检索结果-内蒙古大学图书馆

Medical Artificial Intelligence (MedAI), IEEE International Conference on

作者： Xing Zhang Yucan Guo Xiaolong Jin Haozhe Liang Saiping Guan School of Computer Science and Technology University of Chinese Academy of Sciences CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Institute of Systems Engineering Academy of Military Science

Existing works in event extraction typically extract event arguments within the sentence scope. However, besides the sentence level, events may also be naturally presented at the document level. A document-level event usually reflects, to some extent, the theme (i.e., the main content) of the document (e.g., electronic medical records and news articles), which is thus referred to as the thematic event. Thematic Event Extraction (TEE) aims to extract the arguments of thematic events. TEE faces a major challenge, i.e., the sparsity and dispersion of arguments, which means that the arguments of a thematic event are dispersed in different sentences of the document. To overcome this challenge, we propose an Event-related Sentence Detection based TEE model, called ESDTEE, which first detects the sentences related to the thematic event and then extracts the arguments only within these detected sentences using existing models. Extensive experiments with comprehensive analyses demonstrate the effectiveness of ESDTEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Digital Twin-Assisted data-Driven Optimization for Reliable Edge Caching in Wireless Networks

arXiv

引用

arXiv 2024年

作者： Zhang, Zifan Liu, Yuchen Peng, Zhiyuan Chen, Mingzhe Xu, Dongkuan Cui, Shuguang Department of Computer Science North Carolina State University RaleighNC27695 United States Department of Electrical and Computer Engineering Frost Institute for Data Science and Computing University of Miami Coral GablesFL33146 United States School of Science and Engineering The Chinese University of Hong Kong Shenzhen China

Optimizing edge caching is crucial for the advancement of next-generation (nextG) wireless networks, ensuring high-speed and low-latency services for mobile users. Existing data-driven optimization approaches often lack awareness of the distribution of random data variables and focus solely on optimizing cache hit rates, neglecting potential reliability concerns, such as base station overload and unbalanced cache issues. This oversight can result in system crashes and degraded user experience. To bridge this gap, we introduce a novel digital twinassisted optimization framework, called D-REC, which integrates reinforcement learning (RL) with diverse intervention modules to ensure reliable caching in nextG wireless networks. We first develop a joint vertical and horizontal twinning approach to efficiently create network digital twins, which are then employed by D-REC as RL optimizers and safeguards, providing ample datasets for training and predictive evaluation of our cache replacement policy. By incorporating reliability modules into a constrained Markov decision process, D-REC can adaptively adjust actions, rewards, and states to comply with advantageous constraints, minimizing the risk of network failures. Theoretical analysis demonstrates comparable convergence rates between DREC and vanilla data-driven methods without compromising caching performance. Extensive experiments validate that D-REC outperforms conventional approaches in cache hit rate and load balancing while effectively enforcing predetermined reliability intervention modules. Copyright © 2024, The Authors. All rights reserved.

关键词： Wireless networks

来源：评论

学校读者我要写书评

暂无评论

Resource Aware Multi-User Task Offloading In Mobile Edge computing

Resource Aware Multi-User Task Offloading In Mobile Edge Com...

引用

IEEE International Conference on Web Services (ICWS)

作者： Shunhui Ji Jiajia Li Huiying Jin Hai Dong Zhiyuan Ge Shuhan Yang Pengcheng Zhang Key Laboratory of Water Big Data Technology of Ministry of Water Resources Hohai University Nanjing China College of Computer Science and Software Engineering Hohai University Nanjing China School of Computer Science Nanjing University of Posts and Telecommunications Nanjing China School of Computing Technologies RMIT University Melbourne Australia

ISBN: (数字)9798350368550

ISBN: (纸本)9798350368567

Mobile edge computing (MEC) relies on offloading tasks to edge nodes to avoid delays and failures caused by local computing. However, developing efficient offloading decisions is challenging, as it involves addressing the intricacies of tasks and the instability of edge node resources(e.g. available computer resources, memory, and bandwidth). In this paper, we propose a novel approach to tackle the problem of task offloading. Our approach involves dividing tasks into smaller units and considering the correlations between these sub-tasks. To make optimal offloading decisions, we employ a deep reinforcement learning algorithm that takes into account user movement patterns and the availability of resources at edge nodes. Through simulations, we demonstrate that our proposed algorithm outperforms several existing algorithms in terms of offloading decisions. It effectively reduces task execution delays and energy costs. These findings highlight the potential of our approach in improving the performance of task offloading in MEC systems.

关键词： Multi-access edge computing Costs Correlation Web services Heuristic algorithms Image edge detection Prediction algorithms Dynamic scheduling Deep reinforcement learning Delays

来源：评论

学校读者我要写书评

暂无评论

Utilizing Web Scraping and Machine Learning for Improving Accuracy of Smartphone Price Prediction

Utilizing Web Scraping and Machine Learning for Improving Ac...

引用

Advances in data engineering and Intelligent computing Systems (ADICS), International Conference on

作者： V. Vasanth Kumar C. TamizhSelvan L. Manoharan R. Vishnu Sekhar V. Vinoth Kumar Department of Electronics and Communication Engineering Hindustan Institute of Technology and Science Chennai India Department of Data Science and Business Systems School of Computing SRM Institute of Science and Technology India Department of Computer Science and Engineering Hindustan Institute of Technology and Science Chennai India Department of Biotechnology Integrated Bioprocessing Laboratory School of Bioengineering SRM Institute of Science and Technology India

ISBN: (数字)9798350364828

ISBN: (纸本)9798350364835

Mobile prices play a pivotal role in determining their popularity amongst consumers and their competitive standing within the market. As customers consider their budget while evaluating a mobile phone's specifications and design, estimating the price beforehand becomes essential to cater to their needs and expectations. Hence, accurately forecasting mobile phone prices is a vital step in the product launch process to remain competitive and assess the market dynamics and competitors. The primary aim of this research is to determine the true market value of mobile phones. In this research, the dataset was extracted by means of utilizing a web scraping process from the flipkart website. The main objective of this research is to fetch the most recent dataset based on the most recent features. The extracted dataset is fitted into regression models such as linear regression, decision tree regressor, random forest regressor, KNN regressor, and gradient boosting regressor and performs the comparative analysis. The models are evaluated based on the mean absolute error metric.

关键词： Measurement Computational modeling Linear regression Predictive models Feature extraction Boosting data models

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Bayesian Modeling for FVC Prediction in Pulmonary Fibrosis and Low-Cost Spirometer Incorporating Internet of Things

Hierarchical Bayesian Modeling for FVC Prediction in Pulmona...

引用

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

作者： Sumithra M Sundari. S V. Deepa Nagaraj P Dhiliphan Rajkumar T S Magesh Kumar Department of Computer Science and Engineering School of Computing Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai India Department of Computer Science and Engineering School of Engineering and Technology Jeppiaar University Chennai India Department of Artificial Intelligence and Data Science Rajalakshmi Institute of Technology Chennai India Department of Computer Science and Engineering Kalasalingam Academy of Research and Education Virudhunagar India Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai India

ISBN: (数字)9798331516284

ISBN: (纸本)9798331516291

Lung disease remains a significant public health concern in India, with a rising prevalence attributed to various environmental and lifestyle factors. Recent statistics reveal that chronic obstructive pulmonary disease (COPD) affects approximately 57.8 million people in India, while pulmonary fibrosis accounts for a substantial portion of respiratory-related morbidity and mortality nationwide. Despite the growing prevalence, accurate lung function diagnosis and monitoring remain challenging, particularly in resource-constrained settings. This study presents a novel approach utilizing hierarchical Bayesian modelling in conjunction with low-cost IoT-based spirometry technology for predicting forced vital capacity (FVC) in pulmonary fibrosis patients. Leveraging real-time data from the Indian population,[7] [8] where respiratory diseases are prevalent, our research underscores the critical need for reliable and accessible spirometry measurements for effective disease management. We begin by elucidating the epidemiological landscape of lung disease in India, highlighting the alarming rates of COPD and pulmonary fibrosis. Recent studies suggest that when integrated into clinical practice, spirometry data can significantly improve diagnostic accuracy and treatment outcomes for respiratory conditions. Leveraging data from the Indian population, where respiratory diseases are prevalent, our research underscores the critical need for reliable and accessible spirometry measurements for effective disease management. Our proposed methodology integrates the YFS201 flow sensor with an ESP8266 microcontroller, providing a cost-effective solution for real-time measurement of airflow. Through hierarchical Bayesian modeling, we demonstrate the capability of our approach to accurately predict FVC in pulmonary fibrosis patients, thereby facilitating early detection and personalized treatment strategies. By incorporating spirometry data into clinical practice, our research aims to empow

关键词： Spirometry Adaptation models Accuracy Lungs Predictive models data models Real-time systems Bayes methods Monitoring Context modeling

来源：评论

学校读者我要写书评

暂无评论

Machine Vision-Driven Semantic Segmentation for Autonomous Navigation

Machine Vision-Driven Semantic Segmentation for Autonomous N...

引用

Applied Artificial Intelligence and computing (ICAAIC), International Conference on

作者： N. Bala Krishna K. Lokesh Dudekula Azmeer Vali Kanna Mahathi Koramatla Siva Kumar Gudisirayula Padmini Department of CSE(AI/ML) School of Computing Mohan Babu University Tirupati Andhra Pradesh India Department of Artificial Intelligence & Data Science Mother Theresa Institute of Engineering and Technology Palamaner Andhra Pradesh India Department of CSE Sree Vidyanikethan Engineering College(Autonomous) Tirupati Andhra Pradesh India

ISBN: (数字)9798350375190

ISBN: (纸本)9798350375206

One of the main roles played by real time image segmentation is to enhance and catalyse self driving cars that can accurately sense their surroundings due to in terms of proper functioning. The new model was proposed with a completely new image segmentation paradigm for enabling self-driving in real time. The deployment of deep learning techniques, accurate real-time object segmentation through a fusion of fully convolutional network (FCN) with multilevel pyramid analysis. FCN uses the input image for segmentation, and in return creates a map-based on pixel-wise classification from which we can get more detailed information about different objects present in the scene. This approach creates a very large FCN network that is combined with a multiscale pyramid architecture that process an image in multiple stages effectively collecting complex surroundings information to improve performance. The proposed method is then experimented on different data with a particular focus on challenging to adopt such infrastructure in order to achieve modern day results in terms of accuracy and real time performance.

关键词： Deep learning Accuracy Navigation Semantic segmentation Computer architecture Real-time systems Safety

来源：评论

学校读者我要写书评

暂无评论

Flow-Level Bandwidth Allocation on P4 Tofino Switch with In-Network DRL Inference

Flow-Level Bandwidth Allocation on P4 Tofino Switch with In-...

引用

International Conference on Artificial Intelligence in Information and Communication (ICAIIC)

作者： Muhammad Irfan Hang Hu Myung J. Lee Arslan Qadeer Yang G. Kim Kazi Ahmed Daiki Nobayashi Department of Electrical Engineering City College of New York New York NY USA School of Computing & Data Science Wentworth Institute of Technology Boston MA USA Department of Computer Engineering Technology NYCCT Brooklyn NY USA Department of Electrical & Computer Engineering Technology NYIT New York NY USA Department of Electrical and Electronic Engineering Kyushu Institute of Technology Fukuoka Japan

ISBN: (数字)9798331507022

ISBN: (纸本)9798331507039

The Software-Defined Networking (SDN) paradigm has significantly improved network efficiency by integrating machine learning (ML) capabilities into the control plane (CP). This integration allows adaptive management of network resources in response to dynamic traffic conditions. However, the significant geographical distance between the CP and data plane (DP) causes considerable round-trip latency, measured in milliseconds, which poses a major challenge to time-sensitive traffic. To address this challenge, our research proposes a novel in-network Reinforcement Learning (RL) inference framework. This framework extends programmability from the CP to the DP, enabling timely and precise control of network resources to meet the stringent Quality of Service (QoS) requirements of mission-critical applications. The in-network RL inference is implemented using match-action tables within the Protocol Independent Switch Architecture (PISA) framework in the DP and validated through hardware deployment of protocol-independent packet processors (P4). To allocate bandwidth precisely based on QoS requirements, a P4 meter extern is used to differentiate the unique demands of individual traffic flows. Our enhanced deep-deterministic policy gradient (eDDPG)-based RL inference achieves superior performance with minimal processing overhead, reducing latency by 88.7% and jitter by 89.1 % compared to systems without RL inference.

关键词： Protocols Program processors Process control Switches Quality of service Reinforcement learning Channel allocation Jitter Network resource management Software defined networking

来源：评论

学校读者我要写书评

暂无评论

From Missing Pieces to Masterpieces: Image Completion with Context-Adaptive Diffusion

arXiv

引用

arXiv 2025年

作者： Shamsolmoali, Pourya Zareapoor, Masoumeh Zhou, Huiyu Felsberg, Michael Tao, Dacheng Li, Xuelong Department of Computer Science University of York University of UK SCEE East China Normal University China Department of Electrical Engineering Shanghai Jiao Tong University China School of Computing and Mathematical Sciences University of Leicester United Kingdom Computer Vision Laboratory Linkoping University Sweden College of Computing and Data Science Nanyang Technological University Singapore of China Telecom China

Image completion is a challenging task, particularly when ensuring that generated content seamlessly integrates with existing parts of an image. While recent diffusion models have shown promise, they often struggle with maintaining coherence between known and unknown (missing) regions. This issue arises from the lack of explicit spatial and semantic alignment during the diffusion process, resulting in content that does not smoothly integrate with the original image. Additionally, diffusion models typically rely on global learned distributions rather than localized features, leading to inconsistencies between the generated and existing image parts. In this work, we propose ConFill, a novel framework that introduces a Context-Adaptive Discrepancy (CAD) model to ensure that intermediate distributions of known and unknown regions are closely aligned throughout the diffusion process. By incorporating CAD, our model progressively reduces discrepancies between generated and original images at each diffusion step, leading to contextually aligned completion. Moreover, ConFill uses a new Dynamic Sampling mechanism that adaptively increases the sampling rate in regions with high reconstruction complexity. This approach enables precise adjustments, enhancing detail and integration in restored areas. Extensive experiments demonstrate that ConFill outperforms current methods, setting a new benchmark in image completion. © 2025, CC BY-SA.

关键词： Photointerpretation

来源：评论

学校读者我要写书评

暂无评论

UniTSFace: unified threshold integrated sample-to-sample loss for face recognition 23

UniTSFace: unified threshold integrated sample-to-sample los...

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Qiufu Li Xi Jia Jiancan Zhou Linlin Shen Jinming Duan National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China and Computer Vision Institute Shenzhen University China and SZU Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China and Computer Vision Institute Shenzhen University China and School of Computer Science University of Birmingham UK National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China and Computer Vision Institute Shenzhen University China and Aqara Lumi United Technology Co. Ltd China School of Computer Science University of Birmingham UK and Alan Turing Institute UK

Sample-to-class-based face recognition models can not fully explore the cross-sample relationship among large amounts of facial images, while sample-to-sample-based models require sophisticated pairing processes for training. Furthermore, neither method satisfies the requirements of real-world face verification applications, which expect a unified threshold separating positive from negative facial pairs. In this paper, we propose a unified threshold integrated sample-to-sample based loss (USS loss), which features an explicit unified threshold for distinguishing positive from negative pairs. Inspired by our USS loss, we also derive the sample-to-sample based softmax and BCE losses, and discuss their relationship. Extensive evaluation on multiple benchmark datasets, including MFR, IJB-C, LFW, CFP-FP, AgeDB, and MegaFace, demonstrates that the proposed USS loss is highly efficient and can work seamlessly with sample-to-class-based losses. The embedded loss (USS and sample-to-class Softmax loss) overcomes the pitfalls of previous approaches and the trained facial model UniTSFace exhibits exceptional performance, outperforming state-of-the-art methods, such as CosFace, ArcFace, VPL, AnchorFace, and UNPG. Our code is available at https://***/CVI-SZU/UniTSFace.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Automatic and Robust Segmentation of Multiple Sclerosis Lesions with Convolutional Neural Networks

引用

Computers, Materials & Continua 2021年第1期66卷 977-991页

作者： H.M.Rehan Afzal Suhuai Luo Saadallah Ramadan Jeannette Lechner-Scott Mohammad Ruhul Amin Jiaming Li M.Kamran Afzal M.Kamran Afzal School of Electrical Engineering and Computing University of NewcastleCallaghanNSW 2308Australia Hunter Medical Research Institute New Lambton HeightsNSW 2305Australia Department of Neurology John Hunter HospitalNew Lambton HeightsNSW 2305Australia CSIRO Data61 MarsfieldNSW 2122Australia School of Computer Science and Technology Xiamen UniversityXiamen361005China

The diagnosis of multiple sclerosis(MS)is based on accurate detection of lesions on magnetic resonance imaging(MRI)which also provides ongoing essential information about the progression and status of the *** detection of lesions is very time consuming and lacks *** of the lesions are difficult to detect manually,especially within the grey *** paper proposes a novel and fully automated convolution neural network(CNN)approach to segment *** proposed system consists of two 2D patchwise CNNs which can segment lesions more accurately and *** first CNN network is implemented to segment lesions accurately,and the second network aims to reduce the false positives to increase *** system consists of two parallel convolutional pathways,where one pathway is concatenated to the second and at the end,the fully connected layer is replaced with *** routine MRI sequences T1-w,T2-w and FLAIR are used as input to the CNN,where FLAIR is used for segmentation because most lesions on MRI appear as bright regions and T1-w&T2-w are used to reduce MRI *** evaluated the proposed system on two challenge datasets that are publicly available from MICCAI and *** and qualitative evaluation has been performed with various metrics like false positive rate(FPR),true positive rate(TPR)and dice similarities,and were compared to current state-of-the-art *** proposed method shows consistent higher precision and sensitivity than other *** proposed method can accurately and robustly segment MS lesions from images produced by different MRI scanners,with a precision up to 90%.

关键词： Multiple sclerosis lesion segmentation automatic segmentation CNN automated tool lesion detection

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：