ArticlePDF Available

An Improved Artificial Intelligence Based on Gray Wolf Optimization and Cultural Algorithm to Predict Demand for Dairy Products: A Case Study

Authors:

Abstract and Figures

This paper provides an integrated framework based on statistical tests, time series neural network and improved multi-layer perceptron neural network (MLP) with novel meta-heuristic algorithms in order to obtain best prediction of dairy product demand (DPD) in Iran. At first, a series of economic and social indicators that seemed to be effective in the demand for dairy products is identified. Then, the ineffective indices are eliminated by using Pearson correlation coefficient, and statistically significant variables are determined. Then, MLP is improved with the help of novel meta-heuristic algorithms such as gray wolf optimization and cultural algorithm. The designed hybrid method is used to predict the DPD in Iran by using data from 2013 to 2017. The results show that the MLP offers 71.9% of the coefficient of determination, which is better compared to the other two methods if no improvement is achieved.
Content may be subject to copyright.
- 1 -
Please cite this article in press as:



I. 
D        


         

        
         

.
        

         
    
important .
         
       
        
         
         

      
    
.
         

           
        
         
compare to traditional methods. Several main related research in this

Keywords
A


Regression, Time-series

Abstract

             
         

     







, Hassan Khademi Zare, Ahmad Sadeghieh


Received 20 December 2018 | Accepted 12 January 2019 | Published 8 March 2019


DOI: 10.9781/ijimai.2019.03.003
- 2 -
International Journal of Interactive Multimedia and Artificial Intelligence
II. 

 have developed
         
           have
      

   




        
         
         

      
   
      


         
  
 to improve the



  
      
   


      
         
        


           

  

III. 
        
         
           
         


        


xf xw
h
hh

 
xhhth
whohth hidden
oth
            

x
xw
hhh
0
0
1
1


exp 
           


MSE
nyo
i
n
ii


12
 
Ryo
yy
i
ii
i
i
2
2
2
1


 
MAEn
yo
i
n
ii

 
            
         
       

      
.

          
          
          
      

 

           
algorithms.
A. Prediction Network Optimization

         


- 3 -
Article in Press
       
        
         
         







   Y      
O


         

algorithms are expressed.
IV. 
A. Gray Wolf Optimization
        


   

       






    

   

1. Social Behavior of Wolves
    
     
         

            

2. Turning Around the Prey

.
 
 

            
  

rrur r
Aa
ra
21
. 
rur
Cr
=22
. 
 
and r and r are random vectors.
3. Detecting the Position of the Prey
       
         

      


DC
1
 
DC
XX

uruu uruuruu r

2
.,
 
DC
3
 
ruruu urur
XXAD
11



.,
 
ruruu urur
XXAD
21



.,
 
ruruu urur
XXAD
31



.,
 

Xt XXX


13
123
 
           


    








5: repeat










.
- 4 -
International Journal of Interactive Multimedia and Artificial Intelligence
B. Cultural Algorithm (CA)
        .
   
        
        





     


     
      
      

  


1. Population Space


2. Belief Space
          


       
     
         
         
 

         

     
     
  
.
yt St Nt

 


 


3. Positional or Situational Knowledge
         

      

 
4. Normative Knowledge (Criterion)
   
        
the space is competitive, norms take a proper shape and . This
         
        
.
NXXX X
n
(}
123
,,,,  
XluLU
iiii i

   
 
li and ui   th dimension,
Li and Ui


5. Admission Function



.
n
n
t
s
 
nsγ
t
6. Effect Function
         
          
  
.
 

ij j
max
j
min
txtx t



 






5. Repeat
 

 
 
 


V. 
     , the
         
         
           
            

- 5 -
Article in Press
    
           
          



DescriptionPeriod
General price increase rates







PPI




DPI


areas









AMPAverage milk price












AAGI

income







This index determines the



IPI

index
Indicates the change in the


IPI

index

VI. 
 

         
        


   




Pearson correlationParameter



PPI
DPI
AMP


AAGI


IPI


     


   



  Std. error  
    
    
    
PPI    
AMP    
    
    
    
    

            
      
         
 
         
       

 
  



- 6 -
International Journal of Interactive Multimedia and Artificial Intelligence
     
   


 
          

      
            
           


       

predictions.

          



         
        
          
       
           






A. Significant Variables Prediction


   
    
 


CPIfCPICPI CPICPI CPI
tttt
tt

 1
2345
,,,,  
IN fINININININ
tttt
tt

 1
2345
,,,,  
PPI fPPI PPI PPI PPI PPI
tttt
tt

 1
2345
,,,,  
AMPfAMPAMP AMPAMP AMP
tttt
tt

 1
2345
,,,,  
POPfPOPPOP POPPOP POP
tttt
tt

 1
2345
,,,,  
 
LPIfLPILPI CPILPI LPI
tttt
tt

 12
345
,,,,  
GC fGCGCGCGCGC
tttt
tt

 1
2345
,,,,  





   

    





TotalTestTrain
R
R
R



PPI

AMP



          



          
        
  

         

         
  


- 7 -
Article in Press

             

         



          
           

.



          

        
          
      

    
    
data and predictions.
B. DDP Prediction Using Hybrid MLP
  


     
          


      



0.94760.01270.0941



          
   
         
           
   







         
     












VII. 
         
        
- 8 -
International Journal of Interactive Multimedia and Artificial Intelligence
Alireza Goli
       
     
       
  
      
         
        
        

Hasan Khademi Zare
       


      
        

Ahmad Sadeghieh
 
        
    
      
        

Reza Tavakkoli-Moghaddam
      
     
         
     
     



   
   
         
        

         

       






         
            







         
       

          
         

         
        
       

  
          

 

         

 


  

       

           
        

 
    
         

 

         
       

 



 

        

         
 

         
        
        

      

       
        

 
        
        

           
        

 
       

         
 

... GWO can be used to solve complex optimization issues in engineering (Yu et al. 2020;Xu et al. 2020;Choopan and Emami 2019). Gray wolves are classified as Canidae and have extremely precise class hierarchies that is divided into four groups based on their abilities (see figure 2), including alpha (α), beta (β), delta (δ) and omega (ω) wolves (Purushothaman et al. 2020;Emary et al. 2017;Mirjalili et al. 2014;Emami et al. 2018;Goli et al. 2019;Onyelowe et al. 2022). ...
... The process of the GWO algorithm is shown in Figure 3 and is repeated until it reaches the stop criterion. The exact formula for GWO is described in the literature (Mirjalili et al. 2014;Lawal et al. 2021a;Xu et al. 2020;Onyelowe et al. 2022;Yu et al. 2020;Emary et al. 2017;Goli et al. 2019;Purushothaman et al. 2020). ...
Article
Flyrock is known as one of the main problems in open pit mining operations. This phenomenon can threaten the safety of mine personnel, equipment and buildings around the mine area. One way to reduce the risk of accidents due to flyrock is to accurately predict that the safe area can be identified and also with proper design of the explosion pattern, the amount of flyrock can be greatly reduced. For this purpose, 14 effective parameters on flyrock have been selected in this paper i.e. burden, blasthole diameter, sub-drilling, number of blastholes, spacing, total length, amount of explosives and a number of other effective parameters, predicting the amount of flyrock in a case study, Songun mine, using linear multivariate regression (LMR) and artificial intelligence algorithms such as Gray Wolf Optimization algorithm (GWO), Moth-Flame Optimization algorithm (MFO), Whale Optimization Algorithm (WOA), Ant Lion Optimizer (ALO) and Multi-Verse Optimizer (MVO). Results showed that intelligent algorithms have better capabilities than linear regression method and finally method MVO showed the best performance for predicting flyrock. Moreover, the results of the sensitivity analysis show that the burden, ANFO, total rock blasted, total length and blast hole diameter are the most significant factors to determine flyrock, respectively, while dynamite has the lowest impact on flyrock generation.
... On the one hand, this approach makes it possible to consider the genetic structure. On the other hand, the connection between genetic markers and some quantitative traits under different production conditions has not always been considered [28][29][30][31]. The use of phenotypic distances makes it possible to solve this problem and reflects the final result of the genotype-environment interaction [32][33][34][35][36]. ...
Article
Full-text available
Background and Aim The aim of any breeding process is to create a herd based on certain parameters that reflect an ideal animal vision. Targeted herding involves selecting the source of breeding material to be imported from another country. Therefore, there is a problem in selecting a breeding material importer to rapidly form a uterine canopy with the required properties. The purpose of this study was to evaluate a set of predictive milk productivity traits in Holstein cattle across countries. Materials and Methods This research was based on records of 819,358 recorded animals from 28 countries born after January 1, 2018, from open databases. We used the Euclidean metric to construct dendrograms characterizing the similarity of countries according to the complex milk productivity traits of the daughters of bulls. The Ward method was used to minimize intracluster variance when forming clusters and constructing the corresponding diagrams. Principal component analysis was used to reduce dimensionality and eliminate the effect of multicollinearity. The principal components were selected using the Kaiser–Harris criteria. Results A ranking of multidimensional complex milk productivity traits in different countries over the past 5 years was performed. A group of leading countries led by the USA was established according to the studied indicators, and the possible reasons for such a division into groups were described. Conclusion The pressure of purposeful artificial selection prevails in comparison with the pressure of natural selection concerning milk productivity traits in a certain group of countries, which allows specialists to choose suppliers when buying breeding animals and materials. The findings are based solely on data from recorded animals, which may not represent the entire breed population within each country, especially in regions where record-keeping may be inconsistent. It is expected that further studies will include regional data from large enterprises not part of Interbull, with mandatory verification and validation. An important element of such work is seen as the ability to compare the milk productivity of populations from different countries using a different scale, as well as studying the differentiation of countries by other selection traits of dairy
... Omega wolves are the last group permitted to eat; in other words, they are the self-sacrificing members. In addition to alpha, beta, and omega wolves, other wolves in the group are sentinels and scouts of the group (delta wolfs) [60]. During optimization, alpha is always assumed to be the most preproperate solution. ...
... It simulates the social behavior of grey wolf for hunting prey which is a swarm intelligence algorithm based on leadership hierarchy. The application of GWO has been greatly active in the literature and related engineering fields [13][14][15][16][17][18]. In this study, customized GWO is designed to cope with problems in pickup (from supply nodes to hubs) and delivery processes (from hubs to demand nodes) within a hub-andspoke transportation network. ...
Article
When COVID-19 suddenly broke out, the epidemic areas are short of basic emergency relief which need to be transported from surrounding areas. To make transportation both time-efficient and cost-effective, we consider a multimodal hub-and-spoke transportation network for emergency relief schedules. Firstly, we establish a mixed integer nonlinear programming (MINLP) model considering multi-type emergency relief and multimodal transportation. The model is a bi-objective one that aims at minimizing both transportation time consumption and transportation costs. Due to its NP-hardness, devising an efficient algorithm to cope with such a problem is challenging. This study thus employs and redesigns Grey Wolf Optimizer (GWO) to tackle it. To benchmark our algorithm, a real-world case is tested with three solution methods which include other two state-of-the-art meta-heuristics. Results indicate that the customized GWO can solve such a problem in a reasonable time with higher accuracy. The research could provide significant practical management insights for related government departments and transportation companies on designing an effective transportation network for emergency relief schedules when faced with the unexpected COVID-19 pandemic.
Chapter
CAs have been employed to solve a variety of problems in other branches of science, such as computer, physical, social, and biological sciences. The main aim of this chapter is to review the problems in these areas and discuss related mathematical formulations.
Chapter
CAs are EAs modelled based on the biocultural evolutionary theory in real societies. The idea of using multiple sources of knowledge during the search process has emerged with the development of CAs. They model a dual inheritance system observed from the human cultural evolution, in which the belief space represents the macro-evolutionary level and the population space performs the micro-evolutionary level. The belief space includes a network of knowledge components obtained from the evolution process of individuals in the population space, in which each knowledge category represents a collection of problem-specific information. This chapter presents the basic definitions, framework, operators, and formulations of CAs.KeywordsCultural algorithmsBelief spaceKnowledgeCommunication protocols
Article
Full-text available
All over the world, the real estate sector under construction industry is one of the most hazardous sectors. The jobs consist of high risks like accidents, fatalities, and injuries. Working with height, excavation, dust, noise, heavy machinery, and modern gadgets all are playing an extensive role in the work environment of the real estate sector. Over the past few years in developing and underdeveloped countries, construction work has increased. With the development of these sectors, occupational hazards, accidents, etc. are also getting increased. To focus on Real Estate 4.0, the study emphasizes health and safety performance with the integration of artificial intelligence. As Real Estate 4.0 becomes more real, it will lead to a new series of paradigm shifts. In this study, the authors have highlighted the new industrial health and safety issues and management based on an adaptation of various aspects of artificial intelligence.
Book
This comprehensive reference text discusses nature inspired algorithms and their applications. It presents the methodology to write new algorithms with the help of MATLAB programs and instructions for better understanding of concepts. It covers well-known algorithms including evolutionary algorithms, genetic algorithm, particle Swarm optimization and differential evolution, and recent approached including gray wolf optimization. A separate chapter discusses test case generation using techniques such as particle swarm optimization, genetic algorithm, and differential evolution algorithm. The book-• Discusses in detail various nature inspired algorithms and their applications; • Provides MATLAB programs for the corresponding algorithm; • Presents methodology to write new algorithms; • Examines well-known algorithms like the genetic algorithm, particle swarm optimization and differential evolution, and recent approaches like gray wolf optimization; • Provides conceptual linking of algorithms with theoretical concepts. The text will be useful for graduate students in the field of electrical engineering, electronics engineering, computer science and engineering. Discussing nature inspired algorithms and their applications in a single volume, this text will be useful as a reference text for graduate students in the field of electrical engineering, electronics engineering, computer science and engineering. It discusses important algorithms including deterministic algorithms, randomized algorithms, evolutionary algorithms, particle swarm optimization, big bang big crunch (BB-BC) algorithm, genetic algorithm and grey wolf optimization algorithm.
Article
In the business sector, predicting the movement of the Stock Exchange of Thailand (SET) index is challenging. Due to worldwide stock market fluctuations, investors commonly invest in price-changing businesses solely in the long term. Therefore, an accurate SET index movement prediction method is significant for investment purposes and has been the goal of many previous studies. Some studies have indicated that neural network (NN) models perform more effectively and accurately than traditional statistical models; accordingly, NNs employing backpropagation (BP) with sigmoid and smooth adaptive activation functions (SAAFs) and 10 metaheuristic algorithms to determine the initial prediction weights were developed in this study. An experiment was conducted using a Thailand SET50 index dataset, and the results revealed that the model utilizing SAAFs with a cultural algorithm (CA) for weight initialization yielded more precise and efficient predictions than those of other competing models. This finding indicated the possibility of applying the proposed method for SET index movement prediction in the future.
Article
Full-text available
During the past few decades, many researchers have studied the issue of air travel demand in different countries. On the other hand, the development of airports requires considerable space in the vicinity of cities which needs planning and huge investment. However, development of air travel through different airports will be affected by various factors such as population growth and economic development. The purpose of this study is to predict air travel demand in Iran. Data were provided by the Civil Aviation Organization of Islamic Republic of Iran from 2011 to 2015. Collected information includes airports of the country and destination cities all across the country. For this purpose, the artificial neural network (ANN) is used to predict the air travel demand by considering income elasticity and population size in each zone. Evolutionary meta-heuristic algorithms have been implemented in order to improve the performance of ANN. Bat and Firefly algorithms are new meta-heuristic algorithms which have been examined in this study. The results show that the use of these algorithms increases adaptation rate of neural network (NN) prediction with real data. The coefficient of determination increases from 0.2 up to about 0.9 while using the meta-heuristics NN. This represents the high rate of efficiency using this new method.
Article
Full-text available
Purpose The principal concern of organization managers in the global rivalry of commerce environment is how to select the project portfolio among available projects. In this matter, organizations should consider the uncertainty intrinsic in the projects regarding an appropriate valuation technique within an optimization framework. In this research, the purpose of this paper is to formulate using a robust optimization algorithm to deal with the complexities and uncertainty inherent in the construction of the project portfolio. Design/methodology/approach First, a general mathematical formulation is presented, which in compound real options valuation is highlighted. This formulation gives managerial flexibility by correcting the deficiency of traditional discounted cash flow technique that excludes any form of flexibility. Then, considering a limitation on budget of the organization, an integer programming formulation to maximize the n-fold compound options for project portfolio selection is proposed. Finally, a robust optimization model is developed along with the robust combinatorial optimization algorithm, which is effective for solving problems under uncertainty. Findings Sensitivity analysis showed that projects in later phases of development, having survived several phases of pre-clinical and clinical tests, are worth more because they are more likely to pertain to business. However, the investment costs related to each project during development phases limit the number of projects that a company can bring to their final portfolio. Additionally, the analysis of conservatism level represented how project managers can quite easily determine their risk attitude and the corresponding portfolio composition. From a managerial point of view, the proposed framework is very useful because it requires only financial estimates. Hence, the proposed decision support tool can assist research and development (R&D) project managers in the pharmaceutical industry for making decisions. Originality/value The first is the application of the n-fold compound options on portfolio of R&D projects and the employment of compound options value of a project portfolio as an objective function. The second one is a mathematical formulation of these concepts and solving it by the robust combinatorial optimization algorithm. The literature is lacking in the application of the robust combinatorial optimization algorithm to R&D project portfolio selection based on the generalized n-fold compound option model of Cassimon et al. (2004). Every framework from calculation of the n-fold compound option to solving robust combinatorial algorithm is programmed in Matlab software, since it can be used as a business support tool.
Article
Full-text available
Efficient management of a drinking water network reduces the economic costs related to water production and transport (pumping). Model predictive control (MPC) is nowadays a quite well-accepted approach for the efficient management of the water networks because it allows formulating the control problem in terms of the optimization of the economic costs. Therefore, shortterm forecasts are a key issue in the performance of MPC applied to water distribution networks. However, the short-term horizon demand forecast in a horizon of 24 hours in an hourly based scale presents some challenges as the water consumption can change from one day to another, according to certain patterns of behavior (e.g., holidays and business days). This paper focuses on the problem of forecasting water demand for the next 24 hours. In this work, we propose to use a bank of models instead of a single model. Each model is designed for forecasting one particular hour. Hourly models use artificial neural networks. The architecture design and the training process are performed using genetic algorithms. The proposed approach is assessed using demand data from the Barcelona water network.
Article
Full-text available
There are three disadvantages of weighted scoring stock selection models. First, they cannot identify the relations between weights of stock-picking concepts and performances of portfolios. Second, they cannot systematically discover the optimal combination for weights of concepts to optimize the performances. Third, they are unable to meet various investors’ preferences. This study aimed to more efficiently construct weighted scoring stock selection models to overcome these disadvantages. Since the weights of stock-picking concepts in a weighted scoring stock selection model can be regarded as components in a mixture, we used the simplex-centroid mixture design to obtain the experimental sets of weights. These sets of weights are simulated with US stock market historical data to obtain their performances. Performance prediction models were built with the simulated performance data set and artificial neural networks. Furthermore, the optimization models to reflect investors’ preferences were built up, and the performance prediction models were employed as the kernel of the optimization models, so that the optimal solutions can now be solved with optimization techniques. The empirical values of the performances of the optimal weighting combinations generated by the optimization models showed that they can meet various investors’ preferences and outperform those of S&P’s 500 not only during the training period but also during the testing period.
Article
Irrigated agriculture is one of the key factors responsible for decreasing freshwater availability in recent years. Thus, the development of new tools which will help Irrigation District managers in their daily decision making process about the use of water and energy is essential. On the other hand, the new era of Big Data and information and communications technologies (ICT) has made it possible to have a larger amount of information available, leading to the development of new prediction tools. However, the quality and quantity of this information in many fields such as irrigated agriculture is limited. Consequently, the way in which the development of new predictive models is addressed must be reformulated. Thus, in this work, a new methodology to provide short-term forecasting of daily irrigation water demand when data availability is limited has been developed by coupling dynamic Artificial Neural Networks (ANN) architecture, the Bayesian framework and Genetic Algorithms (GA). The methodology was applied in the Bembézar MD Irrigation District (Southern Spain). The developed model improved the prediction accuracy by between 3% and 11% with respect to previous work. The best ANN model had a Standard Error Prediction (SEP) and a determination coefficient (R²) of 8.7% and 96%, respectively. The accuracy of the model developed makes it a powerful tool for the daily management of irrigation districts.
Article
Portfolio selection is one of the major capital allocation and budgeting issues in financial management, and a variety of models have been presented for optimal selection. Semi-variance is usually considered as a risk factor in drawing up an efficient frontier and the optimal portfolio. Since semi-variance offers a better estimation of the actual risk portfolio, it was used as a measure to approximate the risk of investment in this work. The optimal portfolio selection is one of the non-deterministic polynomial (NP)-hard problems that have not been presented in an exact algorithm, which can solve this problem in a polynomial time. Meta-heuristic algorithms are usually used to solve such problems. A novel hybrid harmony search and artificial bee colony algorithm and its application were introduced in order to draw efficient frontier portfolios. Computational results show that this algorithm is more successful than the harmony search method and genetic algorithm. In addition, it is more accurate in finding optimal solutions at all levels of risk and return.
Article
In this work, the annual gross electricity demand of Turkey was modeled by multiple linear regression and artificial neural networks as a function population, gross domestic product per capita, inflation percentage, unemployment percentage, average summer temperature and average winter temperature. Among these, the unemployment percentage and the average winter temperature were found to be insignificant to determine the demand for the years between 1975 and 2013. Next, the future values of the statistically significant variables were predicted by time series ANN models, and these were simulated in a multilayer perceptron ANN model to forecast the future annual electricity demand. The results were validated with a very high accuracy for the years that the electricity demand was known (2007–2013), and they were also superior to the official predictions (done by Ministry of Energy and Natural Resources of Turkey). The model was then used to forecast the annual gross electricity demand for the future years, and it was found that, the demand will be doubled reaching about 460 TW h in the year 2028. Finally, it was concluded that the approach applied in this work can easily be implemented for other countries to make accurate predictions for the future.
Article
Grey Wolf Optimizer (GWO) is a newly proposed algorithm that developed based on inspiration of grey wolves (Canis Lupus). This GWO algorithm mimics the nature of grey wolves in leadership hierarchy and hunting mechanism. This paper is in the purpose of introducing GWO to solve combined economic emission dispatch problem (CEED) in power system. CEED actually is a bi-objective problem where the objective of economic dispatch (ED) and emission dispatch (EMD) are combined into a single function by using price penalty factor. Hence, CEED is used to minimize total generation cost by minimized fuel cost and emission at the same time determines the optimum power generation. The proposed algorithm will be implemented in two different systems which are 6 and 11-generating unit test systems with different constraints on various power load demands. The results were compared with the optimization techniques reported in recent literature in order to observe the effectiveness of GWO.