scholarly journals Deep Learning From Spatio-Temporal Data Using Orthogonal Regularizaion Residual CNN for Air Prediction

IEEE Access ◽  
2020 ◽  
Vol 8 ◽  
pp. 66037-66047
Author(s):  
Lei Zhang ◽  
Dong Li ◽  
Quansheng Guo
Keyword(s):  
Deep Learning ◽  
Temporal Data ◽  
Spatio Temporal

ACM TIST Special Issue on Deep Learning for Spatio-Temporal Data: Part 1

2021 ◽  
Vol 12 (6) ◽  
pp. 1-3
Author(s):  
Senzhang Wang ◽  
Junbo Zhang ◽  
Yanjie Fu ◽  
Yong Li
Keyword(s):  
Deep Learning ◽  
Temporal Data ◽  
Special Issue ◽  
Spatio Temporal

scholarly journals Deep learning with 4D spatio-temporal data representations for OCT-based force estimation

2020 ◽  
Vol 64 ◽  
pp. 101730 ◽  
Author(s):  
Nils Gessert ◽  
Marcel Bengs ◽  
Matthias Schlüter ◽  
Alexander Schlaefer
Keyword(s):  
Deep Learning ◽  
Temporal Data ◽  
Force Estimation ◽  
Data Representations ◽  
Spatio Temporal

scholarly journals Generalization of spatio-temporal deep learning for vision-based force estimation

2020 ◽  
Vol 6 (1) ◽  
Author(s):  
Finn Behrendt ◽  
Nils Gessert ◽  
Alexander Schlaefer
Keyword(s):  
Deep Learning ◽  
Force Feedback ◽  
Haptic Feedback ◽  
Absolute Error ◽  
Estimation Methods ◽  
Temporal Data ◽  
Learning Models ◽  
Force Estimation ◽  
Tissue Samples ◽  
Spatio Temporal

AbstractRobot-assisted minimally-invasive surgery is increasingly used in clinical practice. Force feedback offers potential to develop haptic feedback for surgery systems. Forces can be estimated in a vision-based way by capturing deformation observed in 2D-image sequences with deep learning models. Variations in tissue appearance and mechanical properties likely influence force estimation methods’ generalization. In this work, we study the generalization capabilities of different spatial and spatio-temporal deep learning methods across different tissue samples. We acquire several data-sets using a clinical laparoscope and use both purely spatial and also spatio-temporal deep learning models. The results of this work show that generalization across different tissues is challenging. Nevertheless, we demonstrate that using spatio-temporal data instead of individual frames is valuable for force estimation. In particular, processing spatial and temporal data separately by a combination of a ResNet and GRU architecture shows promising results with a mean absolute error of 15.450 compared to 19.744 mN of a purely spatial CNN.

Sign in / Sign up

Export Citation Format

Share Document