检索结果-内蒙古大学图书馆

SI-EDTL: Swarm intelligence ensemble deep transfer learning for multiple vehicle detection in UAV images

CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE 2022年第5期34卷

作者： Darehnaei, Zeinab Ghasemi Shokouhifar, Mohammad Yazdanjouei, Hossein Fatemi, Seyed Mohammad Jalal Rastegar Islamic Azad Univ Coll Engn Dept Elect Engn Saveh Branch Saveh Iran Shahid Beheshti Univ Dept Elect & Comp Engn Tehran Iran Urmia Univ Microelect Res Lab Orumiyeh Iran

This article proposes a swarm intelligence ensemble deep transfer learning (named SI-EDTL) for multiple vehicle detection in unmanned aerial vehicle (UAV) images. This method is based on Faster regional-based convolutional neural networks (Faster R-CNN), in which, a set of region proposals are extracted using region proposal network (RPN), and then, CNN is used to mine highly descriptive features of these windows to classify regions. We use three Faster R-CNNs as feature extractors (InceptionV3, ResNet50, and GoogLeNet) that have already pre-trained on ImageNet data, combined with five transfer classifiers (KNN, SVM, MLP, C4.5 Decision Tree, and Naive Bayes). As a result, 15 different base learners are trained through deep transfer learning on a UAV dataset to classify the region proposals into multiple vehicles (car, van, truck, and bus). We combine these 15 base learners through a weighted averaging aggregation into four vehicle classes or no vehicle (background). Hyperparameters of the ensemble model are tuned using whale optimization algorithm, to achieve the best trade-off between total accuracy, precision, and recall. The proposed SI-EDTL model has been successfully developed using parallel processing in MATLAB R2020b. Experimental results on AU-AIR dataset of UAV images demonstrate the superiority of the SI-EDTL model against existing techniques.

关键词： deep transfer learning ensemble learning Faster R-CNN unmanned aerial vehicle vehicle detection whale optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Prediction of Remaining Useful Life of Lithium Batteries Based on WOA-VMD and LSTM

引用

ENERGIES 2022年第23期15卷 8918页

作者： Ouyang, Mingsan Shen, Peicheng Anhui Univ Sci & Technol Coll Elect & Informat Engn Huainan 232000 Peoples R China

The remaining useful life (RUL) of a lithium-ion battery is directly related to the safety and reliability of the electric system powered by a lithium-ion battery. Accurate prediction of RUL can ensure timely replacement and maintenance of the batteries of the power supply system, and avoid potential safety hazards in the lithium-ion battery power supply system. In order to solve the problem that the prediction accuracy of the RUL of lithium-ion batteries is reduced due to the local capacity recovery phenomenon in the process of the capacity degradation of lithium-ion batteries, a prediction model based on the combination of the whale optimization algorithm (WOA)-variational mode decomposition (VMD) and short-term memory neural network (LSTM) was proposed. First, WOA was used to optimize the VMD parameters, so that the WOA-VMD could fully decompose the capacity signal of the lithium-ion battery and separate the dual component with global attenuation trend and a series of fluctuating components representing the capacity recovery from the capacity signal of the lithium-ion battery. Then, LSTML was used to predict the dual component and fluctuation components, so that LSTM could avoid the interference of the capacity recovery to the prediction. Finally, the RUL prediction results were obtained by stacking and reconstructing the component prediction results. The experimental results show that WOA-VMD-LSTM can effectively improve the prediction accuracy of the RUL of lithium-ion batteries. The average cycle error was one cycle, the average RMSE was less than 0.69%, and the average MAPE was less than 0.43%.

关键词： lithium-ion battery remaining useful life whale optimization algorithm variational mode decomposition long short-term memory neural network

来源：评论

学校读者我要写书评

暂无评论

Research on multi-modal autonomous diagnosis algorithm of COVID-19 based on whale optimized support vector machine and improved D-S evidence fusion

引用

COMPUTERS IN BIOLOGY AND MEDICINE 2022年 150卷 106181-106181页

作者： Wang, Guowei Guo, Shuli Han, Lina Song, Xiaowei Zhao, Yuanyuan Beijing Inst Technol Sch Automat State Key Lab Intelligent Control & Decis Complex Beijing 100081 Peoples R China Chinese Peoples Liberat Army Gen Hosp Med Ctr 2 Natl Clin Res Ctr Geriatr Dis Dept Cardiol Beijing Peoples R China

Aiming at the problem that the single CT image signal feature recognition method in the self-diagnosis of diseases cannot accurately and reliably classify COVID-19, and it is easily confused with suspected cases. The collected CT signals and experimental indexes are extracted to construct different feature vectors. The support vector machine is optimized by the improved whale algorithm for the preliminary diagnosis of COVID-19, and the basic probability distribution function of each evidence is calculated by the posterior probability modeling method. Then the similarity measure is introduced to optimize the basic probability distribution function. Finally, the multi-domain feature fusion prediction model is established by using the weighted D-S evidence theory. The experimental results show that the fusion of multi-domain feature information by whale optimized support vector machine and improved D-S evidence theory can effectively improve the accuracy and the precision of COVID-19 autonomous diagnosis. The method of replacing a single feature parameter with multi-modal indicators (CT, routine laboratory indexes, serum cytokines and chemokines) provides a more reliable signal source for the diagnosis model, which can effectively distinguish COVID-19 from the suspected cases.

关键词： COVID-19 Multi-modal information Support vector machine D-S evidence theory whale optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Distribution parameter-determining method comparison for airborne wind energy potential assessment in the eastern coastal area of China

引用

SUSTAINABLE ENERGY TECHNOLOGIES AND ASSESSMENTS 2022年第PartB期52卷

作者： Wang, Jianzhou Li, Qiwei Ma, Xuejiao Lu, Haiyan Dongbei Univ Finance & Econ Sch Stat Dalian Peoples R China Dalian Univ Technol Sch Econ & Management Dalian Peoples R China Univ Technol Fac Engn & Informat Technol Sch Software Sydney NSW Australia

In recent years, airborne wind energy generation (AWEG) has increasingly been discussed as a better alternative to traditional wind turbine generation owing to less expensive raw materials, higher electricity capacity, and being more friendly to the surrounding environment. Thus, the planning of AWEG-based wind farms is necessary. To control the risk and ensure the future investment revenue to guarantee the ultimate success of this planning, airborne wind energy potential assessment (AWEPA) is essential;however, it has rarely been done so far. In this study, an AWEPA for the eastern coastal area of China was implemented. As wind speed distribution is an essential factor in AWEPA, to guarantee a reliable assessment, selecting a suitable distribution parameter determining method is critical. In this paper, two conventional numerical parameter-determining methods and three intelligent parameter-determining methods were compared, and the intelligent parameter-determining method embedding the whale optimization algorithm that showed outstanding performance in the comparison was finally selected to be used in the AWEPA. The assessment results show that developing AWEG in the study area is highly likely feasible, and the results also provide some other valuable information for planning.

关键词： Wind speed distribution whale optimization algorithm Flower pollination algorithm Genetic algorithm Parameter estimation

来源：评论

学校读者我要写书评

暂无评论

Swarm-based optimization as stochastic training strategy for estimation of reference evapotranspiration using extreme learning machine

引用

AGRICULTURAL WATER MANAGEMENT 2021年 243卷 106447-106447页

作者： Chia, Min Yan Huang, Yuk Feng Koo, Chai Hoon Univ Tunku Abdul Rahman Lee Kong Chian Fac Engn & Sci Dept Civil Engn Kampar Perak Malaysia

Reference evapotranspiration (ET0) is usually calculated as a pre-requisite to obtain the actual evapotranspiration (ET). Estimation of ET0 using extreme learning machine (ELM) is a new norm due to its excellent computation efficiency and its lower data dependency. However, the lack of stochastic tuning often results in the convergence to the local optima instead of the global optimum. This study attempts to address this issue by hybridizing the ELM with three swarm-based optimization algorithms, namely the particle swarm optimization (PSO), the moth-flame optimization (MFO) and the whale optimization algorithm (WOA) with different fitness functions. This study was conducted with three stations in Sabah and Sarawak (states in East Malaysia) as this region is to a very large extent covered with oil palm plantation. The water resources management is thus rather crucial for the area. The results showed that the WOA-ELM achieved a higher average rank score relative to the PSO-ELM and MFO-ELM, especially when the simple Taylor skill score was used as the fitness function. The application of different fitness functions did not show any significant effect. The reported standard deviations of the mean absolute error (MAE), root mean square error (RMSE) and coefficient of determination (R2) for the three variations of the hybridized ELM were close to 0;thus reflecting their similarity in accuracy. However, in terms of computational efficiency, the simple Taylor skill score exhibited better stability where it could effectively reduce the number of required hidden neurons when the input meteorological parameters were decreased. The WOA was suggested as the best optimization algorithm for this study. For the three stations, respectively it achieved an average MAE, RMSE and R-2 of 0.0007 to 0.1443, 0.0011 to 0.1927 and 1.0000 to 0.9486, from cases C1 to C6 with minimum time cost.

关键词： Extreme learning machine Reference evapotranspiration Particle swarm optimization Moth-flame optimization whale optimization algorithm Fitness function

来源：评论

学校读者我要写书评

暂无评论

optimization of support vector machine through the use of metaheuristic algorithms in forecasting TBM advance rate

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2021年 97卷 104015-104015页

作者： Zhou, Jian Qiu, Yingui Zhu, Shuangli Armaghani, Danial Jahed Li, Chuanqi Hoang Nguyen Yagiz, Saffet Cent South Univ Sch Resources & Safety Engn Changsha 410083 Peoples R China Duy Tan Univ Inst Res & Dev Da Nang 550000 Vietnam Hanoi Univ Min & Geol Min Fac Dept Surface Min 18 Vien St Hanoi Vietnam Hanoi Univ Min & Geol Ctr Min Electromech Res 18 Vien St Hanoi Vietnam Nazarbayev Univ Sch Min & Geosci Nur Sultan City 010000 Kazakhstan

The advance rate (AR) of a tunnel boring machine (TBM) in hard rock condition is a key parameter for the successful accomplishment of a tunneling project, and the proper and reliable prediction of this parameter can lead to minimizing the risks associated to high capital costs and scheduling for such projects. This research aims at optimizing the hyper-parameters of the support vector machine (SVM) technique through the use of three optimization algorithms, namely, gray wolf optimization (GWO), whale optimization algorithm (WOA) and moth flame optimization (MFO), in forecasting TBM AR. In fact, the role of these optimization techniques is to optimize the hyperparameters 'C' and 'gamma' of the SVM model to get higher performance prediction. To develop the hybrid SVM-based models, 1,286 sample sets of data collected from a water transfer tunnel in Malaysia comprising seven input variables, i.e., rock mass rating, uniaxial compressive strength, Brazilian tensile strength, rock quality designation, weathering zone, thrust force and revolution per minute, and one output variable, i.e., TBM AR, were considered and used. Several GWO-SVM, WOA-SVM and MFO-SVM models were constructed to predict TBM AR considering their effective parameters. The accuracy levels of the proposed models were assessed using four statistical indices, i.e., the coefficient of determination (R-2), root mean squared error (RMSE), mean absolute error (MAE), and variance accounted for (VAF). Modeling results revealed that the MFO algorithm can capture better hyper-parameters of the SVM model in predicting TBM AR among all three hybrid models. R-2 of (0.9623 and 0.9724), RMSE of (0.1269 and 0.1155), and VAF of (96.24 and 97.34%), respectively, for training and test stages of the MFO-SVM model confirmed that this hybrid SVM model is a powerful and applicable technique addressing problems related to TBM performance with a high level of accuracy.

关键词： TBM performance Support vector machine whale optimization algorithm Gray wolf optimization Moth flame optimization

来源：评论

学校读者我要写书评

暂无评论

A new meta-heuristic task scheduling algorithm for optimizing energy efficiency in data centers 19

A new meta-heuristic task scheduling algorithm for optimizin...

引用

19th IEEE International Symposium on Parallel and Distributed Processing with Applications (IEEE ISPA)

作者： Zhang, Shikui Chi, Ce Ji, Kaixuan Liu, Zhiyong Zhang, Fa Song, Penglei Yuan, Huimei Qiu, Dehui Wan, Xiaohua Capital Normal Univ Informat Engn Coll Beijing Peoples R China Chinese Acad Sci High Performance Comp Ctr Inst Comp Technol Beijing Peoples R China Univ Chinese Acad Sci Beijing Peoples R China

ISBN: (纸本)9781665435741

Data center, as an important infrastructure of cloud computing, is experiencing rapid growth in both quantity and scale, which causes the high energy consumption and severe environmental problems restricting the development of data centers. Task scheduling can significantly improve the energy efficiency in cloud computing and alleviate the constrain of the high stress on environment. But efficient task scheduling in heterogeneous cloud environment is rather challenging because of the dynamic and complicated environment of data centers. In this paper, we propose a new meta-heuristic task scheduling algorithm called WACOA combining the whale optimization algorithm with the ant colony algorithm, which uses pheromones to collect part excellent solutions from historical information to schedule tasks. Experiments show that WACOA is superior to the whale optimization algorithm and ant colony algorithm. WACOA can reduce energy consumption and improve the performance on task scheduling.

关键词： Data center energy consumption Independent task scheduling whale optimization algorithm Ant colony algorithm Multi-objective optimization

来源：评论

学校读者我要写书评

暂无评论

Feature subset selection for predicting the success of crowdfunding project campaigns

引用

ELECTRONIC MARKETS 2021年第3期31卷 671-684页

作者： Ryoba, Michael J. Qu, Shaojian Zhou, Yongyi Univ Shanghai Sci & Technol Sch Business Shanghai Peoples R China

Statistics from crowdfunding platforms show that a small percent of crowdfunding projects succeed in securing funds. This makes project creators eager to know the probability of success of their campaign and the features that contribute to its success before launching it on crowdfunding platforms. The existing literature focuses on examining success probability using the entire list of identified projects features. For situations for which project creators have limited resources to invest on the required project features, the list suggested by previous researchers is somewhat large and gives a small success probability. A minimal number of features that predict success with a higher probability can benefit project creators by providing them with insight and guidance in investing their limited resources. This paper presents a metaheuristic whale optimization algorithm (WOA) in the crowdfunding context to perform a complete search of a subset of features that have a high success contribution power. Experiments were conducted using WOA with the K-Nearest Neighbor (KNN) classifier on a Kickstarter dataset. Our approach obtains a subset of 9 features that predict the success of project campaigns with an accuracy (F-score) of 90.28% (90.11%), which is an increase (F-score) of 22.23% (21.61%) than when a complete set of features is used. The findings of this study contribute knowledge to various crowdfunding stakeholders, as they will provide new insights regarding a subset of essential features th4at influence the success of project campaigns with high accuracy.

关键词： Crowdfunding Crowdfunding prediction Machine learning Feature selection whale optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Non-linear static and dynamic buckling analysis of laminated composite cylindrical shell embedded in non-linear elastic foundation using the swarm-based metaheuristic algorithms

引用

EUROPEAN JOURNAL OF MECHANICS A-SOLIDS 2022年 91卷 1页

作者： Foroutan, Kamran Varedi-Koulaei, Seyyed Mojtaba Duc, Nguyen Dinh Ahmadi, Habib Shahrood Univ Technol Fac Mech & Mechatron Engn Shahrood Iran Hanoi Univ Engn & Technol UET Vietnam Natl Univ Dept Technol & Engn Construct & Transportat Hanoi Vietnam Nguyen Tat Thanh Univ NTT Inst High Technol Dist 4 Ho Chi Minh City Vietnam Sejong Univ Dept Civil & Environm Engn Natl Res Lab 209 Neungdong Ro Seoul 05006 South Korea

In this paper, by determining the optimal fiber's angles for maximum critical buckling load, the non-linear static and dynamic buckling analyses of laminated composite cylindrical shells resting on non-linear elastic foundation subjected to external loading are investigated. The laminated composite cylindrical with three, four, and five layers is considered. In the present study, first, the optimal fiber's angles are found using the swarm-based metaheuristic algorithms, then, the non-linear static and dynamic buckling analyses are carried out at optimum fiber directions. According to classical shell theory, von-Karman equation, and Hooke's law, the stressstrain relations are derived for the laminated composite cylindrical shell. Then, based on the Galerkin's method, the discretized motion equation is obtained. For the optimization problem, the design variables are ply angles, and the objective function is maximizing the critical buckling load. Four recently developed swarm-based metaheuristic algorithms including, grey wolf optimizer (GWO), whale optimization algorithm (WOA), grasshopper optimization algorithm (GOA), and salp swarm algorithm (SSA), are utilized to solve these optimization problems. Based on the results, the optimization algorithms have improved the value of the critical buckling load significantly. Also, the WOA algorithm had better results than the others, while the GOA was the weakest.

关键词： Laminated composite cylindrical shell Non-linear elastic foundation Grey wolf optimizer whale optimization algorithm Grasshopper optimization algorithm Salp swarm algorithm Non-linear static and dynamic buckling

来源：评论

学校读者我要写书评

暂无评论

Evolutionary inspired approach for mental stress detection using EEG signal

引用

EXPERT SYSTEMS WITH APPLICATIONS 2022年第0期197卷 116634-116634页

作者： Sharma, Lakhan Dev Bohat, Vijay Kumar Habib, Maria Al-Zoubi, Ala' M. Faris, Hossam Aljarah, Ibrahim VIT AP Univ Sch Elect Engn Amaravati India Netaji Subhas Univ Technol Dept Comp Sci & Engn Delhi India Altibbi Amman Jordan Univ Jordan Informat Technol Dept Amman Jordan Univ Granada Sch Sci Technol & Engn Granada Spain Al Hussein Tech Univ Sch Comp & Informat Amman Jordan Univ Granada Univ Granada CITIC UGR Res Ctr Informat & Commun Technol Granada Spain

Stress is a pensive issue in our competitive world and it has a huge impact on physical and mental health. Severe health issues may arise due to long exposure of stress. Hence, its timed detection can be helpful in managing stress periods. In this regard, electroencephalogram (EEG) based techniques have been widely explored, as stress severely impact the functioning and structure of brain. These non-invasive methods for stress detection need improvement in terms of predictive accuracy and reliability. In this work, a novel approach for stress detection has been presented using short duration of EEG signal. Entropy based features were extracted from EEG signal decomposed using stationary wavelet transform. Selected features were used for classification using different supervised machine learning algorithms. Further, different evolutionary inspired approaches were deployed to optimize the parameters of support vector machines (SVM) and perform feature weighting, simultaneously. SVM optimized using whale optimization algorithm resulted in an accuracy of 97.2559%. Accurate detection using short duration EEG signal shows potential of this technique for timed and reliable detection of stress.

关键词： Mental stress Electroencephalogram Stationary wavelet transform Evolutionary inspired whale optimization algorithm Support vector machine

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：