检索结果-内蒙古大学图书馆

Trip route simulation for pre-Qin settlements based on a gradient descent and variable-neighborhood ant colony optimization algorithm in the Linfen Basin, China

引用

EARTH SCIENCE INFORMATICS 2021年第1期14卷 415-428页

作者： Liu, Fang Yu, Lijun Zhu, Jianfeng Nie, Yueping Sun, Yu Chinese Acad Sci Aerosp Informat Res Inst Beijing 100101 Peoples R China Beijing Jinghang Computat & Commun Res Inst Beijing 100074 Peoples R China Hainan Univ Sch Informat & Commun Engn Haikou 570228 Hainan Peoples R China

A travel or transport path reflects the settlement pattern and the spread of civilization. Travel simulations of the pre-Qin period of the Central Plains of China can deepen our understanding of the origin and development of Chinese civilization. Here, based on the idea of swarm intelligence, an ant colony optimization algorithm based on gradient descent and variable-neighborhood search (GD-VNSACO) methods is proposed to simulate the travel routes of ancestors. We simulate the process of humans gradually exploring the surrounding space and obtaining experience and inspiration in four cultural periods from 7 to 2.7 ka B.P. (including the Yangshao Period, Miaodigou II Period, Longshan Period and Xia Shang and Zhou Period). The GD-VNSACO algorithm is suitable for studying settlement travel because of its improved search ability and convergence speed based on local and overall optimization. We conclude that in the four periods, the high-density routes of transport were concentrated along the Fen River, forming a main line from north to south. Over time, high-density areas of transport and communication among settlements, as well as the transport scope, expanded. However, there was an abnormality in the Miaodigou II Period, which was mainly caused by the climate becoming dryer and colder.

关键词： Route simulation GD-VNSACO ACO Linfen Basin Variable-neighborhood research gradient descent algorithm

来源：评论

学校读者我要写书评

暂无评论

Hybrid gradient descent spider monkey optimization (HGDSMO) algorithm for efficient resource scheduling for big data processing in heterogenous environment

引用

JOURNAL OF BIG DATA 2020年第1期7卷 1-25页

作者： Seethalakshmi, V. Govindasamy, V. Akila, V. Pondicherry Engn Coll Dept Comp Sci & Engn Pondicherry India Pondicherry Engn Coll Dept Informat Technol Pondicherry India

Big Data constructed based on the advancement of distributed computing and virtualization is considered as the current emerging trends in Data Analytics. It is used for supporting potential utilization of computing resources focusing on, on-demand services and resource scalability. In particular, resource scheduling is considered as the process of resource distribution through an effective decision making process with the objective of facilitating required tasks over time. The incorporation of heterogeneous computing resources by the Big Data consumers also permits the option of reducing energy usage and enhanced resource efficiency. Further, optimal scheduling of resources is considered as an NP hard problem due to the dynamic characteristics of the resources and fluctuating users' demand. In this paper, a Hybrid gradient descent Spider Monkey Optimization (HGDSMO) algorithm is proposed to efficient resource scheduling by handling the issues and challenges in the Hadoop heterogenous environment. The proposed HGDSMO algorithm uses the gradient descentand foraging and social behavior of the spider monkey optimization algorithm involved in the objective of effective resource allocation. It is designed as the efficient task scheduling approach that balances the load of the cloud by allocating them to appropriate VMs depending on their requirements. It is also proposed as a dynamic resource management scheme for efficiently allocating the cloud resources for effective execution of clients' tasks. The simulation results of the proposed HGDSMO algorithm confirmed to be potent in throughput, load balancing and makespan compared to the baseline hybrid meta-heuristic resource allocation algorithms used for investigation.

关键词： Heterogeneous Environment Optimal Resource Allocation gradient descent algorithm Spider Monkey Optimization (SMO) Load balancing

来源：评论

学校读者我要写书评

暂无评论

A novel filtering-based recursive identification method for a fractional-order Hammerstein state space system with piecewise nonlinearity

引用

PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART I-JOURNAL OF SYSTEMS AND CONTROL ENGINEERING 2025年

作者： Lang, Hongjun Bi, Yiqun Li, Meihang Ji, Yan Qingdao Univ Sci & Technol Coll Automat & Elect Engn Songlin Rd 99 Qingdao 266061 Peoples R China

This paper investigates parameters and states estimation for a class of fractional-order state space systems with colored noises. To provide accurate parameter estimation, we suggest a novel gradient descent algorithm based on the extended Kalman filtering. The new approach features lower estimation error variances and a faster convergence rate than the conventional gradient descent algorithm. A data filtering is introduced to filter the input and output data, thereby reducing the impact of colored noises on the accuracy of the parameter estimates.

关键词： Piecewise linearity fractional-order system parameter estimation state filtering gradient descent algorithm

来源：评论

学校读者我要写书评

暂无评论

Optimal Control of Nonlinear Competitive Epidemic Spreading Processes With Memory in Heterogeneous Networks

引用

IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING 2025年第1期12卷 96-109页

作者： You, Jin Li, Yan Cao, Xiangyang Zhao, Daduan Chen, Yangquan Zhang, Chenghui Shandong Univ Sch Control Sci & Engn Jinan 250061 Peoples R China Luoyang Inst Sci & Technol Sch Elect Engn & Automat Luoyang 471000 Peoples R China Univ Calif Merced Mechatron Embedded Syst & Automat Lab Merced CA 95343 USA

Modeling and control of epidemic-like spreading processes, such as contagions, rumors or products in complex networks, holds profound significance for understanding transmission mechanisms, formulating effective prevention and optimizing resource allocation. This paper investigates the optimal control problems for competing processes modeled by fractional-order bi-virus systems with memory in complex networks for the first time. The proposed model performs exceptionally well in capturing the dynamics of virus transmission and immune. First, the key indicators: bi-basic reproduction numbers (BBRNs) are introduced for the metapopulation model with nonlinear infectious functions in heterogenous networks. Then they are utilized to classify the equilibria, including extinction, absolute dominance and coexistence ones. Second, sufficient conditions for the stability of the equilibria are derived. Leveraging this result, an optimal therapeutic protocol is presented to eradicate viruses and minimize the cost function simultaneously. The corresponding optimal control solutions are generated via gradient descent algorithm, which can converge relatively quickly by iteratively adjusting control variables. Particularly, the role of fractional-order $\alpha$ in system modeling and optimization is deeply probed into. Finally, numerical examples are also included at the end of this paper to further shed light on the effectiveness of our results.

关键词： Optimal control Epidemics Process control Predictive models Mathematical models Infectious diseases Prevention and mitigation COVID-19 Heuristic algorithms Heterogeneous networks Complex network competing process gradient descent algorithm fractional-order system optimal control

来源：评论

学校读者我要写书评

暂无评论

Chirality-Free Full Decoupling of Jones Matrix Phase-Channels with a Planar Minimalist Metasurface

引用

NANO LETTERS 2025年第4期25卷 1322-1328页

作者： Mu, Xinyang Qin, Haoye Zhao, Wannian Han, Sanyang Liu, Ziqi Shi, Yuzhi Huang, Wei Li, Bo Song, Qinghua Tsinghua Univ Tsinghua Shenzhen Int Grad Sch Shenzhen 518055 Peoples R China Chinese Acad Sci Suzhou Inst Nanotech & Nanob SINANO Key Lab Multifunct Nanomat & Smart Syst Suzhou 215123 Peoples R China Tongji Univ Inst Precis Opt Engn Sch Phys Sci & Engn Shanghai 200092 Peoples R China Suzhou Lab Suzhou 215000 Peoples R China

The complete manipulation of Jones matrix phase-channels using metasurfaces brings forth unparalleled possibilities across diverse wavefront modulation applications. Traditionally, achieving independent control over all four phase-channels usually involves the introduction of chirality with multilayer or three-dimensional metasurfaces. Here, we present a general chirality-free method that relies on polarization base transformation with a planar minimalist metasurface, effectively decoupling the four Jones matrix phase-channels, thereby unleashing the fundamental boundaries imposed by conventional linear or circular polarization bases. To achieve independent wavefront modulation across these four channels, we employ an inverse design methodology leveraging a gradient descent algorithm. Remarkably, our strategy enables four channel wavefront modulations with only three control degrees of freedom within the minimalist meta-structures. As a proof-of-concept, we experimentally project four far-field holographic images, each corresponding to one of the four phase-channels, holding promises for various applications such as augmented/virtual reality display, information encryption, optical communication and data storage.

关键词： Metasurface Meta-Hologram Polarization Multiplexing Chirality Free gradient descent algorithm Jones Matrix

来源：评论

学校读者我要写书评

暂无评论

Dynamic gain-based neural network backstepping control with its applications to a quad-rotor hover

引用

TRANSACTIONS OF THE INSTITUTE OF MEASUREMENT AND CONTROL 2025年第4期47卷 677-687页

作者： Yang, Jiaxing Yang, Xuebo Zheng, Xiaolong Harbin Inst Technol Sch Astronaut Res Inst Intelligent Control & Syst Harbin 150001 Peoples R China

In this paper, a novel neural network (NN) backstepping control method is proposed for a class of uncertain nonlinear systems with unknown control direction functions. To solve the control problems caused by unknown control direction functions, a method called "virtual control coefficient" is presented using equivalence transformations. However, to improve the flexibility of the control method, a function named "dynamic gain" is introduced to design the feedback gains of the NN backstepping controllers. Moreover, instead of using sigma-modification, gradient descent algorithm is applied to train the weights of NNs such that the unknown nonlinearities of the system can be well approximated by NNs. With the help of Lyapunov stability criterion, it can be proved that the system tracking error is semi-global uniformly ultimately bounded. Finally, the effectiveness of the proposed control method is verified by the experimental results on a quad-rotor hover platform.

关键词： Neural network backstepping dynamic gain gradient descent algorithm unknown control direction functions quad-rotor hover

来源：评论

学校读者我要写书评

暂无评论

Dual Jones Matrices Empowered Six Phase Channels Modulation with Single-Layer Monoatomic Metasurfaces

引用

LASER & PHOTONICS REVIEWS 2025年第7期19卷

作者： Liu, Ziqi Mu, Xinyang Song, Helun Yu, Yefeng Zhang, Ruirui Zou, Yonggang Geng, Zihan Wang, Mingdi Chen, Linghu Sun, Yunfei Tong, Xiaogang Song, Qinghua Huang, Wei Changchun Univ Sci & Technol Natl Key Lab High Power Semicond Lasers Changchun 130022 Jilin Peoples R China Chinese Acad Sci Suzhou Inst Nanotech & Nanobion Key Lab Multifunct Nanomat & Smart Syst Suzhou 215123 Jiangsu Peoples R China Chinese Acad Sci Suzhou Inst Nanotech & Nanobion Key Lab Semicond Display Mat & Chips Suzhou 215123 Jiangsu Peoples R China Tsinghua Univ Tsinghua Shenzhen Int Grad Sch Shenzhen 518055 Guangdong Peoples R China Nanjing Univ Sci & Technol Sch Microelect Nanjing 210094 Jiangsu Peoples R China Soochow Univ Sch Mech & Elect Engn Suzhou 215021 Jiangsu Peoples R China Suzhou Yihua Biomed Technol Co Ltd Suzhou 215000 Jiangsu Peoples R China Suzhou Univ Sci & Technol Sch Elect & Informat Engn Suzhou 215009 Jiangsu Peoples R China Taiyuan Inst Technol Dept Elect Engn Taiyuan 030008 Shanxi Peoples R China

A comprehensive manipulation of the Jones matrix phase channels is crucial for enhancing the information capacity and security of the metasurface. However, a single-layer planar metasurface, without the incorporation of chirality, can only achieve a maximum of three independent phase channels for single Jones matrix under either linear or circular polarization bases. Here, an effective strategy is proposed that utilizes dual Jones matrices in different polarization bases with a single-layer monoatomic metasurface, thus extending the number of independent phase channels to six. To encode six holographic images into these six phase channels, a three-step gradient descent algorithm is introduced. As a proof of principle, a metasurface consisting of arrays of monoatomic dielectric structure is designed and fabricated in each unit cell, which exhibits six independent holographic images in the far field. The demonstrated metasurface platform is expected to open up new possibilities for the development of optical devices for applications in high-capacity information storage, high-security encrypted communication, and high-solution optical displays.

关键词： dual Jones matrices gradient descent algorithm holography metasurface six phase channels modulation

来源：评论

学校读者我要写书评

暂无评论

Literature Survey: A Survey on Stock Market Prediction Using LSTM and gradient descent

Literature Survey: A Survey on Stock Market Prediction Using...

引用

5th International Conference on Recent Trends in Machine Learning, IoT, Smart Cities, and Applications, ICMISC 2024

作者： Chaudhari, Deepak Suryawanshi, Gaurav Koparkar, Tanmay Sal, Ujwala Patil, Shubham Dr.D.Y Patil Institute of Technology Pimpri Pune India

ISBN: (纸本)9789819788644

In the quest to enhance stock market predictions and provide investors with valuable insights, we endeavor to create a comprehensive stock market prediction application. This application will seamlessly combine machine learning (ML) and deep learning (DL) models with human sentiment analysis, employing statistical tools such as exponential weighted moving averages and gradient descent optimization. The primary goal is to generate precise projections of future stock prices. A unique aspect of this endeavor is the dynamic adjustment of model predictions through a combination of gradient descent and auto-correlation techniques. These adjustments are made in response to ever-changing external factors, with human sentiment toward the stock being a pivotal factor in this context. As these external influences evolve, the application ensures that both gradient descent and auto-correlation adapt themselves accordingly. The core objective of this project is to deliver a platform that not only refines stock market forecasts but also empowers investors with valuable information. This is achieved by harnessing a rich blend of quantitative and qualitative data sources. The application aims to provide a holistic view of the stock market, integrating advanced data-driven methodologies with human sentiment analysis to assist investors in making well-informed decisions in the dynamic world of financial markets. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Artificial neural network Auto correlation Deep learning gradient descent algorithm Long-short term memory (LSTM) Recurrent neural network Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Heat losses in directly buried solar heat collection networks in high-altitude regions

引用

SOLAR ENERGY 2025年 290卷

作者： Chen, Hongsen Wang, Baichao Song, Cong Wang, Dengjia Liu, Yanfeng Xian Univ Architecture & Technol Sch Bldg Serv Sci & Engn 13Yanta Rd Xian 710055 Peoples R China Xian Univ Architecture & Technol State Key Lab Green Bldg 13Yanta Rd Xian 710055 Peoples R China

Due to the fluctuations in the medium temperature, the solar collector system (SCS) based on temperature difference control currently lacks a medium temperature value for accurately calculating the operational heat loss of directly buried solar heat collection pipelines. This research proposed a method for calculating heat loss utilizing an equivalent medium temperature (EMT). Initially, a computational model is established for assessing the heat loss of directly buried solar collector pipelines in Xizang plateau. Based on the primary factors influencing heat loss, the study investigated the temperature drop and operational heat loss patterns of directly buried solar heat collection pipelines. The ranges of regional equivalent medium temperature (REMT) and condition equivalent medium temperature (CEMT) were optimized using the gradient descent algorithm and heat loss calculation theory. The variations of REMT and CEMT with different regions and key heat loss factors were analyzed, and a CEMT association model was obtained. The EMT is highest in Lhasa and lowest in Gar, related to the ambient temperature for heating design and collector field operation time. For REMT, Lhasa ranges from 50.4 degrees C to 52.8 degrees C, and Gar from 31.1 degrees C to 33.4 degrees C. CEMT decreases with increasing flow rate coefficient and nominal diameter, ranging in Lhasa from 77.1 degrees C to 35.5 degrees C, and in Gar from 54.9 degrees C to 18.5 degrees C. The study aims to provide fundamental data and theoretical support for heat loss calculation and designing the insulation thickness of directly buried solar heat collection pipelines in high-altitude regions.

关键词： Equivalent medium temperature Solar heat collection pipeline Directly buried pipeline gradient descent algorithm Heat loss calculation Altitude

来源：评论

学校读者我要写书评

暂无评论

Neural fractional order differential equations

引用

EXPERT SYSTEMS WITH APPLICATIONS 2025年 267卷

作者： Sivalingam, S. M. Govindaraj, V. Natl Inst Technol Puducherry Dept Math Karaikal 609609 India

Neural ordinary differential equations are architectures that connect the neural network theory with dynamical system, providing scope for continuous propagation of the layers. Meanwhile, fractional-order differential equations offer an approach to model systems with the scope to retain long-term memory. In this study, we use the idea of fractional derivative in the neural differential equations and develop the fractional version named the neural fractional differential equations. These networks can retain long-term memory and is trained using the ensemble Kalman inversion algorithm. The detailed derivation of the network architecture and the existence of a solution using Schauder's fixed point theorem are given in detail. The forward propagation of the system is executed utilizing the L1 predictor-corrector. The issue in obtaining the gradient is explained in detail. The ensemble Kalman inversion is used to train the network memory efficiently. Numerical results for studying the dynamics of linear and nonlinear systems are provided to demonstrate the effectiveness of the network with the proposed learning method. Also, the model's capacity to fit with real-world data is shown in the HIV, monkey-pox, Delhi temperature, and Netflix stock price datasets. The method has shown excellent performance in fewer iterations compared to neural ordinary differential equations, classical recurrent neural network, gated recurrent unit, long short-term memory networks and Bi-directional long short-term memory neural network.

关键词： Caputo derivative Neural ordinary differential equations gradient descent algorithm Ensemble Kalman inversion

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：