检索结果-内蒙古大学图书馆

International symposium on Systems Engineering (ISSE)

作者： Wagenmann, Steffen Krause, Artur Rapp, Simon Albers, Albert Sommer, Lutz Bursac, Nikola Karlsruher Inst Technol IPEK Karlsruhe Germany TRUMPF Machine Tools SE CoKG Stuttgart Germany Albstadt Univ Appl Sci Sigmaringen Germany Tech Univ Hamburg Hamburg Germany

ISBN: (纸本)9781665481823

Development practice shows that it is currently almost impossible for developers themselves to actively use data of customer's use of machines to derive decisions in the context of the development of mechatronic systems. In the light of the steadily growing data volumes and the associated costs, it makes sense for companies to make this data accessible to as many developers as possible. Therefore, an initial process model for the data- driven validation of the system of objectives is adapted to further improve the methodical support of developers to actively use machine usage data in the development process. To get a better understanding on how the initial process model for the data-driven validation needs to be adapted to meet the challenges developers are facing in using data, a validation study is executed. The study is carried out by 14 data Science students under the supervision of company-internal domain experts. The main challenges as for example large data volumes, data availability, understanding of the technical system and unclear validation objectives can be assigned to the three causes: knowledge about data, organizations internal processes and combination of domain knowledge. To cope with the identified challenges, it is necessary to also incorporate the distinct selection of data and tools complemented by an estimation of the opportunities and risks of choosing a certain combination of data and tools. The study shows that adaptations to the process model increased the applicability, understandability and the perception of feeling supported in conducting analyses for validation purposes. It could be observed that a lack of knowledge about the technical system under investigation results in incomplete or incorrect information being shared. Therefore, a centralization of analysis activities in the development of mechatronic systems is not expedient.

关键词： Advanced Systems data Driven Validation data Mining Systems Engineering Reference System

来源：评论

学校读者我要写书评

暂无评论

Sharing is Caring: Optimized Threat visualization for a Cybersecurity data Sharing Platform 20

Sharing is Caring: Optimized Threat Visualization for a Cybe...

引用

ieee 20th International symposium on Network Computing and Applications (NCA)

作者： Cassell, Adam Das, Tapadhir Black, Zachary Sadique, Farhan Schnebly, James Dascalu, Sergiu Sengupta, Shamik Springer, Jeff Univ Nevada Dept Comp Sci & Engn Reno NV 89557 USA

ISBN: (纸本)9781665495509

Cyberattacks are increasingly costing organizations billions of dollars annually. To protect against them, cybersecurity information sharing and cyberthreat visualization have become crucial research topics. Our platform, CYBersecurity information EXchange with Privacy (CYBEX-P), implements developments in both areas as an approachable collaborative security tool. CYBEX-P's threat-intelligence graph displays indicators of compromise and their crowd-reported threat levels. Intuitive and efficient data interaction is key for adoption of such a contributor-driven system and is the focus of this work. A user study was conducted with participants from cybersecurity backgrounds to test different visualization configurations. Measurements pertaining to dependent variables such as task accuracy and threat-detection time were recorded. Subsequent analysis revealed that relying on localized color to represent threat comes with serious limitations. Likewise, information density must be carefully considered. We conclude that the misuse of simple visual properties can lead to perilous reductions in accuracy and response-time and provide recommendations for avoiding these pitfalls.

关键词： Graph visualization cyberthreat investigation cybersecurity information sharing user study

来源：评论

学校读者我要写书评

暂无评论

Interactive visualization and Portable Image Blending of Massive Aerial Image Mosaics

Interactive Visualization and Portable Image Blending of Mas...

引用

2023 ieee International Conference on Big data, Bigdata 2023

作者： Petruzza, Steve Summa, Brian Gooch, Amy Laney, Christine M. Goulden, Tristan Schreiner, John Callahan, Steven Pascucci, Valerio Utah State University United States Tulane University United States ViSOAR Llc United States Battelle Neon United States Zero-Epsilon Llc United States University of Utah United States

ISBN: (纸本)9798350324457

Processing, managing and publishing the substantial volume of data collected through modern remote sensing technologies in a format that is easy for researchers - across broad skill levels and scientific domains - to view and use presents a formidable challenge. As a prime example, the massive scale of image mosaics produced by NEON's Airborne Observation Platform (AOP), often several to hundreds of gigabytes in volume, demands efficient data management strategies. Additionally, these aerial mosaics frequently exhibit seams due to variations in lighting conditions during the data acquisition process. These seams undermine the integrity of subsequent scientific analyses, introducing distortions that hinder accurate interpretation of ecological patterns. Finally, one of NEON's core objectives is to make these data broadly accessible to users, including those who are not yet versed in working with remote sensing data or who wish to view the datasets without needing to download and process *** response to these challenges, we have developed a comprehensive data management pipeline that enables interactive access for analysis and visualization of NEON's aerial mosaic collection. This pipeline automates data ingestion, conversion, and publication in a streamable format, facilitating seamless user interaction through web viewers and programming APIs. Moreover, we have implemented a portable blending algorithm aimed at eliminating these problematic seams from large aerial mosaics. This algorithm, grounded in the Conjugate Gradient (CG) method, has been implemented both in CUDA and using the modern SYCL programming model for enhanced portability across diverse computing *** results demonstrate scalable performance across both CPU and GPU architectures. This work not only addresses the challenges of large aerial data management and seam removal but also opens avenues for more accurate and comprehensive scientific investigations within the NEON ecosystem

关键词： aerial imagery Color blending data streaming interactive visualization remote sensing

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Visual Representation Learning via Dual-Level Progressive Similar Instance Selection

引用

ieee TRANSACTIONS ON CYBERNETICS 2022年第9期52卷 8851-8861页

作者： Fan, Hehe Liu, Ping Xu, Mingliang Yang, Yi Univ Technol Sydney Ctr Artificial Intelligence Ultimo NSW 2007 Australia Natl Univ Singapore Sch Comp Singapore 119077 Singapore Agcy Sci Technol & Res Inst High Performance Comp Singapore 138632 Singapore Zhengzhou Univ Sch Informat Engn Zhengzhou 450001 Peoples R China

The superiority of deeply learned representations relies on large-scale labeled datasets. However, annotating data are usually expensive or even infeasible in some scenarios. To address this problem, we propose an unsupervised method to leverage instance discrimination and similarity for deep visual representation learning. The method is based on an observation that convolutional neural networks (CNNs) can learn a meaningful visual representation with instancewise classification, in which each instance is treated as an individual class. By this instancewise discriminative learning, instances can reasonably distribute in the representation space, which reveals their similarities. In order to further improve visual representations, we propose a dual-level progressive similar instance selection (DPSIS) method to build a bridge from instance to class by selecting similar instances (neighbors) for each instance (anchor) and treating the anchor and its neighbors as the same class. To be specific, DPSIS adaptively selects two levels of neighbors, that is: 1) an ``absolutely similar level'' and 2) a ``relatively similar level.'' Instances in the absolutely similar level are used as hard labels, while instances in the relatively similar level are used as soft labels. Moreover, during training, DPSIS is able to progressively select more neighbors without human supervision. At the beginning of training, because CNNs are weak, most instances are distributed relatively randomly in the representation space and only a few easy-to-recognize instances are selected as neighbors. As CNN models become stronger, the semantic meaning of each instance grows clearer. Those instances originally distributed in a relatively random manner gradually move to meaningful positions. This consequently facilitates CNN training since the number of reliable samples increases. Experiments on seven benchmarks, including three small-scale and two large-scale coarse-grained image classification datasets, a

关键词： visualization Training Task analysis Reliability Neural networks Fans Correlation Deep learning fine-grained categorization image classification unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Open Game data: Defining a Pipeline and Standards for Educational data Mining and Learning Analytics with Video Game data

Open Game Data: Defining a Pipeline and Standards for Educat...

引用

ieee symposium on Computational Intelligence and Games, CIG

作者： David J. Gagnon Luke Swanson Erik Harpstead Field Day Lab University of Wisconsin - Madison Madison USA Human-Computer Interaction Institute Carnegie Mellon University Pittsburgh USA

ISBN: (数字)9798350350678

ISBN: (纸本)9798350350685

In this paper we describe the need for a framework to support collaborative educational research with game data, then demonstrate a promising solution. We review existing efforts, explore a collection of use cases and requirements, then propose a new data architecture with related data standards. The approach provides modularity to the various stages of game data generation and analysis, exposing intermediate transformations and work products. Foregrounding flexibility, each stage of the pipeline generates datasets for use in other tools and workflows. A series of interconnected standards allow for the development of reusable analysis and visualization tools across games, while remaining responsive to the diversity of potential game designs. Finally, we demonstrate the feasibility of the approach through an existing implementation that uses this architecture to process and analyze data from a wide range of games developed by multiple institutions, at scale, supporting a variety of research projects.

关键词： Video games Reviews Pipelines data visualization Collaboration Games data mining

来源：评论

学校读者我要写书评

暂无评论

RRT-based maximum entropy inverse reinforcement learning for robust and efficient driving behavior prediction

RRT-based maximum entropy inverse reinforcement learning for...

引用

33rd ieee Intelligent Vehicles symposium (ieee IV)

作者： Hosoma, Shinpei Sugasaki, Masato Arie, Hiroaki Shimosaka, Masamichi Tokyo Inst Technol Dept Comp Sci Tokyo Japan DENSO Corp Tokyo Japan

ISBN: (纸本)9781665488211

Advanced driver assistance systems have gained popularity as a safe technology that helps people avoid traffic accidents. To improve system reliability, a lot of research on driving behavior prediction has been extensively researched. Inverse reinforcement learning (IRL) is known as a prominent approach because it can directly learn complicated behaviors from expert demonstrations. Because driving data tend to have a couple of optimal behaviors from the drivers' preferences, i.e., sub-optimality issue, maximum entropy IRL has been getting attention with their capability of considering suboptimality. While accurate modeling and prediction can be expected, standard maximum entropy IRL needs to calculate the partition function, which requires large computational costs. Thus, it is not straightforward to apply this model to a high-dimensional space for detailed car modeling. In addition, existing research attempts to reduce these costs by approximating maximum entropy IRL;however, a combination of the efficient path planning and the proper parameter updating is required for an accurate approximation, and existing methods have not achieved them. In this study, we leverage a rapidly-exploring random tree (RRT) motion planner. With the RRT planner, we propose novel importance sampling for an accurate approximation from the generated trees. This ensures a stable and fast IRL model in a large high-dimensional space. Experimental results on artificial environments show that our approach improves stability and is faster than the existing IRL methods.

关键词： Training Road transportation Computational modeling Reinforcement learning Entropy Stability analysis Behavioral sciences

来源：评论

学校读者我要写书评

暂无评论

PromptLandscape: Guiding Prompts Exploration and analysis with visualization

PromptLandscape: Guiding Prompts Exploration and Analysis wi...

引用

Pacific (formerly Asia-Pacific APVIS) visualization symposium

作者： Junpeng Wang Chin-Chia Michael Yeh Yujie Fan Xin Dai Yan Zheng Liang Wang Wei Zhang Visa Research

ISBN: (数字)9798350393804

ISBN: (纸本)9798350393811

Prompts, which are pieces of text injected into the inputs of NLP models, can significantly enhance these models’ performance. Despite their effectiveness, a straightforward method for exploring a large number of possible prompts and assessing their quality in down-stream tasks is lacking. This paper introduces PromptLandscape, a visualization approach to exploring prompts in the zero-shot image classification context. Our focus is on the CLIP model [26], which has been pre-trained on a large number of image-text pairs and exhibits exceptional performance in zero-shot image classifications. However, its performance is also considerably influenced by the text labels. Prompts were introduced to refine the text labels and improve the classification performance. Nevertheless, the prompts are often proposed through trial-and-error and it is challenging to find the best prompts for different image datasets. PromptLandscape presents the large number of possible prompts as points in a 3D space to guide their exploration and enables users to decode any points back as texts for better interpretation. Through concrete case studies, we demonstrate the effectiveness of PromptLandscape in (1) finding the best prompts for image classifications and (2) interpreting the prompts to reveal the crucial features of the studied image datasets.

关键词： visualization Three-dimensional displays Task analysis Image classification

来源：评论

学校读者我要写书评

暂无评论

Classification of Images with Linear Objects in All-Sky Astronomical Survey data using Convolutional Neural Networks 23

Classification of Images with Linear Objects in All-Sky Astr...

引用

23rd ieee International symposium on Computational Intelligence and Informatics, CINTI 2023

作者： Kaliskova, Lenka Butka, Peter Fei Technical University of Košice Dept. of Cybernetics and Artificial Intelligence Košice Slovakia

ISBN: (纸本)9798350342949

This paper focuses on the classification of astronomical data, specifically images with or without linear features, which can be of different origin like meteors, asteroids, or satellites. Such models might be helpful in fast recognition of contaminated images from astronomical surveys, where satellites or other phenomena might decrease scientific value of survey for astrophysicists. It is quite large problem in astronomy today, due to increasing number of new satellites. On the other hand, such identification might also bring information on objects that pass through cameras field of view. Therefore, any fast way to recognize such cases is helpful. To achieve our goal of classification, we propose two main methods. Firstly, we focus on annotation project of images to create a dataset divided into two classes based on the occurrence of linear objects. Secondly, we suggest three different experiments utilizing convolutional neural networks. The results of each experiment are crucial as we create a sequence of experiments, with the best result serving as input for the subsequent experiment. To determine the success of our experiments, we define a threshold value of 98% for accuracy, which we were able to achieve in the final of the three experiments. © 2023 ieee.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Playful Interactions for Representation Learning

Playful Interactions for Representation Learning

引用

ieee/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Young, Sarah Pari, Jyothish Abbeel, Pieter Pinto, Lerrel Univ Calif Berkeley Berkeley CA 94720 USA NYU New York NY 10003 USA

ISBN: (数字)9781665479271

ISBN: (纸本)9781665479271

One of the key challenges in visual imitation learning is collecting large amounts of expert demonstrations for a given task. While methods for collecting human demonstrations are becoming easier with teleoperation methods and the use of low-cost assistive tools, we often still require 100-1000 demonstrations for every task to learn a visual representation and policy. To address this, we turn to an alternate form of data that does not require task-specific demonstrations play. Playing is a fundamental method children use to learn a set of skills and behaviors and visual representations in early learning. Importantly, play data is diverse, task-agnostic, and relatively cheap to obtain. In this work, we propose to use playful interactions in a self-supervised manner to learn visual representations for downstream tasks. We collect 2 hours of playful data in 19 diverse environments and use self-predictive learning to extract visual representations. Given these representations, we train policies using imitation learning for two downstream tasks: Pushing and Stacking. We demonstrate that our visual representations generalize better than standard behavior cloning and can achieve similar performance with only half the number of required demonstrations. Our representations, which are trained from scratch, compare favorably against ImageNet pretrained representations. Finally, we provide an experimental analysis on the effects of different pretraining modes on downstream task learning.

关键词： Representation learning visualization Stacking Cloning Behavioral sciences data mining Task analysis

来源：评论

学校读者我要写书评

暂无评论

MLN-Visualizer: Interactive visualization of Graphs and Multilayer Network analysis Results

MLN-Visualizer: Interactive Visualization of Graphs and Mult...

引用

ieee International Conference on Big data Computing Service and Applications (BigdataService)

作者： Viraj Sabhaya Amey Shinde Abhishek Santra Sharma Chakravarthy IT Lab and CSE Department UT Arlington Arlington Texas

Big data analysis is broader with a life cycle from choosing a model to represent data, generation of the model for the given data set, analysis using operations relevant to the model, and finally, visualization to understand the results. The ability to perform this end-to-end workflow has become more important as the data size and complexity have increased significantly. visualization is especially important when the data sizes are large and models are complex (e.g., graphs, multilayer networks (MLNs)) which is difficult to comprehend without *** this poster paper, we describe a web-based tool MLN-Visualizer for visualizing graphs and MLN analysis results. Interactively, the user can visualize their uploaded input data and analysis results, in multiple ways, using a menu-driven interface. We hint at adding privacy to the resulting visualization.

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：