Support Vector-based learning methods are an important part of Computational Intelligence techniques. Recent efforts have been dealing with the problem of learning from very large datasets. This paper reviews the most...Support Vector-based learning methods are an important part of Computational Intelligence techniques. Recent efforts have been dealing with the problem of learning from very large datasets. This paper reviews the most commonly used formulations of support vector machines for regression (SVRs) aiming to emphasize its usability on large-scale applications. We review the general concept of support vector machines (SVMs), address the state-of-the-art on training methods SVMs, and explain the fundamental principle of SVRs. The most common learning methods for SVRs are introduced and linear programming-based SVR formulations are explained emphasizing its suitability for large-scale learning. Finally, this paper also discusses some open problems and current trends.展开更多
During the height of the Coronavirus Disease (COVID-19) Pandemic, nurses all over the world, including members of the National Association of Nigerian Nurses in North America (NANNNA) experienced a heightened and unpr...During the height of the Coronavirus Disease (COVID-19) Pandemic, nurses all over the world, including members of the National Association of Nigerian Nurses in North America (NANNNA) experienced a heightened and unprecedented level of stress, anxiety, fear, uncertainty, concern for their safety and that of their loved ones. This prompted NANNNA leadership to initiate and conduct support programs for nurses especially those on the frontline of care. This project evaluates the effectiveness of the support programs conducted by NANNNA during the early surge of COVID-19. The Centers for Disease Control’s (CDC’s) Framework for Evaluation in Public Health guided this evaluation. Focus group discussion and online survey was utilized to gather data. While 19% of respondents reported being diagnosed with COVID-19, the majority (81%) were not. About 44% of respondents had family members who were diagnosed with COVID-19, while 18% reported loss of a close family member due to COVID-19 complications. Most respondents reported that the program was impactful in information sharing as well as significant in helping them feel connected with other nurses. Hence, this subsequently enhanced their support networks, provided emotional and spiritual support. Survey results revealed that NANNNA support programs had positive effects in helping members mitigate the fear, anxiety and uncertainty experienced during the surge of the COVID-19.展开更多
This proposal focuses on the prevalence of teenage pregnancy issue in NJ and illustrates the benefits of school-based health clinics and educational programs which should be implemented for teenage pregnancy and child...This proposal focuses on the prevalence of teenage pregnancy issue in NJ and illustrates the benefits of school-based health clinics and educational programs which should be implemented for teenage pregnancy and childbearing.Without the early intervention of educational programs and preventive medical services which should be implemented in school areas,teen pregnancy and childbearing can have physical and emotional health influences on teen mothers,their babies and other family members,and the worst consequence should be abortion.What’s more,teenage pregnancy and childbearing have substantial economic consequence for state.The annual estimated cost associated with teen childbearing (teens 19 and younger) in NJ to taxpayers is at least $167 million in 2004 (24% federal costs and 76% state and local costs).Studies demonstrated that a much larger amount of money is spent on the consequences of teenage pregnancy than on prevention.NJ has an opportunity to invest in prevention and reduce not only the monetary but also the societal costs to our youth burdened by the often overwhelming responsibilities of teenage pregnancy and parenting.According to the 15 years follow-up research and data analyzing,two models of success which specifically implemented in South Carolina high schools and Chicago public schools have been proved to effectively reduce incidence of repeat pregnancy and emergency room visits,reduce incidence of teen mothers smoking during pregnancy,improve emotional outcomes among teen mothers,decrease incidence of teen mothers drug impairment,arrest,conviction,or jail time and reduce use of food stamps and other public assistances,which can consequently increase the state public health costs.In order to support teen mothers’ academic,physical,emotional and social needs in a stable and consistent school environment,the plan which titled "Physical and Mental Health Promotion for NJ Teen Mothers" is effective and practical enough to arouse the attention of some relevant departments.It’s worth patron to fund the plan because supporting teenage pregnancy at early stage can subsequently benefit the national and state economy and teen mothers.展开更多
To solve the problems of SVM in dealing with large sample size and asymmetric distributed samples, a support vector classification algorithm based on variable parameter linear programming is proposed. In the proposed ...To solve the problems of SVM in dealing with large sample size and asymmetric distributed samples, a support vector classification algorithm based on variable parameter linear programming is proposed. In the proposed algorithm, linear programming is employed to solve the optimization problem of classification to decrease the computation time and to reduce its complexity when compared with the original model. The adjusted punishment parameter greatly reduced the classification error resulting from asymmetric distributed samples and the detailed procedure of the proposed algorithm is given. An experiment is conducted to verify whether the proposed algorithm is suitable for asymmetric distributed samples.展开更多
Ensuring program satisfaction for undergraduate students in the areas of science,technology,engineering and mathematics(STEM)matters in student retention and education quality improvement.This study explores how four ...Ensuring program satisfaction for undergraduate students in the areas of science,technology,engineering and mathematics(STEM)matters in student retention and education quality improvement.This study explores how four rarely examined variables support from faculty members,interdisciplinary features of STEM program courses,disciplinary connectedness of STEM program core courses,and examination difficulty impact Chinese STEM undergraduates’program satisfaction.With data from 619 Chinese STEM undergraduates,structural equation modeling shows that course satisfaction partially mediates the impact of support from faculty members on program satisfaction,while fully mediating that of interdisciplinary features of STEM program courses and disciplinary connectedness of STEM program core courses on program satisfaction.Examination difficulty exerts no significant impact on program satisfaction neither directly nor indirectly.Support from faculty members impact course satisfaction significantly stronger for junior and senior students than for freshmen and sophomores,while interdisciplinary features of STEM program courses impact course satisfaction stronger for freshmen and sophomores than for juniors and seniors.The study ends with practical implications for the higher education reform in relevant areas.展开更多
A second-order Mond-Weir type dual problem is formulated for a class of continuous programming problems in which both objective and constraint functions contain support functions;hence it is nondifferentiable. Under s...A second-order Mond-Weir type dual problem is formulated for a class of continuous programming problems in which both objective and constraint functions contain support functions;hence it is nondifferentiable. Under second-order strict pseudoinvexity, second-order pseudoinvexity and second-order quasi-invexity assumptions on functionals, weak, strong, strict converse and converse duality theorems are established for this pair of dual continuous programming problems. Special cases are deduced and a pair of dual continuous problems with natural boundary values is constructed. A close relationship between the duality results of our problems and those of the corresponding (static) nonlinear programming problem with support functions is briefly outlined.展开更多
A second-order dual problem is formulated for a class of continuous programming problem in which both objective and constrained functions contain support functions, hence it is nondifferentiable. Under second-order in...A second-order dual problem is formulated for a class of continuous programming problem in which both objective and constrained functions contain support functions, hence it is nondifferentiable. Under second-order invexity and second-order pseudoinvexity, weak, strong and converse duality theorems are established for this pair of dual problems. Special cases are deduced and a pair of dual continuous problems with natural boundary values is constructed. A close relationship between duality results of our problems and those of the corresponding (static) nonlinear programming problem with support functions is briefly outlined.展开更多
Aim: We devised a self-care supporting program targeting patients with early stages of secondary lower-limb lymphedema. The program incorporates “Simple exercises to replace lymphatic drainage” based on lymphatic fl...Aim: We devised a self-care supporting program targeting patients with early stages of secondary lower-limb lymphedema. The program incorporates “Simple exercises to replace lymphatic drainage” based on lymphatic flow. The purpose of this study was to consider the feasibility of continuing this program. Methods: The participants were patients in the early stages of secondary lower-limb lymphedema after gynecological cancer surgery and lymphedema therapists with more than five years of experience. Patients continued self-care at home after being briefed on the program, and they were analyzed on their self-care continuity status one month later based on a self-administered questionnaire survey and self-care notes. We interviewed the lymphedema therapists about this program to discuss the feasibility of continuing it and obtain feedback. Results: The patients who participated in the study were six women who underwent surgery with lymph node dissection for gynecological cancer. The therapists were five nurses and one occupational therapist. The patient understood the importance of all items in the self-care. “Observation,” “Touching,” and “Skin care” were relatively easy to continue. “Lymph drainage” and “Exercise” were continued with “Simple exercises to replace lymphatic drainage”. “Other exercises” were able to continue by adding distance and time to daily activities. Furthermore, “Measurement” and “Recording” became a burden and were difficult to continue. Nonetheless, this program was generally approved by the lymphedema therapists. They also pointed out the content and format of the self-care notes as improvements. Conclusions: We found that the self-care supporting program that incorporated “Simple exercises to replace lymphatic drainage” might be feasible to continue self-care for patients with early stages of secondary lower-limb lymphedema. Furthermore, we found that we needed to improve the “Measurement” and “Recording” sections of this program.展开更多
In online programming education,if teachers can determine any difficulties their students are experiencing and provide support,it would significantly improve the outcome of their teaching.This paper describes an attem...In online programming education,if teachers can determine any difficulties their students are experiencing and provide support,it would significantly improve the outcome of their teaching.This paper describes an attempt to build a time prediction model on the demand for personalized affective support based on a modified version of the Synthetic Minority Over-sampling Technique.We designed and conducted a data collection experiment based on the specific features of the affective support.Meanwhile,the modified oversampling algorithm can ascertain the time for providing such support for learners,which solves the problem of a class imbalance distribution.In addition,we obtained a sorting algorithm of the time prediction regarding the demand for personalized affective support in programming learning and constructed a time prediction model on the demand for affective support.Meanwhile,we conducted experiments on both public data and our own collected data to verify the effectiveness of the constructed model.The results show that the model is able to judge whether learners need affective support during the writing code process.展开更多
In this article, for a differentiable function , we introduce the definition of the higher-order -invexity. Three duality models for a multiobjective fractional programming problem involving nondifferentiability in te...In this article, for a differentiable function , we introduce the definition of the higher-order -invexity. Three duality models for a multiobjective fractional programming problem involving nondifferentiability in terms of support functions have been formulated and usual duality relations have been established under the higher-order -invex assumptions.展开更多
The potential demand on financial risk management has being increased considerably by the reason of Basel 11 regulations and instabilities in economy. In recent years, financial institutions and companies have been st...The potential demand on financial risk management has being increased considerably by the reason of Basel 11 regulations and instabilities in economy. In recent years, financial institutions and companies have been struggled for building up intensive financial risk management tools due to Basel II guidance on establishing financial self-assessment systems. In this respect, decision support system has a significant role on effectuating intensive financial risk management roadmap. In this study, a reformative financial risk management system is presented with the combination of determining financial risks with their importance, calculating risk scores and making suggestions based on detected risk scores by applying corrective actions. First, financial risk factors and indicators of these risk variables are selected and weights of these variables are specified by using fuzzy goal programming. After that, total risk scores are calculated and amendatory financial activities are appeared by means of expertons method which also provides possibilities of the alternative decisions. To illustrate the performance of integrated and multistage decision support system, a survey is applied on the end users.展开更多
The purpose of this paper was to describe the development, planning and implementing of an internet-based intervention program for providing support to families with prematurely born infants. During the families initi...The purpose of this paper was to describe the development, planning and implementing of an internet-based intervention program for providing support to families with prematurely born infants. During the families initial stay at home with their infant;families were given access to use of videoconference system from their home to have contact with staff at the neonatal unit, via direct link, throughout twenty-four hours. This program successfully ended, and video-conferencing is incorporated as a tool to support families after coming home. Probably, a variety of factors has contributed to make this program successful, as for example user friendliness and the close collaboration between researchers and staff at the neonatal unit. In conclusion, Information and Communication Technology (ICT) must be taken into consideration in developing upcoming care, thereby making possible a program to extend accessibility to health care.展开更多
Since the Hundreds, of Talents Program was put into operation at the CAS in 1994, nearly 400 young scholars at home and abroad have participated in the public bidding. Among them, 59 applicants have won the support fr...Since the Hundreds, of Talents Program was put into operation at the CAS in 1994, nearly 400 young scholars at home and abroad have participated in the public bidding. Among them, 59 applicants have won the support from the Program as a result of competition based on publicity, equality, fairness and the enrollment of the most outstanding. The followings are profiles of the winners in the program in 1996.展开更多
Water-Decision Support System (DSS) tools enhance decision-makings towards improved water supply in a given region. The rigours of manual design of the conventional water treatment plants are easily eliminated with th...Water-Decision Support System (DSS) tools enhance decision-makings towards improved water supply in a given region. The rigours of manual design of the conventional water treatment plants are easily eliminated with the use of softwares as in the case of DSS. Therefore, this paper focuses on the development of a Water-DSS for design of treatment plant in Karkala Town, Udupi District of India. A four-decade population projection was made using the baseline data of 1971 till date. The manual computation for water demand, unit operations and adjoining facilities was carried out and later coded in C-programming language for development of a DSS for easier design and process selection. Data validation was done and results from the two approaches were compared. With the C-programming technique, a decision support tool for design and process selection of drinking water treatment plant using conventional method has been developed and named Water-DSS1. The designed tool is simple, accurate, flexible, efficient and universal, easily adaptable to any similar conventional treatment plant. Water-DSS1 is thus recommended for general use in ultimately alleviating water supply challenges.展开更多
In order to solve the black-box modeling problem and improve the prediction accuracy of model,two distinguished models for tensile strength(Ts)and yield strength(Ys)of hot-rolled strip steel are established based on t...In order to solve the black-box modeling problem and improve the prediction accuracy of model,two distinguished models for tensile strength(Ts)and yield strength(Ys)of hot-rolled strip steel are established based on the industrial hot-rolled data and the algorithm of gene expression programming(GEP).Firstly,the industrial data of hot-rolled strip steel are preprocessed using the Pauta criterion,so as to eliminate outliers.The key input variables that affect Ys and Ts are selected by using the method of the maximal information coefficient(MIC).Secondly,the explicit prediction models of Ys and Ts are established using GEP.Subsequently,the model results based on GEP are compared with those based on the support vector regression(SVR)and the back propagation neural network(BPNN).Finally,the mathematical expression models for Ys and Ts obtained by GEP are used to further analyse the specific relationships between the chemical composition and mechanical property.It is shown that the errors of Ys and Ts based on GEP are less than 4%,and the coefficient of determination(R^(2))of Ys and Ts based on GEP is above 0.9,which has strong prediction performance.The prediction accuracy of GEP can achieve the same level with SVR and BPNN.It is worth mentioning that the proposed model can not only show the explicit relationship between the chemical composition,production process,and mechanical property of strip steel,but also occupy high prediction accuracy,which can make reliable reference for strip steel product design and optimisation.展开更多
文摘Support Vector-based learning methods are an important part of Computational Intelligence techniques. Recent efforts have been dealing with the problem of learning from very large datasets. This paper reviews the most commonly used formulations of support vector machines for regression (SVRs) aiming to emphasize its usability on large-scale applications. We review the general concept of support vector machines (SVMs), address the state-of-the-art on training methods SVMs, and explain the fundamental principle of SVRs. The most common learning methods for SVRs are introduced and linear programming-based SVR formulations are explained emphasizing its suitability for large-scale learning. Finally, this paper also discusses some open problems and current trends.
文摘During the height of the Coronavirus Disease (COVID-19) Pandemic, nurses all over the world, including members of the National Association of Nigerian Nurses in North America (NANNNA) experienced a heightened and unprecedented level of stress, anxiety, fear, uncertainty, concern for their safety and that of their loved ones. This prompted NANNNA leadership to initiate and conduct support programs for nurses especially those on the frontline of care. This project evaluates the effectiveness of the support programs conducted by NANNNA during the early surge of COVID-19. The Centers for Disease Control’s (CDC’s) Framework for Evaluation in Public Health guided this evaluation. Focus group discussion and online survey was utilized to gather data. While 19% of respondents reported being diagnosed with COVID-19, the majority (81%) were not. About 44% of respondents had family members who were diagnosed with COVID-19, while 18% reported loss of a close family member due to COVID-19 complications. Most respondents reported that the program was impactful in information sharing as well as significant in helping them feel connected with other nurses. Hence, this subsequently enhanced their support networks, provided emotional and spiritual support. Survey results revealed that NANNNA support programs had positive effects in helping members mitigate the fear, anxiety and uncertainty experienced during the surge of the COVID-19.
文摘This proposal focuses on the prevalence of teenage pregnancy issue in NJ and illustrates the benefits of school-based health clinics and educational programs which should be implemented for teenage pregnancy and childbearing.Without the early intervention of educational programs and preventive medical services which should be implemented in school areas,teen pregnancy and childbearing can have physical and emotional health influences on teen mothers,their babies and other family members,and the worst consequence should be abortion.What’s more,teenage pregnancy and childbearing have substantial economic consequence for state.The annual estimated cost associated with teen childbearing (teens 19 and younger) in NJ to taxpayers is at least $167 million in 2004 (24% federal costs and 76% state and local costs).Studies demonstrated that a much larger amount of money is spent on the consequences of teenage pregnancy than on prevention.NJ has an opportunity to invest in prevention and reduce not only the monetary but also the societal costs to our youth burdened by the often overwhelming responsibilities of teenage pregnancy and parenting.According to the 15 years follow-up research and data analyzing,two models of success which specifically implemented in South Carolina high schools and Chicago public schools have been proved to effectively reduce incidence of repeat pregnancy and emergency room visits,reduce incidence of teen mothers smoking during pregnancy,improve emotional outcomes among teen mothers,decrease incidence of teen mothers drug impairment,arrest,conviction,or jail time and reduce use of food stamps and other public assistances,which can consequently increase the state public health costs.In order to support teen mothers’ academic,physical,emotional and social needs in a stable and consistent school environment,the plan which titled "Physical and Mental Health Promotion for NJ Teen Mothers" is effective and practical enough to arouse the attention of some relevant departments.It’s worth patron to fund the plan because supporting teenage pregnancy at early stage can subsequently benefit the national and state economy and teen mothers.
基金the National Natural Science Foundation of China (70471074)China Postdoctoral Science Foundation(2005038042)Department of Science and Technology of Guangdong Province(2004B36001051).
文摘To solve the problems of SVM in dealing with large sample size and asymmetric distributed samples, a support vector classification algorithm based on variable parameter linear programming is proposed. In the proposed algorithm, linear programming is employed to solve the optimization problem of classification to decrease the computation time and to reduce its complexity when compared with the original model. The adjusted punishment parameter greatly reduced the classification error resulting from asymmetric distributed samples and the detailed procedure of the proposed algorithm is given. An experiment is conducted to verify whether the proposed algorithm is suitable for asymmetric distributed samples.
文摘Ensuring program satisfaction for undergraduate students in the areas of science,technology,engineering and mathematics(STEM)matters in student retention and education quality improvement.This study explores how four rarely examined variables support from faculty members,interdisciplinary features of STEM program courses,disciplinary connectedness of STEM program core courses,and examination difficulty impact Chinese STEM undergraduates’program satisfaction.With data from 619 Chinese STEM undergraduates,structural equation modeling shows that course satisfaction partially mediates the impact of support from faculty members on program satisfaction,while fully mediating that of interdisciplinary features of STEM program courses and disciplinary connectedness of STEM program core courses on program satisfaction.Examination difficulty exerts no significant impact on program satisfaction neither directly nor indirectly.Support from faculty members impact course satisfaction significantly stronger for junior and senior students than for freshmen and sophomores,while interdisciplinary features of STEM program courses impact course satisfaction stronger for freshmen and sophomores than for juniors and seniors.The study ends with practical implications for the higher education reform in relevant areas.
文摘A second-order Mond-Weir type dual problem is formulated for a class of continuous programming problems in which both objective and constraint functions contain support functions;hence it is nondifferentiable. Under second-order strict pseudoinvexity, second-order pseudoinvexity and second-order quasi-invexity assumptions on functionals, weak, strong, strict converse and converse duality theorems are established for this pair of dual continuous programming problems. Special cases are deduced and a pair of dual continuous problems with natural boundary values is constructed. A close relationship between the duality results of our problems and those of the corresponding (static) nonlinear programming problem with support functions is briefly outlined.
文摘A second-order dual problem is formulated for a class of continuous programming problem in which both objective and constrained functions contain support functions, hence it is nondifferentiable. Under second-order invexity and second-order pseudoinvexity, weak, strong and converse duality theorems are established for this pair of dual problems. Special cases are deduced and a pair of dual continuous problems with natural boundary values is constructed. A close relationship between duality results of our problems and those of the corresponding (static) nonlinear programming problem with support functions is briefly outlined.
文摘Aim: We devised a self-care supporting program targeting patients with early stages of secondary lower-limb lymphedema. The program incorporates “Simple exercises to replace lymphatic drainage” based on lymphatic flow. The purpose of this study was to consider the feasibility of continuing this program. Methods: The participants were patients in the early stages of secondary lower-limb lymphedema after gynecological cancer surgery and lymphedema therapists with more than five years of experience. Patients continued self-care at home after being briefed on the program, and they were analyzed on their self-care continuity status one month later based on a self-administered questionnaire survey and self-care notes. We interviewed the lymphedema therapists about this program to discuss the feasibility of continuing it and obtain feedback. Results: The patients who participated in the study were six women who underwent surgery with lymph node dissection for gynecological cancer. The therapists were five nurses and one occupational therapist. The patient understood the importance of all items in the self-care. “Observation,” “Touching,” and “Skin care” were relatively easy to continue. “Lymph drainage” and “Exercise” were continued with “Simple exercises to replace lymphatic drainage”. “Other exercises” were able to continue by adding distance and time to daily activities. Furthermore, “Measurement” and “Recording” became a burden and were difficult to continue. Nonetheless, this program was generally approved by the lymphedema therapists. They also pointed out the content and format of the self-care notes as improvements. Conclusions: We found that the self-care supporting program that incorporated “Simple exercises to replace lymphatic drainage” might be feasible to continue self-care for patients with early stages of secondary lower-limb lymphedema. Furthermore, we found that we needed to improve the “Measurement” and “Recording” sections of this program.
基金supported by the 2018-2020 Higher Education Talent Training Quality and Teaching Reform Project of Sichuan Province(Grant No.JG2018-46)the Science and Technology Planning Program of Sichuan University and Luzhou(Grant No.2017CDLZG30)the Postdoctoral Science fund of Sichuan University(Grant No.2019SCU12058).
文摘In online programming education,if teachers can determine any difficulties their students are experiencing and provide support,it would significantly improve the outcome of their teaching.This paper describes an attempt to build a time prediction model on the demand for personalized affective support based on a modified version of the Synthetic Minority Over-sampling Technique.We designed and conducted a data collection experiment based on the specific features of the affective support.Meanwhile,the modified oversampling algorithm can ascertain the time for providing such support for learners,which solves the problem of a class imbalance distribution.In addition,we obtained a sorting algorithm of the time prediction regarding the demand for personalized affective support in programming learning and constructed a time prediction model on the demand for affective support.Meanwhile,we conducted experiments on both public data and our own collected data to verify the effectiveness of the constructed model.The results show that the model is able to judge whether learners need affective support during the writing code process.
文摘In this article, for a differentiable function , we introduce the definition of the higher-order -invexity. Three duality models for a multiobjective fractional programming problem involving nondifferentiability in terms of support functions have been formulated and usual duality relations have been established under the higher-order -invex assumptions.
文摘The potential demand on financial risk management has being increased considerably by the reason of Basel 11 regulations and instabilities in economy. In recent years, financial institutions and companies have been struggled for building up intensive financial risk management tools due to Basel II guidance on establishing financial self-assessment systems. In this respect, decision support system has a significant role on effectuating intensive financial risk management roadmap. In this study, a reformative financial risk management system is presented with the combination of determining financial risks with their importance, calculating risk scores and making suggestions based on detected risk scores by applying corrective actions. First, financial risk factors and indicators of these risk variables are selected and weights of these variables are specified by using fuzzy goal programming. After that, total risk scores are calculated and amendatory financial activities are appeared by means of expertons method which also provides possibilities of the alternative decisions. To illustrate the performance of integrated and multistage decision support system, a survey is applied on the end users.
文摘The purpose of this paper was to describe the development, planning and implementing of an internet-based intervention program for providing support to families with prematurely born infants. During the families initial stay at home with their infant;families were given access to use of videoconference system from their home to have contact with staff at the neonatal unit, via direct link, throughout twenty-four hours. This program successfully ended, and video-conferencing is incorporated as a tool to support families after coming home. Probably, a variety of factors has contributed to make this program successful, as for example user friendliness and the close collaboration between researchers and staff at the neonatal unit. In conclusion, Information and Communication Technology (ICT) must be taken into consideration in developing upcoming care, thereby making possible a program to extend accessibility to health care.
文摘Since the Hundreds, of Talents Program was put into operation at the CAS in 1994, nearly 400 young scholars at home and abroad have participated in the public bidding. Among them, 59 applicants have won the support from the Program as a result of competition based on publicity, equality, fairness and the enrollment of the most outstanding. The followings are profiles of the winners in the program in 1996.
文摘Water-Decision Support System (DSS) tools enhance decision-makings towards improved water supply in a given region. The rigours of manual design of the conventional water treatment plants are easily eliminated with the use of softwares as in the case of DSS. Therefore, this paper focuses on the development of a Water-DSS for design of treatment plant in Karkala Town, Udupi District of India. A four-decade population projection was made using the baseline data of 1971 till date. The manual computation for water demand, unit operations and adjoining facilities was carried out and later coded in C-programming language for development of a DSS for easier design and process selection. Data validation was done and results from the two approaches were compared. With the C-programming technique, a decision support tool for design and process selection of drinking water treatment plant using conventional method has been developed and named Water-DSS1. The designed tool is simple, accurate, flexible, efficient and universal, easily adaptable to any similar conventional treatment plant. Water-DSS1 is thus recommended for general use in ultimately alleviating water supply challenges.
基金supported by the National Natural Science Foundation of China(Grant Nos.52074187 and 52274388)Liaoning Province Artificial Intelligence Innovation and Development Plan Project(Major Science and Technology Project)(2023JH26-10100002)the National Key Research and Development Program of China(No.2022YFB3304800).
文摘In order to solve the black-box modeling problem and improve the prediction accuracy of model,two distinguished models for tensile strength(Ts)and yield strength(Ys)of hot-rolled strip steel are established based on the industrial hot-rolled data and the algorithm of gene expression programming(GEP).Firstly,the industrial data of hot-rolled strip steel are preprocessed using the Pauta criterion,so as to eliminate outliers.The key input variables that affect Ys and Ts are selected by using the method of the maximal information coefficient(MIC).Secondly,the explicit prediction models of Ys and Ts are established using GEP.Subsequently,the model results based on GEP are compared with those based on the support vector regression(SVR)and the back propagation neural network(BPNN).Finally,the mathematical expression models for Ys and Ts obtained by GEP are used to further analyse the specific relationships between the chemical composition and mechanical property.It is shown that the errors of Ys and Ts based on GEP are less than 4%,and the coefficient of determination(R^(2))of Ys and Ts based on GEP is above 0.9,which has strong prediction performance.The prediction accuracy of GEP can achieve the same level with SVR and BPNN.It is worth mentioning that the proposed model can not only show the explicit relationship between the chemical composition,production process,and mechanical property of strip steel,but also occupy high prediction accuracy,which can make reliable reference for strip steel product design and optimisation.
