检索结果-内蒙古大学图书馆

2022 learning, Knowledge, Data, Analysis, LWDA 2022 - Workshops: Special Interest Group on Knowledge Management (FGWM), Knowledge Discovery, Data Mining, and machine learning (FGKD) and Special Interest Group on Database Systems (FGDB)

作者： Seiffarth, Florian Horváth, Tamás Wrobel, Stefan Dept. of Computer Science University of Bonn Bonn Germany Fraunhofer IAIS Schloss Birlinghoven Sankt Augustin Germany Fraunhofer Center for Machine Learning Sankt Augustin Germany

We study a recently introduced adaptation of Tukey depth to graphs and discuss its algorithmic properties and potential applications to mining and learning with graphs. In particular, since it is NP-hard to compute the Tukey depth of a node, as a first contribution we provide a simple heuristic based on maximal closed set separation in graphs and show empirically on different graph datasets that its approximation error is small. Our second contribution is concerned with geodesic core-periphery decompositions of graphs. We show empirically that the geodesic core of a graph consists of those nodes that have a high Tukey depth. This information allows for a parameterized deterministic definition of the geodesic core of a graph. © 2022 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

Anomaly detection of wind turbine time series using Variational Recurrent Autoencoders

arXiv

引用

arXiv 2021年

作者： Preciado-Grijalva, Alan Iza-Teran, Victor Rodrigo Hochschule Bonn-Rhein-Sieg Fraunhofer Center for Machine Learning SCAI Fraunhofer Center for Machine Learning SCAI

Ice accumulation in the blades of wind turbines can cause them to describe anomalous rotations or no rotations at all, thus affecting the generation of electricity and power output. In this work, we investigate the problem of ice accumulation in wind turbines by framing it as anomaly detection of multi-variate time series. Our approach focuses on two main parts: first, learning low-dimensional representations of time series using a Variational Recurrent Autoencoder (VRAE), and second, using unsupervised clustering algorithms to classify the learned representations as normal (no ice accumulated) or abnormal (ice accumulated). We have evaluated our approach on a custom wind turbine time series dataset, for the two-classes problem (one normal versus one abnormal class), we obtained a classification accuracy of up to 96% on test data. For the multiple-class problem (one normal versus multiple abnormal classes), we present a qualitative analysis of the low-dimensional learned latent space, providing insights into the capacities of our approach to tackle such problem. The code to reproduce this work can be found here https://***/agrija9/Wind-Turbines-VRAE-Paper. © 2021, CC BY.

关键词： Wind turbines

来源：评论

学校读者我要写书评

暂无评论

Clark-Park Transformation based Autoencoder for 3-Phase Electrical Signals

Clark-Park Transformation based Autoencoder for 3-Phase Elec...

引用

IEEE PES Innovative Smart Grid Technologies Conference Europe (ISGT Europe)

作者： André Kummerow Mansour Alramlawi Mohammad Dirbas Steffen Nicolai Peter Bretschneider Cognitive Energy Systems Fraunhofer IOSB IOSB-AST Fraunhofer Center for Machine Learning Ilmenau Germany

During the past decades, significant progress has been made in the field of artificial neural networks to process images (Convolutional Neural Networks), audio signals (Temporal Convolutional Networks), or textual information (Transformers). However, for electrical three-phase signals processing, these network architectures ignore important characteristics and therefore lack of computational efficiency. This can lead to performance problems and limits the application potential of neural networks for a fast and efficient local analysis of three-phase electrical current or voltage waveforms. To address this issue, a novel autoencoder architecture is proposed in this paper, which incorporates Clark-Park transformation to learn the representations of three-phase electrical signals. Using unbalanced and noisy voltage signals, the Clark-Park based autoencoder shows superior performance and computational efficiency compared to recurrent and convolutional benchmark architectures.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Interpretable Association Rule Mining Methods on Time-Series in the Maritime Domain 25th

Evaluation of Interpretable Association Rule Mining Methods ...

引用

25th International Conference on Pattern Recognition Workshops, ICPR 2020

作者： Veerappa, Manjunatha Anneken, Mathias Burkart, Nadia Fraunhofer IOSB Fraunhofer Str. 1 Karlsruhe76131 Germany Fraunhofer Center for Machine Learning Karlsruhe Germany

ISBN: (纸本)9783030687953

In decision critical domains, the results generated by black box models such as state of the art deep learning based classifiers raise questions regarding their explainability. In order to ensure the trust of operators in these systems, an explanation of the reasons behind the predictions is crucial. As rule-based approaches rely on simple if-then statements which can easily be understood by a human operator they are considered as an interpretable prediction model. Therefore, association rule mining methods are applied for explaining time-series classifier in the maritime domain. Three rule mining algorithms are evaluated on the classification of vessel types trained on a real world dataset. Each one is a surrogate model which mimics the behavior of the underlying neural network. In the experiments the GiniReg method performs the best, resulting in a less complex model which is easier to interpret. The SBRL method works well in terms of classification performance but due to an increase in complexity, it is more challenging to explain. Furthermore, during the evaluation the impact of hyper-parameters on the performance of the model along with the execution time of all three approaches is analyzed. © 2021, Springer Nature Switzerland AG.

关键词： Association rules

来源：评论

学校读者我要写书评

暂无评论

Visual Prompting for Adversarial Robustness

Visual Prompting for Adversarial Robustness

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Aochuan Chen Peter Lorenz Yuguang Yao Pin-Yu Chen Sijia Liu Michigan State University USA Fraunhofer ITWM and Fraunhofer Center of Machine Learning Germany IBM Research USA

In this work, we leverage visual prompting (VP) to improve adversarial robustness of a fixed, pre-trained model at test time. Compared to conventional adversarial defenses, VP allows us to design universal (i.e., data-agnostic) input prompting templates, which have plug-and-play capabilities at test time to achieve desired model performance without introducing much computation overhead. Although VP has been successfully applied to improving model generalization, it remains elusive whether and how it can be used to defend against adversarial attacks. We investigate this problem and show that the vanilla VP approach is not effective in adversarial defense since a universal input prompt lacks the capacity for robust learning against sample-specific adversarial perturbations. To circumvent it, we propose a new VP method, termed Class-wise Adversarial Visual Prompting (C-AVP), to generate class-wise visual prompts so as to not only leverage the strengths of ensemble prompts but also optimize their interrelations to improve model robustness. Our experiments show that C-AVP outperforms the conventional VP method, with 2.1× standard accuracy gain and 2× robust accuracy gain. Compared to classical test-time defenses, C-AVP also yields a 42× inference time speedup. Code is available at https://***/Phoveran/vp-for-adversarial-robustness.

关键词： Visualization Codes Computational modeling Perturbation methods Signal processing Robustness Acoustics

来源：评论

学校读者我要写书评

暂无评论

Security Fence Inspection at Airports Using Object Detection

Security Fence Inspection at Airports Using Object Detection

引用

IEEE Winter Applications and Computer Vision Workshops (WACVW)

作者： Nils Friederich Andreas Specker Jürgen Beyerer Karlsruhe Institute of Technology Institute for Automation and Applied Informatics Fraunhofer IOSB Fraunhofer Center for Machine Learning Karlsruhe Institute of Technology Institute for Anthropomatics and Robotics

To ensure the security of airports, it is essential to protect the airside from unauthorized access. For this pur-pose, security fences are commonly used, but they require regular inspection to detect damages. However, due to the growing shortage of human specialists and the large man-ual effort, there is the need for automated methods. The aim is to automatically inspect the fence for damage with the help of an autonomous robot. In this work, we explore object detection methods to address the fence inspection task and localize various types of damages. In addition to evaluating four State-of-the-Art (SOTA) object detection models, we analyze the impact of several design criteria, aiming at adapting to the task-specific challenges. This in-cludes contrast adjustment, optimization of hyperparameters, and utilization of modern backbones. The experimental results indicate that our optimized You Only Look Once v5 (YOLOv5) model achieves the highest accuracy of the four methods with an increase of 6.9% points in Average Precision (AP) compared to the baseline. Moreover, we show the real-time capability of the model. The trained models are published on GitHub: hups://***/IN-Friederichlairport_fence_inspection.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Knowledge-Distillation-Based Label Smoothing for Fine-Grained Open-Set Vehicle Recognition

Knowledge-Distillation-Based Label Smoothing for Fine-Graine...

引用

IEEE Winter Applications and Computer Vision Workshops (WACVW)

作者： Stefan Wolf Dennis Loran Jürgen Beyerer Vision and Fusion Lab (IES) Karlsruhe Institute of Technology Karlsruhe Germany Fraunhofer IOSB Karlsruhe Germany Fraunhofer Center for Machine Learning Munich Germany

Fine-grained vehicle classification describes the task of estimating the make and the model of a vehicle based on an image. It provides a useful tool for security authorities to find suspects in surveillance cameras. However, most research about fine-grained vehicle classification is only focused on a closed-set scenario which considers all possible classes to be included in the training. This is not realistic for real-world surveillance applications where the images fed into the classifier can be of arbitrary vehicle models and the large number of commercially available vehicle models renders learning all models impossible. Thus, we investigate fine-grained vehicle classification in an open-set recognition scenario which includes unknown vehicle models in the test set and expects these samples to be rejected. Our experiments highlight the importance of label smoothing for open-set recognition performance. Nonetheless, it lacks recognizing the different semantic distances between vehicle models which result in largely different confusion probabilities. Thus, we propose a knowledge-distillation-based label smoothing approach which considers these different semantic similarities and thus, improves the closed-set classification as well as the open-set recognition performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Bézier Curve Gaussian Processes

arXiv

引用

arXiv 2022年

作者： Hug, Ronny Becker, Stefan Hübner, Wolfgang Arens, Michael Beyerer, Jürgen Fraunhofer IOSB and Fraunhofer Center for Machine Learning Germany Germany

Probabilistic models for sequential data are the basis for a variety of applications concerned with processing timely ordered information. The predominant approach in this domain is given by recurrent neural networks, implementing either an approximate Bayesian approach (e.g. Variational Autoencoders or Generative Adversarial Networks) or a regression-based approach, i.e. variations of Mixture Density networks (MDN). In this paper, we focus on the N-MDN variant, which parameterizes (mixtures of) probabilistic Bézier curves (N-Curves) for modeling stochastic processes. While in favor in terms of computational cost and stability, MDNs generally fall behind approximate Bayesian approaches in terms of expressiveness. Towards this end, we present an approach for closing this gap by enabling full Bayesian inference on top of N-MDNs. For this, we show that N-Curves are a special case of Gaussian processes (denoted as N-GP) and then derive corresponding mean and kernel functions for different modalities. Following this, we propose the use of the N-MDN as a data-dependent generator for N-GP prior distributions. We show the advantages granted by this combined model in an application context, using human trajectory prediction as an example. Copyright © 2022, The Authors. All rights reserved.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Position: A Call to Action for a Human-centered AutoML Paradigm 41

Position: A Call to Action for a Human-Centered AutoML Parad...

引用

41st International Conference on machine learning, ICML 2024

作者： Lindauer, Marius Karl, Florian Klier, Anne Moosbauer, Julia Tornede, Alexander Mueller, Andreas Hutter, Frank Feurer, Matthias Bischl, Bernd Leibniz University Hannover Germany L3S Research Center Hannover Germany Fraunhofer Institute for Integrated Circuits IIS Fraunhofer IIS Nuremberg Germany Ludwig-Maximilians-Universität München Munich Germany Munich Center for Machine Learning Munich Germany Microsoft Redmond United States Albert-Ludwigs-Universität Freiburg Freiburg Germany

Automated machine learning (AutoML) was formed around the fundamental objectives of automatically and efficiently configuring machine learning (ML) workflows, aiding the research of new ML algorithms, and contributing to the democratization of ML by making it accessible to a broader audience. Over the past decade, commendable achievements in AutoML have primarily focused on optimizing predictive performance. This focused progress, while substantial, raises questions about how well AutoML has met its broader, original goals. In this position paper, we argue that a key to unlocking AutoML's full potential lies in addressing the currently underexplored aspect of user interaction with AutoML systems, including their diverse roles, expectations, and expertise. We envision a more human-centered approach in future AutoML research, promoting the collaborative design of ML systems that tightly integrates the complementary strengths of human expertise and AutoML methodologies. Copyright 2024 by the author(s)

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

A Quantitative Human-Grounded Evaluation Process for Explainable machine learning

A Quantitative Human-Grounded Evaluation Process for Explain...

引用

作者： Beckh, Katharina Müller, Sebastian Rüping, Stefan Fraunhofer IAIS Germany University of Bonn Germany ML2R - Competence Center Machine Learning Rhein-Ruhr Germany

Methods from explainable machine learning are increasingly applied. However, evaluation of these methods is often anecdotal and not systematic. Prior work has identified properties of explanation quality and we argue that evaluation should be based on them. In this position paper, we provide an evaluation process that follows the idea of property testing. The process acknowledges the central role of the human, yet argues for a quantitative approach for the evaluation. We find that properties can be divided into two groups, one to ensure trustworthiness, the other to assess comprehensibility. Options for quantitative property tests are discussed. Future research should focus on the standardization of testing procedures. © 2022 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).

关键词： machine learning

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：