检索结果-内蒙古大学图书馆

data Intelligence and Innovative Application (DiiA), IEEE International conference on

作者： Haigui Zhu Xiaonan Luo Zhongyi Zhai Ji Li Fang Li Xiaoshu Zhu School of Computer Science and Information Security Guilin University of Electronic Technology Guilin China

ISBN: (数字)9798331504434

ISBN: (纸本)9798331504441

Vision-guided autonomous underwater vehicles (AUVs) are becoming crucial tools for deep-sea exploration, resource assessment, and mariculture, among other underwater tasks. However, the challenging underwater environment often leads to image distortion and quality degradation, which negatively impacts the accuracy of vision systems and hinders effective target detection. Recently, the advancement of deep learning, particularly through Transformer-based architectures, has opened new avenues for improving underwater image enhancement. However, applying Transformer models directly for this task faces challenges, including the difficulty of capturing global information at the pixel level while preserving local details. In this paper, we introduce an innovative approach that combines the U-Net network with YOLOv5 for enhanced underwater target detection. Firstly, we construct an improved U-Net model, which can better correct color distortion in global and local features, and overcome the limitations of Transformer in extracting details and textures through convolutional neural networks. Next, YOLOv5 is used to detect the target of the enhanced image, and the quality of information extraction at high and low resolutions is improved through multi-level feature fusion, thus strengthening the attention and correction of severely degraded areas in the image. The experimental results show that our method has obvious advantages in subjective visual perception and comprehensive performance evaluation compared with the existing technology, and shows excellent learning and generalization ability.

关键词： YOLO Image color analysis Feature extraction Distortion visual effects Transformers Real-time systems Circuit faults Image enhancement visual perception

来源：评论

学校读者我要写书评

暂无评论

visual Communication Design of Multi-dimensional Image visualization Fusion System Based on Wavelet Transform

Visual Communication Design of Multi-dimensional Image Visua...

引用

Electronic Technology, Communication and Information (ICETCI), IEEE International conference on

作者： Wenjie Li Art Education Teaching and Research Section of Marxism College Changchun University of Chinese Medicine Changchun China

With the rapid development of remote sensing technology, multi-source remote sensing image fusion has become one of the hot issues in remote sensing field in recent years. Aiming at the poor edge registration of images obtained by conventional remote sensing image fusion system, a multidimensional visual fusion system of remote sensing images based on visual communication is designed. CABAC encoder is selected to make data flow and control flow cooperate with each other to obtain feedback data. However, the rapid increase of data also increases the difficulty of comprehensive observation, because the image data obtained by different sensors have their own differences and limitations in spectral information and spatial details, so we want to bring the fusion technology into this field, expand the working range of the system, improve the reliability of the system, obtain a more efficient representation of information and improve the cost performance of the system. Image fusion technology plays an extremely important role in remote sensing, medicine, natural resources exploration, marine resources management, topography analysis, biology and other fields. The left and right focused images, infrared images and visible images are used for simulation experiments, and the objective evaluation indexes of images are used to verify the feasibility of this method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Interpreting Autonomous Driving Corner Cases: A visual Analytics Approach

Interpreting Autonomous Driving Corner Cases: A Visual Analy...

引用

Pacific (formerly Asia-Pacific APVIS) visualization Symposium

作者： Yi Sun Zekai Shao Xingyu Qiu Yun Li Ting Liu Linbing Xiang Dong Sun Siming Chen Fudan University NIO Shanghai

ISBN: (数字)9798350393804

ISBN: (纸本)9798350393811

With the progression of artificial intelligence, there has been substantial advancement in autonomous driving technology. However, even the most advanced systems may confront failures in certain corner cases, necessitating enhanced analytical approaches. Traditional approaches focused on the numerical analysis of isolated sensor data, are often insufficient for deriving meaningful insights in such situations. To address this inadequacy, we propose a visual analytics approach, crafted to aid domain experts in performing analyses and extracting system improvements from cases with unexpected behaviors. This approach intricately integrates extensive driving scenarios and low-level module behaviors into the autonomous driving decision-making process, utilizing rich visualizations and an interface for interactive exploration and systematic synthesis of findings. Uniquely, our system opens the "black box" of modules in the decision-making pipeline during corner cases, taking into account both the overall decision-making pipeline and the fine-grained behaviors of the modules in the pipeline, setting our approach apart from previous works. To validate our system’s effectiveness, we perform two case studies, inviting domain experts for evaluation, and the results confirm our system’s efficacy in allowing experts to obtain crucial insights into autonomous driving systems.

关键词： Systematics Numerical analysis visual analytics Pipelines Decision making System improvement Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Short Video E-Commerce Marketing of Convolutional Neural Network Based Transfer Learning with visual Geometry Group16

Short Video E-Commerce Marketing of Convolutional Neural Net...

引用

Integrated Intelligence and Communication Systems (ICiiCS), International conference on

作者： Jia Wen School of Business Administration Guangzhou Institute of Science and Technology Guangzhou China

ISBN: (数字)9798331504960

ISBN: (纸本)9798331504977

In Recent years, E-commerce stands as a prominent testament to the transformative power of information and communications technologies in driving economic growth and development. Traditional approaches from short video ecommerce marketing had faced several issues which include large data size, required more computational resources. Therefore, this research proposes Convolutional Neural Network (CNN) based Transfer Learning with visual Geometry Group (VGG)16 for Short Video E-commerce Marketing. Initially, the data is taken from Buyer-generated Fashion Video (BFV) dataset and consists of fashion videos generated by users, showcasing their purchases and experiences with fashion products. The data is preprocessed by using frame extraction and then the features are extracted by using CNN based Transfer Learning with VGG16 which effectively reduces the training time and computational resources. Next, the You Only Look Once (YOLO) is used for feature engineering where YOLO enabled the analysis of object based features. Finally, the evaluation and optimization is done by Multi armed bandit where it provides efficient way to balance exploration and exploitation which enabled real time optimization. The proposed CNN based Transfer Learning with VGG16 achieved accuracy (0.955), precision (0.977), recall (0.968) and F1 Score (0.970) when compared with existing Hierarchical Oversampling Word Embedding Network (HOWNET).

关键词： YOLO Geometry Training visualization Transfer learning Feature extraction Convolutional neural networks Electronic commerce data mining Optimization

来源：评论

学校读者我要写书评

暂无评论

ClusterSets: Optimizing Planar Clusters in Categorical Point data

引用

COMPUTER GRAPHICS FORUM 2021年第3期40卷 471-481页

作者： Geiger, J. Cornelsen, S. Haunert, J. -H. Kindermann, P. Mchedlidze, T. Noellenburg, M. Okamoto, Y. Wolff, A. Univ Wurzburg Wurzburg Germany Univ Konstanz Constance Germany Univ Bonn Bonn Germany Univ Trier Trier Germany Univ Utrecht Utrecht Netherlands TU Wien Vienna Austria Univ Electrocommun Tokyo Japan

In geographic data analysis, one is often given point data of different categories (such as facilities of a university categorized by department). Drawing upon recent research on set visualization, we want to visualize category membership by connecting points of the same category with visual links. Existing approaches that follow this path usually insist on connecting all members of a category, which may lead to many crossings and visual clutter. We propose an approach that avoids crossings between connections of different categories completely. Instead of connecting all data points of the same category, we subdivide categories into smaller, local clusters where needed. We do a case study comparing the legibility of drawings produced by our approach and those by existing approaches. In our problem formulation, we are additionally given a graph G on the data points whose edges express some sort of proximity. Our aim is to find a subgraph G ' of G with the following properties: (i) edges connect only data points of the same category, (ii) no two edges cross, and (iii) the number of connected components (clusters) is minimized. We then visualize the clusters in G '. For arbitrary graphs, the resulting optimization problem, Cluster Minimization, is NP-hard (even to approximate). Therefore, we introduce two heuristics. We do an extensive benchmark test on real-world data. Comparisons with exact solutions indicate that our heuristics do astonishing well for certain relative-neighborhood graphs.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

A Systematic Approach to Tuning Cover Parameters in Mapper for Improved TDA Representation

A Systematic Approach to Tuning Cover Parameters in Mapper f...

引用

Metrology for Extended Reality, Artificial Intelligence and Neural Engineering (MetroXRAINE), IEEE International conference on

作者： Stefano Vannoni Emma Tassi Inês Won Sampaio Anna M. Bianchi Eleonora Maggioni Dept. of Electronics Information and Bioengineering Politecnico di Milano Milan Italy Dept. of Neurosciences and Mental Health Fondazione IRCCS Ca’ Granda Osp. Maggiore Policlinico Milan Italy

ISBN: (数字)9798350378009

ISBN: (纸本)9798350378016

Topological data analysis (TDA) offers a powerful framework for analyzing complex datasets by leveraging algebraic topology to unveil underlying structures. Within TDA, the Mapper algorithm plays a pivotal role in transforming data into a simplified graph representation, known as a simplicial complex. However, selecting appropriate parameters within the Mapper algorithm remains a challenge due to the absence of a standardized approach. In this study, we propose a systematic methodology for choosing Cover parameters by integrating quantitative assessment, using the Netsimile metric and graph topological features, with qualitative visual analysis. We demonstrate the efficacy of our approach using brain features from the Human Connectome Project dataset. Through a comprehensive evaluation, we identify parameter configurations that enhance graph properties stability producing informative graph structures. Our findings highlight the importance of integrating quantitative metrics into the parameter selection process, paving the way for enhanced data exploration and understanding. The open-source nature of our methodology promotes broader adoption and application across diverse datasets and analytical workflows.

关键词： Measurement visualization Systematics Extended reality Neural engineering Metrology Stability analysis Topology Tuning Testing

来源：评论

学校读者我要写书评

暂无评论

visual exploration of Urban Road Network Traffic Based on Reconstructed Trajectory data 21

Visual Exploration of Urban Road Network Traffic Based on Re...

引用

20th and 21st Joint COTA International conference of Transportation Professionals - Advanced Transportation, Enhanced Connection

作者： He, Ning Liu, Linwei Ma, Chengyuan Gao, Lizhi Tang, Guangying Yu, Chunhui ShenZhen Genvict Technol Co Ltd Shenzhen Guangdong Peoples R China Tongji Univ Coll Transportat Engn Shanghai Peoples R China

ISBN: (纸本)9780784483565

There are a lot of Automotive Vehicle Identification (AVI) devices in urban traffic environment in some Chinese cities. Vehicles will leave a series of timestep-location records when travelling through the road network, which is a valuable data source for macroscopic traffic supply-demand analysis. A method using the AVI data based on the Arcgis platform to reconstruct vehicles' trajectories is proposed, which can obtain nearly full sample of vehicles' reconstructed trajectories in the road network with devices. The macroscopic features of traffic demand are explored based on the reconstructed trajectory data. Through visual analysis, the distribution of traffic OD demand, traffic volume and spatial-temporal changes are obtained. Additionally, the relationship between traffic supply and demand is evaluated from the macroscopic view.

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

Automatic Detection of Waterbodies from Satellite Images Using DeepLabV3+ 1

引用

9th International conference on Mining Intelligence and Knowledge exploration, MIKE 2023

作者： Kadry, Seifedine Al-Betar, Mohammed Azmi Yassine, Sahar Mohan, Ramya Arunmozhi, Rama Rajinikanth, Venkatesan Department of Applied Data Science Noroff University College Kristiansand4612 Norway College of Engineering and Information Technology Ajman University Ajman United Arab Emirates Department of Computer Science and Engineering Division of Research and Innovation Saveetha School of Engineering SIMATS Chennai602105 India

ISBN: (数字)9783031440847

ISBN: (纸本)9783031440830

In recent times, it has become increasingly popular to examine a wide range of environmental and earth data using remote sensing schemes supported by satellite images (SI). Due to the complex nature of spatial, spectral, and temporal characteristics of SI, it is quite difficult for automatic analysis to be performed as it requires specially designed algorithms. As part of the research proposal, an enhanced deep-learning scheme will be implemented in order to extract the waterbodies from the chosen SIs. The phases involved in this scheme includes;(i) the collection and resizing of images, (ii) Shannon's Entropy preprocessing, (iii) DeepLabV3+ extraction of waterbodies, (iv) the comparison of extracted sections with ground truth (GT) and the calculation of performance metrics, and (v) validation of the effectiveness of the implemented scheme. In the proposed work, the proposed multi-thresholding approach is combined with DeepLabV3+ in order to get the waterbodies to be extracted from the chosen test images. DeepLabV3 is demonstrated to have excellent segmentation performance when it is compared to UNet and SegNet. The experimental results of this scheme indicate that DeepLabV3+ results in higher Jaccard value (>89%), Dice value (>93%), and segmentation accuracy value (>97%) when compared to other pretrained segmentation schemes. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Remote sensing

来源：评论

学校读者我要写书评

暂无评论

exploration and Implementation of data Processing Methods in Admission and Enrollment for Adult Higher Education Institutions

Exploration and Implementation of Data Processing Methods in...

引用

IEEE International conference on Big data analysis (ICBDA)

作者： Xuping Lin Bin Wang Yuejiang Sun Lei Li Qingdao Preschool Education College Qingdao China Ocean University of China Qingdao China

ISBN: (数字)9798350352962

ISBN: (纸本)9798350352979

data processing, as an intermediate link in adult college entrance examination enrollment and admission, establishes a bridge between the enrollment and admission institution subsystem and the data output window. However, the data processing work is relatively cumbersome. This article combines the characteristics of the college subsystem of the adult college entrance examination enrollment online admission software, and proposes the use of three commonly used office software and processing methods such as visual FoxPro, ACCESS, and EXCEL to achieve enrollment data processing work, all of which can effectively complete enrollment data processing. Firstly, it is necessary to clarify the basic meaning of the admission data table, the basic structure of the data table, and the data relationships between the tables. When using visual FoxPro software to process data, execute the command line through the VFP command window, write SQL statements based on the correspondence between tables, and encapsulate the VFP command line into a visualization program to achieve data processing. When processing admission data in Access 2016, after establishing relationships between tables, creating queries and outputting corresponding field information, the data processing operation can be completed. When using Excel to process data, it is necessary to first convert the admission DBF file into an Excel file, use functions and formulas to match the corresponding fields, delete excess fields, and replace function references with fixed values to complete data processing. The three methods of processing enrollment and admission data can all complete the post-processing work of the data, but each has its own advantages and disadvantages. VFP does not require data conversion in the early stage of data processing, which is efficient, but mastering and flexibly using commands can be challenging; During the data processing of ACCESS, there is no need to write programs or use formula functions, but

关键词： Bridges visualization data conversion Education data visualization Big data data processing

来源：评论

学校读者我要写书评

暂无评论

visual exploration and Planning of the Automated Material Handling System for Smart Factory in the Immersive Environment

Visual Exploration and Planning of the Automated Material Ha...

引用

Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW), IEEE conference on

作者： Yifei Zhang Yougao Li Xiangyang Xue Jianfeng Feng Siming Chen Fudan University Shanghai Jiao Tong University Ji Hua Laboratory School of Data Science Fudan University

The combination of the digital twin and the smart factory has been a popular research direction in recent years. Automated Material Handling System (AMHS) is an important scene of smart factory, while most traditional simulation AMHS analysis tools only provide results or simple 2D displays. We introduce a visual exploration system that combines virtual reality (VR) with AMHS to allow users to observe and analyze the performance of the system in real-time, and we provide a series of egocentric interactions to help users analyze and interfere with the performance of the system. The interactions include ray interaction, task scheduling interaction, and path planning interaction, We demonstrate how to explore AMHS using visualization and interaction in our system through case studies.

关键词： visualization Solid modeling Three-dimensional displays Two dimensional displays Materials handling Virtual reality User interfaces

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：