Proprioception, the ability to perceive one’s own configuration and movement in space, enables organisms to safely and accurately interact with their environment and each other. The underlying sensory nerves that make this possible are highly dense and use sophisticated communication pathways to propagate signals from nerves in muscle, skin and joints to the central nervous system wherein the organism can process and react to stimuli. In a step forward to realize robots with such perceptive capability, we propose a flexible sensor framework that incorporates a novel hybrid modeling strategy, taking advantage of computational mechanics and machine learning. We implement the sensor framework on a large, thin and flexible sensor that transforms sparsely distributed strains into continuous surface shape. Finite element (FE) analysis is utilized to determine sensor design parameters, while an FE model is built to enrich the morphological data used in the supervised training to achieve continuous surface reconstruction. A mapping between the local strain data and the enriched surface data is subsequently trained using ensemble learning. This hybrid approach enables real-time, robust and high-order surface shape reconstruction. The sensing performance is evaluated in terms of accuracy, repeatability, and feasibility with numerous scenarios, which has not been demonstrated and reported on such a large-scale (A4-paper-size) sensor before.
This Supporting Information includes:Figure S1, S2, S3Supplementary Video Supplementary Video S1: Locomotion of the mobile robot. Supplementary Video S2: Vortex deforming the liquid-liquid interface. Supplementary Video S3: Locomotion of the mobile robot without electrode attached. Supplementary Video S4: Locomotion of the mobile robot with reversed polarity. Supplementary Video S5: Drawing “SIT” by controlling a floating robot with multiple electrodes. Corresponding author Email: firstname.lastname@example.org, email@example.com
This Supporting information includes:1. Component Selection and Performance of SFA2. Actuator Manufacturing and Preparation of Conductive Ink 3. Average Thickness of Conductive Coating layer on PU Foam4. Time Response of the Actuator in Different Modes 5. Characterization and Experimental Setup6. Measurement and Data Analysis7. Design Specifications of Soft Robotic Applications8. Supporting Video Corresponding author Email: firstname.lastname@example.org, email@example.com
This Supporting Information includes the extended description of the superposition state of the asymmetric double-well system in vacuum system and in solution, truth tables for the residue pairs and their corresponding quantum logic gates, and figures for the double well potential energy surfaces and transmission spectra of the residue pairs.Corresponding Authors Email: firstname.lastname@example.org and email@example.com
Identifying Clostridioides difficile infection (CDI) patients at risk of mortality or recurrence will facilitate prevention, timely treatment and improve clinical outcomes. We aim to establish an open-access web-based prediction system, which estimates CDI patients’ mortality and recurrence outcomes, and explains the machine learning prediction with patients’ characteristics. Prognostic models were developed using four various types of machine learning algorithms and statistical logistics regression model utilizing over 15,000 CDI patients from 41 hospitals in Hong Kong. The boosting-based machine learning algorithm Gradient Boosting Machine (Mortality AUC: 0.7878; Recurrence AUC: 0.7076) outperformed statistical models (Mortality AUC: 0.7573; Recurrence AUC: 0.6927) and other machine learning algorithms. The open-access prediction system for clinicians to assess and interpret the risk factors of CDI patients is now available at https://www.cdiml.care/. In this article, we explain the development of machine learning models and illustrate how to apply hyperparameter tuning with cross-validation to optimize the model accuracy.
Appendix ATable S1. Results of the WS-CNN classifier for post-HI spike transient identification in experimental data (entire 6 hours – 13 layers) Trained and validated on Sheep No. No. of patterns in the Train and Validation Dataset Tested on Sheep No. No. of patterns in the Test-set TP hits TN hits FP hits FN hits Sensitivity [%] Selectivity [%] Precision [%] Accuracy [%] 2,3,4,5,6,7 4567 1 443 152 269 1 21 87.9 99.6 99.3 95.0 1,3,4,5,6,7 4751 2 259 110 149 0 0 100 100 100 100 1,2,4,5,6,7 4731 3 279 81 196 0 2 97.6 100 100 99.3 1,2,3,5,6,7 3372 4 1638 824 806 8 0 100 99.0 99.0 99.5 1,2,3,4,6,7 4088 5 922 454 466 1 1 99.8 99.8 99.8 99.8 1,2,3,4,5,7 4466 6 544 231 312 1 0 100 99.7 99.6 99.8 1,2,3,4,5,6 4085 7 925 209 714 2 0 100 99.7 99.1 99.8 Overall performance of the 13 layers WS-CNN in the entire 6 hours 99.03±1.66