检索结果-内蒙古大学图书馆

2nd IEEE International conference on Electrical, Automation and Computer Engineering, ICEACE 2024

作者： Yuying, Cai Tongxi, Lin Guangzhou Huashang Vocational College Guangzhou China

ISBN: (纸本)9798350368208

This paper discusses the method of short video content recognition and personalized recommendation by using deep learning technology. Different from traditional behavior recognition techniques, deep learning shows its strong ability in feature extraction, which can automatically learn adaptive and highly distinguishable features. First of all, considering the dual properties of time and space of video content, this paper adopts deep learning model to extract spatial and temporal features of video respectively, and combines them to form spatiotemporal fusion features. A video behavior recognition algorithm based on spatiotemporal convolutional network is designed to process video behavior recognition as the acquisition of spatial and temporal information of video. Based on the two-flow convolutional network, the effects of optical flow image and salience image on behavior recognition are compared and analyzed. On this basis, the attention mechanism inspired by the human visual system is introduced, and the space-time fusion model based on the attention mechanism is constructed. By assigning higher weights to key frames in video clips, the model focuses more on the important parts of the video, thus reducing the impact of redundant information on behavior analysis. Finally, the reliability of the model is verified on a real world data set. © 2024 IEEE.

关键词： Video analysis

来源：评论

学校读者我要写书评

暂无评论

A Multimodal Off- Road Terrain Classification Benchmark for Extraterrestrial Traversability analysis 12

A Multimodal Off- Road Terrain Classification Benchmark for ...

引用

12th International conference on Cyber-Enabled Distributed Computing and Knowledge Discovery (CyberC)

作者： Huang, Huang Yang, Yi Tang, Liang Zhang, Zhang Liu, Nailong Li, Mou Wang, Liang Beijing Inst Control Engn Beijing Peoples R China Chinese Acad Sci Inst Automat Beijing Peoples R China Univ Chinese Acad Sci Beijing Peoples R China

ISBN: (纸本)9798350331547

A rover in extraterrestrial exploration works in challenging environment featured by primitive landforms and hidden dangerous areas. Due to the far distance from the rover to Earth, it is one of the most crucial capabilities that the rover can recognize and model the terrain properties efficiently and autonomously. In this paper, we present a Multimodal Off-road Terrain Classification (MOTC) dataset which is collected by a four-wheeled rover equipped with ego-centric visual cameras and inertial measurement unit (IMU). The dataset is generated from a boulder-strewn mock- up of the real Mars at the Intelligent Autonomous System Laboratory in Beijing Institute of Control Engineering. 24,982 images and corresponding sensor sequences are collected and annotated into 3 kinds of surface materials and 3 kinds of scene geometries. Based on the MOTC dataset, a baseline model with a multimodal fusion architecture is proposed for terrain classification. The experiment shows that the features extracted from visual images and from IMU complement each other to achieve improvements of terrain classification accuracy of the challenging extraterrestrial surface.

关键词： terrain classification sensor fusion transformer extraterrestrial exploration

来源：评论

学校读者我要写书评

暂无评论

Multimodal data Fusion for Automatic Detection of Alzheimer's Disease 1

引用

13th International conference on Digital Human Modeling and Applications in Health, Safety, Ergonomics and Risk Management (DHM) Held as Part of the 24th International conference on Human-Computer Interaction (HCii)

作者： Krstev, Ivan Pavikjevikj, Milan Toshevska, Martina Gievska, Sonja Ss Cyril & Methodius Univ Fac Comp Sci & Engn Skopje North Macedonia

ISBN: (数字)9783031060182

ISBN: (纸本)9783031060182;9783031060175

The viability of multimodal fusion of linguistic and acoustic biomarkers in speech to help in identifying a person with probable Alzheimer's dementia symptoms have been explored in this research. For capturing the effect of dementia on person's language and verbal abilities, a novel way of disease detection was explored based on visual analysis of images of spectrogram extracted from patient's interview recordings. We put forward three fusion methods, which allow the major advancements in representation learning to be utilized. The objective of the empirical study and ensuing discussion presented in this paper was threefold: 1) to examine the potential of state-of-the-art transformer-based architectures and transfer learning to assist the disease diagnosis, 2) to map the problem of acoustic analysis into the realm of image processing, by transforming spectrograms into images and employing pretrained deep neural networks, such as ResNet to extract visual patterns, and 3) to investigate the sound interplay of multi-modal biomarkers of Alzheimer's dementia when fusing the learned representations in different modalities. We present the results of independent evaluations of the unimodal methods against which the fusion methods have been compared to.

关键词： Alzheimer's dementia Audio Text Multimodal fusion Machine learning Deep learning Transformers

来源：评论

学校读者我要写书评

暂无评论

Breast Cancer Biomarker analysis Using Gene Co-expression Networks 11th

Breast Cancer Biomarker Analysis Using Gene Co-expression Ne...

引用

11th International Work-conference on Bioinformatics and Biomedical Engineering (IWBBIO)

作者： Lopez-Fernandez, Aurelio Gallejones-Eskubi, Janire Saz-Navarro, Dulcenombre M. Gomez-Vela, Francisco A. Univ Pablo de Olavide Intelligent Data Anal Grp DATAi Ctra Utrera Km 1 Seville 41013 Spain Galdakano Usansolo Univ Hosp Hlth Syst Res Inst Biosistemak Galdakano 48960 Spain

ISBN: (纸本)9783031646355;9783031646362

Gene co-expression networks have emerged as a robust tool for conducting comprehensive analyses of gene expression patterns. These networks, constructed through inference algorithms, facilitate the exploration of various biological processes and enable the identification of novel biomarkers from which to explore new lines of disease research. This work found that breast cancer stromal cells are strongly dysregulated in genes related to modifications in cellular structures that hold stromal tissue cells together, inflammatory responses, and molecules implicated in immune system regulation. Finally, ANAPC11, LRFN5, COL8A2, TEX11, DOCK9, CPLX1, LONP2, and LAT2 biomarkers were suggested in the context of stromal breast tumors.

关键词： Gene co-expression network Bioinformatics Biomarkers Breast cancer

来源：评论

学校读者我要写书评

暂无评论

Confides: A visual Analytics Solution for Automated Speech Recognition analysis and exploration

Confides: A Visual Analytics Solution for Automated Speech R...

引用

International conference on visualisation, VIS

作者： Sunwoo Ha Chaehun Lim R. Jordan Crouser Alvitta Ottley

ISBN: (数字)9798350354850

ISBN: (纸本)9798350354867

Confidence scores of automatic speech recognition (ASR) outputs are often inadequately communicated, preventing its seamless integration into analytical workflows. In this paper, we introduce Confides, a visual analytic system developed in collaboration with intelligence analysts to address this issue. Confides aims to aid exploration and post-AI-transcription editing by visually representing the confidence associated with the transcription. We demonstrate how our tool can assist intelligence analysts who use ASR outputs in their analytical and exploratory tasks and how it can help mitigate misinterpretation of crucial information. We also discuss opportunities for improving textual data cleaning and model transparency for human-machine collaboration.

关键词： Analytical models Uncertainty visual analytics Human-machine systems Collaboration data visualization Cleaning data models Speech to text Automatic speech recognition

来源：评论

学校读者我要写书评

暂无评论

An exploration of structural brain differences in Autism Spectrum Disorders: A multi-parcellation and multi-age analysis

引用

BIOMEDICAL SIGNAL PROCESSING AND CONTROL 2024年 92卷

作者： Gonzalez, Jully Munera, Nicolas Alvarez-Jimenez, Charlems Velasco, Nelson Romero, Eduardo Univ Nacl Colombia Bogota 111321 Colombia Univ Mil Nueva Granada Bogota 111071 Colombia

Autism Spectrum Disorders (ASD) assessment relies on clinical rating scales to measure related social and behavioral changes, a subjective process which is prone to misdiagnosis. ASD heterogeneity of social and cognitive functioning has been associated with underlying neuro-anatomical alterations. Automatic medical imaging analyses have made possible quantification of these anatomical changes, yet these complex morphological patterns have been partially characterized by simple absolute scalar values. This paper presents a much more complete exploration of the global-local differences between ASD and control subjects using a multiscale descriptor that captures sub -visual spatial patterns. This analysis consists in three main steps: a preprocessing for segmenting the brain into a particular anatomical parcellation, a region-based characterization for capturing global-local folding/shape patterns, and a statistical analysis for quantifying differences between ASD and control individuals. A large data cohort (n = 1245) consisting in three different age groups, was used to perform this exploration. The analysis was carried out in the entire set of cortical and subcortical brain regions: (i) using two different brain parcellations, and (ii) separately for each age group. This characterization revealed statistically significant differences (p < 0.05) in the ASD group compared to control individuals using two brain parcellations. These results demonstrate the representation is able to identify folding and shape differences for a particular age range in both parcellations, supporting the generalizability of these findings.

关键词： Autism Spectrum Disorders Magnetic resonance imaging Texture descriptor Frequency space Statistical analysis

来源：评论

学校读者我要写书评

暂无评论

visual analysis of Spinels with General Line Coordinates

Visual Analysis of Spinels with General Line Coordinates

引用

International conference on Information visualisation (IV)

作者： Leandro Luque María Luján Ganuza Ernesto Bjerg Boris Kovalerchuk Department of Computer Science and Engineering (UNS) Inst. for Computer Science and Eng. (CONICET-UNS) Bahia Blanca Argentina Department of Geology (UNS) INGEOSUR (UNS-CONICET) Bahia Blanca Argentina Department of Computer Science Central Washington University Ellensburg United States

ISBN: (数字)9798350380163

ISBN: (纸本)9798350380170

In the geological context, the analysis of multidimensional data is a very common task and requires visualization techniques for exploration. General Line Coordinates (GLC) is a technique especially intended for lossless representation among the various techniques available for the visualization of multidimensional data. In this study, the application of GLC for pattern analysis and identification in mineral datasets is investigated. Furthermore, we develop a web-based tool to explore the possibility of employing GLC to leverage these approaches to derive visual discovery rules for pattern recognition.

关键词： visualization data visualization Pattern recognition Minerals Pattern analysis

来源：评论

学校读者我要写书评

暂无评论

UMAP 2023 - Adjunct Proceedings of the 31st ACM conference on User Modeling, Adaptation and Personalization

UMAP 2023 - Adjunct Proceedings of the 31st ACM Conference o...

引用

31st ACM conference on User Modeling, Adaptation and Personalization, UMAP 2023

ISBN: (纸本)9781450398916

The proceedings contain 71 papers. The topics discussed include: a multi-factorial analysis of polarization on social media;addressing popularity bias in recommender systems: an exploration of self-supervised learning models;an out-of-the-box application for reproducible graph collaborative filtering extending the Elliot framework;chai wallpaper: a mindfulness-based persuasive intervention for absent-minded smartphone usage;covering covers: characterization of visual elements regarding sleeves;cyclops: looking beyond the single perspective in information access systems;eudaimonic and hedonic qualities as predictors of music videos’ relevance to users: a human-centric study;expected and experienced utility of points of interest in tourism recommender systems;how can we model climbers’ future visits from their past records?;and personalized learning systems for computer science students: analyzing and predicting learning behaviors using programming error data.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Automated Assessment of Historic Tiles Degradation by Deep Learning Approach and HBIM Implementation: Application Cases in Seville 5th

Automated Assessment of Historic Tiles Degradation by Deep L...

引用

5th International conference on Protection of Historical Constructions-PROHITECH

作者： Giannuzzi, Valeria Nieto-Julian, Enrique Marin-Garcia, David Polytech Bari I-70126 Bari Italy Univ Seville Dept Expres Graf & Ingn Edificac Grp TEP97 Innovac Tecnol Sistemas Modelado Diag E Seville 41012 Spain

ISBN: (纸本)9783031873140;9783031873126;9783031873119

Recent advances in digital technologies and automated analysis techniques applied to historic buildings have shown significant benefits in efficiently collecting and interpreting data for conservation activities. Close-range photogrammetry has become a valuable tool for detecting damage in historic buildings due to its non-invasive nature, which allows for the identification of issues while preserving the building's structure. In particular, detecting and measuring damage on historic tiled surfaces is essential for the maintenance and protection of these buildings. However, current visual inspection methods are time-consuming and labor-intensive. This study proposes an automated inspection system that uses a trained and validated convolutional neural network for classifying degradation phenomena based on images acquired through photogrammetric surveys. The detection, segmentation, and quantification strategy for degradation phenomena relies on deep learning techniques to automatically detect and measure damage affecting historic tiles. Additionally, the Historic Building Information Model (HBIM) serves as an information repository by including semantic and graphical components for comprehensive documentation management in cultural heritage conservation and restoration field. The results highlight the potential of these techniques for detecting heritage damage, supporting decision-makers in planning recovery and maintenance interventions.

关键词： Historic Tiles Decay Degradation Assessment HBIM Cultural Heritage Deep-Learning

来源：评论

学校读者我要写书评

暂无评论

Pioneering Pain Relief: Exploring Neuromodulation with Electrical Impulses and Mechanical Techniques for Effective Pain Management 6

Pioneering Pain Relief: Exploring Neuromodulation with Elect...

引用

6th International conference on Intelligent Systems and Computer Vision, ISCV 2024

作者： Radouane, Asmaa Touil, Mohamed Kadil, Youness Rahmoune, Imane Filali, Houda Hassan II University Laboratory of Pharmacology and Toxicology Faculty of Medicine and Pharmacy of Casablanca Casablanca Morocco Hassan II University EEIS Laboratory Enset Mohammadia Casablanca Morocco

ISBN: (纸本)9798350350180

According to a World Health Organization report, chronic pain is becoming a widespread issue in the larger context of global health, impacting about 20% of the world's population. This continuous problem includes several types of chronic pain that significantly affect people's everyday lives and overall health. Neuromodulation - the use of neuromodulators, electrical and mechanical stimulation - is at the forefront of innovative pain management strategies. Here we examine recent advances in the effects of neuromodulation on three different types of pain, such as dental neuralgia and orofacial pain, osteoarthritis, which is considered to be one of the most painful sensations, and the pain associated with Parkinson's disease. To carry out this study, we undertook an in-depth exploration of the relevant scientific literature. Our approach consisted of carefully reading and understanding numerous articles from major databases. Each article was carefully read through to ensure that the methodology, findings, and consequences were understood. The amalgamation of this data has facilitated the cultivation of a refined comprehension of the present status of knowledge in this particular field, establishing the fundamental groundwork for subsequent investigations in this domain. Our in-depth analysis of the effect of electrical stimulation through various neuromodulation methods reveals compelling insights into advances in the field of pain management. Through this review, we present the results of different methods, highlighting their efficacy and contributions to chronic pain relief, showing their ability to modulate in a complex way the neural circuits associated with pain processing. This review highlights the paradigm shifts in pain treatment facilitated by neuromodulation. The controlled application of electrical impulses offers a promising route to personalized and effective relief for people suffering from chronic pain. © 2024 IEEE.

关键词： Disease control

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：