检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Xu, Meiyan Chen, Qingqing Chen, Duo Ding, Yi Wang, Jingyuan Gu, Peipei Pan, Yijie Huang, Deshuang Guo, Jiayang Zhang, Xun Department of Computer Science The Institute of Human Factors Engineering Minnan Normal University Zhangzhou363000 China School of Artificial Intelligence and Information Technology Nanjing University of Chinese Medicine Nanjing210023 China College of Computing and Data Science Nanyang Technological University Singapore School of Digital Media and Design Arts Beijing University of Posts and Telecommunications Beijing100088 China College of Software Engineering Zhengzhou University of Light Industry Zhengzhou450000 China Department of Computer Science and Technology Tsinghua University Beijing100084 China Eastern Institute for Advanced Study Eastern Institute of Technology Ningbo315200 China Ningbo Institute of Digital Twin Eastern Institute of Technology Ningbo315200 China National Institute for Data Science in Health and Medicine Xiamen University Xiamen361005 China

EEG-based fatigue monitoring can effectively reduce the incidence of related traffic accidents. In the past decade, with the advancement of deep learning, convolutional neural networks (CNN) have been increasingly used for EEG signal processing. However, due to the data’s non-Euclidean characteristics, existing CNNs may lose important spatial information from EEG, specifically channel correlation. Thus, we propose the node-holistic graph convolutional network (NHGNet), a model that uses graphic convolution to dynamically learn each channel’s features. With exact fit attention optimization, the network captures inter-channel correlations through a trainable adjacency matrix. The interpretability is enhanced by revealing critical areas of brain activity and their interrelations in various mental states. In validations on two public datasets, NHGNet outperforms the SOTAs. Specifically, in the intra-subject, NHGNet improved detection accuracy by at least 2.34% and 3.42%, and in the inter-subjects, it improved by at least 2.09% and 15.06%. Visualization research on the model revealed that the central parietal area plays an important role in detecting fatigue levels, whereas the frontal and temporal lobes are essential for maintaining vigilance. Copyright © 2025, The Authors. All rights reserved.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Lessons Learnt from designing a Smart Clothing Telehealth System for Hospital Use 32

Lessons Learnt from Designing a Smart Clothing Telehealth Sy...

引用

32nd Australian Computer-Human Interaction Conference, OzCHI 2020

作者： Aggarwal, Deepti Hoang, Thuong Ploderer, Bernd Vetere, Frank Khot, Rohit Ashok Bradford, Mark Hafp Research Lab Rmit University Australia School of Information Technology Deakin University Australia School of Electrical Engineering and Computer Science Queensland University of Technology Australia Interaction Design Lab School of Computing and Information Systems The University of Melbourne Australia Dept. of Anaesthesia and Pain Management Royal Children's Hospital Australia

ISBN: (纸本)9781450389754

In this paper, we describe the design journey of a smart clothing system, SoPhy from the research laboratory to finally being evaluated in the hospital setting. SoPhy is a smart socks-based system, designed to make physiotherapy video consultations effective for assessing lower limb issues. SoPhy is the result of a 3-year journey of development, study and refinement of a research prototype done in collaboration with a physiotherapist. Drawing on this journey, we present seven lessons that emphasize on the importance of fostering strong collaborations with clinicians to move beyond laboratory studies and reach the target health setting. We provide contextual narratives on how we designed a comfortable smart clothing for patients;how we created an intuitive mapping of sensor data for clinicians;how we integrated hospital practice in the system design, and how we managed the ethics clearance for the field evaluation. We hope that these lessons are useful for HCI and health researchers who aim to innovate the field of health but feel restricted with the little knowledge of design and electronics. © 2020 ACM.

关键词： Research laboratories

来源：评论

学校读者我要写书评

暂无评论

Location embedding based pairwise distance learning for fine-grained diagnosis of urinary stones

arXiv

引用

arXiv 2024年

作者： Jin, Qiangguo Huang, Jiapeng Sun, Changming Cui, Hui Xuan, Ping Su, Ran Wei, Leyi Wu, Yu-Jie Wu, Chia-An Duh, Henry B.L. Lu, Yueh-Hsun School of Software Northwestern Polytechnical University Shaanxi China Yangtze River Delta Research Institute of NPU Suzhou China CSIRO Data61 Sydney Australia Department of Computer Science and Information Technology La Trobe University Melbourne Australia School of Engineering Shantou University Guangdong China College of Intelligence and Computing Tianjin University Tianjin China School of Information Xiamen University Xiamen China AIDD Faculty of Applied Science Macao Polytechnic University China Department of Radiology Shuang-Ho Hospital Taipei Medical University Taipei Taiwan Master of Public Health Program National Yang Ming Chiao Tung University Taipei Taiwan School of Design The Hong Kong Polytechnic University Hong Kong Department of Radiology School of Medicine College of Medicine Taipei Medical University Taipei Taiwan

The precise diagnosis of urinary stones is crucial for devising effective treatment strategies. The diagnostic process, however, is often complicated by the low contrast between stones and surrounding tissues, as well as the variability in stone locations across different patients. To address this issue, we propose a novel location embedding based pairwise distance learning network (LEPD-Net) that leverages low-dose abdominal X-ray imaging combined with location information for the fine-grained diagnosis of urinary stones. LEPD-Net enhances the representation of stone-related features through context-aware region enhancement, incorporates critical location knowledge via stone location embedding, and achieves recognition of fine-grained objects with our innovative fine-grained pairwise distance learning. Additionally, we have established an in-house dataset on urinary tract stones to demonstrate the effectiveness of our proposed approach. Comprehensive experiments conducted on this dataset reveal that our framework significantly surpasses existing state-of-the-art methods. Copyright © 2024, The Authors. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Enhancing IoT-Edge Computation with Data Forwarding based Decentralized Deep Neural Networks

Enhancing IoT-Edge Computation with Data Forwarding based De...

引用

International Conference on Image Information Processing

作者： Bmg Prasad Rachappa Jopate Pankaj Savita A Basi Reddy B Prabu Shankar M S Arunkumar Department of CSE Ravindra College of Engineering for Women(RCEW Autonomous) Kurnool Andhra Pradesh India Department of Information Technology University of Technology And Applied Sciences - Al Mussanah Al Muladha Muscat Sultanate of Oman Department of CSE Sagar Institute of Science & Technology Bhopal Organization-Sagar Institute of Science & Technology Bhopal Madhya Pradesh India Department of Computer Science and Engineering School of Computing Mohan Babu University Tirupati Andhra Pradesh India Department of Computer Science and Engineering Alliance College of Engineering and Design Alliance University Banglore Karnataka India Department of Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Tamilnadu India

ISBN: (数字)9798350371406

ISBN: (纸本)9798350371413

The incorporation of edge computing has become essential in the big data and Internet of Things age to tackle issues related to latency, real-time processing, and data scale. This paper delves into the imperative need for edge computing within the context of big data environments. Distributed deep learning methodologies are explored, encompassing a diverse array of deep learning models. Particularly, a novel paradigm named Data Forwarding based Decentralized Deep Neural Network (DF-DDNN) is introduced to achieve low latency IoT-Edge computation. In order to reduce latency in Io T ecosystems, the DF-DDNN model makes use of edge devices’ processing capabilities. By strategically distributing data processing and computation at the edge, this model seeks to overcome inherent limitations of conventional Io T architectures, with a keen focus on network, processing, and overall latencies. The research provides a thorough performance evaluation that compares the DF-DDNN model’s performance versus conventional IoT models in a number of areas. The outcomes demonstrate how much better the suggested DF-DDNN model is than traditional IoT systems. Notably, improvements are evident in terms of reduced network latency, accelerated processing speeds, and overall latency mitigation. This research underscores the critical importance of embracing edge computing in the context of big data and deep learning applications. The DF-DDNN model emerges as a promising avenue for advancing IoT-Edge computation, effectively addressing latency concerns and augmenting the performance of IoT-enabled systems.

关键词： Deep learning Performance evaluation Computational modeling Biological system modeling Artificial neural networks Big Data Data models

来源：评论

学校读者我要写书评

暂无评论

Explainable Natural Language Processing for Corporate Sustainability Analysis

arXiv

引用

arXiv 2024年

作者： Ong, Keane Mao, Rui Satapathy, Ranjan Filho, Ricardo Shirota Cambria, Erik Sulaeman, Johan Mengaldo, Gianmarco College of Design and Engineering National University of Singapore 9 Engineering Drive 1 117575 Singapore Asian Institute of Digital Finance National University of Singapore Innovation 4.0 3 Research Link #04-03 117602 Singapore College of Computing and Data Science Nanyang Technological University 50 Nanyang Ave 639798 Singapore Institute of High Performance Computing Agency for Science Technology and Research Fusionopolis Way #16-16 Connexis 138632 Singapore Sustainable and Green Finance Institute National University of Singapore Innovation 4.0 3 Research Link #02-02 117602 Singapore NUS Business School National University of Singapore Mochtar Riady Building 15 Kent Ridge Dr Mocthar Riady Building 119245 Singapore Honorary Research Fellow Imperial College London United Kingdom

Sustainability commonly refers to entities, such as individuals, companies, and institutions, having a non-detrimental (or even positive) impact on the environment, society, and the economy. With sustainability becoming a synonym of acceptable and legitimate behaviour, it is being increasingly demanded and regulated. Several frameworks and standards have been proposed to measure the sustainability impact of corporations, including United Nations’ sustainable development goals and the recently introduced global sustainability reporting framework, amongst others. However, the concept of corporate sustainability is complex due to the diverse and intricate nature of firm operations (i.e. geography, size, business activities, interlinks with other stakeholders). As a result, corporate sustainability assessments are plagued by subjectivity both within data that reflect corporate sustainability efforts (i.e. corporate sustainability disclosures) and the analysts evaluating them. This subjectivity can be distilled into distinct challenges, such as incompleteness, ambiguity, unreliability and sophistication on the data dimension, as well as limited resources and potential bias on the analyst dimension. Put together, subjectivity hinders effective cost attribution to entities non-compliant with prevailing sustainability expectations, potentially rendering sustainability efforts and its associated regulations futile. To this end, we argue that Explainable Natural Language Processing (XNLP) can significantly enhance corporate sustainability analysis. Specifically, linguistic understanding algorithms (lexical, semantic, syntactic), integrated with XAI capabilities (interpretability, explainability, faithfulness), can bridge gaps in analyst resources and mitigate subjectivity problems within data. © 2024, CC BY.

关键词： Sustainable development goals

来源：评论

学校读者我要写书评

暂无评论

Second-order Attention Guided Convolutional Activations for Visual Recognition

Second-order Attention Guided Convolutional Activations for ...

引用

International Conference on Pattern Recognition

作者： Shannan Chen Qian Wang Qiule Sun Bin Liu Jianxin Zhang Qiang Zhang Key Lab of Advanced Design and Intelligent Computing (Ministry of Education) Dalian University Dalian China School of Information and Communication Engineering Dalian University of Technology Dalian China International School of Information Science and Engineering (DUT-RUISE) Dalian University of Technology Dalian China School of Computer Science and Technology Dalian University of Technology Dalian China

Recently, modeling deep convolutional activations by the global second-order pooling has shown great advance on visual recognition tasks. However, most of the existing deep second-order statistical models mainly compute second-order statistics of activations of the last convolutional layer as image representations, and they seldom introduce second-order statistics into earlier layers to better fit network topology, thus limiting the representational ability to a certain extent. Motivated by the flexibility of attention blocks that are commonly plugged into intermediate layers of deep convolutional networks (ConvNets), this work makes an attempt to combine deep second-order statistics with attention mechanisms in ConvNets, and further proposes a novel Second-order Attention Guided Network (SoAG-Net) for visual recognition. More specifically, SoAG-Net involves several SoAG modules seemingly inserted into intermediate layers of the network, in which SoAG collects second-order statistics of convolutional activations by polynomial kernel approximation to predict channel-wise attention maps utilized for guiding the learning of convolutional activations through tensor scaling along channel dimension. SoAG improves the nonlinearity of ConvNets and enables ConvNets to fit more complicated distribution of convolutional activations. Experiment results on three commonly used datasets illuminate that SoAG-Net outperforms its counterparts and achieves competitive performance with state-of-the-art models under the same backbone.

关键词： Visualization Tensors Limiting Network topology Computational modeling Image representation Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

HCI, the web and the older population 20

HCI, the web and the older population

引用

20th British Computer Society Conference on Human-Computer Interaction: Engage, HCI 2006

作者： Goodman, Joy Dickinson, Anna Keith, Suzette Whitney, Gill Engineering Design Centre University of Cambridge CambridgeCB2 1PZ United Kingdom Division of Applied Computing University of Dundee DundeeDD1 4HN United Kingdom School of Computing Science Middlesex University Burroughs Hendon LondonNW4 4 BT United Kingdom

Workshop website: http://***/~jag76/hci_workshop06 This workshop on HCI and the older population will provide a forum for the presentation of current work and a platform for discussing key challenges in this area. It aims to build up and support the research community in this area, encouraging communication with older people and addressing key issues together. HCI issues for older people are extremely important in light of the rapidly ageing population in developed countries and the potential offered by computerised technology, a potential that can only be fulfilled if the technology can be used effectively by its target user group. The workshop continues a successful series held at HCI in recent years and this year focuses on the creation and use of websites, a particularly important and timely topic as the use of the internet becomes increasingly integrated with daily life. © BCS HCI Group Conference: Engage, HCI *** right reserved.

关键词： Human computer interaction

来源：评论

学校读者我要写书评

暂无评论

Enabling Training-Free Semantic Communication Systems with Generative Diffusion Models

arXiv

引用

arXiv 2025年

作者： Tang, Shunpu Jia, Yuanyuan Yang, Qianqian Zhang, Ruichen Park, Jihong Niyato, Dusit College of Information Science and Electronic Engineering Zhejiang University Hangzhou China School of Electronics and Communication Engineering Sun Yat-sen University Shenzhen China College of Computing and Data Science Nanyang Technological University Singapore ISTD Pillar Singapore University of Technology and Design Singapore

Semantic communication (SemCom) has recently emerged as a promising paradigm for next-generation wireless systems. Empowered by advanced artificial intelligence (AI) technologies, SemCom has achieved significant improvements in transmission quality and efficiency. However, existing SemCom systems either rely on training over large datasets and specific channel conditions or suffer from performance degradation under channel noise when operating in a training-free manner. To address these issues, we explore the use of generative diffusion models (GDMs) as training-free SemCom systems. Specifically, we design a semantic encoding and decoding method based on the inversion and sampling process of the denoising diffusion implicit model (DDIM), which introduces a two-stage forward diffusion process, split between the transmitter and receiver to enhance robustness against channel noise. Moreover, we optimize sampling steps to compensate for the increased noise level caused by channel noise. We also conduct a brief analysis to provide insights about this design. Simulations on the Kodak dataset validate that the proposed system outperforms the existing baseline SemCom systems across various metrics. © 2025, CC BY.

关键词： Image denoising

来源：评论

学校读者我要写书评

暂无评论

Spatial mapping and analysis of forest fire risk areas in Sri Lanka – Understanding environmental significance

引用

Case Studies in Chemical and Environmental engineering 2024年 9卷

作者： Makumbura, Randika K. Dissanayake, Prasad Gunathilake, Miyuru B. Rathnayake, Namal Kantamaneni, Komali Rathnayake, Upaka Water Resources Management and Soft Computing Research Laboratory Millennium City Athurugiriya 10150 Sri Lanka Faculty of Engineering and Information Sciences University of Wollongong Northfields Ave Wollongong 2522 NSW Australia Hydrology and Aquatic Environment Division of Environmental and Natural Resources Norwegian Institute of Bioeconomy and Research Ås 1431 Norway Water Energy and Environmental Engineering Research Unit Faculty of Technology University of Oulu Oulu 90014 Finland Department of Civil Engineering Faculty of Engineering The University of Tokyo 1 Chome-1-1 Yayoi Bunkyo City Tokyo 113-8656 Japan School of Engineering University of Central Lancashire Preston PR1 2HE United Kingdom Department of Civil Engineering and Construction Faculty of Engineering and Design Atlantic Technological University Sligo F91 YW50 Ireland

This study presents the first attempt in Sri Lanka to generate a forest fire risk map covering the entire country using a GIS-based forest fire index (FFI) model. The model utilized seven parameters: land use, temperature, slope, proximity to roads and settlements, elevation, and aspect. All these parameters were derived using GIS techniques with ArcGIS10.4 and QGIS3.16. Data from Remote Sensing sources, particularly the MODIS hotspot real-world dataset, were employed to gather fire count information for the year 2020. Validation was conducted through the merging hotspot technique and kernel density estimation (KDE). The research findings highlight the districts in the Central and Uva provinces, such as NuwaraEliya (10.3 km²), Kandy (2.74 km²), and Badulla (10.41 km²), as having a “very low risk" of forest fire potential. Conversely, districts like Hambanthota (0.1 km²), Kaluthara (0.04 km²), and Kurunegala (0.2 km²) exhibit a “very high risk" of forest fire potential, although it is negligible compared country's total area. Overall, the study suggests that Sri Lanka is not currently facing a significant threat of forest fires and is a “medium risk" of forest fires as 49.49% of land falls under this category. These results are of immense value to relevant authorities, including the Ministry of Wildlife and Forest Resources Conservation, in formulating effective strategies to manage and mitigate forest fire risks in the country. © 2024 The Authors

关键词： Forest fire index (FFI) Geographic information system (GIS) Kernel density estimation (KDE) MODIS hotspot Remote sensing top of form

来源：评论

学校读者我要写书评

暂无评论

On-Road Information Extraction from Lidar Data Via Multiple Feature Maps 24

On-Road Information Extraction from Lidar Data Via Multiple ...

引用

2020 24th ISPRS Congress on Technical Commission I

作者： Wu, H. Xie, Z. Wen, C. Wang, C. Li, J. Fujian Key Laboratory of Sensing and Computing for Smart Cities School of Informatics Xiamen University Xiamen361005 China Departments of Geography and Environmental Management/Systems Design Engineering University of Waterloo WaterlooONN2L3G1 Canada

On-road information, including road boundaries, road markings, and road cracks, provides significant guidance or warning to all road users. Recently, the on-road information extraction from LiDAR data have been widely studied. However, for the LiDAR data with lower accuracy and higher noise, some detailed information, such as road boundary, is difficult to be extracted correctly. Furthermore, most of previous studies lack an exploration of efficiently extracting multiple on-road information from a single framework. In this paper, we propose a new framework that can simultaneously extract multiple on-road information from high accuracy LiDAR data and can also more robustly extract detailed road boundaries from low accuracy LiDAR data. First, we propose a Curb-Aware Ground Filter to extract ground points with rich curb structure features. Second, we transform the vertical density, elevation gradient and intensity features of the ground points into multiple feature maps and extract multiple on-road information from the feature maps by employing a semantic segmentation network. Experimental results on three datasets with different data accuracy demonstrate that our method outperforms other recent competitive methods. © 2020 Copernicus GmbH. All rights reserved.

关键词： Semantics

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：