检索结果-内蒙古大学图书馆

Optimal threshold selection for segmentation of Chest X-Ray images using opposition-based swarm-inspired algorithm for diagnosis of pneumonia

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2024年第9期83卷 27089-27119页

作者： Khosla, Tejna Verma, Om Prakash Delhi Technol Univ Comp Sci Engn Dept Bawana Delhi India Delhi Technol Univ Elect & Commun Engn Dept Bawana Delhi India

Image Segmentation using thresholding is one of the most significant areas of image processing. However, the challenge lies in accurately and effectively segmenting medical images, which is a crucial step in many applications of medical image analysis. It necessitates the development of an effective and robust segmentation approach that can handle the complexity and diversity of medical images. To address this problem, we propose a novel image segmentation technique based on minimizing the cross-entropy function using a hybrid approach that combines the features of Opposition-Based Learning (OBL), Chameleon swarm algorithm (CSA), and particle swarm optimization algorithm (PSO). The opposition-based technique generates the initial population and improves convergence. Then, PSO and CSA are run in parallel on an unequal population set to improve the optimal results. The proposed approach, named the Opposition-based Chameleon swarm algorithm improved by particle swarm algorithm (CSAPSO), is evaluated on twelve Chest X-Ray (CXR) images of patients for the detection of Pneumonia. It is further tested on a large data set related to COVID-19. We conducted extensive comparisons with other state-of-the-art methods and the Deep Learning algorithms and used the performance indicators, namely Root Mean Square Error (RMSE), Peak Signal to Noise Ratio (PSNR) and Structure Similarity Index (SSIM), Classification Accuracy, Area Under Curve for evaluating the performance. The proposed approach is statically analyzed using the Friedman rank-sum test. Through the analysis, CSAPSO demonstrates better global optimal results compared to state-of-the-art techniques.

关键词： Chameleon swarm algorithm Cross entropy thresholding Medical imaging particle swarm optimization algorithm Pneumonia Segmentation

来源：评论

学校读者我要写书评

暂无评论

Improving Meteorological Drought Prediction in Tamil Nadu Through Weighted Dataset Construction and Multi-Objective optimization

引用

IEEE ACCESS 2024年 12卷 96878-96892页

作者： Sundararajan, Karpagam Srinivasan, Kathiravan Kaliappan, Jayakumar Vellore Inst Technol Sch Comp Sci Engn & Informat Syst Vellore 632014 India Vellore Inst Technol Sch Comp Sci & Engn Vellore 632014 India

Droughts typically develop gradually, and early prediction is crucial for the government to formulate effective mitigation plans. Our approach does not involve predicting specific drought index values. Instead, we forecast whether a particular year will experience drought. Insufficient investigation has been carried out regarding variations in additional climatic indicators like shortwave radiation, wind speed, sea level, and pollution in the context of droughts in the state of Tamil Nadu, India. In the study period taken from 1995 to 2020, only three years (2002, 2009, and 2017) experienced drought occurrences, resulting in an imbalanced dataset. To enhance the classification performance of this imbalanced dataset, a weighted dataset is constructed using a feature weighting approach known as the Single Objective Scorer (SOS) based Multi-objective PSO(MPSO) in conjunction with the Gradient Boosting Classifier. The proposed model facilitates objective-based multi-population formation and neighborhood learning. Precision and recall are crucial metrics, particularly in measuring imbalanced dataset classification performance. The application of multi-objective optimization techniques helps to strike a suitable balance between precision and recall. In addition to the Standardized Precipitation Index (SPI) and Standardized Precipitation Evapotranspiration Index (SPEI), 14 climatic indicators based on land, atmosphere, and sea are utilized. By employing the weighted dataset created with SOS-based MPSO, a significant improvement in recall value of 0.81 is achieved. Based on the weights assigned to the features, it is identified that the Mean Sea Level of the Arabian Sea and CO2 are significant indicators for predicting meteorological drought. The Explainable AI techniques SHAP and LIME are employed for interpreting the drought prediction model, providing insights into its workings.

关键词： Droughts optimization Atmospheric measurements Terrestrial atmosphere Sea level Ocean temperature Sea measurements particle swarm optimization Climate change Pollution measurement particle swarm optimization algorithm multi-population climatic indicators imbalanced dataset pollution mean sea level

来源：评论

学校读者我要写书评

暂无评论

Fast and accurate auto-disturbances-rejection temperature control system based on particle swarm optimized fuzzy control: Applied for particle three-dimensional (3D) printing prosthetic orthotic plate

引用

ADDITIVE MANUFACTURING 2025年 101卷

作者： Liu, Biaoqiang Qian, Bo Liang, Yuxin Dai, Peng Li, Ruidi Wei, Qingsong Shanghai Univ Engn Sci Sch Mech & Automot Engn Longteng Rd 333 Shanghai 201620 Peoples R China Cent South Univ State Key Lab Powder Met Changsha 410083 Peoples R China Huazhong Univ Sci & Technol Sch Mat Sci & Engn Luoyu Rd 1037 Wuhan 430074 Peoples R China

In traditional temperature control system of particle 3D printing extrusion device, it exists many issues such as slow response speed, large fluctuation, and poor anti-interference ability. The above issues cause the instability of the extruded PLA filament, affecting the mechanical properties and surface quality of the printed samples. Based on particle swarm optimization algorithm, this paper proposes a precise control method for temperature control system to iteratively optimize the quantization factor and proportion factor, finally it obtains the optimal weight factor. Compared with traditional PID control and fuzzy PID control, response speed has improved by 58.6 % and 40.0 % respectively, overshoot has reduced by 76 % and 35 % respectively, and steady-state time has shortened to 24 s. Comparison of experimental results: The tensile strength of the samples increases by 15.52 % and 7.47 % respectively, the bending strength increases by 17.93 % and 11.58 % respectively, and the internal pores are improved significantly. In summary, the method proposed in this paper can effectively solve the problems of the temperature control system for particle 3D printing, and improve the mechanical properties and surface quality of the samples. The printed prosthetic orthotic plate can well meet the fitness and comfort of the human body.

关键词： Accurate temperature control 3D printing particle swarm optimization algorithm Screw extrusion Analogue simulation

来源：评论

学校读者我要写书评

暂无评论

AN EXTENDED CONFORMABLE FRACTIONAL ORDER GREY PREDICTION MODEL OF PER CAPITA ELECTRICITY CONSUMPTION FOR DAILY LIFE IN CHINA

引用

THERMAL SCIENCE 2025年第1期29卷 477-487页

作者： Jiang, Jianming Ban, Yandong Youjiang Med Univ Nationalities Sch Publ Hlth & Management Baise Peoples R China

Conformable fractional-order grey prediction models have attracted considerable attention due to their versatile modeling techniques. However, existing models often suffer from limitations in adaptability. To address this, this study proposes a new extended conformable fractional-order grey prediction model, namely the ECFGM(1,1) model. By integrating an adaptive weighting coefficient into the conformable fractional-order accumulation process, the model can effectively prioritize new information, thereby enhancing its rationality and adaptability. Moreover, the adjusted process can be tailored to either emphasize new information or adhere to traditional accumulation methods, which improves its adaptability. To verify the effectiveness of the ECFGM(1,1) model, ECFGM(1,1) is applied to two examples from the literature. The model evaluation results show that the ECFGM(1,1) model has higher fitting accuracy and predictive accuracy than the GM(1,1), CFGM(1,1), and NIPGM(1,1) models. Using the constructed ECFGM(1,1) for predictive analysis of the per capita electricity consumption for daily life in China, the results show that this model can capture the laws of its changes over time. Finally, per capita electricity consumption for daily life in China from 2022 to 2026 is predicted. The results show that by 2026, such consumption is estimated to reach 1165.35 KWh.

关键词： fractional-order grey prediction model new information priority particle swarm optimization algorithm per capita electricity consumption for daily life

来源：评论

学校读者我要写书评

暂无评论

Lithium battery state of health estimation based on PSO-GWO algorithm optimization under chaotic mapping with hybrid kernel extreme learning machine model

引用

JOURNAL OF APPLIED ELECTROCHEMISTRY 2025年第6期55卷 1383-1398页

作者： Ding, Xvqiang Ni, Yiwei Zhu, Dandan Li, Zhiwei Jiao, Yunxiao Wang, Qi Nantong Inst Technol Sch Automot Engn Nantong 226001 Peoples R China Jiangsu Univ Sci & Technol Zhenjiang 212003 Peoples R China

In battery management systems, the health status of lithium batteries constantly affects the accurate estimation of their charging status and energy status, making the health status particularly important. However, in energy storage systems, rapidly and accurately estimating the health status of lithium batteries, as well as estimating it at an appropriate proportion, has always been a challenge. Therefore, to improve the stable operation of energy storage systems, this paper proposes a model that optimizes a hybrid kernel extreme learning machine using the circle mapping chaotic method and particle swarm optimization algorithm to improve the gray wolf algorithm. First, to address the issues of initialization instability and slow convergence speed in the gray wolf optimization algorithm, the ideas of circle mapping chaos and particle swarm optimization are proposed to replace the position update formula of the gray wolf optimization algorithm, thereby enhancing the algorithm's stability and convergence speed. Second, to address the limitation of the single learning capability of the kernel extreme learning machine model, a hybrid kernel extreme learning machine model is employed. The generalization and learning capabilities of the entire model are verified through simulation experiments. Finally, simulation predictions are conducted again under different data-splitting proportions to obtain an optimal training proportion, providing additional reference directions for practical application. Experimental results demonstrate that the proposed model maintains a fit above 0.99 for four sets of batteries, and ensures the reliability and reasonableness of the model when using a 50% training set proportion.

关键词： Lithium battery state of health Gray wolf optimization algorithm Hybrid kernel extreme learning machine particle swarm optimization algorithm Circle chaos mapping

来源：评论

学校读者我要写书评

暂无评论

Cloud-based estimation of lithium-ion battery life for electric vehicles using equivalent circuit model and recurrent neural network

引用

JOURNAL OF ENERGY STORAGE 2025年 114卷

作者： Chen, Ziqing Chen, Jianguo Zhu, Zhicheng Chen, Jian Lv, Taolin Qiao, Dongdong Zheng, Yuejiu Univ Shanghai Sci & Technol Coll Mech Engn Shanghai 200093 Peoples R China Shanghai Inst Space Power Sources State Key Lab Space Power Sources Shanghai 200245 Peoples R China

With the increasing adoption of electric vehicles, the limitations of BMS in terms of storage capacity and computational power lead to a gradual accumulation of errors in battery capacity estimation over time. This growing inaccuracy significantly compromises the effective management of on-board power battery states. The challenge of battery capacity estimation based on extensive cloud-stored data has become a key focus in current research. In this paper, we propose an enhanced method that combines the ECM with a RNN to address this issue. By incorporating the relationship between OCV and SOC into the ECM, and employing PSO for direct capacity identification, we achieve accurate estimation. Furthermore, the use of RNN dynamically adjusts the observation noise in Kalman filtering, significantly improving the precision of the estimation. Experimental results demonstrate that the proposed `method yields a RMSE of <3 % and an average relative error below 2 %, compared to traditional approaches. This study presents a high-precision, efficient solution for estimating battery capacity using cloud-based data from electric vehicles, offering substantial application value.

关键词： Electric vehicle cloud data Equivalent circuit model particle swarm optimization algorithm Recurrent neural network

来源：评论

学校读者我要写书评

暂无评论

Development and simulation of two novel indoor odor source localization methods using a modified shark smell optimization algorithm

引用

MEASUREMENT 2025年 240卷

作者： Lin, Qin Wu, Sihuan Wu, Sifan Wang, Hui Zhang, Jinxiu Sun Yat Sen Univ Sch Aeronaut & Astronaut Shenzhen Campus Shenzhen 518107 Peoples R China Southern Marine Sci & Engn Guangdong Lab Zhuhai 519085 Peoples R China

Aiming to solve the problem of odor source localization (OSL) in the presence of interference sources, this paper presents two methods based on swarm intelligence algorithms. We initially introduced the shark smell optimization (SSO) algorithm and modified it for OSL tasks. Subsequently, mechanisms for collective information sharing and preventing falling into local minima were incorporated, leading to the development of the Improved Shark Smell optimization (I-SSO) algorithm. We tested both algorithms in a computational fluid dynamics (CFD) simulated environment with a single interference source and compared them to the particle swarm optimization (PSO) algorithm and whale optimization algorithm (WOA). In scenarios with one and two interference sources. The results showed that the I-SSO algorithm outperformed the other three algorithms in both environment settings, demonstrating a higher success rate and superior search distance efficiency.

关键词： Odor source localization particle swarm optimization algorithm Shark smell optimization algorithm Whale optimization algorithm swarm intelligence

来源：评论

学校读者我要写书评

暂无评论

A simplified swarm optimization-based restricted Boltzmann machine algorithm for a time series clustering

引用

APPLIED SOFT COMPUTING 2025年 173卷

作者： Zulvia, Ferani E. Kuo, R. J. Inst Teknol Bandung Dept Ind Engn Jalan Ganesha 10 Bandung 40132 Indonesia Natl Taiwan Univ Sci & Technol Dept Ind Management 43Sect 4Kee Lung Rd Taipei 106 Taiwan

Time series clustering is an important area of research, driven by the prevalence of time series data in domains such as power and maintenance data. However, most existing clustering algorithms are not specialized for time series data. Therefore, this study introduces a metaheuristics-based approach, utilizing a restricted Boltzmann machine (RBM) for feature extraction in time series clustering. The RBM, a neural network algorithm with two layers and undirected weights, is kept simple to avoid complex parameter settings. The study employs the RBM as an encoder, coupled with a K-step contrastive divergence and an improved, simplified swarm optimization (iSSO) algorithm for training. The proposed hybrid of iSSO-based RBM and K-means algorithm is compared with RBM and particle swarm optimization-based RBM across the tested time series datasets. Results indicate that the proposed algorithm yields superior performance, reconstructing time series data with minimal error and achieving the highest clustering accuracy compared to other baseline algorithms.

关键词： Feature-based time series clustering Restricted Boltzmann machine Simplified swarm optimization algorithm particle swarm optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Thermodynamic performance prediction and optimization of a 1 kW ocean thermal energy cogeneration system based on artificial neural network

引用

ENERGY 2025年 314卷

作者： Zhang, Yuan Li, Yifan Tian, Zhen Yang, Chao Peng, Hao Kan, Ankang Gao, Wenzhong Shanghai Maritime Univ Coll Merchant Marine Shanghai 201306 Peoples R China Hainan Univ State Key Lab Marine Resource Utilizat South China Haikou 570228 Peoples R China

In this paper, a prediction model based on the artificial neural network (ANN) method was constructed, and the thermodynamic performance prediction and optimization were conducted for a system for ocean thermal energy conversion that integrates an air conditioning cycle (OTEC-AC). By employing the variable importance measure (VIM) method, ten key parameters were selected as input parameters, and three output parameters, including system power generation (Wele), cold energy efficiency (eta co), and energy efficiency (eta en) were defined. The accuracies of prediction models constructed by the back propagation neural network (BPNN) and BPNN optimized by the particle swarm optimization algorithm (BPNN-PSO) were compared. Analysis of the thermodynamic characteristics and multi-objective optimization of the system were performed, and performance differences between the experimental data-based and the BPNN-PSO model-based system were compared. Results showed that optimizing the initial weights and thresholds of the model using the PSO algorithm could enhance the model's generalization capability. Multi-objective optimal results based on prediction data were very close to those based on experimental data, with a maximum relative error of 4.4498 %. This study validates the feasibility of using the ANN model for data prediction in OTEC cogeneration systems, which could provide guidelines for the optimal design of related systems.

关键词： OTEC Air conditioning Artificial neural network particle swarm optimization algorithm Multi-objective optimization

来源：评论

学校读者我要写书评

暂无评论

Soil moisture retrieval using GNSS signal-to-noise ratio data based on an improved optimal arc selection method

引用

GPS SOLUTIONS 2025年第1期29卷 1-14页

作者： He, Jiaxing Zheng, Nanshan Ding, Rui Liu, Xuexi China Univ Min & Technol Sch Environm & Spatial Informat Xuzhou 221116 Peoples R China China Univ Min & Technol Key Lab Land Environm & Disaster Monitoring Minist Nat Resources Xuzhou 221116 Peoples R China

Global Navigation Satellite System-interferometric reflectometry (GNSS-IR) can be used to monitor soil moisture by establishing a relationship between phase and soil moisture. Therefore, the accuracy of the phase value is very important. However, topography and vegetation can introduce errors in the phase values when processing the raw signal-to-noise ratio reflection component (SRC). This study proposes an optimal arc selection (OAS) method to overcome this limitation. The novelty of this method is the use of entropy to evaluate the accuracy of curve fitting and the use of a particle swarm optimization algorithm to search for the optimal elevation range of SRC. We processed SNR data from 3 GNSS stations and provided the verification results through in-situ soil moisture measurements. The results showed that the phase values calculated using the OAS method were more accurate than those calculated using the conventional method. The new method improved the agreement between GNSS-derived soil moisture and in-situ measurements, with a reduction of 29% in root mean square error and 31% in mean absolute error. This suggests that the OAS method can improve the capacity of soil moisture retrieval in undulating terrain areas and promote the development of GNSS-IR.

关键词： GNSS-IR Soil moisture particle swarm optimization algorithm Entropy method

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：