检索结果-内蒙古大学图书馆

Massive data clustering by multi-scale psychological observations

National Science Review 2022年第2期9卷 43-51页

作者： Shusen Yang Liwen Zhang Chen Xu Hanqiao Yu Jianqing Fan Zongben Xu National Engineering Laboratory of Big Data Analytics Xi'an Jiaotong University Industrial Artificial Intelligent Center Pazhou Laboratory Department of Mathematics and Statistics University of Ottawa Center for Statistics and Machine Learning Princeton University

Clustering is the discovery of latent group structure in data and is a fundamental problem in artificial intelligence,and a vital procedure in data-driven scientific research over all ***,existing methods have various limitations,especially we ak cognitive interpretability and poor computational scalability,when it comes to clustering massive datasets that are increasingly available in all ***,by simulating the multi-scale cognitive observation process of humans,we design a scalable algorithm to detect clusters hierarchically hidden in massive *** observation scale changes,following the Weber-Fechner law to capture the gradually emerging meaningful grouping *** validated our approach in real datasets with up to a billion records and 2000 dimensions,including taxi trajectories,single-cell gene expressions,face images,computer logs and *** approach outperformed popular methods in usability,efficiency,effectiveness and robustness across different domains.

关键词： massive data clustering psychological observation Weber–Fechner law cognitive interpretability computational scalability

来源：评论

学校读者我要写书评

暂无评论

Radar-Based Tremor Quantification Using Deep learning for Improved Parkinson's and Palliative Care Assessment

IEEE Transactions on Radar Systems

引用

IEEE Transactions on Radar Systems 2024年 2卷 1174-1185页

作者： Mejdani, Desar Braunig, Johanna Griebhammer, Stefan G. Krauss, Daniel Steigleder, Tobias Engel, Lukas Jukic, Jelena Rozhdestvenskaya, Anna Winkler, Jurgen Eskofier, Bjoern Ostgathe, Christoph Vossiek, Martin Institute of Microwaves and Photonics Erlangen91058 Germany Machine Learning and Data Analytics Laboratory Erlangen91058 Germany University Hospital Erlangen Department of Palliative Medicine Erlangen91054 Germany University Hospital Erlangen Department of Molecular Neurology Erlangen91054 Germany

Tremor is one of the most prevalent movement disorders, which is especially observed in patients with Parkinson's disease (PD) and other conditions common in palliative care (PC). Effective treatment and monitoring of disease progression are crucial in the context of PC for patients suffering from movement disorders. To this aim, accurate and continuous detection and assessment of tremor characteristics, such as the tremor frequency, is required. Current evaluations by clinicians conducted during sporadic consultations are subjective and intermittent. Radar sensors provide continuous, objective evaluations of tremor motion in patient monitoring, offering a contactless, light-independent, and privacy-preserving method that directly measures tremor's radial motion through the Doppler effect. As previous radar-based research lacks continuous tremor monitoring in realistic scenarios, this study uses a frequency-modulated continuous-wave (FMCW) radar to detect subtle tremor motions and estimates their frequencies amid challenges such as large body motion interference in a clinical setting. Seventeen healthy participants were instructed to mimic tremors in their right hand while performing three diagnostics movements frequently used in tremor assessment, and two activities that were inspired by common daily tasks encountered in PC settings. Tremor detection and frequency estimation was enabled using suitable radar signal preprocessing followed by a neural network comprising convolutional and recurrent layers. Reference frequencies were obtained from an inertial measurement unit (IMU) attached to the participants' right hands. Cross-validation revealed a mean absolute error (MAE) of 1.47 Hz in radar-based frequency estimation compared with the reference and a 90% accuracy in distinguishing the presence or absence of tremor, highlighting the proposed approach's high potential for future tremor assessment. © 2023 IEEE.

关键词： Frequency estimation

来源：评论

学校读者我要写书评

暂无评论

XAIMed-Net: Towards Explainable Brain Tumour Detection in 2D T1-weighted CE-MRI Images Using Transfer learning 26

XAIMed-Net: Towards Explainable Brain Tumour Detection in 2D...

引用

26th Irish machine Vision and Image Processing Conference, IMVIP 2024

作者： Adegboro, Oluwabukola Ganepola, Vayangi Dietlmeier, Julia Mazo, Claudia O'Connor, Noel E. SFI Centre for Research Training in Machine Learning Dublin City University Ireland Insight SFI Research Centre for Data Analytics Dublin City University Ireland School of Computing Dublin City University Ireland

ISBN: (纸本)9781837242672

Malignant brain tumours comprise one of the deadliest types of cancer and their timely and accurate detection is receiving urgent attention. Radiology can benefit from the recent impressive progress of AI and deep learning that provide the non-invasive diagnostic opportunity. However, the challenge of explainable AI-based decision-making processes remains. In this work, we aim to take a step toward more explainable classification of brain tumours in medical images by designing a new convolutional architecture while also leveraging the advantages of transfer learning. Specifically, we introduce a new shallow convolutional head that can be added to a pre-trained ResNet50 model to produce EigenCAM-based importance heatmaps. We investigate pre-training based on the ImageNet and RadImageNet datasets. Furthermore, we also address the problem of weakly-supervised brain tumour segmentation in a challenging 2D T1-weighted CE-MRI dataset by developing an approach to post-process the resulting heatmaps. Our preliminary experimental results with the Dice Score Coefficient of 0.145 and the new objective distance metric μΔ = 59.55 show the potential of combining large pre-trained models with shallow convolutional architectures to localize tumours using only weak classification labels. Our code is publicly available at https://***/juliadietlmeier/Explainable_brain_tumor_detection_in_MRI. © This is an open access article published by the IET under the Creative Commons Attribution License (http://***/licenses/by/3.0/)

关键词： Transfer learning

来源：评论

学校读者我要写书评

暂无评论

XAI-ResUNet: Analysing the Impact of Pre-training in ResUNet Architectures for Multiple Sclerosis Lesion Segmentation using EigenGradCAM 26

XAI-ResUNet: Analysing the Impact of Pre-training in ResUNet...

引用

26th Irish machine Vision and Image Processing Conference, IMVIP 2024

作者： Ganepola, Vayangi Mathur, Prateek Adegboro, Oluwabukola Dietlmeier, Julia Lawlor, Aonghus O'Connor, Noel E. Mazo, Claudia SFI Centre for Research Training in Machine Learning Dublin Ireland Insight SFI Research Centre for Data Analytics Dublin Ireland Dublin City University Dublin Ireland University College Dublin Dublin Ireland

ISBN: (纸本)9781837242672

Multiple Sclerosis (MS) is a chronic disease that causes lesions in the central nervous system. Diagnosing MS is a challenging process that strongly relies on Magnetic Resonance Imaging (MRI) and exhibits high and largely unexplained variability across patients. In this paper, we propose a novel XAI-ResUNet architecture by integrating ResNet-50 as an encoder in a U-Net-like architecture and demystifying the detection and segmentation process by incorporating EigenGradCAM into the encoder. We used the training and testing sets of the MSSEG-2016 dataset for our experiments. We compared three architectures with ResNet-50 pre-trained on ImageNet, RadImageNet, and without pre-training. Our preliminary results show that ResNet-50 pre-trained on ImageNet outperforms the others, achieving a DSC of 0.638. We also demonstrate how pre-training on large image datasets can affect MS lesion detection and segmentation. Our code is publicly available at https://***/VishmiVishara/XAI-ResUNet. © This is an open access article published by the IET under the Creative Commons Attribution License (http://***/licenses/by/3.0/)

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

End-to-End learning for Human Pose Estimation from Raw Millimeter Wave Radar data 58

End-to-End Learning for Human Pose Estimation from Raw Milli...

引用

58th Asilomar Conference on Signals, Systems and Computers, ACSSC 2024

作者： Mueller, Jonas Engel, Lukas Krauss, Daniel Ullmann, Ingrid Vossiek, Martin Eskofier, Bjoern M. Dorschky, Eva Friedrich-Alexander-Universität Erlangen-Nürnber Machine Learning and Data Analytics Lab Erlangen Germany Friedrich-Alexander-Universität Erlangen-Nürnber Institute of Microwaves and Photonics Erlangen Germany

ISBN: (纸本)9798350354058

Millimeter wave radar has gained considerable attention for its potential to analyze human motion, for example, within home environments. Here, radar offers a privacy-preserving and lighting-insensitive alternative to vision-based systems, particularly in smart home applications such as gesture control or human activity monitoring. Current methods involve pre-processing the raw radar data through multiple Fourier transforms, extracting essential parameters such as range, Doppler, azimuth, and elevation information, and applying a constant false alarm rate algorithm for point cloud extraction. However, this approach relies on numerous hyperparameters, requires expert knowledge, and may result in information loss. Our novel approach involves end-to-end learning of neural networks, resulting in a trainable, data-driven, and sparse method. This method automatically extracts important features from the raw radar data, which increases overall accuracy. First, a neural network architecture incorporating attention mechanism is introduced to train an encoder to represent raw radar data as features in an informative low-dimensional vector space. Second, the mean per joint position error of human poses estimated from these features is evaluated using a dataset encompassing a diverse range of human motions. Third, the results are discussed, and conclusions about large-scale attention-based modeling in the radar-based human pose estimation domain are given. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

ProbSAINT: Probabilistic Tabular Regression for Used Car Pricing

ProbSAINT: Probabilistic Tabular Regression for Used Car Pri...

引用

IEEE International Conference on Big data

作者： Kiran Madhusudhanan Gunnar Behrens Maximilian Stubbemann Lars Schmidt-Thieme Information Systems and Machine Learning Lab VWFS Data Analytics Research Center University Of Hildesheim Data Analytics & AI Engineering Volkswagen Financial Services AG

ISBN: (数字)9798350362480

ISBN: (纸本)9798350362497

Used car pricing is a critical aspect of the automotive industry, influenced by many economic factors and market dynamics. With the recent surge in online marketplaces and increased demand for used cars, accurate pricing would benefit both buyers and sellers by ensuring fair transactions. However, the transition towards automated pricing algorithms using machine learning necessitates the comprehension of model uncertainties, specifically the ability to flag predictions that the model is unsure about. Although recent literature proposes the use of boosting algorithms or nearest neighbor-based approaches for swift and precise price predictions, encapsulating model uncertainties with such algorithms presents a complex challenge. We introduce ProbSAINT, a model that offers a principled approach for uncertainty quantification of its price predictions, along with accurate point predictions that are comparable to state-of-the-art boosting techniques. Furthermore, acknowledging that the business prefers pricing used cars based on the number of days the vehicle was listed for sale, we show how ProbSAINT can be used as a dynamic forecasting model for predicting price probabilities for different expected offer durations. Our experiments further indicate that ProbSAINT is especially accurate in instances where it is highly certain. This proves the applicability of its probabilistic predictions in real-world scenarios where trustworthiness is crucial.

关键词： Industries Accuracy Uncertainty machine learning algorithms Pricing Predictive models Probabilistic logic Prediction algorithms Automobiles Vehicle dynamics

来源：评论

学校读者我要写书评

暂无评论

Self-Supervised learning based on Transformed Image Reconstruction for Equivariance-Coherent Feature Representation

arXiv

引用

arXiv 2025年

作者： Wang, Qin Bruns, Benjamin Scharr, Hanno Krajsek, Kai IAS-8: Data Analytics and Machine Learning Forschungszentrum Jülich Germany Forschungszentrum Jülich Germany

The equivariant behaviour of features is essential in many computer vision tasks, yet popular self-supervised learning (SSL) methods tend to constrain equivariance by design. We propose a self-supervised learning approach where the system learns transformations independently by reconstructing images that have undergone previously unseen transformations. Specifically, the model is tasked to reconstruct intermediate transformed images, e.g. translated or rotated images, without prior knowledge of these transformations. This auxiliary task encourages the model to develop equivariance-coherent features without relying on predefined transformation rules. To this end, we apply transformations to the input image, generating an image pair, and then split the extracted features into two sets per image. One set is used with a usual SSL loss encouraging invariance, the other with our loss based on the auxiliary task to reconstruct the intermediate transformed images. Our loss and the SSL loss are linearly combined with weighted terms. Evaluating on synthetic tasks with natural images, our proposed method strongly outperforms all competitors, regardless of whether they are designed to learn equivariance. Furthermore, when trained alongside augmentation-based methods as the invariance tasks, such as iBOT or DINOv2, we successfully learn a balanced combination of invariant and equivariant features. Our approach performs strong on a rich set of realistic computer vision downstream tasks, almost always improving over all baselines. Copyright © 2025, The Authors. All rights reserved.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Sensor-based Stride Segmentation and Gait Parameter Extraction Using a Hidden Markov Model in Patients with Hereditary Spastic Paraplegia

Sensor-based Stride Segmentation and Gait Parameter Extracti...

引用

IEEE EMBS Conference on Biomedical Engineering and Sciences (IECBES)

作者： Alzhraa A. Ibrahim Veronika Koch Verena Jakob Arne Küderle Malte Ollenschlager Kathrin Kotter Bjoern M. Eskofier Martin Regensburger Jürgen Winkler Heiko Gaßner Department of Molecular Neurology University Hospital Erlangen Erlangen Germany Fraunhofer IIS Machine Learning and Data Analytics Lab FAU Fraunhofer Institute for Integrated Circuits Erlangen Germany Machine Learning and Data Analytics Lab FAU Erlangen Germany

ISBN: (数字)9798350383409

ISBN: (纸本)9798350383416

Hereditary Spastic Paraplegia (HSP) comprises a group of neurodegenerative disorders causing progressive lower limb symptoms primarily affecting gait functions. Progressive symmetric gait spasticity poses challenges for gait analysis. Traditional motion capture systems offer precise gait parameters but are confined to laboratory settings. In contrast, wearable sensor technology allows for gait analysis settings in real-world environments. Yet, accurate segmentation of gait cycles and ex-traction of temporal parameters remain challenging, particularly in the context of HSP. This paper introduces a comprehensive approach for gait analysis in patients with HSP, comprising two main components: stride segmentation utilizing a Hidden Markov Model (HMM), enabling robust identification of gait cycles from sensor data, and event detection and temporal gait parameter extraction. By leveraging the inherent temporal dynamics of gait patterns captured by wearable sensors, our method aims to overcome the limitations of existing techniques and provide reliable insights into the gait characteristics of HSP patients. Validation of this approach reveals promising results, with an F1 score of 89% for segmentation achieved through to-fold cross-validation. Additionally, our method demonstrates a mean absolute error of 0.008 seconds for stride time estimation compared to a gold standard motion capture system indicating the validity of our approach and its potential utility in hospital and real-world settings.

关键词： Accuracy Event detection Motion segmentation Hidden Markov models Motion capture Reliability Gait recognition Wearable sensors Parameter extraction Foot

来源：评论

学校读者我要写书评

暂无评论

On the scalability of certified adversarial robustness with generated data 24

On the scalability of certified adversarial robustness with ...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Thomas Altstidl David Dobre Arthur Kosmala Björn Eskofier Gauthier Gidel Leo Schwinn Machine Learning and Data Analytics Lab FAU Erlangen Nürnberg Germany Mila Université de Montréal Canada Data Analytics and Machine Learning Technische Universität München Germany Machine Learning and Data Analytics Lab FAU Erlangen Nürnberg Germany and Institute of AI for Health Helmholtz Zentrum München Germany Mila Université de Montréal Canada and Canada CIFAR AI Chair

ISBN: (纸本)9798331314385

Certified defenses against adversarial attacks offer formal guarantees on the robustness of a model, making them more reliable than empirical methods such as adversarial training, whose effectiveness is often later reduced by unseen attacks. Still, the limited certified robustness that is currently achievable has been a bottleneck for their practical adoption. Gowal et al. and Wang et al. have shown that generating additional training data using state-of-the-art diffusion models can considerably improve the robustness of adversarial training. In this work, we demonstrate that a similar approach can substantially improve deterministic certified defenses but also reveal notable differences in the scaling behavior between certified and empirical methods. In addition, we provide a list of recommendations to scale the robustness of certified training approaches. Our approach achieves state-of-the-art deterministic robustness certificates on CIFAR-10 for the ℓ2 (ε = 36/255) and ℓ∞ (ε = 8/255) threat models, outperforming the previous results by +3.95 and +1.39 percentage points, respectively. Furthermore, we report similar improvements for CIFAR-100.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Channel Dependence, Limited Lookback Windows, and the Simplicity of datasets: How Biased is Time Series Forecasting?

arXiv

引用

arXiv 2025年

作者： Abdelmalak, Ibram Madhusudhanan, Kiran Choi, Jungmin Stubbemann, Maximilian Schmidt-Thieme, Lars Information Science and Machine Learning Lab VWFS Data Analytics Research Center University of Hildesheim Niedersachsen Hildesheim Germany

Time-series forecasting research has converged to a small set of datasets and a standardized collection of evaluation scenarios. Such a standardization is to a specific extent needed for comparable research. However, the underlying assumption is, that the considered setting is a representative for the problem as a whole. In this paper, we challenge this assumption and show that the current scenario gives a strongly biased perspective on the state of time-series forecasting research. To be more detailed, we show that the current evaluation scenario is heavily biased by the simplicity of the current datasets. We furthermore emphasize, that when the lookback-window is properly tuned, current models usually do not need any information flow across channels. However, when using more complex benchmark data, the situation changes: Here, modeling channel-interactions in a sophisticated manner indeed enhances performances. Furthermore, in this complex evaluation scenario, Crossformer, a method regularly neglected as an important baseline, is the SOTA method for time series forecasting. Based on this, we present the Fast Channel-dependent Transformer (FaCT), a simplified version of Crossformer which closes the runtime gap between Crossformer and TimeMixer, leading to an efficient model for complex forecasting datasets. © 2025, CC BY.

关键词：

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：