检索结果-内蒙古大学图书馆

A Hybrid Method for Positioning a Moving Magnetic Target and Estimating Its Magnetic Moment

IEEE SENSORS JOURNAL 2023年第21期23卷 25882-25894页

作者： Chi, Cheng Wang, Dan Yu, Zhentao Wang, Fajie Yu, Lu Qin, Feng Navy Submarine Acad Inst Remote Sensing Qingdao 266000 Peoples R China Qingdao Univ Coll Mech & Elect Engn Qingdao 266071 Peoples R China

To solve the problem of false solutions being present in the inversion of magnetic target parameters on airborne scalar magnetometer and of the inversion method being limited to stationary targets, this article proposes a hybrid method for estimating both the motion parameters and magnetic moments of single moving magnetic target. The proposed method first measures the magnetic field signals along a cross-crossing flight trajectory and then denoises the measurement signals using a signal extraction algorithm based on orthonormal basis. After that, it builds an optimization model based on magnetic dipole model and the geometric relations between the magnetic target and the magnetometer. To solve the problem of the model easily converging to locally optimal solutions, a hybrid algorithm combining the adaptive weighted particle swarm optimization (AWPSO) algorithm and the Levenberg-Marquardt (LM) algorithm is proposed to determine the target parameters. The hybrid algorithm first uses the AWPSO algorithm to produce initial values for the target parameters via iteration, and then, the initial values of the parameters are used as the input to determine the precise values of the target parameters by fitting the LM algorithm. Simulation and actual test results show that the proposed method has high positioning accuracy and good robustness. Simulation shows that when Gaussian white noise with a standard deviation of 0.2 nT is superimposed, the max relative error of the target parameter estimation is 4.6%. The field test results of a water surface ship show that the average positioning error of the method is 20.9 m.

关键词： Magnetic moment moving magnetic target optimization algorithm positioning scalar magnetometer

来源：评论

学校读者我要写书评

暂无评论

INTEGRATION OF GRADIENT LEAST MEAN SQUARES IN BIDIRECTIONAL LONG SHORT-TERM (LSTM) MEMORY NETWORKS FOR METALLURGICAL BEARING BALL FAULT DIAGNOSIS

引用

METALURGIJA 2024年第3-4期63卷 403-406页

作者： Tang, X. F. Long, Y. B. Univ Sci & Technol Liaoning Sch Comp Sci & Software Engn Anshan Peoples R China

This paper introduces a novel diagnostic approach for bearing ball failures: a synergistic implementation of a bidileverages deep analysis of operational data from bearings, enabling the precise identification of incipient bearing ball failures at early stages, thus markedly improving prediction accuracy. Our empirical results underscore the superior performance of this composite methodology in accurately detecting a spectrum of five mechanical bearing ball failure types, achieving a substantial enhancement in diagnostic precision.

关键词： bearing ball fault detection mechanical vibration Bi-LSTM optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

A High-Accuracy Advanced Persistent Threat Detection Model: Integrating Convolutional Neural Networks with Kepler-Optimized Bidirectional Gated Recurrent Units

引用

ELECTRONICS 2025年第9期14卷 1772-1772页

作者： Hu, Guangwu Sun, Maoqi Zhang, Chaoqin Shenzhen Inst Informat Technol Sch Comp & Software Shenzhen 518029 Peoples R China Zhengzhou Univ Light Ind Coll Comp Sci & Technol Zhengzhou 450002 Peoples R China

Advanced Persistent Threat (APT) refers to a highly targeted, sophisticated, and prolonged form of cyberattack, typically directed at specific organizations or individuals. The primary objective of such attacks is the theft of sensitive information or the disruption of critical operations. APT attacks are characterized by their stealth and complexity, often resulting in significant economic losses. Furthermore, these attacks may lead to intelligence breaches, operational interruptions, and even jeopardize national security and political stability. Given the covert nature and extended durations of APT attacks, current detection solutions encounter challenges such as high detection difficulty and insufficient accuracy. To address these limitations, this paper proposes an innovative high-accuracy APT attack detection model, CNN-KOA-BiGRU, which integrates Convolutional Neural Networks (CNN), Bidirectional Gated Recurrent Units (BiGRU), and the Kepler optimization algorithm (KOA). The model first utilizes CNN to extract spatial features from network traffic data, followed by the application of BiGRU to capture temporal dependencies and long-term memory, thereby forming comprehensive temporal features. Simultaneously, the Kepler optimization algorithm is employed to optimize the BiGRU network structure, achieving globally optimal feature weights and enhancing detection accuracy. Additionally, this study employs a combination of sampling techniques, including Synthetic Minority Over-sampling Technique (SMOTE) and Tomek links, to mitigate classification bias caused by dataset imbalance. Evaluation results on the CSE-CIC-IDS2018 experimental dataset demonstrate that the CNN-KOA-BiGRU model achieves superior performance in detecting APT attacks, with an average accuracy of 98.68%. This surpasses existing methods, including CNN (93.01%), CNN-BiGRU (97.77%), and Graph Convolutional Network (GCN) (95.96%) on the same dataset. Specifically, the proposed model demonstrates an acc

关键词： APT detection imbalanced dataset SMOTE-Tomek combined sampling optimization algorithm deep learning networks

来源：评论

学校读者我要写书评

暂无评论

Crystal Symmetry-Inspired algorithm for Optimal Design of Contemporary Mono Passivated Emitter and Rear Cell Solar Photovoltaic Modules

引用

algorithmS 2024年第7期17卷 297页

作者： Vais, Ram Ishwar Sahay, Kuldeep Chiranjeevi, Tirumalasetty Devarapalli, Ramesh Knypinski, Lukasz Rajkiya Engn Coll Sonbhadra Elect Engn Dept Churk 231206 Uttar Pradesh India Inst Engn & Technol Lucknow Elect Engn Dept Lucknow 226021 Uttar Pradesh India Inst Chem Technol Dept Elect Elect & Instrumentat Engn Indianoil Odisha Campus Bhubaneswar 751013 Orissa India Poznan Univ Tech Fac Automat Control Robot & Elect Engn PL-60965 Poznan Poland

A metaheuristic algorithm named the Crystal Structure algorithm (CrSA), which is inspired by the symmetric arrangement of atoms, molecules, or ions in crystalline minerals, has been used for the accurate modeling of Mono Passivated Emitter and Rear Cell (PERC) WSMD-545 and CS7L-590 MS solar photovoltaic (PV) modules. The suggested algorithm is a concise and parameter-free approach that does not need the identification of any intrinsic parameter during the optimization stage. It is based on crystal structure generation by combining the basis and lattice point. The proposed algorithm is adopted to minimize the sum of the squares of the errors at the maximum power point, as well as the short circuit and open circuit points. Several runs are carried out to examine the V-I characteristics of the PV panels under consideration and the nature of the derived parameters. The parameters generated by the proposed technique offer the lowest error over several executions, indicating that it should be implemented in the present scenario. To validate the performance of the proposed approach, convergence curves of Mono PERC WSMD-545 and CS7L-590 MS PV modules obtained using the CrSA are compared with the convergence curves obtained using the recent optimization algorithms (OAs) in the literature. It has been observed that the proposed approach exhibited the fastest rate of convergence on each of the PV panels.

关键词： optimization algorithm crystal symmetry solar photovoltaic single diode model double diode model

来源：评论

学校读者我要写书评

暂无评论

Landslide susceptibility prediction using machine learning and remote sensing: Case study in Thua Thien Hue province, Vietnam

引用

GEOLOGICAL JOURNAL 2024年第2期59卷 636-658页

作者： Nguyen, Huu Duy Nguyen, Quoc Huy Du, Quan Vu Viet Pham, Viet Thanh Pham, Le Tuan Hoang, Thanh Van Truong, Quang-Hai Bui, Quang-Thanh Petrisor, Alexandru-Ionut Vietnam Natl Univ Univ Sci Fac Geog Hanoi Vietnam Feng Chia Univ Geog Informat Syst Res Ctr Taichung Taiwan Vietnam Natl Univ VNU Inst Vietnamese Studies & Dev Sci Hanoi Vietnam Ion Mincu Univ Architecture & Urbanism Doctoral Sch Urban Planning Bucharest Romania Tech Univ Moldova Fac Urbanism & Architecture Dept Architecture Kishinev Moldova Natl Inst Res & Dev Construct Urbanism & Sustainab Bucharest Romania Natl Inst Res & Dev Tourism Bucharest Romania Vietnam Natl Univ Univ Sci Fac Geog 334 Nguyen Trai Hanoi Vietnam

Landslides lead to widespread devastation and significant loss of life in mountainous regions around the world. Susceptibility assessments can provide critical data to help decision-makers, for example, local authorities and other organizations, mitigating the landslide risk, although the accuracy of existing studies needs to be improved. This study aims to assess landslide susceptibility in the Thua Thien Hue province of Vietnam using deep neural networks (DNNs) and swarm-based optimization algorithms, namely Adam, stochastic gradient descent (SGD), Artificial Rabbits optimization (ARO), Tuna Swarm optimization (TSO), Sand Cat Swarm optimization (SCSO), Honey Badger algorithm (HBA), Marine Predators algorithm (MPA) and Particle Swarm optimization (PSO). The locations of 945 landslides occurring between 2012 and 2022, along with 14 conditioning factors, were used as input data to build the DNN and DNN-hybrid models. The performance of the proposed models was evaluated using the statistical indices receiver operating characteristic curve, area under the curve (AUC), root mean square error, mean absolute error (MAE), R2 and accuracy. All proposed models had a high accuracy of prediction. The DNN-MPA model had the highest AUC value (0.95), followed by DNN-HBA (0.95), DNN-ARO (0.95), DNN-Adam (0.95), DNN-SGD (0.95), DNN-TSO (0.93), DNN-PSO (0.9) and finally DNN-SCSO (0.83). High-precision models have identified that the majority of the western region of Thua Thien Hue province is very highly susceptible to landslides. Models like the aforementioned ones can support decision-makers in updating large-scale sustainable land-use strategies. Hybrid machine learning algorithms were applied for landslide susceptibility ***

关键词： deep neural network landslide optimization algorithm Thua Thien Hue Vietnam

来源：评论

学校读者我要写书评

暂无评论

Deep Diffusion for Training Chatter Detection Systems for Machine Tools

引用

IEEE SENSORS JOURNAL 2024年第19期24卷 29814-29823页

作者： Kuo, Ping-Huan Wu, Hao-Hsuan Yau, Her-Terng Natl Chung Cheng Univ Dept Mech Engn Chiayi 62102 Taiwan Natl Chung Cheng Univ Adv Inst Mfg High Tech Innovat AIM HI Chiayi 62102 Taiwan

In machine tool operations, chatter can cause machining errors and reduce a tool's lifespan and the production quality, and artificial intelligence (AI) is commonly used for predicting vibrations and chatter. In this study, 1-D chatter data were preprocessed through time delay mapping (TDM) to generate 2-D images. Diffusion models were then trained on the images and used to generate additional images to augment a small training dataset. The dataset was further used to train a convolutional neural network (CNN) model for detecting chatter. The data augmentation method can reduce data imbalance and improve a model's feature recognition capability, enhancing its accuracy on small datasets. An optimization algorithm was used in this study to obtain the CNN hyperparameters that maximized the model's robustness and accuracy. Overall, the TDM, model-based augmentation, and optimization methods were discovered to effectively enhance the chatter detection accuracy of the final model. The results of image generation can be used to construct a large database, providing more training data for models and reducing time and labor costs. In addition, because the images retain critical features, the model's complexity can be substantially reduced.

关键词： Diffusion models Data models Training Accuracy Predictive models Time division multiplexing Machining Chatter detection convolutional neural network (CNN) diffusion models optimization algorithm time delay mapping (TDM)

来源：评论

学校读者我要写书评

暂无评论

State-of-the-art advanced hybrid ANNs paradigm for assessment and prediction of slope stability

引用

MULTISCALE AND MULTIDISCIPLINARY MODELING EXPERIMENTS AND DESIGN 2024年第4期7卷 3483-3509页

作者： Kumar, Nitish Kumari, Sunita Natl Inst Technol Patna Dept Civil Engn Patna India

The study presents advanced hybrid artificial neural network (ANN) models to enhance the analysis of slope stability and the prediction of the factor of safety (FOS). Conventional methodologies, such as analytical procedures and numerical simulations, encounter difficulties in accurately representing intricate interactions. Consequently, machine learning (ML) simulation methods are being introduced as contemporary alternatives. This paper provides a comparative examination of hybrid artificial neural network (ANN) models utilizing several optimization algorithms (OAs) like Firefly (FF), Ant Lion (ALO), shuffled complex evolution (SCE), and the imperialist colony algorithm (ICA), simulated on a dataset of 349 slope cases. The performance of the ML models is enhanced by hyperparameter tuning and verified using various proven statistical indicators, error matrix, and external validation. It is concluded that all the applied models are robust for practical applications. The comparative analysis is carried out using rank analysis which proposes ANN-FF (rank = 64, RTR2 = 0.983 and RTS2 = 0.943) as the best performing model, followed by ANN-ICA (rank = 42, RTR2 = 0.9772 and RTS2 = 0.937) and ANN-ALO (rank = 37, RTR2 = 0.973 and RTS2 = 0.909). The developed hybrid ANN models demonstrate significant potential as a novel tool to aid engineers in estimating rock strain during the design phase of various engineering projects.

关键词： Slope stability Machine learning Factor of safety Artificial neural network optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Clamping Error Calibration algorithm of Aero-Engine Blade Surface Polishing

引用

INTERNATIONAL JOURNAL OF PRECISION ENGINEERING AND MANUFACTURING 2023年第7期24卷 1147-1159页

作者： Wu, Dongbo Wang, Zesheng Liang, Jiawei Wang, Hui Zhang, Kung Yu, Jie Tsinghua Univ Dept Mech Engn Beijing 100084 Peoples R China Tsinghua Univ Inst Aero Engine Beijing 100084 Peoples R China Beihang Univ Beijing 100191 Peoples R China Xinjiang Univ Urumqi 830000 Xinjiang Peoples R China AECC Xian Aeroengine LTD Xian 710021 Shaanxi Peoples R China

Polishing is an effective process method to improve the surface quality of aero-engine blade. The clamping error between fixture and blade leads to position error of blade surface and reduces processing quality. In this paper, a laser calibration system and a calibration algorithm are proposed to compensate clamping error. Firstly, theoretical point data of blade surface is obtained from CAD model, and the measurement point data of blade surface is obtained through laser sensor. A modified ICP algorithm is designed to calculate the coordinate transformation between the theoretical points and the measurement points. Secondly, Bezier surface is introduced to evaluate the calibration accuracy based on the distance between fitting surfaces rather than points. Finally, the point cloud registration is optimized by particle swarm optimization (PSO) algorithm based on the Bezier surface evaluation. The calibration algorithm combined ICP algorithm, Bezier surface evaluation and PSO algorithm to realize clamping error compensation. The quality of polished blade surface is consequently improved.

关键词： Blade polishing process Clamping error calibration Error evaluation optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

The effect of choosing optimizer algorithms to improve computer vision tasks: a comparative study

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2023年第11期82卷 16591-16633页

作者： Hassan, Esraa Shams, Mahmoud Y. Hikal, Noha A. Elmougy, Samir Kafrelsheikh Univ Fac Artificial Intelligence Kafrelsheikh 33516 Egypt Mansoura Univ Fac Comp & Informat Dept Informat Technol Mansoura 35516 Egypt Mansoura Univ Fac Comp & Informat Dept Comp Sci Mansoura 35516 Egypt

optimization algorithms are used to improve model accuracy. The optimization process undergoes multiple cycles until convergence. A variety of optimization strategies have been developed to overcome the obstacles involved in the learning process. Some of these strategies have been considered in this study to learn more about their complexities. It is crucial to analyse and summarise optimization techniques methodically from a machine learning standpoint since this can provide direction for future work in both machine learning and optimization. The approaches under consideration include the Stochastic Gradient Descent (SGD), Stochastic optimization Descent with Momentum, Rung Kutta, Adaptive Learning Rate, Root Mean Square Propagation, Adaptive Moment Estimation, Deep Ensembles, Feedback Alignment, Direct Feedback Alignment, Adfactor, AMSGrad, and Gravity. prove the ability of each optimizer applied to machine learning models. Firstly, tests on a skin cancer using the ISIC standard dataset for skin cancer detection were applied using three common optimizers (Adaptive Moment, SGD, and Root Mean Square Propagation) to explore the effect of the algorithms on the skin images. The optimal training results from the analysis indicate that the performance values are enhanced using the Adam optimizer, which achieved 97.30% accuracy. The second dataset is COVIDx CT images, and the results achieved are 99.07% accuracy based on the Adam optimizer. The result indicated that the utilisation of optimizers such as SGD and Adam improved the accuracy in training, testing, and validation stages.

关键词： optimization algorithm Stochastic gradient decent Rung Kutta optimization Deep ensembles Medical images

来源：评论

学校读者我要写书评

暂无评论

FastAdaBelief: Improving Convergence Rate for Belief-Based Adaptive Optimizers by Exploiting Strong Convexity

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2023年第9期34卷 6515-6529页

作者： Zhou, Yangfan Huang, Kaizhu Cheng, Cheng Wang, Xuguang Hussain, Amir Liu, Xin Univ Sci & Technol China Sch Nano Tech & Nano Bio Hefei 230026 Peoples R China Chinese Acad Sci Suzhou Inst Nanotech & Nanobio SINANO Suzhou 215123 Peoples R China Duke Kunshan Univ Data Sci Res Ctr Kunshan 215316 Peoples R China Gusu Lab Mat Suzhou 215123 Peoples R China Edinburgh Napier Univ Sch Comp Edinburgh EH11 4BN Midlothian Scotland Univ Sci & Technol China Sch Nanotech & Nanobio Hefei 230026 Peoples R China

AdaBelief, one of the current best optimizers, demonstrates superior generalization ability over the popular Adam algorithm by viewing the exponential moving average of observed gradients. AdaBelief is theoretically appealing in which it has a data-dependent O(root T) regret bound when objective functions are convex, where T is a time horizon. It remains, however, an open problem whether the convergence rate can be further improved without sacrificing its generalization ability. To this end, we make the first attempt in this work and design a novel optimization algorithm called FastAdaBelief that aims to exploit its strong convexity in order to achieve an even faster convergence rate. In particular, by adjusting the step size that better considers strong convexity and prevents fluctuation, our proposed FastAdaBelief demonstrates excellent generalization ability and superior convergence. As an important theoretical contribution, we prove that FastAdaBelief attains a data-dependent O(log T) regret bound, which is substantially lower than AdaBelief in strongly convex cases. On the empirical side, we validate our theoretical analysis with extensive experiments in scenarios of strong convexity and nonconvexity using three popular baseline models. Experimental results are very encouraging: FastAdaBelief converges the quickest in comparison to all mainstream algorithms while maintaining an excellent generalization ability, in cases of both strong convexity or nonconvexity. FastAdaBelief is, thus, posited as a new benchmark model for the research community.

关键词： Convergence optimization Training Task analysis Learning systems Deep learning Benchmark testing Adaptive learning rate image classification online learning optimization algorithm stochastic gradient descent strong convexity

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：