检索结果-内蒙古大学图书馆

A Fuzzy C-Means Clustering-Based Hybrid Multivariate Time Series prediction Framework With Feature Selection

IEEE TRANSACTIONS ON FUZZY SYSTEMS 2024年第8期32卷 4270-4284页

作者： Zhan, Jianming Huang, Xianfeng Qian, Yuhua Ding, Weiping Hubei Minzu Univ Sch Math & Stat Enshi 445000 Peoples R China Shanxi Univ Inst Big Data Sci & Ind Taiyuan 030006 Peoples R China Shanxi Univ Key Lab Computat Intelligence & Chinese Informat P Minist Educ Taiyuan 030006 Peoples R China Shanxi Univ Engn Res Ctr Machine Vis & Data Min Shanxi Prov Taiyuan 030006 Peoples R China Nantong Univ Sch Informat Sci & Technol Nantong 226019 Peoples R China City Univ Macau Fac Data Sci Macau 999078 Peoples R China

Multivariate time series prediction (MTSP) stands as a significant and challenging frontier in the data science domain, garnering considerable interest among researchers. Extreme learning machine (ELM) has emerged as a popular machine learning algorithm capable of effectively addressing MTSP challenges. However, the high-dimensional and nonlinear nature of prediction information within Big Data contexts exposes certain limitations in ELM's prediction performance. To address this issue, this article proposes a hybrid MTSP framework based on fuzzy C-means (FCM) clustering coupled with feature selection. The framework begins with a possibility distribution (PD)-based feature selection algorithm designed to evaluate information quality and describe information uncertainty via multisource information fusion. Subsequently, a robust FCM algorithm is developed, optimizing the clustering process by incorporating feature differences and neighbor information of samples while employing a multimetric hybrid strategy to determine cluster numbers. Additionally, an enhanced dual-kernel ELM (EDKELM) network is established to enhance prediction capabilities. The resulting hybrid MTSP framework with feature selection excels in autonomously discovering intrinsic feature-model connections, exhibiting superior prediction performance, and demonstrating excellent generalization ability. Experimental results using real-world datasets showcase the competitiveness of the proposed framework over existing machine learning prediction models in resolving multivariate prediction challenges.

关键词： Feature extraction Predictive models Clustering algorithms prediction algorithms Time series analysis Data models Possibility theory Extreme learning machine (ELM) feature selection fuzzy C-means (FCM) clustering multivariate time series prediction (MTSP) possibility theory

来源：评论

学校读者我要写书评

暂无评论

High-Precision Debris Flow Scale prediction Model Based on CIHHO Algorithm Combined With Multilayer Perceptron Neural Network

引用

IEEE ACCESS 2024年 12卷 144710-144724页

作者： Qiang, Yue Xu, Xinlong Li, Li Liang, Siyu Wang, Xi Chen, Cheng Tan, Xinyi Chongqing Three Gorges Univ Civil Engn Coll Wanzhou 404100 Chongqing Peoples R China

This study focuses on improving the precision and global search capabilities of the Harris Hawk Optimization algorithm when dealing with debris flow disasters. The enhanced algorithm, called Cubic map Improved Harris Hawk Optimization (CIHHO), incorporates a BP neural network and integrates Grey relational analysis and Spearman correlation analysis to address the factors influencing debris flow disasters effectively. Additionally, The CIHHO-BP model was tested on 92 debris flows in Beichuan County and was found to be more accurate than a standalone BP neural network model in predicting the size of the debris flow scale, and the CIHHO-BP model outperformed a model that combined the Harris Hawk Algorithm (HHO), Genetic Algorithm (GA), Coyote Optimization Algorithm (COA), and Particle Swarm Algorithm (PSO) with the BP neural network. The research demonstrates that the enhanced Harris Hawk optimization algorithm, which integrates a cubic map to optimize the initial population and updates the iterative formula E, effectively resolves the issue of local optimization and inadequate global search capability in the Harris Hawk algorithm. The R2 of the debris flow scale prediction model optimized by the enhanced Harris Hawk Optimization algorithm combined with the BP neural network has reached 0.974, demonstrating enhanced stability in the prediction of the scale of small and medium-sized debris flows. The combined prediction model offers a novel approach to the prediction of debris flow scale, providing a valuable reference for the prevention and control of debris flows and machine learning algorithms.

关键词： prediction algorithms Optimization Disasters Predictive models Neural networks Accuracy Machine learning algorithms Biological neural networks Machine learning Genetic algorithms Debris flow scale chaotic mapping BPNN improved Harris Hawk optimization algorithm correlation analysis

来源：评论

学校读者我要写书评

暂无评论

Enhanced Deep Learning Method for Natural Gas Pipeline Flow prediction Based on Integrated Learning

引用

IEEE ACCESS 2024年 12卷 83822-83829页

作者： Li, Yunhao Sun, Changjing Li, Qiang China Jiliang Univ Coll Energy Environm & Safety Engn Hangzhou 310018 Peoples R China Hangzhou Nat Gas Co Ltd High Pressure Storage & Distribut Branch Hangzhou 310018 Peoples R China

Urban gas pipelines must contend with situations such as road construction and excavation for house building, where short-term emergencies leading to large-scale leaks pose significant risks to both people and the environment. To enhance the response cycle for detecting leaks in urban natural gas pipelines, this paper proposes a real-time flow prediction model for gas pipelines. This model is an improved version of the Long Short-Term Memory (LSTM) neural network, utilizing an ensemble learning algorithm. It processes the instant flow data from preprocessed historical flow meters as input and fine-tunes the neural network's hyperparameters through grid search. The LSTM, with its inherent temporal memory function, serves as a weak predictor within the ensemble, which is then strengthened through a weighted combination using the Adaboost ensemble learning algorithm. The findings indicate that our approach, in comparison to a singular LSTM network, yields lower Mean Squared Error (MSE), Mean Absolute Error (MAE), and Symmetric Mean Absolute Percentage Error (SMAPE). The enhanced LSTM model with ensemble learning significantly improves time-series forecasting accuracy, exhibiting robust generalization and stable predictive performance, thus providing critical insights for real-time monitoring and intelligent alarm systems in urban gas networks.

关键词： Long short term memory Pipelines Logic gates Natural gas prediction algorithms Accuracy Training Forecasting AdaBoost algorithm forecasting long short-term memory natural gas flow

来源：评论

学校读者我要写书评

暂无评论

Research on a Novel Wind Power prediction Method Based on VMD-IMPA-BiLSTM

引用

IEEE ACCESS 2024年 12卷 73451-73469页

作者： Tan, Ning Zhou, Zhiyi Zou, Miaojie Shenyang Jianzhu Univ Sch Management Shenyang 110168 Peoples R China Huaneng Liaoning Power Supply Co Ltd Shenyang 110167 Peoples R China Monash Univ Fac Business & Econ Melbourne Vic 3800 Australia

Wind power, as a pivotal technology in the fight against climate change and the advancement of sustainable energy, occupies an essential role in the global shift towards a new energy paradigm. However, the inherent fluctuation and episodic nature of wind power output pose formidable challenges to achieving precise forecasts, thereby impeding the accuracy of traditional forecasting methodologies. To address this, the paper introduces a novel forecasting approach, the VMD-IMPA-BiLSTM method. This method begins by applying the VMD technique to decompose wind power output into several sub-sequences, significantly reducing data non-stationarity and thus mitigating the negative impact of data volatility on forecasting accuracy. The IMPA method, an improvement over the traditional MPA, incorporates a Tent chaotic mapping for population initialization and a priority selection strategy based on average fitness, enhancing the model's ability to perform global searches and local optimizations. Moreover, the IMPA is leveraged to optimize critical parameters of the BiLSTM, such as maximum training iterations, hidden layer units, and learning rate, thereby curtailing the subjectivity inherent in manual tuning and bolstering the model's forecasting robustness. A thorough comparative analysis with other models has been conducted to evaluate the performance of the developed VMD-IMPA-BiLSTM forecasting model comprehensively. Simulation results indicate that the proposed method significantly outperforms the benchmark models in terms of prediction accuracy across various application scenarios, showcasing not only exceptional stability in forecasts but also a robust generalization capability across diverse contexts.

关键词： Predictive models Wind power generation Wind forecasting Forecasting Data models prediction algorithms Optimization Climate change Long short term memory Hyperparameter optimization Bidirectional control Wind power prediction variational modal decomposition improved marine predator algorithm bidirectional long and short-term memory neural networks hyperparameter optimization

来源：评论

学校读者我要写书评

暂无评论

A Novel Blending Approach for Smoking Status prediction in Hidden Smokers to Reduce Cardiovascular Disease Risk

引用

IEEE ACCESS 2024年 12卷 162956-162976页

作者： Ammar, Muhammad Javaid, Nadeem Alrajeh, Nabil Shafiq, Muhammad Aslam, Muhammad Natl Yunlin Univ Sci & Technol Int Grad Sch Artificial Intelligence Touliu 64002 Taiwan King Saud Univ Coll Appl Med Sci Dept Biomed Technol Riyadh 11633 Saudi Arabia Yeungnam Univ Sch Comp Sci & Engn Gyongsan 38541 South Korea Aberystwyth Univ Dept Comp Sci Aberystwyth SY23 3FL Wales

Smoking has a serious complicated impact on Cardiovascular Health (CVH), which makes it an easily controlled risk factor for Cardiovascular Disease (CVD). The importance of early diagnosis and treatment is crucial because of CVD, which remains to be the leading cause of morbidity and death across the globe, therefore, smoking behaviour prediction is essential. This research explores the complex relationship between smoking and CVD, and clarifies how smoking negatively impacts CVH. The first step of the analysis is removing the Not-a-Number (NaN) values in the smoking behaviour bio signals data because all NaN values are in the target column 'smoking', which could lead to generate biased predictions. Further, robust scaling is applied to standardize the data, where all features are on the same scale. The Random Forest feature selection technique is applied to select the most relevant features for smoking status prediction. The Borderline-Synthetic Minority Oversampling Technique is used to balance the minority class with the majority class, to reduce the risk of overfitting in results. Finally, the cleaned and preprocessed data is passed to the Proposed Blending Model (PBM). In PBM, the Echo State Network and GoogleNet are placed on the base layer, and AlexNet is placed on the meta layer to make a robust smoking status prediction model. In terms of accuracy, precision, recall, and f1-score, the PBM outperforms the baseline techniques with an improvement score of 5%, 6%, 5%, and 7%, respectively. Additionally, the PBM's results are validated through a 10-fold cross-validation method, which can increase its reliability and durability. Finally, the SHapley Additive exPlanations technique is used to understand the predictions made by the PBM. It can reveal the explainability and interpretability of the PBM. Conclusively, during the thorough simulation process, the results are collected and the ablation study is performed. The simulation results show that the early predic

关键词： Predictive models Diseases Data models Lung cancer prediction algorithms Medical diagnostic imaging Analytical models Accuracy Random forests Biological system modeling AlexNet borderline-synthetic minority oversampling technique cardiovascular disease deep learning echo state network GoogleNet proposed blending model random forest SHapley additive exPlanations smoking status prediction

来源：评论

学校读者我要写书评

暂无评论

Dense Contrastive-Based Federated Learning for Dense prediction Tasks on Medical Images

引用

IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS 2024年第4期28卷 2055-2066页

作者： Yang, Yuning Liu, Xiaohong Gao, Tianrun Xu, Xiaodong Zhang, Ping Wang, Guangyu Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing 100876 Peoples R China UCL UCL Canc Inst London WC1E 6DD England

Deep learning (DL) models have achieved remarkable success in various domains. But training an accurate DL model requires large amounts of data, which can be challenging to obtain in medical settings due to privacy concerns. Recently, federated learning (FL) has emerged as a promising solution that shares local models instead of raw data. However, FL in medical settings faces challenges of client drift due to the data heterogeneity across dispersed institutions. Although there exist studies to address this challenge, they mainly focus on the classification tasks that learn global representation of an entire image. Few have been studied on the dense prediction tasks, such as object detection. In this study, we propose dense contrastive-based federated learning (DCFL) tailored for dense prediction tasks in FL settings. DCFL introduces dense contrastive learning to FL, which aligns the local optimization objectives towards the global objective by maximizing the agreement of representations between the global and local models. Moreover, to improve the performance of dense target prediction at each level, DCFL applies multi-scale contrastive representation by utilizing multi-scale representations with dense features in contrastive learning. We evaluated DCFL on a set of realistic datasets for pulmonary nodule detection. DCFL demonstrates an overall performance improvement compared with the other federated learning methods in heterogeneous settings-improving the mean average precision by 4.13% and testing recall by 6.07% in highly heterogeneous settings.

关键词： Task analysis Predictive models Training Federated learning Self-supervised learning prediction algorithms Servers Client drift dense prediction object detection federated learning contrastive learning

来源：评论

学校读者我要写书评

暂无评论

Aging Assessment of Insulating Paper Based on Furfural Concentration prediction in Transformer Oil

引用

IEEE TRANSACTIONS ON DIELECTRICS AND ELECTRICAL INSULATION 2024年第4期31卷 2226-2234页

作者： Zhang, Heng Liu, Jiefeng Jiang, Zaijun Fan, Xianhao Zhang, Dongdong Li, Wen Liu, Chuying Rao, Ruidong Wu, Thomas Guangxi Univ Guangxi Key Lab Power Syst Optimizat & Energy Tech Nanning 530004 Guangxi Peoples R China Tsinghua Univ Dept Elect Engn Beijing 100084 Peoples R China

Furfural is a chemical marker that characterizes the aging state of paper insulation in power transformers. Current research lacks reports on the prediction of furfural concentration in insulating oils, which is not favorable for predicting the potential failure or aging state of transformer paper insulation. In light of this, this article presents a method for predicting furfural concentrations utilizing the multistrategy particle swarm optimization (MSPSO) combined with the back propagation neural network (BPNN) algorithm (MSPSO-BPNN), and thus evaluates the aging state of the insulating paper. First, oil-paper insulation samples are prepared under laboratory conditions, and concentrations of furfural in oil are measured at different aging periods;second, the furfural concentration time-series data are predicted using the MSPSO-BPNN algorithm, and the root mean squared error (RMSE) of the predicted results reached 0.05;ultimately, based on the predicted furfural concentration data and the furfural-polymerization degree (DP) assessment model considering the second-order aging kinetic theory, the aging assessment of the insulating paper has been achieved with an accuracy of 98.7%. Therefore, this work can provide technical and theoretical support in the assessment of the aging state of insulating paper through the application of furfural concentration prediction.

关键词： Aging Oils Power transformer insulation Oil insulation prediction algorithms Statistics Sociology Aging assessment furfural concentration prediction multistrategy particle swarm optimized back propagation neural network (BPNN) algorithm oil-paper insulation power transformer

来源：评论

学校读者我要写书评

暂无评论

Characterization of the Complexity of Computing the Minimum Mean Square Error of Causal prediction

引用

IEEE TRANSACTIONS ON INFORMATION THEORY 2024年第9期70卷 6627-6638页

作者： Boche, Holger Pohl, Volker Poor, H. Vincent Tech Univ Munich Chair Theoret Informat Technol D-80333 Munich Germany BMBF Res Hub 6G Life D-80333 Munich Germany Ctr Quantum Sci & Technol MCQST D-80799 Munich Germany Munich Quantum Valley MQV D-80807 Munich Germany Princeton Univ Dept Elect & Comp Engn Princeton NJ 08544 USA

This paper investigates the complexity of computing the minimum mean square prediction error for wide-sense stationary stochastic processes. It is shown that if the spectral density of the stationary process is a strictly positive, computable continuous function then the minimum mean square error (MMSE) is always a computable number. Nevertheless, we also show that the computation of the MMSE is a #P-1 complete problem on the set of strictly positive, polynomial-time computable, continuous spectral densities. This means that if, as widely assumed, FP1 not equal #P-1 , then there exist strictly positive, polynomial-time computable continuous spectral densities for which the computation of the MMSE is not polynomial-time computable. These results show in particular that under the widely accepted assumptions of complexity theory, the computation of the MMSE is generally much harder than an $NP_{1}$ complete problem.

关键词： Stochastic processes Finite impulse response filters Computational complexity Turing machines Signal processing algorithms Filtering theory prediction algorithms Wiener prediction filter minimum mean square error computability Turing machine complexity theory complexity blowup

来源：评论

学校读者我要写书评

暂无评论

***: AdaBoost Integrated With Residual-Based Decision Tree for Demand prediction of Bike Sharing Systems Under Extreme Demands

引用

IEEE ACCESS 2024年 12卷 144316-144336页

作者： Lee, Dohyun Kim, Kyoungok Seoul Natl Univ Sci & Technol SeoulTech Dept Data Sci Seoul 01811 South Korea Seoul Natl Univ Sci & Technol SeoulTech Dept Ind Engn Seoul 01811 South Korea

Boosting algorithms are widely used for predicting demand in bike-sharing systems (BSSs). However, these systems often encounter sudden spikes in demand (extreme demand). Ordinary boosting algorithms tend to be biased toward extreme demands, leading to increased prediction errors in other scenarios. Noise-robust boosting algorithms perform well with normal samples;however, for normal samples in datasets containing extreme demands, their accuracy remains poor for extreme demand samples. To address these limitations, we propose a novel boosting algorithm, ***, which integrates adaptive boosting with a residual-based decision tree. Our approach aims to enhance prediction accuracy for extreme demand scenarios without compromising performance in normal situations. By incorporating a decision tree (DT) model at each boosting iteration to predict residuals from the base model, we effectively identify and improve predictions for underestimated extreme demands. *** was compared with six boosting algorithms, including noise-robust variants, using Seoul Bike and Daejeon Bike data. Experimental results demonstrated that the DT model within *** effectively distinguished between over- and under-estimated samples, significantly reducing prediction errors for extreme demand scenarios with compromised accuracy for very low demands. On the stance in operating a shared bicycle service, it is important to alleviate the customer dissatisfaction caused by not being able to rent bicycle encouraged by extreme events. Therefore, it should be achieved even if it requires compromised accuracy for very low demands.

关键词： prediction algorithms Boosting Accuracy Predictive models Noise robustness Adaptation models Noise measurement Decision trees Training Shared transport Bicycles AdaBoost bike demand prediction bike sharing system extreme demand noise-robust boosting

来源：评论

学校读者我要写书评

暂无评论

Adaptive Synchronization Interface With Key-Frame prediction Method for Accelerating Power Electronics Co-Simulation

引用

IEEE JOURNAL OF EMERGING AND SELECTED TOPICS IN POWER ELECTRONICS 2024年第6期12卷 6017-6027页

作者： Liu, Weicheng Zhao, Zhengming Zeng, Yangbin Zheng, Jialin Xu, Han Shi, Bochen Mou, Di Li, Hong Tsinghua Univ Dept Elect Engn Beijing 100084 Peoples R China South China Univ Technol Sch Elect Power Guangzhou 510641 Peoples R China Beijing Jiaotong Univ Sch Elect Engn Beijing 100044 Peoples R China

The co-simulation is becoming increasingly popular in the analysis and design of power electronic systems (PESs). However, effectively synchronizing system state changes caused by switches poses a challenge, as the existing methods often incur high-interaction time costs. Therefore, this article introduces an adaptive synchronization interface (ASI), leveraging the discrete-continuous characteristics of PES to minimize the number of synchronization points and accelerate co-simulation. The key-frame prediction algorithm precisely identifies the system state change caused by power electronic switches and the external system. Subsequently, the proposed ASI utilizes the key-frame to dynamically adjust synchronization step size, thereby enhancing the accuracy and efficiency of co-simulation. The ASI is deployed on a co-simulation prototype for Simulink and DSIM. Additionally, a case study involving a 10-kVA modular multilevel converter (MMC) demonstrates alignment with experimental results, the ASI achieving a 394-fold reduction in synchronization time costs, compared to the fixed time-step synchronization interface (FSI) while maintaining accuracy. The proposed ASI presents a promising co-simulation interface for accelerating PES co-simulations.

关键词： Synchronization Switches Power electronics Accuracy Power systems prediction algorithms Pulse width modulation Adaptive synchronization interface (ASI) co-simulation key-frame power electronic system (PES)

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：