Research article

Designing Meyer wavelet neural networks for the three-species food chain model

  • Received: 16 August 2022 Revised: 15 September 2022 Accepted: 22 September 2022 Published: 27 September 2022
  • MSC : 65K10, 92B20

  • The current research work is related to present the numerical solutions of three-species food chain model (TS-FCM) by exploiting the strength of Meyer wavelet neural networks (MWNNs) along with the global and local search competencies. The particle swarm optimization technique works as a global operator, while the sequential quadratic programming scheme is applied as a local operator for the TS-FCM. The nonlinear TS-FCM is dependent upon three categories, called consistent of prey populations, specialist predator and top predator. The optimization of an error-based fitness function is presented by using the hybrid computing efficiency of the global and local search schemes, which is designed through the differential form of the designed ordinary differential model and its initial conditions. The proposed results of the TS-FCM are calculated through the stochastic numerical techniques and further comparison is performed by the Adams method to check the exactness of the scheme. The absolute error in good ranges is performed, which shows the competency of the proposed solver. Moreover, different statistical procedures have also been used to check the reliability of the proposed stochastic procedure along with forty numbers of independent trials and 10 numbers of neurons.

    Citation: Thanasak Mouktonglang, Zulqurnain Sabir, Muhammad Asif Zahoor Raja, Saira Bhatti, Thongchai Botmart, Wajaree Weera, Chantapish Zamart. Designing Meyer wavelet neural networks for the three-species food chain model[J]. AIMS Mathematics, 2023, 8(1): 61-75. doi: 10.3934/math.2023003

    Related Papers:

    [1] Zulqurnain Sabir, Muhammad Asif Zahoor Raja, Adnène Arbi, Gilder Cieza Altamirano, Jinde Cao . Neuro-swarms intelligent computing using Gudermannian kernel for solving a class of second order Lane-Emden singular nonlinear model. AIMS Mathematics, 2021, 6(3): 2468-2485. doi: 10.3934/math.2021150
    [2] Zhimin Liu . Data-driven two-stage sparse distributionally robust risk optimization model for location allocation problems under uncertain environment. AIMS Mathematics, 2023, 8(2): 2910-2939. doi: 10.3934/math.2023152
    [3] Vikas Kumar, Nitu Kumari . Controlling chaos in three species food chain model with fear effect. AIMS Mathematics, 2020, 5(2): 828-842. doi: 10.3934/math.2020056
    [4] Ranbir Kumar, Sunil Kumar, Jagdev Singh, Zeyad Al-Zhour . A comparative study for fractional chemical kinetics and carbon dioxide CO2 absorbed into phenyl glycidyl ether problems. AIMS Mathematics, 2020, 5(4): 3201-3222. doi: 10.3934/math.2020206
    [5] Yankui Song, Bingzao Ge, Yu Xia, Shouan Chen, Cheng Wang, Cong Zhou . Low-cost adaptive fuzzy neural prescribed performance control of strict-feedback systems considering full-state and input constraints. AIMS Mathematics, 2022, 7(5): 8263-8289. doi: 10.3934/math.2022461
    [6] Jagdev Singh, Behzad Ghanbari, Ved Prakash Dubey, Devendra Kumar, Kottakkaran Sooppy Nisar . Fractional dynamics and computational analysis of food chain model with disease in intermediate predator. AIMS Mathematics, 2024, 9(7): 17089-17121. doi: 10.3934/math.2024830
    [7] Yuanyuan Cheng, Yuan Li . A novel event-triggered constrained control for nonlinear discrete-time systems. AIMS Mathematics, 2023, 8(9): 20530-20545. doi: 10.3934/math.20231046
    [8] Ailing Li, Xinlu Ye . Finite-time anti-synchronization for delayed inertial neural networks via the fractional and polynomial controllers of time variable. AIMS Mathematics, 2021, 6(8): 8173-8190. doi: 10.3934/math.2021473
    [9] Zhimin Liu, Ripeng Huang, Songtao Shao . Data-driven two-stage fuzzy random mixed integer optimization model for facility location problems under uncertain environment. AIMS Mathematics, 2022, 7(7): 13292-13312. doi: 10.3934/math.2022734
    [10] Ruyue Hu, Chi Han, Yifan Wu, Xiaohui Ai . Analysis of a stochastic Leslie-Gower three-species food chain system with Holling-II functional response and Ornstein-Uhlenbeck process. AIMS Mathematics, 2024, 9(7): 18910-18928. doi: 10.3934/math.2024920
  • The current research work is related to present the numerical solutions of three-species food chain model (TS-FCM) by exploiting the strength of Meyer wavelet neural networks (MWNNs) along with the global and local search competencies. The particle swarm optimization technique works as a global operator, while the sequential quadratic programming scheme is applied as a local operator for the TS-FCM. The nonlinear TS-FCM is dependent upon three categories, called consistent of prey populations, specialist predator and top predator. The optimization of an error-based fitness function is presented by using the hybrid computing efficiency of the global and local search schemes, which is designed through the differential form of the designed ordinary differential model and its initial conditions. The proposed results of the TS-FCM are calculated through the stochastic numerical techniques and further comparison is performed by the Adams method to check the exactness of the scheme. The absolute error in good ranges is performed, which shows the competency of the proposed solver. Moreover, different statistical procedures have also been used to check the reliability of the proposed stochastic procedure along with forty numbers of independent trials and 10 numbers of neurons.



    The two and three kinds of trophic-level study of the systems of the food chain are considered huge significant in recent years. This study is related to present the numerical solutions of three-species food chain model (TS-FCM) by introducing the Meyer wavelet neural networks (MWNNs) along with the competencies of the global and local search algorithms. The particle swarm optimization (PSO) technique works as a global operator, while the sequential quadratic programming (SQP) scheme is applied as a local operator for the TS-FCM. This nonlinear model depends upon the logistic prey P, Lotka-Volterra special predator V as well as top-predator T [1,2,3,4,5,6,7,8]. The generic form of the TS-FCM is given as [9]:

    {dP(x)dx=α0P(x)β0P2(x)λ0P(x)V(x)P(x)+δ0,P0=I1,dV(x)dx=α1V(x)+λ1P(x)V(x)δ1+P(x)λ2V(x)T(x)V(x)+δ2,V0=I2,dT(x)dx=γ3T2(x)λ3T2(x)V(x)+δ3,T0=I3. (1)

    where P0, V0 and T0 are initial population of P, V, and T, respectively. The nonlinear system (1) indicates the TS-FCM, which has been solved by using the numerical and analytical schemes based on the prey population P, that is applied as a single form of the food predator V and the top-predator T. The prey P features with the V species represents the Volterra approach modelling, which is used to reduce the population of predator exponentially when the prey is missed. The T species association along with with the V prey is achieved based on the Leslie-Gower scheme to reduce the population of the predator [10,11]. The descriptions of the TS-FCM is given in the Table 1. A good source of the information for the interested reader related with food chain model can be seen in [12,13].

    The aim of this work is to design a stochastic framework based on the MWNNs for presenting the numerical solutions of the TS-FCM. The PSO technique works as a global operator, while the SQP scheme is applied as a local operator to solve the TS-FCM. The numerical stochastic algorithms have been accomplished to solve various stiff models. To mention some of the applications that have been tackled through the stochastic solvers are smoke differential systems [14], fractional models based on the singular differential equations [15,16], dengue virus model [17], singular higher kind of systems [18,19,20] and periodic boundary value problems [21,22,23].

    Table 1.  Detail of the parameter based TS-FCM.
    Parameters Description
    α0 Specific growth rate of P
    γ3 Rate of progression of T
    δ2 Rate of exclusion of V per capita 0.5λ2
    δ3 Surplus cost in the T species to severe inadequacy of the food V
    α1 V rate that is used to decrease the P omission
    δ0,δ1 Parameters for production conservation of P
    β0 Power of competition using the individuals of species P
    λ0,λ1,λ2,λ3 Achieved maximum performances/capita by lessoning the P

     | Show Table
    DownLoad: CSV

    The aim of research work is to present the numerical solutions of three-species food chain model (TS-FCM) by exploiting the strength of Meyer wavelet neural networks (MWNNs) along with the global and local search competencies. The particle swarm optimization (PSO) technique works as a global operator, while the sequential quadratic programming (SQP) scheme is applied as a local operator. As the stochastic algorithms have been used to solve many stiff nature models, but none has applied the MWNNs using the optimization based PSO-SQP. The contributions, novelty and advantages of the designed MWNNs optimized with PSO-SQP are presented briefly as follows:

    • The stochastic numerical procedure based on the MWNN models is designed first time to solve the TS-FCM numerically.

    • The numerical results of the TS-FCM are provided by using modeling knacks of proposed MWNNs together with the competency of hybrid optimization procedures based on PSO-SQP for training/learning of networks.

    • The correctness of the approach MWNNs trained with PSO-SQP is observed with very small values of absolute error (AE) from reference numerical outcomes for solving governing relations of TS-FCM

    • The authorization, consistency and reliability of the scheme are acknowledged for larger number of runs based different statistical performances to solve the TS-FCM.

    The organization of the paper is presented as: The computational procedures of MWNNs using the optimization procedures of PSO-SQP are given in Section 2. Discussions based on the results are described in Section 3. The final remarks are listed in the last Section.

    In this section, the stochastic MWNNs using the optimization procedures of PSO-SQP is provided to solve the TS-FCM. An objective function is structured based on some necessary steps of PSO-SQP hybridization of GA-ASA is provided also in this section.

    The mathematical representations of TS-FCM with its first order derivatives are presented as:

    [ˆP(x),ˆV(x),ˆT(x)]=[qs=1yP,sQ(wP,sx+zP,s),qs=1yV,sQ(wV,sx+zV,s),qs=1yT,sQ(wT,sx+zT,s)], (2)
    [dˆPdx,dˆVdx,dˆTdx]=[qs=1yP,sddxQ(wP,sx+zX,s),qs=1yV,sddxQ(wV,sx+zV,s),qs=1yT,sddxQ(wT,sx+zT,s)].

    An unidentified vector W is defined as:

    W=[WP,WV,WT], for WP=[yP,ωP,zP], WV=[yV,ωV,zV], and WT=[yT,ωT,zT],

    where

    yP=[yP,1,yP,2,yP,3,,yP,q],yV=[yV,1,yV,2,yV,3,,yV,q],yT=[yT,1,yT,2,yT,3,,yT,q],wP=[wP,1,wP,2,wP,3,,wP,q],wV=[wV,1,wV,2,wV,3,,wV,q],wT=[wT,1,wT,2,wT,3,,wT,q],zP=[zP,1,zP,2,zP,3,,zP,q],zV=[zV,1,zV,2,zV,3,,zV,q],zT=[zT,1,zT,2,zT,3,,zT,q].

    An activation kernel using the Meyer wavelet function Q(x) as reported in [24,25] is given as:

    Q(x)=35x484x5+70x620x7. (3)

    The updated form of the Eq (2) using the above Eq (3) is given as:

    [ˆP(x),ˆV(x),ˆT(x)]=[qs=1yP,s(35(wP,sx+zP,s)484(wP,sx+zP,s)5+70(wP,sx+zP,s)620(wP,sx+zP,s)7),qs=1yV,s(35(wV,sx+zV,s)484(wV,sx+zV,s)5+70(wV,sx+zV,s)620(wV,sx+zV,s)7),qs=1yT,s(35(wT,sx+zT,s)484(wT,sx+zT,s)5+70(wT,sx+zT,s)620(wT,sx+zT,s)7)]. (4)

    A fitness function formulation is given as:

    EFit=EFit1+EFit2+EFit3+EFit4, (5)
    EFit1=1NNk=1[dˆpdx+α0ˆPk+β0ˆP2k+λ0ˆPkˆVkδ0+ˆPk]2, (6)
    EFit2=1NNk=1[dˆVdx+α1ˆVkλ1ˆPkˆVkδ1+ˆPk+λ2ˆVkˆTkδ2+ˆVk]2, (7)
    EFit3=1NNk=1[dˆTdxγ3ˆT2k+λ3ˆT2kδ3+ˆVk]2, (8)
    EFit4=13[(ˆP0I1)2+(ˆV0I2)2+(ˆT0I3)2], (9)

    here ˆPk=P(xk),ˆVk=V(xk),ˆTj=T(xk),Nh=1, and xk=kh. ˆPk, ˆVk and ˆTk are the proposed solutions. The Eqs (5)-(9) are the error functions based on the TS-FCM and the ICs. Figure 1 shows the design of the MWNNs-PSO-SQP for the TS-FCM.

    Figure 1.  Design of the MWNNs-PSO-SQP for the TS-FCM.

    In this section, the procedures of PSO and SQP are provided.

    Particle swarm optimization scheme is one of the global search methods that is used to solve the optimization model and work as an alternate of genetic algorithm (GA). PSO is introduced in the last century as a natural metaheuristic approach because of enormous optimization aptitudes in larger spans of search. PSO performs more efficiently as GA because it has a small memory. In PSO, the prime swarm intensifies in the extensive domain. To improve the parameters of PSO, the system produces optimal results iteratively that are Ph1LB for the position of swarm and Ph1GB for the velocity of swarm, shown as:

    χhl=χh1l+Vh1l, (10)
    Vhl=RVh1lh1(χh1lPh1LB)r1h2(χh1lPh1GB)r2, (11)

    where R, Xl and Vl indicate the weight vector of inertia, position, and velocity, respectively. Whereas acceleration constants are h1 and h2. Some prominent submissions of the PSO are classify imbalanced statics [26], features combination to detect the brain tumor [27], diagnosis of breast cancer [28], quality prediction in parts production processes [29], production enhancing based on the biodiesel through Microalga [30] and multilevel thresholding with the subdivision of the health image [31].

    PSO converges more reliably with the hybridization of the local SQP, which is applied to assess the adjustment of the results. SQP has been applied in various submissions, some are economic dispatch with non-smooth fuel cost function [32], economic dispatch with valve-point effect [33], power system valve-point economic dispatch problems [34], dynamic dispatch with valve-point effect [35], trajectory optimization [36], kinetic parameters of hydrogenation reactions [37], non-convex short term hydrothermal scheduling problem [38] and equality constrained optimization on Hilbert manifolds [39].

    This section narrates the statistical performances using the Theil's inequality coefficient (TIC), semi-interquartile range (SIR) and variance account for (VAF) along with the global depictions for the TS-FCM is given as:

    [TICP,TICV,TICT]=[1nnJ=1(PjˆPj)2(1nnJ=1P2j+1nnJ=1ˆP2j),1nnJ=1(VjˆVj)2(1nnJ=1V2j+1nnJ=1ˆV2j),1nnJ=1(TjˆTj)2(1nnJ=1T2j+1nnJ=1ˆT2j)], (12)
    SIR=0.5(1stQuartile3rdQuartile), (13)
    {[VAFP,VAFV,VAFT]=[(1var(PjˆPj)var(Pj))100,(1var(VjˆVj)var(Vj))100,(1var(TjˆTj)var(Tj))100,][EVAFP,EVAFV,EVAFT]=[|100VAFP,100VAFV,100VAFT|]. (14)

    where ˆP, ˆV and ˆT are the proposed solutions.

    In this section, the detailed results, and discussions of the TS-FCM based on the stochastic MWNNs-PSO-SQP procedure. The achieved numerical results based TS-FCM have been compared with the reference solutions to find the correctness of the designed MWNNs-PSO-SQP scheme. The AE plots, the performance of the scheme and convergence routines using VAF, SIR and, TIC operators have been illustrated. The simplified TS-FCM form using the appropriate parameter measures is written as:

    {dP(x)dx=1.5P(x)0.06P2(x)P(x)V(x)P(x)+10,P0=1.2,dV(x)dx=V(x)+2P(x)V(x)10+P(x)0.405V(x)T(x)V(x)+10,V0=1.2,dT(x)dx=1.5T2(x)λ3T2(x)V(x)+20,T0=1.2. (15)

    A fitness function using the TS-FCM is given as:

    EFit=1NNq=1([dˆpdx+1.5ˆPk+0.06ˆP2k+ˆPkˆVk10+ˆPk]2+[dˆVdx+ˆVk2ˆPkˆVk10+ˆPk+0.0405ˆVkˆTk10+ˆVk]2+[dˆTdx1.5ˆT2k+ˆT2k20+ˆVk]2)+13[(ˆP01.2)2+(ˆV01.2)2+(ˆT01.2)2]. (16)

    The optimization of the fitness function given in the Eq (16) based on the TS-FCM is performed using the using the proposed MWNNs under the optimization of PSO-SQP procedures. The neurons throughout this work are taken as 10 and the best weight vectors for each class of the TS-FCM is presented in the below equations. The mathematical form of these best weight vectors for each class of the TS-FCM is given as:

    ˆP(x)=3.44(35(1.7359x+3.150)484(1.7359x+3.150)5+70(1.7359x+3.150)620(1.7359x+3.150)7)1.084(35(0.2881x+0.139)484(0.2881x+0.139)5+70(0.2881x+0.139)620(0.2881x+0.139)7)0.928(35(0.518x+0.0176)484(0.518x+0.0176)5+70(0.518x+0.0176)620(0.518x0.0176)7)++1.8520(35(0.0016x+1.9229)484(0.0016x+1.9229)5+70(0.0016x+1.9229)620(0.0016x+1.9229)7), (17)
    ˆV(x)=1.4861(35(1.900x2.2698)484(1.900x2.2698)5+70(1.900x2.2698)620(1.900x2.2698)7)0.4707(35(0.4707x1.331)484(0.4707x1.331)5+70(0.4707x1.331)620(0.4707x1.331)7)0.1584(35(0.3672x+0.6896)484(0.3672x+0.6896)5+70(0.3672x+0.6896)620(0.3672x+0.6896)7)++0.2417(35(0.4986x+0.6398)484(0.4986x+0.6398)5+70(0.4986x+0.6398)620(0.4986x+0.6398)7), (18)
    ˆT(x)=2.205(35(4.7785x+2.0850)484(4.7785x+2.0850)5+70(4.7785x+2.0850)620(4.7785x+2.0850)7)0.4081(35(0.2606x+0.4083)484(0.2606x+0.4083)5+70(0.2606x+0.4083)620(0.2606x+0.4083)7)+1.6674(35(4.0804x+1.4421)484(4.0804x+1.4421)5+70(4.0804x+1.4421)620(4.0804x+1.4421)7)+2.5064(35(2.9104x+1.7957)484(2.9104x+1.7957)5+70(2.9104x+1.7957)620(2.9104x+1.7957)7), (19)

    The best values of the weights, comparison performances of the solutions and AE is illustrated in Figures 1-3 for the TS-FCM using the stochastic numerical schemes. The neurons have been taken as 10 with 30 numbers of variables for solving the TS-FCM. The calculated outcomes using the MWNNs under the optimization of PSO-SQP procedures are drawn in Figures 2(a)-(c) based on the Eqs (17)-(19) for TS-FCM. The comparison performances of the worst, best and mean outcomes is authenticated in Figures 2(d-f) for the TS-FCM. The overlapping of the results indicates that the proposed stochastic scheme for solving the model. The AE plots drawn in Figures 3(a)-(c) for each category of the TS-FCM. These plots indicate best performances based on the mean/best results. It is indicated that the best AE measures for P(x), V(x) and T(x) found as 10-06-10-08, 10-05-10-07 and 10-05-10-06, while the mean AE for P(x), V(x) and T(x) found as 10-04-10-06, 10-05-10-06 and 10-04-10-06. The performances of the operators EVAF and TIC for TS-FCM are provided in the last portion of Figure 3. For P(x), the EVAF, RMSE and TIC best values found as 10-12-10-14, 10-06-10-08 and 10-10-10-12. For V(x), these measures lie as 10-10-10-12, 10-06-10-08 and 10-10-10-11. Likewise, for T(x), these gages found as 10-10-10-12, 10-05-10-06 and 10-10-10-11. The EVAF and TIC gages together with the plots of histogram based MWNNs under the optimization of PSO-SQP procedures are drawn in Figures 4 and 5. It is seen that most of the independent runs obtained a level of accuracy for the TIC and EVAF gages for solving the TS-FCM.

    Figure 2.  Weights for each class of the TS-FCM (a)-(c) and comparison of the results (d)-(f).
    Figure 3.  AE and performances of the TIC and EVAF operators for TS-FCM.
    Figure 4.  Performances of TIC gages together with histogram based MWNNs-PSO-SQP procedures.

    Tables 2 to 4 shows the statistical operator values for each category of the TS-FCM. The statistical values based on the minimum, median, SIR, mean, maximum and standard deviation (S.D) have also been used to analyze the statistical performances of the TS-FCM by using the proposed MWNNs-PSO-SQP approach. The maximum values represent the worst runs and it is observed that the worst runs also found around 10-04 to 10-05. While the Minimum performances indicate the good trials, and it is observed that the best runs are calculated as 10-07 to 10-09. Moreover, the median, SIR, mean, and S.D values also lie around in good measures that are around 10-05 to 10-07 for each class of the TS-FCM.

    Figure 5.  Performances of EVAF gages together with histogram based MWNNs under the optimization of PSO-SQP procedures.
    Table 2.  Statistical operators for the TS-FCM based P(x) category.
    x P(x)
    Maximum Minimum Median SIR Mean S.D
    0 1.560E-05 1.306E-09 1.650E-07 2.803E-07 9.229E-07 2.631E-06
    0.1 2.770E-05 1.509E-07 4.559E-06 3.795E-06 7.108E-06 6.992E-06
    0.2 9.269E-05 5.038E-07 1.259E-05 7.821E-06 1.738E-05 1.969E-05
    0.3 1.150E-04 3.931E-07 1.013E-05 9.751E-06 1.849E-05 2.335E-05
    0.4 7.951E-05 3.019E-08 8.277E-06 6.633E-06 1.359E-05 1.580E-05
    0.5 4.894E-05 4.518E-08 7.653E-06 5.003E-06 9.726E-06 1.013E-05
    0.6 5.524E-05 9.898E-09 8.524E-06 6.815E-06 1.236E-05 1.263E-05
    0.7 1.175E-04 1.538E-07 1.341E-05 7.795E-06 2.022E-05 2.307E-05
    0.8 1.748E-04 3.748E-08 1.608E-05 1.123E-05 2.653E-05 3.456E-05
    0.9 1.547E-04 5.977E-08 1.512E-05 1.106E-05 2.473E-05 2.980E-05
    1 1.172E-04 9.026E-07 1.593E-05 1.057E-05 2.258E-05 2.325E-05

     | Show Table
    DownLoad: CSV
    Table 3.  Statistical operators for the TS-FCM based V(x) category.
    x V(x)
    Maximum Minimum Median SIR Mean S.D
    0 1.091E-04 5.175E-09 2.212E-07 2.803E-07 3.738E-06 1.725E-05
    0.1 1.170E-04 7.323E-08 8.129E-06 3.795E-06 1.059E-05 1.781E-05
    0.2 4.539E-05 1.594E-06 9.562E-06 7.821E-06 1.291E-05 9.621E-06
    0.3 4.880E-05 3.712E-07 4.250E-06 9.751E-06 9.037E-06 1.217E-05
    0.4 8.413E-05 9.092E-09 2.378E-06 6.633E-06 6.147E-06 1.379E-05
    0.5 7.417E-05 2.679E-08 2.149E-06 5.003E-06 4.553E-06 1.158E-05
    0.6 3.275E-05 1.422E-07 5.479E-06 6.815E-06 7.681E-06 7.202E-06
    0.7 2.674E-05 8.017E-08 8.815E-06 7.795E-06 9.818E-06 6.380E-06
    0.8 6.019E-05 1.700E-07 6.708E-06 1.123E-05 8.661E-06 9.564E-06
    0.9 6.621E-05 2.207E-07 2.778E-06 1.106E-05 7.858E-06 1.241E-05
    1 2.633E-05 4.242E-08 2.952E-06 1.057E-05 6.118E-06 7.030E-06

     | Show Table
    DownLoad: CSV
    Table 4.  Statistical operators for the TS-FCM based T(x) category.
    x T(x)
    Maximum Minimum Median SIR Mean S.D
    0 1.482E-05 1.405E-09 1.954E-07 2.803E-07 1.062E-06 2.705E-06
    0.1 8.653E-05 2.383E-06 2.613E-05 3.795E-06 2.933E-05 2.024E-05
    0.2 5.367E-05 1.118E-06 8.362E-06 7.821E-06 1.434E-05 1.227E-05
    0.3 4.237E-05 1.899E-08 2.918E-06 9.751E-06 5.597E-06 8.230E-06
    0.4 5.365E-05 5.482E-08 7.215E-06 6.633E-06 8.984E-06 9.045E-06
    0.5 3.816E-05 1.107E-06 1.267E-05 5.003E-06 1.347E-05 8.201E-06
    0.6 5.675E-05 8.576E-07 7.775E-06 6.815E-06 1.407E-05 1.487E-05
    0.7 5.195E-05 5.877E-07 3.459E-06 7.795E-06 1.060E-05 1.396E-05
    0.8 2.496E-05 7.648E-08 3.311E-06 1.123E-05 5.428E-06 5.716E-06
    0.9 4.198E-05 1.746E-08 4.990E-06 1.106E-05 8.954E-06 1.038E-05
    1 3.761E-05 2.332E-07 6.006E-06 1.057E-05 8.896E-06 8.509E-06

     | Show Table
    DownLoad: CSV

    The obtained good global RMSE, EVAF and TIC operator performances for the TS-FCM are described in Table 5 using forty numbers of independent executions based on the MWNNs under the PSO-SQP optimization procedures. The global Median operator are found as 10−05-10−06, 10−09-10−10, and 10−10-10−11 for RMSE, TIC and EVAF. While the global SIR is calculated as 10−06-10−07, 10−09-10−10 and 10−10-10−11 for the TS-FCM. The optimal close measures via global presentations validate the precision and precision of the MWNNs under the optimization of PSO-SQP procedures.

    Table 5.  Global representations for the TS-FCM.
    Index G. RMSE G. TIC G. EVAF
    Median SIR Median SIR Median SIR
    P(x) 1.3218E-05 8.0860E-06 5.3079E-10 3.1485E-10 4.6702E-11 6.0644E-11
    V(x) 6.5471E-06 2.6698E-07 2.5025E-09 1.0578E-09 4.6200E-10 4.8615E-10
    T(x) 1.1708E-05 5.5292E-06 4.3169E-10 2.2095E-10 9.9967E-10 9.1617E-10

     | Show Table
    DownLoad: CSV

    The current investigations are related to examine the numerical simulations of nonlinear three-species food chain system by exploiting the strength of Meyer wavelet neural networks along with the global and local search competencies. Few concluding remarks are presented as:

    • The stochastic numerical procedure using the MWNNs is presented first time for the TS-FCM numerically.

    • The correctness of the MWNNs-PSO-SQP is authenticated via the overlapping of the proposed and reference results.

    • The AE measures is calculated in good performances for each class of the TS-FCM, i.e., 10-06-10-08.

    • The reliability of the stochastic MWNNs-PSO-SQP approach is approved by taking a large number of trials for the TS-FCM.

    • The statistical TIC and EVAF operators have been used to check the convergence of the MWNNs-PSO-SQP approach.

    • The minimum, median, SIR, mean, maximum and standard deviation have also been used to analyze the statistical performances of the TS-FCM by using the proposed MWNNs-PSO-SQP approach.

    • The global representations are presented based on the median and SIR operators for solving the TS-FCM.

    In future, the designed MWNNs trained/learned with PSO-SQP scheme should be implemented to solve patchy model [40], stage-structured models [41], and longer food chain systems [42] as well as other stiff nonlinear systems.

    The research is partially supported by Chiang Mai University. This research received funding support from the NSRF via the Program Management Unit for Human Resources and Institutional Development, Research and Innovation (Grant number B05F650018).

    The authors declare that there is no conflict of interests regarding the publication of this paper.



    [1] H. M. El-Owaidy, A. A. Ragab, M. Ismail, Mathematical analysis of a food-web model, Appl. Math. Comput., 121 (2001), 155–167. https://doi.org/10.1016/S0096-3003(99)00269-6 doi: 10.1016/S0096-3003(99)00269-6
    [2] Y. A. Kuznetsov, S. Rinaldi, Remarks on food chain dynamics, Math. Biosci., 134 (1996), 1–33. https://doi.org/10.1016/0025-5564(95)00104-2 doi: 10.1016/0025-5564(95)00104-2
    [3] F. Wang, M. N. Khan, I. Ahmad, H. Ahmad, H. Abu-Zinadah, Y. M. Chu, Numerical solution of traveling waves in chemical kinetics: time-fractional Fishers equations, Fractals, 30 (2022), 2240051. https://doi.org/10.1142/S0218348X22400515 doi: 10.1142/S0218348X22400515
    [4] H. I. Freedman, J. H. So, Global stability and persistence of simple food chains, Math. Biosci., 76 (1985), 69–86. https://doi.org/10.1016/0025-5564(85)90047-1 doi: 10.1016/0025-5564(85)90047-1
    [5] H. I. Freedman, P. Waltman, Mathematical analysis of some three-species food-chain models, Math. Biosci., 33 (1977), 257–276. https://doi.org/10.1016/0025-5564(77)90142-0 doi: 10.1016/0025-5564(77)90142-0
    [6] Z. Sabir, Stochastic numerical investigations for nonlinear three-species food chain system, Int. J. Biomath., 15 (2021), 2250005. https://doi.org/10.1142/S179352452250005X doi: 10.1142/S179352452250005X
    [7] S. Muratori, S. Rinaldi, Low-and high-frequency oscillations in three-dimensional food chain systems, SIAM J. Appl. Math., 52 (1992), 1688–1706. https://doi.org/10.1137/0152097 doi: 10.1137/0152097
    [8] M. Umar, Z. Sabir, M. A. Z. Raja, Intelligent computing for numerical treatment of nonlinear prey–predator models, Appl. Soft Comput., 80 (2019), 506–524. https://doi.org/10.1016/j.asoc.2019.04.022 doi: 10.1016/j.asoc.2019.04.022
    [9] Z. Sabir, Stochastic numerical investigations for nonlinear three-species food chain system, Int. J. Biomath., 15 (2022), 2250005. https://doi.org/10.1142/S179352452250005X doi: 10.1142/S179352452250005X
    [10] P. H. Leslie, J. C. Gower, The properties of a stochastic model for the predator-prey type of interaction between two species, Biometrika, 47 (1960), 219–234. https://doi.org/10.2307/2333294 doi: 10.2307/2333294
    [11] R. K. Upadhyay, S. R. K. Iyengar, V. Rai, Chaos: An ecological reality? Int. J. Bifurcat. Chaos, 8 (1998), 1325–1333. https://doi.org/10.1142/S0218127498001029 doi: 10.1142/S0218127498001029
    [12] A. Hastings, T. Powell, Chaos in a three‐species food chain, Ecology, 72 (1991), 896–903. https://doi.org/10.2307/1940591 doi: 10.2307/1940591
    [13] H. Y. Jin, Z. A. Wang, L. Wu, Global dynamics of a three-species spatial food chain model, J. Differ. Equ., 333 (2022), 144–183. https://doi.org/10.1016/j.jde.2022.06.007 doi: 10.1016/j.jde.2022.06.007
    [14] Z. Sabir, M. A. Z. Raja, A. S. Alnahdi, M. B. Jeelani, M. A. Abdelkawy, Numerical investigations of the nonlinear smoke model using the Gudermannian neural networks, Math. Biosci. Eng., 19 (2022), 351–370. https://doi.org/10.3934/mbe.2022018 doi: 10.3934/mbe.2022018
    [15] Z. Sabir, M. A. Z. Raja, J. L. G. Guirao, M. Shoaib, A novel design of fractional Meyer wavelet neural networks with application to the nonlinear singular fractional Lane-Emden systems, Alex. Eng. J., 60 (2021), 2641–2659. https://doi.org/10.1016/j.aej.2021.01.004 doi: 10.1016/j.aej.2021.01.004
    [16] Z. Sabir, M. A. Z. Raja, D. Baleanu, Fractional Mayer Neuro-swarm heuristic solver for multi-fractional Order doubly singular model based on Lane-Emden equation, Fractals, 29 (2021), 2140017. https://doi.org/10.1142/S0218348X2140017X doi: 10.1142/S0218348X2140017X
    [17] M. Umar, Z. Sabir, M. A. Z. Raja, Y. G. Sánchez, A stochastic numerical computing heuristic of SIR nonlinear model based on dengue fever, Results Phys., 19 (2020), 103585. https://doi.org/10.1016/j.rinp.2020.103585 doi: 10.1016/j.rinp.2020.103585
    [18] Z. Sabir, S. Saoud, M. A. Z. Raja, H. A. Wahab, A. Arbi, Heuristic computing technique for numerical solutions of nonlinear fourth order Emden–Fowler equation, Math. Comput. Simulat., 178 (2020), 534–548. https://doi.org/10.1016/j.matcom.2020.06.021 doi: 10.1016/j.matcom.2020.06.021
    [19] Z. Sabir, M. A. Z. Raja, J. L. G. Guirao, M. Shoaib, Integrated intelligent computing with neuro-swarming solver for multi-singular fourth-order nonlinear Emden–Fowler equation, Comput. Appl. Math., 39 (2020), 307. https://doi.org/10.1007/s40314-020-01330-4 doi: 10.1007/s40314-020-01330-4
    [20] Z. Sabir, M. A. Z. Raja, M. Umar, M. Shoaib, Design of neuro-swarming-based heuristics to solve the third-order nonlinear multi-singular Emden–Fowler equation, Eur. Phys. J. Plus, 135 (2020), 410. https://doi.org/10.1140/epjp/s13360-020-00424-6 doi: 10.1140/epjp/s13360-020-00424-6
    [21] Z. Sabir, M. A. Z. Raja, J. L. G. Guirao, M. Shoaib, A neuro-swarming intelligence-based computing for second order singular periodic non-linear boundary value problems, Front. Phys., 8 (2020), 224. https://doi.org/10.3389/fphy.2020.00224 doi: 10.3389/fphy.2020.00224
    [22] Y. Che, M. Y. A. Keir, Study on the training model of football movement trajectory drop point based on fractional differential equation, Appl. Math. Nonlinear Sci., 7 (2022), 425–430. https://doi.org/10.2478/amns.2021.2.00095 doi: 10.2478/amns.2021.2.00095
    [23] Z. Sabir, C. M. Khalique, M. A. Z. Raja, D. Baleanu, Evolutionary computing for nonlinear singular boundary value problems using neural network, genetic algorithm and active-set algorithm, Eur. Phys. J. Plus, 136 (2021), 195. https://doi.org/10.1140/epjp/s13360-021-01171-y doi: 10.1140/epjp/s13360-021-01171-y
    [24] Z. Sabir, M. A. Z. Raja, J. L. G. Guirao, T. Saeed, Meyer wavelet neural networks to solve a novel design of fractional order pantograph Lane-Emden differential model, Chaos Soliton. Fract., 152 (2021), 111404. https://doi.org/10.1016/j.chaos.2021.111404 doi: 10.1016/j.chaos.2021.111404
    [25] Z. Sabir, M. A. Z. Raja, M. Umar, M. Shoaib, D. Baleanu, FMNSICS: Fractional Meyer neuro-swarm intelligent computing solver for nonlinear fractional Lane–Emden systems, Neural Comput. Appl, 34 (2022), 4193–4206. https://doi.org/10.1007/s00521-021-06452-2 doi: 10.1007/s00521-021-06452-2
    [26] J. Li, Y. Wu, S. Fong, A. J. Tallón-Ballesteros, X. S. Yang, S. Mohammed, et al., A binary PSO-based ensemble under-sampling model for rebalancing imbalanced training data, J. Supercomput., 78 (2022), 7428–7463. https://doi.org/10.1007/s11227-021-04177-6 doi: 10.1007/s11227-021-04177-6
    [27] M. Sharif, J. Amin, M. Raza, M. Yasmin, S. C. Satapathy, An integrated design of particle swarm optimization (PSO) with fusion of features for detection of brain tumor, Pattern Recogn. Lett., 129 (2020), 150–157. https://doi.org/10.1016/j.patrec.2019.11.017 doi: 10.1016/j.patrec.2019.11.017
    [28] S. Shahbeig, M. S. Helfroush, A. Rahideh, A fuzzy multi-objective hybrid TLBO–PSO approach to select the associated genes with breast cancer, Signal Process., 131 (2017), 58–65. https://doi.org/10.1016/j.sigpro.2016.07.035 doi: 10.1016/j.sigpro.2016.07.035
    [29] Y. Su, L. Han, J. Wang, H. Wang, Quantum‐behaved RS‐PSO‐LSSVM method for quality prediction in parts production processes, Concurr. Comput. Pract. Exp., 34 (2022), e5522. https://doi.org/10.1002/cpe.5522 doi: 10.1002/cpe.5522
    [30] M. A. Abdelkareem, H. Rezk, E. T. Sayed, A. Alaswad, A. M. Nassef, A. G. Olabi, Data on fuzzy logic based-modelling and optimization of recovered lipid from microalgae, Data Brief, 28 (2020), 104931. https://doi.org/10.1016/j.dib.2019.104931 doi: 10.1016/j.dib.2019.104931
    [31] M. Maitra, A. Chatterjee, A hybrid cooperative–comprehensive learning based PSO algorithm for image segmentation using multilevel thresholding, Expert Syst. Appl., 34 (2008), 1341–1350. https://doi.org/10.1016/j.eswa.2007.01.002 doi: 10.1016/j.eswa.2007.01.002
    [32] P. Attaviriyanupap, H. Kita, E. Tanaka, J. Hasegawa, A hybrid EP and SQP for dynamic economic dispatch with nonsmooth fuel cost function, IEEE T. Power Syst., 17 (2002), 411–416. https://doi.org/10.1109/TPWRS.2002.1007911 doi: 10.1109/TPWRS.2002.1007911
    [33] T. A. A. Victoire, A. E. Jeyakumar, Hybrid PSO–SQP for economic dispatch with valve-point effect, Electr. Pow. Syst. Res., 71 (2004), 51–59. https://doi.org/10.1016/j.epsr.2003.12.017 doi: 10.1016/j.epsr.2003.12.017
    [34] J. S. Alsumait, J. K. Sykulski, A. K. Al-Othman, A hybrid GA–PS–SQP method to solve power system valve-point economic dispatch problems, Appl. Energ., 87 (2010), 1773–1781. https://doi.org/10.1016/j.apenergy.2009.10.007 doi: 10.1016/j.apenergy.2009.10.007
    [35] T. A. A. Victoire, A. E. Jeyakumar, A modified hybrid EP–SQP approach for dynamic dispatch with valve-point effect, Int. J. Elec. Power, 27 (2005), 594–601. https://doi.org/10.1016/j.ijepes.2005.06.006 doi: 10.1016/j.ijepes.2005.06.006
    [36] P. E. Gill, W. Murray, M. A. Saunders, Large-scale SQP methods and their application in trajectory optimization, In: Computational optimal control, Switzerland: Birkhä user Basel, 1994, 29–42. https://doi.org/10.1007/978-3-0348-8497-6_3
    [37] B. Mansoornejad, N. Mostoufi, F. Jalali-Farahani, A hybrid GA–SQP optimization technique for determination of kinetic parameters of hydrogenation reactions, Comput. Chem. Eng., 32 (2008), 1447–1455. https://doi.org/10.1016/j.compchemeng.2007.06.018 doi: 10.1016/j.compchemeng.2007.06.018
    [38] S. Sivasubramani, K. S. Swarup, Hybrid DE–SQP algorithm for non-convex short term hydrothermal scheduling problem, Energ. Convers. Manage., 52 (2011), 757–761. https://doi.org/10.1016/j.enconman.2010.07.056 doi: 10.1016/j.enconman.2010.07.056
    [39] A. Schiela, J. Ortiz, An SQP method for equality constrained optimization on Hilbert manifolds, SIAM J. Optim., 31 (2021), 2255–2284. https://doi.org/10.1137/20M1341325 doi: 10.1137/20M1341325
    [40] N. Bajeux, B. Ghosh, Stability switching and hydra effect in a predator–prey metapopulation model, Biosystems, 198 (2020), 104255. https://doi.org/10.1016/j.biosystems.2020.104255 doi: 10.1016/j.biosystems.2020.104255
    [41] B. Ghosh, O. L. Zhdanova, B. Barman, E. Y. Frisman, Dynamics of stage-structure predator-prey systems under density-dependent effect and mortality, Ecol. Complex., 41 (2020), 100812. https://doi.org/10.1016/j.ecocom.2020.100812 doi: 10.1016/j.ecocom.2020.100812
    [42] D. Pal, B. Ghosh, T. K. Kar, Hydra effects in stable food chain models, Biosystems, 185 (2019), 104018. https://doi.org/10.1016/j.biosystems.2019.104018 doi: 10.1016/j.biosystems.2019.104018
  • This article has been cited by:

    1. A. A. Alderremy, J. F. Gómez-Aguilar, Zulqurnain Sabir, Shaban Aly, J. E. Lavín-Delgado, José R. Razo-Hernández, Numerical performances based artificial neural networks to deal with the computer viruses spread on the complex networks, 2024, 101, 0020-7160, 314, 10.1080/00207160.2024.2326926
    2. Daniel Andrade Girón , William Marín-Rodriguez, Edgardo Carreño Cisneros , Marcelo Zuñiga Rojas , Irina Calvo Rivera , Systems Development: a Holistic Vision in Health Science, 2023, 3, 2796-9711, 394, 10.56294/saludcyt2023394
    3. Kottakkaran Sooppy Nisar, Rafia Tabassum, Muhammad Asif Zahoor Raja, Muhammad Shoaib, Advanced Bio-Inspired computing paradigm for nonlinear smoking model, 2023, 76, 11100168, 411, 10.1016/j.aej.2023.06.032
    4. Manal Alqhtani, J.F. Gómez-Aguilar, Khaled M. Saad, Zulqurnain Sabir, Eduardo Pérez-Careta, A scale conjugate neural network learning process for the nonlinear malaria disease model, 2023, 8, 2473-6988, 21106, 10.3934/math.20231075
    5. Syed Ali Asghar, Hira Ilyas, Shafaq Naz, Muhammad Asif Zahoor Raja, Iftikhar Ahmad, Muhammad Shaoib, Intelligent predictive computing for functional differential system in quantum calculus, 2024, 15, 1868-5137, 2153, 10.1007/s12652-023-04744-0
    6. Muhammad Shoaib, Saba Kainat, Areej Abdullah Alabduljabbar, Kottakkaran Sooppy Nisar, Muhammad Asif Zahoor Raja, Integrated intelligent neuro-evolutionary computing approach to study SEIRC model representing campylobacteriosis transmission dynamics, 2025, 33, 2769-0911, 10.1080/27690911.2024.2441257
  • Reader Comments
  • © 2023 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)
通讯作者: 陈斌, bchen63@163.com
  • 1. 

    沈阳化工大学材料科学与工程学院 沈阳 110142

  1. 本站搜索
  2. 百度学术搜索
  3. 万方数据库搜索
  4. CNKI搜索

Metrics

Article views(2135) PDF downloads(174) Cited by(6)

Figures and Tables

Figures(5)  /  Tables(5)

/

DownLoad:  Full-Size Img  PowerPoint
Return
Return

Catalog