Long short-term memory neural network for glucose prediction

Carrillo-Moreno, Jaime; Pérez-Gandía, Carmen; Sendra-Arranz, Rafael; García-Sáez, Gema; Hernando, M. Elena; Gutiérrez, Álvaro

doi:10.1007/s00521-020-05248-0

Cited by 28 publications

(7 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There is a type of recurrent neural network known as the long short-term memory (LSTM). LSTM's improved structure allows information to selectively change the state of instant in the recurrent neural network using some gate structures [18].…”

Section: Wireless Communications and Mobile Computingmentioning

confidence: 99%

Self-Driving Tour Travel Route Planning Model Construction Using Recurrent Neural Network

Wang

2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

With the continuing increase of people’s living standards, tourism has now become the primary mode of holiday and leisure activity. Scientific and reasonable route planning can best meet people’s essential needs, provide detailed planning in terms of travel time and cost, resolve the impact of various external factors, and realize the complementary benefits of scenic tourism while ensuring that each factor configuration is optimized. External factors such as trip time, cost, travel date, and transport mode all have an impact on route planning. In order to develop a mathematical model and gather other information, it is frequently essential to determine two or more of these influencing elements. The ideal plan for the influencing elements is to first develop an optimal self-driving trip route that meets all of the requirements. This strategy is becoming increasingly popular among the general public, and it focuses on how to spend the least amount of money in order to visit more tourist attractions, construct the most reasonable routes, and provide circumstances for tourists to save time and money. The purpose of this study is to examine the topic of self-driving travel route planning and to suggest the creation of a route planning model. In this paper, a self-driving journey route planning model is built using a recurrent neural network model. The driving route is designed with a high-speed priority strategy, and the travel route selection problem takes into account the consumption condition as well as the quantity of scenic sites. The developed model is used to optimize self-driving trip routes, and the results are promising.

show abstract

Section: Wireless Communications and Mobile Computingmentioning

confidence: 99%

Self-Driving Tour Travel Route Planning Model Construction Using Recurrent Neural Network

Wang

2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

show abstract

“…As a key technology to control glucose level, numerous research studies about glucose prediction have been developed and reported in the literature. Through horizontal comparison with other algorithms [13,[34][35][36][37][38], Table 8 presents the comparison results. It can be seen from the table that most algorithms use a neural network algorithm for prediction, and the pH is mostly less than 60 min.…”

Section: Resultsmentioning

confidence: 99%

“…On the other hand, the differences between the predictive data and the original data can be further quantified and analyzed to carry out research on the soft alarm of glucose control. [34] Clinical data 45 0.89 21.52 n.r. DE-SVR [35] Clinical data 60 0.982 12.95 5.65 EMD-SSA-KELM [36] Clinical data 30 n.r.…”

Section: Discussionmentioning

confidence: 99%

Research of GPCEMBP Glucose Prediction Algorithm Based on Continuous Glucose Monitoring

Cai,

Ge,

Liu

2023

Journal of Sensors

View full text Add to dashboard Cite

In view of the poor timeliness of dynamic blood glucose data and a delay of insulin effect for blood glucose control, and considering the nonlinearity and nonstationarity of the glucose data, a new blood Glucose Prediction algorithm combined Correlation coefficient-based complete ensemble empirical mode decomposition with adaptive noise and back propagation neural network (GPCEMBP) was proposed to increase the prediction time and improve the prediction accuracy. It refined the mode decomposition algorithm and integrated the correlation mode filter function to extract the characteristic intrinsic mode functions from the original signal. A new neural network prediction model was constructed by optimizing the number of hidden layer neurons, the number of hidden layers, activation functions, the number of inputs, structure, and other parameters. Finally, a predicted blood glucose value was calculated by phase space reconstruction technology. Through ablation and comparison experiments, it was demonstrated that the GPCEMBP algorithm had better prediction accuracy, convergence, and robustness in blood glucose prediction within 84 min. In addition, it has good adaptability to deal with different quality glucose data.

show abstract

“…OhioT1DM dataset consists of blood glucose level values for two men and four women. Carrillo-Moreno et al [24] proposed an LSTM model using historical glucose levels, insulin units, and carbohydrate intake data. They used CGM data from 3 Type-1 diabetic patients and created 12 models with various combinations of patient-specific, prediction horizon (PH), LSTM layers, and the number of neurons for performance comparison.…”

Section: Related Workmentioning

confidence: 99%

“…Most of the blood glucose prediction studies used CGM data and diet information of Type-1 diabetes patients [ 6 , 7 , 8 , 9 , 10 , 11 , 14 , 15 , 16 , 17 , 18 , 19 , 20 , 21 , 22 , 23 , 24 ]. Pérez-Gandía et al [ 6 ] predicted blood glucose after 15, 30, and 45 min after a given time using an artificial neural network (ANN) model and used the CGM data from 15 Type-1 diabetic patients.…”

Section: Related Workmentioning

confidence: 99%

Developing an Individual Glucose Prediction Model Using Recurrent Neural Network

Kim

Choi

Kim

et al. 2020

Sensors

View full text Add to dashboard Cite

In this study, we propose a personalized glucose prediction model using deep learning for hospitalized patients who experience Type-2 diabetes. We aim for our model to assist the medical personnel who check the blood glucose and control the amount of insulin doses. Herein, we employed a deep learning algorithm, especially a recurrent neural network (RNN), that consists of a sequence processing layer and a classification layer for the glucose prediction. We tested a simple RNN, gated recurrent unit (GRU), and long-short term memory (LSTM) and varied the architectures to determine the one with the best performance. For that, we collected data for a week using a continuous glucose monitoring device. Type-2 inpatients are usually experiencing bad health conditions and have a high variability of glucose level. However, there are few studies on the Type-2 glucose prediction model while many studies performed on Type-1 glucose prediction. This work has a contribution in that the proposed model exhibits a comparative performance to previous works on Type-1 patients. For 20 in-hospital patients, we achieved an average root mean squared error (RMSE) of 21.5 and an Mean absolute percentage error (MAPE) of 11.1%. The GRU with a single RNN layer and two dense layers was found to be sufficient to predict the glucose level. Moreover, to build a personalized model, at most, 50% of data are required for training.

show abstract

Long short-term memory neural network for glucose prediction

Cited by 28 publications

References 34 publications

Self-Driving Tour Travel Route Planning Model Construction Using Recurrent Neural Network

Self-Driving Tour Travel Route Planning Model Construction Using Recurrent Neural Network

Research of GPCEMBP Glucose Prediction Algorithm Based on Continuous Glucose Monitoring

Developing an Individual Glucose Prediction Model Using Recurrent Neural Network

Contact Info

Product

Resources

About