检索结果-内蒙古大学图书馆

GLOBECOM 2022 - 2022 IEEE Global Communications Conference

作者： Lu Xia Zheng Yang Jingjing Cui Fuhui Zhou Yi Wu Zhicheng Dong Zhiguo Ding Fujian Provincial Engineering Technology Research Center of Photoelectric Sensing Application Fujian Normal University Fuzhou China School of Electronics and Computer Science University of Southampton Southampton UK College of Electronic and Information Engineering Nanjing University of Aeronautics and Astronautics Nanjing China School of Engineering Tibet University Lhasa China School of Electrical and Electronics Engineering The University of Manchester Manchester UK

ISBN: (纸本)9781665435413

In this paper, we study an uplink reconfigurable intelligent surfaces-non-orthogonal multiple access (RIS-NOMA) assisted mobile edge computing (MEC) network with simultaneous wireless information and power transfer (SWIPT), where the users want to offload their computing tasks to the BS via a RIS and a relay based on the SWIPT technique. The goal of the paper is to minimize the delay concerning the computing tasks of the users by jointly optimizing the power allocation ratio, the phase shift matrix of the RIS, the offloading task ratio, and the offloading transmit power. For solving the challenging optimization problem, we conceive a low-complexity algorithm by optimizing two subproblems separately, based on the penalty method as well as the successive convex approximation. Simulation results demonstrate that the proposed RIS-NOMA assisted MEC network with SWIPT outperforms both the conventional RIS-NOMA assisted MEC network without SWIPT and the RIS-orthogonal multiple access assisted MEC network.

关键词： Multi-access edge computing Simulation Minimization Delays Resource management Task analysis Uplink

来源：评论

学校读者我要写书评

暂无评论

Pre-trained Language Model based Medical Named Entity Recognition

Pre-trained Language Model based Medical Named Entity Recogn...

引用

Chinese Automation Congress (CAC)

作者： Zheng Cheng Jiaju Wu Bin Ji Huijun Liu School of Automation University of Electronic Science and Technology of China. Institute of Computer Application China Academy of Engineering Physics Mianyang China College of Civil Aviation Nanjing University of Aeronautics and Astronautic Nanjing China Institute of Computer Application China Academy of Engineering Physics Mianyang China College of Computer National University of Defense Technology Changsha China

ISBN: (纸本)9781665426480

Medical named entity recognition is an important part of structuring Chinese electronic medical records and construction of medical knowledge graph. The CCKS2019 conference organized a medical named entity recognition evaluation task to extract six types of medical entities from unstructured Chinese electronic medical records. Based on the data set of this evaluation task, pre-trained language model based entity recognition approaches are studied. First, select the BiLSTM-CRF model based on random initialized word embedding as the baseline system; secondly, apply word2vec to the baseline system; thirdly, apply ELMo to the baseline system. Experimental results show that the pre-trained language model is comparable to the best approach of this evaluation task, and the context-related pre-trained language model performs better.

关键词： Automation Data models Task analysis Electronic medical records Context modeling

来源：评论

学校读者我要写书评

暂无评论

MATNet: MRI Super-Resolution with Multiple Attention Mechanisms

MATNet: MRI Super-Resolution with Multiple Attention Mechani...

引用

New Trends in Computational Intelligence (NTCI), International Conference on

作者： Longfeng Shen Fenglan Qin Yingjie Zhang Qiong Wang Bowen Hu Wei Zhao Anhui Engineering Research Center for Intelligent Computing and Application on Cognitive Behavior (ICACB) Hefei Comprehensive National Science Center Institute of Artificial Integence Hefei China School of Computer Science and Technology Huaibei Normal University Huaibei Anhui China Anhui Big-Data Research Center on University Management Huaibei Anhui China People's Hospital of Huaibei City Anhui China

High-resolution magnetic resonance imaging (MRI) provides a clear anatomical structure for diagnosis, however, its high cost makes it unsuitable in practice. On the contrary, low-resolution MRI cannot provide fine structural information but is resource and time efficient. Super-resolution methods are high-resolution images obtained from low-resolution MRI. However, existing MRI super-resolution methods suffer from the following defects: (1) CNN-based super-resolution methods lack the ability to build relationships for remote features. (2) While models using transformer based on self-attentive mechanism have achieved a breakthrough in super-resolution, the single self-attentive model fails to fully utilize the useful features of the input image. Thus, in this paper, an MRI super-resolution network (MATNet) based on a multi-attention mechanism is proposed that can utilize multiple useful image features from different dimensions for image super-resolution, improved super-resolution performance. To enable the network to obtain noise-free image features before sampling the image, we also added a denoising module to it. Finally, we prove the effectiveness of the model using the IXI public dataset.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Semi-supervised 3D Object Detection with Proficient Teachers

arXiv

引用

arXiv 2022年

作者： Yin, Junbo Fang, Jin Zhou, Dingfu Zhang, Liangjun Xu, Cheng-Zhong Shen, Jianbing Wang, Wenguan School of Computer Science Beijing Institute of Technology China Baidu Research United States National Engineering Laboratory of Deep Learning Technology and Application China SKL-IOTSC Cis University of Macau China ReLER Aaii University of Technology Sydney Australia

Dominated point cloud-based 3D object detectors in autonomous driving scenarios rely heavily on the huge amount of accurately labeled samples, however, 3D annotation in the point cloud is extremely tedious, expensive and time-consuming. To reduce the dependence on large supervision, semi-supervised learning (SSL) based approaches have been proposed. The Pseudo-Labeling methodology is commonly used for SSL frameworks, however, the low-quality predictions from the teacher model have seriously limited its performance. In this work, we propose a new Pseudo-Labeling framework for semi-supervised 3D object detection, by enhancing the teacher model to a proficient one with several necessary designs. First, to improve the recall of pseudo labels, a Spatial-temporal Ensemble (STE) module is proposed to generate sufficient seed boxes. Second, to improve the precision of recalled boxes, a Clustering-based Box Voting (CBV) module is designed to get aggregated votes from the clustered seed boxes. This also eliminates the necessity of sophisticated thresholds to select pseudo labels. Furthermore, to reduce the negative influence of wrongly pseudo-labeled samples during the training, a soft supervision signal is proposed by considering Box-wise Contrastive Learning (BCL). The effectiveness of our model is verified on both ONCE and Waymo datasets. For example, on ONCE, our approach significantly improves the baseline by 9.51 mAP. Moreover, with half annotations, our model outperforms the oracle model with full annotations on Waymo. Copyright © 2022, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

A Convolution-Based System for Malicious URLs Detection

引用

computers, Materials & Continua 2020年第1期62卷 399-411页

作者： Chaochao Luo Shen Su Yanbin Sun Qingji Tan Meng Han Zhihong Tian Institute of Computer Application China Academy of Engineering PhysicsMianyang621054China Cyberspace Institute of Advanced Technology Guangzhou UniversityGuangzhou510006China School of Mechanical and Electrical Engineering Heilongjiang State Farm Science Technology Vocational CollegeHarbin150431China Department of Computing and Software Engineering Kennesaw State UniversityKennesawGA 30144USA

Since the web service is essential in daily lives,cyber security becomes more and more important in this digital *** Uniform Resource Locator(URL)is a common and serious threat to *** hosts unsolicited content and lure unsuspecting users to become victim of scams,such as theft of private information,monetary loss,and malware ***,it is imperative to detect such ***,traditional approaches for malicious URLs detection that based on the blacklists are easy to be bypassed and lack the ability to detect newly generated malicious *** this paper,we propose a novel malicious URL detection method based on deep learning model to protect against web ***,we firstly use auto-encoder to represent ***,the represented URLs will be input into a proposed composite neural network for *** order to evaluate the proposed system,we made extensive experiments on HTTP CSIC2010 dataset and a dataset we collected,and the experimental results show the effectiveness of the proposed approach.

关键词： CNN anomaly detection web security auto-encoder deep learning

来源：评论

学校读者我要写书评

暂无评论

Manifold Guided Graph Neural Networks for Skeleton-based Action Recognition in Human computer Interaction Videos

Manifold Guided Graph Neural Networks for Skeleton-based Act...

引用

2021 International Conference on Signal Processing and Machine Learning (CONF-SPML)

作者： Xin Li Ce Li Xianlong Wei Feng Yang Computer Application Technology China University of Mining & Technology Beijing Computer Science and Technology China University of Mining & Technology Beijing School of Mechanical Electronic & Information Engineering China University of Mining & Technology Beijing

ISBN: (纸本)9781665417358

As the key application in video analysis for human computer interaction(HCI),the problem of skeleton-based action recognition has been solved by some researchers with graph neural networks,but it remains an unsolved issue on complex variations of spatiotemporal dependence across skeleton joints flow.A newly dynamic spatio-temporal graph structure learning method,manifold guided graph neural networks(MGNN),was proposed to solve this *** MGNN,a novel manifold guided graph updating mechanism is built based on the baseline graph neural network to further describe the spatio-temporal *** the manifold guided multi-scale skeleton graph,the proposed MGNN is further trained with two streams of joint and bone to improve the efficiency,which forms a single network seamlessly and enables it be trained in a same *** with the existing methods,MGNN has been proved that it yields better performance on challenging datasets:NTU RGB+D 60 and Kinetics 400.

关键词： Action recognition Manifold guided Graph neural network spatio-temporal dependence

来源：评论

学校读者我要写书评

暂无评论

Efficient Reconstruction of Spatial Features for Remote Sensing Image-Text Retrieval

引用

Transactions of Nanjing University of Aeronautics and Astronautics 2025年第1期42卷 101-111页

作者： ZHANG Weihang CHEN Jialiang ZHANG Wenkai LI Xinming GAO Xin SUN Xian Aerospace Information Research Institute Chinese Academy of SciencesBeijing 100190P.R.China Key Laboratory of Target Cognition and Application Technology(TCAT) Chinese Academy of SciencesBeijing 100190P.R.China School of Electronic Electrical and Communication EngineeringUniversity of Chinese Academy of SciencesBeijing 100190P.R.China School of Computer Science and Artificial Intelligence Aerospace Information Technology UniversityJinan 250299P.R.China

Remote sensing cross-modal image-text retrieval(RSCIR)can flexibly and subjectively retrieve remote sensing images utilizing query text,which has received more researchers’attention ***,with the increasing volume of visual-language pre-training model parameters,direct transfer learning consumes a substantial amount of computational and storage ***,recently proposed parameter-efficient transfer learning methods mainly focus on the reconstruction of channel features,ignoring the spatial features which are vital for modeling key entity *** address these issues,we design an efficient transfer learning framework for RSCIR,which is based on spatial feature efficient reconstruction(SPER).A concise and efficient spatial adapter is introduced to enhance the extraction of spatial *** spatial adapter is able to spatially reconstruct the features in the backbone with few parameters while incorporating the prior information from the channel *** conduct quantitative and qualitative experiments on two different commonly used RSCIR *** with traditional methods,our approach achieves an improvement of 3%-11% in sumR *** with methods finetuning all parameters,our proposed method only trains less than 1% of the parameters,while maintaining an overall performance of about 96%.

关键词： remote sensing cross-modal image-text retrieval(RSCIR) spatial features channel features contrastive learning parameter effective transfer learning

来源：评论

学校读者我要写书评

暂无评论

Computing for Mitigation of Health Vulnerabilities for the Village Morasiya in Bihar, India 1st

Computing for Mitigation of Health Vulnerabilities for the V...

引用

1st International Conference on Data science, Machine Learning and applications, 2019

作者： Hooda, Mohit Gupta, Abhijeet Ramesh, Meera U, Rahul Nair, Jayashree Mohan, Renjith Department of Computer Science Engineering Amrita School of Engineering Amrita Vishwa Vidyapeetham Amritapuri India Department of Electronics and Communication Engineering Amrita School of Engineering Amrita Vishwa Vidyapeetham Amritapuri India Amrita School of Biotechnology Amrita Vishwa Vidyapeetham Amritapuri India Department of Computer Science and Application Engineering Amrita School of Engineering Amrita Vishwa Vidyapeetham Amritapuri India Amrita Center for International Programs Amrita School of Engineering Amrita Vishwa Vidyapeetham Amritapuri India

ISBN: (纸本)9789811514197

The health of the Indian villagers is on a decline from past years. Hence, uplifting health care standards is a prime concern and must be given the highest priority. This research primarily focuses on the health care sector of the village Morasiya, Bihar (India). We analyzed the existing treatment methods adopted by the villagers. Interviews with the villagers and doctor, keen inspection of the health care facilities and observational studies of the surroundings contributed significantly to our study. Lack of a nearby clinic, negligence towards personal hygiene, unavailability of professional doctors were the main causes behind the downfallen health of the villagers. This study focuses on understanding the prevalence of skin diseases among children. The paper presents the qualitative information and quantitative data gathered from the village and how it can be utilized to exploit technological innovations in order to design a feasible and sustainable solution to aid the villagers. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Dermatology

来源：评论

学校读者我要写书评

暂无评论

ExpoNAS: Using Exposure-based Candidate Exclusion to Reduce NAS Space for Heterogeneous Pipeline of CNNs

ExpoNAS: Using Exposure-based Candidate Exclusion to Reduce ...

引用

International Conference on Parallel and Distributed Systems (ICPADS)

作者： Huijuan Duan Danghui Wang Xingting Zhao Kuizhi Mei Jihe Wang School of Computer Science Northwestern Polytechnical University Xi'an China Engineering Research Center of Embedded System Integration Ministry of Education Northwestern Polytechnical University Xi'an China Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University Xi'an China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Northwestern Polytechnical University Xi'an China

Efficiently deploying neural network models on heterogeneous edge systems faces unique challenges. Two major issues are underutilized pipelines caused by hardware heterogeneity and explosive growth of architecture search space. To address these challenges, we propose ExpoNAS, a framework enabling fast deployment-oriented neural architecture search on heterogeneous platforms. ExpoNAS evaluates model partitioning and deployability before search to meet accuracy and latency constraints. However, repeated partitioning leads to exponential growth in architecture search space. We first observe a strong correlation between operational exposure and accuracy improvement, and then we propose an exposure-based reduction technique that excludes the operations of low exposure. By removing these non-critical operations, the exposure-based pruning successfully reduces architecture search time. Our experiments on popular datasets show that the ExpoNAS pipelined design improves execution efficiency by a factor of 2 compared to traditional batch processing. Without compromising accuracy, ExpoNAS is able to reduce the architecture search time by 47.5% for discovering high-accuracy networks, compared to the SOTA NAS strategies.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ResfEANet: ResNet-fused External Attention Network for Tuberculosis Diagnosis using Chest X-ray Images

引用

computer Methods and Programs in Biomedicine Update 2024年 5卷

作者： Ejiyi, Chukwuebuka Joseph Qin, Zhen Nnani, Ann O Deng, Fuhu Ejiyi, Thomas Ugochukwu Ejiyi, Makuachukwu Bennedith Agbesi, Victor Kwaku Bamisile, Olusola Network and Data Security Key Laboratory of Sichuan Province University of Electronic Science and Technology of China Chengdu China College of Environmental Science and Engineering Hohai University Nanjing China Department of Pure and Industrial Chemistry University of Nigeria Nsukka Enugu Nigeria Pharmacy Department University of Nigeria Nsukka Enugu Nigeria School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China Sichuan Industrial Internet Intelligent Monitoring and Application Engineering Technology Research Centre Chengdu University of Technology Chengdu China

Pulmonary tuberculosis (TB), the most prevalent form of TB, remains a major global public health concern, contributing to more than a million deaths each year. The accurate and timely diagnosis of this disease is of paramount importance for effective control and treatment. Chest X-ray (CXR) images have emerged as a valuable tool for screening lung diseases, including TB, owing to their cost-effectiveness and non-invasiveness. Despite advancements in technology, the challenges associated with interpreting CXR images persist, primarily due to the scarcity of trained radiologists. This underscores the pressing need for an automated and cost-effective computer-aided system capable of diagnosing TB, assisting medical practitioners in distinguishing between TB-positive and negative CXR scans. In response to this need, we introduce an innovative approach called ResNet-fused External Attention Network (ResfEANet). This network excels in accurately classifying TB from CXR images, achieving remarkable levels of accuracy and sensitivity. ResfEANet is built upon ResNet and incorporates an External Attention mechanism, albeit with fewer residual network blocks than ResNet-50 resulting in a relatively shallow network with fewer layers. This approach proves highly effective in feature extraction and yields competitive results in the classification of TB. Our method was employed to train a model that demonstrated an impressive accuracy rate of 97.59% and a remarkable sensitivity of 100% in binary classification tasks with optimal computational cost. These outcomes suggest that our proposed approach has the potential to serve as a valuable secondary tool in clinical decision-making, providing crucial assistance to radiologists and healthcare professionals. © 2023

关键词： Chest X-ray images External Attention ResfEANet ResNet Tuberculosis

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：