检索结果-内蒙古大学图书馆

A survey on dynamic populations in bio-inspired algorithms

GENETIC PROGRAMMING AND EVOLVABLE MACHINES 2024年第2期25卷 19-19页

作者： Farinati, Davide Vanneschi, Leonardo Univ Nova Lisboa NOVA Informat Management Sch NOVA IMS Campus Campolide P-1070312 Lisbon Portugal

Population-Based bio-inspired algorithms (PBBIAs) are computational methods that simulate natural biological processes, such as evolution or social behaviors, to solve optimization problems. Traditionally, PBBIAs use a population of static size, set beforehand through a specific parameter. Nevertheless, for several decades now, the idea of employing populations of dynamic size, capable of adjusting during the course of a single run, has gained ground. Various methods have been introduced, ranging from simpler ones that use a predefined function to determine the population size variation, to more sophisticated methods where the population size in different phases of the evolutionary process depends on the dynamics of the evolution itself and events occurring within the population during the run. The common underlying idea in many of these approaches, is similar: to save a significant amount of computational effort in phases where the evolution is functioning well, and therefore a large population is not needed. This allows for reusing the previously saved computational effort when optimization becomes more challenging, and hence a greater computational effort is required. Numerous past contributions have demonstrated a notable advantage of using dynamically sized populations, often resulting in comparable results to those obtained by the standard PBBIAs but with a significant saving of computational effort. However, despite the numerous successes that have been presented, to date, there is still no comprehensive collection of past contributions on the use of dynamic populations that allows for their categorization and critical analysis. This article aims to bridge this gap by presenting a systematic literature review regarding the use of dynamic populations in PBBIAs, as well as identifying gaps in the research that can lead the path to future works.

关键词： Population-based algorithms bio-inspired algorithms Population size Dynamic population Adaptive population

来源：评论

学校读者我要写书评

暂无评论

Comparison of three different bio-inspired algorithms to improve ability of neuro fuzzy approach in prediction of agricultural drought, based on three different indexes

引用

COMPUTERS AND ELECTRONICS IN AGRICULTURE 2020年 170卷 105279-105279页

作者： Aghelpour, Pouya Bahrami-Pichaghchi, Hadigheh Kisi, Ozgur Univ Tehran Coll Agr & Nat Resources Fac Agr Engn & Technol Dept Irrigat & Reclamat EngnAgr Meteorol Karaj Iran Sari Agr Sci & Nat Resources Univ Fac Agr Engn Dept Water Engn Sari Iran Ilia State Univ Sch Technol Tbilisi Georgia

Monitoring agricultural drought utilizing the least variables can be useful at the areas with just rain gauge stations, especially in Iran, which is located in arid belt of the world. In this study, all of the stations having long duration data in Iran (31 stations with more than 59 years' data), have been used to calculate three drought indices: (1) Palmer Drought Severity Index (PDSI);(2) Standardized Precipitation Index (SPI);(3) Multivariate Standardized Precipitation Index (MSPI). According to the recommendation of world meteorological organization (WMO), Palmer index has been defined as the reference index and SPI9 (9-month time window of SPI), SPI10, SPI11 & SPI12, and also MSPI9-12 (9-12 months' time window), was evaluated by Palmer index. The results showed significant relation between SPI11 or SPI12 and PDSI in Iran's climates. MSPI9-12 has a significant relation with PDSI too, and the correlation of MSPI with Palmer Index was found to be stronger than the SPI, in all stations. The relation between MSPI and PDSI is also stronger in extra-arid climates, and weaker in humid and per-humid areas. So, MSPI can be used for agricultural drought monitoring in the places where there are restrictions in meteorological dataset (when precipitation data are only available). In the second part, prediction of MSPI9-12 has been done using Adaptive Neuro-Fuzzy Inference System (ANFIS) merged with bio-inspired optimization algorithms. The meta-heuristic models implemented are ANFIS-ACO (ANFIS merged with Ant Colony Optimization), ANFIS-GA (ANFIS merged with Genetic Algorithm) and ANFIS-PSO (ANFIS merged with Particle Swarm Optimization). The models had their best predictions in arid, semi-arid and Mediterranean climates while humid climate provided the weakest predictions. Among the mentioned algorithms, the ACO and GA had the best performances to optimize ANFIS;they improved the ANFIS's accuracy by 45.9% and 43.2%, respectively.

关键词： Agricultural drought MSPI SPI PDSI bio-inspired algorithms

来源：评论

学校读者我要写书评

暂无评论

Sunagoke Moss Water Content Sensing Using Machine Vision-Texture Analysis and bio-inspired algorithms-

引用

IFAC Proceedings Volumes 2010年第26期43卷 268-273页

作者： Yusuf Hendrawan Haruhiko Murase Osaka Prefecture University Graduate School of Life and Environmental Sciences Department of Applied Life Sciences 1-1 Gakuen-cho Sakai 5998531 Osaka Japan

One of the primary determinants of Sunagoke moss Rachomitrium japonicum growth is water availability. Too much water or too little water can cause water stress in plants. Non-destructive sensing (machine vision using texture analysis) was developed for sensing water content of Sunagoke moss to realize automation and precision irrigation to stabilize the water content at optimum condition. The goal of this study is to propose and investigate bio-inspired algorithms i.e. Neural-Genetic algorithms (N-GAs) and Neural-Ant Colony optimization (N-ACO) to find the most significant set of textural image features suitable for predicting cultured Sunagoke moss water content in a close bio-production system. Textural features consisted of 90 textural features included grey level co-occurrence matrix, RGB, HSV and HSL colour co-occurrence matrix textural features. Nonlinear relationships between textural features and water content were identified by Back-Propagation Neural Network (BPNN). The lowest average prediction Mean Square Error (MSE) based on average testing-set data was 4.79×10- 3 when using HSL co-occurrence matrix textural features as the input of BPNN. Based on testing-set data, N-ACO had better performance for predicting Sunagoke moss water content than N-GAs with the average testing-set MSE of 1.43×10 −3 .

关键词： bio-inspired algorithms feature selection machine vision texture analysis water content sensing

来源：评论

学校读者我要写书评

暂无评论

Recommendation system using bio-inspired algorithms for urban orchards

引用

INTERNET OF THINGS 2024年 26卷

作者： Nunez, Juan M., V Corchado, Juan M. Giraldo, Diana M. Rodriguez-Gonzalez, Sara De la Prieta, Fernando Univ Salamanca BISITE Res Grp Edificio Multiusos I D I Salamanca 37007 Spain Univ Autonoma Occidente Calle 25 115-85 Cali 760001 Valle Del Cauca Colombia

According to the Food and Agriculture Organization of the United Nations (FAO), climate change is exponentially affecting agricultural production worldwide, with food prices expected to increase by up to 90 percent by 2030 and hunger and malnutrition rates to rise by 2050. This paper presents the development of a platform based on the Internet of Things (IoT) for monitoring urban gardens as a strategy to mitigate hunger, promote food sovereignty and circular economy in areas of food shortage. To this end, an Internet of Things (IoT) architecture is proposed and implemented that involves a social design layer that allows an effective transfer of knowledge to communities and a recommendation system based on evolutionary computation to optimize and maximize the productivity of urban orchards, and thus contribute to the 2030 agenda of the Sustainable Development Goals (SDGs). Finally, three experiments in urban gardens are shown to validate evolutionary computation and artificial intelligence models, such as multiple linear regression, genetic algorithms, ant colony algorithms and spatial estimation and inference algorithms such as the Kriging algorithm. The productivity of urban lettuce orchards is increased between 25 and 45%.

关键词： Internet of Things bio-inspired algorithms Urban orchards Lettuce crops Social design

来源：评论

学校读者我要写书评

暂无评论

Enhancing spatial prediction of groundwater-prone areas through optimization of a boosting algorithm with bio-inspired metaheuristic algorithms

引用

APPLIED WATER SCIENCE 2024年第11期14卷 1-25页

作者： Razavi-Termeh, Seyed Vahid Sadeghi-Niaraki, Abolghasem Abba, Sani I. Ali, Farman Choi, Soo-Mi Sejong Univ XR Res Ctr Dept Comp Sci & Engn & Convergence Engn Intelligen Seoul South Korea Prince Mohammad Bin Fahd Univ Dept Civil Engn Al Khobar Saudi Arabia Sungkyunkwan Univ Coll Comp & Informat Sch Convergence Dept Comp Sci & Engn Seoul 03063 South Korea

Groundwater resources are essential for ensuring a consistent water supply in many regions. Groundwater potential maps (GPMs) can be utilized in many ways to estimate the quantity, quality, and distribution of subsurface water, supporting the decision-making processes of numerous stakeholders. This study contributes to improving the accuracy of GPMs, focusing on implementing Geospatial Artificial Intelligence (GeoAI) models. For this purpose, the accuracy performance of the Extreme Gradient Boosting (XGBoost) algorithm is improved in this study. To do this, two such popular metaheuristic algorithms, i.e., invasive weed optimization (IWO) and biogeography-based optimization (BBO), are integrated into the XGBoost algorithm for modeling and spatial prediction of the areas prone to groundwater. Three models-XGBoost, XGBoost-IWO, and XGBoost-BBO-are implemented within the Python programming environments to execute spatial modeling and generate predictive maps. The evaluation of results unfolds in two stages: model validation and GPM validation. For the training data, the root mean square error (RMSE) and mean absolute error (MAE) indices were 0.165 and 0.121 for XGBoost, 0.13 and 0.087 for XGBoost-IWO, and 0.114 and 0.082 for XGBoost-BBO, respectively. The test data showed similar trends, with XGBoost yielding RMSE and MAE values of 0.424 and 0.295, XGBoost-IWO at 0.416 and 0.287, and XGBoost-BBO at 0.39 and 0.28. XGBoost-BBO, XGBoost-IWO, and XGBoost had a prediction accuracy higher than other models. The respective area under the curve (AUC) of GMPs using receiver operating characteristic (ROC) curves for XGBoost, XGBoost-IWO, and XGBoost-BBO were 81.8 %, 83.1 %, and 83.7 %. Using bio-inspired metaheuristic algorithms, the GPM accuracy rate has improved further. The study of groundwater resources demonstrated how geological feature extraction by GeoAI may help employ advanced techniques.

关键词： Groundwater resource Spatial prediction Geospatial artificial intelligence (GeoAI) bio-inspired algorithms Water scarcity

来源：评论

学校读者我要写书评

暂无评论

Comparative study of bio-inspired optimization algorithms and their application to dielectric function fitting

引用

JOURNAL OF ELECTROMAGNETIC WAVES AND APPLICATIONS 2016年第14期30卷 1885-1894页

作者： Liu, D. Michalski, K. A. Southwest Jiaotong Univ Sch Elect Engn Chengdu Peoples R China Texas A&M Univ Dept Elect & Comp Engn College Stn TX USA

A comparative study is presented for the latest bio-inspired optimization algorithms, known as bacterial foraging, firefly, cuckoo search, krill herd, and cuttlefish algorithms. This study also included the more established genetic and particle swarm optimization methods. These algorithms are then applied to a partial-fraction model fitting of tabulated measured dielectric function data for noble metals at optical wavelengths.

关键词： Optimization bio-inspired algorithms dielectric function complex curve fitting

来源：评论

学校读者我要写书评

暂无评论

bio-inspired optimization algorithms for parameter determination of three-phase induction motor

引用

COMPEL-THE INTERNATIONAL JOURNAL FOR COMPUTATION AND MATHEMATICS IN ELECTRICAL AND ELECTRONIC ENGINEERING 2012年第2期31卷 528-551页

作者： Sakthivel, V. P. Subramanian, S. Annamalai Univ Dept Elect Engn Annamalainagar 608002 Tamil Nadu India

Purpose - The aim of this research paper is to examine the bio-inspired optimization algorithms, namely, genetic algorithm (GA), particle swarm optimization (PSO) and bacterial foraging optimization (BFO) algorithm with adaptive chemotactic step for determining the steady-state equivalent circuit parameters of the three-phase induction motor using a set of manufacturer data. Design/methodology/approach - The induction motor parameter determination issue is devised as a nonlinear constrained optimization problem. The nonlinear equations of various quantities (torque, current and power factor) are derived in terms of equivalent circuit parameters from a single and a double-cage model, and then, equates to the corresponding manufacturer data. These equations are solved by the bio-inspired algorithms. Using the squared error between the determined and the manufacturer data as the objective function, the parameter determination problem is transferred into an optimization process where the model parameters are determined that minimize the defined objective function. The objective function is iteratively minimized using GA, PSO and BFO techniques. In order to balance the exploration and exploitation searches of the BFO algorithm, an adaptive chemotactic step is utilized. Findings - Comparisons of the results of GA, PSO, BFO and IEEE Std. 112-F (using no-load, locked-rotor and stator resistance tests) methods for two sample motors are presented. Results show the superiority of the bio-inspired optimization algorithms over the classical one. Besides, BFO-based parameter determination method is observed to obtain better quality solutions quickly than GA and PSO methods. Practical implications - The parameters obtained by the proposed approaches can be used in analyzing the stalling and/or reacceleration process of a loaded motor following a fault or during voltage sag condition as well as in system-level studies. Originality/value - The most significant contribution of the re

关键词： Parameter determination Induction motor bio-inspired algorithms Sensitivity analysis Genetic algorithms Circuits

来源：评论

学校读者我要写书评

暂无评论

Detecting Spam Email With Machine Learning Optimized With bio-inspired Metaheuristic algorithms

引用

IEEE ACCESS 2020年 8卷 187914-187932页

作者： Gibson, Simran Issac, Biju Zhang, Li Jacob, Seibu Mary Northumbria Univ Dept Comp & Informat Sci Newcastle Upon Tyne NE1 8ST Tyne & Wear England Teesside Univ Sch Comp Engn & Digital Technol Middlesbrough TS1 3BX Cleveland England

Electronic mail has eased communication methods for many organisations as well as individuals. This method is exploited for fraudulent gain by spammers through sending unsolicited emails. This article aims to present a method for detection of spam emails with machine learning algorithms that are optimized with bio-inspired methods. A literature review is carried to explore the efficient methods applied on different datasets to achieve good results. An extensive research was done to implement machine learning models using Naive Bayes, Support Vector Machine, Random Forest, Decision Tree and Multi-Layer Perceptron on seven different email datasets, along with feature extraction and pre-processing. The bio-inspired algorithms like Particle Swarm Optimization and Genetic Algorithm were implemented to optimize the performance of classifiers. Multinomial Naive Bayes with Genetic Algorithm performed the best overall. The comparison of our results with other machine learning and bio-inspired models to show the best suitable model is also discussed.

关键词： Machine learning bio-inspired algorithms cross-validation particle swarm optimization genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

Optimal allocation of capacitor banks in radial distribution systems for minimization of real power loss and maximization of network savings using bio-inspired optimization algorithms

引用

INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS 2015年 69卷 441-455页

作者： Injeti, Satish Kumar Thunuguntla, Vinod Kumar Shareef, Meera Sir CR Reddy Coll Engn Dept Elect & Elect Engn West Godavari 534007 Andhra Pradesh India

In this paper, two new algorithms are implemented to solve optimal placement of capacitors in radial distribution systems in two ways that is, optimal placement of fixed size of capacitor banks (Variable Locations Fixed Capacitor banks-VLFQ) and optimal sizing and placement of capacitors (Variable Locations Variable sizing of Capacitors-VLVQ) for real power loss minimization and network savings maximization. The two bio-inspired algorithms Bat Algorithm (BA) and Cuckoo Search (CS): search for all possible locations in the system along with the different sizes of capacitors, in which the optimal sizes of capacitor are chosen to be standard sizes that are available in the market. To check the feasibility, the proposed algorithms are applied on standard 34 and 85 bus radial distribution systems. And the results are compared with results of other methods like Particle Swarm Optimization (PSO), Harmonic Search (HS), Genetic Algorithm (GA), Artificial Bee Colony (ABC), Teaching Learning Based Optimization (TLBO) and Plant Growth Simulation Algorithm (PGSA), as available in the literature. The proposed approaches are capable of producing high-quality solutions with good performance of convergence. The entire simulation has been developed in MATLAB R2010a software. (C) 2015 Elsevier Ltd. All rights reserved.

关键词： bio-inspired algorithms Capacitor banks Real power loss minimization Network savings maximization Radial distribution systems

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of bio-inspired Optimization algorithms in Neural Network-Based Data Mining Classification

引用

INTERNATIONAL JOURNAL OF SWARM INTELLIGENCE RESEARCH 2022年第1期13卷 1-25页

作者： Murugan, Mathi T. Baburaj, Eppipanious Sathyabama Inst Sci & Technol Chennai Tamil Nadu India Marian Engn Coll Dept Comp Sci & Engn Trivandrum Kerala India

It always helps to determine optimal solutions for stochastic problems thereby maintaining good balance between its key elements. Nature-inspired algorithms are meta-heuristics that mimic the natural activities for solving optimization issues in the era of computation. In the past decades, several research works have been presented for optimization especially in the field of data mining. This paper addresses the implementation of bio-inspired optimization techniques for machine learning-based data mining classification by four different optimization algorithms. The stochastic problems are overcome by training the neural network model with techniques such as barnacles mating, black widow optimization, cuckoo algorithm, and elephant herd optimization. The experiments are performed on five different datasets, and the outcomes are compared with existing methods with respect to runtime, mean square error, and classification rate. From the experimental analysis, the proposed bio-inspired optimization algorithms are found to be effective for classification with neural network training.

关键词： bio-inspired algorithms Classification Data Mining Neural Networks Optimization

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：