A RECURRENT NEURAL NETWORK AND A SYSTEM TO PREDICT BLOOD GLUCOSE LEVEL

Provided is a recurrent neural network (RNN) for predicting a blood sugar level. The RNN comprises: a first long short-term memory (LSTM) network including input and output for receiving near-infrared radiation (NIR) data; and a second LSTM network including input for receiving the output of the fir...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	LIU LIU, GEORGIADIS GEORGIOS, DENG WEIRAN, SAKHAEE ELHAM
Format:	Patent
Sprache:	eng ; kor
Schlagworte:	CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING DIAGNOSIS HUMAN NECESSITIES HYGIENE IDENTIFICATION MEDICAL OR VETERINARY SCIENCE PHYSICS SURGERY
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Beschreibung
Zusammenfassung:	Provided is a recurrent neural network (RNN) for predicting a blood sugar level. The RNN comprises: a first long short-term memory (LSTM) network including input and output for receiving near-infrared radiation (NIR) data; and a second LSTM network including input for receiving the output of the first LSTM network and output for outputting a blood sugar level based on the NIR data input to the first LSTM network. 혈당 수준을 예측하는 순환 신경망(RNN)이 제공된다. 상기 순환 신경망(RNN)은 근적외선(NIR) 방사선 데이터를 수신하는 입력과 출력을 포함하는 제1 롱 숏텀 메모리(Long Short-Term Memory, LSTM) 네트워크, 상기 제1 LSTM 네트워크의 출력을 수신하는 입력과 상기 제1 LSTM 네트워크에 입력되는 근적외선 방사선 데이터를 근거하여 혈당 수준을 출력하는 출력을 포함하는 제2 LSTM 네트워크를 포함한다.