检索结果-内蒙古大学图书馆

56th ieee International symposium on Circuits and Systems (ISCAS)

作者： Wang, Qingxun Pan, Yuhan Chen, Kaiquan Lin, Yu Wang, Biao Qi, Liang Shanghai Jiao Tong Univ Dept Micronano Elect Shanghai Peoples R China Univ Macau State Key Lab Analog & Mixed Signal VLSI Macau Peoples R China

ISBN: (纸本)9781665451093

This paper presents a two-phase linear-exponential incremental analog-to-digital converter (IADC) with using second-order noise coupling (NC). In the first phase, it works as a first-order IADC. Then the second-order NC path is activated in the second phase to significantly expedite the accumulation speed. Moreover, during the second phase, the integrator is disabled to achieve a large maximum stable amplitude (MSA). Simulations demonstrated that the proposed architecture could achieve a higher signal-to-quantization-noise ratio (SQNR) while avoiding the noise penalty and keeping the high effectiveness of data weighting averaging (DWA) compared with the prior art with using first-order NC. Mathematical analysis and further simulation results are presented to confirm the theory of the proposed structure.

关键词： incremental analog-to-digital converter (IADC) linear-exponential second-order noise coupling (NC) the effective data weighting averaging (DWA) and suppression of thermal noise

来源：评论

学校读者我要写书评

暂无评论

TraceStream: Anomalous Service Localization based on Trace Stream Clustering with Online Feedback 34

TraceStream: Anomalous Service Localization based on Trace S...

引用

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

作者： Zhou, Tong Zhang, Chenxi Peng, Xin Yan, Zhenghui Li, Pairui Liang, Jianming Zheng, Haibing Zheng, Wujie Deng, Yuetang Fudan Univ Sch Comp Sci Shanghai Peoples R China Fudan Univ Shanghai Key Lab Data Sci Shanghai Peoples R China Shanghai Collaborat Innovat Ctr Intelligent Visua Shanghai Peoples R China Tencent Inc Shenzhen Peoples R China

ISBN: (纸本)9798350315943

Modern large-scale service-based systems such as microservice systems have become increasingly complex, making it hard to localize anomalous services when various issues emerge. Traces record the workflows of requests through service instances and have been widely used in anomaly detection and root cause analysis. Existing trace-based approaches widely use statistical methods or learning-based techniques to detect trace anomalies and localize anomalous services. However, these approaches often suffer from the concept drift problem, i.e., the statistical properties of traces change over time in unforeseen ways. In this paper, we propose TraceStream, an anomalous service localization approach based on trace data stream clustering. TraceStream uses data stream clustering to discover potential anomalous trace clusters in evolving trace data and uses spectrum analysis to localize anomalous services based on the clusters. Moreover, TraceStream can effectively incorporate the online feedback of operation engineers based on the trace clusters to improve the accuracy for localizing anomalous services. Our evaluation confirms that TraceStream can effectively detect anomalies and localize anomalous services in an evolving microservice system. It can effectively incorporate human feedback to further improve the performance of anomalous service localization. Moreover, TraceStream is efficient and its efficiency can be further improved by sampling a small portion of traces by cluster.

关键词： microservice anomaly detection fault localization distributed tracing trace stream clustering

来源：评论

学校读者我要写书评

暂无评论

Visual analysis of large Multivariate Scattered data using Clustering and Probabilistic Summaries

引用

ieee TRANSACTIONS ON visualization AND COMPUTER GRAPHICS 2021年第2期27卷 1580-1590页

作者： Rapp, Tobias Peters, Christoph Dachsbacher, Carsten Karlsruhe Inst Technol Karlsruhe Germany

Rapidly growing data sizes of scientific simulations pose significant challenges for interactive visualization and analysis techniques. In this work, we propose a compact probabilistic representation to interactively visualize large scattered datasets. In contrast to previous approaches that represent blocks of volumetric data using probability distributions, we model clusters of arbitrarily structured multivariate data. In detail, we discuss how to efficiently represent and store a high-dimensional distribution for each cluster. We observe that it suffices to consider low-dimensional marginal distributions for two or three data dimensions at a time to employ common visual analysis techniques. Based on this observation, we represent high-dimensional distributions by combinations of low-dimensional Gaussian mixture models. We discuss the application of common interactive visual analysis techniques to this representation. In particular, we investigate several frequency-based views, such as density plots in 1D and 2D, density-based parallel coordinates, and a time histogram. We visualize the uncertainty introduced by the representation, discuss a level-of-detail mechanism, and explicitly visualize outliers. Furthermore, we propose a spatial visualization by splatting anisotropic 3D Gaussians for which we derive a closed-form solution. Lastly, we describe the application of brushing and linking to this clustered representation. Our evaluation on several large, real-world datasets demonstrates the scaling of our approach.

关键词： data visualization Probabilistic logic data models visualization Three-dimensional displays Gaussian mixture model interactive visual analysis probabilistic data summaries multivariate data scattered data Gaussian mixture models Gaussian rendering

来源：评论

学校读者我要写书评

暂无评论

MemesViTa: A Novel Multimodal Fusion Technique for Troll Memes Identification

引用

ieee ACCESS 2024年 12卷 177811-177828页

作者： Sultan, Tipu Rony, Mohammad Abu Tareq Islam, Mohammad Shariful Aldosary, Saad El-Shafai, Walid St Louis Univ Dept Aerosp & Mech Engn St Louis MO 63103 USA Noakhali Sci & Technol Univ Dept Stat Noakhali 3814 Bangladesh Noakhali Sci & Technol Univ Dept Comp Sci & Telecommun Engn Noakhali 3814 Bangladesh King Saud Univ Community Coll Dept Comp Sci Riyadh 11437 Saudi Arabia Menoufia Univ Fac Elect Engn Dept Elect & Elect Commun Engn Menoufia 32952 Egypt

The proliferation of troll memes on social media platforms has become a pressing issue due to their potential to spread misinformation and incite conflict. Detecting troll memes is complex due to the intricate interplay between visual and textual elements. In this research, we propose MemesViTa, a novel multimodal fusion model that combines Vision Transformer (ViT) for image processing and DeBERTa for textual analysis, specifically designed to detect troll memes with high accuracy. This research uses a public dataset of 4,368 training image-text and 1092 testing image-text. The primary goal of this study is to identify the most effective approach for troll meme detection by evaluating the performance of different multimodal models. We comprehensively assess multimodal deep learning approaches for troll meme detection, leveraging visual, textual, and large Language Models in zero-shot and few-shot scenarios. Our study integrates models including BERT, GPT-2, GPT-4, VGG16, ResNet50, and ViT to analyze their performance. Experimental results indicate that the proposed ViT+DeBERTa model, named MemesViTa, achieves superior results, with 94.287% accuracy and 95.82% F1 score, representing a 41.3% improvement over the best visual model of VGG16 and a 48.1% improvement over the best textual model of CNN. Standalone LLMs like GPT-4, even in few-shot scenarios, show promising yet inferior results, with GPT-4 in a 50-shot scenario reaching an accuracy of 80.00% and an F1 score of 37.00%. Multimodal combinations, including BERT+VGG16 and BERT+VGG16+CLIP, highlight the importance of integrating multiple data modalities. Our findings suggest that combining visual and textual data and the strategic use of LLMs can significantly improve the robustness and accuracy of troll meme detection systems. In the future, we intend to enhance our dataset by incorporating a broader spectrum of troll memes. This will help our model to work better across different social media platforms and conte

关键词： visualization Accuracy Adaptation models Electronic mail Computational modeling Analytical models Training Social networking (online) Hate speech Safety Deep learning troll memes text multimodal GPT large language model

来源：评论

学校读者我要写书评

暂无评论

Applying Innovative AI Techniques to Complex U.S. Army datasets 71

Applying Innovative AI Techniques to Complex U.S. Army Datas...

引用

71st Annual Reliability and Maintainability symposium, RAMS 2025

作者： Mills, Jordan Shumate, Megan Walker, Kris Alexander, Russ INTUITIVE Research and Technologies Corporation 5030 Bradford Drive Bldg. 2 Ste. 205 HuntsvilleAL35805 United States RAM Engineering & System Assessment Division DEVCOM Aviation & Missile Center 5400 Fowler Road Redstone Arsenal AL35898 United States SpecTrum A&T Solutions LLC United States

ISBN: (纸本)9798350367744

As the amount of data that engineers and analysts needed to evaluate increases, the use of Artificial Intelligence (AI) techniques become more critical. Big data analytics tools can be used to find patterns and relationships within large data sets and the domain of Reliability, Availability, and Maintainability (RAM) for aircraft and missiles provides an ideal application for these big data methods. For aviation data, looking at relationships and patterns within and between maintenance events and on-board flight sensor data can provide added value for maintenance and logistics managers. For missile system data, looking at relationships and patterns within different collections of test data for the weapon system helps support important RAM decisions related to root cause analysis, the identification of reliability degradation trends, and the extension of missile shelf life. In this paper, the authors detail the integration of big data analytics tools and techniques to provide value to RAM stakeholders through the innovative analysis of aviation and missile datasets. © 2025 ieee.

关键词： data reliability

来源：评论

学校读者我要写书评

暂无评论

Deep Learning with HM-VGG: AI Strategies for Multi-modal Image analysis 3

Deep Learning with HM-VGG: AI Strategies for Multi-modal Ima...

引用

3rd International symposium on Sensor Technology and Control, ISSTC 2024

作者： Du, Junliang Cang, Yiru Zhou, Tong Hu, Jiacheng He, Weijie Shanghai Jiao Tong University Shanghai China Northeastern University Boston United States Rice University Houston United States Tulane University New Orleans United States University of California Los Angeles Los Angeles United States

ISBN: (纸本)9798331541637

This study introduces the Hybrid Multi-modal VGG (HM-VGG) model, a cutting-edge deep learning approach for the early diagnosis of glaucoma. The HM-VGG model utilizes an attention mechanism to process Visual Field (VF) data, enabling the extraction of key features that are vital for identifying early signs of glaucoma. Despite the common reliance on large annotated datasets, the HM-VGG model excels in scenarios with limited data, achieving remarkable results with small sample sizes. The model's performance is underscored by its high metrics in Precision, Accuracy, and F1-Score, indicating its potential for real-world application in glaucoma detection. The paper also discusses the challenges associated with ophthalmic image analysis, particularly the difficulty of obtaining large volumes of annotated data. It highlights the importance of moving beyond single-modality data, such as VF or Optical Coherence Tomography (OCT) images alone, to a multimodal approach that can provide a richer, more comprehensive dataset. This integration of different data types is shown to significantly enhance diagnostic accuracy. The HMVGG model offers a promising tool for doctors, streamlining the diagnostic process and improving patient outcomes. Furthermore, its applicability extends to telemedicine and mobile healthcare, making diagnostic services more accessible. The research presented in this paper is a significant step forward in the field of medical image processing and has profound implications for clinical ophthalmology. © 2024 ieee.

关键词： Ophthalmology

来源：评论

学校读者我要写书评

暂无评论

Corrigible Action Recognition System through Motion-Sphere Trajectories for Standard Metaverse Actions 21

Corrigible Action Recognition System through Motion-Sphere T...

引用

21st ieee International symposium on Mixed and Augmented Reality (ISMAR)

作者： Ryu, Jaeyeong Kim, Dongyeong Chai, Youngho Chung Ang Univ Grad Sch Adv Imaging Sci Seoul South Korea

ISBN: (数字)9781665453653

ISBN: (纸本)9781665453653

We propose a corrigible motion recognition system for metaverse applications, which can visualize motion data to analyze user motion and correct wrong motion data. To test the system performance, we created a metaverse dataset. The dataset consists of user interface/game/interaction classes, all of which are actions that can be used in metaverse applications. We collected motion data and conducted a recognition rate comparison experiment. We hypothesize that the recognition rate could be enhanced using proper input data types. To verify this hypothesis, we converted the motion data into three data types and recognized the data using spatial-temporal graph convolutional networks. The experimental results revealed that the recognition rate varied according to the input data types. The highest recognition performance was derived from angle-based data types. Finally, we analyzed the reason for misclassifications using Motion-Sphere. During the analysis process, we determined the standard action of the training data. We corrected wrong action data according to the standard action and confirmed the increased recognition rate. We proved that our system could correct misclassification cases using standard action through the enhanced recognition rate.

关键词： Human-centered computing-Human computer interaction (HCI)-Interaction techniques-Gestural input Human-centered computing-visualization-visualization application domains-Visual analytics

来源：评论

学校读者我要写书评

暂无评论

The Method of Making the Low-dimensional Map that Preserves the Distance Relationships from Selected data Point 24

The Method of Making the Low-dimensional Map that Preserves ...

引用

ieee 24th International Conference on Information Reuse and Integration for data Science (IRI)

作者： Yoshioka, Koki Niina, Gen Dozono, Hiroshi Saga Univ Fac Sci & Engn Saga Japan Saga Densan Ctr R&D Ctr Saga Japan

ISBN: (纸本)9798350334586

In recent years, data analyses have been conducted in various fields. If the data distribution is unknown before analysis, it is often necessary to determine it. Based on the obtained distribution, hypotheses are set up and the analysis is conducted according to the task. In general, data are high-dimensional with many elements. Therefore, dimensionality reduction is performed to determine the data distribution. Dimensionality reduction maps high-dimensional data onto a low-dimensional space of two or three dimensions while preserving the data features. This allows humans to easily grasp the data distribution. However, in a low-dimensional space, the number of dimensions that can be used for expression is reduced;thus, there will inevitably be gaps in the distance relationships between data in high-dimensional and low-dimensional spaces. As a result, the gaps lead to misinterpretation of the data distribution and analyses, based on incorrect hypotheses. To solve this problem, one possible method is to select a data point with a large gap in the distance relationships as a candidate and check the low-dimensional map that preserves the distance relationships from the candidate data point to the other data points, while preserving the distance relationships between noncandidate data points as much as possible. In this paper, we propose a method that creates a low- dimensional map in which the distance relationships from one selected data point to the other data points are preserved. As a result of the experiment, we confirmed that the proposed method preserves the distance relationships from the candidate data point to the other data points, while preserving the distance relationships between noncandidate data points as much as possible.

关键词： machine learning dimensionality reduction data visualization Self-Organizing Map

来源：评论

学校读者我要写书评

暂无评论

Semi-Supervised Multimodal Representation Learning Through a Global Workspace

引用

ieee TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2025年第5期36卷 7843-7857页

作者： Devillers, Benjamin Maytie, Leopold VanRullen, Rufin Univ Toulouse CerCo CNRS UMR 5549 F-31013 Toulouse France Artificial & Nat Intelligence Toulouse Inst ANITI F-31400 Toulouse France

Recent deep learning models can efficiently combine inputs from different modalities (e.g., images and text) and learn to align their latent representations or to translate signals from one domain to another (as in image captioning or text-to-image generation). However, current approaches mainly rely on brute-force supervised training over large multimodal datasets. In contrast, humans (and other animals) can learn useful multimodal representations from only sparse experience with matched cross-modal data. Here, we evaluate the capabilities of a neural network architecture inspired by the cognitive notion of a "global workspace" (GW): a shared representation for two (or more) input modalities. Each modality is processed by a specialized system (pretrained on unimodal data and subsequently frozen). The corresponding latent representations are then encoded to and decoded from a single shared workspace. Importantly, this architecture is amenable to self-supervised training via cycle-consistency: encoding-decoding sequences should approximate the identity function. For various pairings of vision-language modalities and across two datasets of varying complexity, we show that such an architecture can be trained to align and translate between two modalities with very little need for matched data (from four to seven times less than a fully supervised approach). The GW representation can be used advantageously for downstream classification and cross-modal retrieval tasks and for robust transfer learning. Ablation studies reveal that both the shared workspace and the self-supervised cycle-consistency training are critical to the system's performance.

关键词： Task analysis Training visualization Trajectory Synchronization Representation learning Annotations Cycle-consistency global workspace (GW) theory multimodal learning semi-supervised learning

来源：评论

学校读者我要写书评

暂无评论

RISK analysis OF COASTAL AREAS: AN AI-BASED PERSPECTIVE USING SAR data

RISK ANALYSIS OF COASTAL AREAS: AN AI-BASED PERSPECTIVE USIN...

引用

ieee International Geoscience and Remote Sensing symposium (IGARSS)

作者： Mastro, Pietro Pepe, Antonio Italian Natl Res Council Inst Electromagnet Sensing Environm IREA 328 Diocleziano I-80124 Naples Italy

ISBN: (纸本)9798350320107

In this work, a Change Detection (CD) analysis was conducted based on the assessment of ground deformation (subsidence) in the Venice Lagoon over recent years. The multi-temporal interferometric Small Baseline Subset (SBAS) technique [1], [2] was employed to analyze the interconnections between the subsidence in the area and the occurrence of extreme flood events, with a specific focus on the floods that occurred in November 2019. Examining the time series of backscattered signals from the Sentinel-1 (S-1) synthetic aperture radar (SAR) sensor, we identified the extent of the flooded regions and evaluated the impact of the floods on the city. The potential of a newly developed Artificial Intelligence (AI) method [3] based on Random Forest [4], [5] was exploited. This methodology leverages the capability of several coherent/incoherent SAR change detection indices (CDIs) and their mutual interaction in a single corpus for rapid mapping of surface changes. This method [3] has shown great success in rapidly mapping land surface changes of areas in Sardinia and Sicily that were affected by large wildfires in the summer of 2021 and flooded areas in Houston and Galveston Bay as a result of Hurricane Harvey in 2017. In conclusion, the comprehensive CD/SBAS analysis provided valuable insights into the relationship between subsidence and recent extreme flood events in the Venice Lagoon, revealing the dynamics of the lagoon and its vulnerability to such events.

关键词： SAR Interferometry Displacement Machine Learning (ML) Change Detection (CD)

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：