检索结果-内蒙古大学图书馆

2023 World Wide Web Conference, WWW 2023

作者： Wang, Kaibin He, Qiang Chen, Feifei Jin, Hai Yang, Yun School of Computer Science and Technology Huazhong University of Science and Technology China Department of Computing Technologies Swinburne University of Technology Australia School of Information Technology Deakin University Australia National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)9781450394161

Federated learning (FL) has been widely acknowledged as a promising solution to training machine learning (ML) model training with privacy preservation. To reduce the traffic overheads incurred by FL systems, edge servers have been included between clients and the parameter server to aggregate clients' local models. Recent studies on this edge-assisted hierarchical FL scheme have focused on ensuring or accelerating model convergence by coping with various factors, e.g., uncertain network conditions, unreliable clients, heterogeneous compute resources, etc. This paper presents our three new discoveries of the edge-assisted hierarchical FL scheme: 1) it wastes significant time during its two-phase training rounds;2) it does not recognize or utilize model diversity when producing a global model;and 3) it is vulnerable to model poisoning attacks. To overcome these drawbacks, we propose FedEdge, a novel edge-assisted hierarchical FL scheme that accelerates model training with asynchronous local federated training and adaptive model aggregation. Extensive experiments are conducted on two widely-used public datasets. The results demonstrate that, compared with state-of-the-art FL schemes, FedEdge accelerates model convergence by 1.14 × -3.20 ×, and improves model accuracy by 2.14% - 6.63%. © 2023 ACM.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

Development and modeling of advanced systems Na2SnBr6-based perovskite solar cells: a comprehensive study on electron transport layers

引用

Optics Express 2025年第10期33卷 21152-21172页

作者： Roy, Dipta Reza, M.D. Selim Ghosh, Avijit Roy, Anup Kumar Chowdhury, Bivash Ranjan Aktarujjaman, M.D. Alrafai, H.A. Hassan, Abeer A. Department of Electrical and Computer Engineering California State University at Northridge NorthridgeCA91330 United States Department of Electrical and Electronic Engineering Begum Rokeya University Rangpur5400 Bangladesh Phillip M. Drayer Department of Electrical and Computer Engineering Lamar University BeaumontTX77710 United States Department of Management Information System International American University Los AngelesCA90010 United States Department of Information Technology Management Webster University St. LouisMO63119 United States Department of Chemistry Faculty of Science King Khalid University PO Box 9004 Abha61413 Saudi Arabia

This study simulates a n-i-p planar heterojunction for Na2SnBr6-based perovskite solar cells (PSCs), with Na2SnBr6 as the absorber layer, fluorine-doped tin oxide (FTO) as the substrate, and In2S3, IGZO, and SnS2 as electron transport layers (ETLs). Gold (Au) is used as the back contact. Na2SnBr6 was chosen for its low cost, non-toxicity, tunable band gap, excellent electrical properties, and stability. The SCAPS-1D simulator was employed to model the solar cell performance under AM 1.5 G light irradiation, focusing on factors like doping concentration, layer thickness, defect density, and interface defects across three device configurations: Device I (Au/Na2SnBr6/ In2S3/FTO/Al), Device II (Au/ Na2SnBr6/IGZO/FTO/Al), and Device III (Au/ Na2SnBr6/SnS2/FTO/Al). Device III achieved the highest PCE of 31.35%, FF of 85.95%, VOC of 0.7926 V, and JSC of 46.01 mA/cm22, making it a promising candidate for high-efficiency, lead-free perovskite solar cells. Devices I and II showed lower efficiencies of 27.47% and 30.98%, respectively. The study also analyzed quantum efficiency (QE), carrier dynamics, and recombination rates, highlighting the potential of Device III in advancing Na2SnBr6-based hybrid perovskite solar technologies for future solar energy applications. © 2025 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement.

关键词： Semiconductor doping

来源：评论

学校读者我要写书评

暂无评论

ESNet: Evolution and Succession Network for High-Resolution Salient Object Detection 41

ESNet: Evolution and Succession Network for High-Resolution ...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Liu, Hongyu Cong, Runmin Li, Hua Xu, Qianqian Huang, Qingming Zhang, Wei Institute of Information Science Beijing Jiaotong University Beijing Key Laboratory of Advanced Information Science and Network Technology Beijing China School of Control Science and Engineering Shandong University Key Laboratory of Machine Intelligence and System Control Ministry of Education Jinan China School of Computer Science and Technology Hainan University Hainan China Key Laboratory of Intelligent Information Processing Institute of Computing Technology CAS Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China

Preserving details and avoiding high computational costs are the two main challenges for the High-Resolution Salient Object Detection (HRSOD) task. In this paper, we propose a two-stage HRSOD model from the perspective of evolution and succession, including an evolution stage with Low-resolution Location Model (LrLM) and a succession stage with High-resolution Refinement Model (HrRM). The evolution stage achieves detail-preserving salient objects localization on the low-resolution image through the evolution mechanisms on supervision and feature;the succession stage utilizes the shallow high-resolution features to complement and enhance the features inherited from the first stage in a lightweight manner and generate the final high-resolution saliency prediction. Besides, a new metric named Boundary-Detail-aware Mean Absolute Error (MAEBD) is designed to evaluate the ability to detect details in high-resolution scenes. Extensive experiments on five datasets demonstrate that our network achieves superior performance at real-time speed (49 FPS) compared to state-of-the-art methods. Our code is publicly available at: https://***/rmcong/ESNet_ICML24. Copyright 2024 by the author(s)

关键词： Miocene

来源：评论

学校读者我要写书评

暂无评论

Virtual Reality Technology in Peruvian Higher Education: Influence of University Tenure 13

Virtual Reality Technology in Peruvian Higher Education: Inf...

引用

13th International Conference on Virtual Campus, JICV 2023

作者： Vergara-Rodriguez, Diego Solis, Ronald Melgarejo Anton-Sancho, Alvaro Depaz, Carlos Edmundo Navarro Fernandez-Arias, Pablo Samala, Agariadne Dwinggo Ávila Spain Web Digital School University Department of Virtual Education Lima Peru San Marcos University Dept. System Engineering and Computer Science Lima Peru Universitas Negeri Padang Facuity of Engineering West Sumatera Padang Indonesia

ISBN: (纸本)9798350343441

The use of virtual reality (VR) technologies in higher education has been growing in recent years due to their didactic potential in the most diverse areas of knowledge. However, the implementation of VR in universities is affected by several factors, including the level of digitization of the country or the tenure, private or public, of the universities. In this paper, a quantitative, descriptive and correlational research is carried out on the assessments of a group of professors in Peru about the use of VR in their lectures and on the differences in these perceptions according to the tenure of the university of the participants. For this purpose, a validated questionnaire was used, and its responses were statistically analyzed. The results reveal that professors express high ratings for the use of VR but show insufficient levels of digital skills for its use. In addition, professors from private universities give higher ratings of the didactic and usability aspects of VR. It is suggested that VR equipment and faculty training should be strengthened. © 2023 IEEE.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

Invertible Mosaic Image Hiding Network for Very Large Capacity Image Steganography

Invertible Mosaic Image Hiding Network for Very Large Capaci...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Zihan Chen Tianrui Liu Jun-Jie Huang Wentao Zhao Xing Bi Meng Wang College of Computer Science and Technology National University of Defense Technology China College of System Engineering National University of Defense Technology China School of Computer Science and Information Engineering Hefei University of Technology China

The existing image steganography methods either sequentially conceal secret images or conceal a concatenation of multiple images. In such ways, the interference of information among multiple images will become increasingly severe when the number of secret images becomes larger, thus restrict the development of very large capacity image steganography. In this paper, we propose an Invertible Mosaic Image Hiding Network (InvMIHNet) which realizes very large capacity image steganography with high quality by concealing a single mosaic secret image. InvMIHNet consists of an Invertible Image Rescaling (IIR) module and an Invertible Image Hiding (IIH) module. The IIR module works for downscaling the single mosaic secret image form by spatially splicing the multiple secret images, and the IIH module then conceal this mosaic image under the cover image. The proposed InvMIHNet successfully conceal and reveal up to 16 secret images with a small number of parameters and memory consumption. Extensive experiments on ImageNet-1K, COCO and DIV2K show InvMIHNet outperforms state-of-the-art methods in terms of both the imperceptibility of stego image, recover accuracy of secret image and security against steganlysis methods. The code is available at https://***/Brittany-Chen/InvMIHNet.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Adversarial Learning Under Hybrid Perturbations for Robust Acute Lymphoblastic Leukemia Classification 39

Adversarial Learning Under Hybrid Perturbations for Robust A...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Chen, Jie Liu, Xinyuan Liu, Xintong Li, Jianqiang College of Computer Science and Software Engineering Shenzhen University China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China

ISBN: (纸本)157735897X

Acute lymphoblastic leukemia is a childhood cancer prevalent worldwide, which can prove fatal within weeks or months. However, current diagnosis models based on machine learning and deep learning methods fail to consider device noise (pixel-level perturbations) and rotation/translation (spatial-transformed perturbations), which can undermine the model's robustness. Adversarial training is a potential solution to this issue. This paper presents a hybrid perturbation adversarial training (HPAT) strategy that leverages two types of adversarial samples: pixel-level adversarial samples and spatial adversarial samples. This work generates these hybrid adversarial samples through Projected Gradient Descent (PGD) in couple with spatial transformation based on the Bayesian optimization (STBO) algorithm, respectively. This work introduced the Mixed Batch Normalization (MixBN) module to handle both adversarial samples and clean samples, alleviating the problem of clean accuracy degradation due to adversarial training. The proposed hybrid adversarial training strategy is tested on the public acute lymphoblastic leukemia dataset and found that it outperformed existing acute lymphoblastic cell classification models. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Structure design and analysis of a rigid-soft robotic hand with large load capacity 3

Structure design and analysis of a rigid-soft robotic hand w...

引用

3rd International Conference on Electrical, Electronics, and Information engineering, EEIE 2024

作者： Wu, Peichen Lan, Fuming Hong, Wen Chen, Xiaoping Shuai, Wei Cui, Guowei Gao, Yang Institute of Intelligent Manufacturing Guangdong Academy of Sciences Guangdong Key Laboratory of Modern Control Technology Guangzhou510070 China Shanghai Institute of Aerospace System Engineering Shanghai201100 China Intelligent Manufacturing Institute of HFUT HeFei230041 China School of Computer Science and Technology University of Science and Technology of China Hefei230026 China

ISBN: (纸本)9781510688179

In recent years, soft grippers have gained significant attention due to their adaptability and safety. However, when performing horizontal object grasping, their limited structural stiffness prevents them from withstanding the torque generated by friction between the gripper and the object, leading to a loss of contact and limiting their horizontal load capacity. To address this limitation while preserving the adaptability of soft grippers, this paper proposes a gripper structure called the rigid-soft robotic hand, which incorporates lateral rigid connecting rods outside the soft joints. The paper analyzes the bending capacity of the rigid-soft joint using kinematic methods and investigates the influence of link design parameters on maximum bending angle. Subsequently, a finite element analysis is conducted to study the finger structure with the added connecting rods, aiming to optimize the link design parameters. Experimental results demonstrate the grasping capabilities of the rigid-soft gripper in both vertical and horizontal orientations. The findings show that the rigid-soft gripper significantly improves the load-carrying capacity during horizontal object grasping while maintaining the adaptability of the soft gripper. © The Authors.

关键词： Robotic arms

来源：评论

学校读者我要写书评

暂无评论

Toward Reliable Nanosatellite Missions: A Novel Graph Neural Network Framework for Fault and Anomaly Detection via Single Event Effect

Toward Reliable Nanosatellite Missions: A Novel Graph Neural...

引用

International Conference on Electrical, computer and Communication engineering (ECCE)

作者： Sara Karim Takia Sultana Nova Sohana Tasneem Department of Space System Engineering Bangladesh Aviation and Aerospace University Bangladesh Department of Computer Science and Engineering International Islamic University Chittagong Chattogram Bangladesh

ISBN: (数字)9798350357509

ISBN: (纸本)9798350357516

As nanosatellites play a critical role in scientific research, Earth observation, and communication, their vulnerability to space radiation is a substantial risk. Specifically Single Event Effect, caused by high-energy particles, can lead to data corruption, hardware malfunctions, and potentially mission-critical failures. Traditional SEE mitigation techniques such as radiation-hardened electronics and redundancy systems, although effective, are often infeasible for nanosatellites due to limitations in size, weight, and cost. Our proposed GNNsee algorithm addresses this gap by leveraging the power of GNNs to model complex interactions between nanosatellite subsystems, enabling real-time detection and prediction of SEE-induced faults and anomalies. Unlike conventional machine learning models that struggle to capture the interconnected nature of nanosatellite components, GNNs inherently represent these relationships, allowing for more accurate prediction of potential failures. Our approach integrates a fault detection mechanism and an anomaly detection system, which monitor the behavior of subsystems to proactively identify and respond to *** extensive testing, GNNsee achieved a prediction accuracy of 75%, demonstrating its effectiveness in mitigating SEE-related disruptions in space environments. This research contributes a scalable and cost-effective framework to improve nanosatellite resilience, reduce mission risks, and extend satellite lifespans. By advancing the predictive capabilities for SEEs, GNNsee sets a new standard in ensuring data integrity and operational reliability for nanosatellites operating in harsh space conditions.

关键词： Adaptation models Accuracy Data integrity Computational modeling Small satellites Predictive models Prediction algorithms Graph neural networks Real-time systems Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Container lifecycle-aware scheduling for serverless computing

Container lifecycle-aware scheduling for serverless computin...

引用

作者： Wu, Song Tao, Zhiheng Fan, Hao Huang, Zhuo Zhang, Xinmin Jin, Hai Yu, Chen Cao, Chun National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China State Key Laboratory for Novel Software Technology Department of Computer Science and Technology Nanjing University Nanjing China

Elastic scaling in response to changes on demand is a main benefit of serverless computing. When bursty workloads arrive, a serverless platform launches many new containers and initializes function environments (known as cold starts), which incurs significant startup latency. To reduce cold starts, platforms usually pause a container after it serves a request, and reuse this container for subsequent requests. However, this reuse strategy cannot efficiently reduce cold starts because the schedulers are agnostic of container lifecycle. For example, it may ignore soon available containers or evict soon needed containers. We propose a container lifecycle-aware scheduling strategy for serverless computing, CAS. The key idea is to control distribution of requests and determine creation or eviction of containers according to different lifecycle phases of containers. We implement a prototype of CAS on OpenWhisk. Our evaluation shows that CAS reduces 81% cold starts and therefore brings a 63% reduction at 95th percentile latency compared with native scheduling strategy in OpenWhisk when there is worker contention between workloads, and does not add significant performance overhead. © 2021 John Wiley & Sons Ltd.

关键词： Containers

来源：评论

学校读者我要写书评

暂无评论

Packet Format Detection and Modulation Classification of Wireless LAN Using Distributed Convolutional Neural Network

Packet Format Detection and Modulation Classification of Wir...

引用

2021 International Symposium on Intelligent Signal Processing and Communication systems, ISPACS 2021

作者： Putra, Dody Ichwana Pratama, Muhammad Harry Bintang Lanante, Leonardo Grad, Hiroshi Ochi Kyushu Institute of Technology School of Computer Science and System Engineering Iizuka Japan

ISBN: (纸本)9781665419512

This paper proposes a method to detect the packet format and classify signal modulation type of wireless LAN signals using the distributed model of Convolutional Neural Network (CNN). The main advantages of this method compared to the conventional are the high accuracy of the model and the flexibility for lowering the complexity. These are achieved because the CNN models are trained to perform multiple small classification tasks instead of a single big classification task. This method makes retraining much easier. The five-fold cross-validation is applied to assess the performance for training and testing the model. To validate the model, actual Wi-Fi signals are used to test the model using Software Define Radio (SDR). The result shows the proposed method can accurately classify different packet formats and signal modulation types above 90%, even when different timing offsets occur. © 2021 IEEE.

关键词： Orthogonal frequency division multiplexing

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：