检索结果-内蒙古大学图书馆

Communications and Information Technologies (GCCIT), Global Conference on

作者： V Y John N. N. Wasatkar K. Yuvaraj Shubhansh Bansal A.S. Valarmathy Shitij Goyal School of Mangement - PG Management JAIN (Deemed to be University) Bangalore Karnataka Computer Engineering Vishwakarma Institute of Technology Pune Department of Computer Science Karpagam Academy of Higher Education Coimbatore Centre of Research Impact and Outcome Chitkara University Rajpura Punjab India Department of Electrical and Electronics Engineering Prince Shri Venkateshwara Padmavathy Engineering College Chennai Quantum University Research Center Quantum University Roorkee Uttarakhand India

ISBN: (数字)9798350388916

ISBN: (纸本)9798350388923

In the traditional text classification technique, values are read as letters, which destroys the original semantic illustration of numerical attributes. Completely mining deeper latent semantics features in agricultural literature requires a novel text classification technique that makes use of multivariate characteristic dynamic fusion. The global principal semantic components of the text were extracted using the Bi-Convolutional Neural Networks (CNNs) system using an attention mechanism, and the local semantic information was extracted using the Multiple Window Convolutional Neural Network. When classifying textual content based on phenotypic quantitative categories, the deep semantic portrayal of agricultural texts may be significantly enhanced by using the attention strategy to dynamically merge the obtained various semantic features.

关键词： Resistance Semantics Text categorization Neural networks Feature extraction Data models Information and communication technology Data mining Convolutional neural networks Kernel

来源：评论

学校读者我要写书评

暂无评论

Incentive-compatible diffusion auctions 29

Incentive-compatible diffusion auctions

引用

29th International Joint Conference on Artificial Intelligence, IJCAI 2020

作者： Li, Bin Hao, Dong Zhao, Dengji School of Computer Science and Engineering University of Electronic Science and Technology of China China Shanghai Engineering Research Center of Intelligent Vision and Imaging ShanghaiTech University China

ISBN: (纸本)9780999241165

Diffusion auction is a new model in auction design. It can incentivize the buyers who have already joined in the auction to further diffuse the sale information to others via social relations, whereby both the seller's revenue and the social welfare can be improved. Diffusion auctions are essentially nontypical multidimensional mechanism design problems and agents' social relations are complicatedly involved with their bids. In such auctions, incentive-compatibility (IC) means it is best for every agent to honestly report her valuation and fully diffuse the sale information to all her neighbors. Existing work identified some specific mechanisms for diffusion auctions, while a general theory characterizing all incentive-compatible diffusion auctions is still missing. In this work, we identify a sufficient and necessary condition for all dominant-strategy incentive-compatible (DSIC) diffusion auctions. We formulate the monotonic allocation policies in such multidimensional problems and show that any monotonic allocation policy can be implemented in a DSIC diffusion auction mechanism. Moreover, given any monotonic allocation policy, we obtain the optimal payment policy to maximize the seller's revenue. © 2020 Inst. Sci. inf., Univ. Defence in Belgrade. All rights reserved.

关键词： Diffusion

来源：评论

学校读者我要写书评

暂无评论

Autonomic Faulty Node Replacement in UAV-Assisted Wireless Sensor Networks: a Test-bed

Autonomic Faulty Node Replacement in UAV-Assisted Wireless S...

引用

Consumer Communications and Networking Conference, CCNC IEEE

作者： Leonardo Montecchiari Angelo Trotta Luciano Bononi Marco Di Felice Enrico Natalizio Department of Computer Science and Engineering University of Bologna Italy Technology Innovation Institute (TII) United Arab Emirates Advanced Research Center on Electronic Systems “Ercole De Castro” University of Bologna Italy

Several use-cases of the Internet of Things (IoT) rely on the development of large-scale Wireless Sensor Networks (WSNs) in harsh environments characterized by limited Internet connectivity and battery-powered operations. In such scenarios, the failure of a single node due to energy depletion or hardware issues may cause network partitions and disrupt partially or completely the system operations until the intervention of a human operator. In this paper, we investigate the usage of Unmanned Aerial Networks (UAVs) to enable sensory data collection and support resilient communications in presence of faulty sensor nodes. More specifically, we study the possibility of replacing the ground devices with UAVs which are able to temporarily restore the multi-hop communication towards the WSN sink. To this aim, we extended the Uhura framework, a platform for robotic networking, with novel features for automatic network partition detection and UAV-sink coordination. Then, we created a small test-bed composed of a Bluetooth Mesh WSN and one drone, and characterized the performance of the UAV-assisted WSN system in terms of packet delivery ratio of the end-to-end data flows.

关键词： Wireless sensor networks Systems operation Robot kinematics Spread spectrum communication Data collection Robot sensing systems Feature extraction

来源：评论

学校读者我要写书评

暂无评论

A Norm Regularization Training Strategy for Robust Image Quality Assessment Models

引用

International Journal of computer vision 2025年 1-15页

作者： Liu, Yujia Yang, Chenxi Li, Dingquan Jiang, Tingting Huang, Tiejun School of Computer Science Peking University Beijing China National Key Laboratory for Multimedia Information Processing Peking University Beijing China National Engineering Research Center of Visual Technology Peking University Beijing China School of Mathematical Sciences Peking University Beijing China Department of Networked Intelligence Pengcheng Laboratory Shenzhen China

Image Quality Assessment (IQA) models predict the quality score of input images. They can be categorized into Full-Reference (FR-) and No-Reference (NR-) IQA models based on the availability of reference images. These models are essential for performance evaluation and optimization guidance in the media industry. However, researchers have observed that introducing imperceptible perturbations to input images can notably influence the predicted scores of both FR- and NR-IQA models, resulting in inaccurate assessments of image quality. This phenomenon is known as adversarial attacks. In this paper, we initially define attacks targeted at both FR-IQA and NR-IQA models. Subsequently, we introduce a defense approach applicable to both types of models, aimed at enhancing the stability of predicted scores and boosting the adversarial robustness of IQA models. To be specific, we present theoretical evidence showing that the magnitude of score changes is related to the $$\ell _1$$ norm of the model’s gradient with respect to the input image. Building upon this theoretical foundation, we propose a norm regularization training strategy aimed at reducing the $$\ell _1$$ norm of the gradient, thereby boosting the robustness of IQA models. Experiments conducted on three FR-IQA and four NR-IQA models demonstrate the effectiveness of our strategy in reducing score changes in the presence of adversarial attacks. To the best of our knowledge, this work marks the first attempt to defend against adversarial attacks on both FR- and NR-IQA models. Our study offers valuable insights into the adversarial robustness of IQA models and provides a foundation for future research in this area.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A BLE Mesh Edge Framework for QoS-Aware IoT Monitoring Systems

A BLE Mesh Edge Framework for QoS-Aware IoT Monitoring Syste...

引用

IEEE World Forum on Internet of Things (WF-IoT)

作者： Leonardo Montecchiari Angelo Trotta Ivan D. Zyrianoff Luciano Bononi Enrico Natalizio Marco Di Felice Technology Innovation Institute (TII) United Arab Emirates Department of Computer Science and Engineering University of Bologna Italy Advanced Research Center on Electronic Systems “Ercole De Castro” University of Bologna Italy

ISBN: (数字)9798350311617

ISBN: (纸本)9798350311624

Internet of Things (IoT) monitoring applications of-ten require a flexible network design to continuously adjust device configurations and meet Quality of Service (QoS) requirements effectively. In this paper, we provide evidence of this concept in the context of the Bluetooth Low Energy (BLE) Mesh network, where performance heavily relies on tuning various network parameters. Our contributions in this study are threefold. First, we present a software framework designed for BLE Mesh monitoring, QoS metrics computation, and QoS-aware parameter selection. This framework operates on an edge device connected to the BLE gateway, enabling efficient data gathering and decision-making. Second, we propose a Reinforcement Learning (RL) algorithm to determine the optimal BLE Mesh parameters, allowing for the simultaneous fulfillment of multiple QoS requirements. Through the RL technique, we can dynamically adapt network configurations to varying conditions and demands. Third, we conduct thorough validation of our framework on a real-world BLE Mesh test-bed, demonstrating the effectiveness of the proposed technique in network performance enhancement. The results show the ability to maximize Packet Delivery Ratio (PDR), minimize delay, or determine a suitable trade-off between these two metrics, depending on the specific user's needs.

关键词： Performance evaluation Mesh networks Software algorithms Quality of service Reinforcement learning Logic gates Software

来源：评论

学校读者我要写书评

暂无评论

Predicting optical properties of NiO films fabricated by RF magnetron sputtering: A machine learning approach

引用

Optik 2025年 321卷

作者： Yüksek, Ahmet Gürkan Horoz, Sabit Altuntaş, İsmail Demır, İlkay Tüzemen, Ebru Ş. Nanophotonics Research and Application Center Sivas Cumhuriyet University Sivas58140 Turkey Computer Engineering Department Sivas Cumhuriyet University Sivas58140 Turkey Department of Fundamental Engineering Sciences Sivas University of Science and Technology Sivas58140 Turkey Department of Nanotechnology Engineering Sivas Cumhuriyet University Sivas58140 Turkey Department of Physics Sivas Cumhuriyet University Sivas58140 Turkey

NiO films with different thicknesses (100, 150, 200, 250, 300 and 400 nm) were grown on glass substrates using the RF Magnetron sputtering method and their optical transmittance properties were analysed with a spectrophotometer. An innovative aspect of this work was the application of machine learning techniques used to derive new insights from experimental data. Four different machine learning algorithms -ANFIS, Artificial Neural Networks (ANN), Support Vector Machines (SVM) and Gaussian Process Regression (GPR)- were tested. While the models were trained using films of different thicknesses, a randomly selected 75 % of the whole dataset was used for model testing and the remaining 25 % of the films were used for testing the models. Among these, ANN and GPR models were found to be the most successful models. Using these models, the energy band gaps were estimated at 1 nm intervals and the values ranged from approximately 3.50 eV to 3.76 eV. © 2024 Elsevier GmbH

关键词： Magnetron sputtering

来源：评论

学校读者我要写书评

暂无评论

MMIL: A novel algorithm for disease associated cell type discovery

arXiv

引用

arXiv 2024年

作者： Craig, Erin Keyes, Timothy Sarno, Jolanda Zaslavsky, Maxim Nolan, Garry Davis, Kara Hastie, Trevor Tibshirani, Robert Department of Biomedical Data Science Stanford University United States Department of Statistics Stanford University United States M. Tettamanti Research Center Pediatric Clinic University of Milano Bicocca Italy Department of Computer Science Stanford University United States Department of Pathology Stanford University United States Department of Pediatrics Stanford University United States

Single-cell datasets often lack individual cell labels, making it challenging to identify cells associated with disease. To address this, we introduce Mixture Modeling for Multiple Instance Learning (MMIL), an expectation maximization method that enables the training and calibration of cell-level classifiers using patient-level labels. Our approach can be used to train e.g. lasso logistic regression models, gradient boosted trees, and neural networks. When applied to clinically-annotated, primary patient samples in Acute Myeloid Leukemia (AML) and Acute Lymphoblastic Leukemia (ALL), our method accurately identifies cancer cells, generalizes across tissues and treatment timepoints, and selects biologically relevant features. In addition, MMIL is capable of incorporating cell labels into model training when they are known, providing a powerful framework for leveraging both labeled and unlabeled data simultaneously. Mixture Modeling for MIL offers a novel approach for cell classification, with significant potential to advance disease understanding and management, especially in scenarios with unknown gold-standard labels and high dimensionality. Copyright © 2024, The Authors. All rights reserved.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

FogROS2-FT: Fault Tolerant Cloud Robotics

arXiv

引用

arXiv 2024年

作者： Chen, Kaiyuan Hari, Kush Chung, Trinity Wang, Michael Tian, Nan Juette, Christian Ichnowski, Jeffrey Ren, Liu Kubiatowicz, John Stoica, Ion Goldberg, Ken Department of Electrical Engineering and Computer Science United States Robert Bosch Research and Technology Center North America SunnyvaleCA United States Robotics Institute Carnegie Mellon University United States Department of Industrial Engineering and Operations Research United States University of California BerkeleyCA United States

— Cloud robotics enables robots to offload complex computational tasks to cloud servers for performance and ease of management. However, cloud compute can be costly, cloud services can suffer occasional downtime, and connectivity between the robot and cloud can be prone to variations in network Quality-of-Service (QoS). We present FogROS2-FT (Fault Tolerant) to mitigate these issues by introducing a multi-cloud extension that automatically replicates independent stateless robotic services, routes requests to these replicas, and directs the first response back. With replication, robots can still benefit from cloud computations even when a cloud service provider is down or there is low QoS. Additionally, many cloud computing providers offer low-cost "spot" computing instances that may shutdown unpredictably. Normally, these low-cost instances would be inappropriate for cloud robotics, but the fault tolerance nature of FogROS2-FT allows them to be used reliably. We demonstrate FogROS2-FT fault tolerance capabilities in 3 cloud-robotics scenarios in simulation (visual object detection, semantic segmentation, motion planning) and 1 physical robot experiment (scan-pick-and-place). Running on the same hardware specification, FogROS2-FT achieves motion planning with up to 2.2x cost reduction and up to a 5.53x reduction on 99 Percentile (P99) long-tail latency. FogROS2-FT reduces the P99 long-tail latency of object detection and semantic segmentation by 2.0x and 2.1x, respectively, under network slowdown and resource contention. Videos and code are available at https://***/view/fogros2-ft. © 2024, CC BY.

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

Diversity-Augmented Diffusion Network With LLM Assistance For Radiology Report Generation 25

Diversity-Augmented Diffusion Network With LLM Assistance Fo...

引用

Companion Proceedings of the ACM on Web Conference 2025

作者： Jieting Long Zhiyuan Li Jianan Fan Zhuonan Liang Ao Ma Henning Müller Weidong Cai School of Computer Science The University of Sydney Sydney NSW Australia Institute of Informatics The University of Applied Sciences Western Switzerland Sierre Switzerland Department of Radiology and Medical Informatics The University of Geneva Geneva Switzerland and The Sense Innovation and Research Center Sion & Lausanne Switzerland

ISBN: (纸本)9798400713316

Radiology report generation (RRG) is a demanding yet challenging task that involves producing multi-sentence diagnostic narratives, requiring long-form text with high diversity while addressing inherent data bias. Sentence-level diversity is therefore crucial for capturing varying diagnostic details across multiple regions of interest (ROIs) within a single report, yet it remains underexplored in the field. In this paper, we propose DADNET, a novel diffusion-based framework that leverages the inherent ability of diffusion models to generate diverse text. We make the first attempt to integrate large language models (LLMs) to bridge the inherent training-inference gap in diffusion models. Specifically, LLMs are used to draft a preliminary report, which is subsequently incorporated into the diffusion process to enhance report diversity. Additionally, we introduce a bias equalization technique using domain-specific priors to mitigate data distribution biases, improving the quality and reliability of generated reports under various scenarios. Experimental results demonstrate that DADNET outperforms existing approaches under the same non-autoregressive (NAR) mechanism and sets a new benchmark for diversity in RRG. This work underscores the importance of diversity in RRG and establishes DADNET as a pioneering framework for addressing this challenge with NAR methods.

关键词： diffusion model

来源：评论

学校读者我要写书评

暂无评论

Linking Multi-Scale Brain Connectivity with Vigilance, Working Memory, and Behavior in Adolescents

Linking Multi-Scale Brain Connectivity with Vigilance, Worki...

引用

IEEE International Symposium on Biomedical Imaging

作者： Prerana Bajracharya Ram Ballem Jiayu Chen Pablo Andrés-Camazón Nigar Khasayeva Vince Calhoun Jingyu Liu Armin Iraji Tri-Institutional Center for Translational Research in Neuroimaging and Data Science Atlanta USA Department of Computer Science Georgia State University Atlanta USA Institute of Psychiatry and Mental Health Hospital General Universitario Gregorio Marañón IiSGM CIBERSAM ISCIII School of Medicine Universidad Complutense Madrid Spain

ISBN: (数字)9798331520526

ISBN: (纸本)9798331520533

This study examines how multi-scale intrinsic connectivity networks (ICNs) relate to cognitive and behavioral functions in adolescents, focusing on attention/vigilance, working memory, and behavioral regulation. Leveraging the NeuroMark 2.2 multi-scale ICN template obtained from over 100,000 subjects, we obtained multi-scale ICNs from baseline resting-state fMRI data from the ABCD Study. For this study, we are interested in “the fronto-thalamo-cerebellar (FTC) circuitry” and choose the subdomains of Neuromark 2.2 that cover it: Cerebellar (CB), Subcortical - Extended Thalamic (SC-ET), Higher Cognition - Insular Temporal (HC-IT), and Higher Cognition - Frontal (HC-FR), previously identified as relevant to cognitive and behavioral functions. Employing a multivariate approach combining principal component analysis (PCA) and canonical correlation analysis (CCA), we examined associations between these multi-scale ICNs and cognitive-behavioral outcomes. Our findings revealed significant associations, particularly for one of the estimated canonical components, linking multi-scale ICNs to cognitive and behavioral measures across both discovery and replication sets. This connectivity pattern may serve as a potential marker for attention, working memory, and behavioral regulation, offering new insights into a wide spectrum of neurodevelopmental disorders including Attention-Deficit/Hyperactivity Disorder (ADHD).

关键词： Correlation Focusing Functional magnetic resonance imaging Biomedical measurement Regulation Cognition Stability analysis Circuit stability Principal component analysis Biomedical imaging

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：