检索结果-内蒙古大学图书馆

SSRN 2023年

作者： Gao, Penglei Yang, Xi Zhang, Rui Huang, Kaizhu Department of Computer Science University of Liverpool United Kingdom School of Advanced Technology Department of Foundational Mathematics Xi’an Jiaotong-Liverpool University China Institute of Applied Physical Sciences and Engineering Duke Kunshan University China

Different from image inpainting, generalised image outpainting aims to extend appealing content all-side around a given image. Existing state-of-the-art outpainting methods often rely on discrete extrapolation to extend the feature map in the bottleneck. They thus suffer from content unsmoothness, especially in circumstances where the outlines of objects in the extrapolated regions are incoherent with the input sub-images. To mitigate this issue, we design a novel bottleneck with Neural ODEs to make continuous extrapolation in latent space, which could be a plug-in for many deep learning frameworks. Our ODE-based network continuously transforms the state and makes accurate predictions by learning the incremental relationship among latent points, leading to both smooth and structured feature representation. Experimental results on three real-world datasets both applied on transformer-based and CNN-based frameworks show that our methods could generate more realistic and coherent images against the state-of-the-art image outpainting approaches. © 2023, The Authors. All rights reserved.

关键词： Extrapolation

来源：评论

学校读者我要写书评

暂无评论

A Copyright Protection Scheme of Visual Media in Big Data Environment 7th

A Copyright Protection Scheme of Visual Media in Big Data En...

引用

7th International Conference on Artificial Intelligence and Security, ICAIS 2021

作者： Wang, Shiqi Qin, Jiaohua Jiang, Mingfang Gao, ZhiChen College of Computer Science and Information Technology Central South University of Forestry and Technology Changsha410004 China Department of Information Science and Engineering Hunan First Normal University Changsha410205 China Department of Applied Mathematics and Statistics College of Engineering and Applied Sciences Stony Brook University Stony BrookNY11794 United States

ISBN: (纸本)9783030786083

Rapid development and application of big data technology is speeding up the dissemination and utilization of visible media big data. The intensive application of visual media brings about some security issues. The building of copyright protection mechanism of visual media big data under Internet environment can provide safety guarantee for content services of visual media in a digital library, and enhance integrated serviceability of digital resources in the digital library. Firstly, sparse features are extracted by exploiting the data sparsity and perception sparsity of visual media, and then a sparse perception computing model for visual media big data is built. Then the design idea of visual media copyright encryption, copyright authentication, copyright notice, and audit trail scheme are given from the point of view of sparse feature computation of visual media. Finally, a copyright protection application scheme of visual media big data under the network environment is developed. Its application in the digital library validates the effectiveness of this copyright protection mechanism of visual media. It can safeguard the confidentiality, integrity, availability, and auditing of visual media big data in the digital library, and enhance content serviceability of visual media in the digital library under big data environment. © 2021, Springer Nature Switzerland AG.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-based Spectral Efficiency Maximization in Massive MIMO-NOMA Systems with STAR-RIS

Deep Learning-based Spectral Efficiency Maximization in Mass...

引用

International Conference on Artificial Intelligence in Information and Communication (ICAIIC)

作者： Ridho Hendra Yoga Perdana Toan-Van Nguyen Yushintia Pramitarini Kyusung Shim Beongku An Dept. of Software and Communications Engineering in Graduate School Hongik University Republic of Korea School of Computer Science and Engineering International University - Vietnam National University HCM City Vietnam School of Computer Engineering and Applied Mathematics Hankyong National University Republic of Korea Dept. of Software and Communications Engineering Hongik University Republic of Korea

This paper studies a deep learning-based framework for spectral efficiency maximization problem in massive multiple-input multiple-output (MIMO)-non-orthogonal multiple access (NOMA) systems with simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR-RIS). We formulate the spectral efficiency maximization with a joint design of power allocation of the users, phase shift matrix of transmission and reflection element at the STAR-RIS. Since the problem is non-convex and power allocation of the users and reflector/transmitter elements at a STAR-RIS are coupled, it is very challenging to solve optimally. We propose a low-complexity iterative algorithm based on the inner approximation (IA) method to solve this problem with guaranteed convergence at a relatively optimal level. For real-time optimization, we design a deep learning (DL) framework to predict the optimal solution of power allocation of users, phase shift matrix of transmission and reflection elements at the STAR-RIS according to distances and channel gains from the base station (BS) to STAR-RIS and from STAR-RIS to users. Simulation results show that the suggested scheme improves the spectral efficiency (SE) compared to the massive MIMO system with direct link and without STAR-RIS. Besides, the DL framework can predict the optimal solution within a short time under the suggested scheme.

关键词： Deep learning Base stations Spectral efficiency Simulation Massive MIMO Reflection Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Anomaly Detection with Variance Stabilized Density Estimation

arXiv

引用

arXiv 2023年

作者： Rozner, Amit Battash, Barak Li, Henry Wolf, Lior Lindenbaum, Ofir Faculty of Engineering Bar Ilan University Ramat-Gan Israel Department of Applied Mathematics Yale University New HavenCT United States School of Computer Science Tel Aviv University Tel-Aviv Israel

We propose a modified density estimation problem that is highly effective for detecting anomalies in tabular data. Our approach assumes that the density function is relatively stable (with lower variance) around normal samples. We have verified this hypothesis empirically using a wide range of real-world data. Then, we present a variance-stabilized density estimation problem for maximizing the likelihood of the observed samples while minimizing the variance of the density around normal samples. To obtain a reliable anomaly detector, we introduce a spectral ensemble of autoregressive models for learning the variance-stabilized distribution. We have conducted an extensive benchmark with 52 datasets, demonstrating that our method leads to state-of-the-art results while alleviating the need for data-specific hyperparameter tuning. Finally, we have used an ablation study to demonstrate the importance of each of the proposed components, followed by a stability analysis evaluating the robustness of our model. © 2023, CC BY.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Prediction of Vehicle Braking State Based on Longitudinal Dynamics Using On-Road Driving Data

SSRN

引用

SSRN 2023年

作者： Jensen, Kenneth M. Santos, Ilmar F. Clemmensen, Line K.H. Theodorsen, Søren Corstens, Harry J.P. Department of Civil and Mechanical Engineering Technical University of Denmark Kgs. Lyngby Denmark Department of Applied Mathematics and Computer Science Technical University of Denmark Kgs. Lyngby Denmark ILIAS Solutions Brussels Belgium

This work considers the problem of predicting the braking state of vehicles i.e., when the friction brakes are being applied. The work is aimed at providing the foundation for the prediction of brake pad wear from vehicle usage data. The braking state is predicted from vehicle longitudinal dynamics, considering 6-axis inertial measurement unit (IMU), global navigation satellite system (GNSS), and vehicle on-board diagnostics (OBD-II) data, along with sensor fusion for more accurate vehicle state estimation. The proposed method aims at providing broad applicability to different vehicles, by using only standard OBD-II data instead of relying on manufacturer specific data. Rolling resistance coefficient and product of aerodynamic drag coefficient and frontal area are estimated using linear regression on data from vehicle coast-down tests with the drivetrain disengaged. Engine mass moment of inertia along with engine braking torque is estimated from similar tests with the drivetrain engaged in different gears. The engine braking torque is approximated using a polynomial expression in the engine speed. Braking state predictions are made by comparing measured longitudinal decelerations with estimated, assuming that if the measured exceeds the estimated, then the difference is caused by the application of the friction brakes. Experimental validation was carried out using two modern passenger cars. Comparisons of measured and estimated decelerations from coast-down tests with fitted parameters show good agreements when the drivetrain is disengaged, as well as engaged. For one vehicle labels for the braking state are obtained indirectly using a camera pointed at the brake pedal, using object tracking to determine if the brakes are being applied. For the other vehicle, the braking states are obtained more directly trough access to the brake pressure. Overall prediction performance is good with accuracy >94% and precision around 99%, while recall is around 90% across the two v

关键词： Parameter estimation

来源：评论

学校读者我要写书评

暂无评论

Gcl-Psd: Graph Contrastive Learning for Phishing Scams Detection in Ethereum Networks

SSRN

引用

SSRN 2023年

作者： Sui, Hao Zhang, Jiale Sun, Xiaobing Chen, Bing Meng, Weizhi Yu, Shui School of Information Engineering Yangzhou University Yangzhou225009 China Yangzhou University China Department of Applied Mathematics and Computer Science Technical University of Denmark Copenhagen Denmark School of Computing Science University of Technology Sydney UltimoNSW2007 Australia

Currently, Ethereum has become a public blockchain platform for developers to build and deploy smart contracts and decentralized applications (DApps). However, the fact that accounts of the user are able to trade directly only through their addresses in Ethereum, phishing scam attackers can easily disguise themselves as legitimate accounts to defraud large amounts of money. At present, phishing scam detection methods mainly focus on improving the detection accuracy by continuously extracting the account's feature information. Another issue is data imbalance, since the current publicly available URLs for labeling phishing scam data are no longer updated, it becomes an incomplete understanding of the data by supervised learning methods. To address these challenges, we present a self-supervised phishing scams detection method based on graph contrastive learning, named GCL-PSD, which can effectively handle the unavailability of labeled data. GCL-PSD can learn features between accounts by constructing positive and negative samples without labeling. To further enhance the inconspicuous feature representation in contrastive learning, our method leverages ``node versus local subgraph" as contrastive instances, and learns feature information of neighboring nodes through the contrastive training between nodes and subgraphs. Additionally, our extensive experimental results on real-world datasets demonstrate that GCL-PSD can effectively detect phishing scams without relying on training labels and outperforms baseline methods (97% Precision, and 95% F1 score). © 2023, The Authors. All rights reserved.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

An Array of Bandpass Detectors for Measuring Beam Spectral Components

An Array of Bandpass Detectors for Measuring Beam Spectral C...

引用

applied Sensing Conference (APSCON), IEEE

作者： Mojtaba Jahangiri Paolo Sberna Amir Sammak Stoyan Nihtianov A Department of Microelectronics Faculty of Electrical Engineering Mathematics and Computer Science Delft University of Technology Mekelweg 4 Delft Netherlands B QuTech and Netherlands Organization for Applied Scientific Research (TNO) Stieltjesweg 1 Delft Netherlands

A clear understanding of the spectral components of an irradiated beam, or captured optical emission, is essential to optimize an optical system and increase its performance. Logically, for this purpose a grating-based spectrometer could be the first choice. However, in the case of a wide range spectrum, and for radiation with one dominant wavelength, this option may not work well. In this paper, we present a technique based on an array of bandpass detectors to measure accurately the power of a number of beam-specific spectral components in a wide spectrum range: from soft X-ray to infrared. The main unique features of this technique are: customization for specific wavelengths of interest; vacuum compatibility; and high sensitivity to low-energy spectral components in the presence of one or more dominant highpower spectral components.

关键词： Optical filters Sensitivity Stimulated emission Wavelength measurement Ultraviolet sources Detectors Vacuum technology

来源：评论

学校读者我要写书评

暂无评论

A heterogeneous graph cross-omics attention model for single-cell representation learning

A heterogeneous graph cross-omics attention model for single...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Yue Liu Junfeng Zhang Shulin Wang Wei Zhang Xiangxiang Zeng Chee Keong Kwoh College of Computer Science and Electronic Engineering Hunan University Changsha Hunan Hangzhou Machine Learning Research and Development Center Sina Weibo Hangzhou Zhejiang College of Computer Engineering & Applied Mathematics Changsha University Changsha Hunan School of Computer Science and Engineering Nanyang Technological University Singapore

ISBN: (数字)9781665468190

ISBN: (纸本)9781665468206

Single-cell multi-omics sequencing technologies allow simultaneous measurement of transcriptome and epigenome profiles in the same cell, providing unprecedented opportunities to dissect cell heterogeneity. Despite great efforts, conjoint analysis of single-cell multi-omics data still suffers from sparsity, high dimensionality and binary. In this study, we present a heterogeneous graph cross-omics attention model (scHGA), a computational tool based on a heterogeneous graph neural network combining two attention mechanisms to jointly analyze single-cell multi-omics data based on different protocols data, including SNARE-seq, scMT-seq and sci-CAR. To avoid the cell heterogeneity of single-omics data, scHGA automatically learns a cell association graph to capture neighbor information. The latent representation of aggregated cells generated by hierarchical attention can fuse knowledge across different omics to dissect cellular heterogeneity, providing a better scheme to characterize the features of cells. scHGA is an effective exploration of graph neural networks in single-cell multi-omics analysis, providing new insights into the understanding of single-cell sequencing data.

关键词： Heating systems Analytical models Sequential analysis Correlation Protocols Data analysis Biological system modeling

来源：评论

学校读者我要写书评

暂无评论

Data Assimilation for Sign-indefinite Priors: A generalization of Sinkhorn's algorithm

arXiv

引用

arXiv 2023年

作者： Dong, Anqi Georgiou, Tryphon T. Tannenbaum, Allen Department of Mechanical and Aerospace Engineering University of California IrvineCA92697 United States Department of Computer Science and Applied Mathematics & Statistics The State University of New York Stony BrookNY11794 United States

The purpose of this work is to develop a framework to calibrate signed datasets so as to be consistent with specified marginals by suitably extending the Schrödinger-Fortet-Sinkhorn paradigm. Specifically, we seek to revise sign-indefinite multi-dimensional arrays in a way that the updated values agree with specified marginals. Our approach follows the rationale in Schrödinger's problem [25, 26], aimed at updating a "prior" probability measure to agree with marginal distributions. The celebrated Sinkhorn's algorithm [28, 18] (established earlier by R. Fortet [13, 11]) that solves Schrödinger's problem found early applications in calibrating contingency tables in statistics and, more recently, multi-marginal problems in machine learning and optimal transport. Herein, we postulate a sign-indefinite prior in the form of a multi-dimensional array, and propose an optimization problem to suitably update this prior to ensure consistency with given marginals. The resulting algorithm generalizes the Sinkhorn algorithm in that it amounts to iterative scaling of the entries of the array along different coordinate directions. The scaling is multiplicative but also, in contrast to Sinkhorn, inverse-multiplicative depending on the sign of the entries. Our algorithm reduces to the classical Sinkhorn algorithm when the entries of the prior are *** Codes 49M29, 90C25 Copyright © 2023, The Authors. All rights reserved.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Learning for Interval Prediction of Electricity Demand: A Cluster-Based Bootstrapping Approach

SSRN

引用

SSRN 2024年

作者： Dube, Rohit Gautam, Natarajan Banerjee, Amarnath Nagarajan, Harsha Industrial and Systems Engineering Texas A & M University College StationTX77843 United States Electrical Engineering and Computer Science Syracuse University SyracuseNY13210 United States Applied Mathematics and Plasma Physics Los Alamos National Laboratory Los Alamos NM87545 United States

Accurate predictions of electricity demands are necessary for managing operations in a small aggregation load setting like a Microgrid. Due to low aggregation, the electricity demands can be highly stochastic and point estimates would lead to inflated errors. Interval estimation in this scenario, would provide a range of values within which the future values might lie and helps quantify the errors around the point estimates. This paper introduces a residual bootstrap algorithm to generate interval estimates of day-ahead electricity demand. A machine learning algorithm is used to obtain the point estimates of electricity demand and respective residuals on the training set. The obtained residuals are stored in memory and the memory is further partitioned. Days with similar demand patterns are grouped in clusters using an unsupervised learning algorithm and these clusters are used to partition the memory. The point estimates for test day are used to find the closest cluster of similar days and the residuals are bootstrapped from the chosen cluster. This algorithm is evaluated on the real electricity demand data from EULR (End Use Load Research) and is compared to other bootstrapping methods for varying confidence intervals. © 2024, The Authors. All rights reserved.

关键词： Machine learning

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：