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

Comprehensive Assessment and Early Prediction of Gross Motor Performance in Toddlers With Graph Convolutional Networks–Based Deep Learning: Development and Validation Study

Comprehensive Assessment and Early Prediction of Gross Motor Performance in Toddlers With Graph Convolutional Networks–Based Deep Learning: Development and Validation Study

The first stage is the action evaluation stage, in which each behavior is evaluated separately using a graph convolutional networks (GCN)–based deep learning algorithm. To improve the performance of the stage-1 model, we performed transfer learning with pretrained weights. These pretrained weights are released by PYSKL and are trained with the channel-wise topology refinement graph convolution networks (CTR-GCN) model on the NTU RGB+D dataset by detecting 17 skeleton nodes with HRNet [32-34].

Sulim Chun, Sooyoung Jang, Jin Yong Kim, Chanyoung Ko, JooHyun Lee, JaeSeong Hong, Yu Rang Park

JMIR Form Res 2024;8:e51996

Download Citation: END BibTex RIS

Download PDF Download XML
Article has an altmetric score of 1

Conditional Probability Joint Extraction of Nested Biomedical Events: Design of a Unified Extraction Framework Based on Neural Networks

Conditional Probability Joint Extraction of Nested Biomedical Events: Design of a Unified Extraction Framework Based on Neural Networks

To capture the interrelations between triggers and related entities and improve the performance of extracting nested biomedical events, we integrated the syntactic dependency tree into an attention-based gate graph convolutional network (GCN), which can capture the flow direction of the key information.

Yan Wang, Jian Wang, Huiyi Lu, Bing Xu, Yijia Zhang, Santosh Kumar Banbhrani, Hongfei Lin

JMIR Med Inform 2022;10(6):e37804

Download Citation: END BibTex RIS

Download PDF Download XML
Article has an altmetric score of 2

Relation Classification for Bleeding Events From Electronic Health Records Using Deep Learning Systems: An Empirical Study

Relation Classification for Bleeding Events From Electronic Health Records Using Deep Learning Systems: An Empirical Study

Recent DL architectures, such as Bidirectional Encoder Representations from Transformers (BERT) [27] and graph convolutional network (GCN), have shown promising results for relation classification across different domains. Wu and He [28] used BERT with entity information for relation classification on the Sem Eval-2010 Task 8 data set [29] and obtained better results than other state-of-the-art methods.

Avijit Mitra, Bhanu Pratap Singh Rawat, David D McManus, Hong Yu

JMIR Med Inform 2021;9(7):e27527

Download Citation: END BibTex RIS

Download PDF Download XML
Article has an altmetric score of 2