检索结果-内蒙古大学图书馆

Comparative Study Between MLR and ANN techniques to Predict Swelling Pressure of Expansive Clays

GEOTECHNICAL AND GEOLOGICAL ENGINEERING 2022年第7期40卷 3443-3455页

作者： Bag, Ramakrishna Bharti, Abhishek Jadda, Koteswaraarao Kumar, M. L. S. Sai Indian Inst Technol Patna Dept Civil & Environm Engn Patna Bihar India Natl Inst Technol Jamshedpur Dept Elect Engn Jamshedpur Bihar India

Locally available expansive clays (bentonites) are planned to be used as buffer material in deep geological repositories. The current study highlighted the significance of various geotechnical properties such as specific gravity, liquid limit, plastic limit, specific surface area, cation exchange capacity, percentage of clay content, smectite content and dry density on the swelling pressure of the compacted expansive clays using soft computing techniques such as multiple linear regression (MLR) and artificial neural network (ANN). In total, 185 experimental results of 14 different expansive clays of 27 batches were considered from literature. The investigation was carried out by 2 computational approaches. Initially, MLR technique was used and the swelling pressure was assumed to vary linearly with clay properties. In the second approach, nonlinearity was included using ANN technique. Levenberg-Marquardt (LM) and Scaled Conjugate Gradient (SCG) algorithms were used in ANN approach. The sensitivity analysis of the soil properties was carried out and the parameters were ranked according to their influence on the development of swelling pressure. The nonlinear method was found to be more accurate than the linear method. The LM algorithm was noted to be more accurate in predicting swelling pressure of compacted expansive soil than that of SCG. Among all the influential parameters, the dry density was found to be the most critical parameter to predict the swelling pressure of compacted expansive clays. The outcome of current study models can be useful to predict swelling pressure of compacted bentonite that would be helpful to select buffer material in deep geological repositories.

关键词： soft computing technique MLR ANN Expansive soil Swelling pressure

来源：评论

学校读者我要写书评

暂无评论

Prediction of the concrete compressive strength using improved random forest algorithm

引用

Journal of Building Pathology and Rehabilitation 2023年第2期8卷 1-12页

作者： Khodaparasti, Mohammad Alijamaat, Ali Pouraminian, Majid Department of Computer Engineering Rasht Branch Islamic Azad University Rasht Iran Department of Computer Engineering Abhar Branch Islamic Azad University Abhar Iran Department of Civil Engineering Ramsar Branch Islamic Azad University Ramsar Iran

Concrete is one of the most widely used materials in the construction industry. The most common parameter to achieve the quality and strength of concrete is the compressive strength of the concrete sample. The strength of concrete depends on various variables, such as the ratio of water to cement, the amount of its constituents, including cement, fine aggregate, coarse aggregate, and additives. Predicting the strength of concrete effectively helps relevant experts to use it in various projects. Predicting the strength of concrete samples from the mentioned variables using machine learning methods that are highly accurate can save the costs of samples construction, maintenance, and loading of concrete samples, without waiting for the sample to reach a certain age. The purpose of this article is to predict the compressive strength of concrete using the improved random forest method. The proposed predictive model were based on eight input parameters as features, namely cement, fly ash, water, superplasticizer, coarse aggregate, fine aggregate and age, while concrete compressive strength was an output parameter. Three most popular statistical parameters such as coefficient of determination (R²), mean absolute error (MAE), and root mean square error (RMSE) model efficiency were utilized for assessment of proposed predictive model. In the proposed method, compared to the classic random forest, two changes have been made in the stage of creating trees and in the testing stage. The values of the criteria R², MAE, and RMSE achieved respectively 0.931, 3.21 and 4.71, which has better results than other machine learning methods and the classical random forest method. © 2023, The Author(s), under exclusive licence to Springer Nature Switzerland AG.

关键词： Classification method Compressive strength Improved random forest Machine learning Prediction soft computing technique

来源：评论

学校读者我要写书评

暂无评论

A comparative study of statistical and soft computing techniques for reliability prediction of automotive manufacturing

引用

APPLIED soft computing 2021年 98卷 106738-106738页

作者： Soltanali, Hamzeh Rohani, Abbas Abbaspour-Fard, Mohammad Hossein Farinha, Jose Torres Ferdowsi Univ Mashhad Dept Biosyst Engn Mashhad Razavi Khorasan Iran Ctr Mech Engn Mat & Proc CEMMPRE Coimbra Portugal ISEC Coimbra Inst Engn Coimbra Portugal

Reliability and safety analyses are the most important activities for reducing risk of failure events and upgrading availability of manufacturing industries. The traditional statistical models have been currently used;however, the complexity growth and diversity of systems as well as uncertainty of their functions result in extreme difficulties in analyzing the reliability by such models. To overcome such drawbacks, the soft computing techniques are useful alternative for modeling of complex systems and prediction applications. Hence, this paper provides a comparative structure for predicting the operational reliability in automotive manufacturing industry, using soft computing + statistical techniques. The results of comparative structure revealed that the soft computing techniques can estimate the reliability function with the lowest error in all cases. Based on the performance criteria, it was observed that among the soft computing techniques, the Adaptive Neuro-Fuzzy Inference System (ANFIS) model yields better results in most cases and thus can be used for predicting operational reliability, since it predicts the reliability more accurately and precisely than the statistical models. Ultimately, the maintenance intervals based on the ANFIS model are proposed to upgrade the reliability and safety of automotive manufacturing process. (C) 2020 Elsevier B.V. All rights reserved.

关键词： Reliability Statistical model Automotive soft computing technique Maintenance

来源：评论

学校读者我要写书评

暂无评论

Grey Wolf Optimizer Based PID Controller for Speed Control of BLDC Motor

引用

JOURNAL OF ELECTRICAL ENGINEERING & TECHNOLOGY 2021年第2期16卷 955-961页

作者： Dutta, Pallav Nayak, Santanu Kumar Aliah Univ Dept Elect Engn Kolkata 700160 India Infosys Ltd Hyderabad 500088 India

A BLDC motor is superior to a brushed DC motor, as it replaces the mechanical commutation unit with an electronic one;hence improving the dynamic characteristics, efficiency and reducing the noise level marginally. Maximum BLDC motor drives use PID controller to control the speed of the machine;because it is simple in structure, relatively cheaper and exhibits good performance. But the main problem associated with PID controller is adjusting its parameters during implementation. In recent works, it has been observed that Particle Swarm Optimization (PSO) technique showed good performance in tuning PID controller. For this purpose, in this article, "Grey Wolf Optimization" (GWO) algorithm is introduced;which is used to optimally tune the PID controller parameters. The objective of this article is to compare the results obtained for tuning of PID controller based on of GWO and PSO technique and a conclusion has been derived that the proposed approach yields superior dynamic performance for BLDC motor.

关键词： Brushless DC motor Grey wolf optimization PID controller Particle swarm optimization soft computing technique

来源：评论

学校读者我要写书评

暂无评论

Simulation, Fabrication and Microfiltration Using Dual Anodic Aluminum Oxide Membrane

引用

MEMBRANES 2023年第10期13卷 825-825页

作者： Qasim, Faheem Ashraf, Muhammad Waseem Tayyaba, Shahzadi Tariq, Muhammad Imran Herrera-May, Agustin L. GC Univ Lahore Inst Phys Dept Elect Lahore 54000 Pakistan Univ Educ Dept Informat Sci Div Sci & Technol Township Campus Lahore 54000 Pakistan Super Univ Lahore Dept Comp Sci Lahore 54000 Pakistan Univ Veracruzana Micro & Nanotechnol Res Ctr Boca del Rio 94294 Veracruz Mexico

Microfluidic devices have gained subsequent attention due to their controlled manipulation of fluid for various biomedical applications. These devices can be used to study the behavior of fluid under several micrometer ranges within the channel. The major applications are the filtration of fluid, blood filtration and bio-medical analysis. For the filtration of water, as well as other liquids, the micro-filtration based microfluidic devices are considered as potential candidates to fulfill the desired conditions and requirements. The micro pore membrane can be designed and fabricated in such a way that it maximizes the removal of impurities from fluid. The low-cost micro-filtration method has been reported to provide clean fluid for biomedical applications and other purposes. In the work, anodic-aluminum-oxide-based membranes have been fabricated with different pore sizes ranging from 70 to 500 nm. A soft computing technique like fuzzy logic has been used to estimate the filtration parameters. Then, the finite-element-based analysis system software has been used to study the fluid flow through the double membrane. Then, filtration is performed by using a dual membrane and the clogging of the membrane has been studied after different filtration cycles using characterization like a scanning electron microscope. The filtration has been done to purify the contaminated fluid which has impurities like bacteria and protozoans. The membranes have been tested after each cycle to verify the results. The decrease in permeance with respect to the increase in the velocity of the fluid and the permeate volume per unit clearly depicts the removal of containments from the fluid after four and eight cycles of filtration. The results clearly show that the filtration efficiency can be improved by increasing the number of cycles and adding a dual membrane in the micro-fluidic device. The results show the potential of dual anodic aluminum oxide membranes for the effective filtration of f

关键词： microfluidics filtration soft computing technique anodization

来源：评论

学校读者我要写书评

暂无评论

Mathematical models of CBSC over wireless channels and their analysis by using the LeNN-WOA-NM algorithm

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2022年第0期107卷 104537-104537页

作者： Khan, Naveed Ahmad Sulaiman, Muhammad Aljohani, Abdulah Jeza Bakar, Maharani A. Miftahuddin Abdul Wali Khan Univ Dept Math Mardan 23200 KP Pakistan King Abdulaziz Univ Dept Elect & Comp Engn Jeddah 21589 Saudi Arabia King Abdulaziz Univ Ctr Excellence Intelligent Engn Syst Jeddah 21589 Saudi Arabia Univ Malaysia Terengganu Fac Ocean Engn Technol & Informat Special Interest Grp Modelling & Data Analyt Terengganu 21300 Malaysia Univ Syiah Kuala Fac Math & Nat Sci Dept Stat Banda Aceh Indonesia

In recent studies, several chaos-based secure communication (CBSC) systems are developed and are assumed to be effective and promising tools for balancing communications in wireless applications. The reliability of a wireless communication system is dependent on the synchronization between receiving and transmitting nodes. Therefore, it is crucial to analyze the mathematical models for different enhancements through CBSC and avoid the difficulty in synchronization. We have designed a novel computational paradigm that uses weighted Legendre polynomials to construct series solutions for mathematical models of the Lorenz Chaotic Attractor (LCA) and Double Scroll Attractor (DSA) (with filter and without filter) by using Chua's circuits. We design fitness functions for each system of differential equations. Two optimization techniques, the Whale Optimization Algorithm (WOA) and the Nelder-Mead (NM) algorithm are adopted to optimize the objective functions and calculate the best set of unknown weights. We name our soft computing paradigm, the LeNN-WOA-NM algorithm. We have compared our results with state-of-the-art, and we establish that the LeNN-WOA-NM algorithm is fast, accurate, and reliable. We present graphical and statistical analysis to further elaborate on the performance of our algorithm.

关键词： Chaotic communications Wireless communication Chao's circuits Secure communication Chaotic synchronization System of ODE's soft computing technique Mathematical modeling and analysis Optimization problems

来源：评论

学校读者我要写书评

暂无评论

Compressive Strength Evaluation of Ultra-High-Strength Concrete by Machine Learning

引用

MATERIALS 2022年第10期15卷 3523-3523页

作者： Shen, Zhongjie Deifalla, Ahmed Farouk Kaminski, Pawel Dyczko, Artur Xijing Univ Xian 710123 Peoples R China Future Univ Egypt Fac Engn & Technol Struct Engn & Construct Management Dept Cairo 11835 Egypt AGH Univ Sci & Technol Fac Civil Engn & Resource Management Mickiewicza 30 PL-30059 Krakow Poland Polish Acad Sci Mineral & Energy Econ Res Inst J Wybickiego 7a PL-31261 Krakow Poland

In civil engineering, ultra-high-strength concrete (UHSC) is a useful and efficient building material. To save money and time in the construction sector, soft computing approaches have been used to estimate concrete properties. As a result, the current work used sophisticated soft computing techniques to estimate the compressive strength of UHSC. In this study, XGBoost, AdaBoost, and Bagging were the employed soft computing techniques. The variables taken into account included cement content, fly ash, silica fume and silicate content, sand and water content, superplasticizer content, steel fiber, steel fiber aspect ratio, and curing time. The algorithm performance was evaluated using statistical metrics, such as the mean absolute error (MAE), root mean square error (RMSE), and coefficient of determination (R-2). The model's performance was then evaluated statistically. The XGBoost soft computing technique, with a higher R-2 (0.90) and low errors, was more accurate than the other algorithms, which had a lower R-2. The compressive strength of UHSC can be predicted using the XGBoost soft computing technique. The SHapley Additive exPlanations (SHAP) analysis showed that curing time had the highest positive influence on UHSC compressive strength. Thus, scholars will be able to quickly and effectively determine the compressive strength of UHSC using this study's findings.

关键词： UHSC building material compressive strength soft computing technique concrete

来源：评论

学校读者我要写书评

暂无评论

Employing artificial neural network for accurate modeling, simulation and performance analysis of an RO-based desalination process

引用

SUSTAINABLE computing-INFORMATICS & SYSTEMS 2022年 35卷

作者： Mahadeva, Rajesh Kumar, Mahendra Patole, Shashikant P. Manik, Gaurav Indian Inst Technol Roorkee Dept Polymer & Proc Engn Roorkee 247667 Uttaranchal India Indian Inst Technol Roorkee Dept Elect Engn Roorkee 247667 Uttaranchal India Khalifa Univ Sci & Technol Dept Phys Abu Dhabi 127788 U Arab Emirates

In this paper, we implement sustainable soft computing via application of Artificial Neural Networks (ANN) to predict the desalination plant output more accurately. The proposed ANN models have been trained with a backpropagation (BP) algorithm. Motivated by the literature, an exhaustive modeling has been performed using an extended list of six ANN modeling parameters that include number of hidden layers and their nodes, activation and training functions, dataset fractional allocation, and error analysis functions. For this, 4 suitable experimental inputs and permeate flux as output have been considered for the modeling investigation. The proposed models have been simulated in the MATLAB/Simulink platform and compared with literature models, based on the regression coefficient (R2), errors, and iterations. An investigation of 127 trials leads to the optimal selection of the parameters that achieve higher optimal model performance (R2 = 99.4%, Error = 0.003) than the existing models in the literature. We have observed that choice of softmax-purelin function (activation function for hidden layer-output layer), two hidden layers with 20 nodes each, Levenberg-Marquardt training function, dataset divisions (80% training: 10% validation: 10% testing) and the mean square error (MSE) demonstrate best model performance. Such an efficient and sustainable soft computing system modeling and simulation exemplifies an indispensable method for supporting the desalination design and engineering and assists in an efficient and robust control of the desalination plants.

关键词： soft computing technique Artificial Neural Network Modeling and simulation Desalination Water treatment

来源：评论

学校读者我要写书评

暂无评论

Identification of diabetes disease from human blood using machine learning techniques

Identification of diabetes disease from human blood using ma...

引用

2020 International Conference on Smart Technologies in computing, Electrical and Electronics, ICSTCEE 2020

作者： Khatoon, Hasina Verma, Dipti Arora, Ankit Chhattisgarh Swami Vivekanand Ttechnical University Vishwavidyalaya Engineering College Lakhanpur Department of CSE Bhilai C. G. Chhattisgarh India Chhattisgarh Swami Vivekanand Ttechnical University Vishwavidyalaya Engineering College Lakhanpur Department of CSE Chhattisgarh Bhilai India

ISBN: (纸本)9781728172132

Diabetes among one of the most common diseases occurs in human beings due to imbalance of insulin level in blood. The early detection of diabetes is very necessary as it can affect many internal parts and immune system of human body silently. In this paper, we are comparing various machine learning and neural network based approaches that are applied on publically available datasets. Here, we have used two datasets for experiments 1st dataset is UCI dataset and other is PIMA Indian dataset then we have performed lots of experiments using different machine learning classifiers and neural network models to observe the performance of each classifier. After experiments, the highest accuracy of identification obtained from decision tree method which is 99.8% for dataset1 and for dataset 2 the highest accuracy was obtained from back propagation neural network model which is 80.8 %. © 2020 IEEE.

关键词： Neural Network soft computing technique Types of Diabetes UCI Diabetes Dataset

来源：评论

学校读者我要写书评

暂无评论

An efficient grey wolf optimization algorithm based extended kalman filtering technique for various image modalities restoration process

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2018年第23期77卷 30205-30232页

作者： Sam, B. Baron Fred, A. Lenin Sathyabama Inst Sci & Technol Dept Comp Sci & Engn Madras 600119 Tamil Nadu India Mar Ephraem Coll Engn & Technol Malankara Hills Marthandam 629171 Tamil Nadu India

The procedure of procurement the original image from the degraded image assumed the knowledge of the debasing factors is called as Image Restoration. The corrupted image will be considered as input and provided to the soft computing method for decreasing the noisy information from the input image in our suggested method. Nonetheless, the established output image obtained from the soft computing method will seem to be blurry with less superiority in the contrast level. This blurred information damages the function of image reconstruction. Thus, into overawed this disadvantage, we deed an Extended Kalman filter method to provide great quality reconstructed the image, in that an optimization algorithm Grey Wolf Optimization (GWO) will be used for a greater reconstructed image. The main contribution of the proposed work is to improve the image quality of reconstruction image by means of optimal Extended Kalman filter. For proving the function of our suggested method, the reconstructed image quality will be associated with the conventional methods. The restoration method was tested with different image modalities such as MRI, CT and also Ultra Sound images of the Human abdomen. The method will be applied to the functioning platform of MATLAB. The implemented restoration technique achieves the maximum Peak Signal to Noise Ratio (PSNR) and structural similarity index (SSIM) value for liver CT image are 35.10db and 0.999 and minimum Mean square error (MSE) and Mean absolute error (MAE) value for liver CT image are 7.90E-05 and 1.1281 respectively.

关键词： Image reconstruction Extended kalman filter Gray wolf optimization soft computing technique

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：