A surrogate model for interference prevention in the limaçon-to-limaçon machines
- Authors: Sultan, Ibrahim
- Date: 2007
- Type: Text , Journal article
- Relation: Engineering Computations (Swansea, Wales) Vol. 24, no. 5 (2007), p. 437-449
- Full Text:
- Reviewed:
- Description: Purpose - This paper aims to replace the complicated iterative procedure used to prevent interference in limacon-to-limacon machines by a simplified mathematical equation which can be solved by a straightforward substitution of the required clearance value. Design/methodology/approach - The input data to the iterative procedure and the obtained results have been employed in regression models to construct the sought after equation. Searching for a proper form of this equation involved numerical experiments to study the effects of the various model parameters on the system response. Findings - The numerical experiments conducted proved to be an effective model construction technique, and the regression model proposed has been found extremely accurate in the specified parameter space. Research limitations/implications - The proposed equation is applicable within the parameter range chosen for the study. This range is the one often used for industrial applications. Should the parameters selected for a specific design fall outside the specified range, the proposed model structure may have to be varied to maintain a desirable level of accuracy. Practical implications - The interference study is a part of the iterative procedure employed to design the dimensions of the limaçon-to-limaçon machine. This iterative procedure searches for the proper design amongst hundreds of various possible solutions. The results of this paper will ensure a much faster convergence for the design procedure, since the interference study will be eliminated from the iterative section of the analysis. Originality/value - The paper offers a valid and accurate model that can be efficiently used for the intended purpose. © Emerald Group Publishing Limited.
- Description: C1
- Description: 2003004799
- Authors: Sultan, Ibrahim
- Date: 2007
- Type: Text , Journal article
- Relation: Engineering Computations (Swansea, Wales) Vol. 24, no. 5 (2007), p. 437-449
- Full Text:
- Reviewed:
- Description: Purpose - This paper aims to replace the complicated iterative procedure used to prevent interference in limacon-to-limacon machines by a simplified mathematical equation which can be solved by a straightforward substitution of the required clearance value. Design/methodology/approach - The input data to the iterative procedure and the obtained results have been employed in regression models to construct the sought after equation. Searching for a proper form of this equation involved numerical experiments to study the effects of the various model parameters on the system response. Findings - The numerical experiments conducted proved to be an effective model construction technique, and the regression model proposed has been found extremely accurate in the specified parameter space. Research limitations/implications - The proposed equation is applicable within the parameter range chosen for the study. This range is the one often used for industrial applications. Should the parameters selected for a specific design fall outside the specified range, the proposed model structure may have to be varied to maintain a desirable level of accuracy. Practical implications - The interference study is a part of the iterative procedure employed to design the dimensions of the limaçon-to-limaçon machine. This iterative procedure searches for the proper design amongst hundreds of various possible solutions. The results of this paper will ensure a much faster convergence for the design procedure, since the interference study will be eliminated from the iterative section of the analysis. Originality/value - The paper offers a valid and accurate model that can be efficiently used for the intended purpose. © Emerald Group Publishing Limited.
- Description: C1
- Description: 2003004799
Estimation of a regression function by maxima of minima of linear functions
- Bagirov, Adil, Clausen, Conny, Kohler, Michael
- Authors: Bagirov, Adil , Clausen, Conny , Kohler, Michael
- Date: 2009
- Type: Text , Journal article
- Relation: IEEE Transactions on Information Theory Vol. 55, no. 2 (2009), p. 833-845
- Full Text:
- Reviewed:
- Description: In this paper, estimation of a regression function from independent and identically distributed random variables is considered. Estimates are defined by minimization of the empirical L2 risk over a class of functions, which are defined as maxima of minima of linear functions. Results concerning the rate of convergence of the estimates are derived. In particular, it is shown that for smooth regression functions satisfying the assumption of single index models, the estimate is able to achieve (up to some logarithmic factor) the corresponding optimal one-dimensional rate of convergence. Hence, under these assumptions, the estimate is able to circumvent the so-called curse of dimensionality. The small sample behavior of the estimates is illustrated by applying them to simulated data. © 2009 IEEE.
- Authors: Bagirov, Adil , Clausen, Conny , Kohler, Michael
- Date: 2009
- Type: Text , Journal article
- Relation: IEEE Transactions on Information Theory Vol. 55, no. 2 (2009), p. 833-845
- Full Text:
- Reviewed:
- Description: In this paper, estimation of a regression function from independent and identically distributed random variables is considered. Estimates are defined by minimization of the empirical L2 risk over a class of functions, which are defined as maxima of minima of linear functions. Results concerning the rate of convergence of the estimates are derived. In particular, it is shown that for smooth regression functions satisfying the assumption of single index models, the estimate is able to achieve (up to some logarithmic factor) the corresponding optimal one-dimensional rate of convergence. Hence, under these assumptions, the estimate is able to circumvent the so-called curse of dimensionality. The small sample behavior of the estimates is illustrated by applying them to simulated data. © 2009 IEEE.
Prediction of drillability of rocks with strength properties using a hybrid GA-ANN technique
- Khandelwal, Manoj, Armaghani, Danial
- Authors: Khandelwal, Manoj , Armaghani, Danial
- Date: 2016
- Type: Text , Journal article
- Relation: Geotechnical and Geological Engineering Vol. 34, no. 2 (2016), p. 605-620
- Full Text:
- Reviewed:
- Description: The purpose of this paper is to provide a proper, practical and convenient drilling rate index (DRI) prediction model based on rock material properties. In order to obtain this purpose, 47 DRI tests were used. In addition, the relevant strength properties i.e. uniaxial compressive strength and Brazilian tensile strength were also used and selected as input parameters to predict DRI. Examined simple regression analysis showed that the relationships between the DRI and predictors are statistically meaningful but not good enough for DRI estimation in practice. Moreover, multiple regression, artificial neural network (ANN) and hybrid genetic algorithm (GA)-ANN models were constructed to estimate DRI. Several performance indices i.e. coefficient of determination (R2), root mean square error and variance account for were used for evaluation of performance prediction the proposed methods. Based on these results and the use of simple ranking procedure, the best models were chosen. It was found that the hybrid GA-ANN technique can performed better in predicting DRI compared to other developed models. This is because of the fact that the proposed hybrid model can update the biases and weights of the network connection to train by ANN.
- Description: The purpose of this paper is to provide a proper, practical and convenient drilling rate index (DRI) prediction model based on rock material properties. In order to obtain this purpose, 47 DRI tests were used. In addition, the relevant strength properties i.e. uniaxial compressive strength and Brazilian tensile strength were also used and selected as input parameters to predict DRI. Examined simple regression analysis showed that the relationships between the DRI and predictors are statistically meaningful but not good enough for DRI estimation in practice. Moreover, multiple regression, artificial neural network (ANN) and hybrid genetic algorithm (GA)-ANN models were constructed to estimate DRI. Several performance indices i.e. coefficient of determination (R2), root mean square error and variance account for were used for evaluation of performance prediction the proposed methods. Based on these results and the use of simple ranking procedure, the best models were chosen. It was found that the hybrid GA-ANN technique can performed better in predicting DRI compared to other developed models. This is because of the fact that the proposed hybrid model can update the biases and weights of the network connection to train by ANN. © 2015 Springer International Publishing Switzerland
- Authors: Khandelwal, Manoj , Armaghani, Danial
- Date: 2016
- Type: Text , Journal article
- Relation: Geotechnical and Geological Engineering Vol. 34, no. 2 (2016), p. 605-620
- Full Text:
- Reviewed:
- Description: The purpose of this paper is to provide a proper, practical and convenient drilling rate index (DRI) prediction model based on rock material properties. In order to obtain this purpose, 47 DRI tests were used. In addition, the relevant strength properties i.e. uniaxial compressive strength and Brazilian tensile strength were also used and selected as input parameters to predict DRI. Examined simple regression analysis showed that the relationships between the DRI and predictors are statistically meaningful but not good enough for DRI estimation in practice. Moreover, multiple regression, artificial neural network (ANN) and hybrid genetic algorithm (GA)-ANN models were constructed to estimate DRI. Several performance indices i.e. coefficient of determination (R2), root mean square error and variance account for were used for evaluation of performance prediction the proposed methods. Based on these results and the use of simple ranking procedure, the best models were chosen. It was found that the hybrid GA-ANN technique can performed better in predicting DRI compared to other developed models. This is because of the fact that the proposed hybrid model can update the biases and weights of the network connection to train by ANN.
- Description: The purpose of this paper is to provide a proper, practical and convenient drilling rate index (DRI) prediction model based on rock material properties. In order to obtain this purpose, 47 DRI tests were used. In addition, the relevant strength properties i.e. uniaxial compressive strength and Brazilian tensile strength were also used and selected as input parameters to predict DRI. Examined simple regression analysis showed that the relationships between the DRI and predictors are statistically meaningful but not good enough for DRI estimation in practice. Moreover, multiple regression, artificial neural network (ANN) and hybrid genetic algorithm (GA)-ANN models were constructed to estimate DRI. Several performance indices i.e. coefficient of determination (R2), root mean square error and variance account for were used for evaluation of performance prediction the proposed methods. Based on these results and the use of simple ranking procedure, the best models were chosen. It was found that the hybrid GA-ANN technique can performed better in predicting DRI compared to other developed models. This is because of the fact that the proposed hybrid model can update the biases and weights of the network connection to train by ANN. © 2015 Springer International Publishing Switzerland
Identifying tobacco retailers in the absence of a licensing system : lessons from Australia
- Baker, John, Masood, Mohd, Rahman, Muhammad Aziz, Thornton, Lukar, Begg, Stephen
- Authors: Baker, John , Masood, Mohd , Rahman, Muhammad Aziz , Thornton, Lukar , Begg, Stephen
- Date: 2021
- Type: Text , Journal article
- Relation: Tobacco Control Vol. 31, no. 4 (2021), p. 543-548
- Full Text:
- Reviewed:
- Description: ObjectivesTo estimate the proportion of retailers that sell tobacco in the absence of appropriate local government oversight, and to describe the characteristics by which they differ from those that can expect to receive such oversight.MethodsA database of listed tobacco retailers was obtained from a regional Victorian local government. Potential unlisted tobacco retailers were added using online searches, and attempts to visit all retailers were undertaken. GPS coordinates and sales type information of retailers that sold tobacco were recorded and attached to neighbourhood-level data on socioeconomic disadvantage and smoking prevalence using ArcMap. Logistic regression analyses, χ2 tests and t-tests were undertaken to explore differences in numbers of listed and unlisted retailers by business and neighbourhood-level characteristics.ResultsOf 125 confirmed tobacco retailers, 43.2% were trading potentially without government oversight. Significant differences were found between listed and unlisted retailers by primary business type (p<0.001), and sales type (p<0.001) but not by the other characteristics.ConclusionsThe database of tobacco retailers was inaccurate in two ways: (1) a number of listed retailers no longer operated or sold tobacco, and (2) 43.2% of businesses confirmed as selling tobacco were missing. As no form of licensing system exists in Victoria, it is difficult to identify the number of retailers operating, or to determine how many receive formal regulatory oversight. A positive licensing system is recommended to regulate the sale of tobacco and to generate a comprehensive database of retailers, similar to that which exists for food registration, gaming and liquor-licensed premises.
- Authors: Baker, John , Masood, Mohd , Rahman, Muhammad Aziz , Thornton, Lukar , Begg, Stephen
- Date: 2021
- Type: Text , Journal article
- Relation: Tobacco Control Vol. 31, no. 4 (2021), p. 543-548
- Full Text:
- Reviewed:
- Description: ObjectivesTo estimate the proportion of retailers that sell tobacco in the absence of appropriate local government oversight, and to describe the characteristics by which they differ from those that can expect to receive such oversight.MethodsA database of listed tobacco retailers was obtained from a regional Victorian local government. Potential unlisted tobacco retailers were added using online searches, and attempts to visit all retailers were undertaken. GPS coordinates and sales type information of retailers that sold tobacco were recorded and attached to neighbourhood-level data on socioeconomic disadvantage and smoking prevalence using ArcMap. Logistic regression analyses, χ2 tests and t-tests were undertaken to explore differences in numbers of listed and unlisted retailers by business and neighbourhood-level characteristics.ResultsOf 125 confirmed tobacco retailers, 43.2% were trading potentially without government oversight. Significant differences were found between listed and unlisted retailers by primary business type (p<0.001), and sales type (p<0.001) but not by the other characteristics.ConclusionsThe database of tobacco retailers was inaccurate in two ways: (1) a number of listed retailers no longer operated or sold tobacco, and (2) 43.2% of businesses confirmed as selling tobacco were missing. As no form of licensing system exists in Victoria, it is difficult to identify the number of retailers operating, or to determine how many receive formal regulatory oversight. A positive licensing system is recommended to regulate the sale of tobacco and to generate a comprehensive database of retailers, similar to that which exists for food registration, gaming and liquor-licensed premises.
The determinants of cluster activities in the Australian wine and tourism industries
- Taylor, Peter, McRae-Williams, Pamela, Lowe, Julian
- Authors: Taylor, Peter , McRae-Williams, Pamela , Lowe, Julian
- Date: 2007
- Type: Text , Journal article
- Relation: Tourism Economics Vol. 13, no. 4 (2007), p. 639-656
- Full Text:
- Reviewed:
- Description: This paper discusses wine and tourism clusters and the recent innovation of wine tourism in which businesses operate within both industries. The concept of micro-clusters is examined in terms of trust, networking, collaboration and other activities, all of which are argued to depend on the concepts of game theory and sunk costs. The study involved both interviews and a questionnaire. Conceptual variables are created from the questionnaire responses using factor analysis. The determinants of cluster activities are modelled using regression analysis. The effects of industry, place and respondents' entrepreneurial characteristics are used as exogenous variables. The study finds that industry does seem to be more important than place in the determination of networking and cooperative cluster activities, and that members of the wine tourism industry participate more in these activities than members of the tourism or hospitality industries. The addition of three variables that embody the entrepreneurial characteristics of the respondents approximately doubles the explanatory power of the original models. There is evidence to suggest that cluster activities are idiosyncratic for each industry-place cluster. The effects of firm size on cluster activities are also examined. No evidence is found of cooperative activities depending on cluster size. The main results support the contention that sunk costs are important in the determination of cluster activities.
- Description: C1
- Description: 2003005195
- Authors: Taylor, Peter , McRae-Williams, Pamela , Lowe, Julian
- Date: 2007
- Type: Text , Journal article
- Relation: Tourism Economics Vol. 13, no. 4 (2007), p. 639-656
- Full Text:
- Reviewed:
- Description: This paper discusses wine and tourism clusters and the recent innovation of wine tourism in which businesses operate within both industries. The concept of micro-clusters is examined in terms of trust, networking, collaboration and other activities, all of which are argued to depend on the concepts of game theory and sunk costs. The study involved both interviews and a questionnaire. Conceptual variables are created from the questionnaire responses using factor analysis. The determinants of cluster activities are modelled using regression analysis. The effects of industry, place and respondents' entrepreneurial characteristics are used as exogenous variables. The study finds that industry does seem to be more important than place in the determination of networking and cooperative cluster activities, and that members of the wine tourism industry participate more in these activities than members of the tourism or hospitality industries. The addition of three variables that embody the entrepreneurial characteristics of the respondents approximately doubles the explanatory power of the original models. There is evidence to suggest that cluster activities are idiosyncratic for each industry-place cluster. The effects of firm size on cluster activities are also examined. No evidence is found of cooperative activities depending on cluster size. The main results support the contention that sunk costs are important in the determination of cluster activities.
- Description: C1
- Description: 2003005195
Nonsmooth optimization-based hyperparameter-free neural networks for large-scale regression
- Karmitsa, Napsu, Taheri, Sona, Joki, Kaisa, Paasivirta, Pauliina, Defterdarovic, J., Bagirov, Adil, Mäkelä, Marko
- Authors: Karmitsa, Napsu , Taheri, Sona , Joki, Kaisa , Paasivirta, Pauliina , Defterdarovic, J. , Bagirov, Adil , Mäkelä, Marko
- Date: 2023
- Type: Text , Journal article
- Relation: Algorithms Vol. 16, no. 9 (2023), p.
- Relation: http://purl.org/au-research/grants/arc/DP190100580
- Full Text:
- Reviewed:
- Description: In this paper, a new nonsmooth optimization-based algorithm for solving large-scale regression problems is introduced. The regression problem is modeled as fully-connected feedforward neural networks with one hidden layer, piecewise linear activation, and the (Formula presented.) -loss functions. A modified version of the limited memory bundle method is applied to minimize this nonsmooth objective. In addition, a novel constructive approach for automated determination of the proper number of hidden nodes is developed. Finally, large real-world data sets are used to evaluate the proposed algorithm and to compare it with some state-of-the-art neural network algorithms for regression. The results demonstrate the superiority of the proposed algorithm as a predictive tool in most data sets used in numerical experiments. © 2023 by the authors.
- Authors: Karmitsa, Napsu , Taheri, Sona , Joki, Kaisa , Paasivirta, Pauliina , Defterdarovic, J. , Bagirov, Adil , Mäkelä, Marko
- Date: 2023
- Type: Text , Journal article
- Relation: Algorithms Vol. 16, no. 9 (2023), p.
- Relation: http://purl.org/au-research/grants/arc/DP190100580
- Full Text:
- Reviewed:
- Description: In this paper, a new nonsmooth optimization-based algorithm for solving large-scale regression problems is introduced. The regression problem is modeled as fully-connected feedforward neural networks with one hidden layer, piecewise linear activation, and the (Formula presented.) -loss functions. A modified version of the limited memory bundle method is applied to minimize this nonsmooth objective. In addition, a novel constructive approach for automated determination of the proper number of hidden nodes is developed. Finally, large real-world data sets are used to evaluate the proposed algorithm and to compare it with some state-of-the-art neural network algorithms for regression. The results demonstrate the superiority of the proposed algorithm as a predictive tool in most data sets used in numerical experiments. © 2023 by the authors.
- «
- ‹
- 1
- ›
- »