Optimizing Input for Gesture Recognition using Convolutional Networks on HD-sEMG Instantaneous Images.

Hand gesture recognition using high-density surface electromyography (HD-sEMG) has gained increasing attention recently due its advantages of high spatio-temporal resolution. Convolutional neural networks (CNN) have also recently been implemented to learn the spatio-temporal features from the instantaneous samples of HD-sEMG signals. While the CNN itself learns the features from the input signal it has not been considered whether certain pre-processing techniques can further improve the classification accuracies established by previous studies.

Thermosensitive and Conductive Hybrid Polymer for Real-Time Monitoring of Spheroid Growth and Drug Responses.

Three-dimensional (3D) cell culture based on polymer scaffold provides a promising tool to mimic a physiological microenvironment for drug testing; however, the next-generation cell activity monitoring technology for 3D cell culture is still challenging. Conventionally, drug efficacy evaluation and cell growth heavily rely on cell staining assays, using optical devices or flow cytometry. Here, we report a dual-function polymer scaffold (DFPS) composed of thermosensitive, silver flake- and gold nanoparticle-decorated polymers, enabling conductance change upon cell proliferation or death for cell activity monitoring and drug screening.