A mixed time series glycemic prediction model
    
    
  
  
  
      
      
      
        
Vestnik Tverskogo gosudarstvennogo universiteta. Seriâ Prikladnaâ matematika, no. 1 (2025), pp. 67-87
    
  
  
  
  
  
    
      
      
        
      
      
      
    Voir la notice de l'article provenant de la source Math-Net.Ru
            
              			The article considers the problem of predicting blood glucose levels using data containing weakly expressed dependencies between parameters, including time series and physiological parameters. An approach based on the use of neural networks with long short-term memory (LSTM) is proposed, which is capable of predicting future glucose values (SGV), as well as identifying anomalies in the data. To improve the quality of the model, the DBSCAN clustering method is used, which allows you to identify groups of data with similar characteristics. An algorithm for filling in missing data based on the average value in the cluster is also developed, which improves the accuracy of forecasting. Numerical experiments were carried out on data collected by monitoring glucose levels, which demonstrated the effectiveness of the proposed approach for predicting SGV, taking into account time dependencies and the influence of associated factors.
			
            
            
            
          
        
      
                  
                    
                    
                    
                    
                    
                      
Keywords: 
time series, missing data, glucose monitoring, SGV (Sensor Glucose Value), time history modeling.
Mots-clés : DBSCAN, data anomalies
                    
                  
                
                
                Mots-clés : DBSCAN, data anomalies
@article{VTPMK_2025_1_a4,
     author = {Z. Z. Mingaliyev and S. V. Novikova},
     title = {A mixed time series glycemic prediction model},
     journal = {Vestnik Tverskogo gosudarstvennogo universiteta. Seri\^a Prikladna\^a matematika},
     pages = {67--87},
     publisher = {mathdoc},
     number = {1},
     year = {2025},
     language = {ru},
     url = {http://geodesic.mathdoc.fr/item/VTPMK_2025_1_a4/}
}
                      
                      
                    TY - JOUR AU - Z. Z. Mingaliyev AU - S. V. Novikova TI - A mixed time series glycemic prediction model JO - Vestnik Tverskogo gosudarstvennogo universiteta. Seriâ Prikladnaâ matematika PY - 2025 SP - 67 EP - 87 IS - 1 PB - mathdoc UR - http://geodesic.mathdoc.fr/item/VTPMK_2025_1_a4/ LA - ru ID - VTPMK_2025_1_a4 ER -
Z. Z. Mingaliyev; S. V. Novikova. A mixed time series glycemic prediction model. Vestnik Tverskogo gosudarstvennogo universiteta. Seriâ Prikladnaâ matematika, no. 1 (2025), pp. 67-87. http://geodesic.mathdoc.fr/item/VTPMK_2025_1_a4/
