检索结果-内蒙古大学图书馆

23rd ieee International symposium on Mixed and Augmented Reality, ISMAR 2024

作者： O'keeffe, Spencer Thomas, Bruce H O'hehir, Jim Rombouts, Jan Balasso, Michelle Cunningham, Andrew University of South Australia Australia OneFortyOne Plantations Pty Ltd

ISBN: (纸本)9798331516475

Virtual Reality (VR) is changing how we interact with complex spatial datasets. VR has the potential within forestry to help analyse remotely sensed spatial data for inventory management. However, challenges of scale and legibility of dense forest point clouds must be addressed. To do so, we present three VR Focus+Context (F+C) techniques: Wedgelight, Remote Lantern, and Ray Lantern. These techniques present point cloud data using a constrained highdetail focus within a broader abstracted context representation, manipulated using egocentric and exocentric interactions. We conducted two user studies. The first informed the design of the F+C techniques. The results from the first study indicate that VR significantly outperforms desktop displays in basic analysis of forestry point clouds, with improvements to both time and accuracy. The second study evaluated the performance of the resulting F+C techniques in a task analogous to real-world forestry operations. Our F+C techniques significantly outperformed current approaches, confirming their viability for facilitating detailed and effective forest assessments. These findings indicate that VR has significant advantages for spatial data analysis tasks in forestry, making a strong argument for its adoption in future analytical frameworks. The FF+CC visualisation techniques we introduced show considerable promise for analysis of high density point clouds, opening new avenues for development in immersive analytics. Supplemental materials (code, scans, results) are available at https://***/hqc9u. © 2024 ieee.

关键词： visualization

来源：评论

学校读者我要写书评

暂无评论

DiCE-M: Distributed Code Generation and Execution for Marine Applications - An Edge-Cloud Approach 9

DiCE-M: Distributed Code Generation and Execution for Marine...

引用

9th symposium on Edge Computing

作者： Coviello, Giuseppe Rao, Kunal Mellone, Gennaro De Vita, Ciro Giuseppe Chakradhar, Srimat NEC Labs Amer Inc Princeton NJ 08540 USA

ISBN: (纸本)9798350378290;9798350378283

Edge computing has emerged as a transformative technology that reduces application latency, improves cost efficiency, enhances security, and enables large-scale deployment of applications across various domains. In environmental monitoring, systems such as MegaSense [49], use low-cost sensors to gather and process real-time air quality data through edge-cloud collaboration, highlighting the critical role of edge computing in enabling scalable, efficient solutions. Similarly, marine science increasingly requires real-time processing and analysis of marine data from remote, resource-constrained environments. In this paper, we extend the power of edge computing by integrating it with Generative Artificial Intelligence (GenAI), specifically large language models (LLMs), to address challenges in marine science applications. We propose DiCE-M (Distributed Code generation and Execution for Marine applications), a robust system that uses LLM to generate distributed code for marine applications and then utilizes a runtime to efficiently execute it on an edge+cloud computing infrastructure. Specifically, DiCE-M leverages edge computing to execute lightweight AI models locally on unmanned surface vehicles (USVs) while offloading complex tasks to the cloud, thus balancing computational load and enabling real-time monitoring in marine environments. We use marine litter identification as an example application to demonstrate the utility of DiCE-M. Our results show that DiCE-M reduces latency by more than 2X when marine litter is not detected and cuts cloud computing costs by more than half compared to traditional cloud-based approaches. By selectively cropping and transmitting relevant image portions, DiCE-M further improves bandwidth efficiency, making it a reliable and cost-effective solution for deploying AI-driven applications on resource-constrained USVs in dynamic marine environments.

关键词： Edge computing Cloud computing Distributed computing Generative artificial intelligence large language models Code generation Runtime Vision applications Marine science

来源：评论

学校读者我要写书评

暂无评论

SNAP: Efficient Extraction of Private Properties with Poisoning 44

SNAP: Efficient Extraction of Private Properties with Poison...

引用

44th ieee symposium on Security and Privacy (SP)

作者： Chaudhari, Harsh Abascal, John Oprea, Alina Jagielski, Matthew Tramer, Florian Ullman, Jonathan Northeastern Univ Boston MA 02115 USA Google Res Mountain View CA USA ETH Zurich Switzerland

ISBN: (纸本)9781665493369

Property inference attacks allow an adversary to extract global properties of the training dataset from a machine learning model. Such attacks have privacy implications for data owners sharing their datasets to train machine learning models. Several existing approaches for property inference attacks against deep neural networks have been proposed [1]-[3], but they all rely on the attacker training a large number of shadow models, which induces a large computational overhead. In this paper, we consider the setting of property inference attacks in which the attacker can poison a subset of the training dataset and query the trained target model. Motivated by our theoretical analysis of model confidences under poisoning, we design an efficient property inference attack, SNAP, which obtains higher attack success and requires lower amounts of poisoning than the state-of-the-art poisoning-based property inference attack by Mahloujifar et al. [3]. For example, on the Census dataset, SNAP achieves 34% higher success rate than [3] while being 56.5x faster. We also extend our attack to infer whether a certain property was present at all during training and estimate the exact proportion of a property of interest efficiently. We evaluate our attack on several properties of varying proportions from four datasets and demonstrate SNAP's generality and effectiveness.

关键词： data-poisoning data-poisoning-in-machine-learning privacy-attacks property-inference

来源：评论

学校读者我要写书评

暂无评论

A Ridge-based Approach for Extraction and visualization of 3D Atmospheric Fronts

A Ridge-based Approach for Extraction and Visualization of 3...

引用

2024 ieee visualization and Visual Analytics Conference, VIS 2024

作者： Gossing, Anne Beckert, Andreas Fischer, Christoph Klenert, Nicolas Natarajan, Vijay Pacey, George Vogt, Thorwin Rautenhaus, Marc Baum, Daniel Universität Hamburg Germany Indian Institute of Science Bangalore India Zuse Institute Berlin Germany Freie Universität Berlin Germany

ISBN: (纸本)9798350354850

An atmospheric front is an imaginary surface that separates two distinct air masses and is commonly defined as the warm-air side of a frontal zone with high gradients of atmospheric temperature and humidity (Fig. 1, left). These fronts are a widely used conceptual model in meteorology, which are often encountered in the literature as two-dimensional (2D) front lines on surface analysis charts. This paper presents a method for computing three-dimensional (3D) atmospheric fronts as surfaces that is capable of extracting continuous and well-confined features suitable for 3D visual analysis, spatiotemporal tracking, and statistical analyses (Fig. 1, middle, right). Recently developed contour-based methods for 3D front extraction rely on computing the third derivative of a moist potential temperature field. Additionally, they require the field to be smoothed to obtain continuous large-scale structures. This paper demonstrates the feasibility of an alternative method to front extraction using ridge surface computation. The proposed method requires only the second derivative of the input field and produces accurate structures even from unsmoothed data. An application of the ridge-based method to a data set corresponding to Cyclone Friederike demonstrates its benefits and utility towards visual analysis of the full 3D structure of fronts. © 2024 ieee.

关键词： Atmospheric humidity

来源：评论

学校读者我要写书评

暂无评论

CliZ: Optimizing Lossy Compression for Climate datasets with Adaptive Fine-tuned data Prediction 38

CliZ: Optimizing Lossy Compression for Climate Datasets with...

引用

International Parallel and Distributed Processing symposium (IPDPS)

作者： Jian, Zizhe Di, Sheng Liu, Jinyang Zhao, Kai Liang, Xin Xu, Haiying Underwood, Robert Wu, Shixun Huang, Jiajun Chen, Zizhong Cappello, Franck Univ Calif Riverside Riverside CA USA Argonne Natl Lab Lemont IL USA Florida State Univ Tallahassee FL USA Univ Kentucky Lexington KY USA Natl Ctr Atmospher Res Boulder CO USA

ISBN: (纸本)9798350387117;9798350387124

Benefiting from the cutting-edge supercomputers that support extremely large-scale scientific simulations, climate research has advanced significantly over the past decades. However, new critical challenges have arisen regarding efficiently storing and transferring large-scale climate data among distributed repositories and databases for post hoc analysis. In this paper, we develop CliZ, an efficient online error-controlled lossy compression method with optimized data prediction and encoding methods for climate datasets across various climate models. On the one hand, we explored how to take advantage of particular properties of the climate datasets (such as mask-map information, dimension permutation/fusion, and data periodicity pattern) to improve the data prediction accuracy. On the other hand, CliZ features a novel multi-Huffman encoding method, which can significantly improve the encoding efficiency. Therefore significantly improving compression ratios. We evaluated CliZ versus many other state-of-the-art error-controlled lossy compressors (including SZ3, ZFP, SPERR, and QoZ) based on multiple real-world climate datasets with different models. Experiments show that CliZ outperforms the second-best compressor (SZ3, SPERR, or QoZ1.1) on climate datasets by 20%-200% in compression ratio. CliZ can significantly reduce the data transfer cost between the two remote Globus endpoints by 32%-38%.

关键词： error-controlled lossy compression climate datasets distributed data repository/database

来源：评论

学校读者我要写书评

暂无评论

Research on Social Service Value of Wutongshan Scenic Area of Shenzhen Based on Big data of Network

Research on Social Service Value of Wutongshan Scenic Area o...

引用

2023 International symposium on World Ecological Design, ISWED 2023

作者： Zhou, Fei Environmental Art Design Major Guangzhou College of Science and Technology in International Trade China

ISBN: (纸本)9781643685069

Wutongshan Scenic Area is an important public space in Shenzhen, known for its well-preserved ecology and rich cultural heritage, attracting a large number of tourists and local residents. This study utilizes network big data analysis to assess the social service value of Wutongshan Scenic Area. By leveraging Tencent Location Big data, the study examines the spatial and temporal variations in the intensity of scenic area usage during holidays and working days. Additionally, ROST CM6.0 software is employed to analyze the frequency, semantic relationships, and emotional associations of online user reviews, identifying key areas of interest and evaluating visitor perceptions. This multidimensional approach aims to provide a comprehensive understanding of the social service value offered by Wutongshan Scenic Area. The visualization of network big data enables real-time and comprehensive analysis, highlighting the significance of the scenic area's social services. © 2024 The Authors.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

MVR: Synergizing large and Vision Transformer for Multimodal Natural Language-Driven Vehicle Retrieval

引用

ieee ACCESS 2025年 13卷 7014-7026页

作者： Alzubi, Tareq Mahmod Mukhtar, Umar Raza Al Balqa Appl Univ Prince Abdullah bin Ghazi Fac Informat & Commun Te Dept Comp Sci As Salt 19117 Jordan Univ Management & Technol Dept Comp Sci Lahore 54770 Pakistan

In recent years, intelligent transportation systems have played a pivotal role in the development of smart cities, with vehicle retrieval becoming a critical component of traffic management and surveillance. Traditional vehicle retrieval systems rely heavily on image-based matching techniques derived from vehicle re-identification (VReID) tasks. However, these approaches are limited by their dependency on image queries, which may not always be available in real-world scenarios. Natural language (NL)-based vehicle retrieval systems offer a more flexible and accessible alternative by enabling users to query vehicles using textual descriptions. Despite progress in NL-based retrieval, existing methods face challenges in fully capturing multi-granularity information and aligning heterogeneous visual and linguistic inputs. This paper addresses these limitations by proposing a robust Multimodal Vehicle Retrieval (MVR) model that integrates both visual and textual data through a dual-stream architecture. Our model captures complementary local features, alongside global information including motion and environmental context. We utilize InfoNCE and instance losses to align the visual and textual modalities within a shared feature space, while post-processing modules, including Granular Vehicle Feature Refinement and Spatial Relationship Modeling, further enhance retrieval performance by refining vehicle attributes and contextual relationships. Our experiments, conducted on the CityFlow-NL dataset, demonstrate that our model achieves a 35.6% improvement in Mean Reciprocal Rank (MRR), a 41.3% increase in recall at 5 (R@5), and a 22.9% improvement in recall at 10 (R@10) compared to the baseline, and overcomes the inherent challenges of cross-modal retrieval in improving real-world VReID.

关键词： visualization Feature extraction Videos Transformers Smart cities Vehicle dynamics Traffic control Streaming media Image color analysis Cameras Traffic surveillance intelligent transportation multimodal smart city vehicle tracking

来源：评论

学校读者我要写书评

暂无评论

A Quantitative Metric of Confidence For Segmentation of Nuclei in large Spatially Variable Image Volumes 26

A Quantitative Metric of Confidence For Segmentation of Nucl...

引用

26th International Workshop on Multimedia Signal Processing

作者： Wu, Liming Chen, Alain Salama, Paul Dunn, Kenneth Winfree, Seth Delp, Edward Purdue Univ Video & Image Proc Lab W Lafayette IN 47907 USA Purdue Univ Sch Elect & Comp Engn Indianapolis IN USA Indiana Univ Div Nephrol Sch Med Indianapolis IN 46204 USA NIAID Rocky Mt Lab Hamilton MT 59840 USA

ISBN: (纸本)9798350387261;9798350387254

Nuclei segmentation is an important step for quantitative analysis of fluorescence microscopy images. A large volume generally has many different regions containing nuclei with varying spatial characteristics. Automatically identifying nuclei that are challenging to segment can speed up the analysis of biological tissues. Here we show a segmentation technique that provides a metric of segmentation "confidence" for each segmented object in an image volume. This confidence metric can be used either to generate a "confidence map" for visual distinction of reliable from unreliable regions, or in the data space to identify questionable measurements that can be analyzed separately or eliminated from analysis. In an analysis of nuclei in a 3-dimensional image volume, we show that the confidence map correlates well with visual evaluations of segmentation quality, and that the confidence metric correlates well with F1 scores within subregions of the image volume. In addition, we also describe three visualization methods that can visualize the segmentation differences between a segmented volume and a reference volume.

关键词： segmentation microscopy metrics confidence

来源：评论

学校读者我要写书评

暂无评论

Trigger Happy: Assessing the Viability of Trigger-Based In Situ analysis 11

Trigger Happy: Assessing the Viability of Trigger-Based In S...

引用

ieee 11th symposium on large data analysis and visualization (LDAV)

作者： Larsen, Matthew Harrison, Cyrus Turton, Terece L. Sane, Sudhanshu Brink, Stephanie Childs, Hank Lawrence Livermore Natl Lab Berkeley CA 94720 USA Los Alamos Natl Lab Los Alamos NM USA Univ Utah Salt Lake City UT 84112 USA Univ Oregon Eugene OR 97403 USA

ISBN: (纸本)9781665432832

Triggers are an emerging strategy for optimizing execution time for in situ analysis. However, their performance characteristics are complex, making it difficult to decide if a particular trigger-based approach is viable. With this study, we propose a cost model for trigger-based in situ analysis that can assess viability, and we also validate the model's efficacy. Then, once the cost model is established, we apply the model to inform the space of viable approaches, considering variation in simulation code, trigger techniques, and analyses, as well as trigger inspection and fire rates. Real-world values are needed both to validate the model and to use the model to inform the space of viable approaches. We obtain these values by surveying science application teams and by performing runs as large as 2,040 GPUs and 32 billion cells.

关键词： Analytical models Adaptation models Costs Codes Inspection Benchmark testing Tools

来源：评论

学校读者我要写书评

暂无评论

Log Parsing Evaluation in the Era of Modern Software Systems 34

Log Parsing Evaluation in the Era of Modern Software Systems

引用

34th ieee International symposium on Software Reliability Engineering (ISSRE)

作者： Petrescu, Stefan den Hengst, Floris Uta, Alexandra Rellerrneyer, Jan S. Leibniz Univ Hannover Dependable & Scalable Software Syst Hannover Germany ING Analyt Amsterdam Netherlands DFINITY Zurich Switzerland

ISBN: (纸本)9798350315943

Due to the complexity and size of modern software systems, the amount of logs generated is tremendous. Hence, it is infeasible to manually investigate these data in a reasonable time, thereby requiring automating log analysis to derive insights about the functioning of the systems. Motivated by an industry use-case, we zoom-in on one integral part of automated log analysis, log parsing, which is the prerequisite to deriving any insights from logs. Our investigation reveals problematic aspects within the log parsing field, particularly its inefficiency in handling heterogeneous real-world logs. We show this by assessing the 14 most-recognized log parsing approaches in the literature using (i) nine publicly available datasets, (ii) one dataset comprised of combined publicly available data, and (iii) one dataset generated within the infrastructure of a large bank. Subsequently, toward improving log parsing robustness in real-world production scenarios, we propose a tool, LOGCHIMERA, that enables estimating log parsing performance in industry contexts through generating synthetic log data that resemble industry logs. Our contributions serve as a foundation to consolidate past research efforts, facilitate future research advancements, and establish a strong link between research and industry log parsing.

关键词： log parsing automated log analysis reliability

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：