检索结果-内蒙古大学图书馆

GroPipe: A Grouped Pipeline Hybrid Parallel Method for Accelerating DCNNs Training

学校读者我要写书评

暂无评论

IEEE Transactions on computers 2025年第7期74卷 2487-2500页

作者： Liu, Bin Ma, Yongyao Hu, Zijian Ji, Zeyu He, Zhenli Li, Keqin Northwest A&F University College of Information Engineering Shaanxi Yangling712100 China Shaanxi Engineering Research Center of Agricultural Information Intelligent Perception and Analysis Shaanxi Key Laboratory of Agricultural Information Perception and Intelligent Service Key Laboratory of Agricultural Internet of Things Ministry of Agriculture and Rural Affairs China Yunnan University Yunnan Key Laboratory of Software Engineering Kunming650091 China Yunnan University School of Software Kunming650091 China State University of New York Department of Computer Science New PaltzNY12561 United States

Training large Deep Convolutional Neural Networks (DCNNs) with increasingly large datasets to improve model accuracy has become extremely time-consuming. Distributed training methods, such as data parallelism (DP) and pipeline model parallelism (PMP), offer potential solutions but face challenges like load imbalance and significant communication overhead. This paper introduces GroPipe, a novel architecture that synergistically integrates PMP and DP, markedly improving training speeds. GroPipe employs an automatic model partitioning algorithm based on a performance projection technique, ensuring load balance and facilitating quantitative performance evaluation in PMP. Additionally, it adopts a group-based delayed asynchronous communication strategy to efficiently reduce communication overhead in DP. Using the ResNet and VGG models with the ImageNet dataset, extensive experiments are performed on an 8-GPU server and demonstrate GroPipe’s effectiveness. GroPipe achieves substantial improvements in time to accuracy, showing an average improvement of 42.2% and 14.0% on the ResNet series, and 79.2% and 43.9% on the VGG series, without compromising Top-1 accuracy. © 1968-2012 IEEE.

关键词： Deep convolutional neural networks Delayed asynchronous communication Hybrid parallelism Pipelined model parallelism

An integrated GIS-based multivariate adaptive regression splines-cat swarm optimization for improving the accuracy of wildfire susceptibility mapping

学校读者我要写书评

暂无评论

Geocarto International 2023年第1期38卷

作者： Hai, Tao Theruvil Sayed, Biju Majdi, Ali Zhou, Jincheng Sagban, Rafid Band, Shahab S. Mosavi, Amir School of Computer and Information Qiannan Normal University for Nationalities Guizhou Duyun China Key Laboratory of Complex Systems and Intelligent Optimization of Guizhou Guizhou Duyun China Institute for Big Data Analytics and Artificial Intelligence (IBDAAI) Universiti Teknologi MARA Selangor Shah Alam Malaysia Department of Computer Science Dhofar University Salalah Oman Department of Building and Construction Technologies Engineering Al-Mustaqbal University College Hilla Iraq Department of Computer Technology Engineering Technical Engineering College Al-Ayen University Thi-Qar Iraq Future Technology Research Center National Yunlin University of Science and Technology Yunlin Douliou Taiwan John von Neumann Faculty of Informatics Obuda University Budapest Hungary German Research Center for Artificial Intelligence Oldenburg Germany Institute of the Information Society University of Public Service Budapest Hungary

A hybrid machine learning method is proposed for wildfire susceptibility mapping. For modeling a geographical information system (GIS) database including 11 influencing factors and 262 fire locations from 2013 to 2018 is used for developing an integrated multivariate adaptive regression splines (MARS). The cat swarm optimization (CSO) algorithm tunes the parameters of the MARS in order to generate accurate susceptibility maps. From the Pearson correlation results, it is observed that land use, temperature, and slope angle have strong correlation with the fire severity. The results demonstrate that the prediction capability of the MARS-CSO model outperforms model tree, reduced error pruning tree and MARS. The resulting wildfire risk map using MARS-CSO reveals that 20% of the study areas is categorized in the very low wildfire risk class, whereas 40% is under the very high class of fire hazard. © 2023 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group.

关键词： artificial intelligence cat swarm optimization geospatial machine learning natural hazard Wildfire susceptibility

A Fuzzy Rule-Based Control System for Fast Line-Following Robots

学校读者我要写书评

暂无评论

A Fuzzy Rule-Based Control System for Fast Line-Following Ro...

International Conference on Distributed Computing in Sensor systems (DCOSS)

作者： G. Eleftheriou L. Doitsidis Z. Zinonos S. A. Chatzichristofis Department of Computer Science Intelligent Systems Laboratory Neapolis University Pafos Cyprus School of Production Engineering and Management Technical University of Crete Greece

ISBN: (数字)9781728143514

ISBN: (纸本)9781728198040

This paper focuses on the optimization of the line-tracking and following control technique used in high speed autonomous movable IoT devices such as line-following robotic vehicles. A fusion of a new pro-active / feed-forward control system, based on the simultaneous use of computer vision and the use of an array of analog infrared reflective phototransistors with an optimised PID based feed-back implementation is proposed. Experimental evaluations demonstrate that the proposed approach aids and improves the performance of line-following robots compared to the traditional PID technique.

关键词： Robot sensing systems Fuzzy logic Cameras Navigation Robustness Mobile robots

Outage Performance and Optimal Design of MIMO-NOMA Enhanced Small Cell Networks With Imperfect Channel-State Information

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Shi, Zheng Wang, Hong Fu, Yaru Yang, Guanghua Ma, Shaodan Ye, Xinrong School of Intelligent Systems Science and Engineering Jinan University Zhuhai519070 China State Key Laboratory of Internet of Things for Smart City University of Macau 999078 China School of Communication and Information Engineering Nanjing University of Posts and Telecommunications Nanjing210003 China National Mobile Communications Research Laboratory Southeast University Nanjing210096 China School of Science and Technology The Open University of Hong Kong Hong Kong State Key Laboratory of Internet of Things for Smart City and the Department of Electrical and Computer Engineering University of Macau 999078 China School of Physics and Electronic Information Anhui Normal University Wuhu241002 China

This paper focuses on boosting the performance of small cell networks (SCNs) by integrating multiple-input multiple-output (MIMO) and non-orthogonal multiple access (NOMA) in consideration of imperfect channel-state information (CSI). The estimation error and the spatial randomness of base stations (BSs) are characterized by using Kronecker model and Poisson point process (PPP), respectively. The outage probabilities of MIMO-NOMA enhanced SCNs are first derived in closed-form by taking into account two grouping policies, including random grouping and distance-based grouping. It is revealed that the average outage probabilities are irrelevant to the intensity of BSs in the interference-limited regime, while the outage performance deteriorates if the intensity is sufficiently low. Besides, as the channel uncertainty lessens, the asymptotic analyses manifest that the target rates must be restricted up to a bound to achieve an arbitrarily low outage probability in the absence of the inter-cell interference. Moreover, highly correlated estimation error ameliorates the outage performance under a low quality of CSI, otherwise it behaves oppositely. Afterwards, the goodput is maximized by choosing appropriate precoding matrix, receiver filters and transmission rates. In the end, the numerical results verify our analysis and corroborate the superiority of our proposed algorithm. © 2022, CC BY.

关键词： Channel state information

衰亡链揭示互利共生生态系统中安全与崩溃的中间阶段（英文）

学校读者我要写书评

暂无评论

engineering 2024年第12期 89-98页

作者：王光炜刘雪明肖颖袁烨潘林强管晓宏高建喜张海涛 The MOE Engineering Research Center of Autonomous Intelligent Unmanned Systems State Key Laboratory of Digital Manufacturing Equipment and Technology School of Artificial Intelligence and Automation Huazhong University of Science and Technology Guangdong HUST Industrial Technology Research Institute Huazhong University of Science and Technology Guangdong Provincial Engineering Technology Center of Autonomous Unmanned Vessels MOE Key Laboratory of Intelligent Networks and Network Security&State Key Laboratory of Manufacturing Systems Xi'an Jiaotong University Tsinghua National Laboratory of Information Science and Technology Department of Automation Tsinghua University Department of Computer Science Rensselaer Polytechnic Institute

Ecosystems are undergoing unprecedented persistent deterioration due to unsustainable anthropogenic human activities, such as overfishing and deforestation, and the effects of such damage on ecological stability are uncertain. Despite recent advances in experimental and theoretical studies on regime shifts and tipping points, theoretical tools for understanding the extinction chain, which is the sequence of species extinctions resulting from overexploitation, are still lacking, especially for large-scale nonlinear networked systems. In this study, we developed a mathematical tool to predict regime shifts and extinction chains in ecosystems under multiple exploitation situations and verified it in 26 real-world mutualistic networks of various sizes and densities. We discovered five phases during the exploitation process: safe,partial extinction, bistable, tristable, and collapse, which enabled the optimal design of restoration strategies for degraded or collapsed systems. We validated our approach using a 20-year dataset from an eelgrass restoration project. Counterintuitively, we also found a specific region in the diagram spanning exploitation rates and competition intensities, where exploiting more species helps increase *** computational tool provides insights into harvesting, fishing, exploitation, or deforestation plans while conserving or restoring the biodiversity of mutualistic ecosystems.

关键词：

Efficient Pyramid Channel Attention Network for Pathological Myopia Recognition

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhang, Xiaoqing Zhao, Jilu Li, Yan Wu, Hao Zhou, Xiangtian Liu, Jiang Research Institute of Trustworthy Autonomous Systems Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China Center for High Performance Computing Shenzhen Key Laboratory of Intelligent Bioinformatics Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China National Clinical Research Center for Ocular Diseases Eye Hospital Wenzhou Medical University Wenzhou325027 China State Key Laboratory of Ophthalmology Optometry and Visual Science Eye Hospital Wenzhou Medical University Wenzhou325027 China Research Unit of Myopia Basic Research and Clinical Prevention and Control Chinese Academy of Medical Sciences Wenzhou325027 China Singapore Eye Research Institute 169856 Singapore

Pathological myopia (PM) is the leading ocular disease for impaired vision worldwide. Clinically, the characteristic of pathology distribution in PM is global-local on the fundus image, which plays a significant role in assisting clinicians in diagnosing PM. However, most existing deep neural networks focused on designing complex architectures but rarely explored the pathology distribution prior of PM. To tackle this issue, we propose an efficient pyramid channel attention (EPCA) module, which fully leverages the potential of the clinical pathology prior of PM with pyramid pooling and multi-scale context fusion. Then, we construct EPCA-Net for automatic PM recognition based on fundus images by stacking a sequence of EPCA modules. Moreover, motivated by the recent pretraining-and-finetuning paradigm, we attempt to adapt pre-trained natural image models for PM recognition by freezing them and treating the EPCA and other attention modules as adapters. In addition, we construct a PM recognition benchmark termed PM-fundus by collecting fundus images of PM from publicly available datasets. The comprehensive experiments demonstrate the superiority of EPCA-Net over state-of-the-art methods in the PM recognition task. For example, EPCA-Net achieves 97.56% accuracy and outperforms ViT by 2.85% accuracy on the PM-fundus dataset. The results also show that our method based on the pretraining-and-finetuning paradigm achieves competitive performance through comparisons to part of previous methods based on traditional fine-tuning paradigm with fewer tunable parameters, which has the potential to leverage more natural image foundation models to address the PM recognition task in limited medical data regime. Copyright © 2023, The Authors. All rights reserved.

关键词： Pathology

Directly wireless communication of human minds via non-invasive brain-computer-metasurface platform

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Ma, Qian Gao, Wei Xiao, Qiang Ding, Lingsong Gao, Tianyi Zhou, Yajun Gao, Xinxin Yan, Tao Liu, Che Gu, Ze Kong, Xianghong Abbasi, Qammer H. Li, Lianlin Qiu, Cheng-Wei Li, Yuanqing Cui, Tie Jun Institute of Electromagnetic Space Southeast University Nanjing210096 China School of Automation Science and Engineering South China University of Technology Guangzhou510641 China State Key Laboratory of Millimeter Wave Southeast University Nanjing210096 China Center of Intelligent Metamaterials Pazhou Laboratory Guangzhou510330 China Research Center for Brain-Computer Interface Pazhou Lab Guangzhou510330 China Department of Electrical and Computer Engineering National University of Singapore Singapore Singapore University of Glasgow James Watt School of Engineering GlasgowG12 8QQ United Kingdom State Key Laboratory of Advanced Optical Communication Systems and Networks Department of Electronics Peking University Beijing100871 China

Brain-computer interfaces (BCIs), invasive or non-invasive, have projected unparalleled vision and promise for assisting patients in need to better their interaction with the surroundings. Inspired by the BCI-based rehabilitation technologies for nerve-system impairments and amputation, we propose an electromagnetic brain-computer-metasurface (EBCM) paradigm, regulated by human's cognition by brain signals directly and non-invasively. We experimentally show that our EBCM platform can translate human's mind from evoked potentials of P300-based electroencephalography to digital coding information in the electromagnetic domain non-invasively, which can be further processed and transported by an information metasurface in automated and wireless fashions. Directly wireless communications of the human minds are performed between two EBCM operators with accurate text transmissions. Moreover, several other proof-of-concept mind-control schemes are presented using the same EBCM platform, exhibiting flexibly-customized capabilities of information processing and synthesis like visual-beam scanning, wave modulations, and pattern encoding. © 2022, CC BY.

关键词： Electrophysiology

Exact Differentiator with Lipschitz Continuous Output and Optimal Worst-Case Accuracy Under Bounded Noise

学校读者我要写书评

暂无评论

Exact Differentiator with Lipschitz Continuous Output and Op...

IEEE Conference on Decision and Control

作者： Rodrigo Aldana-López Richard Seeber Hernan Haimovich David Gómez-Gutiérrez Department of Computer Science and Systems Engineering University of Zaragoza Zaragoza Spain Christian Doppler Laboratory for Model Based Control of Complex Test Bed Systems Institute of Automation and Control Graz University of Technology Graz Austria Centro Internacional Franco-Argentino de Ciencias de la Información y de Sistemas (CIFASIS) CONICET-UNR Rosario Argentina Intel Tecnología de México Intel Labs Intelligent Systems Research Lab Jalisco Mexico Tecnológico Nacional de México Instituto Tecnológico José Mario Molina Pasquel y Henríquez Unidad Académica Zapopan Jalisco Mexico

The online differentiation of a signal contaminated with bounded noise is addressed. A differentiator is developed that generates a Lipschitz continuous output, is exact in the absence of noise, and provides the optimal worst-case accuracy among all possible exact differentiators when noise is present. This combination of features is not shared by any previously existing differentiator. Tuning of the developed differentiator is very simple, requiring only the knowledge of a bound for the second-order derivative of the signal. The approach consists in regularizing the possibly highly noisy output of a recently introduced linear adaptive robust exact differentiator and feeding it to a first-order sliding-mode filter designed to maintain optimal accuracy. The proposed regularization and filtering of this output allows trading the speed with which exactness is obtained for the feature of a Lipschitz continuous, hence less noisy, output. An illustrative example is provided to highlight the features of the developed differentiator.

关键词：

A Survey on epistemic (model) uncertainty in supervised learning: Recent advances and applications

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zhou, Xinlei Liu, Han Pourpanah, Farhad Zeng, Tieyong Wang, Xizhao College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University 518060 China College of Mathematics and Statistics Shenzhen University Shenzhen518060 China Department of Mathematics Chinese University of Hong Kong Hong Kong

Quantifying the uncertainty of supervised learning models plays an important role in making more reliable predictions. Epistemic uncertainty, which usually is due to insufficient knowledge about the model, can be reduced by collecting more data or refining the learning models. Over the last few years, scholars have proposed many epistemic uncertainty handling techniques which can be roughly grouped into two categories, i.e., Bayesian and ensemble. This paper provides a comprehensive review of epistemic uncertainty learning techniques in supervised learning over the last five years. As such, we, first, decompose the epistemic uncertainty into bias and variance terms. Then, a hierarchical categorization of epistemic uncertainty learning techniques along with their representative models is introduced. In addition, several applications such as computer vision (CV) and natural language processing (NLP) are presented, followed by a discussion on research gaps and possible future research directions. Copyright © 2021, The Authors. All rights reserved.

关键词： Uncertainty analysis