检索结果-内蒙古大学图书馆

6th International conference on Big data Cloud and Internet of Things, BDIoT 2022

作者： Mosaif, Afaf Rakrak, Said Faculty of Science and Technology Cadi Ayyad University Marrakesh Morocco

ISBN: (纸本)9783031283864

As wireless sensors and computer vision have advanced, visual Internet of Things (v-IoT) has emerged as a form of IoT that can offer different levels of intelligence based on its application and algorithms. It is important to note, however, that v-IoT nodes collect a substantial amount of visual data that must be transmitted to the network for further analysis. The purpose of our paper is to present a new architecture that will reduce the information flow from the v-IoT nodes to the base station and balance the traffic load on the network. Our architecture is based on the Message Queue Telemetry Transport (MQTT) protocol, and it distributes the data processing across the network levels taking into account the limited resources of the v-IoT nodes. To evaluate our architecture, we built a v-IoT node prototype using a Raspberry Pi board and then used it as part of an experiment to recognize and track faces. The results of the prototype implementation indicate that our proposal is effective. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

v2X based vehicle Environment Perception and Occupancy analysis for Dynamic Pedestrian Behaviour

V2X based Vehicle Environment Perception and Occupancy Analy...

引用

European Control conference (ECC)

作者： Tendulkar, Swaraj Khandelwal, Mayank Yogesh Schrodel, Frank Schmalkalden Univ Appl Sci Fac Mech Engn D-98574 Schmalkalden Germany

ISBN: (纸本)9798331540920;9783907144107

This research paper addresses the topics of the environment perception domain to realise the solution for connected autonomous mobility by using simulation softwares and real life sensors in tandem. The camera and lidar sensor simulation is performed for a specific scenario arising in the environment and the simulation results, sensor readings and the binary occupancy grids received from sensor simulations are analysed. The RealSense Depth Camera is used to perform visual mapping of the static environment for static obstacle perception and map generation whereas the SICK 2D lidar is used to create a dynamic probabilistic occupancy grid for perceiving the dynamic obstacles in the environment. The results from the sensors in simulation and real life are compared, analysed and validated. The dynamic probabilistic occupancy is used as a foundation to further develop an occupancy prediction model which predicts the future occupancy of any dynamic obstacle based on its velocity and direction of motion. Furthermore, a framework is conceptualised for the vehicle to Everything (v2X) communication system which includes the identification and determination of the essential communication infrastructure, type of data, recipients, rate of data transfer and ROS communication nodes.

关键词： data transfer

来源：评论

学校读者我要写书评

暂无评论

MeDaX Prototype v0.2 15

MeDaX Prototype v0.2

引用

15th International conference on Semantic Web Applications and Tools for Health Care and Life Sciences, SWAT4HCLS 2024

作者： Mazein, Ilya Braun, Sarah Gebhardt, Tom Henkel, Ron Michaelis, Lea Waltemath, Dagmar Wodke, Judith A.H. Medical Informatics Department Institute of Community Medicine University Medicine Greifswald Germany Core Unit Data Integration Center University Medicine Greifswald Germany

The MeDaX project aims to develop and implement concepts and tools for bioMedical data exploration using graph technologies. Here, we present v0.2 of our prototype, representing FHIR formatted clinical data in a graph format. We build on the pre-existing CyFHIR tool for generic conversion, optimise the resulting graph structure to lessen complexity, and incorporate the BioCypher framework, integrating the clinical data with ontology information. This makes the data more accessible and convenient for querying, information retrieval and analysis. © 2024 Copyright for this paper by its authors.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Rich Screen Reader Experiences for Accessible data visualization

引用

COMPUTER GRAPHICS FORUM 2022年第3期41卷 15-27页

作者： Zong, Jonathan Lee, Crystal Lundgard, Alan Jang, JiWoong Hajas, Daniel Satyanarayan, Arvind MIT Cambridge MA 02139 USA Carnegie Mellon Univ Pittsburgh PA 15213 USA UCL London England

Current web accessibility guidelines ask visualization designers to support screen readers via basic non-visual alternatives like textual descriptions and access to raw data tables. But charts do more than summarize data or reproduce tables;they afford interactive data exploration at varying levels of granularity-from fine-grained datum-by-datum reading to skimming and surfacing high-level trends. In response to the lack of comparable non-visual affordances, we present a set of rich screen reader experiences for accessible data visualization and exploration. Through an iterative co-design process, we identify three key design dimensions for expressive screen reader accessibility: structure, or how chart entities should be organized for a screen reader to traverse;navigation, or the structural, spatial, and targeted operations a user might perform to step through the structure;and, description, or the semantic content, composition, and verbosity of the screen reader's narration. We operationalize these dimensions to prototype screen-reader-accessible visualizations that cover a diverse range of chart types and combinations of our design dimensions. We evaluate a subset of these prototypes in a mixed-methods study with 13 blind and visually impaired readers. Our findings demonstrate that these designs help users conceptualize data spatially, selectively attend to data of interest at different levels of granularity, and experience control and agency over their data analysis process. An accessible HTML version of this paper is available at: http://***/pubs/rich-screen-reader-vis-experiences.

关键词： CCS Concepts • Human-centered computing → visualization design and evaluation methods Accessibility design and evaluation methods

来源：评论

学校读者我要写书评

暂无评论

Reinforced Approximate Exploratory data analysis 37

Reinforced Approximate Exploratory Data Analysis

引用

37th AAAI conference on Artificial Intelligence (AAAI) / 35th conference on Innovative Applications of Artificial Intelligence / 13th Symposium on Educational Advances in Artificial Intelligence

作者： Garg, Shaddy Mitra, Subrata Yu, Tong Gadhia, Yash Kashettiwar, Arjun Adobe Res Bangalore India Indian Inst Technol Bombay India

ISBN: (纸本)9781577358800

Exploratory data analytics (EDA) is a sequential decision making process where analysts choose subsequent queries that might lead to some interesting insights based on the previous queries and corresponding results. data processing systems often execute the queries on samples to produce results with low latency. Different downsampling strategy preserves different statistics of the data and have different magnitude of latency reductions. The optimum choice of sampling strategy often depends on the particular context of the analysis flow and the hidden intent of the analyst. In this paper, we are the first to consider the impact of sampling in interactive data exploration settings as they introduce approximation errors. We propose a Deep Reinforcement Learning (DRL) based framework which can optimize the sample selection in order to keep the analysis and insight generation flow intact. Evaluations with 3 real datasets show that our technique can preserve the original insight generation flow while improving the interaction latency, compared to baseline methods.

关键词： data Analytics

来源：评论

学校读者我要写书评

暂无评论

Exploring Deep Learning-Based visual Localization Techniques 3

Exploring Deep Learning-Based Visual Localization Techniques

引用

2023 IEEE 3rd International conference on data Science and Computer Application, ICDSCA 2023

作者： Yu, Zhuoyi Maynooth University International Engineering College Fuzhou University Fuzhou China

ISBN: (纸本)9798350341546

This comprehensive review paper explores the state of the art in visual localization and navigation, drawing on the principles and methodologies of three significant deep learning networks: visual Localization Network (vLocNet), Deep Fusion Network (DFNet), and Hybrid Frontend Network (HFNet). Each of these networks demonstrates the application of deep learning to spatial awareness and navigation tasks in unique and significant ways. Rather than an exhaustive dissection of these networks, the paper provides an encompassing overview, illuminating their underlying principles, architectural design, and their relative performance within the field. Additionally, the paper delves into the practical implications of these networks, examining their applications in diverse real-world scenarios. It underlines this examination with a comprehensive analysis of existing literature and experimental results, intended to impart a profound understanding of these networks' strengths, limitations, and potential application areas. Ultimately, this review aims to present a valuable compass to researchers navigating the evolving landscape of advancements in visual localization and navigation, thereby fostering enriched understanding and facilitating future exploration and development in this compelling field. © 2023 IEEE.

关键词： Computer vision Deep learning Object recognition Robotics visual localization Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Disinformation analysis and Tracking Dashboard

Disinformation Analysis and Tracking Dashboard

引用

International conference on Military Communications and Information Systems (ICMCIS)

作者： Mandravickait, Justina Songailait, Milita Kankeviciute, Egle volcok, Anton Krilavicius, Tomas Vytautas Magnus Univ Fac Informat CARD Kaunas Lithuania Lingo Data CARD Vilnius Lithuania

ISBN: (纸本)9798350343854

The importance of disinformation identification and tracking in the information age is not questionable. War in Ukraine, information attacks in Baltic states, and a number of other disinformation attacks worldwide show that it is becoming a conventional tool in information space. In this paper, we present a disinformation analysis and tracking dashboard. It has 3 main components: Disinformation Analyzer, Match disinformation cases and Model Accuracy. The first component consists of a fined-tuned RoBERTa model for classifying textual input into fake and neutral. The second component contains semantic matching functionality for checking the semantic similarity of input text to the set of known disinformation cases. The third component includes the confusion matrix and model accuracy information. All 3 components have been combined into visual analytics platform for easy inspection and exploration of potential and known disinformation cases. The majority of the work was done during TIDE Hackathon 2023 as a part of the Disinformation Analyzer Challenge.

关键词： fake news disinformation deep learning BERT visual analytics

来源：评论

学校读者我要写书评

暂无评论

Brain Stroke Prediction Using visual Geometry Group Model 13

Brain Stroke Prediction Using Visual Geometry Group Model

引用

13th International conference on data Science, Technology and Applications, data 2024

作者： Narayanan, v.v.L. Reddy, A. venkatesh, v. Tutun, S. Norouzzadeh, P. Snir, E. Mahmoud, S. Rahmani, B. Saint Louis University Computer Science Department St. LouisMO United States Washington University in Saint Louis Olin Business School St. LouisMO United States Saint Louis University Medical School St. LouisMO United States

ISBN: (纸本)9789897587078

Stroke has become the leading cause of high mortality and disability rates in the modern era. Early detection and prediction of stroke can significantly improve patient outcomes. In this study, we propose a deep learning approach using the visual Geometry Group (vGG-16) model. vGG-16 is a type of Convolutional Neural Network (CNN) which is one of the best computer vision models to date to predict the occurrence of a stroke in the brain. vGG-16 is a type of CNN that is one of the best computer vision models to date. We used a dataset consisting of Magnetic resonance imaging (MRI) images of patients with and without stroke. The vGG-16 model was pre-trained on the ImageNet dataset and fine-tuned on our dataset to predict the occurrence of a stroke. Our experimental results demonstrated that the proposed approach achieves high accuracy and can effectively predict stroke occurrence. We have also conducted an extensive analysis of the model's performance and provided insights into important features used by the model to predict stroke occurrence. The proposed approach has the potential to be used in clinical settings to aid in the early detection and prevention of stroke. © 2024 by SCITEPRESS – Science and Technology Publications, Lda.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Minddata for Enhanced Entertainment: Building a Comprehensive EEG dataset of Emotional Responses to Audio-visual Stimuli 3rd

MindData for Enhanced Entertainment: Building a Comprehensiv...

引用

3rd International conference on Applied Intelligence and Informatics (AII)

作者： Thejaswini, M. S. Kumar, G. Hemantha Aradhya, v. N. Manjunath Narendra, R. Suresha, M. Guru, D. S. Univ Mysore Dept Studies Comp Sci Mysuru 570006 Karnataka India JSS Sci & Technol Univ Dept Comp Applicat Mysuru 570006 Karnataka India Kuvempu Univ Dept Comp Sci Shivamogga 577451 India

ISBN: (纸本)9783031686382;9783031686399

We present data from Electroencephalograph signals that can be used to analyse audio-visual stimuli for emotion recognition. A successful attempt towards recording of EEG signals of 46 subjects is made using portable Biopic 2 channel EEG device and a self-rating scale. Two different kinds of experiments were exposed to subjects, included with commercial advertisements and musical clips from South-Indian-Kannada language, that recorded a range of emotional reactions (Relaxed, Sad, Scary, Funny, Enjoyment). In our data repository, Labeled preprocessed EEG data is stored in CSv format. Our goal in this endeavor is to establish an emotion dataset based on entertainment, providing an efficient approach for collecting brain signal data. Finally, in order to evaluate the suitability of our dataset, we ran statistical implementation like frequency time analysis on the data that had been recorded. With this analysis, we further categorized the EEG signals into segments linked to both positive and negative emotions across the two experiments. Since the data will be made publicly accessible, interested can use it for research/educative purpose with suitable acknowledgements.

关键词： Emotional Awareness BCI (Brain Computer Interfacing) Electroencephalography Social Entertainment

来源：评论

学校读者我要写书评

暂无评论

Enhanced Real-Time Abnormal Event Detection in video Surveillance for Safety and Security 3

Enhanced Real-Time Abnormal Event Detection in Video Surveil...

引用

3rd International conference on Smart Technologies and Systems for Next Generation Computing, ICSTSN 2024

作者： Muralidharan, C. Arulalan, v. Kishore Anthuvan Sahayaraj, K. Sheoran, Nishant Department of Computing Technologies SRM Institute of Science and Technology Chengalpattu District Tamil Nadu Kattankulathur603203 India

ISBN: (纸本)9798350391565

Surveillance technology is one of the important and critical tools that is used for maintaining security and safety across various situations such as public places, transportation hubs, industrial facilities, and especially smart city infrastructure. However, the sheer volume of visual data generated poses a significant challenge in monitoring and analyzing this information effectively. In this rapidly evolving landscape of surveillance technology, the need for effective abnormal event detection. This paper presents a comprehensive exploration and implementation of abnormal event detection techniques in real-time video monitoring scenarios. Leveraging recent advancements in deep learning and machine learning methodologies, a novel architecture comprising spatial and temporal encoders-decoders, alongside a binary classifier, is proposed. The architecture aims to discern abnormal events from normal activities in surveillance videos by encoding spatial and temporal features and classifying frames as normal or abnormal and cross-entropy loss. The study conducts a mathematical analysis of the proposed framework and discusses its implementation using real-time video data. Furthermore, the paper critically examines related works, emphasizing recent advancements in deep learning-based approaches, unsupervised learning, attention mechanisms, and multimodal fusion techniques in abnormal event detection. The conclusions drawn from this research highlight the potential and challenges in deploying such systems for enhanced security and safety across diverse domains. © 2024 IEEE.

关键词： Unsupervised learning

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：