检索结果-内蒙古大学图书馆

2nd International Conference on Intelligent Cyber Physical Systems and Internet of Things (ICoICI)

作者： Vidhya, K. Thiyagu, T. M. Taurshia, Antony Nagarajan, B. Jenefa, A. Jebas, Joshua Flower, I Karunya Inst Tech & Sci Sch Cst Coimbatore Tamil Nadu India Vel Tech Rangarajan Dr Sagunthala R&D Inst Sci & Dept CSE Morai India KPR Inst Engn & Technol Dept Artificial Intelligence & Data Sci Coimbatore Tamil Nadu India

ISBN: (纸本)9798331540661;9798331540678

In today's fast-paced world, many individuals struggle to maintain a balanced diet, leading to various nutritional deficiencies. Effective management and education on these deficiencies are crucial for improving public health. Traditional methods of addressing nutritional deficiencies often lack personalization and user engagement. The NutriGuide application, developed using the Flutter framework, aims to revolutionize nutritional management by providing a user-centric, cross-platform solution. Utilizing a comprehensive database of nutrients and symptoms, the application offers personalized dietary recommendations based on user inputs. The dataset includes detailed information on common deficiencies, symptoms, and nutrient-rich foods. Experimental results indicate high user satisfaction, with an average satisfaction score of 4.5 out of 5, and significant improvements in nutritional intake, such as a 28.6% increase in Vitamin A intake and a 50% increase in Vitamin D intake. In conclusion, NutriGuide presents an innovative approach to nutritional health, combining modern technology with evidence-based recommendations to empower users in managing their dietary needs.

关键词： Nutritional Deficiencies Personalized Dietary Recommendations Flutter Framework Cross-Platform Application Nutritional Health Management User-Centric Design data-driven algorithms Mobile Health Applications Nutritional Education

来源：评论

学校读者我要写书评

暂无评论

Comparative analysis of data-driven electric vehicle battery health models across different operating conditions

引用

ENERGY 2024年 309卷

作者： Kumar, Roushan Das, Kaushik Krishna, Anurup Univ Petr & Energy Studies Sch Engn Mech Cluster Dehra Dun 248007 India Indian Inst Technol BHU Dept Elect & Commun Engn Varanasi 221005 India

The work covers the development of a data-driven algorithm and computes the performance of learning models for lithium-ion battery state of health (SOH) estimation. A wide range of environmental and temperature conditions (15 degree celsius, 25 degree celsius, and 35 degree celsius) at different charging and discharging rates of 1C and 2C are used for electric vehicle battery health estimation. The result of the tested data of cell 'a' is validated with a different set of cell 'b' on identical test parameters, and the results are tabulated and compared. At 25 degree celsius, the mean absolute errors for the regression algorithms decision tree (DT), k-nearest neighbor (KNN), and random forest (RF) are 3.78641E-03, 3.62524E-03, and 6.16931E-03. The mean absolute percent error for regression algorithms DT, KNN, and RF is 1.48921E-03, 1.40631E-03, and 2.40260E-03. The root mean square error for regression algorithms DT, KNN, and RF is 1.26813E-02, 9.73320E-03, and 1.17238E-02, and the mean squared error for regression algorithms DT, KNN, and RF is 1.60816E-04, 9.47351E-05, and 1.37448E-04. The results show that the KNN and DT methods accurately estimate the SOH under diversified operating conditions in comparison with RF methods and can foster advanced battery health monitoring systems.

关键词： State of health Lithium-ion battery Charge cycle Discharge cycle Machine learning data-driven algorithms

来源：评论

学校读者我要写书评

暂无评论

Generalization Bounds for data-driven Numerical Linear Algebra 35

Generalization Bounds for Data-Driven Numerical Linear Algeb...

引用

35th Conference on Learning Theory (COLT)

作者： Bartlett, Peter Indyk, Piotr Wagner, Tal Univ Calif Berkeley Berkeley CA 94720 USA MIT Cambridge MA 02139 USA Microsoft Res Redmond WA USA

data-driven algorithms can adapt their internal structure or parameters to inputs from unknown application-specific distributions, by learning from a training sample of inputs. Several recent works have applied this approach to problems in numerical linear algebra, obtaining significant empirical gains in performance. However, no theoretical explanation for their success was known. In this work we prove generalization bounds for those algorithms, within the PAC-learning framework for data-driven algorithm selection proposed by Gupta and Roughgarden (SICOMP 2017). Our main results are closely matching upper and lower bounds on the fat shattering dimension of the learning-based low rank approximation algorithm of Indyk et al. (NeurIPS 2019). Our techniques are general, and provide generalization bounds for many other recently proposed data-driven algorithms in numerical linear algebra, covering both sketching-based and multigrid-based methods. This considerably broadens the class of data-driven algorithms for which a PAC-learning analysis is available.

关键词： data-driven algorithms low rank approximation numerical linear algebra PAC-learning pseudo-dimension fat shattering dimension sketching multigrid

来源：评论

学校读者我要写书评

暂无评论

Moment Matching for Linear Systems in Discrete-Time: Towards Enhanced Performance 63

Moment Matching for Linear Systems in Discrete-Time: Towards...

引用

63rd IEEE Conference on Decision and Control, CDC 2024

作者： Bhattacharjee, Debraj Moreschini, Alessio Astolfi, Alessandro Imperial College London Department of Electrical and Electronic Engineering LondonSW7 2AZ United Kingdom University of Rome 'Tor Vergata' Dipartimento di Ingegneria Civile e Ingegneria Informatica Rome Italy

ISBN: (纸本)9798350316339

We study the moment matching problem for linear systems in a discrete-time setting and introduce a family of reduced-order models that can replicate the steady-state response of the underlying system. We show that reduced-order models can be directly computed from input-output data without needing to compute the moment of the underlying system. We then use a benchmark example to highlight performance improvements of the discrete-time algorithm over its continuous-time counterpart. © 2024 IEEE.

关键词： data-driven algorithms Discrete-time modeling Model reduction Moment matching

来源：评论

学校读者我要写书评

暂无评论

A data-driven method for heat loss estimation from district heating service pipes using heat meter- and GIS data

引用

ENERGY 2023年第1期277卷

作者： Fester, Jakob Ostergaard, Peter Friis Bentsen, Fredrik Nielsen, Brian Kongsgaard Danish Technol Inst Gregersensvej 1 DK-2630 Taastrup Denmark Verdo Varme A S Agerskellet 7 DK-8920 Randers Denmark Grundfos Poul Due Jensens vej 7 DK-8850 Bjerringbro Denmark

District heating (DH) pipes are often older than 20 years and of unknown condition, imposing a strong demand for detailed knowledge about their current state to help cost-effective ongoing renovation and reduce water and energy losses. Here, we develop a scalable method that exploits hourly resolved remotely read heat meter data, pipe coordinates, and soil temperature measurements to continuously estimate the heat loss of service pipes. The method does not require the measured or simulated flows in the full system, making it possible to omit the usual step of establishing a complete thermohydraulic network model which is currently hindering implementation on larger scale. By exploiting open-source soil temperature data, the estimated heat loss is normalized to output the transmission coefficient, U, in W/(m center dot K), allowing for direct intercomparison between pipes of different length and assessment of timely evolution across seasons. Estimated heat losses are validated by complementary techniques, using simulation of data sets and highly time-resolved data from a test area with additional mea-surement equipment installed. Finally, a full-scale application is demonstrated over a year on 1089 service pipes, including detection of a spontaneously emerged leakage, revealed through the model sensitivity towards the consequential changes in heat loss coefficient, U.

关键词： District heating pipe networks Digital tools Smart meter data GIS-data data-driven algorithms Big data Heat loss calculation Asset management Renovation planning

来源：评论

学校读者我要写书评

暂无评论

The Online Knapsack Problem with Departures

引用

PROCEEDINGS OF THE ACM ON MEASUREMENT AND ANALYSIS OF COMPUTING SYSTEMS 2022年第3期6卷 1–32页

作者： Sun, Bo Yang, Lin Hajiesmaili, Mohammad Wierman, Adam Lui, John C. S. Towsley, Don Tsang, Danny H. K. Chinese Univ Hong Kong Hong Kong Peoples R China Nanjing Univ Nanjing Peoples R China Univ Massachusetts Amherst Amherst MA USA CALTECH Pasadena CA 91125 USA Hong Kong Univ Sci & Technol Guangzhou Guangzhou Peoples R China Hong Kong Univ Sci & Technol Hong Kong Peoples R China

The online knapsack problem is a classic online resource allocation problem in networking and operations research. Its basic version studies how to pack online arriving items of different sizes and values into a capacity-limited knapsack. In this paper, we study a general version that includes item departures, while also considering multiple knapsacks and multi-dimensional item sizes. We design a threshold-based online algorithm and prove that the algorithm can achieve order-optimal competitive ratios. Beyond worst-case performance guarantees, we also aim to achieve near-optimal average performance under typical instances. Towards this goal, we propose a data-driven online algorithm that learns within a policy-class that guarantees a worst-case performance bound. In trace-driven experiments, we show that our data-driven algorithm outperforms other benchmark algorithms in an application of online knapsack to job scheduling for cloud computing.

关键词： online knapsack problems knapsack with departures data-driven algorithms competitive ratio cloud job scheduling

来源：评论

学校读者我要写书评

暂无评论

Predicting Positions of People in Human-Robot Conversational Groups 22

Predicting Positions of People in Human-Robot Conversational...

引用

17th Annual ACM/IEEE International Conference on Human-Robot Interaction (HRI)

作者： Hedayati, Hooman Szafir, Daniel Univ North Carolina Chapel Hill Dept Comp Sci Chapel Hill NC 27599 USA

ISBN: (数字)9781665407311

ISBN: (纸本)9781665407311

Robots that operate in social settings must be able to recognize, understand, and reason about human conversational groups (i.e., F-formations). While several algorithms have been developed for identifying such groups, there has been little research on how robots might reason about inaccuracies following group classification (e.g., recognizing only 4 of 5 group members). We address this gap through a data-driven approach that builds knowledge of human group positioning. By analyzing multiple conversational group data sets, we have developed a system for identifying high probability regions that indicate areas where people are likely to stand in a group relative to a single anchor participant. We use knowledge of these regions to train two models, which we implement on a social robot. The first model can estimate the true size of a partially-observed conversational group (i.e., a group where only some of the participants were detected). Our second model can predict the locations where any undetected participants are likely to reside. Together, these models may improve F-formation detection algorithms by increasing robustness to noisy input data.

关键词： F-formations Social robot Human-Robot Interaction (HRI) Conversational groups data-driven algorithms

来源：评论

学校读者我要写书评

暂无评论

A machine-learning minimal-residual (ML-MRes) framework for goal-oriented finite element discretizations

引用

COMPUTERS & MATHEMATICS WITH APPLICATIONS 2021年 95卷 186-199页

作者： Brevis, Ignacio Muga, Ignacio van der Zee, Kristoffer G. Pontificia Univ Catolica Valparaiso Inst Matemat Valparaiso Chile Univ Nottingham Sch Math Sci Nottingham England

We introduce the concept of machine-learning minimal-residual (ML-MRes) finite element discretizations of partial differential equations (PDEs), which resolve quantities of interest with striking accuracy, regardless of the underlying mesh size. The methods are obtained within a machine-learning framework during which the parameters defining the method are tuned against available training data. In particular, we use a provably stable parametric Petrov-Galerkin method that is equivalent to a minimal-residual formulation using a weighted norm. While the trial space is a standard finite element space, the test space has parameters that are tuned in an off-line stage. Finding the optimal test space therefore amounts to obtaining a goal-oriented discretization that is completely tailored towards the quantity of interest. We use an artificial neural network to define the parametric family of test spaces. Using numerical examples for the Laplacian and advection equation in one and two dimensions, we demonstrate that the ML-MRes finite element method has superior approximation of quantities of interest even on very coarse meshes. (C) 2020 Elsevier Ltd. All rights reserved.

关键词： Goal-oriented finite elements Machine-learning acceleration Residual minimization Petrov-Galerkin method Weighted inner-products data-driven algorithms

来源：评论

学校读者我要写书评

暂无评论

Automation of Photonic Networks Using Machine Learning: Case Studies and Future Works

引用

IEEE PHOTONICS TECHNOLOGY LETTERS 2021年第23期33卷 1317-1320页

作者： Rahman, Sabidur Seixas, Nilton F. S. Naznin, Mahmuda Figueiredo, Gustavo B. Sonoma State Univ Dept Comp Sci Rohnert Pk CA 94928 USA Univ Fed Bahia Dept Comp Sci BR-40170110 Salvador BA Brazil Bangladesh Univ Engn & Technol Dept Comp Sci & Engi Dhaka 1205 Bangladesh

Although a "Self-Driving" photonic network is still a long way to go, many time-consuming complex tasks and decision making in photonic networks can be automated using machine learning, and other data-driven solutions. This study explores recent contributions towards photonic network automation, such as alarm prediction, fault localization, resource auto-scaling, quality of transmission prediction, dynamic controller placement, automated service restoration, resource allocation and optimization, minimization of electricity and power supply cost, user data analysis, etc. The studies explored in this letter, provide solution approaches to these problems using wide range of data-driven methods, machine learning, AI, and deep learning based methods. This study discusses different challenges involving these interesting research areas and provides directions for future research opportunities as well.

关键词： Optical fiber networks Automation Heuristic algorithms Machine learning Resource management Predictive models Reinforcement learning Photonic network automation machine learning artificial intelligence data-driven algorithms cost savings

来源：评论

学校读者我要写书评

暂无评论

Model-based machine learning in acoustics applications from a Bayesian perspective 24

Model-based machine learning in acoustics applications from ...

引用

24th International Congress on Acoustics, ICA 2022

作者： Xiang, Ning Chen, Ziqi Zhang, Jiahua Nolan, Mélanie Graduate Program in Architectural Acoustics Rensselaer Polytechnic Institute TroyNY United States

Recent acoustics investigations increasingly employ machine learning methods to analyze experimental data. Using well-understood models or hypotheses, acoustics analyses often embody two levels of inference: model selection and parameter estimation based on the chosen model. Model-based Bayesian analysis provides solutions of both inference levels centered around Bayes' theorem within a unified framework. The data-driven machine learning method represents a learning process from data in order to update our knowledge. This is exactly consistent with the core of Bayesian probability theory, which represents how our prior knowledge is updated in presence of the data. This paper discusses the model-based machine learning methods in a way of thinking like a Bayesian. In particular, it emphasizes that the well-understood models are considered as a part of the prior knowledge which are readily incorporated in the learning process. This paper highlights data-driven machine learning methods from a Bayesian perspective based on recent acoustics investigations, such as acoustic array signal processing, normal incident impedance tube measurements, chamber-based absorption measurements and wavenumber spectral analysis in enclosed spaces. Numerical challenges and promising solutions for two-levels of Bayesian learning are also discussed. © ICA *** rights reserved

关键词： Bayesian inference data-driven algorithms machine learning model-based analysis

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：