检索结果-南通市图书馆

A Deep Learning Based Approach for Context-Aware Multi-Criteria Recommender Systems

在线全文

学校读者我要写书评

暂无评论

Computer Systems Science & Engineering 2023年第1期44卷 471-483页

作者： son-Lam VU Quang-Hung LE Faculty of Information Technology Quy Nhon UniversityQuy Nhon CityVietnam

Recommender systems are similar to an informationfiltering system that helps identify items that best satisfy the users’demands based on their pre-ference ***-aware recommender systems(CARSs)and multi-criteria recommender systems(MCRSs)are extensions of traditional recommender *** have integrated additional contextual information such as time,place,and so on for providing better ***,the majority of CARSs use ratings as a unique criterion for building ***,MCRSs utilize user preferences in multiple criteria to better generate *** to now,how to exploit context in MCRSs is still an open *** paper proposes a novel approach,which relies on deep learning for context-aware multi-criteria recommender *** apply deep neural network(DNN)mod-els to predict the context-aware multi-criteria ratings and learn the aggregation *** conduct experiments to evaluate the effect of this approach on the real-world dataset.A significant result is that our method outperforms other state-of-the-art methods for recommendation effectiveness.

关键词： Recommender systems context-aware multi-criteria deep learning deep neural network

Diffusion tensor interpolation profile control using non-uniform motion on a Riemannian geodesic

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 Zhejiang University-Science C(Computers and Electronics) 2012年第2期13卷 90-98页

作者： Chang-II son Shun-ren XIA MOE Key Laboratory of Biomedical Engineering Zhejiang UniversityHangzhou 310027China Department of Electronics Kim Chaek University of TechnologyPyongyang 104919DPR of Korea

Tensor interpolation is a key step in the processing algorithms of diffusion tensor imaging (DTI), such as registration and tractography. The diffusion tensor (DT) in biological tissues is assumed to be positive definite. However, the tensor interpolations in most clinical applications have used a Euclidian scheme that does not take this assumption into account. Several Rie-mannian schemes were developed to overcome this limitation. Although each of the Riemannian schemes uses different metrics, they all result in a ‘fixed’ interpolation profile that cannot adapt to a variety of diffusion patterns in biological tissues. In this paper, we propose a DT interpolation scheme to control the interpolation profile, and explore its feasibility in clinical applications. The profile controllability comes from the non-uniform motion of interpolation on the Riemannian geodesic. The interpolation experiment with medical DTI data shows that the profile control improves the interpolation quality by assessing the reconstruction errors with the determinant error, Euclidean norm, and Riemannian norm.

关键词： Diffusion tensor (DT) DT imaging (DTI) DT interpolation Interpolation profile control Riemannian geodesic

The Webster Scalar Curvature and Sharp Upper and Lower Bounds for the First Positive Eigenvalue of the Kohn-Laplacian on Real Hypersurfaces

在线全文

学校读者我要写书评

暂无评论

Acta Mathematica Sinica,English Series 2018年第8期34卷 1248-1258页

作者： song Ying LI Duong Ngoc son Department of Mathematics University of California Irvine CA 92697-3875 Department of Mathematics Fujian Normal University Fujian 350108 P. R. China Fakultiit fiir Mathematik Universitiit Wien Oskar-Morgenstern-Platz 1 1090 Wien Osterreich

Let （M, θ） be a compact strictly pseudoconvex pseudonermitian manifold winch is CR embedded into a complex space. In an earlier paper, Lin and the authors gave several sharp upper bounds for the first positive eigenvalue λ1 of the Kohn-Laplacian □b on （M, θ）. In the present paper, we give a sharp upper bound for λ1, generalizing and extending some previous results. As a corollary, we obtain a Reilly-type estimate when M is embedded into the standard sphere. In another direction, using a Lichnerowicz-type estimate by Chanillo, Chiu, and Yang and an explicit formula for the Webster scalar curvature, we give a lower bound for λ1 when the pseudohermitian structure θ is volume-normalized.

关键词： CR manifold eigenvalue Kohn-Laplacian Webster curvature

Effects of Supercritical Environment on Hydrocarbon-fuel Injection

在线全文

学校读者我要写书评

暂无评论

Journal of Thermal Science 2017年第2期26卷 183-191页

作者： Bongchul Shin Dohun Kim Min son Jaye Koo Graduate School Korea Aerospace UniversityGoyangRepublic of Korea School of Aerospace and Mechanical Engineering Korea Aerospace UniversityGoyangRepublic of Korea

In this study, the effects of environment conditions on decane were investigated. Decane was injected in subcritical and supercritical ambient conditions. The visualization chamber was pressurized to 1.68 MPa by using nitrogen gas at a temperature of 653 K for subcritical ambient conditions. For supercritical ambient conditions, the visualization chamber was pressurized to 2.52 MPa by using helium at a temperature of 653 K. The decane injection in the pressurized chamber was visualized via a shadowgraph technique and gradient images were obtained by a post processing method. A large variation in density gradient was observed at jet interface in the case of subcritical injection in subcritical ambient conditions. Conversely, for supercritical injection in supercritical ambient conditions, a small density gradient was observed at the jet interface. In a manner similar to that observed in other cases, supercritical injection in subcritical ambient conditions differed from supercritical ambient conditions such as sphere shape liquid. Additionally, there were changes in the interface, and the supercritical injection core width was thicker than that in the subcritical injection. Furthermore, in cases with the same injection conditions, the change in the supercritical ambient normalized core width was smaller than the change in the subcritical ambient normalized core width owing to high specific heat at the supercritical injection and small phase change at the interface. Therefore, the interface was affected by the changing ambient condition. Given that the effect of changing the thermodynamic properties of propellants could be essential for a variable thrust rocket engine, the effects of the ambient conditions were investigated experimentally.

关键词： Decane Jet Subcritical Supercritical Visualization

Improvement of a temperature response function for divertor heat flux monitoring in fusion devices

在线全文

学校读者我要写书评

暂无评论

Plasma Science and Technology 2023年第3期25卷 217-221页

作者： Xuan Nhat son BUI Hiroto MATSUURA Yousuke NAKASHIMA Quantum and Radiation Engineering Department Osaka Prefecture University Plasma Research Center University of Tsukuba

Temperature response functions have been developed to investigate sensor design and divertor heat flux estimation in magnetically confined plasmas. The time-dependent heat flux can be derived by fitting the response function to experimental thermocouple(TC) data. Because the TC signals have a time delay to transit events such as discharge start or confinement transition, the time delay is taken into account in a temperature response function. Such a function accurately describes the signal from each TC channel with time delay in a sensor test using a neutral beam injection. Measurement for commercial TCs shows that the time delay is caused by the finite heat capacity of TC wire and contact heat resistance between TC and target surface.

关键词： divertor temperature response function thermocouple system primary delay

Privacy-preserving deep learning techniques for wearable sensor-based big data applications

在线全文

学校读者我要写书评

暂无评论

Virtual Reality & Intelligent Hardware 2022年第3期4卷 210-222页

作者： Rafik HAMZA Minh-son DAO Integrated Big Data Research Center|NICT-National Institute of Information and Communications Technology TokyoJapan

Wearable technologies have the potential to become a valuable influence on human daily life where they may enable observing the world in new ways,including,for example,using augmented reality(AR)*** technology uses electronic devices that may be carried as accessories,clothes,or even embedded in the user's *** the potential benefits of smart wearables are numerous,their extensive and continual usage creates several privacy concerns and tricky information security *** this paper,we present a comprehensive survey of recent privacy-preserving big data analytics applications based on wearable *** highlight the fundamental features of security and privacy for wearable device ***,we examine the utilization of deep learning algorithms with cryptography and determine their usability for wearable *** also present a case study on privacy-preserving machine learning ***,we theoretically and empirically evaluate the privacy-preserving deep learning framework's *** explain the implementation details of a case study of a secure prediction service using the convolutional neural network(CNN)model and the Cheon-Kim-Kim-song(CHKS)homomorphic encryption ***,we explore the obstacles and gaps in the deployment of practical real-world *** a comprehensive overview,we identify the most important obstacles that must be overcome and discuss some interesting future research directions.

关键词： Wearable technology Augmented reality Privacy-preserving Deep learning Big data Secure prediction service

Iterative Method for Solving a Problem with Mixed Boundary Conditions for Biharmonic Equation

在线全文

学校读者我要写书评

暂无评论

Advances in Applied Mathematics and Mechanics 2009年第5期1卷 683-698页

作者： Dang Quang A Le Tung son Institute of Information Technology 18 Hoang Quoc Viet Cau giayHanoiVietnam Pedagogic College Thai Nguyen UniversityVietnam

The solution of boundary value problems(BVP)for fourth order differential equations by their reduction to BVP for second order equations,with the aim to use the available efficient algorithms for the latter ones,attracts attention from many *** this paper,using the technique developed by the authors in recent works we construct iterative method for a problem with complicated mixed boundary conditions for biharmonic equation which is originated from nanofluidic *** convergence rate of the method is proved and some numerical experiments are performed for testing its dependence on a parameter appearing in boundary conditions and on the position of the point where a transmission of boundary conditions occurs.

关键词： Iterative method biharmonic equation mixed boundary conditions

Process-Based Crop Modeling for High Applicability with Attention Mechanism and Multitask Decoders

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Plant Phenomics 2023年第2期5卷 378-390页

作者： Taewon Moon Dongpil Kim Sungmin Kwon Jung Eek son Department of Agriculture Forestry and BioresourcesSeoul National UniversitySeoul 08826Republic of Korea Research Institute of Agriculture and Life Sciences Seoul National UniversitySeoul 08826Republic of Korea Protected Horticulture Research Institute National Institute of Horticultural&Herbal ScienceRural Development AdministrationHaman 52054Republic of Korea

Crop models have been developed for wide research purposes and scales,but they have low compatibility due to the diversity of current modeling *** model adaptability can lead to model *** deep neural networks have no conventional modeling parameters,diverse input and output combinations are possible depending on model *** these advantages,no process-based crop model has been tested in full deep neural network *** objective of this study was to develop a process-based deep learning model for hydroponic sweet *** mechanism and multitask learning were selected to process distinct growth factors from the environment *** algorithms were modified to be suitable for the regression task of growth *** were conducted twice a year for 2 years in *** developed crop model,DeepCrop,recorded the highest modeling efficiency(=0.76)and the lowest normalized mean squared error(=0.18)compared to accessible crop models in the evaluation with unseen *** t-distributed stochastic neighbor embedding distribution and the attention weights supported that DeepCrop could be analyzed in terms of cognitive *** the high adaptability of DeepCrop,the developed model can replace the existing crop models as a versatile tool that would reveal entangled agricultural systems with analysis of complicated information.

关键词： Deep replace versatile

Multi-Generator Discriminator Network Using Texture-Edge Information

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2023年第5期75卷 3537-3551页

作者： Kyeongseok Jang Seongsoo Cho Kwang Chul son Department of Plasma Bio Display Kwangwoon University20Gwangun-roNowon-guSeoul01897Korea School of Software Soongsil University369Sangdo-roDongjak-guSeoul06978Korea Department of Information Contents Kwangwoon University20Gwangun-roNowon-guSeoul01897Korea

In the proposed paper,a parallel structure type Generative Adversarial Network(GAN)using edge and texture information is *** the existing GAN-based model,many learning iterations had to be given to obtaining an output that was somewhat close to the original data,and noise and distortion occurred in the output image even when learning was *** solve this problem,the proposed model consists of two generators and three discriminators to propose a network in the form of a parallel *** the network,each edge information and texture information were received as inputs,learning was performed,and each character was combined and outputted through the Combine *** this,edge information and distortion of the output image were improved even with fewer iterations than DCGAN,which is the existing GAN-based *** a result of learning on the network of the proposed model,a clear image with improved contour and distortion of objects in the image was output from about 50,000 iterations.

关键词： Deep learning convolution neural network generative adversarial network edge information texture information