检索结果-内蒙古大学图书馆

3rd International Conference on Artificial Intelligence and Data Sciences, AiDAS 2022

作者： Omar, Zaturrawiah Ali Abu Bakar, Mohd Aftar Zamzuri, Zamira Hasanah Ariff, Noratiqah Mohd Universiti Malaysia Sabah Mathematics with Computer Graphics Programme Faculty of Science and Natural Resources Sabah Malaysia Universiti Kebangsaan Malaysia Faculty of Science and Technology Department of Mathematical Sciences Selangor Malaysia

ISBN: (数字)9781665491648

ISBN: (纸本)9781665491648

Detecting duplicate records is an essential step in data preparation for producing high-quality data for analysis. In statistics, it is commonly referred to as record linkage, but it goes by other names depending on the field of study. This study attempted to conduct duplicate detection on RLdata500 data using unsupervised Random Forests. In general, unsupervised machine learning algorithms are inferior to supervised learning algorithms. However, supervised learning requires labelled training data, which is absent from the majority of real-world datasets. Therefore, unsupervised learning is still applicable, and the performance of unsupervised learning algorithms can be enhanced through proper data conditioning. This paper reports the outcome of such conditioning by using bins and string encoding (Onca and Soundex). The similarity weight produced by the pairwise proximity matrix was used as the matching measure, and an optimal threshold was decided to be the cut-off point for classifying the record pairs as a match (duplicate detected) or non-match. Since the duplicate records in this dataset are known, the performances of the conditions can be compared using recall, precision, and F-measure, and the optimal threshold was determined using the maximum F -measure. Additional precision-recall graphs, as well as an F -measure graph that was transformed for a fair comparison, were used. The results then determined that the optimal conditions (2, 6 and 7) were the ones where the number values were treated as continuous. The performance of the employed encoding methods was equal when applied to the dataset and, together with binning, those conditions were able to detect more perfect matches. In the future, more testing and comparing will be done with different datasets and methods. © 2022 IEEE.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

POINTRESNET: RESIDUAL NETWORK FOR 3D POINT CLOUD SEGMENTATION AND CLASSIFICATION

arXiv

引用

arXiv 2022年

作者： Desai, Aadesh Parikh, Saagar Kumari, Seema Raman, Shanmuganathan Computer Vision Imaging and Graphics Lab Indian Institute of Technology Gandhinagar India

Point cloud segmentation and classification are some of the primary tasks in 3D computer vision with applications ranging from augmented reality to robotics. However, processing point clouds using deep learning-based algorithms is quite challenging due to the irregular point formats. Voxelization or 3D grid-based representation are different ways of applying deep neural networks to this problem. In this paper, we propose PointResNet, a residual block-based approach. Our model directly processes the 3D points, using a deep neural network for the segmentation and classification tasks. The main components of the architecture are: 1) residual blocks and 2) multi-layered perceptron (MLP). We show that it preserves profound features and structural information, which are useful for segmentation and classification tasks. The experimental evaluations demonstrate that the proposed model produces the best results for segmentation and comparable results for classification in comparison to the conventional baselines. © 2022, CC BY.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Influence of Water Droplet Contamination for Transparency Segmentation

arXiv

引用

arXiv 2024年

作者： Knauthe, Volker Weitz, Paul Pöllabauer, Thomas Wirth, Tristan Rak, Arne Kuijper, Arjan Fellner, Dieter W. Technical University of Darmstadt Darmstadt Germany Fraunhofer Institute for Computer Graphics Research IGD Darmstadt Germany CGV Institute Graz University of Technology Graz Austria

computer vision techniques are on the rise for industrial applications, like process supervision and autonomous agents, e.g., in the healthcare domain and dangerous environments. While the general usability of these techniques is high, there are still challenging real-world use-cases. Especially transparent structures, which can appear in the form of glass doors, protective casings or everyday objects like glasses, pose a challenge for computer vision methods. This paper evaluates the combination of transparent objects in conjunction with (naturally occurring) contamination through environmental effects like hazing. We introduce a novel publicly available dataset containing 489 images incorporating three grades of water droplet contamination on transparent structures and examine the resulting influence on transparency handling. Our findings show, that contaminated transparent objects are easier to segment and that we are able to distinguish between different severity levels of contamination with a current state-of-the art machine-learning model. This in turn opens up the possibility to enhance computer vision systems regarding resilience against, e.g., datashifts through contaminated protection casings or implement an automated cleaning alert. Copyright © 2024, The Authors. All rights reserved.

关键词： Transparency

来源：评论

学校读者我要写书评

暂无评论

Transparency Distortion Robustness for SOTA Image Segmentation Tasks

arXiv

引用

arXiv 2024年

作者： Knauthe, Volker Rak, Arne Wirth, Tristan Pöllabauer, Thomas Metzler, Simon Kuijper, Arjan Fellner, Dieter W. Technical University of Darmstadt Darmstadt Germany Fraunhofer Institute for Computer Graphics Research IGD Darmstadt Germany CGV Institute Graz University of Technology Graz Austria

Semantic Image Segmentation facilitates a multitude of real-world applications ranging from autonomous driving over industrial process supervision to vision aids for human beings. These models are usually trained in a supervised fashion using example inputs. Distribution Shifts between these examples and the inputs in operation may cause erroneous segmentations. The robustness of semantic segmentation models against distribution shifts caused by differing camera or lighting setups, lens distortions, adversarial inputs and image corruptions has been topic of recent research. However, robustness against spatially varying radial distortion effects that can be caused by uneven glass structures (e.g. windows) or the chaotic refraction in heated air has not been addressed by the research community yet. We propose a method to synthetically augment existing datasets with spatially varying distortions. Our experiments show, that these distortion effects degrade the performance of state-of-the-art segmentation models. Pretraining and enlarged model capacities proof to be suitable strategies for mitigating performance degradation to some degree, while fine-tuning on distorted images only leads to marginal performance improvements. Copyright © 2024, The Authors. All rights reserved.

关键词： Transparency

来源：评论

学校读者我要写书评

暂无评论

Maximization of L1-norm Using Jacobi Rotations

Maximization of L1-norm Using Jacobi Rotations

引用

European Signal Processing Conference (EUSIPCO)

作者： Adam Borowicz Department of Digital Media and Computer Graphics Faculty of Computer Science Bialystok University of Technology Bialystok Poland

ISBN: (数字)9789082797091

ISBN: (纸本)9781665467995

In recent years, we observe a growing interest in approaches to principal component analysis (PCA) based on L1-norm maximization. Unfortunately, existing L1-PCA algorithms are either computationally expensive or inaccurate. In this paper, we propose to use Jacobi-based rotational framework for solving L1-norm maximization problem. Under this framework, two new suboptimal algorithms are developed: the first one based on exhaustive angle search, and the second one based on a differentiable approximation of the absolute value function. Experimental studies show that the proposed approaches provide high accuracy as compared to the existing suboptimal algorithms. They are also considerably faster than currently the most accurate method based on bit-flipping. Simulation results show that both approaches can be used to perform independent component analysis (ICA) under whitening assumption achieving better robustness to outliers than other methods.

关键词： Jacobian matrices Simulation Signal processing algorithms Independent component analysis Signal processing Approximation algorithms Robustness

来源：评论

学校读者我要写书评

暂无评论

Connected, Cooperative and Automated Driving: Stepping away from dynamic function allocation towards human-machine collaboration

引用

Transportation Research Procedia 2023年 72卷 431-438页

作者： Marten Bloch Maren Eitrheim Ana Mackay Emanuel Sousa Institute for Energy Technology Os Allé 5 Halden 1777 Norway Center for Computer Graphics Campus de Azurém Guimarães 4800-058 Portugal

Implementing the concept of Connected, Cooperative and Automated Driving (CCAD) has many potential societal and individual benefits. However, to do so successfully fundamental challenges need to be tackled, one being the integration of automation and the human driver. The decisive problems with safety surrounding this topic are well-known, in particular when the human is expected to intervene in situations that the automation is unable to handle. Here we argue that the leading human-machine interaction paradigm for automated driving was and continues to be dynamic function allocation and adaptive automation and that this gave rise to many of the issues currently seen in CCAD. As an alternative, we propose the concept of collaboration which has been discussed in other domains. We believe it may in the future allow tackling the issues associated with the integration of CCAD and the human.

关键词： Connected, Cooperative and Automated Driving Human-Automation Integration Driver Vehicle Collaboration

来源：评论

学校读者我要写书评

暂无评论

Learning Gradually Non-convex Image Priors Using Score Matching

arXiv

引用

arXiv 2023年

作者： Kobler, Erich Pock, Thomas Department of Neuroradiology University Hospital Bonn Bonn Germany Institue of Computer Graphics and Vision Graz University of Technology Graz Austria

In this paper, we propose a unified framework of denoising score-based models in the context of graduated non-convex energy minimization. We show that for sufficiently large noise variance, the associated negative log density - the energy - becomes convex. Consequently, denoising score-based models essentially follow a graduated non-convexity heuristic. We apply this framework to learning generalized Fields of Experts image priors that approximate the joint density of noisy images and their associated variances. These priors can be easily incorporated into existing optimization algorithms for solving inverse problems and naturally implement a fast and robust graduated non-convexity mechanism. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Diffusion-based generation of Histopathological Whole Slide Images at a Gigapixel scale

arXiv

引用

arXiv 2023年

作者： Harb, Robert Pock, Thomas Müller, Heimo Institute of Computer Graphics and Vision Graz University of Technology Austria Diagnostic and Research Institute of Pathology Medical University of Graz Austria

We present a novel diffusion-based approach to generate synthetic histopathological Whole Slide Images (WSIs) at an unprecedented gigapixel scale. Synthetic WSIs have many potential applications: They can augment training datasets to enhance the performance of many computational pathology applications. They allow the creation of synthesized copies of datasets that can be shared without violating privacy regulations. Or they can facilitate learning representations of WSIs without requiring data annotations. Despite this variety of applications, no existing deep-learning-based method generates WSIs at their typically high resolutions. Mainly due to the high computational complexity. Therefore, we propose a novel coarse-to-fine sampling scheme to tackle image generation of high-resolution WSIs. In this scheme, we increase the resolution of an initial low-resolution image to a high-resolution WSI. Particularly, a diffusion model sequentially adds fine details to images and increases their resolution. In our experiments, we train our method with WSIs from the TCGA-BRCA dataset. Additionally to quantitative evaluations, we also performed a user study with pathologists. The study results suggest that our generated WSIs resemble the structure of real WSIs. Copyright © 2023, The Authors. All rights reserved.

关键词： Diffusion

来源：评论

学校读者我要写书评

暂无评论

General Concepts in Swarm of Drones Control: Analysis and Implementation

General Concepts in Swarm of Drones Control: Analysis and Im...

引用

2023 IEEE International Conference on Big Data, BigData 2023

作者： Marek, Dariusz Paszkuta, Marcin Szygula, Jakub Biernacki, Piotr Domanski, Adam Szczygiel, Marta Krol, Marcel Wojciechowski, Konrad Silesian University of Technology Dept. of Distributed Systems and Informatic Devices Warsaw Poland Polish-Japanese Academy of Information Technology ul. Koszykowa 86 Warsaw02-008 Poland Silesian University of Technology Dept. of Computer Graphics Vision and Digital Systems Warsaw Poland Institute of Theoretical and Applied Informatics Polish Academy of Sciences Warsaw Poland Silesian University of Technology Warsaw Poland

ISBN: (纸本)9798350324457

In the presented paper, detailed schematics and descriptions concerning communication in the context of swarm drone control are introduced. Methods and technologies behind them are discussed. The implementation of the presented concept was verified through a series of tests. Simulation results which confirm the effectiveness and efficiency of the proposed solutions are presented. The obtained results prove the correctness implementation of the presented methods and also demonstrate the benefits derived from the proposed approach. The presented concept of controlling a swarm of drones represents the current state of knowledge and technology in the field of drones and their control. By utilizing advanced communication technologies, positioning, and analysis of communication structures, this work makes a significant contribution to the UAV (Unmanned Aerial Vehicle) field. © 2023 IEEE.

关键词： Control Concepts Industrial Environment Industry 4.0 simulation environments Swarm of Drones UAV

来源：评论

学校读者我要写书评

暂无评论

Characteristics Analysis of Moving Conversations to Detect Events on Twitter 14

Characteristics Analysis of Moving Conversations to Detect E...

引用

14th IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2022

作者： Senaratne, Hansi Lehle, Dominic Schreck, Tobias Earth Observation Center German Aerospace Center Oberpfaffenhofen Germany Advanced Research & Technologies Avira Tettnang Germany Inst. of Computer Graphics & Knowledge Visualization Graz University of Technology Graz Austria

ISBN: (纸本)9781665456616

A conversation is an exchange of thoughts, news, or ideas about a particular topic between two or more people. On Twit-ter, hashtags allow its users to collate all conversations pertaining to a particular topic. The progressions that occur in such conversations through the geographic space, the time, or the thematic contexts, create trajectories of conversations on Twitter, and they can give us valuable insights into interesting events that take place around us. In this paper we develop an approach based on data analysis and visualisation, to (1) construct such conversation trajectories for chosen popular hashtags, (2) analyse the various geospatial-and content-characteristics of the conversation trajectories (e.g., distance variance, speed of propagation, topic diversity, or credibility) to determine co-located events, and (3) rank and sort the resulting conversation trajectories according to a user-defined interestingess-measure, to narrow down the search space for interesting conversation trajectories. Our approach is among the first to introduce the us-age of movement of conversations across geographic space and time for the exploratory detection and analysis of events, whereas most existing works use keyword-based text analysis to detect events on Twitter. All the three stages of the approach (construct, analyse, rank & sort) are presented in a visual-interactive interface that allows us to explore Twitter text data without extensive prior knowledge, and benefit from the pure exploratory capabilities of the tool. The usefulness of our approach is demonstrated as a proof-of-concept to detect sports-related events, where we were able to identify the outcome of a contest for Major League Baseball sportsmen on Twitter. © 2022 IEEE.

关键词： Trajectories

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：