检索结果-内蒙古大学图书馆

Capsule-Based Regression Tracking via Background Inpainting

ieee TRANSACTIONS ON IMAGE PROCESSING 2023年 32卷 2867-2878页

作者： Ma, Ding Wu, Xiangqian Harbin Inst Technol Sch Comp Sci & Technol Harbin 150001 Peoples R China

Background cues play an accompanying role in most regression trackers, where they directly learn a mapping from dense sampling to soft label by giving a search area. In essence, the trackers need to identify a large amount of background information (i.e., other objects and distractor objects) under the circumstance of extreme target-background data imbalance. Therefore, we believe that it is more worth performing regression tracking depending on the informative background cues and using target cues as supplementary. To do this, we propose a capsule-based approach, referred to as CapsuleBI, which performs regression tracking based on a background inpainting network and a target-aware network. The background inpainting network explores the background representations by restoring the region of the target with all available scenes, and a target-aware network captures the target representations by focusing on the target itself only. To explore the subjects/distractors in the whole scene, we propose a global-guided feature construction module, which helps enhance the local features with global information. Both the background and target are encoded in capsules, which can model the relationships between objects or object parts in the background scene. Apart from this, the target-aware network assists the background inpainting network with a novel background-target routing algorithm that guides the background and target capsules to estimate the target location with multi-video relationships information precisely. Extensive experimental results show that the proposed tracker achieves favorably against state-of-the-art methods.

关键词： Target tracking Routing Tracking Feature extraction visualization Task analysis Semantics Visual object tracking background inpainting capsule networks

来源：评论

学校读者我要写书评

暂无评论

Designing a Topic-Based Literature Exploration Tool in AR - An exploratory study for neuroscience 21

Designing a Topic-Based Literature Exploration Tool in AR - ...

引用

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

作者： Tanhaei, Ghazaleh Troost, Ivar Hardman, Lynda Hurst, Wolfgang Univ Utrecht Utrecht Netherlands CWI Amsterdam Netherlands

ISBN: (数字)9781665453653

ISBN: (纸本)9781665453653

The large and increasing amount of scientific literature makes it difficult for researchers to analyse and understand relations between topics even in their specific sub-field. Neuroscience researchers are interested in relations between, for example, anatomical regions of the brain and the diseases that affect them. To explore relations in the extensive body of literature, using the topics themselves rather than individual articles, can provide a higher-level approach. We have created a prototype interactive AR environment to learn more about how topic-based literature browsing might aid researchers in analysing and understanding relations between topics. Given the three-dimensional nature of the brain, we postulate that visualizing neuroscience topics in Augmented Reality would support the exploration of relations between them and thus improve and extend existing literature exploration workflows. We follow a user-centered approach to identify visualization and interaction design requirements. Using an existing analysis of tens of thousands of neuroscience papers, we designed an interactive AR environment to support researchers in finding relations between brain regions and brain diseases that integrates with existing literature review practices. We carried out two qualitative evaluations to verify our design, first with eight neuroscience students as domain experts and then with seven experienced researchers as literature exploration experts. Our analysis of participants' feedback shows that visualizing topics and their relations in the immersive AR environment is clear, understandable and helpful for topic-based literature exploration, specifically, between brain regions and brain diseases. Our AR literature exploration tool has the potential to be used by neuroscientists in their routine literature reviews.

关键词： Human-centered computing visualization systems and tools Immersive Analytics Augmented Reality

来源：评论

学校读者我要写书评

暂无评论

FPGA-Based Brain-Computer Interface System for Real-Time Eye State Classification 36

FPGA-Based Brain-Computer Interface System for Real-Time Eye...

引用

36th SBC/SBMicro/ieee/ACM symposium on Integrated Circuits and Systems Design (SBCCI)

作者： Acuna, C. Flores, C. Tarrillo, J. Univ Ingn & Tecnol Lima Dept Elect Engn Lima Peru

ISBN: (纸本)9798350318340

Brain-computer interface (BCI) is a system that may benefit people with severe motor disabilities by allowing them to communicate using their brain's signals. However, trends in BCI implementation use large and heavy platforms, such as personal computers (PCs), which limit full integration with portable devices. Due to its parallelism, reconfigurable features, and capabilities to perform multiple channel processing, the Field-Programmable Gate Array (FPGA) platform is suitable for electroencephalography (EEG) signal processing. This paper presents the design and implementation of an FPGA-based BCI embedded system for eye state classification in real-time. The system was implemented using Xilinx Artix-7 family FPGA. The designed system filtered EEG signals using FIR filters and the pattern features were calculated using Power Spectral Density (PSD). Furthermore, Linear Discriminant analysis (LDA) was used to classify EEG data related to the eye state. The proposed system was tested using recorded data from a subject acquired by the open-source biosensing board Cyton for offline and online evaluation. The system achieved an accuracy of 81.1% during real-time sessions. Finally, the results show the execution time, resources, and power consumption of the designed system.

关键词： Brain-computer interface EEG signals reconfigurable systems FPGA digital FIR filters linear discriminant analysis

来源：评论

学校读者我要写书评

暂无评论

Research on 3D visualization of Geographic Information data in Big data Environment

Research on 3D Visualization of Geographic Information Data ...

引用

2023 International Conference on Applied Physics and Computing, ICAPC 2023

作者： Zhang, Jiantao Lai, Weiping Huang, Yanshan Wu, Jianbin Lin, Xiaojun State Grid Info-Telecom Great Power Science and Technology Co. Ltd. Fujian Fuzhou350000 China

ISBN: (纸本)9798350359244

This paper introduces a system framework for rapid construction and rendering of 3D virtual environment using 2D GIS data. A large-scale GIS data 3D visualization system is designed and implemented. ArcSDE and SQL Server are used to store data. After extraction, processing and registration of multi-band images, the images are stored in the database in Shape form. SURF feature points were extracted and images were matched. DEM is combined with preprocessed multi-band remote sensing images. It was 3D visualized by AcrScene software. The system can well realize correlation analysis, two-dimensional and three-dimensional attribute correlation query, and big data rendering. After testing, this design has good smoothness, fast response and good picture quality. It has nice interactive features. The system can automatically load and splice terrain data. © 2023 ieee.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

2023 ieee USNC-URSI Radio Science Meeting (Joint with AP-S symposium), AP-S/URSI 2023 - Proceedings

2023 IEEE USNC-URSI Radio Science Meeting (Joint with AP-S S...

引用

2023 ieee USNC-URSI Radio Science Meeting (Joint with AP-S symposium), AP-S/URSI 2023

ISBN: (纸本)9781946815187

The proceedings contain 60 papers. The topics discussed include: adopting a flying base station for connectivity coverage of temporary events;Green’s Function for pedagogical development III: laboratory visualization;a sub-THz micro-doppler radar for counter-surveillance applications;reliability studies of fully integrated CMOS power amplifier on thinned substrate for flexible electronics;RF interoperability analysis for fighter aircrafts;susceptibility of the radio navigation system of small UAVs to radiated electromagnetic interference;estimating near-field signals emanated by embedded systems using data-dependent EM profiles as basis functions;an efficient indoor and outdoor localization method based on RSSI using ZigBee modules;compact size and thin substrate ultra-wideband antenna for 5g applications;and adopting a flying base station for connectivity coverage of temporary events.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Smart sensors and IoT applied in Digital Twin for Industry 4.0

Smart sensors and IoT applied in Digital Twin for Industry 4...

引用

2024 International symposium on Sensing and Instrumentation in 5G and IoT Era, ISSI 2024

作者： Boltaboyeva, Assiya Baigarayeva, Zhanel Postolache, Octavian Mansurova, Madina Karymssakova, Nurgul Belgibayev, Baurzhan Al-Farabi Kazakh National University Artificial Intellegence and Big Data Almaty Kazakhstan Lisbon Portugal

ISBN: (纸本)9798350378689

This article discusses the integration of smart sensors and the Internet of Things (IoT) in digital twins for Industry 4.0, representing a transformative approach to industrial operations. We explore the applications, benefits, and challenges associated with using smart sensors and IoT technologies in the context of digital twins. Digital twins, virtual replicas of physical assets or processes, rely on real- time data provided by smart sensors and IoT devices for continuous monitoring, analysis, and optimization of industrial operations. The focus is on the role of smart sensors and I o T in creating and maintaining accurate and efficient digital twins, addressing challenges such as data security issues, compatibility concerns, and the complexity of managing heterogeneous sensor networks in large industrial environments. © 2024 ieee.

关键词： Smart manufacturing

来源：评论

学校读者我要写书评

暂无评论

Visual Analytics for Decision Support: A Supply Chain Perspective

引用

ieee ACCESS 2021年 9卷 81326-81344页

作者： Khakpour, Alireza Colomo-Palacios, Ricardo Martini, Antonio Ostfold Univ Coll Fac Comp Sci N-1757 Halden Norway Univ Oslo Dept Informat N-0373 Oslo Norway

Supply chain (SC) activities generate huge amount of data that can be used in decision making processes. However, proper data analytics techniques are required to combine, organize, and analyze data from different sources and produce required insights available for decision makers. These techniques promote analytical reasoning of the events and patterns hidden in the data using visualizations, so-called Visual Analytics (VA). Although there is a large number of VA systems to facilitate the process of analysis and decision making, there is a lack of an adequate overview of what already exists in this area for SC management. To address that need, we conducted a systematic literature review to analyze the state of the art in SC VA systems. Particularly, we focus on use cases, the type of the decisions that a VA system intended to support, the type of visualizations employed, the type of analytics used, and the data that has been used for analysis. The goal of this study is to provide SC and VA researchers with an overview of the works carried out in the field of SC VA, helping them to observe latest trends and to recognize existing gaps that need further investigation. Consequently, a mapping between decisions of various SC business processes and their reciprocal visualization techniques and tactics have been provided. Adding to that, VA applications and use cases in SC are identified based on the SC Operation Reference (SCOR) model and underlying decision areas are recognized.

关键词： data visualization Business Companies Visual analytics Decision making Supply chains data analysis Decision support information visualization value chain analysis visual analytics visualization techniques and methodologies

来源：评论

学校读者我要写书评

暂无评论

A COSMO-SKYMED TEST CASE OF A FAST FRAMEWORK FOR SEMI-AUTOMATIC MONITORING OF INFRASTRUCTURE

A COSMO-SKYMED TEST CASE OF A FAST FRAMEWORK FOR SEMI-AUTOMA...

引用

ieee International Geoscience and Remote Sensing symposium (IGARSS)

作者： Di Tullio, M. Picchiani, M. Polcari, M. Bignami, C. Maranesi, M. Angeli, C. Marchetti, P. G. Pollino, M. Rosato, V. GMATICS SRL Rome Italy Ist Nazl Geofis & Vulcanol Rome Italy On Air Consulting & Solut SRL Rome Italy ENEA Casaccia Res Ctr Rome Italy

ISBN: (数字)9781665427920

ISBN: (纸本)9781665427920

In this study, the potentiality of an automatic processing system for fast implementation of interferometric SAR analysis is tested over a time series of COSMO-SkyMed data. A system architecture for the end-to-end implementation of Permanent Scatterer workflow is illustrated and applied to a test case located over the South-West area of the Rome area. The system architecture is aimed at providing a high degree of automation in the different steps of the procedures, from the Satellite products download and storage up to the data visualization. The proposed solution can be integrated with both commercial processing tools and open source frameworks. A two years of COSMO-SkyMed acquisitions from the MAPITALY archive have been analysed with SARscape and a customized open source workflow. The obtained results highlighted some interesting features on the considered area of interest. Moreover, the outcome of the analyses are in good agreement with previous studies on the same geographical region.

关键词： SAR Interferometry COSMO-SkyMed Automatic processing systems Permanent Scatterer analysis

来源：评论

学校读者我要写书评

暂无评论

Visual analysis of Social Robots in Twitter on China Agenda Setting 2

Visual Analysis of Social Robots in Twitter on China Agenda ...

引用

2nd International symposium on Artificial Intelligence and its Application on Media, ISAIAM 2022

作者： Si, Zhengming Li, Haitong Ding, Yu School of Architecture Harbin Institute of Technology Key Lab. of Interactive Media Des. and Equipment Service Innovation Ministry of Culture and Tourism Harbin China

ISBN: (纸本)9781665485418

With the development and progress of intelligent algorithms, more and more social robots are used to interfere with the information transmission and direction of international public opinion. This paper takes the agenda of COVID-19 in Twitter as the breakthrough point, and through the methods of web crawler, Twitter robot detection, data processing and analysis, aims at the agenda setting of social robots for China issues, that is, to carry out data visualization analysis for the stigmatized China image. Through case analysis, concrete and operable countermeasures for building the international communication system of China image were provided. © 2022 ieee.

关键词： data visualization

来源：评论

学校读者我要写书评

暂无评论

harDNNing: a machine-learning-based framework for fault tolerance assessment and protection of DNNs 28

harDNNing: a machine-learning-based framework for fault tole...

引用

28th ieee European Test symposium (ETS)

作者： Traiola, Marcello Kritikakou, Angeliki Sentieys, Olivier Univ Rennes CNRS INRIA IRISA Rennes France

ISBN: (纸本)9798350336344

Deep Neural Networks (DNNs) show promising performance in several application domains, such as robotics, aerospace, smart healthcare, and autonomous driving. Never-theless, DNN results may be incorrect, not only because of the network intrinsic inaccuracy, but also due to faults affecting the hardware. Indeed, hardware faults may impact the DNN inference process and lead to prediction failures. Therefore, ensuring the fault tolerance of DNN is crucial. However, common fault tolerance approaches are not cost-effective for DNNs protection, because of the prohibitive overheads due to the large size of DNNs and of the required memory for parameter storage. In this work, we propose a comprehensive framework to assess the fault tolerance of DNNs and cost-effectively protect them. As a first step, the proposed framework performs datatype-and-layer-based fault injection, driven by the DNN characteristics. As a second step, it uses classification-based machine learning methods in order to predict the criticality, not only of network parameters, but also of their bits. Last, dedicated Error Correction Codes (ECCs) are selectively inserted to protect the critical parameters and bits, hence protecting the DNNs with low cost. Thanks to the proposed framework, we explored and protected two Convolutional Neural Networks (CNNs), each with four different data encoding. The results show that it is possible to protect the critical network parameters with selective ECCs while saving up to 83% memory w.r.t. conventional ECC approaches.

关键词： Reliability analysis Fault Tolerance Machine Learning Neural Networks

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：