检索结果-内蒙古大学图书馆

Transformer-Based Intelligent prediction Model for Multimodal Multi-Objective Optimization

IEEE COMPUTATIONAL INTELLIGENCE MAGAZINE 2025年第1期20卷 34-49页

作者： Dang, Qianlong Zhang, Guanghui Wang, Ling Yu, Yang Yang, Shuai He, Xiaoyu Northwest A&F Univ Yangling 712100 Peoples R China Hebei Agr Univ Baoding 071001 Peoples R China Tsinghua Univ Beijing 100084 Peoples R China Jiangsu Univ Technol Changzhou 213001 Peoples R China Anhui Agr Univ Hefei 230036 Peoples R China Sun Yat Sen Univ Guangzhou 510006 Peoples R China

Traditional multimodal multi-objective evolutionary algorithms (MMOEAs) usually adopt the reproduction strategy based on meta-heuristic and fail to make full use of changes of multi-generation population distribution, which can help the population to further evolve and improve the exploitation ability of algorithms. To address this issue, this paper proposes a deep learning-based evolutionary algorithm (DLEA), which converts historical population information into time series and uses deep neural networks to predict the population distribution. Specifically, a transformer-based prediction model is constructed to reproduce promising offspring by capturing changes of population distribution in adjacent generations. Moreover, many MMOEAs focus only on global Pareto optimal solution sets (PSs) and ignore local PSs. Although local PSs are inferior to global PSs in terms of objective values, the cost of obtaining global PSs in some practical applications is huge. Local PSs with similar objectives to global PSs are acceptable alternatives for decision makers. Therefore, a difference-based attention mechanism is designed for archive update, which saves solutions on the global PSs and local PSs by calculating the attention value. Experimental studies indicate that DLEA outperforms other six competitive MMOEAs.

关键词： Attention mechanisms Time series analysis Metaheuristics Evolutionary computation Artificial neural networks Predictive models Transformers prediction algorithms Path planning Planning

来源：评论

学校读者我要写书评

暂无评论

Early prediction of Cardiac Arrhythmia using Novel Bio-inspired algorithms 8

Early Prediction of Cardiac Arrhythmia using Novel Bio-inspi...

引用

8th International Conference on Smart Structures and Systems, ICSSS 2022

作者： Digumarthi, Jyothirmai Gayathri, V.M. Pitchai, R. School of Computing Srm Institute of Science and Technology Tamilnadu Kattankulathur India Srm Institute of Science and Technology Department of Networking and Communications Kattankulathur India B v Raju Institute of Technology Department of Computer Science and Engineering Narsapur India

ISBN: (纸本)9781665497619

Cardiovascular disease is one of the world's most dangerous problems since it cannot be seen with the naked eye and strikes suddenly when its levels are reached. Cardiovascular disease (CVD) has reached the top of the list of non-infectious and non-transmissible disease deaths worldwide. Arrhythmias are a set of cardiovascular disorders described by irregular heartbeats that can be slow, rapid, or both. Cardiac arrhythmias are responsible for a large number of cardiac arrests and sudden deaths. They can happen on their own or in combination with other heart conditions. Some significant arrhythmias can happen out of nowhere, resulting in sudden death, stroke, heart failure, and coronary artery disease. Many of the medical procedures used to treat cardiac arrhythmias are traditional. Especially when contrasted to costly procedures that may be required if detection and therapy are delayed and the patient has advanced illness stages. To deliver an early, effective, prediction of CVDs, health systems need to be further strengthened. A computer-assisted automated prediction and classification of heart diseases using Bio-Inspired Optimization algorithms is suggested in this research work. Extraction, classification, and diagnostic sections would be part of the proposed method. This work helps in diagnosis of cardiac arrhythmias. This study also helps effectively and accurately to diagnose the heart condition, which could help the doctor to treat and manage the disease effectively. © 2022 IEEE.

关键词： Heart Hypertension Heart beat Medical treatment prediction algorithms Classification algorithms Intelligent structures

来源：评论

学校读者我要写书评

暂无评论

Clustering-Based Short-Term Wind Speed Interval prediction With Multi-Objective Ensemble Learning

引用

IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE 2025年第1期9卷 304-317页

作者： Zhu, Qingling Xu, Yaojian Lin, Qiuzhen Ming, Zhong Tan, Kay Chen Shenzhen Univ Natl Engn Lab Big Data Syst Comp Technol Shenzhen 518060 Peoples R China Shenzhen Univ Coll Comp Sci & Software Engn Shenzhen 518060 Peoples R China Hong Kong Polytech Univ Dept Comp Hong Kong Peoples R China

As a renewable and green energy source, wind energy has attracted great attention from academia and industry in recent decades. However, it is challenging to integrate wind energy into smart grids due to the instability and randomness of wind speed. To solve this problem, this paper proposes a clustering-based short-term wind speed interval prediction with multi-objective ensemble learning, which can provide an accurate and reliable wind speed interval prediction to support energy dispatch planning. First, a clustering-based uncertainties estimation method segments the initial wind sequence into several groups and determines the estimated width for each group. Second, a variational mode decomposition is employed to acquire the sub-sequence matrix of wind speed, and then a Hurst exponent-based model selection method is used to choose and train an optimal model for each sub-sequence based on its long-term correlation. Finally, an improved multi-objective optimizer is utilized to determine the optimal superposition weights of the prediction results for each model. The proposed approach is evaluated using eight cases from two wind farms, which are published by the National Renewable Energy Laboratory. Experimental results indicate that the proposed approach outperforms several state-of-the-art studies, demonstrating a higher prediction interval coverage probability and a narrower prediction interval width.

关键词： Predictive models Wind speed Logic gates Training Time series analysis Reliability prediction algorithms Clustering hurst exponent model selection multi-objective optimization wind speed prediction

来源：评论

学校读者我要写书评

暂无评论

A Novel Ensemble Classifier Selection Method for Software Defect prediction

引用

IEEE ACCESS 2025年 13卷 25578-25597页

作者： Dong, Xin Wang, Jie Liang, Yan Chengdu Technol Univ Comp Engn Coll Chengdu 611730 Peoples R China Sci & Technol Elect Informat Control Lab Chengdu 610036 Peoples R China

The presence of software defects significantly impacts the quality of software systems and increases development and maintenance costs. To improve system quality and reduce costs, it is necessary to predict software defects in the early stages of the software development lifecycle. This paper proposes Double Fault Disagreement (DFD), a novel diversity metric and method for selecting competent base classifiers for ensemble learning-based software defect prediction. To consider the diversity features of the base learners, several base learners with strong diversity are chosen to build ensemble learning. This method makes full use of the diversity characteristics of base learners, leverages their classification ability, optimizes the selection method for ensemble learning, and enhances the predictive performance of the ensemble model. The experimental results demonstrate that the DFD ensemble learning-based software defect prediction model outperforms the ten other models, including five common machine learning (ML) classification algorithms (logistic regression (LR), na & iuml;ve Bayes (NB), K-nearest neighbor (KNN), decision tree (DT), and support vector machine (SVM)), two deep learning (DL) algorithms (multi-layer perceptron (MLP) and convolutional neural network (CNN)), and three ensemble learning algorithms (random forest (RF), extreme gradient boosting (XGB), and stacking). The DFD model achieves superior performance on eight public NASA and PROMISE datasets (six of which are imbalanced) across five performance indicators, including area under the curve (AUC), geometric mean (G-Mean), F1 score, Matthews correlation coefficient (MCC), and Balance. Furthermore, the DFD method is not only highly performant but also requires a small number of base learners to converge rapidly, thereby reducing the amount of data and computation time required.

关键词： Ensemble learning Predictive models Measurement Computational modeling Classification algorithms Software Volume measurement Weight measurement Stacking prediction algorithms Diversity measures double fault disagreement ensemble classifier selection imbalanced data classification software defect prediction

来源：评论

学校读者我要写书评

暂无评论

Residential Building Energy Usage prediction Using Bayesian-Based Optimized XGBoost Algorithm

引用

IEEE ACCESS 2025年 13卷 36036-36049页

作者： Baqer, Nabaa Riyadh Rashidi-Khazaee, Parviz Urmia Univ Dept Comp Engn Orumiyeh *** Iran Urmia Univ Technol Dept Informat Technol & Comp Engn Orumiyeh *** Iran

With the growing energy demand in residential buildings, selecting energy-efficient building designs is crucial for sustainable development. Therefore, engineers and designers try to find a reliable tool to help them analyze and predict the energy consumption of buildings in the early design stages before construction. The state-of-the-art eXtreme Gradient Boosting (XGB) algorithm was successfully used to estimate the Heating Load (HL) and Cooling Load (CL) energy usage based on building design characteristics. To enhance the performance of XGB and improve prediction reliability, we propose a novel Bayesian optimization approach using the Tree-Structured Parzen Estimator (TPE), leading to the development of the TPE-XGB model for HL and CL estimation. Also, a new fair evaluation method was proposed to have a fair evaluation. The evaluation results based on the proposed fair evaluation method showed that the proposed model has outperformed other state-of-the-art models and improved the prediction accuracy of HL and CL by 3.4% (from 0.175 to 0.167) and 10.4% (from 0.307 to 0.275), respectively. As a result, the new proposed model provides the opportunity to be used as a strong and reliable tool in the early stages of building construction and to evaluate different designs/plans regarding energy consumption efficiency to select the best design with high reliability.

关键词： Predictive models Buildings prediction algorithms Energy consumption Tuning Radio frequency Metaheuristics Data models Bayes methods Heuristic algorithms Energy efficiency energy usage prediction tree-structured Parzen estimator hyper-parameter tuning heating load cooling load

来源：评论

学校读者我要写书评

暂无评论

Airport Capacity prediction and Optimization Based on Semi-Varying Coefficient and Dynamic Programming

引用

IEEE ACCESS 2025年 13卷 67908-67924页

作者： Xia, Huan Yao, Weirui Zheng, Yi Jiang, Chaozhe Zhang, Chenyang Southwest Jiaotong Univ Sch Transportat & Logist Chengdu 610032 Peoples R China Xihua Univ Sch Comp & Software Engn Chengdu 610097 Peoples R China Second Res Inst Civil Aviat Adm China Chengdu 610000 Peoples R China

Air traffic congestion has emerged as a critical challenge in modern air traffic management. Adverse weather conditions and other factors frequently lead to reduced airport arrival capacity, resulting in flight delays. Accurate capacity prediction and optimization are essential for maximizing airport utilization and minimizing flight delays. This study introduces a capacity prediction model based on the semi-varying coefficient approach, utilizing real-world data from Guangzhou Baiyun Airport collected over a specific time period. Through 5-fold cross-validation, the semi-varying coefficient model is compared to the varying-coefficient model, demonstrating superior out-of-sample prediction capabilities. Subsequently, we establish and solve a flight arrival and departure flow allocation optimization model using dynamic programming to enhance traffic flow coordination. Analysis of case study results demonstrates that this method can generate optimal strategies for allocating arrival and departure traffic flows within airport capacity constraints, thereby minimizing overall flight delay costs.

关键词： Airports Atmospheric modeling Delays Estimation Predictive models Resource management Meteorology prediction algorithms Optimization Fitting Air traffic flow management airport capability utilization capacity prediction flow allocation

来源：评论

学校读者我要写书评

暂无评论

A Collaborative Multi-Component Optimization Model Based on Pattern Sequence Similarity for Electricity Demand prediction

引用

IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE 2025年第1期9卷 119-130页

作者： Tang, Xiaoyong Zhang, Juan Cao, Ronghui Liu, Wenzheng Changsha Univ Sci & Technol Sch Comp & Commun Engn Changsha 410114 Peoples R China Hunan Univ Informat Technol Sch Comp Sci & Engn Changsha 410148 Peoples R China

In the new electricity market, the accurate electricity demand prediction can make high possible profit. However, electricity consumption data exhibits nonlinearity, high volatility, and susceptibility to various factors. Most existing prediction schemes inadequately account for these traits, resulting in weak performance. In view of this, we propose a collaborative multi-component optimization model (MCO-BHPSF) to achieve high accuracy electricity demand prediction. For this model, the original data is first decomposed into linear trend components and nonlinear residual components using the Moving Average filter. Then, the enhanced Pattern Sequence-based Forecasting (PSF) algorithm that can effectively capture data patterns with obvious changes is used to accurately forecast the trend component and the embedded LightGBM for residual components. We further optimize the prediction results by using an error optimization scheme based on online sequence extreme learning machines to reduce prediction errors. The results of extensive experiments on four real-world datasets demonstrate that our proposed MCO-BHPSF model outperforms four advanced baseline models. In day-ahead prediction, our model is on average 31% better than PSF baselines. For long-term prediction, our proposed MCO-BHPSF model has an average improvement rate of 37% compared to PSF baselines.

关键词： Predictive models Electricity prediction algorithms Accuracy Time series analysis Optimization Forecasting Machine learning pattern sequence electricity demand prediction component prediction LightGBM

来源：评论

学校读者我要写书评

暂无评论

Reversible Data Hiding in Encrypted Images Based on Edge-Directed prediction and Multi-MSB Self-prediction

引用

IEEE ACCESS 2025年 13卷 63000-63012页

作者： Qiu, Yingqiang Huaqiao Univ Coll Informat Sci & Engn Xiamen 361021 Peoples R China

With the development of cloud computing, reversible data hiding in encrypted images (RDH-EI) technology has gained significant attention in ensuring data security and privacy protection. This paper proposes a high-capacity RDH-EI method that employs a dual prediction strategy, including edge-directed prediction and multiple most significant bits (multi-MSB) self-prediction. First, the image owner utilizes the edge-directed property of least-square optimization to enhance the accuracy of pixel prediction. Subsequently, each pixel undergoes self-prediction starting from the MSB and progressing towards an adaptive high-order bit-plane, plane by plane. A binary location map marks the prediction errors for each bit-plane. After being losslessly compressed using the Joint Bi-level Image Experts Group (JBIG) algorithm, the location maps are embedded into the encrypted image as auxiliary data, thereby creating ample room for embedding additional data. Next, the data hider retrieves the auxiliary data from the encrypted image and embeds the additional data into the reserved embedding room, resulting in a marked encrypted image. Finally, authorized recipients with different keys can either accurately extract data or precisely restore the image from the marked encrypted image without any errors. The experimental results show that the proposed method achieves average pure embedding rates of 4.240 bpp for BOSSBase dataset and 4.088 bpp for BOWS-2 dataset, respectively, outperforming many state-of-the-art RDH-EI methods.

关键词： Cryptography Encryption Image coding Redundancy prediction algorithms Image edge detection Correlation Accuracy Receivers Image restoration Reversible data hiding encrypted image edge-directed prediction multi-MSB self-prediction JBIG

来源：评论

学校读者我要写书评

暂无评论

Gray System prediction Model of GUR Based on Error Feedback Compensation

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2025年 74卷

作者： Guo, Kai Zhang, Yaxian Zhang, Sen Xiao, Wendong Univ Sci & Technol Beijing Sch Automat Beijing 100083 Peoples R China

The blast furnace (BF) is the key equipment for smelting, which consumes about 70% of the energy in the iron-making process. Therefore, improving the smelting efficiency in the context of global energy saving and emission reduction is crucial. The gas utilization rate (GUR) cannot be measured directly, as it is a ratio of different variables. The GUR can directly characterize the energy utilization efficiency of the BF, so energy consumption can be reduced if the GUR prediction model is established. This article proposes the gray system prediction model (GSPM) for GUR. First, the key variables that affect the GUR are obtained through analysis of the smelting process. Then, the time lags of the above key variables are determined through correlation analysis (CA). The principal component analysis (PCA) is adopted to rule out irrelevant and negatively correlated variables, as different variables impact GUR differently. Finally, the GSPM for BF GUR is established, and the feedback compensation is implemented based on the prediction error. The experimental results between GSPM with and without error feedback compensation indicate that the proposed model can reduce the maximum prediction error by about 55%. The mean squared error indices of the proposed GSPM, feedforward, and deep learning neural network (DLNN) under 100 samples are 0.251, 1.635, and 0.6247, which means that the GSPM performs better in the accuracy indicator.

关键词： Predictive models Smelting Data models Carbon monoxide Accuracy Atmospheric modeling Machine learning Carbon dioxide prediction algorithms Feature extraction Error feedback compensation gas utilization rate (GUR) gray system prediction model (GSPM) principal component analysis (PCA)

来源：评论

学校读者我要写书评

暂无评论

Dynamic Window Approach Using GOA Search Algorithm for Collision Avoidance Based on Obstacle Trajectory prediction

引用

IEEE ACCESS 2025年 13卷 44169-44183页

作者： Liu, Yuan Zhang, Lingyu Liu, Jiasheng She, Yingying Zhang, Birui Min, Feiyan Wuhan Second Ship Design & Res Inst Wuhan 430030 Peoples R China Jinan Univ Sch Intelligent Syst Sci & Engn Zhuhai 519070 Peoples R China

Mobile robots not only need to navigate autonomously in complex environments, but also need to avoid collisions with dynamic obstacles, especially pedestrians. This paper realizes dynamic obstacles detection and state estimation algorithm with LiDAR data, and proposes the path planning and obstacle avoidance algorithm based on dynamic obstacle trajectory prediction. The current planning methods of mobile robots are mostly applicable to static scenes and lack adaptability to pedestrian dynamics. The core idea of the proposed algorithm is to guide the mobile robot towards the back of the pedestrian to reduce the psychological pressure on the pedestrian as well as to avoid interfering with the pedestrian's movement and to achieve dynamic obstacle avoidance, which is in line with the idea of going around from the back in the Convention on the International Regulations for the Avoidance of Collisions at Sea (COLREGS). Firstly, the pedestrian detection method is studied on the basis of Lidar data, and the pedestrian motion state is estimated based on Kalman filter to avoid error detection. Secondly, the dynamic window approach (DWA) method is improved and pedestrian dynamic is added with carefully designed algorithm for path planning and obstacle avoidance. Furthermore, to improve the computational efficiency and flexibility, the GOA(Grasshopper Optimization Algorithm) is used to improve the DWA search schema. Finally, the effectiveness of the proposed method is proved by comparing the existing methods with simulation and experimental tests. The research of this paper can improve the safety of the robot in the human-machine crowd scene.

关键词： Heuristic algorithms Pedestrians Collision avoidance Laser radar prediction algorithms Trajectory Legged locomotion Planning Classification algorithms Vehicle dynamics dynamic window approach trajectory prediction GOA algorithm

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：