检索结果-内蒙古大学图书馆

Optimized path planning for underground coal mine filling: an greedy adaptive directional bidirectional rapidly-exploring random tree

引用

MEASUREMENT SCIENCE AND TECHNOLOGY 2025年第2期36卷 026205-026205页

作者： Zhang, Zihang Liu, Yang Bo, Lei Yang, Shangqing Wang, Yanwen China Univ Min & Technol Sch Artificial Intelligence Beijing 100083 Peoples R China China Univ Min & Technol Sch Mech & Elect Engn Beijing 100083 Peoples R China

The technology of mining filling is of great significance in improving coal recovery rates, protecting the environment, and conserving land resources. The current efficiency of filling is constrained by single-method approaches. To address this issue, this study develops a path planning model based on underground fill space data, which comprehensively considers fill path length and material volume using a goal programming method, and designs corresponding constraints and adaptive weights. To further optimize search efficiency, an adaptive directional bidirectional rapidly-exploring random tree (AD-BIRRT) algorithm is proposed. This algorithm can intelligently adjust the optimal exploration direction based on current demand and state, significantly enhancing search efficiency and accuracy through the establishment of a dual-tree structure. Additionally, a novel greedy strategy is introduced to resolve path smoothing and redundancy issues. To verify the rationality and effectiveness of the proposed method, comparative tests were conducted in test scenarios, fill scenarios, and on experimental platforms against BIRRT, BIRRT*, Genetic algorithm, and artificial potential field algorithms. The results indicate that the proposed greedy AD-BIRRT algorithm exhibits significant advantages in terms of computation time, path quality, and material accumulation. This algorithm effectively enhances the efficiency and quality of the filling process.

关键词： solid filling path planning optimization algorithm BIRRT greedy algorithm

来源：评论

学校读者我要写书评

暂无评论

Attitude estimation using an adaptive generalized complementary filter

引用

MEASUREMENT 2025年 251卷

作者： Wu, Wenyu Jin, Zhonghe A, Zeya Zhejiang Univ Microsatellite Res Ctr Hangzhou 310058 Peoples R China Huanjiang Lab Hangzhou 310058 Peoples R China Key Lab Micronano Satellite Res Zhejiang Prov Hangzhou 310058 Peoples R China

A precise and reliable attitude estimation system is essential for the accurate motion control of micro-/nano-satellites. This paper proposes a generalized attitude estimation framework that integrates optimization techniques with an adaptive nonlinear complementary filter for multi-sensor systems. The framework utilizes the Levenberg-Marquardt optimization algorithm to derive quaternion measurements, which are used as attitude error inputs for an adaptive nonlinear filter. Compared with traditional complementary filters, the proposed approach offers broader applicability and enhanced adaptability through a parameter adjustment strategy. Comprehensive experiments, including performance evaluation, fault tolerance analysis, and real on-orbit data validation, confirm the framework's effectiveness and robustness. Results demonstrate that the proposed method provides efficient attitude angle estimations and gyro bias information, even in disturbed environments. Consequently, this scheme is well-suited for micro-/nano-satellite applications.

关键词： Attitude estimation Micro-/nano-satellites Gyro bias determination optimization algorithm Complementary filter

来源：评论

学校读者我要写书评

暂无评论

Enhanced Hyperspectral Forest Soil Organic Matter Prediction Using a Black-Winged Kite algorithm-Optimized Convolutional Neural Network and Support Vector Machine

引用

APPLIED SCIENCES-BASEL 2025年第2期15卷 503-503页

作者： Deng, Yun Xiao, Lifan Shi, Yuanyuan Guilin Univ Technol Coll Comp Sci & Engn Guilin 541006 Peoples R China Guilin Univ Technol Guangxi Key Lab Embedded Technol & Intelligent Sys Guilin 541006 Peoples R China Guangxi Forestry Res Inst Forestry Minist China Key Lab Cent South Fast Growing Timber Cultivat Nanning 530002 Peoples R China

Soil Organic Matter (SOM) is crucial for soil fertility, and effective detection methods are of great significance for the development of agriculture and forestry. This study uses 206 hyperspectral soil samples from the state-owned Yachang and Huangmian Forest Farms in Guangxi, using the SPXY algorithm to partition the dataset in a 4:1 ratio, to provide an effective spectral data preprocessing method and a novel SOM content prediction model for the study area and similar regions. Three denoising methods (no denoising, Savitzky-Golay filter denoising, and discrete wavelet transform denoising) were combined with nine mathematical transformations (original spectral reflectance (R), first-order differential (1DR), second-order differential (2DR), MSC, SNV, logR, (logR)', 1/R, ((1/R)') to form 27 combinations. Through Pearson heatmap analysis and modeling accuracy comparison, the SG-1DR preprocessing combination was found to effectively highlight spectral data features. A CNN-SVM model based on the Black Kite algorithm (BKA) is proposed. This model leverages the powerful parameter tuning capabilities of BKA, uses CNN for feature extraction, and uses SVM for classification and regression, further improving the accuracy of SOM prediction. The model results are RMSE = 3.042, R2 = 0.93, MAE = 4.601, MARE = 0.1, MBE = 0.89, and PRIQ = 1.436.

关键词： optimization algorithm organic matter content spectral data processing forest soil Guangxi

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

Joint DOA and distance estimation via spatial diversity wideband signal synthesis calibrated by distance parameter

引用

DIGITAL SIGNAL PROCESSING 2025年 157卷

作者： Zhang, Wentao Miao, Chen Wu, Wen Nanjing Univ Sci & Technol Key Lab Near Range RF Sensing ICs & Microsyst Nanjing 210094 Peoples R China Southeast Univ State Key Lab Millimetre Waves Nanjing 210094 Peoples R China

Wideband signal synthesis is a technique designed to achieve large bandwidth detection capabilities by utilizing multiple relatively narrow bandwidth signals. Traditional single-antenna, time-diversity wideband synthesis method is inefficient, which has led to using Multiple-Input Multiple-Output (MIMO) architectures to introduce spatial diversity. However, this method introduces challenges such as frequency-phase inconsistencies in the selfmixing signals from different array elements due to differences in wave travel distances. In previous research, we studied the calibration of frequency and phase for synthesized sub-signals using DOA parameters, which required additional high-precision direction of arrival (DOA) estimation algorithms. In contrast, this paper proposes a novel spatial-diversity wideband synthesis method that utilizes distance parameter calibration for joint DOA and distance estimation (JDDE). A key advantage of this method is the relative simplicity of obtaining distance parameters. To address the issue where the accuracy of distance parameters does not meet the requirements for synthesis, we proposed a grid search synthesis method in this paper. Furthermore, we introduced a search synthesis based on optimization algorithms to reduce computational load and enhance the synthesis performance. Theoretical analysis and simulations confirm the high accuracy of our JDDE method. Under conditions of high signal-to-noise ratios, our method significantly reduces the DOA's root mean square error-approximately halving it compared to the multiple signal classification algorithm within the same wideband self-mixing framework. Additionally, both distance resolution and range accuracy exceed those achieved with presynthesis methods.

关键词： Doa estimation Distance estimation Wideband signal synthesis optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Optimal energy management system and techno-economic assessment in Urban and Rural AC microgrids

引用

JOURNAL OF ENERGY STORAGE 2025年 114卷

作者： Montano, Jhon Gonzalez-Montoya, Daniel Candelo-Becerra, John E. Herrera-Jaramillo, Diego A. Inst Tecnol Metropolitano Dept Elect & Telecommun Medellin 050028 Colombia Univ Nacl Colombia Sede Medellin Dept Energia Electr & Automat Medellin 050034 Colombia Inst Univ Envigado Lab Desarrollo Tecnol Sostenible Envigado 055420 Colombia

This paper introduces an energy management system that incorporates a model for managing urban and rural alternating current (AC) microgrids (MGs), integrating renewable energy sources and energy storage systems. The proposed model aims to improve key technical, economic, and environmental performance indicators. It employs a mono-objective optimization framework, focusing on the independent minimization of operating costs, power losses, and CO2 emissions. To solve the optimization problem, seven bio-inspired algorithms are implemented and compared: Black Hole Optimizer (BHO), Crow Search algorithm (CSA), Salp Swarm algorithm (SSA), Equilibrium Optimizer (EO), Generalized Normal Distribution Optimizer (GNDO), Particle Swarm optimization (PSO), and Grasshopper optimization algorithm (GOA). The effectiveness of the proposed model is validated through a comparative analysis against a baseline scenario that represents conventional MG operation without optimization. This baseline scenario includes photovoltaic distributed generators and energy storage systems operating under static dispatch strategies. The results demonstrate that EO, SSA, and GNDO are the most effective algorithms for optimizing the specified objectives. For urban MGs, the proposed model achieves reductions of up to 7.16% in power losses, 0.163% infixed costs, 1.436% invariable costs, and 0.165% in CO2 emissions when compared to the baseline. Similarly, for rural MGs, the proposed approach yields reductions of 10.938% in power losses, 0.095% in energy costs, and 0.145% in CO2 emissions relative to the baseline scenario. These findings confirm the innovation and effectiveness of the proposed energy management model and its optimization algorithms. The study highlights the model's capability to ensure technical efficiency while significantly reducing economic and environmental impacts. Moreover, the adaptability of the model to both urban and rural settings demonstrates its potential as a robust framework

关键词： Energy management system Techno-economic analysis AC MGs optimization algorithm Variable power demand Variable renewable generation

来源：评论

学校读者我要写书评

暂无评论

Intelligent Network Selection Mechanisms in the Internet of Everything System

引用

IEEE ACCESS 2025年 13卷 9666-9678页

作者： Singh, Indrasen Munjal, Meenakshi Vellore Inst Technol Sch Elect Engn Dept Embedded Technol Vellore 632014 Tamil Nadu India Chandigarh Univ Univ Inst Engn ECE Dept Sahibzada Ajit Singh Naga 140413 India

In the Internet of Everything (IoE) ecosystem, it is necessary for connected devices to move between different access points seamlessly. As IoE is deployed in diverse environments, such as smart cities, industrial settings, and vehicular networks, ensuring reliable connectivity and uninterrupted services across different networks becomes important. As part of the IoE framework, this research paper focuses on developing and evaluating intelligent handoff decision mechanisms. So, in this work, the optimal handoff decision technique is proposed, which transmits the information in a fast manner. The Fuzzy Analytical Hierarchical Process (FAHP) and Analytical Hierarchical Process (AHP) two-user preference calculation algorithms are used. Then, the user preference is included in the prospect algorithm and the optimal network is selected. After that, the result of the prospect algorithm is compared with the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS), Grey Rational Analysis (GRA), and Multiplicative Exponent Weighting (MEW) algorithms in terms of network scores and the number of handoffs. The advantage of network selection using a prospect algorithm is that it will decrease the failure rate and increase the data transfer and user experience. These advantages deliver seamless connectivity for a diverse range of applications and devices using an IoE infrastructure that is more robust and reliable. The network selected by combining different techniques is the optimal network because it selects the most efficient or effective network.

关键词： SIM card Internet of Things Real-time systems User experience Interference Handover Ecosystems Delays Wireless fidelity WiMAX Handoff heterogeneous network Internet of Everything (IoE) network selection optimization algorithm prospect theory

来源：评论

学校读者我要写书评

暂无评论

Development of a Performance-Based Approach for Optimizing Sensor Placement in Building Fire Detection

引用

FIRE TECHNOLOGY 2025年 1-28页

作者： Fang, Hongqiang Xu, Mingjun Chen, Xiao Lo, S. M. Wan, Man Pun Univ Sci & Technol China State Key Lab Fire Sci Hefei 230026 Peoples R China City Univ Hong Kong Dept Architecture & Civil Engn Hong Kong Peoples R China Nanyang Technol Univ Sch Mech & Aerosp Engn 50 Nanyang Ave Singapore 639798 Singapore

Fire detection systems play a vital role in ensuring effective fire protection within buildings. At present, the placement of fire detectors is guided by established codes and standards, which specify maximum coverage areas for each detector. Building engineers typically follow these guidelines, positioning detectors strategically to achieve full coverage. While this approach provides adequate protection, it fails to consider the impact of varying environmental factors in different settings and accurately assess the actual performance of fire detection systems. This limitation is particularly evident in unique spaces like warehouses, where fire types and potential ignition locations may differ significantly from those in conventional environments, necessitating a more customized approach to sensor placement. To address this issue, a fire detection performance-based sensor placement optimization (FDPB-SPO) approach is proposed. This methodology integrates numerical datasets generated from multiple simulated fire scenarios with advanced optimization algorithms to evaluate fire sensor placement performance and identify the optimal arrangement. The optimization process balances effective fire detection with compliance to code requirements, ensuring both enhanced performance and practical applicability. A case study evaluating this proposed approach demonstrates its effectiveness in determining the more appropriate arrangement for fire detection. Additionally, integrating it with the Genetic algorithm (GA) yields an optimized solution that enhances fire detection performance and reliability. These findings highlight the potential of the FDPB-SPO approach in advancing sensor placement strategies and contributing to the development of future fire detection system standards.

关键词： Building fire safety Fire detection Sensor placement Performance-based design optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Integrating Analytical Simulations With Regression Learning: Advancing Efficiency in Energy and Water Use in Sugar Production

引用

JOURNAL OF FOOD PROCESS ENGINEERING 2025年第2期48卷

作者： Azizi, Mohammad Mosharaf-Dehkordi, Mehdi Fouladi, Nourbaksh Kazanci, Caner Univ Isfahan Fac Engn Dept Mech Engn Esfahan Iran Univ Georgia Coll Engn Athens GA USA

Energy and water consumption are critically important in the sugar industry. In this context, the heat exchanger network of a target sugar factory has been modeled and optimized, as this sector is the primary consumer of energy and water. A key innovation of this work lies in the coupling of interacting components within the model, leading to a more comprehensive framework compared to previous models in the literature. Some sections of the system are modeled using analytical interpretations, while others are developed through a regression learning process utilizing statistical data. This integration of analytical formulation and data-driven modeling represents another significant advancement in this research. The resulting model demonstrates acceptable accuracy for most measurable parameters, with an average deviation of approximately 4%. The optimization results indicate that certain parameters, such as the cooling pool evaporation rate, exhibit considerable flexibility, allowing optimization algorithms to converge more easily. Conversely, other parameters, such as the vapor fed to the exchangers, are more rigid, which restricts the freedom of the optimization process. Moreover, the effectiveness of the elements within the optimization target function is crucial for identifying the optimal point. Overall, minimizing energy consumption and water usage simultaneously presents a significant challenge, necessitating careful consideration in determining which optimal point is most practical.

关键词： heat exchanger network multiple evaporation optimization algorithm regression learner

来源：评论

学校读者我要写书评

暂无评论

Air quality index prediction through TimeGAN data recovery and PSO-optimized VMD-deep learning framework

引用

APPLIED SOFT COMPUTING 2025年 170卷

作者： Wang, Kenan Yang, Tianning Kong, Shanshan Li, Mingduo North China Univ Sci & Technol Coll Sci Tangshan 063210 Peoples R China North China Univ Sci & Technol Coll Elect Engn Tangshan 063210 Peoples R China

With the rapid development of the economy, air pollution has become increasingly severe. Accurate prediction of the Air Quality Index (AQI) is crucial for safeguarding public health and the environment. However, AQI time series exhibit strong randomness and volatility, posing challenges for traditional forecasting methods to achieve precise AQI predictions. Therefore, we propose a new AQI hybrid prediction model, TG-Hybrid model, which integrates generative artificial intelligence, signal decomposition techniques, artificial intelligence methods, and optimization algorithms. In the proposed model, missing values in the data are handled using generative adversarial networks, effectively addressing the issue of a large number of missing values in time series data. Autoregressive integrated moving average is employed to forecast the linear components of the data, while variational mode decomposition decomposes AQI into multiple modes. Particle swarm optimization is used to combine the prediction results of convolutional neural network combined with bidirectional long short-term memory and extreme gradient boosting. Additionally, AQI prediction experiments were conducted using air pollution data from Tangshan and Beijing, and compared with fifteen other models. The results indicate that the root mean square error for Tangshan and Beijing are 6.407 and 7.485, respectively, significantly outperforming other baseline models.

关键词： Time Generative Adversarial Network Air Quality Index Prediction Deep learning model optimization algorithm Variational Mode Decomposition

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：