检索结果-内蒙古大学图书馆

Improved whale optimization algorithm for feature selection in Arabic sentiment analysis

APPLIED INTELLIGENCE 2019年第5期49卷 1688-1707页

作者： Tubishat, Mohammad Abushariah, Mohammad A. M. Idris, Norisma Aljarah, Ibrahim Univ Malaya Dept Artificial Intelligence Fac Comp Sci & Informat Technol Kuala Lumpur 50603 Malaysia Univ Jordan Comp Informat Syst Dept King Abdullah II Sch Informat Technol Amman Jordan Univ Jordan Business Informat Technol Dept King Abdullah II Sch Informat Technol Amman Jordan

To help individuals or companies make a systematic and more accurate decisions, sentiment analysis (SA) is used to evaluate the polarity of reviews. In SA, feature selection phase is an important phase for machine learning classifiers specifically when the datasets used in training is huge. whale optimization algorithm (WOA) is one of the recent metaheuristic optimization algorithm that mimics the whale hunting mechanism. However, WOA suffers from the same problem faced by many other optimization algorithms and tend to fall in local optima. To overcome these problems, two improvements for WOA algorithm are proposed in this paper. The first improvement includes using Elite Opposition-Based Learning (EOBL) at initialization phase of WOA. The second improvement involves the incorporation of evolutionary operators from Differential Evolution algorithm at the end of each WOA iteration including mutation, crossover, and selection operators. In addition, we also used Information Gain (IG) as a filter features selection technique with WOA using Support Vector Machine (SVM) classifier to reduce the search space explored by WOA. To verify our proposed approach, four Arabic benchmark datasets for sentiment analysis are used since there are only a few studies in sentiment analysis conducted for Arabic language as compared to English. The proposed algorithm is compared with six well-known optimization algorithms and two deep learning algorithms. The comprehensive experiments results show that the proposed algorithm outperforms all other algorithms in terms of sentiment analysis classification accuracy through finding the best solutions, while its also minimizes the number of selected features.

关键词： Arabic sentiment analysis Support vector machine Information gain whale optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Fine-tuning of neural computing using whale optimization algorithm for predicting compressive strength of concrete

引用

ENGINEERING WITH COMPUTERS 2021年第1期37卷 701-712页

作者： Tien Bui, Dieu Abdullahi, Mu'azu Mohammed Ghareh, Soheil Moayedi, Hossein Nguyen, Hoang Duy Tan Univ Inst Res & Dev Da Nang 550000 Vietnam Univ Hafr Al Batin Coll Engn Civil Engn Dept Al Jamiah 39524 Eastern Provinc Saudi Arabia Payam Noor Univ Dept Civil Engn Tehran Iran Ton Duc Thang Univ Dept Management Sci & Technol Dev Ho Chi Minh City Vietnam Ton Duc Thang Univ Fac Civil Engn Ho Chi Minh City Vietnam Hanoi Univ Min Land Geol Dept Surface Min 18 Vien StDuc Thang Ward Hanoi Vietnam Hanoi Univ Min & Geol Ctr Min Electromech Res 18 Vien StDuc Thang Ward Hanoi Vietnam

Due to the important role of concrete in construction sector, a novel metaheuristic method, namely whale optimization algorithm (WOA), is employed for simulating 28-day compressive strength of concrete (CSC). To this end, the WOA is coupled with a neural network (NN) to optimize its computational parameters. Also, dragonfly algorithm (DA) and ant colony optimization (ACO) techniques are considered as the benchmark methods. The CSC influential parameters are cement, slag, water, fly ash, superplasticizer (SP), fine aggregate (FA), and coarse aggregate (CA). First, a population-based sensitivity analysis is carried out to achieve the most efficient structure of the proposed model. In this sense, the WOA-NN with the population size of 400 and five hidden nodes constructed the best-fitted network. The results revealed that the WOA-NN (Error = 2.0746 and Correlation = 0.8976) presents the most reliable prediction of the CSC, followed by the DA-NN (Error = 2.5138 and Correlation = 0.8209) and ACO-NN (Error = 2.8843 and Correlation = 0.8000) benchmark models. The findings showed that utilizing the WOA optimization technique, along with typical neural network, results in developing a promising tool for modeling the CSC.

关键词： Neural computing whale optimization algorithm WOA-NN Compressive strength

来源：评论

学校读者我要写书评

暂无评论

A novel hybrid firefly-whale optimization algorithm and its application to optimization of MPC parameters

引用

SOFT COMPUTING 2022年第4期26卷 1845-1872页

作者： Cimen, Murat Erhan Yalcin, Yaprak Sakarya Univ Appl Sci Dept Elect & Elect Engn Serdivan Sakarya Turkey Istanbul Tech Univ Dept Control & Automat Engn Istanbul Turkey

In this paper, a novel optimization algorithm is proposed by hybridizing firefly and whale optimization algorithms and it is applied to the problem of determining optimal design parameters of model predictive control. The developed hybrid algorithm is compared with firefly and whale optimization algorithms considering unimodal, multimodal, composite and CEC-C06 2019 benchmark optimization problems in terms of statistical analysis. Comparison results showed that hybrid algorithm has the best performance for approximately 67% of 39 benchmark functions in finding the minimum in an average of independent 100 experiments for each function. For the functions in which the proposed algorithm gives the best results, approximately 64% improvement is achieved compared to FA and 39% improvement compared to WOA. In terms of convergence speed, in average 2% of improvement is obtained. As an application to engineering problems, optimization of parameters of the model predictive control for inverted pendulum and distillation column is considered and the performance of the proposed algorithm is compared with the performances of firefly algorithm and whale optimization algorithm. For the considered applications, a novel objective function is selected. The selected objective function for hybrid firefly-whale optimization algorithm enables finding the optimal prediction horizon and control horizon as well as the Q and R matrices such that the system responses satisfy desired settling time and maximum overshoot criteria. Most of considered comparisons demonstrate that the proposed hybrid algorithm has better performance.

关键词： Firefly algorithm whale optimization algorithm Hybrid metaheuristic algorithm Model predictive control

来源：评论

学校读者我要写书评

暂无评论

Energy cost optimization in distribution network considering hybrid electric vehicle and photovoltaic using modified whale optimization algorithm

引用

JOURNAL OF SUPERCOMPUTING 2023年第13期79卷 14427-14456页

作者： Zadehbagheri, Mahmoud Abbasi, Ali Reza Islamic Azad Univ Dept Elect Engn Yasuj Branch Yasuj Iran Univ Fasa Dept Elect Engn Fasa Fars Iran

The economic emission dispatch problem is one of the most crucial problems for the future smart power network. The integration of renewable energy resources and the use of electric vehicles (EVs) are various techniques that have been suggested to deal with the increase in greenhouse gas emissions. However, to carefully examine various scenarios of integration of the above elements is important to reduce emission rates while considering economic constraints. In this research, the effectiveness of the use of photovoltaics (PVs) and EVs' discharging/charging behavior is investigated from various perspectives in a hybrid economic emission dispatch. Here, a multi-objective model includes the optimization of two objectives: cost and pollution is suggested. Based on a penalty factor, we convert the multi-objective function into a single objective. For solving this non-convex, nonlinear and on-smooth problem, a modified whale optimization algorithm (WOA) is exerted to gain the optimum results. The idea of two sub-modifications is derived from Levy flight algorithm and the mutation operator of the genetic algorithm. The verification of the suggested model is performed by the IEEE 30-bus system with 6-units. The simulated results illustrate that the incorporation of PV along with EVs in economic dispatch problem can improve the pollution emission, the economic costs, and convergence rate, effectively.

关键词： Economic dispatch Electricity distribution network Hybrid electric vehicle Cost reduction Pollution reduction whale optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Pipeline damage identification based on an optimized back-propagation neural network improved by whale optimization algorithm

引用

APPLIED INTELLIGENCE 2023年第10期53卷 12937-12954页

作者： Wu, Lei Mei, Jiangtao Zhao, Shuo China Univ Petr Sch Petr Engn Qingdao 266580 Peoples R China China Univ Petr Natl Engn Res Ctr Offshore Geophys & Explorat Equ Qingdao 266580 Peoples R China Nanyang Technol Univ Maritime Inst NTU Sch Civil & Environm Engn Singapore 639798 Singapore China Univ Petr Coll Mech & Elect Engn Qingdao 266580 Peoples R China

With the advantages of high economy and large transportation capacity, pipeline transportation is commonly used in industrial production. Pipeline damage induced by various factors will result in changes of physical properties, further leading to changes of dynamic parameters such as natural frequency and vibration mode. Recently, as a new type of tool, artificial intelligence is widely used for pipeline damage identification. In this study, to promote the accuracy of pipeline damage identification, a novel method that employs the artificial neural network (ANN) and swarm intelligence algorithm is proposed. In detail, based on the original whale optimization algorithm (WOA), an improved WOA (IWOA) is presented in which an adaptive coefficient strategy and a stochastic optimal substitution strategy are introduced. Then, the IWOA and back-propagation neural network (BPNN) are hybridized into IWOA-BPNN. Subsequently, a damage location detector and a damage degree detector are established based on the proposed IWOA-BPNN. By taking a pipeline fixed at both ends and its curvature and displacement modes, the proposed damage identification method is verified to confirm its effectiveness and accuracy in different damage states. Experimental results demonstrate that the comprehensive performance of IWOA-BPNN is better than other compared models. The relative error of the predicted results obtained by IWOA-BPNN is less than 2.2% when evaluating the damage location and degree for 12 randomly selected test samples, indicating the superiority of the proposed method. The proposed method has broad application prospects in modern industries.

关键词： Pipeline damage identification Back-propagation neural network whale optimization algorithm Damage location and degree

来源：评论

学校读者我要写书评

暂无评论

Color difference classification of solid color printing and dyeing products based on optimization of the extreme learning machine of the improved whale optimization algorithm

引用

TEXTILE RESEARCH JOURNAL 2020年第2期90卷 135-155页

作者： Zhou, Zhiyu Wang, Chao Zhang, Jianxin Zhu, Zefei Zhejiang Sci Tech Univ Sch Informat Sci & Technol Xiasha Hang Zhou Zhejiang Peoples R China Zhejiang Sci Tech Univ Res Ctr Modern Text Machinery Technol Minist Educ Xiasha Hang Zhou Zhejiang Peoples R China Hangzhou Dianzi Univ Sch Mech Engn Hangzhou Peoples R China

To mitigate the problem of low classification accuracy in solid color printing and dyeing, a color difference classification model based on the differential evolution (DE) improved whale optimization algorithm (WOA) for extreme learning machine (ELM) optimization, named the DE-WOA-ELM, was developed in this study. Considering that the initial population of the WOA has a significant influence on the solution speed and quality, DE was used to generate a more suitable initial population for the WOA by avoiding local optima, thereby improving the performance. The method used an excellent global search ability to improve the WOA for optimization and obtained an optimal parameter combination for the ELM. Thus, the problem of randomly initializing the input weight and the hidden layer bias of the ELM, which leads to a nonuniform training model and unstable algorithm, was solved. Finally, by optimizing the input weight and hidden layer bias, the color difference classification model of the ELM with a strong generalization ability was constructed. The results of the color difference classification experiments on fabric images collected under standard light sources show that the average classification accuracy for the dataset is increased by 2.15%, 11.06%, 12.11%, and 0.47% compared with those of the ELM, support vector machine, back propagation neural network, and kernel ELM, respectively.

关键词： color difference classification differential evolution extreme learning machine whale optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

A new improved whale optimization algorithm with joint search mechanisms for high-dimensional global optimization problems

引用

ENGINEERING WITH COMPUTERS 2021年第3期37卷 1851-1878页

作者： Fan, Qian Chen, Zhenjian Li, Zhao Xia, Zhanghua Yu, Jiayong Wang, Dongzheng Fuzhou Univ Coll Civil Engn Fuzhou 350116 Peoples R China Hong Kong Polytech Univ Dept Land Surveying & Geoinformat Kowloon Hong Kong 999077 Peoples R China Hunan Univ Coll Civil Engn Changsha 410082 Hunan Peoples R China

Similar to other swarm-based algorithms, the recently developed whale optimization algorithm (WOA) has the problems of low accuracy and slow convergence. It is also easy to fall into local optimum. Moreover, WOA and its variants cannot perform well enough in solving high-dimensional optimization problems. This paper puts forward a new improved WOA with joint search mechanisms called JSWOA for solving the above disadvantages. First, the improved algorithm uses tent chaotic map to maintain the diversity of the initial population for global search. Second, a new adaptive inertia weight is given to improve the convergence accuracy and speed, together with jump out from local optimum. Finally, to enhance the quality and diversity of the whale population, as well as increase the probability of obtaining global optimal solution, opposition-based learning mechanism is used to update the individuals of the whale population continuously during each iteration process. The performance of the proposed JSWOA is tested by twenty-three benchmark functions of various types and dimensions. Then, the results are compared with the basic WOA, several variants of WOA and other swarm-based intelligent algorithms. The experimental results show that the proposed JSWOA algorithm with multi-mechanisms is superior to WOA and the other state-of-the-art algorithms in the competition, exhibiting remarkable advantages in the solution accuracy and convergence speed. It is also suitable for dealing with high-dimensional global optimization problems.

关键词： whale optimization algorithm Tent chaotic map Adaptive inertia weight Opposition-based learning High-dimensional optimization problems

来源：评论

学校读者我要写书评

暂无评论

Locating and Sizing Method of Electric Vehicle Charging Station Based on Improved whale optimization algorithm (vol 8, pg 4386, 2022)

引用

ENERGY REPORTS 2022年 8卷 10816-10817页

作者： Cheng, Junchao Xu, Jindi Chen, Wentao Song, Beibei Shanghai Dianji Univ Business Sch Pudong New Area 300 Shuihua Rd Shanghai 201306 Peoples R China

An Improved whale optimization algorithm (IWOA) is proposed to solve the problem of poor accuracy and stability in optimizing the locating and sizing of nonconvex and nonlinear electric vehicle (EV) charging stations (CSs). The variability index of convergence factor, the differential evolution operator, and the antibody affinity are introduced in the algorithm framework. Twelve classical test functions show that IWOA significantly improves the algorithm accuracy and convergence speed compared to WOA. Finally. The Voronoi diagram based on Floyd’s shortest path is adopted to decide the service area of charging stations. With the goal of delivering cost optimization, IWOA is applied to a 45-node transportation network for case study analysis, and the results show that both the proposed model and algorithm can be effectively applied to the locating and sizing and help reduce the cost for the whole society.

关键词： whale optimization algorithm Electric vehicle Locating and sizing Differential Evolution Artificial immune algorithm Convergence factor

来源：评论

学校读者我要写书评

暂无评论

An Author Gender Detection Method Using whale optimization algorithm and Artificial Neural Network

引用

IEEE ACCESS 2020年 8卷 48428-48437页

作者： Safara, Fatemeh Mohammed, Amin Salih Potrus, Moayad Yousif Ali, Saqib Quan Thanh Tho Souri, Alireza Janenia, Fereshteh Hosseinzadeh, Mehdi Islamic Azad Univ Islamshahr Branch Dept Comp Engn Islamshahr *** Iran Lebanese French Univ Dept Comp Engn Erbil 44001 Iraq Salahaddin Univ Erbil Dept Software & Informat Engn Erbil 44001 Iraq Sultan Qaboos Univ Dept Informat Syst Coll Econ & Polit Sci Muscat 123 Oman Vietnam Natl Univ Ho Chi Minh City Univ Technol Dept Software Engn Ho Chi Minh City 76000 Vietnam Islamic Azad Univ Dept Comp Engn Sci & Res Branch Tehran *** Iran Duy Tan Univ Inst Res & Dev Da Nang 550000 Vietnam Duy Tan Univ Fac Elect Elect Engn Da Nang 550000 Vietnam Iran Univ Med Sci Hlth Management & Econ Res Ctr Tehran *** Iran

Author gender detection (AGD) is a serious and crucial issue in Internet security applications, in particular in email, messenger, and social network communications. Detecting the gender of communication partner helps preventing massive fraud and abuses happening through social media such as email, blogs, forums. Text and writings of people on the Internet have valuable information that can be used to identify the gender of an author. Machine learning and meta-heuristic algorithms are valuable techniques to extract hidden patterns useful for detecting gender of a text. In this paper, an artificial neural network (ANN) is employed as a classifier to detect the gender of an email author and the whale optimization algorithm (WOA) is used to find optimal weights and biases for improving the accuracy of the ANN classification. Through this combination of ANN and WOA an accuracy of 98 & x0025;, precision of 97.16 & x0025;, and recall of 99.67 & x0025;were achieved, which indicates the superiority of the proposed method on Bayesian networks, regression, decision tree, support vector machine, and ANN examined.

关键词： Author gender detection machine learning artificial neural network whale optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Accuracy control of contactless laser sensor system using whale optimization algorithm and moth-flame optimization

引用

TM-TECHNISCHES MESSEN 2017年第11期84卷 734-746页

作者： Pathak, Vimal Kumar Singh, Amit Kumar Malaviya Natl Inst Technol Dept Mech Engn JLN Marg Jaipur 302017 Rajasthan India Manipal Univ Jaipur Sch Mech Engn Jaipur 303007 Rajasthan India

This paper predict the effect of the object's morphology on the final accuracy of the scanned data, for the case of contactless laser scanning. On the basis of the scanned objects morphology, two important process parameters are specified namely scanning angle and distance of the laser from the part surface. Experiments have been performed with different scanning conditions using full factorial design. An analytical prediction model for determining the standard deviation of the final surface is developed in terms of the aforesaid scanning parameters using response surface methodology (RSM). Furthermore, the optimal scanning parameters are predicted after comparing two almost unexplored nature inspired algorithms i.e. whale optimization algorithm(WOA) andMoth-Flame optimization (MFO). Finally, two realistic non-trivial case studies are considered for validation of the proposed methodology. The result shows that the standard deviation of the final reverse engineered models significantly reduced by 21.6% and 13.77%. The adopted methodology provides the optimal combination of morphological scanning process parameters with a considerable reduction in standard deviation for final scanned surface models.

关键词： Contactless laser scanning accuracy control whale optimization algorithm moth-flame 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：