检索结果-内蒙古大学图书馆

Online estimation method for extreme learning machine with kernels based on the multi-innovation theory and intelligent optimization strategy

引用

ISA TRANSACTIONS 2025年 156卷 142-153页

作者： Wang, Yanjiao Liu, Yiting Li, Weidi Deng, Muqing Wang, Kaiwei Guangdong Univ Technol Sch Automat Guangzhou 510006 Peoples R China Guangdong Prov Key Lab Elect Informat Prod Reliabi Guangzhou 511370 Peoples R China

In order to effectively model data online, a learning model must not only have the high adaptability of dynamic data but also keep the low complexity to meet the online computing requirements. In this paper, a novel multi-innovation online sequential extreme learning machine (MIOSELM) and its kernel version called multi- innovation kernel online sequential extreme learning machine (MIKOSELM) are proposed to establish the online estimation models based on p latest samples using the multi-innovation theory. Besides, a modified whale optimization algorithm (MWOA) is introduced to optimize the execution parameters of our algorithms and is capable of automatically searching a proper p as the practical need, which can further improve the adaptability performance of the online learning models. Finally, two different datasets (the UCI dataset and KDD99 dataset) are used to evaluate the superiority of our methods. Experimental results show that the accuracy, F-score, and G-mean of MIKOSELM are 98.25%, 98.11% and 98.63% on WDBC from the UCI dataset, and are 83.61%, 75.96% and 70.97% on the KDD99 dataset respectively. Besides, our MIKOSELM based on MWOA achieves F-score of 94.28% and 76.73% on Musk from the UCI dataset and the KDD99 dataset. These results validate the effectiveness of our proposed methods.

关键词： Kernel extreme learning machine Online learning model Parameter estimation Multi-innovation theory swarm intelligence algorithm

来源：评论

学校读者我要写书评

暂无评论

Stochastic biogeography-based learning improved RIME algorithm: application to image segmentation of lupus nephritis

引用

CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS 2024年第10期27卷 14185-14229页

作者： Zheng, Boli Chen, Yi Wang, Chaofan Heidari, Ali Asghar Liu, Lei Chen, Huiling Chen, Xiaowei Chen, Peirong Wenzhou Univ Inst Big Data & Informat Technol Wenzhou 325000 Peoples R China Univ Tehran Coll Engn Sch Surveying & Geospatial Engn Tehran Iran Sichuan Univ Coll Comp Sci Chengdu 610065 Sichuan Peoples R China Wenzhou Med Univ Affiliated Hosp 1 Dept Rheumatol & Immunol Wenzhou 325000 Peoples R China

Lupus nephritis (LN) is the most common symptom of systemic lupus erythematosus, emphasizing its importance in the field of medicine. The growing frequency of LN has increased the need for effective image segmentation algorithms. With the increasing prevalence of LN, the demand for efficient image segmentation techniques has grown. To enhance the efficiency of image segmentation of LN, many researchers employ a methodology that integrates multi-threshold image segmentation (MTIS) with metaheuristic algorithms (MAs). However, conventional MAs-based MTIS methods tend to converge towards local optima and have slow convergence rates, resulting in poor segmentation results within a limited iteration number. To address these challenges, this study proposes an advanced optimization algorithm termed Biogeography-based Learning Rime Optimization algorithm (BLRIME) and integrates it with the MTIS approach for LN image segmentation. MTIS employs a non-local means 2D histogram to gather image information and uses 2D Renyi's entropy as the fitness function. BLRIME builds upon the foundation of the RIME algorithm, incorporating two significant strategies. Firstly, the introduction of piecewise chaotic mapping (PCM) ameliorates the quality of the initial solution provided by the algorithm. Secondly, a stochastic biogeography-based learning strategy (SBLS) prevents the RIME algorithm from falling into the local optimum early. SBLS is proposed by this study based on the biogeography-based learning strategy. In order to assess the efficacy of the BLRIME, this paper devises a series of experiments to compare it with similar algorithms presented at IEEE CEC 2017. Experimental studies have been conducted to provide empirical evidence demonstrating the superior rates of convergence and precision achieved by BLRIME. Subsequently, the BLRIME-based MTIS algorithm is employed to segment the LN images compared to other peer algorithms. Furthermore, the peak signal-to-noise ratio, feature simi

关键词： swarm intelligence algorithm Chaotic mapping Rime optimization algorithm Renal pathology Biogeography-based strategy

来源：评论

学校读者我要写书评

暂无评论

Multi-strategy chimp optimization algorithm for global optimization and minimum spanning tree

引用

SOFT COMPUTING 2024年第3期28卷 2055-2082页

作者： Du, Nating Zhou, Yongquan Luo, Qifang Jiang, Ming Deng, Wu Guangxi Univ Nationalities Coll Artificial Intelligenc Nanning 530006 Peoples R China Guangxi Key Labs Hybrid Computat & IC Design Anal Nanning 530006 Peoples R China Guangxi Inst Digital Technol Nanning 530000 Peoples R China Civil Aviat Univ China Coll Elect Informat & Automat Tianjin 300300 Peoples R China

Aiming at the shortcomings of Chimp optimization algorithm (ChOA), which is easy to fall into local optimal value and imbalance between global exploration ability and local exploitation ability. To improve ChOA from the perspective of multi-strategy mixing, MSChimp was proposed, and the algorithm was applied to global optimization and minimum spanning tree problems. The main research work of this paper is as follows: (1) In the initialization stage of ChOA, an opposition-based learning strategy was introduced to improve the population diversity;Sine Cosine algorithm (SCA) was introduced in the exploitation process to improve the convergence speed and accuracy of the algorithm in the later stage, so as to balance the exploration and exploitation capabilities of the algorithm. (2) The improved algorithm was compared with different types of meta-heuristic algorithms in 20 benchmark functions and CEC 2019 test sets, and was used to solve the minimum spanning tree. The experimental results show that the improved ChOA has significantly improved the ability to find the optimal value, which verifies the effectiveness and feasibility of MSChimp. Compared with other algorithms, the algorithm proposed in this paper has strong competitiveness.

关键词： Chimp optimization algorithm Opposition-based learning strategy Sine cosine algorithm Minimum spanning tree swarm intelligence algorithm

来源：评论

学校读者我要写书评

暂无评论

Monthly Runoff forecasting using A Climate-driven Model Based on Two-stage Decomposition and Optimized Support Vector Regression

引用

WATER RESOURCES MANAGEMENT 2024年第14期38卷 5701-5722页

作者： Jia, Zhuo Peng, Yuhao Li, Qin Xiao, Rui Chen, Xue Cheng, Zhijin Nanchang Univ Sch Infrastruct Engn Nanchang 330031 Peoples R China Nanchang Univ Key Lab Poyang Lake Environm & Resource Utilizat Minist Educ Nanchang 330031 Peoples R China Jiangxi Acad Sci Inst Energy Res Nanchang 330096 Peoples R China

Accurate and reliable monthly runoff forecasting is crucial for water resource management, but the increasing non-stationarity of runoff series poses new challenges to the development of forecasting models. To overcome these problems, this study proposes a novel climate-driven hybrid model based on two-stage decomposition ***, called ICEEMDAN-SVMD-ESPSO-SVR. Firstly, the original runoff is decomposed into a set of components by improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN), and high-frequency components identified through entropy analysis are further decomposed into multiple subcomponents by successive variational mode decomposition (SVMD). Secondly, the input variables are selected from the candidate set consisting of runoff, subcomponents and key climate factors by using correlation coefficient and mutual information, respectively. Thirdly, support vector regression (SVR) is employed to forecast each sub-component, and particle swarm optimization algorithm using eagle strategy (ESPSO) is used to select each model's parameters. Finally, the forecasted values of all sub-components are aggregated as the final result. Monthly runoff data from three different hydrological stations in China's Poyang Lake Basin are employed to evaluate the performance of the proposed hybrid model and other comparable models. Results indicate that the proposed hybrid model outperforms single models and other combination models based on single-stage decomposition, and the correlation coefficient method is more suitable for input variable selection in climatedriven models, thus confirming the effectiveness of two-stage decomposition, the ESPSO algorithm, and input variable selection in enhancing modeling accuracy. Therefore, the proposed hybrid model is a feasible and promising new method for monthly runoff forecasting.

关键词： Input variable selection Monthly runoff forecasting Support vector regression swarm intelligence algorithm Two-stage decomposition

来源：评论

学校读者我要写书评

暂无评论

Energy-aware virtual machine placement based on a holistic thermal model for cloud data centers

引用

FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE 2024年 161卷 302-314页

作者： Lin, Jianpeng Lin, Weiwei Wu, Wentai Lin, Wenjun Li, Keqin South China Univ Technol Dept Comp Sci & Engn Guangzhou 510000 Peoples R China Peng Cheng Lab Shenzhen 518066 Peoples R China Jinan Univ Coll Informat Sci & Technol Guangzhou 510000 Peoples R China SUNY Coll New Paltz Dept Comp Sci New Paltz NY 12561 USA

As energy-intensive infrastructures, data centers (DCs) have become a pressing challenge for managers due to their significant energy consumption and carbon emissions. Information technology (IT) and cooling systems contribute the most to energy consumption. Energy-aware virtual machine (VM) scheduling methods have been widely demonstrated to reduce energy consumption and operating costs in DCs. However, as realistic DCs exhibit complex power and thermodynamic behaviors, existing works cannot provide efficient measures to optimize computing and cooling power consumption simultaneously. To overcome this challenge, we construct a holistic thermal model (including CPU and server inlet thermal models) to accurately represent the nonuniform, dynamic thermal environment. Subsequently, this work proposes a thermal model-based energy-aware VM placement method (TEVP) to minimize the holistic energy consumption of the DCs, considering resource and thermal constraints. We develop a novel hybrid swarm intelligence algorithm (DE-ERPSO) combining differential evolution (DE) and particle swarm optimization with an elite re-selection mechanism (ERPSO) to explore more energy-efficient VM placement schemes. Extensive experiments are conducted on an extended CloudSim to validate the performance of the proposed TEVP using real-world workload traces (PlanetLab and Azure). Results show that TEVP saves over 5.6% of the total energy consumption over the advanced baselines while maintaining low thermal violations.

关键词： Data center Thermal model VM placement swarm intelligence algorithm Energy saving

来源：评论

学校读者我要写书评

暂无评论

Reconstituted data-driven air conditioning energy consumption prediction system employing occupant-orientated probability model as input and swarm intelligence optimization algorithms

引用

ENERGY 2024年 288卷

作者： Zhang, Chengyu Ma, Liangdong Xing, Han Zhao, Tianyi Dalian Univ Technol Inst Bldg Energy Dalian Peoples R China PCI Technol Grp Guangzhou Peoples R China

With recent energy and environmental crises, the energy consumption prediction of air conditioning (AC) is essential. Notably, existing general prediction systems use the air temperature, real-time AC usage, time, oc-cupancy, and AC historical energy consumption as inputs and employ feedforward neural networks. However, such systems face certain challenges. First, the input system may be difficult to reflect the real-time interaction among the building environment, occupants, and energy system;Second, the algorithms need to be upgraded to further improve accuracy, speed up convergence, and avoid overfitting. his paper introduces a novel parameter (group occupant behavior probability, GOBP) in the input system;and uses swarm intelligence algorithms with chaotic mapping and adaptive weight adjustment as optimization with LSTM and BP as the basic algorithms. The verification results obtained from five different buildings indicate the following: (1) The novel prediction system improved prediction performance with 20.08%-78.37 % of MAPE and 3.99%-53.28 % of CV-RMSE, however, it will increase 148.70s-1065.11s of calculation time. (2) For accuracy, using GOBP will improve the 0.30%-51.87 % and 0.18%-64.77 % by using swarm intelligence optimization algorithms. (3) This paper discusses the priority of selecting suitable inputs, algorithms, and optimization to combine a whole prediction system.

关键词： AC energy consumption Energy consumption prediction Group occupant behavior probability swarm intelligence algorithm Long short-term memory neural network

来源：评论

学校读者我要写书评

暂无评论

WOAD3QN-RP: An intelligent routing protocol in wireless sensor networks - A swarm intelligence and deep reinforcement learning based approach

引用

EXPERT SYSTEMS WITH APPLICATIONS 2024年 246卷

作者： Yang, Xuan Yan, Jiaqi Wang, Desheng Xu, Yonggang Hua, Gang China Univ Min & Technol Sch Informat & Control Engn Xuzhou Peoples R China

Wireless Sensor Networks (WSN) are a crucial part of the Internet of Things (IoT), and research on WSN routing protocols has always been a hot topic in academia. However, traditional WSN routing protocols have limited utilization of available information during the routing decision process, leading to challenges such as insufficient adaptability to network topology changes, high communication delays, and short network lifetimes. To address these issues, this paper proposes an innovative intelligent routing algorithm WOAD3QN-RP, which cleverly integrates swarm intelligence algorithms and deep reinforcement learning. The WOAD3QN-RP not only effectively reduces delay but also balances energy consumption and flexibly adapts to changes in network topology, while simultaneously determining the optimal multi -hop path, effectively extending the lifetime of the network. Firstly, the WOAD3QN-RP algorithm employs the Whale Optimization algorithm (WOA) to determine the optimal cluster heads (CHs). In the process of selecting CHs, the algorithm comprehensively considers key factors such as the residual energy of nodes, node distance, and communication delay, thereby significantly improving the accuracy and efficiency of CH selection, which contributes to better energy distribution and performance of the network. Secondly, in terms of multi -hop path selection, WOAD3QN-RP uses a dueling double deep Q -network (D3QN) to determine the optimal multi -hop path. Through utilizing neural networks to interact with the environment, intelligent agents are trained to learn routing policies to adapt to dynamic changes in the network topology and ensure the balance between energy consumption and multi -hop routing performance. Experimental results show that WOAD3QN-RP exhibits significant advantages over existing routing protocols in terms of network lifetime, energy efficiency, and communication delay.

关键词： Wireless sensor networks Clustering Routing swarm intelligence algorithm Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Multi-Strategy Golden Jackal Optimization for engineering design

引用

JOURNAL OF SUPERCOMPUTING 2025年第4期81卷 1-60页

作者： Yang, Wenbiao Lai, Tingfeng Fang, Yuhui Guangzhou Univ Sch Elect & Commun Engn Guangzhou 510006 Peoples R China Nanyang Technol Univ Sch Mech & Aerosp Engn Nanyang 639798 Singapore

The Golden Jackal Optimization algorithm (GJO) is a swarm intelligence (SI) algorithm utilized for tackling arduous problems in undefined search spaces. In order to address the issues of slow convergence and difficulty in evading local optima encountered by GJO, the Multi-Strategy Golden Jackal Optimization (MSGJO) algorithm is proposed. Three strategies were implemented to enhance the original GJO. Firstly, the utilization of a Good Point Set, as opposed to random numbers, improves the quality of the initial population. Secondly, the introduction of a Quasi-Opposition-Based Learning strategy facilitates the balancing of algorithmic exploration and exploitation capabilities, leading to enhanced convergence efficiency. Lastly, the maintenance of population diversity during the iterative process is achieved through the adoption of the Cauchy mutation and chaotic circle perturbation strategies. A comparative analysis was conducted on 23 benchmark functions using fourteen SI algorithms. Additionally, MSGJO was applied to the CEC2019 competition suite, successfully solving two distinct engineering design problems. The results demonstrate that MSGJO exhibits significant superiority not only in solving problems involving global optimal solutions but also in addressing challenging constrained problems. The code for this study will be available at https://***/ProfYangPaperCode/MSGJO-code.

关键词： swarm intelligence algorithm Golden Jackal Optimization algorithm Quasi-Opposition-Based Learning strategy Benchmark test function Engineering design

来源：评论

学校读者我要写书评

暂无评论

Autonomous bonobo optimization algorithm for power allocation in wireless networks

引用

MATHEMATICS AND COMPUTERS IN SIMULATION 2024年 217卷 294-310页

作者： Eid, Heba F. Cuevas, Erik Mansour, Romany F. Al Azhar Univ Fac Sci Cairo Egypt Univ Guadalajara Dept Elect Guadalajara Mexico New Valley Univ Fac Sci Dept Math Kharga Egypt

Bonobo optimizer (BO) is a recent metaheuristic algorithm inspired by the social behavior of bonobos. BO maintains a robust search strategy based on two distinct phases that involve interesting mechanisms, such as the fission-fusion method for selection and an efficient process for producing new candidate solutions. Despite its remarkable capacity, BO presents a critical flaw that corresponds to an inappropriate balance between exploration and exploitation. Under such conditions, suboptimal or even poor solutions can be obtained. This paper proposes a modified BO algorithm in which the trajectory of each search agent is modified dynamically through the adaptation of the main parameters of the algorithm. With this new mechanism, the algorithm allows for the exploration and exploitation of different regions of the solution space and determines the global optimum in a faster manner. The performance of the proposed algorithm is evaluated by considering two scenarios. One is the optimization of 23 benchmark functions and the second is the problem of power allocation in wireless networks. The results show that the proposed scheme enhances the performance of the basic BO method by increasing the robustness and providing a better solution quality.

关键词： Bonobo optimization algorithm Bio-inspired optimization swarm intelligence algorithm Wireless networks Secure communication Energy-spectral efficiency

来源：评论

学校读者我要写书评

暂无评论

Dynamic formation optimisation for energy saving of a fleet of unmanned surface vehicles based on robust optimisation over time strategy

引用

OCEAN ENGINEERING 2024年 301卷

作者： Dong, Zhenpeng Liang, Xiao Liu, Dianyong Yu, Changdong Li, Wei Dalian Maritime Univ Coll Naval Architecture & Ocean Engn Dalian Liaoning Peoples R China Dalian Maritime Univ Coll Artificial Intelligence Dalian Liaoning Peoples R China Dalian Maritime Univ Coll Environm Sci & Engn Dalian Liaoning Peoples R China

This paper presents a dynamic formation optimisation strategy that focuses on constructing an energy-saving formation for a fleet of unmanned surface vehicles (USVs) by considering two optimisation objectives: minimum energy consumption and minimum switching cost. The dynamic formation optimisation strategy based on robust optimisation over time (ROOT) is used to determine the energy-saving formation with the optimal position layout. The formation switching cost is first proposed to define the energy consumption cost of switching from the original position to the new position. Dynamic environments are established using the modified moving peak benchmark (mMPB) to simulate the movement of waves. A new swarm intelligence algorithm for solving ROOT is designed using an adaptive gradient training predictor and a solver embedded the dingo optimisation algorithm. The ROOT results are compared with the tank test results, which confirms that the dynamic formation optimisation strategy has a high credibility. The energy-saving formation optimised by dynamic formation optimisation based on ROOT not only ensures the minimum energy consumption, but also ensures the minimum switching cost. The survival time of the spacing configuration is prolonged, indicating that the acquired energysaving formation can be consistently utilized over an extended period without necessitating positional adjustments. This mitigates the escalating energy consumption resulting from frequent formation switching when a fleet encounters dynamic marine conditions.

关键词： Dynamic formation optimisation Energy-saving formation Robust optimisation over time swarm intelligence algorithm Switching cost

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：