检索结果-内蒙古大学图书馆

5th International Conference on Computer science and Management technology, ICCSMT 2024

作者： Hu, Ruijie Faculty of Science and Technology Guangdong Provincial Key Laboratory of Interdisciplinary Research and Application for Data Science BNU-HKBU United International College Zhuhai China

ISBN: (纸本)9798400709999

With the rapid development of financial markets, stock price prediction, as a highly complex and challenging topic, has attracted more and more attention from academia and industry. This study aims to use multiple machine learning algorithms to predict stock market prices, especially exploring the advantages of deep learning models in capturing market nonlinear and time series characteristics. In this article, a machine learning model is used for contribution analysis, analyzing multiple features of stocks, performing a weighted combination analysis of features, and then using a convolutional neural network to perform feature extraction and analysis of stocks, and combining the attention mechanism for deep feature extraction, and finally use the long short-term memory network (LSTM) model to output the model to analyze and predict future stock trends. The experimental results show that combining deep learning analysis technology and factor screening machine can significantly improve the prediction accuracy of the model. At the same time, this article also compared the performance of different models in different market environments, and concluded that in markets with higher volatility, models based on deep learning are more stable. Ultimately, this research provides a new technical means for risk management and investment decisions in financial markets. © 2024 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

From GARCH to Neural Network for Volatility Forecast 38

From GARCH to Neural Network for Volatility Forecast

引用

38th AAAI Conference on Artificial Intelligence, AAAI 2024

作者： Zhao, Pengfei Zhu, Haoren Wilfred Siu Hung, N.G. Lee, Dik Lun Guangdong Provincial Key Laboratory of Interdisciplinary Research and Application for Data Science BNU-HKBU United International College China Hong Kong University of Science and Technology Hong Kong

ISBN: (纸本)1577358872

Volatility, as a measure of uncertainty, plays a crucial role in numerous financial activities such as risk management. The Econometrics and Machine Learning communities have developed two distinct approaches for financial volatility forecasting: the stochastic approach and the neural network (NN) approach. Despite their individual strengths, these methodologies have conventionally evolved in separate research trajectories with little interaction between them. This study endeavors to bridge this gap by establishing an equivalence relationship between models of the GARCH family and their corresponding NN counterparts. With the equivalence relationship established, we introduce an innovative approach, named GARCH-NN, for constructing NN-based volatility models. It obtains the NN counterparts of GARCH models and integrates them as components into an established NN architecture, thereby seamlessly infusing volatility stylized facts (SFs) inherent in the GARCH models into the neural network. We develop the GARCH-LSTM model to showcase the power of the GARCH-NN approach. Experiment results validate that amalgamating the NN counterparts of the GARCH family models into established NN models leads to enhanced outcomes compared to employing the stochastic and NN models in isolation. Copyright © 2024, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Detection of Invisible/Occluded Vehicles Using Passive RFIDs 6th

Detection of Invisible/Occluded Vehicles Using Passive RFIDs

引用

6th EAI International Conference on Intelligent Transport Systems, INTSYS 2022

作者： Hou, Ricky Yuen-Tan Guangdong Provincial Key Laboratory of Interdisciplinary Research and Application for Data Science Faculty of Science and Technology BNU-HKBU United International College Zhuhai519000 China

ISBN: (纸本)9783031308543

Vehicle detection in autonomous driving could be very challenging under adverse road conditions. The problem has been studied intensively. However, recent studies have shown that the problem remains unsolved, especially when the vehicles are occluded or under low-light conditions. This paper adopts a different approach to vehicle detection by taking advantage of RFID technology. Specifically, RFID tags are attached to the vehicle’s surfaces, and then a system is designed to detect, locate, and track those tags dynamically. In addition, RFIDs are allowed to store user data on chips. To fully utilize this feature, this paper develops an algorithm to select and store the most critical information in tags for recovering the boundaries of occluded vehicles and finding the vehicle’s location and orientation. The proposed method achieves the following objectives: (1) Vehicles could be detected at a relatively long distance in any conditions (including low-light or adverse weather). (2) The boundary of the occluded vehicle could be recovered. (3) Vehicles are still detectable even if they are turned off. (4) The implementation is relatively simple. The evaluation results have shown that the proposed method is able to detect a vehicle’s orientation and rotation and recover the boundary for an occluded vehicle. © 2023, ICST Institute for Computer sciences, Social Informatics and Telecommunications Engineering.

关键词： Vehicle safety

来源：评论

学校读者我要写书评

暂无评论

GBC: Gaussian-Based Colorization and Super-Resolution for 3D Reconstruction 19

GBC: Gaussian-Based Colorization and Super-Resolution for 3D...

引用

19th ACM SIGGRAPH International Conference on Virtual-Reality Continuum and its applications in Industry, VRCAI 2024

作者： Liao, Jiecheng He, Shi Yuan, Yichen Zhang, Hui Department of Computer Science and Technology BNU-HKBU United International College ZhuHai China Guangdong Provincial Key Laboratory of Interdisciplinary Research and Application for Data Science BNU-HKBU United International College Zhuhai China

ISBN: (纸本)9798400713484

In this paper, we introduce GBC, an advanced framework for transforming low-resolution, monochrome video sequences into high-resolution, colorized, and geometrically accurate 3D models. GBC combines Bidirectional Optical Flow Super-Resolution (BOF-SR) for temporal super-resolution with a novel colorization approach, Temporal Optical Flow-based Colorization (TOF-CO), designed to enhance frame-to-frame temporal consistency. The integration of these modules with COLMAP-based 3D Gaussian splatting further extends GBC's capability to reconstruct high-fidelity 3D scenes. Additionally, we created a custom dataset tailored to the challenges of low-light, low-quality historical footage, enabling robust evaluation alongside public datasets. This solution offers a new approach to video restoration, advancing temporal coherence, color accuracy, and 3D scene fidelity. The source code is publicly available at https://***/ffftuanxxx/GBC. © 2024 ACM.

关键词： 3D reconstruction

来源：评论

学校读者我要写书评

暂无评论

A Knowledge-Injected Curriculum Pretraining Framework for Question Answering 24

A Knowledge-Injected Curriculum Pretraining Framework for Qu...

引用

33rd ACM Web Conference, WWW 2024

作者： Lin, Xin Su, Tianhuang Huang, Zhenya Xue, Shangzi Liu, Haifeng Chen, Enhong School of Computer Science and Technology University of Science and Technology of China State Key Laboratory of Cognitive Intelligence Hefei China Guangdong OPPO Mobile Telecommunications Corp. Ltd Shenzhen China University of Science and Technology of China Hefei China Anhui Province Key Laboratory of Big Data Analysis and Application University of Science and Technology of China State Key Laboratory of Cognitive Intelligence Hefei China

ISBN: (纸本)9798400701719

Knowledge-based question answering (KBQA) is a key task in natural language processing research, and also an approach to access the web data and knowledge, which requires exploiting knowledge graphs (KGs) for reasoning. In the literature, one promising solution for KBQA is to incorporate the pretrained language model (LM) with KGs by generating KG-centered pretraining corpus, which has shown its superiority. However, these methods often depend on specific techniques and resources to work, which may not always be available and restrict its application. Moreover, existing methods focus more on improving language understanding with KGs, while neglect the more important human-like complex reasoning. To this end, in this paper, we propose a general K nowledge-I njected C urriculum P retraining framework (KICP) to achieve comprehensive KG learning and exploitation for KBQA tasks, which is composed of knowledge injection (KI), knowledge adaptation (KA) and curriculum reasoning (CR). Specifically, the KI module first injects knowledge into the LM by generating KG-centered pretraining corpus, and generalizes the process into three key steps that could work with different implementations for flexible application. Next, the KA module learns knowledge from the generated corpus with LM equipped with an adapter as well as keeps its original natural language understanding ability to reduce the negative impacts of the difference between the generated and natural corpus. Last, to enable the LM with complex reasoning, the CR module follows human reasoning patterns to construct three corpora with increasing difficulties of reasoning, and further trains the LM from easy to hard in a curriculum manner to promote model learning. We provide an implementation of the general framework, and evaluate the proposed KICP on four real-word datasets. The results demonstrate that our framework can achieve higher performances, and have good generalization ability to other QA tasks. © 2024 ACM.

关键词： Curricula

来源：评论

学校读者我要写书评

暂无评论

NUMERICAL ENERGY DISSIPATION FOR TIME-FRACTIONAL PHASE-FIELD EQUATIONS

引用

Journal of Computational Mathematics 2025年第3期43卷 515-539页

作者： Chaoyu Quan Tao Tang Jiang Yang School of Science and Engineering The Chinese University of Hong KongShenzhen 518172China Division of Science and Technology BNU-HKBU United International CollegeZhuhai 519087China Guangdong Provincial Key Laboratory of Interdisciplinary Research and Application for Data Science BNU-HKBU United International CollegeZhuhai 519087China Department of Mathematics SUSTech International Center for Mathematics&National Center for Applied Mathematics Shenzhen(NCAMS)Southern University of Science and TechnologyShenzhen 518055China

The numerical integration of phase-field equations is a delicate task which needs to recover at the discrete level intrinsic properties of the solution such as energy dissipation and maximum *** the theory of energy dissipation for classical phase field models is well established,the corresponding theory for time-fractional phase-field models is still *** this article,we study certain nonlocal-in-time energies using the first-order stabilized semi-implicit L1 *** particular,we will establish a discrete fractional energy law and a discrete weighted energy *** extension for a(2-α)-order L1 scalar auxiliary variable scheme will be ***,we demonstrate that the energy bound is preserved for the L1 schemes with nonuniform time *** numerical experiments are carried to verify our theoretical analysis.

关键词： Time-fractional phased-field equation Allen-Cahn equations Cahn-Hilliard equations Caputo fractional derivative Energy dissipation

来源：评论

学校读者我要写书评

暂无评论

A Decreasing Upper Bound of the Energy for Time-Fractional Phase-Field Equations

引用

Communications in Computational Physics 2023年第4期33卷 962-991页

作者： Chaoyu Quan Tao Tang Boyi Wang Jiang Yang International Center for Mathematics Southern University of Science and TechnologyShenzhen 518055China Division of Science and Technology BNU-HKBU United International CollegeZhuhai 519087China Guangdong Provincial Key Laboratory of Interdisciplinary Research and Application for Data Science BNU-HKBU United International CollegeZhuhai 519087China Department of Mathematics Southern University of Science and TechnologyShenzhen 518055GuangdongChina Department of Mathematics National University of SingaporeSingapore 119076Singapore Guangdong Provincial Key Laboratory of Computational Science and Material Design Southern University of Science and TechnologyShenzhen 518055China

In this article,we study the energy dissipation property of time-fractional Allen–Cahn *** the continuous level,we propose an upper bound of energy that decreases with respect to time and coincides with the original energy at t=0 and as t tends to∞.This upper bound can also be viewed as a nonlocal-in-time modified energy which is the summation of the original energy and an accumulation term due to the memory effect of time-fractional *** particular,the decrease of the modified energy indicates that the original energy indeed decays *** in a small neighborhood at t=*** illustrate the theory mainly with the time-fractional Allen-Cahn equation but it could also be applied to other time-fractional phase-field models such as the Cahn-Hilliard *** the discrete level,the decreasing upper bound of energy is useful for proving energy dissipation of numerical ***-order L1 and second-order L2 schemes for the time-fractional Allen-Cahn equation have similar decreasing modified energies,so that stability can be *** numerical results are provided to illustrate the behavior of this modified energy and to verify our theoretical results.

关键词： Time-fractional Allen-Cahn equation energy dissipation L1 approximation L2 approximation

来源：评论

学校读者我要写书评

暂无评论

Shrinkage Estimation for Location and Scale Parameters of Logistic Distribution Under Record Values

引用

Annals of data science 2024年第4期11卷 1209-1224页

作者： Gupta, Shubham Vishwakarma, Gajendra K. Elsawah, A.M. Department of Mathematics & amp Computing Indian Institute of Technology Dhanbad826004 India Department of Statistics and Data Science Faculty of Science and Technology Beijing Normal University-Hong Kong Baptist University United International College Zhuhai519087 China Guangdong Provincial Key Laboratory of Interdisciplinary Research and Application for Data Science BNU-HKBU United International College Zhuhai519087 China Department of Mathematics Faculty of Science Zagazig University Zagazig44519 Egypt

Logistic distribution (LogDis) is frequently used in many different applications, such as logistic regression, logit models, classification, neural networks, physical sciences, sports modeling, finance and health and disease studies. For instance, the distribution function of the LogDis has the same functional form as the derivative of the Fermi function that can be used to set the relative weight of various electron energies in their contributions to electron transport. The LogDis has wider tails than a normal distribution (NorDis), so it is more consistent with the underlying data and provides better insight into the likelihood of extreme events. For this reason the United States Chess Federation has switched its formula for calculating chess ratings from the NorDis to the LogDis. The outcomes of many real-life experiments are sequences of record-breaking data sets, where only observations that exceed (or only those that fall below) the current extreme value are recorded. The practice demonstrated that the widely used estimators of the scale and location parameters of logistic record values, such as the best linear unbiased estimators (BLUEs), have some defects. This paper investigates the shrinkage estimators of the location and scale parameters for logistic record values using prior information about their BLUEs. Theoretical and computational justifications for the accuracy and precision of the proposed shrinkage estimators are investigated via their bias and mean square error (MSE), which provide sufficient conditions for improving the proposed shrinkage estimators to get unbiased estimators with minimum MSE. The performance of the proposed shrinkage estimators is compared with the performances of the BLUEs. The results demonstrate that the resulting shrinkage estimators are shown to be remarkably efficient. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2023.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

EPRFL:An Efficient Privacy-Preserving and Robust Federated Learning Scheme for Fog Computing

引用

China Communications 2025年第4期22卷 202-222页

作者： Ke Zhijie Xie Yong Syed Hamad Shirazi Li Haifeng School of Computer Technology and Application Qinghai UniversityXining 810016China School of Computer and Information Science Qinghai Institute of TechnologyXining 810016China Guangdong Key Laboratory of Blockchain Security Guangzhou UniversityGuangzhou 510006China Department of Information Technology Hazara UniversityBaffa 21110Pakistan Qinghai Provincial Key Laboratory of Big Data in Finance and Artificial Intelligence Application Technology Xining 810016China

Federated learning(FL)is a distributed machine learning paradigm that excels at preserving data privacy when using data from multiple *** combined with Fog Computing,FL offers enhanced capabilities for machine learning applications in the Internet of Things(IoT).However,implementing FL across large-scale distributed fog networks presents significant challenges in maintaining privacy,preventing collusion attacks,and ensuring robust data *** address these challenges,we propose an Efficient Privacy-preserving and Robust Federated Learning(EPRFL)scheme for fog computing ***,we first propose an efficient secure aggregation strategy based on the improved threshold homomorphic encryption algorithm,which is not only resistant to model inference and collusion attacks,but also robust to fog node ***,we design a dynamic gradient filtering method based on cosine similarity to further reduce the communication *** minimize training delays,we develop a dynamic task scheduling strategy based on comprehensive *** analysis demonstrates that EPRFL offers robust security and low *** experimental results indicate that EPRFL outperforms similar strategies in terms of privacy preserving,model performance,and resource efficiency.

关键词： federated learning fog computing internet of things privacy-preserving robustness

来源：评论

学校读者我要写书评

暂无评论

An Adjusted Gray Map Technique for Constructing Large Four-Level Uniform Designs

引用

Journal of Systems science & Complexity 2023年第1期36卷 433-456页

作者： ELSAWAH A M VISHWAKARMA G K MOHAMED H S FANG Kai-Tai Department of Statistics and Data Science Faculty of Science and TechnologyBeijing Normal University-Hong Kong Baptist University United International CollegeZhuhai 519087China Guangdong Provincial Key Laboratory of Interdisciplinary Research and Application for Data Science BNU-HKBU United International CollegeZhuhai 519087China Department of Mathematics Faculty of ScienceZagazig UniversityZagazig 44519Egypt Department of Mathematics&Computing Indian Institute of Technology DhanbadDhanbad 826004India College of Transportation and Civil Engineering Fujian Agriculture and Forestry UniversityFuzhou 350002China The Key Lab of Random Complex Structures and Data Analysis The Chinese Academy of SciencesBeijing 100190China

A uniform experimental design(UED)is an extremely used powerful and efficient methodology for designing experiments with high-dimensional inputs,limited resources and unknown underlying models.A UED enjoys the following two significant advantages:(i)It is a robust design,since it does not require to specify a model before experimenters conduct their experiments;and(ii)it provides uniformly scatter design points in the experimental domain,thus it gives a good representation of this domain with fewer experimental trials(runs).Many real-life experiments involve hundreds or thousands of active factors and thus large UEDs are *** large UEDs using the existing techniques is an NP-hard problem,an extremely time-consuming heuristic search process and a satisfactory result is not *** paper presents a new effective and easy technique,adjusted Gray map technique(AGMT),for constructing(nearly)UEDs with large numbers of four-level factors and runs by converting designs with s two-level factors and n runs to(nearly)UEDs with 2^(t−1)s four-level factors and 2tn runs for any t≥0 using two simple transformation *** justifications for the uniformity of the resulting four-level designs are given,which provide some necessary and/or sufficient conditions for obtaining(nearly)uniform four-level *** results show that the AGMT is much easier and better than the existing widely used techniques and it can be effectively used to simply generate new recommended large(nearly)UEDs with four-level factors.

关键词： Aberration adjusted Gray map technique Gray map technique Hamming distance moment aberration threshold accepting algorithm uniform design

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：