检索结果-内蒙古大学图书馆

Automating airborne pollen classification: Identifying and interpreting hard samples for classifiers

Heliyon 2025年第2期11卷 e41656页

作者： Milling, Manuel Rampp, Simon D.N. Triantafyllopoulos, Andreas Plaza, Maria P. Brunner, Jens O. Traidl-Hoffmann, Claudia Schuller, Björn W. Damialis, Athanasios CHI – Chair of Health Informatics MRI Technical University of Munich Munich Germany MCML–Munich Center for Machine Learning Germany EIHW – Chair of Embedded Intelligence for Health Care & Wellbeing University of Augsburg Augsburg Germany Institute of Environmental Medicine and Integrative Health Faculty of Medicine University Clinic of Augsburg & University of Augsburg Augsburg Germany Institute of Environmental Medicine Helmholtz Center Munich German Research Center for Environmental Health Germany Faculty of Business and Economics and Faculty of Medicine University of Augsburg Augsburg Germany Department of Technology Management and Economics Technical University of Denmark Denmark Next Generation Technology Region Zealand Denmark Christine Kühne Center for Allergy Research and Education Davos Switzerland MDSI–Munich Data Science Institute Germany GLAM–the Group on Language Audio & Music Imperial College London London United Kingdom Terrestrial Ecology and Climate Change Department of Ecology School of Biology Faculty of Sciences Aristotle University of Thessaloniki Thessaloniki Greece

Deep-learning-based classification of pollen grains has been a major driver towards automatic monitoring of airborne pollen. Yet, despite an abundance of available datasets, little effort has been spent to investigate which aspects pose the biggest challenges to the (often black-box- resembling) pollen classification approaches. To shed some light on this issue, we conducted a sample-level difficulty analysis based on the likelihood for one of the largest automatically-generated datasets of pollen grains on microscopy images and investigated the reason for which certain airborne samples and specific pollen taxa pose particular problems to deep learning algorithms. It is here concluded that the main challenges lie in A) the (partly) co-occurring of multiple pollen grains in a single image, B) the occlusion of specific markers through the 2D capturing of microscopy images, and C) for some taxa, a general lack of salient, unique features. Our code is publicly available under https://***/millinma/SDPollen © 2025

关键词： Deep learning Pollen recognition Sample difficulty analysis

来源：评论

学校读者我要写书评

暂无评论

Time-uniform, nonparametric, nonasymptotic confidence sequences

arXiv

引用

arXiv 2018年

作者： Howard, Steven R. Ramdas, Aaditya McAuliffe, Jon Sekhon, Jasjeet Departments of Statistics Political Science UC Berkeley Departments of Statistics and Data Science United States Machine Learning Carnegie Mellon The Voleon Group United States

A confidence sequence is a sequence of confidence intervals that is uniformly valid over an unbounded time horizon. Our work develops confidence sequences whose widths go to zero, with nonasymptotic coverage guarantees under nonparametric conditions. We draw connections between the Cramér-Chernoff method for exponential concentration, the law of the iterated logarithm (LIL), and the sequential probability ratio test—our confidence sequences are time-uniform extensions of the first;provide tight, nonasymptotic characterizations of the second;and generalize the third to nonparametric settings, including sub-Gaussian and Bernstein conditions, self-normalized processes, and matrix martingales. We illustrate the generality of our proof techniques by deriving an empirical-Bernstein bound growing at a LIL rate, as well as a novel upper LIL for the maximum eigenvalue of a sum of random matrices. Finally, we apply our methods to covariance matrix estimation and to estimation of sample average treatment effect under the Neyman-Rubin potential outcomes model. Copyright © 2018, The Authors. All rights reserved.

关键词： Eigenvalues and eigenfunctions

来源：评论

学校读者我要写书评

暂无评论

machine learning algorithms to classify Fitzpatrick skin types during tissue oxygenation mapping

Machine learning algorithms to classify Fitzpatrick skin typ...

引用

Clinical and Translational Biophotonics, Translational 2022

作者： Kaile, Kacie Sobhan, Masrur Mondal, Ananda Godavarty, Anuradha Department of Biomedical Engineering Optical Imaging Laboratory Florida International University 10555 West Flagler St MiamiFL33174 United States Machine Learning and Data Analytics Group Knight Foundation School of Computing and Information Sciences Florida International University 11200 SW 8th St MiamiFL33199 United States

A machine learning approach is implemented to label different skin tones towards melanin correction of tissue oxygenation maps, when using a smartphone based near-infrared (NIR) imaging device. © 2022 Optica Publ... 详细信息

ISBN: (纸本)9781557528209

关键词： Tissue

来源：评论

学校读者我要写书评

暂无评论

Deep learning algorithms to classify Fitzpatrick skin types for smartphone based NIRS imaging device 15

Deep learning algorithms to classify Fitzpatrick skin types ...

引用

Next-Generation Spectroscopic Technologies XV 2023

作者： Leizaola, Daniela Sobhan, Masrur Kaile, Kacie Mondal, Ananda Mohan Godavarty, Anuradha Optical Imaging Laboratory Department of Biomedical Engineering Florida International University 10555 W Flagler St MiamiFL33174 United States Machine Learning and Data Analytics Group Knight Foundation School Computing and Information Sciences Florida International University 11200 SW 8th St MiamiFL33199 United States

ISBN: (数字)9781510661479

ISBN: (纸本)9781510661462

Non-contact imaging modalities for monitoring wound health could supplement the current standard which is a visual inspection by clinicians. Recently, a smartphone oxygenation tool (SPOT) has been developed for physiological imaging of tissue oxygenation changes in response to treatment. However, upon visual inspection of the wound bed and surrounding area, there are variations of pigmentation. Melanin concentration is a highly absorbing chromophore that can impact spatial oxygenation measurements. The objective of this study was to classify the six Fitzpatrick Skin Types (FST) by applying deep learning techniques prior to correcting SPOT’s oxygenation maps. In this IRB-approved study, control subjects were imaged on seven skin locations of varying FST (I-VI) under three different lighting conditions using SPOT device’s camera. A benchmark dataset with samples of 28 × 28 pixel images of human subjects’ feet was developed in three color spaces (R-G-B, Y-Cb-Cr, L-a-b). A deep learning algorithm, specifically a convolutional neural network (CNN), was used to classify skin into six FST (classes). Preliminary results showed the skin types on control subjects’ feet could be classified using deep learning with hyperparameter tuning with accuracies of > 82%. Our ongoing efforts are focused on extensive in-vivo studies on control subjects of FST I-VI on feet towards future implementation of the technology for diabetic wounds and oxygenation mapping using the SPOT device. © 2023 SPIE.

关键词： Smartphones

来源：评论

学校读者我要写书评

暂无评论

Object Segmentation Tracking from Generic Video Cues

Object Segmentation Tracking from Generic Video Cues

引用

International Conference on Pattern Recognition

作者： Amirhossein Kardoost Sabine Müller Joachim Weickert Margret Keuper Data and Web Science Group University of Mannheim Mannheim Germany Fraunhofer Center Machine Learning Germany Mathematical Image Analysis Group Saarland University Saarbrücken Germany

We propose a light-weight variational framework for online tracking of object segmentations in videos based on optical flow and image boundaries. While high-end computer vision methods on this task rely on sequence specific training of dedicated CNN architectures, we show the potential of a variational model, based on generic video information from motion and color. Such cues are usually required for tasks such as robot navigation or grasp estimation. We leverage them directly for video object segmentation and thus provide accurate segmentations at potentially very low extra cost. Our simple method can provide competitive results compared to the costly CNN-based methods with parameter tuning. Furthermore, we show that our approach can be combined with state-of-the-art CNN-based segmentations in order to improve over their respective results. We evaluate our method on the datasets DAVIS16,17 and SegTrack v2.

关键词： Training Navigation Annotations Video sequences Estimation Object segmentation Task analysis

来源：评论

学校读者我要写书评

暂无评论

CASSPR: Cross Attention Single Scan Place Recognition

CASSPR: Cross Attention Single Scan Place Recognition

引用

International Conference on Computer Vision (ICCV)

作者： Yan Xia Mariia Gladkova Rui Wang Qianyun Li Uwe Stilla João F. Henriques Daniel Cremers Technical University of Munich Munich Center for Machine Learning (MCML) Visual Geometry Group University of Oxford Munich Data Science Institute Microsoft Zurich

Place recognition based on point clouds (LiDAR) is an important component for autonomous robots or self-driving vehicles. Current SOTA performance is achieved on accumulated LiDAR submaps using either point-based or voxel-based structures. While voxel-based approaches nicely integrate spatial context across multiple scales, they do not exhibit the local precision of point-based methods. As a result, existing methods struggle with fine-grained matching of subtle geometric features in sparse single-shot Li-DAR scans. To overcome these limitations, we propose CASSPR as a method to fuse point-based and voxel-based approaches using cross attention transformers. CASSPR leverages a sparse voxel branch for extracting and aggregating information at lower resolution and a point-wise branch for obtaining fine-grained local information. CASSPR uses queries from one branch to try to match structures in the other branch, ensuring that both extract self-contained descriptors of the point cloud (rather than one branch dominating), but using both to inform the out-put global descriptor of the point cloud. Extensive experiments show that CASSPR surpasses the state-of-the-art by a large margin on several datasets (Oxford RobotCar, TUM, USyd). For instance, it achieves AR@1 of 85.6% on the TUM dataset, surpassing the strongest prior model by ~15%. Our code is publicly available. 1

关键词：

来源：评论

学校读者我要写书评

暂无评论

Non-intrusive surrogate modelling using sparse random features with applications in crashworthiness analysis

arXiv

引用

arXiv 2022年

作者： Herold, Maternus Veselovska, Anna Jehle, Jonas Krahmer, Felix Department of Mathematics Technical University of Munich Germany Bmw Group Germany Munich Data Science Institute Germany Munich Center for Machine Learning Germany

Efficient surrogate modelling is a key requirement for uncertainty quantification in data-driven scenarios. In this work, a novel approach of using Sparse Random Features for surrogate modelling in combination with self-supervised dimensionality reduction is described. The method is compared to other methods on synthetic and real data obtained from crashworthiness analyses. The results show a superiority of the here described approach over state of the art surrogate modelling techniques, Polynomial Chaos Expansions and Neural Networks. © 2022, CC BY-NC-ND.

关键词： Crashworthiness

来源：评论

学校读者我要写书评

暂无评论

Customer Segmentation Using Clustering Analysis

Customer Segmentation Using Clustering Analysis

引用

2024 IEEE International Conference on Information Technology, Electronics and Intelligent Communication Systems, ICITEICS 2024

作者： Jiet, Moses Makuei Kamble, Aahash Puri, Chetan Yesankar, Prajyot Verma, Prateek Rewatkar, Rajendra Faculty of Engineering and Technology Department of Computer Science & Design Maharashtra Wardha442001 India Faculty of Engineering and Technology Department of Artificial Intelligence & Data Science Maharashtra Wardha442001 India Faculty of Engineering and Technology Department of Artificial Intelligence & Machine Learning Maharashtra Wardha442001 India Faculty of Engineering and Technology Department of Biomedical Engineering Maharashtra Wardha442001 India

ISBN: (纸本)9798350382693

This research focuses on the crucial role of the clustering technique in data mining, specifically in market forecasting and planning. The study presents a comprehensive report on utilizing the k-means clustering technique and data visualization tools to develop a real- time system for a supermarket, predicting sales across various annual cycles. An open-source dataset of a mall with n = 200 customers divided into k = 3 groups, demonstrated high accuracy in predicting day-to-day sales statistics when compared with actual results. The research highlights the effectiveness of the clustering technique in real-time sales prediction for supermarkets. © 2024 IEEE.

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

MAKING THERMODYNAMIC MODELS OF MIXTURES PREDICTIVE BY machine learning: MATRIX COMPLETION OF PAIR INTERACTIONS

arXiv

引用

arXiv 2022年

作者： Jirasek, Fabian Bamler, Robert Fellenz, Sophie Bortz, Michael Kloft, Marius Mandt, Stephan Hasse, Hans TU Kaiserslautern Kaiserslautern Germany Data Science and Machine Learning University of Tübingen Tübingen Germany Machine Learning Group TU Kaiserslautern Kaiserslautern Germany Kaiserslautern Germany Department of Computer Science University of California Irvine Irvine United States

Predictive models of thermodynamic properties of mixtures are paramount in chemical engineering and chemistry. Classical thermodynamic models are successful in generalizing over (continuous) conditions like temperature and concentration. On the other hand, matrix completion methods (MCMs) from machine learning successfully generalize over (discrete) binary systems;these MCMs can make predictions without any data for a given binary system by implicitly learning commonalities across systems. In the present work, we combine the strengths from both worlds in a hybrid approach. The underlying idea is to predict the pair-interaction energies, as they are used in basically all physical models of liquid mixtures, by an MCM. As an example, we embed an MCM into UNIQUAC, a widely-used physical model for the Gibbs excess energy. We train the resulting hybrid model in a Bayesian machine-learning framework on experimental data for activity coefficients in binary systems of 1,146 components from the Dortmund data Bank. We thereby obtain, for the first time, a complete set of UNIQUAC parameters for all binary systems of these components, which allows us to predict, in principle, activity coefficients at arbitrary temperature and composition for any combination of these components, not only for binary but also for multi-component systems. The hybrid model even outperforms the best available physical model for predicting activity coefficients, the modified UNIFAC (Dortmund) model. Copyright © 2022, The Authors. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

A Coreset-based, Tempered Variational Posterior for Accurate and Scalable Stochastic Gaussian Process Inference

arXiv

引用

arXiv 2023年

作者： Ketenci, Mert Perotte, Adler Elhadad, Noémie Urteaga, Iñigo Columbia University New York United States BCAM Ikerbasque Bilbao Spain Department of Computer Science Department of Biomedical Informatics Machine Learning Group

We present a novel stochastic variational Gaussian process (GP) inference method, based on a posterior over a learnable set of weighted pseudo input-output points (coresets). Instead of a free-form variational family, the proposed coreset-based, variational tempered family for GPs (CVTGP) is defined in terms of the GP prior and the data-likelihood;hence, accommodating the modeling inductive biases. We derive CVTGP's lower bound for the log-marginal likelihood via marginalization of the proposed posterior over latent GP coreset variables, and show it is amenable to stochastic optimization. CVTGP reduces the learnable parameter size to O(M), enjoys numerical stability, and maintains O(M3) time- and O(M2) space-complexity, by leveraging a coreset-based tempered posterior that, in turn, provides sparse and explainable representations of the data. Results on simulated and real-world regression problems with Gaussian observation noise validate that CVTGP provides better evidence lower-bound estimates and predictive root mean squared error than alternative stochastic GP inference methods. Copyright © 2023, The Authors. All rights reserved.

关键词： Mean square error

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：