ChapterPDF Available

Machine Learning-Based Classification of Countries Based on Food Supply Quantities in The Caucasus and Surrounding Regions

Authors:

Abstract and Figures

(https://github.com/hakan-duman-acad/chapter-foodbalance-ml-classification) Food security is vital for human survival, ensuring consistent access to sufficient, safe, and nutritious food for an active, healthy life. This study addresses food security challenges in the Caucasus region by analyzing FAOSTAT food balance data (2010–2022) on daily per capita food supply (kcal/capita/day) for plant- and animal-based products. Using R and Python, statistical analyses (Welch ANOVA and Games-Howell tests) and machine learning models (Logistic Regression, Random Forest, Decision Tree, and Multi-Layer Perceptron) were applied, with 256 hyperparameter combinations and a CRS-DEA model assessing algorithm efficiency. Results revealed significant variations in food consumption patterns, with Kazakhstan excelling in animal product intake and Türkiye leading in vegetal products, while Ukraine’s food supply declined due to conflict. Decision Tree (DT) emerged as the most suitable machine learning model, balancing high performance, minimal computational time, and interpretability. These findings contribute valuable insights into food security and machine learning model efficiency, providing a foundation for future research and practical applications.
Content may be subject to copyright.
Editörler
Doç. Dr. Oğuz ŞİMŞEK
Dr. Çağrı AKGÜN
Öğr. Gör. Çetin İZGİ
KAFKASYA
ARAŞTIRMALARI -II-
Kitabın Adı :KAFKASYAARAŞTIRMALARI-II
Editör :Doç.Dr.OğuzŞİMŞEK,Dr.ÇağrıAKGÜN,Öğr.Gör.ÇetinİZGİ
Yazar :OğuzŞİMŞEK,XanəliKərimli,ÇağrıAKGÜN,SalimSerkanNAS,
UğurPARLAK,VildanYAVUZAKINCI,ÇetinİZGİ,
DilşadHuriyeKAYIRANİZGİ,HakanDuman,YunusEmreKök
Kapak / Mizanpaj :YağmurARDUÇ
1. Baskı :Aralık2024ANKARA
Yayın Koordinatörü :CeydaŞEREFLİOĞLU
Yayın Yönetmeni :SelvaALİM
ISBN :978-625-5537-20-1
Yayın No. :2728
© Tüm hakları yazarına aittir. Yazarın izni alınmadan kitabın tümünün veya bir kısmının
elektronik,mekanikyadafotokopiyoluylabasımı,çoğaltılmasıyapılamaz.Yalnızcakaynak
gösterilerekkullanılabilir.
SONÇAĞ AKADEMİ
İstanbulCad.İstanbulÇarşısıNo.:48/49İskitler06070ANKARA
T/(312)3413667-GSM/(533)0937864
www.soncagyayincilik.com.tr
soncagyayincilik@gmail.com
Yayıncı Sertika Numarası: 47865
BASKI VE CİLT MERKEZİ
UZUNDİJİTALMATBAA,SONÇAĞYAYINCILIKMATBAACILIKTESCİLLİMARKASIDIR.
İstanbulCad.İstanbulÇarşısıNo.:48/48İskitler06070ANKARA
T/(312)3413667
www.uzundijital.com
uzun@uzundijital.com
İÇİNDEKİLER
ÖNSÖZ ............................................................................................................... iii
BAYAN CHANTRE’NİN 1890 YILI GÜNEY KAFKASYA SEYHAT
NOTLARINDA IĞDIR VE ÇEVRESİ
Oğuz ŞİMŞEK ............................................................................................................................................1
NAXÇIVAN POEZİYASINDA VƏTƏNPƏRVƏRLİK MOTİVLƏRİ
Xanəli Kərimli ......................................................................................................................................57
KAFKASYA’DA SINIRAŞAN SULAR SORUNU:
ARAS HAVZASI VE TÜRKİYE’NİN BARAJ POLİTİKALARI
Çağrı AKGÜN - Salim Serkan NAS ........................................................................................75
THEMATIC MAPPING OF AGRICULTURAL AND RURAL RESEARCH IN
DAGESTAN
Duman, Hakan ................................................................................................................................. 99
KONAKLAMADA YENİ TREND AKILLI OTELLER: KAFKASYA VE
TÜRKİYE İNCELEMESİ
Uğur PARLAK .......................................................................................................................................127
BİBLİYOMETRİK YAKLAŞIMLA KAFKASYA EKONOMİSİ:
LİTERATÜRDEKİ EĞİLİMLER VE KAVRAMSAL ÇERÇEVE
Vildan YAVUZ AKINCI - Çetin İZGİ ....................................................................................... 141
ENERJİ JEOPOLİTİĞİ: TÜRKİYE VE KAFKASYA’NIN AVRUPA BİRLİĞİ
İÇİN ÖNEMİ
Dilşad Huriye KAYIRAN İZGİ ....................................................................................................... 161
MACHINE LEARNING-BASED CLASSIFICATION OF COUNTRIES
BASED ON FOOD SUPPLY QUANTITIES IN THE CAUCASUS AND
SURROUNDING REGIONS
Duman, Hakan ................................................................................................................................ 189
TÜRKİYE VE AZERBAYCAN’DA SOSYAL GÜVENLİK SİSTEMLERİNİN
KARŞILAŞTIRMASI
Yunus Emre Kök .............................................................................................................................209
Hakan Duman 189
MACHINE LEARNING-BASED CLASSIFICATION OF
COUNTRIES BASED ON FOOD SUPPLY QUANTITIES IN
THE CAUCASUS AND SURROUNDING REGIONS
Duman, Hakan*
INTRODUCTION
       

       
    1 2      
 

       
     3     



            

     4       
*           

1       “Iğdır ılinde Kırsal Kalkınma Kooperatifi
Üyelerinin Örgütlenme Ve Kooperatif Faaliyetleriyle ılgili Problemleri Ve Çözüm Önerilerinin
BelirlenmesiThird Sector Social Economic Review
2          


3       “Introduction to Agricultural
Economics,”, 6th ed. Pearson, Essex
4         FAO   

190 KAFKASYA ARAŞTIRMALARI-II
         



  
           
5

         

   6     
       

         

         
        
       
7

    
       
    


89 1011
5  Food Programme; Earthscan
6      FAO  

7       “Food security,” NASA; IPCC

8       “Machine Learning in Agriculture: A
Review,” Sensors
9 “Machine Learning Applications for Precision
Agriculture: A Comprehensive Review,” IEEE Access
10 “Machine Learning in Agriculture: A
Comprehensive Updated Review,” Sensors
11 
Hakan Duman 191

12
13
        14


15
       
  16      
 17       
18      
19

20

21
   

        
        


12 
         

13 “IMPACT OF MACHINE learning
ON Management, healthcare AND AGRICULTURE,” Materials Today: Proceedings

14            


15 “Neural network-based clustering for agriculture
management,” EURASIP Journal on Advances in Signal Processing,
16 
17 
18 
19 
20 
21 
192 KAFKASYA ARAŞTIRMALARI-II
    

  
     
  22      
 

         
          
    
           



 

MATERIALS AND METHODS
       23  
       

        





 


22    “Kafkasya’nın Ekonomik Dinamikleri: Azerbaycan, Gürcistan Ve
Ermenistan’ın Türkiye ile Ticari Ve Stratejik Bağlantıları,” Kafkasya Araştırmaları -I

23 The Food; Agriculture Organization
(FAO)
Hakan Duman 193



        
           
       24   
 
25

        








         



26

27
         
24    “On the Comparison of Several Mean Values: An Alternative
Approach,” Biometrika
25  “Comparison of Post Hoc Tests for Unequal
Variance,” International Journal of New Technologies in Science and Engineering

26       “An R Companion to Applied Regression,” SAGE

27 “Applied predictive modeling,Springer
194 KAFKASYA ARAŞTIRMALARI-II
 28 29 30    


31
          

32 33


 
34
          
  

35 3637

  38       
39

28 “Logistic Regression,” Circulation
29 “Logistic Regression,” Topics in Biostatistics,
Ambrosius, W.T. Humana Press
30         

31 “Applied Logistic Regression”, 2nd ed. Wiley

32 
33 
34 “Hands-on machine learning with R,” Chapman;

35       “Practical Machine Learning in R,”Wiley,

36 “Decision tree modeling using R,” Annals of Translational Medicine

37       “Karar Ağacı Optimizasyon Algoritması üzerine Bir
Çalışma,” Journal of the Institute of Science and Technology
38 “Induction of decision trees,” Machine Learning,
39       “Classification and regression
trees,” Chapman & Hall,
Hakan Duman 195

           
40
         
41



     

42 43
       
         44 
     

45
         
46
        




        
       


40 
41 “Random forests,” Machine Learning,
42 
43 “Hands-on machine learning with scikit-learn and tensorflow: Concepts,
tools, and techniques to build intelligent systems”
44       “A logical calculus of the ideas immanent in
nervous activity,” The Bulletin of Mathematical Biophysics
45  “Deep learning: methods and applications,” Foundations
and Trends in Signal Processing
46 
196 KAFKASYA ARAŞTIRMALARI-II




  47         


48
         
49 50



          

    51    
          
52     
53
54         
47 “Data Envelopment Analysis
with R,” Springer
48 “Measuring the efficiency of decision
making units,” European Journal of Operational Research
49        “Some Models for Estimating
Technical and Scale Inefficiencies in Data Envelopment Analysis,” Management Science

50    “Productivity and Efficiency Measurement of Airlines: Data
Envelopment Analysis Usingr” Elsevier
51   “R: A Language and Environment for Statistical Computing,” R
Foundation for Statistical Computing
52   “Welcome to the tidyverse,” Journal of
Open Source Software,
53 

54            

Hakan Duman 197
 55       56

         
   
   57 
 
58
RESULTS AND DISCUSSION
         


            

  


Figure 1. Map highlighting the countries included in the study
55 
56 

57 “Scikit-Learn: Machine Learning
in Python,” Journal of Machine Learning Research
58 
198 KAFKASYA ARAŞTIRMALARI-II






      

           
      
       







Table 1. Mean supply of animal products (kcal/capita/day)
 *
 a
 
 
 c 
 
 
 
 e
* Values with the same letter are not signicantly different at p < 0.05.

      
         

Hakan Duman 199
        



   

Table 2. Mean supply of vegetal products (kcal/capita/day)
 *
 a
 
 
 c
 
 
 
 
* Values with the same letter are not signicantly different at p < 0.05.


  


    

         


    

200 KAFKASYA ARAŞTIRMALARI-II
Figure 2. Box plots illustrating the supply distribution of animal and vegetal products
(kcal/capita/day)
          



         









         


     



Hakan Duman 201



Figure 3. Plots illustrating the annual changes in the supply distribution of animal and
vegetal products (kcal/capita/day)
          
          
Fp   

Fp

            

      



Table 3. Mean weighted F1 scores of machine learning models used in the study
 *
 a
 a
 
 
*Values with the same letter are not signicantly different at p < 0.05.
202 KAFKASYA ARAŞTIRMALARI-II
         



         
        
         F
 p         
         
     F
 p           

         
    
          
     

Table 4. Mean time spent on ne-tuning machine learning models (in seconds)
 *
 a
 
 c
 
*Values with the same letter are not signicantly different at p < 0.05.
       

       
      





Hakan Duman 203
Table 5. CRS-DEA efciency scores of machine learning models, using time as input
and performance as output
 
 
 
 
 
          


          
        
     



 



Table 6. Highest-performing sub-models of studied algorithms, along with their trai-
ning and test scores and ne-tuned hyperparameters.
   
   -

   -

   -

   
204 KAFKASYA ARAŞTIRMALARI-II
CONCLUSION
         
     
          







    
     
 
         
         

   
         
        

         


        



        

        


    
Hakan Duman 205


    




      
          

         

        
    
          







ACKNOWLEDGEMENTS
Statement:

  

206 KAFKASYA ARAŞTIRMALARI-II
REFERENCES
        




      

         

“Karar Ağacı Optimizasyon Algoritması üzerine Bir Çalışma”,
           

       “Some models for estimating technical
and scale ineiciencies in data envelopment analysis” 

          “Machine learning in agriculture: A
comprehensive updated review”,
  


“Random forests”,


        “Measuring the eiciency of decision
making units”, 

“Deep learning: methods and applications”,


        


        

          

   


   

“Iğdır ı
linde kırsal kalkınma kooperatifi
üyelerinin örgütlenme ve kooperatif faaliyetleriyle ı
lgili problemleri ve çözüm
önerilerinin belirlenmesi”
Hakan Duman 207
         


 
      


   “Logistic Regression”,     

          

          “Machine learning in agriculture: A
review”,


    

   “A logical calculus of the ideas immanent in nervous
activity”

      


“IMPACT OF MACHINE learning
ON Management, healthcare AND AGRICULTURE”   

“Scikit-learn: Machine learning in
Python”,
            

              

       

“Induction of decision trees”

“Current and future applications
of statistical machine learning algorithms for agricultural machine vision systems”,
 

 “Machine learning applications for precision
agriculture: A comprehensive review”      

“Comparison of post hoc tests for unequal variance”



208 KAFKASYA ARAŞTIRMALARI-II
      “Neural network-based clustering for agriculture
management”, 



“On the comparison of several mean values: An alternative approach”

  “Welcome to the tidyverse”, 

“Decision tree modeling using R”,
ResearchGate has not been able to resolve any citations for this publication.
Thesis
Full-text available
Makine öğrenmesi, çoklu doğrusal regresyondan yapay sinir ağlarına kadar yüzlerce algoritmayı içeren bir çalışma alanıdır. Bu çalışmada, Türkiye'de süt verimini etkileyen çeşitli çevre unsurlarının süt verimi üzerindeki etkileri özelinde, tarımda makine öğrenmesi modellerinin ve açıklayıcı yapay zekâ algoritmalarının kullanılması, bu kapsamda veri bilimi yöntemleri kullanılarak farklı kaynaklardan verilerin toplanması, incelenmesi, temizlenmesi, dönüştürülmesi, modellenmesi ve elde edilen modellerin açıklanması amaçlanmıştır. Toplam 116.715 satır, 28 sütun ve 3.268.020 gözlemden oluşan ve 73 farklı il ve 567 ilçede faaliyet gösteren 23.793 işletmede yetiştirilmiş 40 farklı sığır ırkına ait veriler temizlenmiş, düzenlenmiş ve TUIK, MGM, TBB ve KYGM kaynaklarından elde edilen bilgiler ile birleştirilmiştir. Meteorolojik veri seti, 22 göstergeye göre en çok göstergenin işaret ettiği yönde, 4 küme oluşturacak şekilde, DIANA metoduyla kümelenmiştir. Elde edilen kümeler, birikmiş yerel profilleri yardımıyla yorumlanmış ve adlandırılmıştır. Benzer şekilde, yaşam standardına ait veri seti de 22 göstergenin 16 sı tarafından işaret edildiği üzere, 3 küme halinde k-means yöntemi ile kümelenmiş ve elde edilen kümeler birikmiş yerel profil grafikleri vasıtasıyla yorumlanmıştır. Hazırlanan veri seti, çoklu doğrusal regresyon, k-en yakın komşular, destek vektör makineleri, karar ağaçları, rastgele ormanlar ve çok katmanlı algılayıcı yöntemleri ile modellenmiş ve RMSE model başarım değerleri üzerinden mukayese edilmiştir. Elde edilen bulgular, k-en yakın komşular ve rastgele ormanlar algoritmalarında aşırı uyum problemi olduğunu, destek vektör makineleri ve çok katmanlı algılayıcı modellerinin başarımları arasında istatistiksel olarak anlamlı bir fark olmadığı ve en yüksek başarıma sahip olduklarını , ayrıca aşırı veya düşük uyum problemi barındırmadıklarını göstermiştir. Elde edilen çok katmanlı algılayıcılar modeli, veri seti genelinde, öznitelik önemliliği, birikmiş yerel profil grafikleri ve vekil modeller ile, örneklem seviyesinde ise Shapley açıklamaları, ceteris paribus profilleri, LIME grafikleri ve kırılım grafikleri yardımıyla yorumlanmış ve alana ait çok sayıda çıktıya ulaşılabilmiştir. Bu çalışma sonucunda, veri bilimi yöntemlerinin tarım ve tarımsal üretim konularında, araştırmacıların ihtiyaç duyacakları çok sayıda alete sahip olduğu, özellikle bu çalışma ile önerilen, vekil model olarak MARS algoritmasının kullanılmasıyla, kara kutu modellerin, interaksiyonları ile beraber yorumlanmasına büyük katkı sağlayabileceği, kümeleme analizinde yerel birikmiş profillerin bir dış tutarlılık ölçütü olarak kullanılabileceği sonucuna ulaşılmıştır.
Article
Full-text available
Bu çalışmanın amacı matematik bölümünde okuyan öğrencilerin, bölümde okutulan analiz derslerindeki türev konusu hakkında nasıl bir tutuma sahip olduklarını karar ağacı optimizasyon algoritması ile ölçmektir. Çalışmada, Kara (2014)’nın geliştirdiği ve Atasoy ve Kara (2021)’nın optimize ettiği 5’li likert ölçeğine sahip türev tutum ölçeği kullanılmıştır. Matematik bölümünde öğrenim gören 194 öğrenciye bu ölçek uygulanmış ve lise düzeyinde pekiştirme derslerine katılan /katılmayan öğrencilerin görüşlerinde farklılık olup olmadığı incelenmiştir. Öğrencilerin ÖSYM matematik testinde doğru cevapladıkları soru sayısına bakıldığında, üniversite analiz dersinde görülen türevlere olumlu baktıkları görülmüştür.
Article
Full-text available
Agriculture plays a vital role in the economic growth of any country. With the increase of population, frequent changes in climatic conditions and limited resources, it becomes a challenging task to fulfil the food requirement of the present population. Precision agriculture also known as smart farming have emerged as an innovative tool to address current challenges in agricultural sustainability. The mechanism that drives this cutting edge technology is machine learning (ML). It gives the machine ability to learn without being explicitly programmed. ML together with IoT (Internet of Things) enabled farm machinery are key components of the next agriculture revolution. In this article, authors present a systematic review of ML applications in the field of agriculture. The areas that are focused are prediction of soil parameters such as organic carbon and moisture content, crop yield prediction, disease and weed detection in crops and species detection. ML with computer vision are reviewed for the classification of a different set of crop images in order to monitor the crop quality and yield assessment. This approach can be integrated for enhanced livestock production by predicting fertility patterns, diagnosing eating disorders, cattle behaviour based on ML models using data collected by collar sensors, etc. Intelligent irrigation which includes drip irrigation and intelligent harvesting techniques are also reviewed that reduces human labour to a great extent. This article demonstrates how knowledge-based agriculture can improve the sustainable productivity and quality of the product.
Article
Full-text available
Machine learning has emerged with big data technologies and high-performance computing to create new opportunities for data intensive science in the multi-disciplinary agri-technologies domain. In this paper, we present a comprehensive review of research dedicated to applications of machine learning in agricultural production systems. The works analyzed were categorized in (a) crop management, including applications on yield prediction, disease detection, weed detection crop quality, and species recognition; (b) livestock management, including applications on animal welfare and livestock production; (c) water management; and (d) soil management. The filtering and classification of the presented articles demonstrate how agriculture will benefit from machine learning technologies. By applying machine learning to sensor data, farm management systems are evolving into real time artificial intelligence enabled programs that provide rich recommendations and insights for farmer decision support and action.
Book
This book introduces readers to the use of R codes for optimization problems. First, it provides the necessary background to understand data envelopment analysis (DEA), with a special emphasis on fuzzy DEA. It then describes DEA models, including fuzzy DEA models, and shows how to use them to solve optimization problems with R. Further, it discusses the main advantages of R in optimization problems, and provides R codes based on real-world data sets throughout. Offering a comprehensive review of DEA and fuzzy DEA models and the corresponding R codes, this practice-oriented reference guide is intended for masters and Ph.D. students in various disciplines, as well as practitioners and researchers.