Lgformer: informer-based personalized modeling for blood glucose prediction

HIGHLIGHTS

• What: This model has been extensively used in time series forecasting , demonstrating strong performance in areas such as wind power prediction , transportation planning, financial market analysis, and other fields. The authors propose a new blood glucose prediction model, LGformer, based on Informer. The authors enable the customization of the weight matrix in Informer`s multihead attention mechanism, allowing the model to adapt its focus on different parts of the blood glucose data more precisely, thereby improving processing and overall performance. To address the limitations of existing blood glucose prediction methods-specifically in handling data dependencies, computational efficiency . . .
  

   

  

  If you want to have access to all the content you need to log in!

  Thanks :)

  Username or E-mail:

  If you don't have an account, you can create one here.