检索结果-南通市图书馆

Fully Distributed Learning for deep Random Vector Functional-Link networks

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Applied Mathematics and Physics 2024年第4期12卷 1247-1262页

作者： Huada Zhu Wu Ai School of Mathematics and Statistics Guilin University of Technology Guilin China Guangxi Colleges and Universities Key Laboratory of Applied Statistics Guilin China

In the contemporary era, the proliferation of information technology has led to an unprecedented surge in data generation, with this data being dispersed across a multitude of mobile devices. Facing these situations and the training of deep learning model that needs great computing power support, the distributed algorithm that can carry out multi-party joint modeling has attracted everyone’s attention. The distributed training mode relieves the huge pressure of centralized model on computer computing power and communication. However, most distributed algorithms currently work in a master-slave mode, often including a central server for coordination, which to some extent will cause communication pressure, data leakage, privacy violations and other issues. To solve these problems, a decentralized fully distributed algorithm based on deep random weight neural network is proposed. The algorithm decomposes the original objective function into several sub-problems under consistency constraints, combines the decentralized average consensus (DAC) and alternating direction method of multipliers (ADMM), and achieves the goal of joint modeling and training through local calculation and communication of each node. Finally, we compare the proposed decentralized algorithm with several centralized deep neural networks with random weights, and experimental results demonstrate the effectiveness of the proposed algorithm.

关键词： Distributed Optimization deep neural network Random Vector Functional-Link (RVFL) network Alternating Direction Method of Multipliers (ADMM)

Novel automated non-invasive detection of ocular surface squamous neoplasia using artificial intelligence

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

World Journal of Methodology 2024年第2期14卷 51-64页

作者： Sony Sinha Prasanna Venkatesh Ramesh Prateek Nishant Arvind Kumar Morya Ripunjay Prasad Department of Ophthalmology–Vitreo Retina Neuro Ophthalmology and OculoplastyAll India Institute of Medical SciencesPatna 801507India Department of Glaucoma and Research Mahathma Eye Hospital Private LimitedTrichy 620017India Department of Ophthalmology ESIC Medical CollegePatna 801113India Department of Ophthalmology All India Institute of Medical SciencesHyderabad 508126India Department of Ophthalmology RP Eye InstituteDelhi 110001India

Ocular surface squamous neoplasia(OSSN)is a common eye surface tumour,characterized by the growth of abnormal cells on the ocular *** includes invasive squamous cell carcinoma(SCC),in which tumour cells penetrate the basement membrane and infiltrate the stroma,as well as non-invasive conjunctival intraepithelial neoplasia,dysplasia,and SCC in-situ thereby presenting a challenge in early detection and *** identification and precise demarcation of the OSSN border leads to straightforward and curative treatments,such as topical medicines,whereas advanced invasive lesions may need orbital exenteration,which carries a risk of *** intelligence(AI)has emerged as a promising tool in the field of eye care and holds potential for its application in OSSN *** algorithms trained on large datasets can analyze ocular surface images to identify suspicious lesions associated with OSSN,aiding ophthalmologists in early detection and *** can also track and monitor lesion progression over time,providing objective measurements to guide treatment ***,AI can assist in treatment planning by offering personalized recommendations based on patient data and predicting the treatment *** manuscript highlights the role of AI in OSSN,specifically focusing on its contributions in early detection and diagnosis,assessment of lesion progression,treatment planning,telemedicine and remote monitoring,and research and data analysis.

关键词： Conjunctival neoplasm Early detection of cancer Machine learning deep neural network Precision medicine

Hybrid method for accurate multi-gravity-assist trajectory design using pseudostate theory and deep neural networks

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(Technological Sciences) 2022年第3期65卷 595-610页

作者： YANG Bin FENG JingLang HUANG XuXing LI Shuang College of Astronautics Nanjing University of Aeronautics and AstronauticsNanjing 211106China Department of Mechanical&Aerospace Engineering University of StrathclydeGlasgow G11XJUK

This paper presents a novel hybrid method to design the continuous and accurate multi-gravity-assist trajectory for a high-fidelity *** gravitational perturbation of the primary body is considered during the gravity *** pseudostate technique is applied to approximate the gravity-assisted trajectory,where the optimal sweepback duration is solved using a trained deep neural *** major factors that affect the optimal sweepback duration of the approach and departure segments are *** results show that the optimal sweepback duration of the approach segment only relies on the shape of the approach trajectory and is independent of the flight ***,a gravity-assisted trajectory patched strategy and a hybrid algorithm combining the particle swarm optimization and the sequential quadratic programming are developed to optimize the multi-gravity-assist *** proposed hybrid method is applied to the Europa orbiter *** comparison with the traditional patched conic method,this method demonstrates outstanding performance on accuracy and significantly reduces the computational time and complexity of the trajectory correction with the high-fidelity dynamics.

关键词： pseudostate theory multiple gravity assist deep neural network trajectory optimization Jovian system

Ensemble forecast of tropical cyclone tracks based on deep neural networks

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Frontiers of Earth Science 2022年第3期16卷 671-677页

作者： Chong WANG Qing XU Yongcun CHENG Yi PAN Hong LI Key Laboratory of Marine Hazards Forecasting(Ministry of Natural Resources) Hohai UniversityNanjing 210098China College of Marine Technology Faculty of Information Science and EngineeringOcean University of ChinaQingdao 266100China Southern Marine Science and Engineering Guangdong Laboratory(Guangzhou) Guangzhou 511458China PIESAT Information Technology Co.Ltd. Beijing 100195China College of Harbor Coastal and Offshore EngineeringHohai UniversityNanjing 210098China Shanghai Typhoon Institute China Meteorological AdministrationShanghai 200030China

A nonlinear artificial intelligence ensemble forecast model has been developed in this paper for predicting tropical cyclone(TC)tracks based on the deep neural network(DNN)by using the 24-h forecast data from the China Meteorological Administration(CMA),Japan Meteorological Agency(JMA)and Joint Typhoon Warning Center(JTWC).Data from a total of 287 TC cases over the Northwest Pacific Ocean from 2004 to 2015 were used to train and validate the DNN based ensemble forecast(DNNEF)*** comparison of model results with Best Track data of TCs shows that the DNNEF model has a higher accuracy than any individual forecast center or the traditional ensemble forecast *** average 24-h forecast error of 82 TCs from 2016 to 2018 is 63 km,which has been reduced by 17.1%,16.0%,20.3%,and 4.6%,respectively,compared with that of CMA,JMA,JTWC,and the error-estimation based ensemble *** results indicate that the nonlinear DNNEF model has the capability of adjusting the model parameter dynamically and automatically,thus improving the accuracy and stability of TC prediction.

关键词： tropical cyclone track deep neural network ensemble forecast

Optimized Artificial neural network Techniques to Improve Cybersecurity of Higher Education Institution

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2022年第8期72卷 3385-3399页

作者： Abdullah Saad AL-Malaise AL-Ghamdi Mahmoud Ragab Maha Farouk S.Sabir Ahmed Elhassanein Ashraf A.Gouda Information Systems Department Faculty of Computing and Information Technology King Abdulaziz UniversityJeddah21589Saudi Arabia Information Technology Department Faculty of Computing and Information TechnologyKing Abdulaziz UniversityJeddah21589Saudi Arabia Centre of Artificial Intelligence for Precision Medicines King Abdulaziz UniversityJeddah21589Saudi Arabia Mathematics Department Faculty of ScienceAl-Azhar UniversityNaser City11884CairoEgypt Mathematics Department College of ScienceUniversity of BishaBishaSaudi Arabia Mathematics Department Faculty of ScienceDamanhour UniversityDamanhourEgypt

Education acts as an important part of economic growth and improvement in human *** educational sectors have transformed a lot in recent days,and Information and Communication Technology(ICT)is an effective part of the education *** every action in university and college,right from the process fromcounselling to admissions and fee deposits has been *** records,quiz,evaluation,mark,and grade submissions involved the utilization of the ***,security is essential to accomplish cybersecurity in higher security institutions(HEIs).In this view,this study develops an Automated Outlier Detection for CyberSecurity in Higher Education Institutions(AOD-CSHEI)*** AOD-CSHEI technique intends to determine the presence of intrusions or attacks in the *** AOD-CSHEI technique initially performs data pre-processing in two stages namely data conversion and class *** addition,the Adaptive Synthetic(ADASYN)technique is exploited for the removal of outliers in the ***,the sparrow search algorithm(SSA)with deep neural network(DNN)model is used for the classification of data into the existence or absence of intrusions in the HEIs ***,the SSA is utilized to effectually adjust the hyper parameters of the DNN *** order to showcase the enhanced performance of the AOD-CSHEI technique,a set of simulations take place on three benchmark datasets and the results reported the enhanced efficiency of the AOD-CSHEI technique over its compared methods with higher accuracy of 0.9997.

关键词： Higher security institutions intrusion detection system artificial intelligence deep neural network hyperparameter tuning deep learning

SOPA-GA-CNN: Synchronous optimisation of parameters and architectures by genetic algorithms with convolutional neural network blocks for securing Industrial Internet-of-Things

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

IET Cyber-Systems and Robotics 2023年第1期5卷 51-66页

作者： Jia-Cheng Huang Guo-Qiang Zeng Guang-Gang Geng Jian Weng Kang-Di Lu College of Cyber Security and the National Joint Engineering Research Center of network Security Detection and Protection Technology Jinan UniversityGuangzhouChina National-Local Joint Engineering Research Center of Digitalize Electrical Design Technology Wenzhou UniversityWenzhouChina National Laboratory of Industrial Control Technology Institute of Cyber-Systems and ControlZhejiang UniversityHangzhouChina

In recent years,deep learning has been applied to a variety of scenarios in Industrial Internet of Things(IIoT),including enhancing the security of ***,the existing deep learning methods utilised in IIoT security are manually designed by heavily relying on the experience of the *** authors have made the first contribution concerning the joint optimisation of neural architecture search and hyper-parameters optimisation for securing IIoT.A novel automated deep learning method called synchronous optimisation of parameters and architectures by GA with CNN blocks(SOPA-GA-CNN)is proposed to synchronously optimise the hyperparameters and block-based architectures in convolutional neural networks(CNNs)by genetic algorithms(GA)for the intrusion detection issue of *** efficient hybrid encoding strategy and the corresponding GA-based evolutionary operations are designed to characterise and evolve both the hyperparameters,including batch size,learning rate,weight optimiser and weight regularisation,and the architectures,such as the block-based network topology and the parameters of each CNN *** experimental results on five intrusion detection datasets in IIoT,including secure water treatment,water distribution,Gas Pipeline,Botnet in Internet of Things and Power System Attack Dataset,have demonstrated the superiority of the proposed SOPA-GA-CNN to the state-of-the-art manually designed models and neuron-evolutionary methods in terms of accuracy,precision,recall,F1-score,and the number of parameters of the deep learning models.

关键词： cyber-systems deep learning deep neural network Internet of things swarm intelligence

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

基于神经网络的卧螺离心机螺旋流场流速建模

基于深度神经网络的端到端长期护理保险定价模型研究

建模与仿真 2024年第2期13卷 1304页

作者：赵曰炜丛佩超周栋李文彬广西科技大学机械与汽车工程学院，广西柳州

提出了一种基于深度学习方法的卧螺离心机螺旋流场流速预测模型。对于流体力学问题的数值模拟主要依赖于求解离散化的控制方程，深度学习由于其处理强非线性和高维性的能力，在解决流体问题方面显示出了新的前景。然而，现成的神经网络... 详细信息

提出了一种基于深度学习方法的卧螺离心机螺旋流场流速预测模型。对于流体力学问题的数值模拟主要依赖于求解离散化的控制方程，深度学习由于其处理强非线性和高维性的能力，在解决流体问题方面显示出了新的前景。然而，现成的神经网络架构大多用于简单流场，对于稍复杂些的流场未得到充分应用。首先，使用一个结构化的深度神经网络，将流场控制的偏微分方程(即Navier-Stokes方程)纳入DNN的损失来驱动训练；然后，根据螺旋流场特征参数施加边界条件建立流速预测模型；最后，利用所构建的模型预测卧螺离心机螺旋流场流速分布并与数值模拟结果做对比实验。结果表明：通过对流场不同压力、角速度下的流速进行预测，构建的模型与数值模拟结果具有很好的一致性。

关键词：深度神经网络螺旋流场流体力学流动控制 deep neural network Spiral Flow Field Fluid Mechanics Flow Control

来源：博看期刊评论

在线全文

博看期刊

学校读者我要写书评

暂无评论

Prediction of Leakage from an Axial Piston Pump Slipper with Circular Dimples Using deep neural networks

统计与精算 2024年第03期

作者：仇春涓刘守贤张楠

本文在大数据、科技赋能的背景下，提出基于深度神经网络的端到端长期护理保险定价模型。端到端模型可以将所有的步骤包含在一个深度神经网络模型内部，输入被保险人的个体特征，直接得到其未来不同护理状态的概率预测值。相比于经典定... 详细信息

本文在大数据、科技赋能的背景下，提出基于深度神经网络的端到端长期护理保险定价模型。端到端模型可以将所有的步骤包含在一个深度神经网络模型内部，输入被保险人的个体特征，直接得到其未来不同护理状态的概率预测值。相比于经典定价模型，端到端模型具有放宽模型假设、减少定价模型的复杂程度、避免误差积累以及自动优化和智能化的优点。本文选取CHARLS 2011年、2013年、2015年和2018年数据进行实证研究，构建一个包含三层隐藏层，每层32个神经元的全连接神经网络模型，考虑样本不平衡性，调整模型参数，对比不同激活函数，得到预测个体护理状态的最优模型LTCmodel。基于LTCmodel，在合理的长期护理保险产品责任、保额增长率以及利率假设下，最终输出不同特征被保险人的年缴均衡保费，实现个性化和精准定价。

关键词：长期护理保险深度神经网络 LTCmodel 保险定价 long-term care insurance deep neural network LTCmodel insurance pricing

来源：人大复印报刊资料评论

在线全文

人大复印报刊资料

学校读者我要写书评

暂无评论

Chinese Journal of Mechanical Engineering 2020年第2期33卷 111-121页

作者： Ozkan Ozmen Cem Sinanoglu Abdullah Caliskan Hasan Badem Tribology Laboratory Industrial Design EngineeringFaculty of EngineeringErciyes UniversityKayseri 38039Turkey Biomedical Engineering Faculty of Engineering and Natural SciencesIskenderun Technical UniversityHatayTurkey Computer Engineering Faculty of Engineering and ArchitectureKahramanmaraşSutcu Imam UniversityKahramanmaraşTurkey

Oil leakage between the slipper and swash plate of an axial piston pump has a significant effect on the efficiency of the ***,it is extremely important that any leakage can be *** study investigates the leakage,oil film thickness,and pocket pressure values of a slipper with circular dimples under different working *** results reveal that flat slippers suffer less leakage than those with textured ***,a deep learning-based framework is proposed for modeling the slipper *** framework is a long short-term memory-based deep neural network,which has been extremely successful in predicting time *** model is compared with four conventional machine learning *** addition,statistical analyses and comparisons confirm the superiority of the proposed model.

关键词： Slipper Leakage Circular dimpled Long short-term memory deep neural network