Search Articles

View query in Help articles search
e.g. mhealth

Search Results (1 to 3 of 3 Results)

Download search results: CSV END BibTex RIS

Deep Learning Approach for Imputation of Missing Values in Actigraphy Data: Algorithm Development Study

Deep Learning Approach for Imputation of Missing Values in Actigraphy Data: Algorithm Development Study

An autoencoder is a deep-learning method that can extract key features from input data and restore them; therefore, an autoencoder can also be used for reconstructing original data from corrupted data [13]. This approach has been used to impute missing values in traffic data, which are similar to actigraphy data—both data sets have time-series characteristics [14]. Furthermore, another study [15] showed that the autoencoder-based approach can extract core features from activity data.

Jong-Hwan Jang, Junggu Choi, Hyun Woong Roh, Sang Joon Son, Chang Hyung Hong, Eun Young Kim, Tae Young Kim, Dukyong Yoon

JMIR Mhealth Uhealth 2020;8(7):e16113

Download Citation: END BibTex RIS

Download PDF Download XML
Article has an altmetric score of 2

Autoencoder as a New Method for Maintaining Data Privacy While Analyzing Videos of Patients With Motor Dysfunction: Proof-of-Concept Study

Autoencoder as a New Method for Maintaining Data Privacy While Analyzing Videos of Patients With Motor Dysfunction: Proof-of-Concept Study

A variational autoencoder was trained on 2230 videos comprising the 9 standardized motor performances included in the ASSESS MS study. The autoencoder was structured so that the frames of each video were encoded into a lower-dimensional space and then decoded into their original form. Figure 1 depicts the structure of the autoencoder [10]. An encoder network was presented with a single frame from the video without further context. The frame passed through 5 encoding blocks.

Marcus D'Souza, Caspar E P Van Munster, Jonas F Dorn, Alexis Dorier, Christian P Kamm, Saskia Steinheimer, Frank Dahlke, Bernard M J Uitdehaag, Ludwig Kappos, Matthew Johnson

J Med Internet Res 2020;22(5):e16669

Download Citation: END BibTex RIS

Download PDF Download XML
Article has an altmetric score of 1

Detection of Bleeding Events in Electronic Health Record Notes Using Convolutional Neural Network Models Enhanced With Recurrent Neural Network Autoencoders: Deep Learning Approach

Detection of Bleeding Events in Electronic Health Record Notes Using Convolutional Neural Network Models Enhanced With Recurrent Neural Network Autoencoders: Deep Learning Approach

Our CNN model differs from the previous neural network models in that we deployed an autoencoder neural network [21] as an unsupervised learning algorithm to learn a latent representation from unlabeled sentences in order to help improve CNN performance. Specifically, we propose the hybrid CNN and LSTM (HCLA) autoencoder model, which employs a CNN model that is integrated with a bidirectional LSTM (Bi LSTM)-based autoencoder model to classify whether a sentence contains a bleeding event.

Rumeng Li, Baotian Hu, Feifan Liu, Weisong Liu, Francesca Cunningham, David D McManus, Hong Yu

JMIR Med Inform 2019;7(1):e10788

Download Citation: END BibTex RIS

Download PDF Download XML
Article has an altmetric score of 5