检索结果-内蒙古大学图书馆

Dealing with Imbalanced Dataset Leveraging Boundary Samples Discovered by Support Vector Data Description

学校读者我要写书评

暂无评论

computers, Materials & Continua 2021年第3期66卷 2691-2708页

作者： Zhengbo Luo Hamïd Parvïn Harish Garg Sultan Noman Qasem Kim-Hung Pho Zulkefli Mansor Graduate School of Information Production and SystemsWaseda UniversityTokyoJapan Institute of Research and Development Duy Tan UniversityDa Nang550000Vietnam Faculty of Information Technology Duy Tan UniversityDa Nang550000Vietnam Department of Computer Science Nourabad Mamasani BranchIslamic Azad UniversityMamasaniIran School of Mathematics Thapar Institute of Engineering and TechnologyDeemed UniversityPatialaPunjab147004India Computer Science Department College of Computer and Information SciencesAl Imam Mohammad Ibn Saud Islamic UniversityRiyadhSaudi Arabia Computer Science Department Faculty of Applied ScienceTaiz UniversityTaizYemen Fractional Calculus Optimization and Algebra Research GroupFaculty of Mathematics and StatisticsTon Duc Thang UniversityHo Chi Minh CityVietnam Fakulti Teknologi dan Sains Maklumat Universiti Kebangsaan MalaysiaSelangorMalaysia

These days,imbalanced datasets,denoted throughout the paper by ID,(a dataset that contains some(usually two)classes where one contains considerably smaller number of samples than the other(s))emerge in many real world problems(like health care systems or disease diagnosis systems,anomaly detection,fraud detection,stream based malware detection systems,and so on)and these datasets cause some problems(like under-training of minority class(es)and over-training of majority class(es),bias towards majority class(es),and so on)in classification process and ***,these datasets take the focus of many researchers in any science and there are several solutions for dealing with this *** main aim of this study for dealing with IDs is to resample the borderline samples discovered by Support Vector Data Description(SVDD).There are naturally two kinds of resampling:Under-sampling(U-S)and oversampling(O-S).The O-S may cause the occurrence of over-fitting(the occurrence of over-fitting is its main drawback).The U-S can cause the occurrence of significant information loss(the occurrence of significant information loss is its main drawback).In this study,to avoid the drawbacks of the sampling techniques,we focus on the samples that may be *** data points that can be misclassified are considered to be the borderline data points which are on border(s)between the majority class(es)and minority class(es).First by SVDD,we find the borderline examples;then,the data resampling is applied over *** the next step,the base classifier is trained on the newly created ***,we compare the result of our method in terms of Area Under Curve(AUC)and F-measure and G-mean with the other state-of-the-art *** show that our method has betterresults than the other state-of-the-art methods on our experimental study.

关键词： Imbalanced learning classification borderline examples

Fast, Accurate Manifold Denoising by Tunneling Riemannian Optimization

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Wang, Shiyu Avagyan, Mariam Shen, Yihan Lamy, Arnaud Wang, Tingran Márka, Szabolcs Márka, Zsuzsa Wright, John Department of Electrical Engineering Columbia University New York United States Data Science Institute Columbia University New York United States Department of Computer Science Columbia University New York United States Department of Physics Columbia University New York United States Columbia Astrophysics Laboratory Columbia University New York United States Department of Applied Physics and Applied Mathematics Columbia University New York United States

Learned denoisers play a fundamental role in various signal generation (e.g., diffusion models) and reconstruction (e.g., compressed sensing) architectures, whose success derives from their ability to leverage low-dimensional structure in data. Existing denoising methods, however, either rely on local approximations that require a linear scan of the entire dataset or treat denoising as generic function approximation problems, often sacrificing efficiency and interpretability. We consider the problem of efficiently denoising a new noisy data point sampled from an unknown ddimensional manifold M ∈ D, using only noisy samples. This work proposes a framework for test-time efficient manifold denoising, by framing the concept of "learning-to-denoise" as "learning-to-optimize". We have two technical innovations: (i) online learning methods which learn to optimize over the manifold of clean signals using only noisy data, effectively "growing" an optimizer one sample at a time. (ii) mixed-order methods which guarantee that the learned optimizers achieve global optimality, ensuring both efficiency and near-optimal denoising performance. We corroborate these claims with theoretical analyses of both the complexity and denoising performance of mixed-order traversal. Our experiments on scientific manifolds demonstrate significantly improved complexity-performance tradeoffs compared to nearest neighbor search, which underpins existing provable denoising approaches based on exhaustive search. Copyright © 2025, The Authors. All rights reserved.

关键词： Nearest neighbor search

DROPLET MOTION WITH CONTACT-LINE FRICTION: LONG-TIME ASYMPTOTICS IN COMPLETE WETTING

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Giacomelli, Lorenzo Gnann, Manuel V. Peschka, Dirk SBAI Department Sapienza University of Rome Via A. Scarpa 16 Roma00161 Italy Delft Institute of Applied Mathematics Faculty of Electrical Engineering Mathematics and Computer Science Delft University of Technology Mekelweg 4 Delft2628 CD Netherlands Weierstrass Institute Mohrenstrasse 39 Berlin10117 Germany

We consider the thin-film equation for a class of free boundary conditions modelling friction at the contact line, as introduced by E and Ren. Our analysis focuses on formal longtime asymptotics of solutions in the perfect wetting regime. In particular, through the analysis of quasi-self-similar solutions, we characterize the profile and the spreading rate of solutions depending on the strength of friction at the contact line, as well as their (global or local) corrections, which are due to the dynamical nature of the free boundary conditions. These results are complemented with full transient numerical solutions of the free boundary *** Codes 35C06, 35K65, 76M10, 76A20 Copyright © 2023, The Authors. All rights reserved.

关键词： Friction

Weisfeiler and Leman go machine learning: the story so far

学校读者我要写书评

暂无评论

The Journal of Machine Learning Research 2023年第1期24卷 15865-15923页

作者： Christopher Morris Yaron Lipman Haggai Maron Bastian Rieck Nils M. Kriege Martin Grohe Matthias Fey Karsten Borgwardt Department of Computer Science RWTH Aachen University Aachen Germany Meta AI Research Department of Computer Science and Applied Mathematics Weizmann Institute of Science Rehovot Israel NVIDIA Research Tel Aviv Israel AIDOS Lab Institute of AI for Health Helmholtz Zentrum München and Technical University of Munich Munich Germany Faculty of Computer Science and Research Network Data Science University of Vienna Vienna Austria Kumo.AI Mountain View CA Machine Learning & Computational Biology Lab Department of Biosystems Science and Engineering ETH Zürich Basel Switzerland and Swiss Institute of Bioinformatics Lausanne Switzerland

In recent years, algorithms and neural architectures based on the Weisfeiler-Leman algorithm, a well-known heuristic for the graph isomorphism problem, have emerged as a powerful tool for machine learning with graphs and relational data. Here, we give a comprehensive overview of the algorithm's use in a machine-learning setting, focusing on the supervised regime. We discuss the theoretical background, show how to use it for supervised graph and node representation learning, discuss recent extensions, and outline the algorithm's connection to (permutation-)equivariant neural architectures. Moreover, we give an overview of current applications and future directions to stimulate further research.

关键词： machine learning for graphs graph neural networks Weisfeiler-Leman algorithm expressivity equivariance

Weather of the dorm Wi-Fi ecosystem at the University of Colorado Boulder: Fall semester 2019 to spring semester 2020 - A case study of Wi-Fi including a campus response to the COVID-19 perturbation

学校读者我要写书评

暂无评论

arXiv 2021年

作者： McGrath, Jake Davis, Armen Curry, James Gartner, Orrie Rodrigues, Glenn Spielman, Seth Massey, Daniel Aeropace Engineering Applied Mathematics Office of Information Technology Office of Data Analytics Department of Computer Science

"Growing use of network-enabled technology in Institutions of Higher Education (IHEs) among students, staff, and faculty means that there has been increasing demand to adapt technology platforms and tools that transform student learning strategies, faculty teaching, research modalities, as well as general operations. In fact, many of the new modalities are a necessity for doing IHE business. In August 2019, our research team, at the University of Colorado Boulder, began collecting and analyzing data from the campus Wi-Fi network. A goal of the research was to answer the question of "what passive sensing" of the IHE's Wi-Fi might be able to tell you about the gross dynamics of the "Wi-Fi weather" in the IHE ecosystem? Or more generally, what does anonymized data tell us about the dynamics in a IHE's ecosystem. Anonymized data were made available by the University of Colorado Boulder (CU) Office of Information Technology (OIT). Our goal was to understand the campus' dynamical ecosystem as a reflection of its collected Wi-Fi data. Those data could then be used to develop forecast models and an understanding of the dynamics of the university ecosystem where the dynamics of Wi-Fi connected device count could be used as a proxy for the ebb and flow of large scale, and small scale, behavior in the ecosystem. The analogy with weather prediction seemed appropriate and a viable strategy. Starting Fall 2019, data were collected in the 'observational phase' (data collection is ongoing). In the 'analysis phase,' briefly touched on here, we applied Singular Spectrum Analysis (SSA) "eigen decomposition," to deconstruct Wi-Fi data from dorms, the central campus dining cafeteria, the recreation center, and other buildings on campus. That analysis led to the identification of clusters of buildings that behaved similarly. Several campus buildings are dual use and they are placed in different clusters. Just as in the case of models of the weather, a final component of this research was

关键词： Weather forecasting

Tensor product-based model transformation approach to cart position modeling and control in pendulum-cart systems

学校读者我要写书评

暂无评论

Tensor product-based model transformation approach to cart p...

作者： Hedrea, Elena-Lorena Precup, Radu-Emil Petriu, Emil M. Bojan-Dragos, Claudia-Adina Hedrea, Ciprian Department of Automation and Applied Informatics Politehnica University of Timisoara Timisoara Romania School of Engineering Edith Cowan University JoondalupWA Australia School of Electrical Engineering and Computer Science University of Ottawa OttawaON Canada Department of Mathematics Politehnica University of Timisoara Timisoara Romania

The paper presents the application of the tensor product (TP)-based model transformation technique to model and control the cart position of single-input multi-output pendulum-cart systems (PCSs). The modeling is first carried out. The derived TP model, the nonlinear model of PCS, and the laboratory equipment are tested in the same open-loop scenario, and their corresponding outputs are collected, measured, and compared. The parallel distributed compensation (PDC) technique is next applied to TP-based cart position controller design. A linear state feedback control design is also designed in order to conduct a comparative analysis. The two proposed control system structures are experimentally validated and tested in the same scenarios on the laboratory equipment, and their performance indices are analyzed and compared. © 2021 Chinese Automatic Control Society and John Wiley & Sons Australia, Ltd

关键词： Position control

CONVERGENCE SPEED AND APPROXIMATION ACCURACY OF NUMERICAL MCMC

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Cui, Tiangang Dong, Jing Jasra, Ajay Tong, Xin T. School of Mathematics Monash University Australia Graduate School of Business Columbia University United States Applied Mathematics and Computational Science Program Computer Electrical Mathematical Sciences and Engineering Division King Abdullah University of Science and Technology Saudi Arabia Department of Mathematics National University of Singapore Singapore

When implementing Markov Chain Monte Carlo (MCMC) algorithms, perturbation caused by numerical errors is sometimes inevitable. This paper studies how perturbation of MCMC affects the convergence speed and Monte Carlo estimation accuracy. Our results show that when the original Markov chain converges to stationarity fast enough and the perturbed transition kernel is a good approximation to the original transition kernel, the corresponding perturbed sampler has similar convergence speed and high approximation accuracy as well. We discuss two different analysis frameworks: ergodicity and spectral gap, both are widely used in the literature. Our results can be easily extended to obtain non-asymptotic error bounds for MCMC estimators. We also demonstrate how to apply our convergence and approximation results to the analysis of specific sampling algorithms, including Random walk Metropolis and Metropolis adjusted Langevin algorithm with perturbed target densities, and parallel tempering Monte Carlo with perturbed densities. Finally we present some simple numerical examples to verify our theoretical claims. Copyright © 2022, The Authors. All rights reserved.

关键词： Inverse problems

A Comparative Study of Deep Learning Robustness for Sensor-based Human Activity Recognition

学校读者我要写书评

暂无评论

A Comparative Study of Deep Learning Robustness for Sensor-b...

International Conference on Telecommunications and Signal Processing (TSP)

作者： Sakorn Mekruksavanich Anuchit Jitpattanakul Department of Computer Engineering School of Information and Communication Technology University of Phayao Phayao Thailand Department of Mathematics Faculty of Applied Science Intelligent and Nonlinear Dynamic Innovations Research Center King Mongkut’s University of Technology North Bangkok Bangkok Thailand

Recognition of human activities has become a highly significant area of research in the current era of the Internet of Things and A.I. technologies. Human activity recognition (HAR) plays a crucial role in monitoring and analyzing human behaviors using various types of sensors. Such sensor-based HAR systems are being used in various industry domains, including healthcare, professional sports, and worker assessment in intelligent factories. The integration of micro electronics mechanical systems sensor technology in smart wearable devices has significantly improved the capabilities of HAR using machine learning and deep learning techniques. However, processing longtime dependent sequence samples with noisy data is still a significant challenge, affecting the classification time and accuracy. This study aimed to analyze noise-tolerant deep learning models for recognizing physical activities from noisy smartphone data. The study analyzed the recognition performances of the five most popular deep learning networks for HAR under different levels of Gaussian noise. The results indicated that the BiGRU network demonstrated outstanding robustness to Gaussian noise of different levels.

关键词：

Functional neural network control chart

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Kulahci, Murat Lepore, Antonio Palumbo, Biagio Sposito, Gianluca Technical University of Denmark Department of Applied Mathematics and Computer Science Kongens Lyngby Denmark Luleå University of Technology Department of Business Administration Technology and Social Sciences Luleå Sweden University of Naples Federico II Department of Industrial Engineering Naples Italy

In many Industry 4.0 data analytics applications, quality characteristic data acquired from manufacturing processes are better modeled as functions, often referred to as profiles. In practice, there are situations where a scalar quality characteristic, referred to also as the response, is influenced by one or more variables in the form of functional data, referred to as functional covariates. To adjust the monitoring of the scalar response by the effect of this additional information, a new profile monitoring strategy is proposed on the residuals obtained from the functional neural network, which is able to learn a possibly nonlinear relationship between the scalar response and the functional covariates. An extensive Monte Carlo simulation study is performed to assess the performance of the proposed method with respect to other control charts that appeared in the literature before. Finally, a case study in the railway industry is presented with the aim of monitoring the heating, ventilation and air conditioning systems installed onboard passenger trains. © 2023, CC BY.

关键词： Control charts