Mathematical Problems in Engineering
1024-123X
Cơ quản chủ quản: Hindawi Publishing Corporation
Lĩnh vực:
Mathematics (miscellaneous)Engineering (miscellaneous)
Các bài báo tiêu biểu
Review on Methods to Fix Number of Hidden Neurons in Neural Networks This paper reviews methods to fix a number of hidden neurons in neural networks for the past 20 years. And it also proposes a new method to fix the hidden neurons in Elman networks for wind speed prediction in renewable energy systems. The random selection of a number of hidden neurons might cause either overfitting or underfitting problems. This paper proposes the solution of these problems. To fix hidden neurons, 101 various criteria are tested based on the statistical errors. The results show that proposed model improves the accuracy and minimal error. The perfect design of the neural network based on the selection criteria is substantiated using convergence theorem. To verify the effectiveness of the model, simulations were conducted on real-time wind data. The experimental results show that with minimum errors the proposed approach can be used for wind speed prediction. The survey has been made for the fixation of hidden neurons in neural networks. The proposed model is simple, with minimal error, and efficient for fixation of hidden neurons in Elman networks.
Tập 2013 - Trang 1-11 - 2013
DEMATEL Technique: A Systematic Review of the State-of-the-Art Literature on Methodologies and Applications Decision making trial and evaluation laboratory (DEMATEL) is considered as an effective method for the identification of cause-effect chain components of a complex system. It deals with evaluating interdependent relationships among factors and finding the critical ones through a visual structural model. Over the recent decade, a large number of studies have been done on the application of DEMATEL and many different variants have been put forward in the literature. The objective of this study is to review systematically the methodologies and applications of the DEMATEL technique. We reviewed a total of 346 papers published from 2006 to 2016 in the international journals. According to the approaches used, these publications are grouped into five categories: classical DEMATEL, fuzzy DEMATEL, grey DEMATEL, analytical network process- (ANP-) DEMATEL, and other DEMATEL. All papers with respect to each category are summarized and analyzed, pointing out their implementing procedures, real applications, and crucial findings. This systematic and comprehensive review holds valuable insights for researchers and practitioners into using the DEMATEL in terms of indicating current research trends and potential directions for further research.
Tập 2018 - Trang 1-33 - 2018
Landslide Susceptibility Assessment in Vietnam Using Support Vector Machines, Decision Tree, and Naïve Bayes Models The objective of this study is to investigate and compare the results of three data mining approaches, the support vector machines (SVM), decision tree (DT), and Naïve Bayes (NB) models for spatial prediction of landslide hazards in the Hoa Binh province (Vietnam). First, a landslide inventory map showing the locations of 118 landslides was constructed from various sources. The landslide inventory was then randomly partitioned into 70% for training the models and 30% for the model validation. Second, ten landslide conditioning factors were selected (i.e., slope angle, slope aspect, relief amplitude, lithology, soil type, land use, distance to roads, distance to rivers, distance to faults, and rainfall). Using these factors, landslide susceptibility indexes were calculated using SVM, DT, and NB models. Finally, landslide locations that were not used in the training phase were used to validate and compare the landslide susceptibility maps. The validation results show that the models derived using SVM have the highest prediction capability. The model derived using DT has the lowest prediction capability. Compared to the logistic regression model, the prediction capability of the SVM models is slightly better. The prediction capability of the DT and NB models is lower.
Tập 2012 Số 1 - 2012
Influence of Data Splitting on Performance of Machine Learning Models in Prediction of Shear Strength of Soil The main objective of this study is to evaluate and compare the performance of different machine learning (ML) algorithms, namely, Artificial Neural Network (ANN), Extreme Learning Machine (ELM), and Boosting Trees (Boosted) algorithms, considering the influence of various training to testing ratios in predicting the soil shear strength, one of the most critical geotechnical engineering properties in civil engineering design and construction. For this aim, a database of 538 soil samples collected from the Long Phu 1 power plant project, Vietnam, was utilized to generate the datasets for the modeling process. Different ratios (i.e., 10/90, 20/80, 30/70, 40/60, 50/50, 60/40, 70/30, 80/20, and 90/10) were used to divide the datasets into the training and testing datasets for the performance assessment of models. Popular statistical indicators, such as Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and Correlation Coefficient (R), were employed to evaluate the predictive capability of the models under different training and testing ratios. Besides, Monte Carlo simulation was simultaneously carried out to evaluate the performance of the proposed models, taking into account the random sampling effect. The results showed that although all three ML models performed well, the ANN was the most accurate and statistically stable model after 1000 Monte Carlo simulations (Mean R = 0.9348) compared with other models such as Boosted (Mean R = 0.9192) and ELM (Mean R = 0.8703). Investigation on the performance of the models showed that the predictive capability of the ML models was greatly affected by the training/testing ratios, where the 70/30 one presented the best performance of the models. Concisely, the results presented herein showed an effective manner in selecting the appropriate ratios of datasets and the best ML model to predict the soil shear strength accurately, which would be helpful in the design and engineering phases of construction projects.
Tập 2021 - Trang 1-15 - 2021
Peristaltic transport of Johnson‐Segalman fluid under effect of a magnetic field The peristaltic transport of Johnson‐Segalman fluid by means of an infinite train of sinusoidal waves traveling along the walls of a two‐dimensional flexible channel is investigated. The fluid is electrically conducted by a transverse magnetic field. A perturbation solution is obtained for the case in which amplitude ratio is small. Numerical results are reported for various values of the physical parameters of interest.
Tập 2005 Số 6 - Trang 663-677 - 2005
UTAUT2 Based Predictions of Factors Influencing the Technology Acceptance of Phablets by DNP The smart mobile devices have emerged during the past decade and have become one of the most dominant consumer electronic products. Therefore, exploring and understanding the factors which can influence the acceptance of novel mobile technology have become the essential task for the vendors and distributors of mobile devices. The Phablets, integrated smart devices combining the functionality and characteristics of both tablet PCs and smart phones, have gradually become possible alternatives for smart phones. Therefore, predicting factors which can influence the acceptance of Phablets have become indispensable for designing, manufacturing, and marketing of such mobile devices. However, such predictions are not easy. Meanwhile, very few researches tried to study related issues. Consequently, the authors aim to explore and predict the intentions to use and use behaviors of Phablets. The second generation of the Unified Theory of Acceptance and Use of Technology (UTAUT2) is introduced as a theoretic basis. The Decision Making Trial and Evaluation Laboratory (DEMATEL) based Network Process (DNP) will be used to construct the analytic framework. In light of the analytic results, the causal relationships being derived by the DEMATEL demonstrate the direct influence of the habit on other dimensions. Also, based on the influence weights being derived, the use intention, hedonic motivation, and performance expectancy are the most important dimensions. The analytic results can serve as a basis for concept developments, marketing strategy definitions, and new product designs of the future Phablets. The proposed analytic framework can also be used for predicting and analyzing consumers’ preferences toward future mobile devices.
Tập 2015 - Trang 1-23 - 2015
Recent Research Trends in Genetic Algorithm Based Flexible Job Shop Scheduling Problems Flexible Job Shop Scheduling Problem (FJSSP) is an extension of the classical Job Shop Scheduling Problem (JSSP). The FJSSP is known to be NP-hard problem with regard to optimization and it is very difficult to find reasonably accurate solutions of the problem instances in a rational time. Extensive research has been carried out in this area especially over the span of the last 20 years in which the hybrid approaches involving Genetic Algorithm (GA) have gained the most popularity. Keeping in view this aspect, this article presents a comprehensive literature review of the FJSSPs solved using the GA. The survey is further extended by the inclusion of the hybrid GA (hGA) techniques used in the solution of the problem. This review will give readers an insight into use of certain parameters in their future research along with future research directions.
Tập 2018 - Trang 1-32 - 2018
c‐Bottlenecks in serial production lines: Identification andapplication The bottleneck of a production line is a machine that impedes the system performance in the strongest manner. In production lines with the so‐called Markovian model of machine reliability, bottlenecks with respect to the downtime, uptime, and the cycle time of the machines can be introduced. The two former have been addressed in recent publications [1] and [2]. The latter is investigated in this paper. Specifically, using a novel aggregation procedure for performance analysis of production lines with Markovian machines having different cycle time, we develop a method for c‐bottleneck identification and apply it in a case study to a camshaft production line at an automotive engine plant.
Tập 7 Số 6 - Trang 543-578 - 2001
Peristaltic motion of a Johnson‐Segalman fluid in a planar channel This paper is devoted to the
study of the two‐dimensional flow of a Johnson‐Segalman fluid in
a planar channel having walls that are transversely displaced by
an infinite, harmonic travelling wave of large wavelength. Both
analytical and numerical solutions are presented. The analysis
for the analytical solution is carried
out for small Weissenberg
numbers. (A Weissenberg number is the ratio of the relaxation
time of the fluid to a characteristic time associated with the
flow.) Analytical solutions have been obtained for the stream
function from which the relations of the velocity and
the longitudinal pressure gradient have been derived. The
expression of the pressure rise over a wavelength has
also been determined. Numerical computations are performed and
compared to the perturbation analysis. Several limiting
situations with their implications can be examined from the
presented analysis.
Tập 2003 Số 1 - Trang 1-23 - 2003
An Improved Random Forest Algorithm for Predicting Employee Turnover Employee turnover is considered a major problem for many organizations and enterprises. The problem is critical because it affects not only the sustainability of work but also the continuity of enterprise planning and culture. Therefore, human resource departments are paying greater attention to employee turnover seeking to improve their understanding of the underlying reasons and main factors. To address this need, this study aims to enhance the ability to forecast employee turnover and introduce a new method based on an improved random forest algorithm. The proposed weighted quadratic random forest algorithm is applied to employee turnover data with high‐dimensional unbalanced characteristics. First, the random forest algorithm is used to order feature importance and reduce dimensions. Second, the selected features are used with the random forest algorithm and the F‐measure values are calculated for each decision tree as weights to build the prediction model for employee turnover. In the area of employee turnover forecasting, compared with the random forest, C4.5, Logistic, BP, and other algorithms, the proposed algorithm shows significant improvement in terms of various performance indicators, specifically recall and F‐measure. In the experiment using the employee dataset of a branch of a communications company in China, the key factors influencing employee turnover were identified as monthly income, overtime, age, distance from home, years at the company, and percent of salary increase. Among them, monthly income and overtime were the two most important factors. The study offers a new analytic method that can help human resource departments predict employee turnover more accurately and its experimental results provide further insights to reduce employee turnover intention.
Tập 2019 Số 1 - 2019