in,a natural sesquiterpene lactone(SL),exhibits a broad spectrum of pharmacological effects,suggesting its potential therapeutic ***,the effects and mechanism of reynosin on neuroinflammation remain *** current study explores the effects and mechanisms of reynosin on neuroinflammation using mice and BV-2 microglial cells treated with lipopolysaccharide(LPS).Our findings reveal that reynosin effectively reduces microglial inflammation in vitro,as demonstrated by decreased CD11b expression and lowered interleukin-1 beta(IL-1β)and interleukin-18(IL-18)mRNA and protein ***,in vivo,results showed a re-duction in the number of Iba-1 positive cells and alleviation of morphological alterations,alongside decreased expressions of IL-1βand *** analysis indicates that reynosin inhibits NLRP3 inflammasome activation,evidenced by reduced transcription of NLRP3 and caspase-1,diminished NLRP3 protein expression,inhibited apoptosis-associated speck-like protein containing a CARD(ASC)oli-gomerization,and decreased caspase-1 ***,reynosin curtailed the activation of nicotinamide adenine dinuc-leotide phosphate(NADPH)oxidase,demonstrated by reduced NADP^(+)and NADPH levels,downregulation of gp91^(phox) mRNA,pro-tein expression,suppression of p47^(phox) expression and translocation to the ***,reynosin exhibited a neuroprotective effect against microglial inflammation in vivo and in *** collective findings underscore reynosin’s capacity to mitigate mi-croglial inflammation by inhibiting the NLRP3 inflammasome,thus highlighting its potential as a therapeutic agent for managing neuroinflammation.

关键词： Microglia NLRP3 inflammasome Reactive oxygen species NADPH oxidase Neuron Reynosin

Limited Label-Support Pavement Damage Segmentation Network with Uniform Rectification and Intrinsic Cross-Dimensional Constraint

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Yan, Yunhui Wang, Yanyan Song, Kechen Ma, Shuai Huang, Liming Cui, Wenqi School of Mechanical Engineering and Automation Northeastern University Liaoning Shenyang China National Frontiers Science Center for Industrial Intelligence and Systems Optimization Northeastern University Shenyang China Laboratory of Data Analytics and Optimization for Smart Industry Northeastern University Ministry of Education China

Most recent research on pavement damage segmentation focuses on fully supervised learning to achieve solid performance. The major limitation of this strategy in practice is the heavy reliance on a large number of pixel-level labels, which are labour-intensive and time-consuming to acquire, especially for curvilinear cracks with fine details and inlaid patches with weak edges. This paper proposes a novel methodology to effectively exploit unlabelled data supported by limited label knowledge, thus reducing the heavy annotation burden. The proposed methodology tackles three critical challenges in the pavement damage segmentation based on a semi-supervised paradigm. The first challenge is the noisy pseudo-labels triggered by severely imbalanced prior distributions, which can result in the underutilisation of unlabelled samples. To tackle this challenge, we propose a labelled prior-support uniform rectification module to explicitly improve the prediction quality of pseudo-labels by rectifying their corresponding semantics conditioned on the class-balanced labelled tokens. For the second challenge of the inter-class indistinction, an intrinsic cross-dimensional constraint mechanism is devised to enforce difficult representations to be aligned with the category distribution by the weak vertical constraint within intra-set hierarchical features and the strong parallel cross-set constraint, enabling the model to identify weak texture defects. Finally, an adaptive dual regularization module is proposed to handle the challenge of irregular and variable defect morphologies, achieved by regularizing the deep descriptor based on the intrinsic and external correlations across various granularity attributes. Extensive experiments on three datasets with the aforementioned challenges demonstrate the superiority of the proposed methodology over other advanced approaches. © 2024, The Authors. All rights reserved.

关键词： Semantics

Mitigating the Impact of Labeling Errors on Training via Rockafellian Relaxation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Chen, Louis L. Chern, Bobbie Eckstrand, Eric C. Royset, Amogh Mahapatra Johannes O. Department of Operations Research Naval Postgraduate School MontereyCA United States Meta Platforms Inc. United States Data Science and Analytics Group Naval Postgraduate School MontereyCA United States Department of Industrial and Systems Engineering University of Southern California United States

Labeling errors in datasets are common, arising in a variety of contexts, such as human labeling, noisy labeling, and weak labeling (i.e., image classification). Although neural networks (NNs) can tolerate modest amounts of these errors, their performance degrades substantially once error levels exceed a certain threshold. We propose a new loss reweighting, architecture-independent methodology, Rockafellian Relaxation Method (RRM) for neural network training. Experiments indicate RRM can enhance neural network methods to achieve robust performance across classification tasks in computer vision and natural language processing (sentiment analysis). We find that RRM can mitigate the effects of dataset contamination stemming from both (heavy) labeling error and/or adversarial perturbation, demonstrating effectiveness across a variety of data domains and machine learning tasks. © 2024, CC BY.

关键词： Adversarial machine learning

Learning to Simulate: Generative Metamodeling via Quantile Regression

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Hong, L. Jeff Hou, Yanxi Zhang, Qingkai Zhang, Xiaowei Department of Industrial and Systems Engineering University of Minnesota MinneapolisMN55455 United States School of Data Science Fudan University Shanghai200433 China School of Management Fudan University Shanghai200433 China Department of Management Sciences City University of Hong Kong Kowloon Hong Kong Department of Industrial Engineering and Decision Analytics The Hong Kong University of Science and Technology Clear Water Bay Hong Kong

Stochastic simulation models effectively capture complex system dynamics but are often too slow for real-time decision-making. Traditional metamodeling techniques learn relationships between simulator inputs and a single output summary statistic, such as the mean or median. These techniques enable real-time predictions without additional simulations. However, they require prior selection of one appropriate output summary statistic, limiting their flexibility in practical applications. We propose a new concept: generative metamodeling. It aims to construct a "fast simulator of the simulator," generating random outputs significantly faster than the original simulator while preserving approximately equal conditional distributions. Generative metamodels enable rapid generation of numerous random outputs upon input specification, facilitating immediate computation of any summary statistic for real-time decision-making. We introduce a new algorithm, quantile-regression-based generative metamodeling (QRGMM), and establish its distributional convergence and convergence rate. Extensive numerical experiments demonstrate QRGMM’s efficacy compared to other state-of-the-art generative algorithms in practical real-time decision-making scenarios. © 2023, CC BY-NC-ND.

关键词： Stochastic models

OSN Rumor Control Model Based on Community Immunization

学校读者我要写书评

暂无评论

OSN Rumor Control Model Based on Community Immunization

International Symposium on Parallel and Distributed Processing with Applications, ISPA

作者： Ming Dong Zhiqiang Sun Zhenhua Tan Bin Zhang School of Computer Science and Engineering Northeastern University Shenyang China Software College Northeastern University Shenyang China National Frontiers Science Center for Industrial Intelligence and Systems Optimization Northeastern University Shenyang China Key Laboratory of Data Analytics and Optimization for Smart Industry (Northeastern University) Ministry of Education China

ISBN: (数字)9798331509712

ISBN: (纸本)9798331509729

This paper proposes a rumor control model based on community immunization. Based on the community division and the trust network inference algorithm, the model redefines the standard to measure the importance of nodes in the network. First, the model uses the Louvain clustering algorithm based on the Ochiai coefficient to discover the network community and then presents the trust network inference algorithm. By analyzing the key factors that affect trust transfer between nodes, the trust evaluation between unfamiliar nodes is inferred, and important nodes with a high degree of trust in the network community are calculated. Finally, combined with the characteristics of inner degree and outer degree centrality of nodes in the network community, five types of important nodes in the network are screened out. To avoid repeated selection of nodes, this paper identifies a group of key nodes in the network community for local immunization by means of deduplication and taking intersection, so as to realize effective control of rumors in the network.

关键词： Distributed processing Clustering algorithms Inference algorithms Standards Open data

Exploring Machine Learning Models for Federated Learning: A Review of Approaches, Performance, and Limitations

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Jafarigol, Elaheh Trafalis, Theodore B. Razzaghi, Talayeh Zamankhani, Mona Data Science and Analytics Institute University of Oklahoma 202 W. Boyd St. Room 409 NormanOK73019 United States School of Industrial and Systems Engineering University of Oklahoma 202 W Boyd St. Room 124 NormanOK73019 United States Department of Industrial Engineering Isfahan University of Technology Isfahan Iran

In the growing world of artificial intelligence, federated learning is a distributed learning framework enhanced to preserve the privacy of individuals' data. Federated learning lays the groundwork for collaborative research in areas where the data is sensitive. Federated learning has several implications for real-world problems. In times of crisis, when real-time decision-making is critical, federated learning allows multiple entities to work collectively without sharing sensitive data. This distributed approach enables us to leverage information from multiple sources and gain more diverse insights. This paper is a systematic review of the literature on privacy-preserving machine learning in the last few years based on the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. Specifically, we have presented an extensive review of supervised/unsupervised machine learning algorithms, ensemble methods, meta-heuristic approaches, blockchain technology, and reinforcement learning used in the framework of federated learning, in addition to an overview of federated learning applications. This paper reviews the literature on the components of federated learning and its applications in the last few years. The main purpose of this work is to provide researchers and practitioners with a comprehensive overview of federated learning from the machine learning point of view. A discussion of some open problems and future research directions in federated learning is also provided. © 2023, CC BY.

关键词： Decision making