检索结果-内蒙古大学图书馆

A machine learning Approach to Exploring Ecological Determinacy of Socially Significant Diseases in Moscow

学校读者我要写书评

暂无评论

A Machine Learning Approach to Exploring Ecological Determin...

International Conference on Management of Large-Scale System Development (MLSD)

作者： Anna Marunko Tatiana Zolotova Faculty of Information Technology and Big Data Analysis Financial University Under the Government of the Russian Federation Moscow Russia Department of Data Analysis and Machine Learning Financial University Under the Government of the Russian Federation Moscow Russia

A study of the relationship between some selected environmental indicators and the presence of socially significant diseases in the population of Moscow was carried out. A statistically significant correlation was confirmed. machine learning models were built during the regression analysis. A web interface was developed to automate the processes of predicting the population’s morbidity.

关键词：

YOLO-ICP: Deep learning Integrated Pose Estimation for Bin-Picking of Multiple Objects

学校读者我要写书评

暂无评论

YOLO-ICP: Deep Learning Integrated Pose Estimation for Bin-P...

IEEE SENSORS

作者： Huajian Li Ivan Kraljevski Paul Meyer Constanze Tschöpe Matthias Wolff Cognitive Material Diagnostics Fraunhofer IKTS Cottbus Germany Machine Learning and Data Analysis Fraunhofer IKTS Dresden Germany Chair of Communications Engineering BTU Cottbus-Senftenberg Cottbus Germany

ISBN: (数字)9798350363517

ISBN: (纸本)9798350363524

In this paper, we present a novel deep learning-integrated pipeline called YOLO-ICP that aims to estimate the six degree of freedom (6-DoF) pose of objects using RGB-D sensors and does not require pose labels to train deep learning networks. YOLO-ICP integrates a real-time object detection algorithm with a point cloud registration method to estimate the pose of multiple objects. We evaluated our approach by quantitatively comparing it with baseline models on the OccludedLINEMOD dataset. Experimental results illustrate that our approach outperforms baseline models in challenging scenarios with textureless and occluded objects. In particular, our pipeline shows superior performance when dealing with small and symmetric objects in terms of the ADD(-S) metric.

关键词： Point cloud compression Deep learning YOLO Solid modeling Pipelines Pose estimation Refining Real-time systems 6-DOF Sensors

Uncertainty Estimation and Propagation in Accelerated MRI Reconstruction

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Fischer, Paul Küstner, Thomas Baumgartner, Christian F. Cluster of Excellence – Machine Learning for Science University of Tübingen Germany Medical Image and Data Analysis Lab University Hospital of Tübingen Germany

MRI reconstruction techniques based on deep learning have led to unprecedented reconstruction quality especially in highly accelerated settings. However, deep learning techniques are also known to fail unexpectedly and hallucinate structures. This is particularly problematic if reconstructions are directly used for downstream tasks such as real-time treatment guidance or automated extraction of clinical paramters (e.g. via segmentation). Well-calibrated uncertainty quantification will be a key ingredient for safe use of this technology in clinical practice. In this paper we propose a novel probabilistic reconstruction technique (PHiRec) building on the idea of conditional hierarchical variational autoencoders. We demonstrate that our proposed method produces high-quality reconstructions as well as uncertainty quantification that is substantially better calibrated than several strong baselines. We furthermore demonstrate how uncertainties arising in the MR reconstruction can be propagated to a downstream segmentation task, and show that PHiRec also allows well-calibrated estimation of segmentation uncertainties that originated in the MR reconstruction process. Copyright © 2023, The Authors. All rights reserved.

关键词： Uncertainty analysis

Conformal Prediction in Hierarchical Classification

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Mortier, Thomas Javanmardi, Alireza Sale, Yusuf Hüllermeier, Eyke Waegeman, Willem Department of Environment Ghent University Ghent Belgium Department of Data Analysis and Mathematical Modelling Ghent University Ghent Belgium Institute of Informatics LMU Munich Munich Germany Munich Center for Machine Learning Munich Germany

Conformal prediction has emerged as a widely used framework for constructing valid prediction sets in classification and regression tasks. In this work, we extend the split conformal prediction framework to hierarchical classification, where prediction sets are commonly restricted to internal nodes of a predefined hierarchy, and propose two computationally efficient inference algorithms. The first algorithm returns internal nodes as prediction sets, while the second relaxes this restriction, using the notion of representation complexity, yielding a more general and combinatorial inference problem, but smaller set sizes. Empirical evaluations on several benchmark datasets demonstrate the effectiveness of the proposed algorithms in achieving nominal coverage. © 2025, CC BY.

关键词： Prediction models

PITFALLS OF EPISTEMIC UNCERTAINTY QUANTIFICATION THROUGH LOSS MINIMISATION

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Bengs, Viktor Hüllermeier, Eyke Waegeman, Willem Germany Munich Center for Machine Learning Germany Department of Data Analysis and Mathematical Modeling Ghent University Belgium

Uncertainty quantification has received increasing attention in machine learning in the recent past. In particular, a distinction between aleatoric and epistemic uncertainty has been found useful in this regard. The latter refers to the learner's (lack of) knowledge and appears to be especially difficult to measure and quantify. In this paper, we analyse a recent proposal based on the idea of a second-order learner, which yields predictions in the form of distributions over probability distributions. While standard (first-order) learners can be trained to predict accurate probabilities, namely by minimising suitable loss functions on sample data, we show that loss minimisation does not work for second-order predictors: The loss functions proposed for inducing such predictors do not incentivise the learner to represent its epistemic uncertainty in a faithful *** Codes 68T37 (Primary) 68T30 (Secondary) Copyright © 2022, The Authors. All rights reserved.

关键词： Probability distributions

Blessemflood21: Advancing Flood analysis with a High-Resolution Georeferenced dataset for Humanitarian Aid Support

学校读者我要写书评

暂无评论

Blessemflood21: Advancing Flood Analysis with a High-Resolut...

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Vladyslav Polushko Alexander Jenal Jens Bongartz Immanuel Weber Damjan Hatic Ronald Rösch Thomas März Markus Rauhut Andreas Weinmann Image Processing Department Fraunhofer ITWM Kaiserslautern Germany Working Group Algorithms for Computer Vision Imaging and Data Analysis Darmstadt Germany Center for Machine Learning and Sensor Technology Hochschule Koblenz Remagen Germany

ISBN: (数字)9798350360325

ISBN: (纸本)9798350360332

Floods are an increasingly common global threat, causing emergencies and severe damage to infrastructure. During crises, organisations such as the World Food Programme use remotely sensed imagery, typically obtained through drones, for rapid situational analysis to plan life-saving actions. Computer Vision tools are needed to support task force experts on-site in the evaluation of the imagery to improve their efficiency and to allocate resources strategically. We introduce the BlessemFlood21 dataset to stimulate research on efficient flood detection tools. The imagery was acquired during the 2021 Erftstadt-Blessem flooding event and consists of high-resolution and georeferenced RGB-NIR images. In the resulting RGB dataset, the images are supplemented with detailed water masks, obtained via a semi-supervised human-in-the-loop technique, where in particular the NIR information is leveraged to classify pixels as either water or non-water. We evaluate our dataset by training and testing established Deep learning models for semantic segmentation. With BlessemFlood21 we provide labeled high-resolution RGB data and a baseline for further development of algorithmic solutions tailored to flood detection in RGB imagery.

关键词： Deep learning Training Semantic segmentation Human in the loop Sensors Floods Task analysis

Dissipative residual layers for unsupervised implicit parameterization of data manifolds

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Reshniak, Viktor Data Analysis and Machine Learning Group Oak Ridge National Laboratory Oak RidgeTN37831 United States

We propose an unsupervised technique for implicit parameterization of data manifolds. In our approach, the data is assumed belonging to a lower dimensional manifold in a higher dimensional space, and the data points are viewed as the endpoints of the trajectories originating outside the manifold. Under this assumption, the data manifold is an attractive manifold of a dynamical system to be estimated. We parameterize such dynamical system with a residual neural network and propose a spectral localization technique to ensure it is locally attractive in the vicinity of data. We also present initialization and additional regularization of the proposed residual layers. We mention the importance of the considered problem for the tasks of reinforcement learning and support our discussion with examples demonstrating the performance of the proposed layers in denoising and generative tasks. Copyright © 2022, The Authors. All rights reserved.

关键词： Dynamical systems

Deliberative XAI: How Explanations Impact Understanding and Decision-Making of AI Novices in Collective and Individual Settings

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Schmude, Timothée Koesten, Laura Möller, Torsten Tschiatschek, Sebastian University of Vienna Faculty of Computer Science Research Network Data Science Doctoral School Computer Science Austria University of Vienna Faculty of Computer Science Research Group Visualization and Data Analysis Austria University of Vienna Faculty of Computer Science Research Group Visualization and Data Analysis Research Network Data Science Austria University of Vienna Faculty of Computer Science Research Network Data Science Research Group Data Mining and Machine Learning Austria

XAI research often focuses on settings where people learn about and assess algorithmic systems individually. However, as more public AI systems are deployed, it becomes essential for XAI to facilitate collective understanding and deliberation. We conducted a task-based interview study involving 8 focus groups and 12 individual interviews to explore how explanations can support AI novices in understanding and forming opinions about AI systems. Participants received a collection of explanations organized into four information categories to solve tasks and decide about a system’s deployment. These explanations improved or calibrated participants’ self-reported understanding and decision confidence and facilitated group discussions. Participants valued both technical and contextual information and the self-directed and modular explanation structure. Our contributions include an explanation approach that facilitates both individual and collaborative interaction and explanation design recommendations, including active and controllable exploration, different levels of information detail and breadth, and adaptations to the needs of decision subjects. Copyright © 2024, The Authors. All rights reserved.

关键词：

analysis of the Pattern Recognition Efficiency on Non-Optical Images

学校读者我要写书评

暂无评论

Analysis of the Pattern Recognition Efficiency on Non-Optica...

2021 Ural Symposium on Biomedical Engineering, Radioelectronics and Information Technology, USBEREIT 2021

作者： Andriyanov, Nikita Dementiev, Vitaly Gladkikh, Anatoly Financial University under the Government of the Russian Federation Department of the Data Analysis and Machine Learning Moscow Russia Ulyanovsk State Technical University Department of the Telecommunications Ulyanovsk Russia

ISBN: (纸本)9781728176918

The article examines algorithms for processing non optical images using convolutional neural networks (CNN). Particular attention is paid to the recognition of objects on radar images of the Earth's surface and on X-ray images of baggage inspection. A brief overview of research in this topic is presented. The indicators of recognition efficiency on limited datasets using data augmentation are considered. In addition, the article describes in detail the processes of building neural networks and their training. A comparative analysis of CNNs is carried out for different training parameters and different network architectures. It has been shown that CNNs provide satisfactory results when processing non-standard types of images, such as Xray images of baggage or radar images from Synthetic Aperture Radar (SAR) systems. Furthermore, the text deals with various metrics such as accuracy, precision and recall. The suggested algorithms provides about 90-100% for recognition of SAR images and about 90% for X-ray images. © 2021 IEEE.

关键词： Convolutional neural networks