检索结果-内蒙古大学图书馆

7th International Conference on Human Aspects of IT for the Aged Population, ITAP 2021, held as part of the 23rd International Conference, HCI International 2021

作者： Zhao, Chunyang Que, Xia Yin, Yue Xing, Xiaoman Yang, Jiaoyun An, Ning Key Laboratory of Knowledge Engineering with Big Data of Ministry of Education Hefei University of Technology Hefei China School of Computer Science and Information Engineering Hefei University of Technology Hefei China Medical Imaging Department Chinese Academy of Sciences Suzhou China

ISBN: (纸本)9783030781101

The Ambient Assisted Living (AAL) systems use sensors to detect the daily behavior of older adults and provide necessary assistance based on changes in their cognitive status and physical functions, thus enabling older adults to maintain their independence at home. However, the effectiveness of the AAL systems depends on the accuracy of the data provided by sensors. Namely, when a human error or a hardware failure occurs, the activity recognition model can become inaccurate. This inaccuracy hinders the identification of critical and potentially life-threatening activities. Although there are many methods for cleaning sensor data, there is no method for binary sensors deployed in smart homes. By considering noisy sensor events and unintentional forgetting of turning off the device, this paper proposes two clustering-based methods for denoising and splitting binary sensor events to address possible inaccuracy due to the two mentioned problems. The effectiveness of the proposed methods is verified by the experiments using four machine learning models and three real-world smart home datasets and adopting different sensor configurations. The experimental results demonstrate that compared to the original unprocessed datasets, by combining the two proposed methods, the average accuracy and F-measure are improved by 15.00% and 17.25%, respectively. © 2021, Springer Nature Switzerland AG.

关键词： Automation

来源：评论

学校读者我要写书评

暂无评论

ImageALCAPA: A 3D Computed Tomography Image Dataset for Automatic Segmentation of Anomalous Left Coronary Artery from Pulmonary Artery

ImageALCAPA: A 3D Computed Tomography Image Dataset for Auto...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： An Zeng Chenxi Mi Dan Pan Qing Lu Xiaowei Xu School of Computer Science Guangdong University of Technology Guangzhou China Department of Computer Science Guangdong Polytechnic Normal University Guangzhou China Department of Computer Science and Engineering University of Notre Dame IN US Guangdong Provincial People’s Hospital Guangdong Academy of Medical Sciences Guangzhou China

ISBN: (数字)9781665468190

ISBN: (纸本)9781665468206

Anomalous left coronary artery from pulmonary artery (ALCAPA) is a serious cardiac anomaly, and surgical repair is the main treatment for ALCAPA patients in clinical practice. Recently, 3D printing has been widely adopted in the surgical planning of ALCAPA, which can give surgeons an intuitive structure of the heart especially the coronary arteries. However, before 3D printing is conducted, experienced radiologists need to manually segment the coronary arteries on computed tomography angiography (CTA) images, which is time-consuming, tedious and biased. On the other hand, automatic coronary artery segmentation with normal structures has been extensively studied in the community, but cannot be effectively applied to ALCAPA due to the significant variation of coronary artery structure in ALCAPA. In this paper, we propose ImageALCAPA, the first 3D CTA image dataset of ALCAPA. The proposed dataset contains 30 ALCAPA CTA images, which is of decent size compared with existing medical imaging datasets. We further propose a baseline method that performs multi-task 2D- 3D ensemble for automatic segmentation of ALCAPA. It is shown by experiment that our baseline method outperforms popular existing works on coronary artery segmentation. However, as the highest average Dice Similarity Coefficient of coronary arteries is merely 65%, there is still much room for improvement. To facilitate further research on this challenging problem, our dataset and codes are released to the public [1].

关键词： Image segmentation Three-dimensional displays Codes Computed tomography Lung Surgery Three-dimensional printing

来源：评论

学校读者我要写书评

暂无评论

Event Stream-Based Visual Object Tracking: A High-Resolution Benchmark Dataset and A Novel Baseline

Event Stream-Based Visual Object Tracking: A High-Resolution...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Xiao Wang Shiao Wang Chuanming Tang Lin Zhu Bo Jiang Yonghong Tian Jin Tang School of Computer Science and Technology Anhui University Hefei China University of Chinese Academy of Sciences Beijing China Institute of Optics and Electronics CAS Chengdu China Beijing Institute of Technoloay Beijing China Peng Cheng Laboratory Shenzhen China National Key Laboratory for Multimedia Information Processing School of Computer Science Peking University China School of Electronic and Computer Engineering Shenzhen Graduate School Peking University China

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Tracking with bio-inspired event cameras has garnered increasing interest in recent years. Existing works either utilize aligned RGB and event data for accurate tracking or directly learn an event-based tracker. The former incurs higher inference costs while the latter may be susceptible to the impact of noisy events or sparse spatial resolution. In this paper, we propose a novel hierarchical knowledge distillation framework that can fully utilize multimodal / multi-view information during training to facilitate knowledge transfer, enabling us to achieve high-speed and low-latency visual tracking during testing by using only event signals. Specifically, a teacher Transformer-based multimodal tracking framework is first trained by feeding the RGB frame and event stream simultaneously. Then, we design a new hierarchical knowledge distillation strategy which includes pairwise similarity, feature representation, and response maps-based knowledge distillation to guide the learning of the student Transformer network. In particular, since existing event-based tracking datasets are all low-resolution (346 × 260), we propose the first large-scale high-resolution (1280 × 720) dataset named EventVOT. It contains 1141 videos and covers a wide range of categories such as pedestrians, vehicles, UAVs, ping pong, etc. Ex-tensive experiments on both low-resolution (FE240hz, Vi-sEvent, COESOT), and our newly proposed high-resolution EventVOT dataset fully validated the effectiveness of our proposed method.

关键词： Knowledge engineering Training Visualization Pedestrians Self-supervised learning Transformers Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

IoT-Enabled Plant Root Monitoring for Improved Water and Nutrient Uptake with Long Short-Term Memory

IoT-Enabled Plant Root Monitoring for Improved Water and Nut...

引用

Smart Technologies for Sustainable Development Goals (ICSTSDG), International Conference on

作者： Chitra Sabapathy Ranganathan Kabaleeswaran S MD Ashfaqul Hasan M. Vadivel S. Srinivasan T. Annalakshmi Mphasis Corporation Chennai Tamil Nadu India Capgemini Overland Park Kansas United States Department of Computer Science and Engineering Malla Reddy Institute of Engineering and Technology Hyderabad Telangana India Department of Electronics and Communication Engineering Vidya Jyothi Institute of Technology Hyderabad Telangana India Department of Biomedical Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai Tamil Nadu India Department of Electronics and Communication Engineering S.A. Engineering College (Autonomous) Chennai Tamil Nadu India

ISBN: (数字)9798331516284

ISBN: (纸本)9798331516291

This research presents a novel method for improving root monitoring in agricultural systems via the use of Long Short-Term Memory (LSTM) networks and the Internet of Things (IoT). The goal is to improve water and nutrient absorption. Ineffective resource management and lower crop yields are common results of using antiquated technologies to track plant roots, which lack both real-time data and accuracy. The proposed IoT system uses sensors to monitor soil moisture, nutrient levels, and root activity in real time, giving valuable information about plant health and growth dynamics. LSTM networks, a subset of recurrent neural networks, are trained on the acquired data to accurately forecast the root's behavior in the future by capturing its relationships throughout time. With this predictive capacity, growers can water and fertilize plants precisely according to their individual requirements, making the most efficient use of resources and reducing waste. With the help of the IoT even massive agricultural operations can be remotely monitored and controlled, allowing for proactive management and intervention. To improve water and nutrient absorption efficiency, this in turn increases crop output and helps to save the environment. It provides a viable alternative for sustainable agriculture.

关键词： Irrigation Absorption Plants (biology) Nutrients Real-time systems Resource management Sustainable development Long short term memory Monitoring Water resources

来源：评论

学校读者我要写书评

暂无评论

Boosting ViT-based MRI Reconstruction from the Perspectives of Frequency Modulation, Spatial Purification, and Scale Diversification 39

Boosting ViT-based MRI Reconstruction from the Perspectives ...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Meng, Yucong Yang, Zhiwei Shi, Yonghong Song, Zhijian Digital Medical Research Center School of Basic Medical Science Fudan University Shanghai200032 China Shanghai Key Laboratory of Medical Image Computing and Computer Assisted Intervention Shanghai200032 China Academy for Engineering and Technology Fudan University Shanghai200433 China

ISBN: (纸本)157735897X

The accelerated MRI reconstruction process presents a challenging ill-posed inverse problem due to the extensive undersampling in k-space. Recently, Vision Transformers (ViTs) have become the mainstream for this task, demonstrating substantial performance improvements. However, there are still three significant issues remain unaddressed: (1) ViTs struggle to capture high-frequency components of images, limiting their ability to detect local textures and edge information, thereby impeding MRI restoration;(2) Previous methods calculate multi-head self-attention (MSA) among both related and unrelated tokens in content, introducing noise and significantly increasing computational burden;(3) The naive feed-forward network in ViTs cannot model the multi-scale information that is important for image restoration. In this paper, we propose FPS-Former, a powerful ViT-based framework, to address these issues from the perspectives of frequency modulation, spatial purification, and scale diversification. Specifically, for issue (1), we introduce a frequency modulation attention module to enhance the self-attention map by adaptively re-calibrating the frequency information in a Laplacian pyramid. For issue (2), we customize a spatial purification attention module to capture interactions among closely related tokens, thereby reducing redundant or irrelevant feature representations. For issue (3), we propose an efficient feed-forward network based on a hybrid-scale fusion strategy. Comprehensive experiments conducted on three public datasets show that our FPS-Former outperforms state-of-the-art methods while requiring lower computational costs. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Frequency modulation

来源：评论

学校读者我要写书评

暂无评论

Dynamic Infrared Thermography and Machine Learning for Advanced Diagnostic Applications in Biomedical Imaging

Dynamic Infrared Thermography and Machine Learning for Adv...

引用

20th International Conference on Dependability of computer Systems, DepCoS-RELCOMEX 2025

作者： Jeleń, Lukasz Krupka, Krzysztof Rusiecki, Andrzej Department of Computer Engineering Wroclaw University of Science and Technology Wybrzeże Wyspiańskiego 27 Wroclaw50-370 Poland The Karol Godula Upper Silesian Academy of Entrepreneurship in Chorzów ul. Raclawicka 23 Chorzów41-506 Poland

ISBN: (纸本)9783031927331

Dynamic infrared thermography (DIRT) is a noninvasive method that provides real-time insights into skin perfusion by tracking thermal variations alongside temperature images. In this study, we explored the possibility of using DIRT imaging data to differentiate selected diagnostic features of examined patients. We employed a combination of preprocessing algorithms and neural models built on the acquired series of full-body DIRT scans to enable accurate discrimination between patients after myocardial infarction and patients after being diagnosed with COVID-19 infection. Training dedicated convolutional neural networks (CNN) on the full thermogram scans yielded promising results, with an overall accuracy of 85%. These findings underline the value of preserving comprehensive thermal information in medical imaging for CNN classification, especially in applications where subtle thermal variations are critical to diagnosis. Our work, as preliminary research, highlights that full-body DIRT imaging data can serve as a meaningful source of information about patients’ health and the presented results clearly show that the application of machine learning techniques can allow for the creation of an automated framework for medical thermogram analysis. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Neuroimaging

来源：评论

学校读者我要写书评

暂无评论

A federated parallel data platform for trustworthy AI 1

A federated parallel data platform for trustworthy AI

引用

1st IEEE International Conference on Digital Twins and Parallel Intelligence, DTPI 2021

作者： Chen, Leiming Zhang, Weishan Xu, Liang Zeng, Xingjie Lu, Qinghua Zhao, Hongwei Chen, Bingyang Wang, Xiao QingDao China College of Computer and Communication Engineering Beijing University of Science and Technology Beijing China Data61 CSIRO Australia Institute of Automation Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781665433372

Traditional data analytics approaches often ignore data security and privacy issues, and are not efficient for dynamic analysis and decision-making. The parallel data and federated data provide new ideas for addressing these issues. However, how to design the analytics applications of parallel data and federated data is challenging and calls for comprehensive tool support. This paper proposes a federated parallel data platform (FPDP) that provides an end-to-end data analytics pipeline, such as virtual data generation, federation model construction, and parallel data deduction. We implement a proof-of-concept prototype and evaluate the feasibility of the platform design using a fault diagnosis case study. The evaluation results show that the proposed approach is effective and efficient to help developing trustworthy AI applications. © 2021 IEEE.

关键词： Data Analytics

来源：评论

学校读者我要写书评

暂无评论

Contrastive Patch Comparison Transformer for Weakly Supervised Semantic Segmentation

Contrastive Patch Comparison Transformer for Weakly Supervis...

引用

IEEE International Conference on Smart Internet of Things (SmartIoT)

作者： Wentian Cai Weixian Yang Jing Lin Ying Gao School of Computer Science and Engineering South China University of Technology Guangzhou China Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application Guangdong Provincial People's Hospital Guangdong Academy of Medical Sciences Guangzhou China

ISBN: (数字)9798350366440

ISBN: (纸本)9798350366457

Weakly supervised semantic segmentation (WSSS) focuses on utilizing image-level labels to classify all pixels into object classes or background class. Class Activation Mapping (CAM) highlights the most discriminative region of the target object, but fails to discover minor details in whole image. The gap between classification task and segmentation task causes a reduction in the accuracy. In this paper, we propose a simple-yet-efficient WSSS framework based on Transformer backbone. We introduce a patch-wise contrastive learning module to discover potential patch embedding information. Additionally, we introduced a multi-scale supervision to constrain the network to focus on target objects while learning patch-wise contrasty. Experimental results validate that our framework yields good performance on VOC2012 without using any salient maps.

关键词： Accuracy Semantic segmentation Semantics Contrastive learning Transformers Internet of Things

来源：评论

学校读者我要写书评

暂无评论

On-board Time-varying Topology Self Prediction Routing Network Communication technology

On-board Time-varying Topology Self Prediction Routing Netwo...

引用

International Conference on Advanced Infocomm technology (ICAIT)

作者： Jiyang Yu Dan Huang Nan Wu Jinyang Li Wenjie Li Xianjie Wang China Academy of Space Technology Beijing Institute of Spacecraft System Engineering Beijing China China Research & Development Academy of Machinery Equipment Chongqing University of Technology Chongqing China Beijing Institute of Computer Technology and Applications Fangzhou Key Technology Laboratory Beijing China Beijing Blackstone Matrix Technology Co. LTD Chongqing Feima Innovation Research Institute Chongqing China College of Computer Science and Engineering Chongqing University of Technology Chongqing China

Facing the difficulties of large-scale networked satellite communication, such as unstable topology, diversified channel types, and uncertain satellite link failure, this paper proposes a general optimal routing path calculation method based on historical data prediction, and establishes a Statistical model based on historical data prediction for inter satellite communication transmission, which is not limited to transient failures caused by aging energy, storage, and load. At the same time, in the process of calculating the transmission rate and packet loss rate of the communication link, historical data is introduced to form a channel rate function that changes over time, which is used to achieve communication prediction within the transmission time and achieve self-sensing of the communication link's state. Based on the self-prediction state of the communication link, combined with the domain search algorithm, the maximum probability optimal solution of the long-term interactive routing process is considered to achieve real-time optimal solution for data transmission in the constellation of Jupiter in orbit. A simulation verification was conducted for a large number of randomly distributed routing applications in a short period of time, and parameters such as link stability, load capacity, and business time delay were compared with previous designs. The results show that the proposed method has good stability, which is more than 10% higher than previous designs; The link load is significantly lower compared to previous designs; Under the condition of a large number of routing applications, the service delay has been reduced by 27% compared to previous designs, ensuring routing communication under the time-varying topology of the constellation group.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Innovations in CPR: A Comprehensive Survey on Enhanced Resuscitation Techniques

arXiv

引用

arXiv 2024年

作者： Islam, Saidul Rjoub, Gaith Elmekki, Hanae Bentahar, Jamal Pedrycz, Witold Cohen, Robin Concordia Institute for Information Systems Engineering Concordia University Montreal Canada Faculty of Information Technology Aqaba University of Technology Aqaba Jordan Department of Computer Science Khalifa University Abu Dhabi United Arab Emirates Department of Electrical and Computer Engineering University of Alberta Edmonton Canada Systems Research Institute Polish Academy of Sciences Warsaw Poland Research Center of Performance and Productivity Analysis Istinye University Sariyer Istanbul Turkey David R. Cheriton School of Computer Science University of Waterloo Waterloo Canada

This survey paper explores the transformative role of Machine Learning (ML) and Artificial Intelligence (AI) in Cardiopulmonary Resuscitation (CPR). It examines the evolution from traditional CPR methods to innovative ML-driven approaches, highlighting the impact of predictive modeling, AI-enhanced devices, and real-time data analysis in improving resuscitation outcomes. The paper provides a comprehensive overview, classification and critical analysis of current applications, challenges, and future directions in this emerging field. © 2024, CC BY.

关键词： Reinforcement 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：