检索结果-内蒙古大学图书馆

Verification of Square Lattices with Dedicated Channels by Infinite Petri Nets

学校读者我要写书评

暂无评论

Verification of Square Lattices with Dedicated Channels by I...

2020 IEEE International Conference on Problems of Infocommunications science and Technology, PIC S and T 2020

作者： Shmeleva, Tatiana Kostikov, Alexander A.S. Popov Odessa National Academy of Telecommunications Computer Science Department Odessa Ukraine Informatics and Engineering Graphics Department Donbass State Engineering Academy Kramatorsk Ukraine

ISBN: (纸本)9781728191775

Abstract structures of rectangular lattice with various edge conditions and neighborhoods play a key role in telecommunications, computing, nanotechnologies, and biological systems. For modeling rectangular structures, an infinite Petri net model has been developed and investigated. Based on the parametric specification of rectangular lattice models, an infinite system of linear homogenous equations has been derived. Using the earlier developed algorithm, a parametric solution of the system has been obtained, the solution contains all the positive components. Thus, the model is a p-invariant Petri net for any given size of square lattice. Consequently, we can use storage elements of limited capacity for practical implementations of a rectangular lattice structure. © 2020 IEEE.

关键词： Petri nets

Synthetic Data for Face Recognition: Current State and Future Prospects

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Boutros, Fadi Struc, Vitomir Fierrez, Julian Damer, Naser Fraunhofer Institute for Computer Graphics Research IGD Darmstadt Germany Faculty of Electrical Engineering University of Ljubljana Ljubljana Slovenia School of Engineering Universidad Autonoma de Madrid Madrid Spain Department of Computer Science TU Darmstadt Darmstadt Germany

Over the past years, deep learning capabilities and the availability of large-scale training datasets advanced rapidly, leading to breakthroughs in face recognition accuracy. However, these technologies are foreseen to face a major challenge in the next years due to the legal and ethical concerns about using authentic biometric data in AI model training and evaluation along with increasingly utilizing data-hungry state-of-the-art deep learning models. With the recent advances in deep generative models and their success in generating realistic and high-resolution synthetic image data, privacy-friendly synthetic data has been recently proposed as an alternative to privacy-sensitive authentic data to overcome the challenges of using authentic data in face recognition development. This work aims at providing a clear and structured picture of the use-cases taxonomy of synthetic face data in face recognition along with the recent emerging advances of face recognition models developed on the bases of synthetic data. We also discuss the challenges facing the use of synthetic data in face recognition development and several future prospects of synthetic data in the domain of face recognition. Copyright © 2023, The Authors. All rights reserved.

关键词： Face recognition

Multilabel segmentation and analysis of skeletal muscle and adipose tissue in routine abdominal CT scans

学校读者我要写书评

暂无评论

computers in Biology and Medicine 2025年 186卷 109622-109622页

作者： Kreher, Robert Hille, Georg Preim, Bernhard Hinnerichs, Mattes Borggrefe, Jan Surov, Alexey Saalfeld, Sylvia Department of Simulation and Graphics Faculty of Computer Science University of Magdeburg Universitätsplatz 2 Magdeburg39106 Germany Department of Radiology and Nuclear Medicine University Hospital Magdeburg Germany Department of Radiology Neuroradiology and Nuclear Medicine Johannes Wesling University Hospital Minden Germany Department of Computational Medicine Ilmenau University of Technology Germany

Purpose: This paper presents a deep learning-based multi-label segmentation network that extracts a total of three separate adipose tissues and five different muscle tissues in CT slices of the third lumbar vertebra and additionally improves the segmentation of the intermuscular fat. Method: Based on a self-created data set of 130 patients, an extended Unet structure was trained and evaluated with the help of Dice score, IoU and Pixel Accuracy. In addition, the interobserver variability for the decision between ground truth and post-processed segmentation was calculated to illustrate the relevance in everyday clinical practice. Results: On average, the presented approach achieved 91.0±0.065% DSC for the muscle tissues and 88.9±0.062% DSC for the adipose tissues. It was shown that by post-processing the intermuscular fat tissue, physicians prefer the result of the algorithm presented in the paper to their segmentation by 91.51%. Conclusion: The algorithm provided more precise segmentations of muscles and adipose tissue, demonstrating high-quality performance in segmenting muscle tissue. In qualitative evaluations, physicians preferred the algorithm's segmentation over expert segmentations, with the preference quantified as 91.51%. This indicates that, based on their assessment, the algorithm's results were significantly favored. This qualitative feedback supports the algorithm's use in subsequent analyses of patient fitness, leveraging the detailed information it provides. © 2025 The Authors

关键词： Muscle

Polar, Spherical and Orthogonal Space Subdivisions for an Algorithm Acceleration: O(1) Point-in-Polygon/Polyhedron Test

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Skala, Vaclav The University of West Bohemia Faculty of Applied Sciences Department .of Computer Science and Engineering Center of Computer Graphics and Visualization Univerzitni 8 PlzenCZ 30614 Czech Republic

Acceleration of algorithms is becoming a crucial problem, if larger data sets are to be processed. Evaluation of algorithms is mostly done by using computational geometry approach and evaluation of computational complexity. However in today’s engineering problems this approach does not respect that number of processed items is always limited and a significant role plays also speed of read/write operations. One general method how to speed up an algorithm is application of space subdivision technique and usually the orthogonal space subdivision is used. In this paper non-orthogonal subdivisions are described. The proposed approach can significantly improve memory consumption and run-time complexity. The proposed modified space subdivision techniques are demonstrated on two simple problems Point-in-Convex Polygon and Point-in-Convex Polyhedron *** Codes 65D17, 65D18 © 2022, CC BY.

关键词： Computational geometry

Privacy-friendly Synthetic Data for the Development of Face Morphing Attack Detectors

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Damer, Naser Fontanillo López, César Augusto Fang, Meiling Spiller, Noemie Pham, Minh Vu Boutros, Fadi Fraunhofer Institute for Computer Graphics Research IGD Darmstadt Germany Department of Computer Science TU Darmstadt Darmstadt Germany Centre for IT & IP Law KU Leuven Leuven Belgium

The main question this work aims at answering is: "can morphing attack detection (MAD) solutions be successfully developed based on synthetic data?". Towards that, this work introduces the first synthetic-based MAD development dataset, namely the Synthetic Morphing Attack Detection Development dataset (SMDD). This dataset is utilized successfully to train three MAD backbones where it proved to lead to high MAD performance, even on completely unknown attack types. Additionally, an essential aspect of this work is the detailed legal analyses of the challenges of using and sharing real biometric data, rendering our proposed SMDD dataset extremely essential. The SMDD dataset, consisting of 30,000 attack and 50,000 bona fide samples, is publicly available for research purposes. Copyright © 2022, The Authors. All rights reserved.

关键词： Biometrics

Privacy-friendly Synthetic Data for the Development of Face Morphing Attack Detectors

学校读者我要写书评

暂无评论

Privacy-friendly Synthetic Data for the Development of Face ...

IEEE computer Society Conference on computer Vision and Pattern Recognition Workshops (CVPRW)

作者： Naser Damer Cé sar Augusto Fontanillo Ló pez Meiling Fang Noé mie Spiller Minh Vu Pham Fadi Boutros Fraunhofer Institute for Computer Graphics Research IGD Darmstadt Germany Department of Computer Science TU Darmstadt Darmstadt Germany Centre for IT &#x0026 IP Law KU Leuven Leuven Belgium

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487405

关键词： Training Data privacy computer vision Law Face recognition Conferences Training data

Human Gait Recognition with Tensor Train Subspace Analysis

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Zdunek, Rafal Switonski, Adam Wroclaw University of Science and Technology Faculty of Electronics Janiszewskiego 11/17 Wroclaw50-372 Poland Silesian University of Technology Department of Computer Graphics Vision and Digital Systems Akademicka 16 Gliwice44-100 Poland

The paper proposes a new computational approach to classification of motion capture data, which is based on a low-rank approximation of multivariate time series containing information on angles of skeletal body segments. In the first stage, the continuous wavelet transform is applied to generate a set of 2D representations. Then, the tensor train decomposition model in conjunction with tensor subspace analysis is used for robust feature extraction. Validation experiments are conducted for highly precise motion capture data and a challenging human gait identification problem. A dataset containing recordings of 30 male individuals with 436 gait samples and 72-dimensional pose space is used. Different variants of preprocessing for motion capture data are applied, resulting in various time series lengths and pose parameters taken into consideration. The comparative analysis with other low-rank approximation methods, such as non-negative matrix factorization, higher-order singular value decompositions, and baseline tensor train, as well as the selected state-of-the-art approaches of mocap data classification, is carried out. The proposed approach outperforms all the tested techniques and achieves a high classification rate, that is, exceeding 96%. © 2024, The Authors. All rights reserved.

关键词： Time series

A driver-in-the-loop co-simulation framework for testing predictive EDAS for commercial vehicles in urban environments

学校读者我要写书评

暂无评论

A driver-in-the-loop co-simulation framework for testing pre...

6th International Commercial Vehicle Technology Symposium, CVT 2020

作者： Chada, Sai Krishna Gőrges, Daniel Ebert, Achim Teutsch, Roman Division of Electromobility Department of Electrical and Computer Engineering University of Kaiserslautern Kaiserslautern67663 Germany Computer Graphics and HCI Group Department of Computer Science University of Kaiserslautern Kaiserslautern67663 Germany Institute for Mechanical and Automotive Engineering Department of Mechanical and Process Engineering University of Kaiserslautern Kaiserslautern67663 Germany

ISBN: (纸本)9783658297169

To experience realistic driving scenarios in the virtual simulation environment, strengths of both the traffic simulation and the vehicle simulation tools must be combined. In this paper, a driver-in-the-loop co-simulation framework for testing predictive eco-driving assistance systems (EDAS) for commercial vehicles in urban environments is proposed. The co-simulation is performed by exchanging information between IPG TruckMaker, a vehicle simulation software tailored for commercial vehicles, and SUMO, an open-source software for microscopic traffic simulation. To avoid delays during the data exchange process, time-steps of both the tools are synchronized. The co-simulation environment replicates a bus route in the city of Kaiserslautern along with the corresponding bus stops, traffic lights, road speed limits, pedestrian crossings and road elevation. The stochastic traffic and pedestrian flow in the road network is generated using SUMO. In this work, the co-simulation framework is extended by introducing the driver into the simulation loop. This is achieved by coupling the vehicle simulation tool with a driving simulator, in which the driver controls the ego-vehicle. The proposed framework will serve to test various use-cases of predictive eco-driving assistant systems (EDAS). © Der/die Autor(en), exklusiv lizenziert durch.

关键词： Open source software

CLASSIFICATION OF LUNG CANCER SUBTYPES ON CT IMAGES WITH SYNTHETIC PATHOLOGICAL PRIORS

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhu, Wentao Jin, Yuan Ma, Gege Chen, Geng Egger, Jan Zhang, Shaoting Metaxas, Dimitris N. Research Center for Healthcare Data Science Zhejiang Lab Hangzhou311121 China School of Computer Science and Engineering Northwestern Polytechnical University Shaanxi Xi’an710072 China Institute of Computer Graphics and Vision Graz University of Technology Graz8010 Austria Shanghai Artificial Intelligence Laboratory Shanghai200120 China Department of Computer Science Rutgers University PiscatawayNJ08854 United States

The accurate diagnosis on pathological subtypes for lung cancer is of significant importance for the follow-up treatments and prognosis managements. In this paper, we propose self-generating hybrid feature network (SGHF-Net) for accurately classifying lung cancer subtypes on computed tomography (CT) images. Inspired by studies stating that cross-scale associations exist in the image patterns between the same case’s CT images and its pathological images, we innovatively developed a pathological feature synthetic module (PFSM), which quantitatively maps cross-modality associations through deep neural networks, to derive the "gold standard" information contained in the corresponding pathological images from CT images. Additionally, we designed a radiological feature extraction module (RFEM) to directly acquire CT image information and integrated it with the pathological priors under an effective feature fusion framework, enabling the entire classification model to generate more indicative and specific pathologically related features and eventually output more accurate predictions. The superiority of the proposed model lies in its ability to self-generate hybrid features that contain multi-modality image information based on a single-modality input. To evaluate the effectiveness, adaptability, and generalization ability of our model, we performed extensive experiments on a large-scale multi-center dataset (i.e., 829 cases from three hospitals) to compare our model and a series of state-of-the-art (SOTA) classification models. The experimental results demonstrated the superiority of our model for lung cancer subtypes classification with significant accuracy improvements in terms of accuracy (ACC), area under the curve (AUC), and F1 score. © 2023, CC0.

关键词： Classification (of information)