检索结果-内蒙古大学图书馆

10th International Conference on Advanced Computing (ICoAC)

作者： Sreedharan, Sujiya Eswaran, Chandra Bharathiar Univ Dept Comp Sci Coimbatore Tamil Nadu India

ISBN: (纸本)9781728103532

Speaker verification technology rely on various speaker voice oriented characteristics to discriminate between speakers. Various features like short-term features, temporal features, and long-term features are the importance features used to verify an individual based on the physiological and behavioral characteristics. Various algorithms are available for extracting speaker specific attributes where in recent literature point of view Mel-frequency Cepstral coefficients (MFCC) are most frequently used acoustic features for verifying a speaker accurately based on the characteristics of the vocal track derivatives. Though the verification process is done accurately computation complexity and feature redundancy is the major problem in a speaker verification system. optimization algorithm is the state-of-art used to reduce feature sets which permit supplementary robust estimates of the model parameters. Also, less computational resources are achieved by using optimal feature selection to overcome time complexity load and redundancy of features during recognition process. In the proposed system Mel-Frequency Cepstral Coefficient (MFCC) are used to extract features and the extracted features are passed on to the optimization algorithm for feature section and finally the computed optimized features are given to GMM classifier for classification. In this article four optimization algorithm like Ant Colony optimization (ACO), Particle Swarm optimization (PSO), Genetic algorithm (GA), Firefly algorithm (FA) and Grey Wolf algorithm (GWA) are tested and evaluated for finding the best optimization algorithm for improving the performance of Speaker Verification with reduced feature size and reduced complexity.

关键词： Speaker Verification Feature Extraction Feature Selection optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Optimal estimation of initial concentrations and emission sources with 4D-Var for air pollution prediction in a 2D transport model

引用

SCIENCE OF THE TOTAL ENVIRONMENT 2021年 773卷 145580-145580页

作者： Liu, Caili Zhang, Shaoqing Gao, Yang Wang, Yuhang Sheng, Lifang Gao, Huiwang Fung, J. C. H. Ocean Univ China Coll Ocean & Atmospher Sci Qingdao Peoples R China Ocean Univ China MOE Inst Adv Ocean StudyKey Lab Phys Oceanog Frontiers Sci Ctr Deep Ocean Multispheres & Earth Qingdao Peoples R China Pilot Natl Lab Marine Sci & Technol QNLM Ocean Dynam & Climate Funct Lab Qingdao Peoples R China Int Lab High Resolut Earth Syst Model & Predict i Qingdao Peoples R China Ocean Univ China Minist Educ Key Lab Marine Environm & Ecol Qingdao 266100 Peoples R China Ocean Univ China Minist Educ Frontiers Sci Ctr Deep Ocean Multispheres & Earth Qingdao 266100 Peoples R China Georgia Inst Technol Sch Earth & Atmospher Sci Atlanta GA 30332 USA Hong Kong Univ Sci & Technol Div Environm & Sustainabil Hong Kong Peoples R China

Attributing sources of air pollution events by deploying an efficient observational network is an important and interesting problem in air quality control and forecast studies, but it is very challenging. In order to estimate the sensitivities of pollution events to emission sources, a comprehensive framework is built based on a horizontal 2-dimensional transport model and its adjoint in solving this problem. In an analysis of an idealized air pollution event of PM2.5 over the region of North China, an objective function is defined to optimally estimate the initial concentrations and emission sources through a series of minimization procedures. Results by means of the 4-dimensional variational approach show that, with the optimal initial conditions and emission sources, the model can successfully forecast the pollution event in a few days. The optimal observing network based on sensitivity analysis takes only one third of the cost but greatly retains predictability skill compared to the full-grid observing system, while nearly no predictability skill is detectable if the same number of observational sites is randomly deployed. We evaluate air pollution predictability in the point of focusing on to what degree the root mean square errors between the modeled concentration and the targeted air pollution are limited by the optimal observational network. Results show that air pollution predictability in association with the optimal observational network is limited in the time scales about 6 days. With the high efficiency and in an economic fashion, such a sensitivity-based optimal observing system holds promise for accurately predicting an air pollution event in the targeted area once the adjoint and variational procedure of a realistic atmosphere model including transport and chemical processes is performed. (C) 2021 Elsevier B.V. All rights reserved.

关键词： Transport model Optimal observational network Adjoint sensitivity Air pollution prediction optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

A robust voltage and current controller of parallel inverters in smart island: A novel approach

引用

ENERGY 2021年 214卷 118879-118879页

作者： Dehghani, Moslem Kavousi-Fard, Abdollah Niknam, Taher Avatefipour, Omid Shiraz Univ Technol Dept Elect & Elect Engn Shiraz Iran Univ Michigan Dept Elect & Comp Engn Dearborn MI 48128 USA

Smart Island (SI) refers to the condition where distributed generation (DG) units e.g. wind turbines (WT), fuel cell (FC), and photovoltaic cells (PV) have to control current, voltage, and frequency of the grid by themselves without any support from the main grid. Therefore, design and implementation of robust controller to overcome disturbances and load variations is very crucial. This paper presents a new approach using General Type-II Fuzzy controller to control smart island in combination with a novel modified optimization algorithm to increase the load sharing throughout the DGs operating in an islanding mode. This case study assumes that there are two DGs in the smart island where each DG has its own responsibilities. In particular, one of the DGs regulates the frequency and voltage based on a reference feedback, while the other DG operates in load current control mode to share load between each DG properly. The simulation results indicate that the suggested controller has a quick response to load alternations with a low steady state error and low THD. Moreover, the proposed controller is independent from system states and other units. The experimental analysis indicate that the suggested control system is effectively capable to coordinate the operations of the DG units in smart island to validate the stable operation of the overall smart island. (C) 2020 Elsevier Ltd. All rights reserved.

关键词： General type-II Fuzzy controller DC/AC converter Smart island optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Global Steering for Control Moment Gyroscope Clusters Using Heuristic Variable Search Techniques

引用

JOURNAL OF SPACECRAFT AND ROCKETS 2021年第4期58卷 972-983页

作者： Papakonstantinou, Charalampos Lappas, Vaios J. Schaub, Hanspeter Kostopoulos, Vassilis Univ Patras Dept Mech Engn & Aeronaut Rion 26504 Greece Univ Patras Rion 26504 Greece Univ Patras Appl Mech & Vibrat Lab Rion 26504 Greece Univ Colorado Colorado Ctr Astrodynam Res Aerosp Engn Sci Dept Boulder CO 80303 USA

This paper addresses the problem of singularity avoidance in a four-control-moment-gyroscope cluster as used for the attitude control of a satellite. A global search algorithm is developed that adjusts the null motion added upon the singularity robust inverse steering law. Its principal characteristic is that it uses global information gathered from the whole maneuver, compared to most conventional techniques that consider only some local information, near the current gimbal configuration for the optimization. The method is implemented using a ternary tree structure, and a heuristic algorithm optimizes a cost function that depends on the manipulability index, the time spent in the vicinity of singularity, the quaternion error, and the gimbal rates. Specific measures are taken to decrease the execution time of the algorithm, even for long maneuvers, without the need of a visit histogram. In addition, the tuning of only two variables can drastically change the execution time and the computational resources needed. The numerical simulation used to evaluate the algorithm indicates that the elliptic singularity can sufficiently be avoided and the algorithm drives the system fast away from the singularity with an overall performance improvement.

关键词： Control Moment Gyroscope Quaternions Singularity Avoidance Steering Laws Search algorithm Satellites Histograms Numerical Simulation optimization algorithm Yaw Polynomial Interpolation

来源：评论

学校读者我要写书评

暂无评论

APs Deployment optimization for Indoor Fingerprint Positioning with Adaptive Particle Swarm algorithm 1

引用

18th International Conference on algorithms and Architectures for Parallel Processing (ICA3PP)

作者： Zhao, Jianhui Li, Jun Ai, Haojun Cai, Bo Wuhan Univ Sch Comp Sci Wuhan 430072 Hubei Peoples R China Collaborat Innovat Ctr Geospatial Technol Wuhan 430079 Hubei Peoples R China

ISBN: (数字)9783030050573

ISBN: (纸本)9783030050573;9783030050566

Indoor positioning service gives people much better convenience, but its efficiency is affected by the spatial deployment of access points, APs. We propose an algorithm from adaptive particle swarm, APS, and then apply it in APs deployment optimization for fingerprint based indoor positioning. In our method, solutions of APs placement are taken as individuals of one population. Particle swarm method is improved with adaptive technology to ensure the population diversity and also avoid large number of inferior particles. After evolutions, the optimal result is obtained, corresponding to the best solution of APs deployment. The algorithm works well for both single-objective and multi-objective optimizations. Experiments with deployments of 107 iBeacons have been tested in an underground parking lot. Compared with the existing APs placement methods, our APS algorithm can obtain the least indoor positioning error with fixed APs number, while receive the best integrated evaluation considering both positioning error and APs cost with unfixed APs number. The proposed algorithm is easily popularized to the other kinds of indoor spaces and different types of signal sources.

关键词： Indoor positioning APs deployment optimization algorithm Adaptive particle swarm

来源：评论

学校读者我要写书评

暂无评论

optimization of the measurement path for the car body parts inspection

引用

MEASUREMENT 2019年 146卷 15-23页

作者： Teodor, Virgil Gabriel Paunoiu, Viorel Susac, Florin Baroiu, Nicusor Dunarea de Jos Univ Galati Fac Engn Domneasca 111 Galati 800210 Romania

The most evident characteristics of body components used in automotive industries are two overall dimensions with much higher values compared to a third one, as well as the relatively uniform apportion of functional elements on the surface of the workpiece. During the inspection process, these characteristics determine the active measuring element to pass greater distances between the measuring areas, in comparison to the distances required for the effective measurement. Heuristic and approximate methods for measuring path optimization have the advantage of finding a solution making fewer operations, and the found solution differs from the optimal solution with no more than 2-3%. In the present paper, optimization algorithms based on the matrix relaxation method and nearest neighbor method were imagined and applied. These algorithms have served as a basis for developing a software. This software allows the optimization of the measurement path for car body parts which characterized by areas where the inspection is carried out, relatively uniformly apportioned over the surface of the workpiece. (C) 2019 Elsevier Ltd. All rights reserved.

关键词： Measurement path Parts inspection optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Can deep learning algorithms outperform benchmark machine learning algorithms in flood susceptibility modeling?

引用

JOURNAL OF HYDROLOGY 2021年 592卷 125615-125615页

作者： Binh Thai Pham Chinh Luu Tran Van Phong Phan Trong Trinh Shirzadi, Ataollah Renoud, Somayeh Asadi, Shahrokh Hiep Van Le von Meding, Jason Clague, John J. Univ Transport Technol Hanoi 100000 Vietnam Natl Univ Civil Engn Fac Hydraul Engn Hanoi Vietnam Vietnam Acad Sci & Technol Inst Geol Sci 84 Chun Lang St Hanoi 100000 Vietnam Univ Kurdistan Dept Rangeland & Watershed Management Fac Nat Res Sanandaj Iran Univ Tehran Dept Engn Data Min Lab Coll Farabi Tehran Iran Duy Tan Univ Inst Res & Dev Da Nang 550000 Vietnam Univ Florida Sch Construct Management Gainesville FL USA Simon Fraser Univ Dept Earth Sci Burnaby BC Canada

This paper introduces a new deep-learning algorithm of deep belief network (DBN) based on an extreme learning machine (ELM) that is structured by back propagation (BN) and optimized by particle swarm optimization (PSO) algorithm, named DEBP, for flood susceptibility mapping in the Vu Gia-Thu Bon watershed, central Vietnam. We use 847 locations of floods that occurred in 2007, 2009, and 2013 and 16 flood conditioning factors evaluated by an information gain ratio (IGR) technique to construct and validate the proposed model. Statistical metrics, including sensitivity, specificity, accuracy, F1-measure, Jaccard coefficient, Matthews correlation coefficient (MCC), root mean square error (RMSE), and area under the receiver operating characteristic curve (AUC), are used to assess the goodness-of-fit/performance and prediction accuracy of the new deep learning model. We further compare the proposed model with several well-known machine learning algorithms, including artificial neural network-based radial base function (ANNRBF), logistic regression (LR), logistic model tree (LMTree), functional tree (FTree), and alternating decision tree (ADTree). The new proposed model, DEBP, has the highest goodness-of-fit (AUC = 0.970) and prediction accuracy (AUC = 0.967) of all of the tested models and thus shows promise as a tool for flood susceptibility modeling. We conclude that novel deep learning algorithms such as the one used in this study can improve the accuracy of flood susceptibility maps that are required by planners, decision makers, and government agencies to manage of areas vulnerable to flood-induced damage.

关键词： Flood susceptibility Deep belief network Extreme machine learning optimization algorithm Goodness-of-fit Vietnam

来源：评论

学校读者我要写书评

暂无评论

Development of optimum watermarking algorithm for radiography images

引用

COMPUTERS & ELECTRICAL ENGINEERING 2021年 89卷 106932-106932页

作者： El Tokhy, Mohamed S. Egyptian Atom Energy Author NRC Engn Dept P 13759 Inshas Egypt

The fusion of captured multi-focus radiography images using the same scene is essential for adaptation of image information. Besides, transmission of secure radiography image between practitioners with keeping all image details is a challenge. These issues are handled using three dependent goals that include fusion amongst neutron and x-ray radiography images, watermarking of fused radiography images and optimization of watermarked images. The watermarking algorithms are analyzed and evaluated under various attacks. Development of optimization technique is an essential purpose for higher robustness with acceptable imperceptibility and negligible image distortion of radiography images. Backtracking search optimization algorithm(BSA) is functionalized for this target. Paired objective functions are suggested for the BSA algorithm to achieve simultaneously high robustness and imperceptibility. It is fulfilled that proficient results with respect to quality fitness function(FF) are realized with proposed ridgelet watermarking. Consequently, secure transmission of multi-focus radiography images within industrial and medical applications can be fulfilled.

关键词： Signal and image processing Nondestructive testing Communication systems optimization algorithm Secure environments

来源：评论

学校读者我要写书评

暂无评论

Single-pixel imaging of temperature/pressure of solid surfaces based on temperature- and pressure-sensitive paint

引用

MEASUREMENT SCIENCE AND TECHNOLOGY 2021年第12期32卷 125205-125205页

作者： Jiang, Yuheng Huang, Jianqing Ju, Dehao Cai, Weiwei Shanghai Jiao Tong Univ Sch Mech Engn Key Lab Educ Minist Power Machinery & Engn 800 Dongchuan Rd Shanghai 200240 Peoples R China

Temperature- and pressure-sensitive paints (TSPs/PSPs) are the coatings containing luminescent molecules and sensitive to the temperature and oxygen concentration. This work proposed a single-pixel imaging modality of TSPs/PSPs, which can reconstruct the two-dimensional distribution of the lifetime using the signals acquired by a cost-effective photomultiplier tube. A hybrid algorithm was developed as well to solve the resulting inversion problem. Simulative studies have been conducted to validate and assess the performance of the imaging technique under different parameters including the number of sampling points for each illumination, sampling ratio (SR) and noise level in terms of mean square error, mean relative error (MRE) and computational time. Increasing both the number of sampling points and SR would improve the accuracy but takes more computational time. In the cases of the SR equals to 0.8, the MREs are approximately less than half of the noise level.

关键词： temperature sensitive paints pressure sensitive paints luminescence lifetime optimization algorithm compressed sensing

来源：评论

学校读者我要写书评

暂无评论

Oriented stochastic loss descent algorithm to train very deep multi-layer neural networks without vanishing gradients

引用

KNOWLEDGE-BASED SYSTEMS 2021年 230卷 107391-107391页

作者： Abuqaddom, Inas Mahafzah, Basel A. Faris, Hossam Univ Jordan King Abdullah II Sch Informat Technol Dept Comp Sci Amman Jordan Al Hussien Tech Univ Sch Comp & Informat Amman Jordan Univ Jordan King Abdullah II Sch Informat Technol Dept Informat Technol Amman Jordan

Deep multi-layer neural networks represent hypotheses of very high degree polynomials to solve very complex problems. Gradient descent optimization algorithms are utilized to train such deep networks through backpropagation, which suffers from permanent problems such as the vanishing gradient problem. To overcome the vanishing problem, we introduce a new anti-vanishing back-propagated learning algorithm called oriented stochastic loss descent (OSLD). OSLD updates a random-initialized parameter iteratively in the opposite direction of its partial derivative sign by a small positive random number, which is scaled by a tuned ratio of the model loss. This paper compares OSLD to stochastic gradient descent algorithm as the basic backpropagation algorithm and Adam as one of the best backpropagation algorithms in five benchmark models. Experimental results show that OSLD is very competitive to Adam in small and moderate depth models, and OSLD outperforms Adam in very long models. Moreover, OSLD is compatible with current backpropagation architectures except for learning rates. Finally, OSLD is stable and opens more choices in front of the very deep multi-layer neural networks. (C) 2021 Elsevier B.V. All rights reserved.

关键词： Vanishing gradient problem Deep learning Backpropagation Gradient descent algorithm optimization algorithm Deep multi-layer neural network

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：