检索结果-内蒙古大学图书馆

Research on English speech recognition system and training enhancement based on bat algorithm and acoustic model inspection

引用

SOFT COMPUTING 2023年 1-9页

作者： Yang, Xi Li, Ling Chengdu Univ Off Int Cooperat & Exchange Chengdu 610106 Sichuan Peoples R China Chengdu Univ Sch Foreign Languages & Cultures Chengdu 610106 Sichuan Peoples R China

Because of its own language characteristics, English has become the main language tool for communication among countries in the world under the global economic environment, and China is no exception. However, due to the constraints of the traditional education model, the English level of the population in China is generally low. The design and optimization of the English speech recognition system are a complex process that involves the integration of various technical components. In this paper, the main technical components of the system design are speech recognition and bat algorithm, which can complete the acquisition, training, and strengthening of target speech. The system will complete noise data elimination, acoustic model detection and recognition model construction, text training model, etc., during speech model training;the system will implement voice input detection, target feature extraction and matching, voice semantic recognition, etc., respectively, during speech recognition and acquisition. Experiments are designed to test the performance of the system. The results show that the recognition rate of the system is high, reaching 90%, but the initial vocabulary is negatively correlated with the recognition rate. In general, the system design meets the target requirements and can better complete the identification task. The use of English speech recognition system can enable learners to have a more perfect oral learning environment, give full play to the role of language interaction, and improve their learning effectiveness and enthusiasm. In this paper, the bat algorithm is introduced into the field of English speech recognition to develop an effective recognition system.

关键词： bat algorithm English teaching Speech recognition System design

来源：评论

学校读者我要写书评

暂无评论

Multi-objective task scheduling in cloud computing environment by hybridized bat algorithm

引用

JOURNAL OF INTELLIGENT & FUZZY SYSTEMS 2022年第1期42卷 411-423页

作者： Bezdan, Timea Zivkovic, Miodrag Bacanin, Nebojsa Strumberger, Ivana Tuba, Eva Tuba, Milan Singidunum Univ Danijelova 32 Belgrade 11000 Serbia

Cloud computing represents relatively new paradigm of utilizing remote computing resources and is becoming increasingly important and popular technology, that supports on-demand (as needed) resource provisioning and releasing in almost real-time. Task scheduling has a crucial role in cloud computing and it represents one of the most challenging issues from this domain. Therefore, to establish more efficient resource employment, an effective and robust task allocation (scheduling) method is required. By using an efficient task scheduling algorithm, the overall performance and service quality, as well as end-users experience can be improved. As the number of tasks increases, the problem complexity rises as well, which results in a huge search space. This kind of problem belongs to the class of NP-hard optimization challenges. The objective of this paper is to propose an approach that is able to find approximate (near-optimal) solution for multi-objective task scheduling problem in cloud environment, and at the same time to reduce the search time. In the proposed manuscript, we present a swarm-intelligence based approach, the hybridized bat algorithm, for multi-objective task scheduling. We conducted experiments on the CloudSim toolkit using standard parallel workloads and synthetic workloads. The obtained results are compared to other similar, metaheuristic-based techniques that were evaluated under the same conditions. Simulation results prove great potential of our proposed approach in this domain.

关键词： Cloud computing task scheduling multi-objective optimization bat algorithm hybridization

来源：评论

学校读者我要写书评

暂无评论

Optimal design of passive power filters based on multi-objective bat algorithm and pareto front

引用

APPLIED SOFT COMPUTING 2015年 35卷 257-266页

作者： Yang, Nien-Che Le, Minh-Duy Yuan Ze Univ Dept Elect Engn Taoyuan 32003 Taiwan Yuan Ze Univ Innovat Ctr Big Data & Digital Convergence Taoyuan 32003 Taiwan

This paper proposes an optimal design method for passive power filters (PPFs) in order to suppress critical harmonics and improve power factor. The characteristics of common passive filters, such as single-tuned, second-order, third-order, and C-type damped filters are introduced. In addition, several objective functions and constraints for PPF design problems are constructed. A new multi-objective optimization based on the modified bat algorithm and Pareto front is developed for solving PPF design problems. A case study is also presented to demonstrate the efficiency and superiority of the proposed method. (C) 2015 Elsevier B.V. All rights reserved.

关键词： bat algorithm External archive Multi-objective optimization Non-dominated solutions Passive power filters

来源：评论

学校读者我要写书评

暂无评论

Optimization design of magnetic gear integrated PMSG using improved bat algorithm for wave energy conversion

引用

INTERNATIONAL JOURNAL OF APPLIED ELECTROMAGNETICS AND MECHANICS 2021年第3期66卷 525-542页

作者： Fang, Hong Wei Wang, Yu Tianjin Univ Sch Elect & Informat Engn Tianjin 300072 Peoples R China

The magnetic gear integrated permanent magnet synchronous generator (MG-PMSG) can reduce the acoustic noise and mechanical loss, which are caused by the mechanical gear box. It also has the merits of increasing efficiency and reducing system volume when it is used for wave energy conversion system. In this paper, an improved bat algorithm (BA) based on velocity weighting factor is proposed. The improved BA is applied for the optimization design of permanent magnet (PM) to reduce the cogging torque of MG-PMSG. The numerical model is constructed by response surface methodology (RSM). The influences of key pole shape parameters on cogging torque were investigated, including the eccentric distance, the pole-arc coefficient and the permanent magnet thickness. A global optimization design is then carried out by using the improved BA, so that the magnet dimensions corresponding to the optimal cogging torque are obtained. Finally, the performances of the MG-PMSG with the optimized permanent magnet are analyzed by finite element method. Results show that cogging torque, steady torque ripple and back electromotive force (EMF) waveform distortion of the optimized MG-PMSG are reduced.

关键词： Magnetic gear wave energy conversion cogging torque bat algorithm response surface methodology

来源：评论

学校读者我要写书评

暂无评论

Global chaotic bat algorithm for feature selection

引用

JOURNAL OF SUPERCOMPUTING 2022年第17期78卷 18754-18776页

作者： Li, Ying Cui, Xueting Fan, Jiahao Wang, Tan Jilin Univ Coll Comp Sci & Technol Changchun Peoples R China Jilin Univ Key Lab Symbol Computat & Knowledge Engn Minist Educ Changchun Peoples R China Jilin Univ Northeast Asian Res Ctr Changchun Peoples R China

The wrapper algorithm adopts the performance of the learning algorithm as the evaluation criteria to obtain excellent classification performance. However, the wrapper algorithm is prone to converge prematurely. A global chaotic bat algorithm (GCBA) is put up forward to improve this shortage. First, GCBA applies chaotic map to population initialization to cover the entire solution space. In addition, adaptive learning factors are presented to balance exploration and exploration. The learning factor of local optimal position gradually decreases in the early stage while the learning factor of global optimal position gradually increases in the later stage. Finally, to improve the exploitation, an improved transfer function is proposed, which transfers the continuous space to discrete binary space. GCBA is tested on 14 UCI data sets and 5 gene expression data sets compared with other 6 comparison algorithms. Compared with other algorithms, the results show that GCBA is able to achieve better classification performance.

关键词： Feature selection Wrapper feature selection algorithm bat algorithm Classification Chaotic map

来源：评论

学校读者我要写书评

暂无评论

Modeling and Optimizing the Composite Prepreg Tape Winding Process Based on Grey Relational Analysis Coupled with BP Neural Network and bat algorithm

引用

NANOSCALE RESEARCH LETTERS 2019年第1期14卷 296页

作者： Deng, Bo Shi, Yaoyao Northwestern Polytech Univ Key Lab Contemporary Design & Integrated Mfg Tech Minist Educ Xian 710072 Shaanxi Peoples R China

As a significant way to manufacture revolving body composite, the composite prepreg tape winding technology is widely applied to the domain of aerospace motor manufacture. Processing parameters, including heating temperature, tape tension, roller pressure, and winding velocity, have considerable effects on the void content and tensile strength of winding products. This paper was devoted to studying the influence of process parameters on the performances of winding products including both void content and tensile strength and trying to provide the optimal parameters combination for the objectives of lower void content and higher tensile strength. In the experiments, tensile strength and void content were selected as the mechanical property and physical performance of winding products to be tested, respectively. An integrated approach by uniting the Grey relational analysis, backpropagation neural network, and bat algorithm was presented to search the optimal technology parameters for composite tape winding process. Then, the composite tape winding process model was provided by backpropagation neural network utilizing the results of Grey relational analysis. According to the bat algorithm, the optimal parameter combination was heating temperature with 73.8 degrees C, tape tension with 291.2N, roller pressure with 1804.1N, and winding velocity with 9.1rpm. The value of tensile strength increased from 1215.31 to 1329.62MPa. Meanwhile, the value of void content decreased from 0.15 to 0.137%. At last, the developed method was verified to be useful for optimizing the composite tape winding process.

关键词： Composite tape winding process Tensile strength Void content Backpropagation neural network bat algorithm

来源：评论

学校读者我要写书评

暂无评论

A Novel Data Fusion Strategy Based on Extreme Learning Machine Optimized by bat algorithm for Mobile Heterogeneous Wireless Sensor Networks

引用

IEEE ACCESS 2020年 8卷 16057-16072页

作者： Cao, Li Cai, Yong Yue, Yinggao Cai, Shaotang Hang, Bo Southwest Univ Sci & Technol Sch Informat Engn Mianyang 621010 Sichuan Peoples R China Hubei Univ Arts & Sci Comp Sch Xiangyang 441053 Peoples R China Tianjin Univ Elect Automat & Informat Engn Sch Tianjin 300072 Peoples R China

In order to effectively reduce the redundant information transmission in the network, a data fusion algorithm based on extreme learning machine optimized by bat algorithm for mobile heterogeneous wireless sensor networks is proposed. In this paper, the data fusion process of mobile heterogeneous wireless sensor networks is mainly studied, and regards the nodes of wireless sensor networks as neurons in the neural network of extreme learning machines. The neural network of the extreme learning machine extracts the sensory data collected by mobile heterogeneous wireless sensor network and combines the collected sensor data with the clustering route to greatly reduce the amount of network data sent to the sink node. Aiming at the problem that the extreme learning machine randomly generates the input layer weight and the hidden layer threshold before training, the output result is unstable, affecting the data fusion efficiency and the long delay, a new method of data fusion for mobile heterogeneous wireless sensor networks based on extreme learning machine optimized by bat algorithm is proposed. Simulation experiments are carried out from two aspects: mobile heterogeneous wireless sensor networks and heterogeneous mobile heterogeneous wireless sensor networks. The simulation results show that compared with the traditional SEP algorithm, BP neural network algorithm and ELM algorithm, the proposed bat-ELM-based data fusion algorithm can effectively reduce network traffic, save network energy, improve network work efficiency, and significantly prolong network & x2019;s lifetime.

关键词： Mobile heterogeneous wireless sensor networks data fusion extreme learning machine bat algorithm energy efficient reliability

来源：评论

学校读者我要写书评

暂无评论

Improved Directional bat algorithm Based Electric Power Dispatch

引用

ELECTRIC POWER COMPONENTS AND SYSTEMS 2021年第19-20期48卷 2089-2105页

作者： Singh, Diljinder Dhillon, Jaspreet Singh St Longowal Inst Engn & Technol Sangrur Punjab India

No single metaheuristic search algorithm can be adjudged universally best general-purpose optimizer. The performance of search algorithms mainly depends upon the weightage assigned to global and local search strategies. This paper proposed an improved directional bat optimizer to minimize the operating cost of the electric power dispatch (EPD) problem that establishes a balance between global and local search strategies. Improved directional bat algorithm exploits directional echolocation bat behavior, directional exploration, neighborhood search and opposition based learning for generation jumping. The directional bat algorithm acts as a global search tool whereas exploration in each direction and neighborhood search performs local search. Opposition learning improves convergence with diversity. An effect of valve-point loading introduces a discontinuity in cost characteristics. The EPD problem addresses energy balance, generator capacity, ramp-rate limits and prohibited operating zones (POZ) avoidance constraints. An iterative technique handles energy balance constraint. The generation is adjusted to avoid the violation of generation capacity, ramp-rate limit and POZ constraints. The proposed algorithm is verified on various electric power systems. The results verify that the proposed algorithm is a potential algorithm to solve EPD problems as it competes with recent existing algorithms undertaken for comparison

关键词： economic power dispatch directional echolocation bat algorithm exploration opposition-based learning local search

来源：评论

学校读者我要写书评

暂无评论

A novel compound wind speed forecasting model based on the back propagation neural network optimized by bat algorithm

引用

ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH 2020年第7期27卷 7353-7365页

作者： Cui, Yanbin Huang, Chenchen Cui, Yanping North China Elect Power Univ Dept Mech Engn Baoding 071000 Peoples R China North China Elect Power Univ Dept Econ Management Baoding 071000 Peoples R China Univ Victoria Victoria BC Canada

Wind power, a clean and renewable resource, is regarded as one of the most promising and economical resources during the transformation from fossil fuels to new energy resources. Thus, the accuracy of wind speed forecasting work is very important to integrate the wind resource into electrical power system on a large scale. To improve the short-term wind speed forecasting accuracy, a novel compound model is introduced in this paper. For the proposed model, the fast ensemble empirical mode decomposition method was employed to do the data preprocessing. After the data preprocessing, phase space reconstruction was used for choosing each sub-series' input and output vectors for the forecasting model dynamically. Then, the bat algorithm was applied to optimize the connection weights and thresholds of the traditional back propagation neural network. The forecasting results can be obtained through the aggregation of sequential prediction. The performance evaluation of this proposed model indicates that it can capture the nonlinear characteristics of the wind speed signal efficiently. The proposed model shows better performance when being compared with the parallel models.

关键词： Wind speed forecasting Fast ensemble empirical mode decomposition Phase space reconstruction bat algorithm Back propagation neural network

来源：评论

学校读者我要写书评

暂无评论

Make robots be bats: specializing robotic swarms to the bat algorithm

引用

SWARM AND EVOLUTIONARY COMPUTATION 2019年 44卷 113-129页

作者： Suarez, Patricia Iglesias, Andres Galvez, Akemi Univ Cantabria ETSI Caminos Canales & Puertos Dept Appl Math & Computat Sci Avda Castros S-N E-39005 Santander Spain Toho Univ Fac Sci Dept Informat Sci 2-2-1 Miyama Funabashi Chiba 2748510 Japan

bat algorithm is a powerful nature-inspired swarm intelligence method proposed by Prof. Xin-She Yang in 2010, with remarkable applications in industrial and scientific domains However, to the best of authors' knowledge, this algorithm has never been applied so far in the context of swarm robotics. With the aim to fill this gap, this paper introduces the first practical implementation of the bat algorithm in swarm robotics. Our implementation is performed at two levels: a physical level, where we design and build a real robotic prototype;and a computational level, where we develop a robotic simulation framework. A very important feature of our implementation is its high specialization: all (physical and logical) components are fully optimized to replicate the most relevant features of the real microbats and the bat algorithm as faithfully as possible. Our implementation has been tested by its application to the problem of finding a target location within unknown static indoor 3D environments. Our experimental results show that the behavioral patterns observed in the real and the simulated robotic swarms are very similar. This makes our robotic swarm implementation an ideal tool to explore the potential and limitations of the bat algorithm for real-world practical applications and their computer simulations.

关键词： Swarm computation Swarm robotics bat algorithm Unknown target location Behavioral patterns

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：