检索结果-内蒙古大学图书馆

Innovative Study on Volatility Prediction Model for New Energy Stock Indices

IEEE ACCESS 2025年 13卷 29754-29777页

作者： Li, Yanguo Long, Chao Yunnan Univ Finance & Econ Sch Econ Kunming 650221 Peoples R China Yunnan Univ Finance & Econ Finance Res Inst Kunming 650221 Peoples R China

Stock market volatility is a pivotal research area in finance, and accurately forecasting stock market volatility has long been a challenge for both academia and practice. The emergence of the new energy industry has drawn widespread attention to new energy stock indices;however, research on forecasting their volatility remains limited. To address this, this paper proposes a deep learning ensemble model based on decomposition optimization for predicting the volatility of new energy stock indices. The model comprises three components: variational mode decomposition (VMD), sparrow search algorithm (SSA), and echo state network (ESN). Initially, this paper employs VMD to decompose the original volatility series of new energy stock indices into multiple subsequences. Subsequently, SSA is utilized to optimize ESN. Finally, the constructed VMD-SSA-ESN model is employed to forecast the volatility of new energy stock indices. Through comparative analysis with other forecasting models, this paper finds that the VMD-SSA-ESN model exhibits significantly better forecasting performance across all selected new energy stock index volatility predictions. The research results indicate that the model constructed in this paper can adequately capture the characteristics of the volatility series, and both VMD and SSA effectively enhance the model's forecasting accuracy and stability. This study can provide robust support for investment decision-making and risk management in the new energy stock market.

关键词： Predictive models Indexes Forecasting Prediction algorithms Industries Stock markets Deep learning Computational modeling Analytical models Accuracy Volatility prediction deep learning variational mode decomposition optimization algorithm new energy

来源：评论

学校读者我要写书评

暂无评论

Squeeze-Inception V3 with Slime Mould algorithm-based CNN features for lung cancer detection

引用

BIOMEDICAL SIGNAL PROCESSING AND CONTROL 2025年 100卷

作者： Lakshmi, Geethu G. Nagaraj, P. Kalasalingam Acad Res & Educ Dept Comp Sci & Engn Srivilliputhur Tamil Nadu India

Worldwide, lung cancer is considered a highly fatal disease, affecting both women and men;it needs additional consideration while assessing several diseases. Moreover, early lung disease detection is highly significant in raising the survival rate of affected persons. There are numerous approaches to detecting lung cancer, yet it can be highly complicated to place the affected region because of the minimal visibility of the tumor section and error rates. In order to diagnose lung cancer accurately, this work created a technique, named as SqueezeInception V3 with Slime Mould algorithm (SMA)-based Convolutional Neural Network (CNN) features. Here, SMA-CNN is proposed for extracting CNN features from preprocessed images since training CNN using SMA enhances the performance. Subsequently, the features are fed to the classification for detecting lung cancer. The classification into normal/abnormal is done using the proposed Squeeze-Inception V3, which is designed by integrating the SqueezeNet and Inception v3 architectures. Finally, the analysis is performed with accuracy, sensitivity, as well as specificity rates of 95 %, 98 %, and 93 %, and reveals that the performance of proposed technique is superior to comparative models.

关键词： Lung cancer CNN features SqueezeNet Inception V3 optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Designing Routes in Terminal Maneuvering Area Using Hybrid Simulated Annealing

引用

JOURNAL OF GUIDANCE CONTROL AND DYNAMICS 2025年第3期48卷 615-629页

作者： Zhou, Jun Wang, Xujie Hu, Xiaobing Civil Aviat Univ China Sino European Inst Aviat Engn Coll Safety Sci Lab Complex Syst Safety & Intelligent Decis Tianjin 300300 Peoples R China Civil Aviat Univ China Coll Safety Sci & Engn Lab Complex Syst Safety & Intelligent Decis Tianjin 300300 Peoples R China

To ensure the safe and efficient operation of flights in terminal maneuvering areas, airports establish standard arrival and departure procedures. However, designing these procedures is typically time-consuming and challenging for quantitative path length optimization. This paper presents an efficient optimization method for designing multiple arrival and departure procedures, taking into account the configuration of the airport and the nearby environment. The objective is to minimize the total length of routes while satisfying related operational constraints, such as obstacle avoidance and route separation. Each route is modeled in three dimensions, consisting of a horizontal polygonal line and a vertical cone. Considering the actual procedures' merging or diverging configuration characteristics, multiple arrival or departure routes are then modeled as a tree-like topology structure. A hybrid algorithm, integrating simulated annealing and an improved A* algorithm, is developed for automated problem-solving. Simulation results, based on tests at Sweden's Arlanda Airport, exhibit advantages over existing related research in terms of both total route length and computing time. Tests at Shanghai Pudong Airport show an 8% reduction in total path length compared to actual procedures, demonstrating the proposed method's effectiveness and potential contributions to energy savings and emissions reduction.

关键词： Annealing Terminal Manoeuvring Area Obstacle Avoidance Computing and Informatics optimization algorithm Initial Approach Fix Standard Terminal Arrival Route Air Navigation Service Provider Standard Instrument Departure Airspace Management

来源：评论

学校读者我要写书评

暂无评论

A data-driven approach for oil production prediction and water injection recommendation in well groups

GEOENERGY SCIENCE AND ENGINEERING

引用

GEOENERGY SCIENCE AND ENGINEERING 2025年 247卷

作者： Yang, Chunyi Chen, Yan Li, Yangbing Chen, Peng Southwest Petr Univ Sch Comp Sci & Software Engn Chengdu 610500 Sichuan Peoples R China Engn Res Ctr Intelligent Oil & Gas Explorat & Dev Chengdu 610500 Sichuan Peoples R China Engn Technol Co Tianjin Dept CNOOC Energy Dev Co Ltd Tianjin 300452 Peoples R China

In oilfield water injection and production, accurate oil production predictions and effective water injection schemes are crucial for improving the oilfield development efficiency and economic benefits. However, most existing data-driven methods primarily focus on single-well production prediction and lack comprehensive evaluation methods for optimizing water injection. This study proposed a new approach to address these issues. First, we proposed a well group oil production prediction (WGOPP) model that can predict the total oil production of a well group over a specified period. Second, we designed a multi-index dynamic normalized comprehensive evaluation (MDNCE) method using comprehensive evaluation coefficient I as the criterion for selecting the optimal optimization algorithm. Finally, we proposed a well group water injection recommendation (WGWIR) method based on the adaptive particle swarm optimization (APSO) algorithm, which provides quantitative injection schemes for wells within the well group. The experimental results showed that the average R 2 of the WGOPP model on the test set was greater than 0.95, and the APSO algorithm had the highest I value among the seven optimization algorithms, reaching 0.8554. After applying the WGWIR method, the average production growth rate of the well groups increased by more than 15%. The code is available at https://***/yangchunyi/Well_Group_Production_Prediction_and_Injection_optimization.

关键词： Data-driven optimization algorithm Oil production prediction Time series Water injection recommendation

来源：评论

学校读者我要写书评

暂无评论

Study on the influence of lead ions on soil fissure development and intelligent prediction model under dry-wet cycle conditions

引用

ENVIRONMENTAL EARTH SCIENCES 2025年第9期84卷 1-25页

作者： Li, Jiaming Tang, Beichang Zhang, Yan Chen, Hongbin Wang, Yan Guilin Univ Technol Guangxi Key Lab Geomech & Geotech Engn Guilin 541004 Peoples R China Guilin Univ Technol Guangxi Key Lab Green Bldg Mat & Construct Industr Guilin 541004 Peoples R China Shenzhen Invest & Res Inst Co Ltd Shenzhen 518000 Peoples R China

This study investigates the fissure development law of soil contaminated with varying degrees of lead ions under the influence of dry-wet cycles. The effects of different lead ion concentrations on the development of fissures in silty clay, red clay, and expansive soil were systematically investigated through dry-wet cycle tests, and parameters such as fissure area and fractal dimension were precisely quantified and analyzed using image processing techniques. The study's results indicate that the presence of lead ions significantly promotes the development of fissure areas in three soils. Based on this, four fractal dimension prediction models, namely, bidirectional long short-term memory network (BiLSTM), gated recurrent unit (GRU), extreme gradient boosting (XGBoost), and regression by relevance vector machine (RVM), are constructed, among which the RVM model exhibits optimal performance. To further improve the prediction accuracy, the sparrow search algorithm (SSA) and particle swarm optimization algorithm (PSO) are introduced to optimize the model parameters, and it is found that the SSA- RVM model performs the best, and its mean squared error (MSE), root mean squared error (RMSE), and mean absolute percentage error (MAPE) metrics are reduced by 3.55%, 6.98%, and 16.79% compared with that of the RVM model, respectively. This study supports the optimization of ecological remediation techniques for contaminated soils and the risk assessment of heavy metal-contaminated sites.

关键词： Lead ions Soil fissure Fractal dimension Machine learning optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Airfoil Design and Performance optimization of Rotorcraft Robots through the Integration of LSTM-PSO and Multilayer Perceptron Technologies 39

Airfoil Design and Performance Optimization of Rotorcraft Ro...

引用

39th Youth Academic Annual Conference of Chinese-Association-of-Automation (YAC)

作者： Li, Zhiqing Wang, Yanbo Zhou, Hongxing Wang, Xin Beijing Univ Chem Technol Coll Informat Sci & Technol Beijing Peoples R China

ISBN: (纸本)9798350390780;9798350379228

This study designs and employs the Long Short-Term Memory-Particle Swarm optimization (LSTM-PSO) algorithm, supplemented by a multilayer perceptron model, focusing on the optimization of rotorcraft airfoil structural parameters in low Reynolds number environments under Mars's unique atmospheric conditions. A new airfoil was successfully developed through the optimized structure. The advantage of this algorithm lies in significantly enhancing the lift-to-drag ratio under ultra-low Reynolds number conditions and achieving a significant reduction in computation time by using a multilayer perceptron to replace traditional Computational Fluid Dynamics (CFD) simulations. This strategy not only reflects an effective improvement over traditional design methods but also demonstrates the tremendous potential of using machine learning technologies to handle complex optimization problems in the aerospace field, offering new insights for finding complex optimization solutions in dynamic and uncertain environments.

关键词： ultra-low Reynolds number rotorcraft airfoil optimization optimization algorithm computational fluid dynamics machine learning

来源：评论

学校读者我要写书评

暂无评论

Estimation of elastic modulus of recycle aggregate concrete based on hybrid and ensemble-hybrid approaches

引用

STRUCTURAL CONCRETE 2024年第2期25卷 1364-1387页

作者： Qu, Bing Putian Univ Sch Civil Engn Putian 351100 Fujian Peoples R China

The utilization of recycled aggregate concrete (RAC) within the construction sector has the potential to prevent irreversible harm to the environment and reduce the depletion of natural resources. Nonetheless, it is essential to scrutinize the quality of RAC before utilizing it in practical applications. RAC's most significant design parameter is its elastic modulus, typically determined through time-consuming and costly experiments. Machine learning (ML) techniques can be a feasible solution to reduce the number of experiments required and obtain accurate estimates. This article employs two robust ML techniques, namely Xtreme Gradient Boosting (XGB) and Adaptive Boosting regression, in three distinct modes, namely individual, hybrid, and ensemble-hybrid methods. Furthermore, phasor particle swarm optimization (PPSO) and chaos game optimization (CGO) have been utilized in hybrid and ensemble-hybrid modes to optimize final results, minimize errors, and obtain highly precise outcomes. As mentioned earlier, several evaluators were employed to identify the most appropriate model to compare the modes. The findings suggest that the relevant optimizers significantly contributed to achieving superior metric values. Specifically, the results indicated that PPSO exhibited greater efficacy than CGO in optimizing outputs and enhancing accuracy. The hybrid models, particularly XGB in conjunction with PPSO, yielded the most favorable correlation coefficient and root mean square error values equal to 0.996 and 0.336 and can serve as an effective ML method to determine elastic modulus of recycle aggregate concrete for time and energy storage.

关键词： elastic modulus of recycle aggregate concrete ensemble and hybrid method machine learning optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Asymptotic capacity maximization for MISO visible light communications with mirror array-based RISs on walls and an LC RIS-based receiver

引用

OPTICS COMMUNICATIONS 2024年 561卷

作者： Wu, Qi Zhang, Jian Zhang, Yan-Yu Xin, Gang Natl Digital Switching Syst Engn & Technol Res Ctr Zhengzhou 450000 Henan Peoples R China

Traditional adoptions of reconfigurable intelligent surfaces (RISs) in visible light communications (VLCs) mainly focus on one kind of RIS. However, the joint application of mirror array-based RIS and a liquid crystal (LC)-based RIS in multiple -input single -output (MISO) VLC has not been investigated in prior works. Considering the huge potential to improve the communication performance provided by the two types of RISs above, combined with the research value of MISO VLC systems, this paper fills in the gap and investigates the performance produced by the joint application of the two types of RISs above in capacity improvement for the MISO VLC system. We formulate an asymptotic capacity maximization problem to optimally configure the parameters of RISs including the orientations of mirror array-based RISs and the refractive index of LC RIS. As for the complex non-convex optimization problem, we propose a low-complexity optimization algorithm to determine the proper parameters of RISs through combining the two types of algorithms proposed in our previous works. Finally, our simulations demonstrate that the joint employment of the two types of RISs in an indoor MISO VLC system can enhance the communication performance to a greater degree compared with the RIS-aided MISO VLC system which employs only one type of VLC RIS, and meanwhile, the proposed method is proved to be an efficient solution to configure the parameters of the two types of RISs compared with other baselines schemes.

关键词： Visible light communication (VLC) Reconfigurable intelligent surface (RIS) Asymptotic capacity Liquid crystal (LC) optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

A Novel Method Based on Probability Density Function Used in Instantaneous Frequency Measurement System for Wider Range and Less Error

引用

JOURNAL OF LIGHTWAVE TECHNOLOGY 2024年第10期42卷 3669-3676页

作者： Wu, Rui Wang, Yuehui Jia, Qianqian Zhao, Zeping Liu, Jianguo Chinese Acad Sci Inst Semicond Beijing 100083 Peoples R China Univ Chinese Acad Sci Ctr Mat Sci & Optoelect Engn Beijing 100049 Peoples R China

This article reports a photonic-assisted instantaneous frequency measurement system based on a multi-group asymmetrical Mach-Zehnder interferometer structure, applicable in contemporary electronic countermeasure. Additionally, we introduce a novel method to obtain measurement results based on probability theory. Employing this method allows for a broader measurement range compared to traditional approaches utilizing amplify compare function without a deterioration in accuracy. Sufficient and systematic experimental results show that the measurement range can be at least 30 GHz and the mean error is 0.102 GHz using our proposed system and method. Moreover, we propose an optimization algorithm based on our method. By using this algorithm, we can adjust measurement range for proposed system with minimal asymmetrical MZI structures, ensuring no compromise in accuracy. In addition, the system is easy to realize hybrid integration or even monolithic integration due to the use of microwave photonics technology.

关键词： Instantaneous frequency measurement optimization algorithm probability density function time delay

来源：评论

学校读者我要写书评

暂无评论

Near-Surface Rayleigh Wave Dispersion Curve Inversion algorithms: A Comprehensive Comparison

引用

SURVEYS IN GEOPHYSICS 2024年第3期45卷 773-818页

作者： Yang, Xiao-Hui Zhou, Yuanyuan Han, Peng Feng, Xuping Chen, Xiaofei Chengdu Univ Informat Technol Sch Atmospher Sci Plateau Atmosphere & Environm Key Lab Sichuan Prov Chengdu 610225 Peoples R China Southern Univ Sci & Technol Shenzhen Key Lab Deep Offshore Oil & Gas Explorat Shenzhen 518055 Peoples R China Southern Univ Sci & Technol Guangdong Prov Key Lab Geophys High Resolut Imagin Shenzhen 518055 Peoples R China Southern Univ Sci & Technol Dept Earth & Space Sci Shenzhen 518055 Peoples R China

Rayleigh wave exploration is a powerful method for estimating near-surface shear-wave (S-wave) velocities, providing valuable insights into the stiffness properties of subsurface materials inside the Earth. The dispersion curve inversion of Rayleigh wave corresponds to the optimization process of searching for the optimal solutions of earth model parameters based on the measured dispersion curves. At present, diversified inversion algorithms have been introduced into the process of Rayleigh wave inversion. However, limited studies have been conducted to uncover the variations in inversion performance among commonly used inversion algorithms. To obtain a comprehensive understanding of the optimization performance of these inversion algorithms, we systematically investigate and quantitatively assess the inversion performance of two bionic algorithms, two probabilistic algorithms, a gradient-based algorithm, and two neural network algorithms. The evaluation indices include the computational cost, accuracy, stability, generalization ability, noise effects, and field data processing capability. It is found that the Bound-constrained limited-memory Broyden-Fletcher-Goldfarb-Shanno (L-BFGS-B) algorithm and the broad learning (BL) network have the lowest computational cost among candidate algorithms. Furthermore, the transitional Markov Chain Monte Carlo algorithm, deep learning (DL) network, and BL network outperform the other four algorithms regarding accuracy, stability, resistance to noise effects, and capability to process field data. The DL and BL networks demonstrate the highest level of generalization compared to the other algorithms. The comparison results reveal the variations in candidate algorithms for the inversion task, causing a clear understanding of the inversion performance of candidate algorithms. This study can promote the S-wave velocity estimation by Rayleigh wave inversion.

关键词： Rayleigh wave inversion Near-surface S-wave velocity optimization algorithm Inversion performance comparison

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：