检索结果-南通市图书馆

On the robustness of median sampling in noisy evolutionary optimization

在线全文

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2021年第5期64卷 32-44页

作者： Chao BIAN Chao QIAN Yang YU Ke TANG State key laboratory for novel software technology Nanjing University Shenzhen key laboratory of Computational intelligence Department of Computer Science and EngineeringSouthern University of Science and Technology

Evolutionary algorithms(EAs) are a sort of nature-inspired metaheuristics, which have wide applications in various practical optimization problems. In these problems, objective evaluations are usually inaccurate, because noise is almost inevitable in real world, and it is a crucial issue to weaken the negative effect caused by noise. Sampling is a popular strategy, which evaluates the objective a couple of times, and employs the mean of these evaluation results as an estimate of the objective value. In this work, we introduce a novel sampling method, median sampling, into EAs, and illustrate its properties and usefulness theoretically by solving OneMax, the problem of maximizing the number of 1 s in a bit string. Instead of the mean, median sampling employs the median of the evaluation results as an estimate. Through rigorous theoretical analysis on OneMax under the commonly used onebit noise, we show that median sampling reduces the expected runtime exponentially. Next, through two special noise models, we show that when the 2-quantile of the noisy fitness increases with the true fitness, median sampling can be better than mean sampling; otherwise,it may fail and mean sampling can be better. The results may guide us to employ median sampling properly in practical applications.

关键词： evolutionary algorithms noisy optimization median sampling computational complexity runtime analysis

SoftSSD:enabling rapid flash firmware prototyping for solid-state drives

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Information technology & Electronic Engineering 2023年第5期24卷 659-674页

作者： Jin XUE Renhai CHEN Tianyu WANG Zili SHAO Department of Computer Science and Engineering The Chinese University of Hong KongHong Kong 999077China College of intelligence and computing Tianjin UniversityTianjin 300354China

Recently,solid-state drives(SSDs)have been used in a wide range of emerging data processing systems.Essentially,an SSD is a complex embedded system that involves both hardware and software design.For the latter,firmware modules such as the flash translation layer(FTL)orchestrate internal operations and flash management,and are crucial to the overall input/output performance of an SSD.Despite the rapid development of new SSD features in the market,the research of flash firmware has been mostly based on simulations due to the lack of a realistic and extensible SSD development platform.In this paper,we propose SoftSSD,a software-oriented SSD development platform for rapid flash firmware prototyping.The core of SoftSSD is a novel framework with an event-driven programming model.With the programming model,new FTL algorithms can be implemented and integrated into a full-featured flash firmware in a straightforward way.The resulting flash firmware can be deployed and evaluated on a hardware development board,which can be connected to a host system via peripheral component interconnect express and serve as a normal non-volatile memory express SSD.Different from existing hardware-oriented development platforms,SoftSSD implements the majority of SSD components(e.g.,host interface controller)in software,so that data flows and internal states that were once confined in the hardware can now be examined with a software debugger,providing the observability and extensibility that are critical to the rapid prototyping and research of flash firmware.We describe the programming model and hardware design of SoftSSD.We also perform experiments with real application workloads on a prototype board to demonstrate the performance and usefulness of SoftSSD,and release the open-source code of SoftSSD for public access.

关键词： Solid-state drives Storage system software hardware co-design

A mesh optimization method using machine learning technique and variational mesh adaptation

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Aeronautics 2022年第3期35卷 27-41页

作者： Tingfan WU Xuejun LIU Wei AN Zenghui HUANG Hongqiang LYU MIITkey laboratory of Pattern Analysis and Machine intelligence College of Computer Science and TechnologyNanjing University of Aeronautics and AstronauticsNanjing 211106China Collaborative Innovation Center of novel software technology and Industrialization Nanjing 210023China College of Aerospace Engineering Nanjing University of Aeronautics and AstronauticsNanjing 211106China

Computational mesh is an important ingredient that affects the accuracy and efficiency of CFD numerical simulation.In light of the introduced large amount of computational costs for many adaptive mesh methods,moving mesh methods keep the number of nodes and topology of a mesh unchanged and do not increase CFD computational expense.As the state-of-the-art moving mesh method,the variational mesh adaptation approach has been introduced to CFD calculation.However,quickly estimating the flow field on the updated meshes during the iterative algorithm is challenging.A mesh optimization method,which embeds a machine learning regression model into the variational mesh adaptation,is proposed.The regression model captures the mapping between the initial mesh nodes and the flow field,so that the variational method could move mesh nodes iteratively by solving the mesh functional which is built from the estimated flow field on the updated mesh via the regression model.After the optimization,the density of the nodes in the high gradient area increases while the density in the low gradient area decreases.Benchmark examples are first used to verify the feasibility and effectiveness of the proposed method.And then we use the steady subsonic and transonic flows over cylinder and NACA0012 airfoil on unstructured triangular meshes to test our method.Results show that the proposed method significantly improves the accuracy of the local flow features on the adaptive meshes.Our work indicates that the proposed mesh optimization approach is promising for improving the accuracy and efficiency of CFD computation.

关键词： CFD Flow field Machine learning Moving mesh method Regression models Variational mesh adaptation

Dropout Rademacher complexity of deep neural networks

在线全文

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2016年第7期59卷 173-184页

作者： Wei GAO Zhi-Hua ZHOU National key laboratory for novel software technology Nanjing University Collaborative Innovation Center of novel software technology and Industrialization Nanjing University

Great successes of deep neural networks have been witnessed in various real applications. Many algorithmic and implementation techniques have been developed; however, theoretical understanding of many aspects of deep neural networks is far from clear. A particular interesting issue is the usefulness of dropout,which was motivated from the intuition of preventing complex co-adaptation of feature detectors. In this paper,we study the Rademacher complexity of different types of dropouts, and our theoretical results disclose that for shallow neural networks(with one or none hidden layer) dropout is able to reduce the Rademacher complexity in polynomial, whereas for deep neural networks it can amazingly lead to an exponential reduction.

关键词： artificial intelligence machine learning deep learning dropout Rademacher complexity

FedIERF: Federated Incremental Extremely Random Forest for Wearable Health Monitoring

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Journal of Computer Science & technology 2023年第5期38卷 970-984页

作者：胡春雨忽丽莎袁林陆佃杰吕蕾陈益强 key laboratory of computing Power Network and Information Security Ministry of EducationShandong Computer Science Center(National Supercomputer Center in Jinan)Qilu University of Technology(Shandong Academy of Sciences)Jinan 250353China Shandong Provincial key laboratory of Computer Networks Shandong Fundamental Research Center for Computer ScienceJinan 250000China Shandong Provincial key laboratory for novel Distributed Computer software technology Jinan 25000China Institute of Information technology Hebei University of Economics and BusinessShijiazhuang 050061China School of Information Science and Engineering Shandong Normal UniversityJinan 250358China Institute of computing technology Chinese Academy of SciencesBeijing 100190China

Wearable health monitoring is a crucial technical tool that offers early warning for chronic diseases due to its superior portability and low power consumption.However,most wearable health data is distributed across dfferent organizations,such as hospitals,research institutes,and companies,and can only be accessed by the owners of the data in compliance with data privacy regulations.The first challenge addressed in this paper is communicating in a privacy-preserving manner among different organizations.The second technical challenge is handling the dynamic expansion of the federation without model retraining.To address the first challenge,we propose a horizontal federated learning method called Federated Extremely Random Forest(FedERF).Its contribution-based splitting score computing mechanism significantly mitigates the impact of privacy protection constraints on model performance.Based on FedERF,we present a federated incremental learning method called Federated Incremental Extremely Random Forest(FedIERF)to address the second technical challenge.FedIERF introduces a hardness-driven weighting mechanism and an importance-based updating scheme to update the existing federated model incrementally.The experiments show that FedERF achieves comparable performance with non-federated methods,and FedIERF effectively addresses the dynamic expansion of the federation.This opens up opportunities for cooperation between different organizations in wearable health monitoring.

关键词： federated learning incremental learning random forest wearable health monitoring

Abductive learning: towards bridging machine learning and logical reasoning

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2019年第7期62卷 220-222页

作者： Zhi-Hua ZHOU National key laboratory for novel software technology Nanjing University

In the history of artificial intelligence research,machine learning and logical reasoning have almost been separately developed. It is often argued that advanced intelligent technologies would emerge when machine lear... 详细信息

关键词： pro towards bridging machine learning and logical reasoning Abductive learning

Public auditing for real‑time medical sensor data in cloud‑assisted HealthIIoT system

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Optoelectronics 2022年第3期15卷 1-14页

作者： Weiping Ye Jia Wang Hui Tian Hanyu Quan College of Computer Science and technology Huaqiao UniversityXiamen 361021China Wuhan National laboratory for Optoelectronics Wuhan 430074China Xiamen key laboratory of Data Security and Blockchain technology Xiamen 361021China Fujian key laboratory of Big Data intelligence and Security Xiamen 361021China

With the advancement of industrial internet of things(IIoT),wireless medical sensor networks(WMSNs)have been widely introduced in modern healthcare systems to collect real-time medical data from patients,which is known as HealthIIoT.Considering the limited computing and storage capabilities of lightweight HealthIIoT devices,it is necessary to upload these data to remote cloud servers for storage and maintenance.However,there are still some serious security issues within outsourcing medical sensor data to the cloud.One of the most signifcant challenges is how to ensure the integrity of these data,which is a prerequisite for providing precise medical diagnosis and treatment.To meet this challenge,we propose a novel and efcient public auditing scheme,which is suitable for cloud-assisted HealthIIoT system.Specifcally,to address the contradiction between the high real-time requirement of medical sensor data and the limited computing power of HealthIIoT devices,a new online/ofine tag generation algorithm is designed to improve preprocessing efciency;to protect medical data privacy,a secure hash function is employed to blind the data proof.We formally prove the security of the presented scheme,and evaluate the performance through detailed experimental comparisons with the state-of-the-art ones.The results show that the presented scheme can greatly improve the efciency of tag generation,while achieving better auditing performance than previous schemes.

关键词： Healthcare industrial internet of things(HealthIIoT) Medical sensor data Online/ofine signature Public auditing

Research and implementation of continuous wave radar ranging method based on tri-frequency

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

High technology Letters 2014年第2期20卷 111-116页

作者：袁其平 Fan Lijieare Tong Zhengrong Yang Xiufeng Cao Ye School of Electronics Information Engineering Tianjin University of Technology key laboratory of Film Electronics and Communication Devices and key laboratory of Intelligent computing and novel software Technolgy School of Computer and Communication EngineeringTianjin University of Technology

In the traditional dual-frequency radar ranging system,there is a contradiction between ranging precision and ranging distance.So a tri-frequency ranging method is proposed.The principle of the tri-frequency ranging is that the distance can be achieved by transmitting the three frequencies and then measuring the three phase difference and calculating the number of wavelength.What's more,range ambiguity will not occur within a certain distance.The experimental results show that,if the waveband is 0.47 ~0.57 m,the measurement of unambiguous distance of 25 ~500m can be realized.If the wavelength tolerance error is less than ± 10^(-7) and the phase error is less than ± 10^(-3),the precision of the distance ranging can reach 10^(-6).

关键词：测距方法连续波雷达三频雷达测距系统测距精度频率范围相位误差距离

Crowdsourcing aggregation with deep Bayesian learning

在线全文

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2021年第3期64卷 46-56页

作者： Shao-Yuan LI Sheng-Jun HUANG Songcan CHEN College of Computer Science and technology College of Artificial IntelligenceNanjing University of Aeronautics and Astronautics State key laboratory for novel software technology Nanjing University

In this study, we consider a crowdsourcing classification problem in which labeling information from crowds is aggregated to infer latent true labels. We propose a fully Bayesian deep generative crowdsourcing model(Bayes DGC), which combines the strength of deep neural networks(DNNs) on automatic representation learning and the interpretable probabilistic structure encoding of probabilistic graphical models. The model comprises a DNN classifier as a prior for the true labels and a probabilistic model for the annotation generation process. The DNN classifier and annotation generation process share the latent true label variables. To address the inference challenge, we developed a natural-gradient stochastic variational inference, which combines variational message passing for conjugate parameters and stochastic gradient descent for DNN and learns the distribution of latent true labels and workers’ confusion matrix via end-to-end training. We illustrated the effectiveness of the proposed model using empirical results on 22 real-world datasets.

关键词： crowdsourcing classification fully Bayesian deep generative models natural gradient stochastic variational inference