Pub Date : 2024-11-22DOI: 10.1016/j.matcom.2024.11.012
Tiancheng Zong, Junhong Li, Guoping Lu
The scarce measurement-data system means that the input or output of one system are sampled at scarce time series. Thus, the sampled data are incomplete in scarce measurement-data systems. In this paper, the parameter estimation of scarce measurement-data multiple input multiple output Hammerstein Box-Jenkins (S-MIMO-H-BJ) systems is studied. To make full use of the system data without adding unknown parameters, the particle filtering method is applied to obtain unknown states and variables in scarce measurement-data systems. Thus, the maximum likelihood Levenberg Marquardt (ML-LM) iterative method based on particle filtering (ML-LM-I-PF) is derived. To verify the superiority of the proposed algorithm, the ML-LM iterative method based on auxiliary model (ML-LM-I-AM) is also derived. Finally, using these two algorithms, unknown parameters in the S-MIMO-H-BJ numerical example and the two-tank level system are identified. Simulations prove that these two methods can all estimate S-MIMO-H-BJ models effectively, but the ML-LM-I-PF method behaves better because it has smaller calculation amount and more accurate parameter estimation.
{"title":"Maximum likelihood LM identification based on particle filtering for scarce measurement-data MIMO Hammerstein Box-Jenkins systems","authors":"Tiancheng Zong, Junhong Li, Guoping Lu","doi":"10.1016/j.matcom.2024.11.012","DOIUrl":"10.1016/j.matcom.2024.11.012","url":null,"abstract":"<div><div>The scarce measurement-data system means that the input or output of one system are sampled at scarce time series. Thus, the sampled data are incomplete in scarce measurement-data systems. In this paper, the parameter estimation of scarce measurement-data multiple input multiple output Hammerstein Box-Jenkins (S-MIMO-H-BJ) systems is studied. To make full use of the system data without adding unknown parameters, the particle filtering method is applied to obtain unknown states and variables in scarce measurement-data systems. Thus, the maximum likelihood Levenberg Marquardt (ML-LM) iterative method based on particle filtering (ML-LM-I-PF) is derived. To verify the superiority of the proposed algorithm, the ML-LM iterative method based on auxiliary model (ML-LM-I-AM) is also derived. Finally, using these two algorithms, unknown parameters in the S-MIMO-H-BJ numerical example and the two-tank level system are identified. Simulations prove that these two methods can all estimate S-MIMO-H-BJ models effectively, but the ML-LM-I-PF method behaves better because it has smaller calculation amount and more accurate parameter estimation.</div></div>","PeriodicalId":49856,"journal":{"name":"Mathematics and Computers in Simulation","volume":"230 ","pages":"Pages 241-255"},"PeriodicalIF":4.4,"publicationDate":"2024-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142722506","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-21DOI: 10.1016/j.matcom.2024.11.013
Lihong Zhang , Keke Lu , Bashir Ahmad
A new fractal-fractional reaction diffusion model with weighted reaction is investigated in this paper. Using Chelyshkov polynomials, we construct the associated Chelyshkov operator matrix to solve this diffusion model. An error estimation is obtained for validation of our method. Numerical examples indicate that the proposed method is easy to apply and produce accurate results. It is imperative to mention that the fractal-fractional reaction diffusion model and the proposed numerical method offer an efficient approach to handle the issues related to the diffusion phenomenon.
{"title":"Numerical simulation and error analysis for a novel fractal–fractional reaction diffusion model with weighted reaction","authors":"Lihong Zhang , Keke Lu , Bashir Ahmad","doi":"10.1016/j.matcom.2024.11.013","DOIUrl":"10.1016/j.matcom.2024.11.013","url":null,"abstract":"<div><div>A new fractal-fractional reaction diffusion model with weighted reaction is investigated in this paper. Using Chelyshkov polynomials, we construct the associated Chelyshkov operator matrix to solve this diffusion model. An error estimation is obtained for validation of our method. Numerical examples indicate that the proposed method is easy to apply and produce accurate results. It is imperative to mention that the fractal-fractional reaction diffusion model and the proposed numerical method offer an efficient approach to handle the issues related to the diffusion phenomenon.</div></div>","PeriodicalId":49856,"journal":{"name":"Mathematics and Computers in Simulation","volume":"230 ","pages":"Pages 227-240"},"PeriodicalIF":4.4,"publicationDate":"2024-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142700821","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-20DOI: 10.1016/j.matcom.2024.11.011
Marco Bee
Dynamic mixture distributions are convenient models for highly skewed and heavy-tailed data. However, estimation has proved to be challenging and computationally expensive. To address this issue, we develop a more parsimonious model, based on a one-parameter weight function given by the exponential cumulative distribution function. Parameter estimation is carried out via maximum likelihood, approximate maximum likelihood and noisy cross-entropy. Simulation experiments and real-data analyses suggest that approximate maximum likelihood is the best method in terms of RMSE, albeit at a high computational cost. With respect to the version of the dynamic mixture with weight equal to the two-parameter Cauchy cumulative distribution function, the reduced flexibility of the present model is more than compensated by better statistical and computational properties.
{"title":"A parsimonious dynamic mixture for heavy-tailed distributions","authors":"Marco Bee","doi":"10.1016/j.matcom.2024.11.011","DOIUrl":"10.1016/j.matcom.2024.11.011","url":null,"abstract":"<div><div>Dynamic mixture distributions are convenient models for highly skewed and heavy-tailed data. However, estimation has proved to be challenging and computationally expensive. To address this issue, we develop a more parsimonious model, based on a one-parameter weight function given by the exponential cumulative distribution function. Parameter estimation is carried out via maximum likelihood, approximate maximum likelihood and noisy cross-entropy. Simulation experiments and real-data analyses suggest that approximate maximum likelihood is the best method in terms of RMSE, albeit at a high computational cost. With respect to the version of the dynamic mixture with weight equal to the two-parameter Cauchy cumulative distribution function, the reduced flexibility of the present model is more than compensated by better statistical and computational properties.</div></div>","PeriodicalId":49856,"journal":{"name":"Mathematics and Computers in Simulation","volume":"230 ","pages":""},"PeriodicalIF":4.4,"publicationDate":"2024-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142700819","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-20DOI: 10.1016/j.matcom.2024.09.028
Mengna Li, Zhanwen Yang
In this paper, we consider the numerical threshold for an age-structured HIV model with latently infected T cells. Based on the continuous collocation methods, a semi-discrete scheme is constructed by discretizing the age variable and a numerical basic reproduction number is provided. With the study of higher-order convergence to the real basic reproduction number , the relations between and local stability of disease-free are presented. From the viewpoint of full discretization, an equivalent block-Leslie matrix expression is obtained by embedding into a piecewise-discontinuous polynomial space rather than the piecewise-continuous polynomial space. An implicit full-discrete scheme is considered based on a linearly implicit Euler (IMEX) method, of which the computational cost is almost the same as an explicit scheme. It is more important that the dynamical behavior of the age-semi-discretization system is also preserved for any time step whenever is the threshold for the numerical dynamical system of the age-semi-discretization. Finally, numerical applications are shown to HIV models to illustrate our analysis.
{"title":"Numerical analysis of an age-structured model for HIV viral dynamics with latently infected T cells based on collocation methods","authors":"Mengna Li, Zhanwen Yang","doi":"10.1016/j.matcom.2024.09.028","DOIUrl":"10.1016/j.matcom.2024.09.028","url":null,"abstract":"<div><div>In this paper, we consider the numerical threshold for an age-structured HIV model with latently infected T cells. Based on the continuous collocation methods, a semi-discrete scheme is constructed by discretizing the age variable and a numerical basic reproduction number <span><math><msub><mrow><mi>R</mi></mrow><mrow><mi>h</mi></mrow></msub></math></span> is provided. With the study of higher-order convergence to the real basic reproduction number <span><math><msub><mrow><mi>R</mi></mrow><mrow><mn>0</mn></mrow></msub></math></span>, the relations between <span><math><msub><mrow><mi>R</mi></mrow><mrow><mi>h</mi></mrow></msub></math></span> and local stability of disease-free are presented. From the viewpoint of full discretization, an equivalent block-Leslie matrix expression is obtained by embedding into a piecewise-discontinuous polynomial space rather than the piecewise-continuous polynomial space. An implicit full-discrete scheme is considered based on a linearly implicit Euler (IMEX) method, of which the computational cost is almost the same as an explicit scheme. It is more important that the dynamical behavior of the age-semi-discretization system is also preserved for any time step whenever <span><math><msub><mrow><mi>R</mi></mrow><mrow><mi>h</mi></mrow></msub></math></span> is the threshold for the numerical dynamical system of the age-semi-discretization. Finally, numerical applications are shown to HIV models to illustrate our analysis.</div></div>","PeriodicalId":49856,"journal":{"name":"Mathematics and Computers in Simulation","volume":"230 ","pages":"Pages 289-305"},"PeriodicalIF":4.4,"publicationDate":"2024-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142759477","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-19DOI: 10.1016/j.matcom.2024.11.009
Lupeng Hao , Weihang Peng , Junhua Liu , Wei Zhang , Yuan Li , Kaixuan Qin
In recent years, the emergence of constrained multi-objective evolutionary algorithms (CMOEAs) has made it increasingly difficult to balance between the diversity and convergence of algorithms. To address this challenge, this paper proposes a competition-based two-stage evolutionary algorithm, named CP-TSEA, for constrained multi-objective problems. In the first stage, a constraint boundary relaxation learning mechanism was applied to the auxiliary population. This mechanism not only improved the diversity of the population but also enhanced the global search capability by relaxing the constraints, allowing infeasible solutions with higher fitness rankings to participate in the evolution. In the second stage, an equal-probability competitive strategy was used to select high-quality parents from the elite mating pool to ensure that the population could converge quickly to the optimal solution. The two-stage approach not only improved the exploration ability of the algorithm, but also was able to select higher quality solutions and prevent them from falling into local optima. Additionally, the solution selection in the elite environment employed a three-criteria ranking method to maintain a balance between population diversity and convergence. In terms of experiments, CP-TSEA was compared with seven advanced CMOEAs across five test suites, and the comprehensive data showed that CP-TSEA significantly outperformed its competitors. In addition, CP-TSEA also achieved the best values in six real-world problems, which further confirmed its scalability in real-world applications.
{"title":"Competition-based two-stage evolutionary algorithm for constrained multi-objective optimization","authors":"Lupeng Hao , Weihang Peng , Junhua Liu , Wei Zhang , Yuan Li , Kaixuan Qin","doi":"10.1016/j.matcom.2024.11.009","DOIUrl":"10.1016/j.matcom.2024.11.009","url":null,"abstract":"<div><div>In recent years, the emergence of constrained multi-objective evolutionary algorithms (CMOEAs) has made it increasingly difficult to balance between the diversity and convergence of algorithms. To address this challenge, this paper proposes a competition-based two-stage evolutionary algorithm, named CP-TSEA, for constrained multi-objective problems. In the first stage, a <span><math><mi>ɛ</mi></math></span> constraint boundary relaxation learning mechanism was applied to the auxiliary population. This mechanism not only improved the diversity of the population but also enhanced the global search capability by relaxing the constraints, allowing infeasible solutions with higher fitness rankings to participate in the evolution. In the second stage, an equal-probability competitive strategy was used to select high-quality parents from the elite mating pool to ensure that the population could converge quickly to the optimal solution. The two-stage approach not only improved the exploration ability of the algorithm, but also was able to select higher quality solutions and prevent them from falling into local optima. Additionally, the solution selection in the elite environment employed a three-criteria ranking method to maintain a balance between population diversity and convergence. In terms of experiments, CP-TSEA was compared with seven advanced CMOEAs across five test suites, and the comprehensive data showed that CP-TSEA significantly outperformed its competitors. In addition, CP-TSEA also achieved the best values in six real-world problems, which further confirmed its scalability in real-world applications.</div></div>","PeriodicalId":49856,"journal":{"name":"Mathematics and Computers in Simulation","volume":"230 ","pages":""},"PeriodicalIF":4.4,"publicationDate":"2024-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142700820","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-18DOI: 10.1016/j.matcom.2024.11.008
Jianping Gao, Wenyan Lian
In this paper, we consider a Lotka–Volterra competition system with two dynamical resources and density-dependent motility under the homogeneous Neumann boundary condition. Here, we put the two competing species into a predator–prey system, and assume that the two competing species as predators can feed on different preys and that the preys as resources admit temporal dynamics including spatial movement, intrinsic birth–death kinetics and loss due to predation. When the distributions of prey’s resources can be homogeneous, by using some proper Lyapunov functionals and applying LaSalle’s invariant principle, we obtain that the solution can converge to the positive steady state exponentially or to the competitive exclusion steady states algebraically as time goes to infinity. Our finding shows that the consideration of temporal dynamics on the resources can lead to the coexistence of two competitors in some parameter conditions regardless of their dispersal rates. When the distributions of prey’s resources are spatially heterogeneous, we conduct several numerical simulations in different combinations of dispersal strategy and the distributions of prey’s resources, and we show that the non-random dispersal and heterogeneous distributions of prey’s resources can affect the fates of two competitors.
{"title":"Long time behavior of a Lotka–Volterra competition system with two dynamical resources and density-dependent motility","authors":"Jianping Gao, Wenyan Lian","doi":"10.1016/j.matcom.2024.11.008","DOIUrl":"10.1016/j.matcom.2024.11.008","url":null,"abstract":"<div><div>In this paper, we consider a Lotka–Volterra competition system with two dynamical resources and density-dependent motility under the homogeneous Neumann boundary condition. Here, we put the two competing species into a predator–prey system, and assume that the two competing species as predators can feed on different preys and that the preys as resources admit temporal dynamics including spatial movement, intrinsic birth–death kinetics and loss due to predation. When the distributions of prey’s resources can be homogeneous, by using some proper Lyapunov functionals and applying LaSalle’s invariant principle, we obtain that the solution can converge to the positive steady state exponentially or to the competitive exclusion steady states algebraically as time goes to infinity. Our finding shows that the consideration of temporal dynamics on the resources can lead to the coexistence of two competitors in some parameter conditions regardless of their dispersal rates. When the distributions of prey’s resources are spatially heterogeneous, we conduct several numerical simulations in different combinations of dispersal strategy and the distributions of prey’s resources, and we show that the non-random dispersal and heterogeneous distributions of prey’s resources can affect the fates of two competitors.</div></div>","PeriodicalId":49856,"journal":{"name":"Mathematics and Computers in Simulation","volume":"230 ","pages":"Pages 131-148"},"PeriodicalIF":4.4,"publicationDate":"2024-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142700817","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-16DOI: 10.1016/j.matcom.2024.11.005
Juan Eloy Ruiz-Castro , Hugo Alaín Zapata-Ceballos
A complex multi-state redundant system undergoing preventive maintenance and experiencing multiple events is being considered in a continuous time frame. The online unit is susceptible to various types of failures, both internal and external in nature, with multiple degradation levels present, both internally and externally. Random inspections are continuously monitoring these degradation levels, and if they reach a critical state, the unit is directed to a repair facility for preventive maintenance. The maintenance place is managed by a repairperson, who follows a multiple vacation policy dependent on the operational status of the units. The repairperson is responsible for two primary tasks: corrective repair and preventive maintenance. The time durations within the system follow phase-type distributions, and the model is constructed utilizing Markovian Arrival Processes with marked arrivals. A variety of performance measures, including transient and stationary distributions, are calculated using matrix-analytic methods. This methodology allows for the representation of significant outcomes and the general behavior of the system in a matrix-algorithmic structure. To enhance the model's efficiency, both costs and rewards are incorporated into the analysis. A numerical example is presented to showcase the model's flexibility and effectiveness in real-world applications.
{"title":"Algorithmic modelling of a complex redundant multi-state system subject to multiple events, preventive maintenance, loss of units and a multiple vacation policy through a MMAP","authors":"Juan Eloy Ruiz-Castro , Hugo Alaín Zapata-Ceballos","doi":"10.1016/j.matcom.2024.11.005","DOIUrl":"10.1016/j.matcom.2024.11.005","url":null,"abstract":"<div><div>A complex multi-state redundant system undergoing preventive maintenance and experiencing multiple events is being considered in a continuous time frame. The online unit is susceptible to various types of failures, both internal and external in nature, with multiple degradation levels present, both internally and externally. Random inspections are continuously monitoring these degradation levels, and if they reach a critical state, the unit is directed to a repair facility for preventive maintenance. The maintenance place is managed by a repairperson, who follows a multiple vacation policy dependent on the operational status of the units. The repairperson is responsible for two primary tasks: corrective repair and preventive maintenance. The time durations within the system follow phase-type distributions, and the model is constructed utilizing Markovian Arrival Processes with marked arrivals. A variety of performance measures, including transient and stationary distributions, are calculated using matrix-analytic methods. This methodology allows for the representation of significant outcomes and the general behavior of the system in a matrix-algorithmic structure. To enhance the model's efficiency, both costs and rewards are incorporated into the analysis. A numerical example is presented to showcase the model's flexibility and effectiveness in real-world applications.</div></div>","PeriodicalId":49856,"journal":{"name":"Mathematics and Computers in Simulation","volume":"230 ","pages":"Pages 165-192"},"PeriodicalIF":4.4,"publicationDate":"2024-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142700824","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-16DOI: 10.1016/j.matcom.2024.11.007
Abdelkrim Chakib , Ibrahim Khalil , Azeddine Sadik
In this paper, we deal with the numerical resolution of some shape optimization models for the volume-constrained buckling and clamped plate bi-Laplacian eigenvalues problems. We propose a numerical method using the Lagrangian functional, Hadamard’s shape derivative and the gradient method combined with the finite elements discretization, to determine the minimizers for the first ten eigenvalues for both problems. We investigate also numerically the maximization of some quotient functionals, which allows us to obtain the optimal possible upper bounds of these spectral quotient problems and establish numerically some conjectures. Numerical examples and illustrations are provided for different and various cost functionals. The obtained numerical results show the efficiency and practical suitability of the proposed approaches.
{"title":"On numerical resolution of shape optimization bi-Laplacian eigenvalue problems","authors":"Abdelkrim Chakib , Ibrahim Khalil , Azeddine Sadik","doi":"10.1016/j.matcom.2024.11.007","DOIUrl":"10.1016/j.matcom.2024.11.007","url":null,"abstract":"<div><div>In this paper, we deal with the numerical resolution of some shape optimization models for the volume-constrained buckling and clamped plate bi-Laplacian eigenvalues problems. We propose a numerical method using the Lagrangian functional, Hadamard’s shape derivative and the gradient method combined with the finite elements discretization, to determine the minimizers for the first ten eigenvalues for both problems. We investigate also numerically the maximization of some quotient functionals, which allows us to obtain the optimal possible upper bounds of these spectral quotient problems and establish numerically some conjectures. Numerical examples and illustrations are provided for different and various cost functionals. The obtained numerical results show the efficiency and practical suitability of the proposed approaches.</div></div>","PeriodicalId":49856,"journal":{"name":"Mathematics and Computers in Simulation","volume":"230 ","pages":"Pages 149-164"},"PeriodicalIF":4.4,"publicationDate":"2024-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142700818","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-13DOI: 10.1016/j.matcom.2024.11.006
Xianghu Liu, Yanfang Li, Guangjun Xu
This paper is concerned with finite-time synchronization analysis for the generalized Caputo fractional spatio-temporal neural networks with time delay(GCFSTNN). The generalized Caputo type fractional derivative are defined, two novel generalized Caputo fractional differential inequalities are proved. Meanwhile, some control strategies are designed to get the finite-time synchronization results. Finally, numerical examples and simulation results are showed to demonstrate validation of finite-time synchronization conditions.
{"title":"Finite-time synchronization analysis for the generalized Caputo fractional spatio-temporal neural networks","authors":"Xianghu Liu, Yanfang Li, Guangjun Xu","doi":"10.1016/j.matcom.2024.11.006","DOIUrl":"10.1016/j.matcom.2024.11.006","url":null,"abstract":"<div><div>This paper is concerned with finite-time synchronization analysis for the generalized Caputo fractional spatio-temporal neural networks with time delay(GCFSTNN). The generalized Caputo type fractional derivative are defined, two novel generalized Caputo fractional differential inequalities are proved. Meanwhile, some control strategies are designed to get the finite-time synchronization results. Finally, numerical examples and simulation results are showed to demonstrate validation of finite-time synchronization conditions.</div></div>","PeriodicalId":49856,"journal":{"name":"Mathematics and Computers in Simulation","volume":"230 ","pages":"Pages 94-110"},"PeriodicalIF":4.4,"publicationDate":"2024-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142700816","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Precision Viticulture (PV) is becoming an active and interdisciplinary research field since it requires solving interesting research issues to concretely answer the demands of specific use cases. A challenging problem in this context is the development of automatic methods for yield estimation. Computer vision methods can contribute to the accomplishment of this task, especially those that can replicate what winemakers do manually. In this paper, an automatic artificial intelligence method for grape bunch detection from RGB images is presented. A customized Convolutional Neural Network (CNN) is employed for pointwise classification of image pixels and the dependence of classification results on the type of input color channels and grapes color properties are studied. The advantage of using additional perception-based input features, such as luminance and visual contrast, is also evaluated, as well as the dependence of the method on the choice of the training set in terms of the amount of labeled data. The latter point has a significant impact on the practical use of the method on-site, its usability by non-expert users, and its adaptability to individual vineyards. Experimental results show that a properly trained CNN can discriminate and detect grape bunches even under uncontrolled acquisition conditions and with limited computational load, making the proposed method implementable on smart devices and suitable for on-site and real-time applications.
{"title":"A perception-guided CNN for grape bunch detection","authors":"Vittoria Bruni , Giulia Dominijanni , Domenico Vitulano , Giuliana Ramella","doi":"10.1016/j.matcom.2024.11.004","DOIUrl":"10.1016/j.matcom.2024.11.004","url":null,"abstract":"<div><div>Precision Viticulture (PV) is becoming an active and interdisciplinary research field since it requires solving interesting research issues to concretely answer the demands of specific use cases. A challenging problem in this context is the development of automatic methods for yield estimation. Computer vision methods can contribute to the accomplishment of this task, especially those that can replicate what winemakers do manually. In this paper, an automatic artificial intelligence method for grape bunch detection from RGB images is presented. A customized Convolutional Neural Network (CNN) is employed for pointwise classification of image pixels and the dependence of classification results on the type of input color channels and grapes color properties are studied. The advantage of using additional perception-based input features, such as luminance and visual contrast, is also evaluated, as well as the dependence of the method on the choice of the training set in terms of the amount of labeled data. The latter point has a significant impact on the practical use of the method on-site, its usability by non-expert users, and its adaptability to individual vineyards. Experimental results show that a properly trained CNN can discriminate and detect grape bunches even under uncontrolled acquisition conditions and with limited computational load, making the proposed method implementable on smart devices and suitable for on-site and real-time applications.</div></div>","PeriodicalId":49856,"journal":{"name":"Mathematics and Computers in Simulation","volume":"230 ","pages":"Pages 111-130"},"PeriodicalIF":4.4,"publicationDate":"2024-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142700823","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号