检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Li, Junjie Ge, Meng Pan, Zexu Wang, Longbiao Dang, Jianwu Tianjin Key Laboratory of Cognitive Computing and Application College of Intelligence and Computing Tianjin University Tianjin China Department of Electrical and Computer Engineering National University of Singapore Singapore Japan Advanced Institute of Science and Technology Ishikawa Japan

Speaker extraction seeks to extract the target speech in a multi-talker scenario given an auxiliary reference. Such reference can be auditory, i.e., a pre-recorded speech, visual, i.e., lip movements, or contextual, i.e., phonetic sequence. References in different modalities provide distinct and complementary information that could be fused to form top-down attention on the target speaker. Previous studies have introduced visual and contextual modalities in a single model. In this paper, we propose a two-stage time-domain visual-contextual speaker extraction network named VCSE, which incorporates visual and self-enrolled contextual cues stage by stage to take full advantage of every modality. In the first stage, we pre-extract a target speech with visual cues and estimate the underlying phonetic sequence. In the second stage, we refine the pre-extracted target speech with the self-enrolled contextual cues. Experimental results on the real-world Lip Reading Sentences 3 (LRS3) database demonstrate that our proposed VCSE network consistently outperforms other state-of-the-art baselines. Copyright © 2022, The Authors. All rights reserved.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Identification of Diabetic Retinopathy by Transfer Learning Based Retinal Images

Identification of Diabetic Retinopathy by Transfer Learning ...

引用

International Conference on Communication and Electronics Systems (ICCES)

作者： Sreenivas Reddy Sagili Chandrashekhar Goswami V.C. Bharathi S. Ananthi K Rani R. Sathya Department of computer science Rochester Institute Of Technology Rochester New York Department of Computer Science & Engineering MIT School of Computing MIT Art Design and Technology University Pune Maharashtra School of Computer Science and Engineering VIT-AP University Amaravati Andhra Pradesh India Advanced Research Centre for Future Networks and Digital Twin Sri Eshwar College of Engineering Coimbatore Tamil Nadu India Department of Information Technology M. Kumarasamy College of Engineering Karur Tamilnadu India Department of IT Kongunadu College of Engineering and Technology Trichy Tamil Nadu India

ISBN: (数字)9798350377972

ISBN: (纸本)9798350377989

The human eye is frequently considered to deliver a space into a person's strength because it is only with diabetic retinopathy (DR), a devastating eye illness caused by diabetes mellitus, that one may understand the subject's unprotected surface without invasive operations. There are certain disorders, notably vascular illness, that authority telltale indicators in the eye retina. Microaneurysms (MAs) are primary indicators of diabetic retinopathy (DR), making their detection crucial for an effective screening program that adheres to clinical procedures. Retinal examinations can reveal pathological deviations caused by limited ocular diseases such as arteriosclerosis, diabetes, cardiovascular disease hypertension and stroke. The proposed work introduces image processing algorithms, such as shady object identification, to predict the disorder or improve the contribution frame, thereby improving the perceptibility of vessels in color fundus frames. Following this enhancement, an automated classification algorithm, specifically a Convolutional Neural Network (CNN), is executed. The CNN architecture is designed to efficiently extract features from retinal frames, capturing complex patterns connected with diabetic retinopathy. The trained CNN is then assessed on a separate test condition, with its performance system of measurement-accuracy, specificity, recall, and Fl measure-being reported.

关键词： Diabetic retinopathy Pathology Image color analysis Transfer learning Retina Feature extraction Prediction algorithms Classification algorithms Convolutional neural networks Object recognition

来源：评论

学校读者我要写书评

暂无评论

Optimizing the Size of Peritumoral Region for Assessing Non-Small Cell Lung Cancer Heterogeneity Using Radiomics 12th

Optimizing the Size of Peritumoral Region for Assessing No...

引用

12th International Conference on Health Information science, HIS 2023

作者： Zhang, Xingping Zhang, Guijuan Qiu, Xingting Yin, Jiao Tan, Wenjun Yin, Xiaoxia Yang, Hong Wang, Kun Zhang, Yanchun Cyberspace Institute of Advanced Technology Guangzhou University Guangzhou510006 China School of Computer Science and Technology Zhejiang Normal University Jinhua321000 China Department of Respiratory and Critical Care First Affiliated Hospital of Gannan Medical University Ganzhou341000 China Institute for Sustainable Industries and Liveable Cities Victoria University Melbourne3011 Australia Department of New Networks Peng Cheng Laboratory Shenzhen518000 China Department of Radiology First Affiliated Hospital of Gannan Medical University Ganzhou341000 China Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Northeastern University Shenyang110189 China

ISBN: (纸本)9789819971077

Objectives: Radiomics has a novel value in accurately and noninvasively characterizing non-small cell lung cancer (NSCLC), but the role of peritumoral features has not been discussed in depth. This work aims to systematically assess the additional value of peritumoral features by exploring the impact of peritumoral region size. Materials and methods: A total of 370 NSCLC patients who underwent preoperative contrast-enhanced CT scans between October 2017 and September 2021 were retrospectively analyzed. The study was carefully designed with a radiomics pipeline to predict lymphovascular invasion, pleural invasion, and T4 staging. To assess the impact of peritumoral features, tumor regions of interest (ROIs) annotated by two medical experts were automatically expanded to produce peritumoral ROIs of different regional sizes, with edge thicknesses of 1 mm, 3 mm, 5 mm, and 7 mm. In a custom pipeline, prediction models were constructed using peritumoral features with different margin thicknesses and intratumoral features of the primary tumor. Results: Radiomics features combining intratumoral and peritumoral regions were created based on the best features of each ROI. Models incorporating peritumoral features yielded varying degrees of improvement in AUCs compared to models using only intratumoral features. The choice of peritumoral size may impact the degree of improvement in radiomics analysis. Conclusions: The integration of peritumoral features has shown potential for improving the predictive value of radiomics. However, selecting an appropriate peritumoral region size is constrained by various factors such as clinical issues, imaging modalities, and ROI annotations. Therefore, future radiomics studies should consider these factors and optimize peritumoral features to cater to specific applications. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2023.

关键词： Tumors

来源：评论

学校读者我要写书评

暂无评论

Industry 4.0 Application in Manufacturing for Real-Time Monitoring and Control

引用

Journal of Dynamics, Monitoring and Diagnostics 2022年第3期1卷 176-187页

作者： Debasish Mishra Ashok Priyadarshi Sarthak M Das Sristi Shree Abhinav Gupta Surjya K Pal Debashish Chakravarty Advanced Technology Development Centre Indian Institute of Technology KharagpurKharagpurWest Bengal 721302India Mathematics and Computing Birla Institute of Technology MesraRanchiJharkhand 835215India Information Technology Birla Institute of Technology MesraRanchiJharkhand 835215India Computer Science and Engineering Birla Institute of Technology MesraRanchiJharkhand 835215India Electronics and Communication Engineering Birla Institute of Technology MesraRanchiJharkhand 835215India Department of Mechanical Engineering Indian Institute of Technology KharagpurKharagpurWest Bengal 721302India Department of Mining Engineering Indian Institute of Technology KharagpurKharagpurWest Bengal 721302India

Modern manufacturing aims to reduce downtime and track process anomalies to make profitable business *** ideology is strengthened by Industry 4.0,which aims to continuously monitor high-value manufacturing *** article builds upon the Industry 4.0 concept to improve the efficiency of manufacturing *** major contribution is a framework for continuous monitoring and feedback-based control in the friction stir welding(FSW)*** consists of a CNC manufacturing machine,sensors,edge,cloud systems,and deep neural networks,all working cohesively in real *** edge device,located near the FSW machine,consists of a neural network that receives sensory information and predicts weld quality in real *** addresses time-critical manufacturing *** receives the sensory data if weld quality is poor,and a second neural network predicts the new set of welding parameters that are sent as feedback to the welding *** experiments are conducted for training the neural *** framework successfully tracks process quality and improves the welding by controlling it in real *** system enables faster monitoring and control achieved in less than 1 *** framework is validated through several experiments.

关键词： cloud edge deep neural networks friction stir welding Industry 4.0 internet of things machine learning manufacturing process control process monitoring signal processing

来源：评论

学校读者我要写书评

暂无评论

Iterative Sound Source Localization for Unknown Number of Sources

arXiv

引用

arXiv 2022年

作者： Fu, Yanjie Ge, Meng Yin, Haoran Qian, Xinyuan Wang, Longbiao Zhang, Gaoyan Dang, Jianwu Tianjin Key Laboratory of Cognitive Computing and Application College of Intelligence and Computing Tianjin University Tianjin China Department of Electrical and Computer Engineering National University of Singapore Singapore Japan Advanced Institute of Science and Technology Ishikawa Japan

Sound source localization aims to seek the direction of arrival (DOA) of all sound sources from the observed multichannel audio. For the practical problem of unknown number of sources, existing localization algorithms attempt to predict a likelihood-based coding (i.e., spatial spectrum) and employ a pre-determined threshold to detect the source number and corresponding DOA value. However, these threshold-based algorithms are not stable since they are limited by the careful choice of threshold. To address this problem, we propose an iterative sound source localization approach called ISSL, which can iteratively extract each source's DOA without threshold until the termination criterion is met. Unlike threshold-based algorithms, ISSL designs an active source detector network based on binary classifier to accept residual spatial spectrum and decide whether to stop the iteration. By doing so, our ISSL can deal with an arbitrary number of sources, even more than the number of sources seen during the training stage. The experimental results show that our ISSL achieves significant performance improvements in both DOA estimation and source number detection compared with the existing threshold-based algorithms. Copyright © 2022, The Authors. All rights reserved.

关键词： Direction of arrival

来源：评论

学校读者我要写书评

暂无评论

CMUNEXT: An Efficient Medical Image Segmentation Network Based on Large Kernel and Skip Fusion

CMUNEXT: An Efficient Medical Image Segmentation Network Bas...

引用

IEEE International Symposium on Biomedical Imaging

作者： Fenghe Tang Jianrui Ding Quan Quan Lingtao Wang Chunping Ning S. Kevin Zhou School of Biomedical Engineering Division of Life Sciences and Medicine University of Science and Technology of China Hefei P.R. China Suzhou Institute for Advanced Research University of Science and Technology of China Suzhou P.R. China School of Computer Science and Technology Harbin Institute of Technology Harbin China Institute of Computing Technology Chinese Academy of Sciences (CAS) Beijing China Ultrasound Department The Affiliated Hospital of Qingdao University Qingdao China

ISBN: (数字)9798350313338

ISBN: (纸本)9798350313345

The u-shaped architecture has emerged as a crucial paradigm in the design of medical image segmentation networks. However, due to the inherent local limitations of convolution, a fully convolutional segmentation network with u-shaped architecture struggles to effectively extract global context information, which is vital for the precise localization of lesions. While hybrid architectures combining CNN and Transformer can address these issues, their applications are limited due to the computational resource. In addition, the inductive bias of convolution in lightweight networks adeptly fits the scarce medical data, which is lacking in the Transformer based network. To extract global context information while taking advantage of the inductive bias, we propose CMUNeXt, an efficient lightweight segmentation network, which leverages large kernel and inverted bottleneck design to thoroughly mix distant spatial and location information, efficiently extracting global context information. We also introduce the Skip-fusion block, designed to enable smooth skip-connections and ensure ample feature fusion. Experimental results demonstrate that CMUNeXt outperforms existing heavyweight and lightweight medical image segmentation networks, while offering a faster inference speed, lighter weights, and a reduced computational cost. The code is available at https://***/FengheTan9/CMUNeXt.

关键词： Location awareness Image segmentation Convolution computer architecture Transformers Computational efficiency Data mining

来源：评论

学校读者我要写书评

暂无评论

Self-Supervised Learning for Point Clouds Data: A Survey

arXiv

引用

arXiv 2023年

作者： Zeng, Changyu Wang, Wei Nguyen, Anh Yue, Yutao Institute of Deep Perception Technology JITRI Wuxi214000 China Department of Computing School of Advanced Technology Xi'an Jiaotong-Liverpool University Suzhou215123 China Department of Computer Science University of Liverpool LiverpoolL69 7ZX United Kingdom

3D point clouds are a crucial type of data collected by LiDAR sensors and widely used in transportation applications due to its concise descriptions and accurate localization. Deep neural networks (DNNs) have achieved remarkable success in processing large amount of disordered and sparse 3D point clouds, especially in various computer vision tasks, such as pedestrian detection and vehicle recognition. Among all the learning paradigms, Self-Supervised Learning (SSL), an unsupervised training paradigm that mines effective information from the data itself, is considered as an essential solution to solve the time-consuming and labor-intensive data labelling problems via smart pretraining task design. This paper provides a comprehensive survey of recent advances on SSL for point clouds. We first present an innovative taxonomy, categorizing the existing SSL methods into four broad categories based on the pretexts' characteristics. Under each category, we then further categorize the methods into more fine-grained groups and summarize the strength and limitations of the representative methods. We also compare the performance of the notable SSL methods in literature on multiple downstream tasks on benchmark datasets both quantitatively and qualitatively. Finally, we propose a number of future research directions based on the identified limitations of existing SSL research on point clouds. Copyright © 2023, The Authors. All rights reserved.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Simulate the Machine Learning Algorithm to Organize the CRAHN Network System

Simulate the Machine Learning Algorithm to Organize the CRAH...

引用

Advancement in Electronics & Communication Engineering (AECE), International Conference on

作者： P Prabakaran L. Chandra Sekhar Reddy LVD Ravikumar Manish Kumar Verma Department Of Computer Applications School of computing sciences Vels Institute of Science Technology and Advanced Studies Chennai India Department of CSE(Data Science) CMR College of Engineering & Technology Medchal Hyderabad India Department of Information Technology Shri Vishnu Engineering College For Women Bhimavaram India Department of Psychology Lovely Professional University Phagwara India

Using available channels in a wireless spectrum, cognitive radio (CR) may automatically adjust transmission settings to optimize radio operational behaviour. To function properly, a CR ad hoc network (CRAHN) has to be dynamically capable construct autonomous and decentralized networks without negatively impacting licensed main user (PU) systems. For this reason, an effective spectrum necessitates a system structure based on artificial intelligence. This research provides a model for network planning, learning, and dynamic configuration that is based on a distributed autonomous CRAHN network system that uses reinforcement learning. The proposed optimization techniques for spectrum sensing, ad hoc network design, and context-aware signal categorization are all derived from the system model and are based on machine learning. The cognitive and detection engines may be used to examine the spectrum utilization and neighbour network status in the immediate area. To adapt to the ever-changing nature of the wireless environment, the suggested policy engine may generate network operating policies, identify policy conflicts, and infer the best course of action. Together with the erudition engine, whereby apply the recommended machine-learning methods, the decision engine arrives at the best possible settings for the CRAHN. In addition, guarantee peaceful cohabitation with surrounding systems to have excellent signal context recognition ability.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Comparison of Edge computing Scheduling Algorithms

Comparison of Edge Computing Scheduling Algorithms

引用

Iberian Conference on Information Systems and Technologies (CISTI)

作者： Pedro S. Catali Aleardo Manacero Renata S. Lobato Roberta Spolon Marcos A. Cavenaghi Computer Science and Statistics Department São Paulo State University – UNESP São José do Rio Preto Brazil Computing Department São Paulo State University – UNESP Bauru Brazil Humber Institute of Technology and Advanced Learning Toronto Canada

Through the advancement of the Internet of Things (IoT), the development of devices for task automation, data extraction, and communication between devices has become increasingly easy. But as a result, tens of zettabytes of data are being generated every year, causing excessive bandwidth consumption as well as slow response times for devices. One of the ways to solve the problem is with the use of Edge computing networks, such paradigm allows the transfer of the data processing to the edges of the network. Since the Edge is mostly composed of devices of varied and limited computational capacity, a good way to distribute the tasks that must be processed is needed. Therefore, efficient, and well tested, scheduling algorithms are a way to distribute tasks in such a way that the time required to perform them is minimized. This work explores the comparison o three distinct scheduling algorithms in Edge computing: the Modified Monte Carlo Tree Search; the Improved Binary Grey Wolf Optmizer and the Application-aware Scheduling Algorithm, analyzing their speed and efficiency as an evaluation metric, using the iSPD grid simulator.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Quantum computing Society of the Philippines: An NGO Perspective on Promoting Quantum Information, science, and Technology in the Philippines

Quantum Computing Society of the Philippines: An NGO Perspec...

引用

Quantum computing and Engineering (QCE), IEEE International Conference on

作者： Dylan Josh Domingo Lopez Elmer Peramo Jabez Mendoza Ayson Angela Nicole S. Masongsong Lance Dominic C. Raquel Bobby O. Corpus Department of Computer Technology De La Salle University Manila Philippines Department of Science and Technology Advanced Science and Technology Institute Quezon City Philippines Electronics Engineering Department Don Honorio Ventura State University Pampanga Philippines STEM Department De La Salle University Integrated School Manila Philippines Department of Physics University of San Carlos Cebu City Philippines Quantum Computing Society of the Philippines Manila Philippines

ISBN: (数字)9798331541378

ISBN: (纸本)9798331541385

The development of Quantum Information science and Technology (QIST) as an emerging technology among developed and developing countries has caught the attention of governments, industries, and educational institutions. However, not all countries have equal starting points in promoting QIST amongst different sectors. Several players in various countries promote QIST as a discipline and education. Although significant developments in quantum technology are focused in Western countries, great innovation can also be seen in Eastern countries, specifically Asia. The Philippines is one of several developing countries in Asia that is in the process of adopting QIST in multiple sectors. In this paper, the Quantum computing Society of the Philippines (QCSP) is introduced as one of the arms of the country for promoting QIST to the public. Further in this paper, the initial impact of QIST promotion on various communities across the Philippines through multiple activities and educational efforts is explained. Several critical success stories for different audiences were described, wherein initial acceptance of QIST was evident through hackathons and lecture series. Events held show improvement in interest and proficiency in the foundations of QIST.

关键词： Industries Technological innovation Quantum computing Program processors Asia Government Education Developing countries Quantum information science Hackathon

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：