Visual Scene Understanding for Enhanced EMG Gesture Recognition.

This work presents a multimodal approach combining electromyography (EMG) and computer vision (CV) for robust real-time gesture recognition in a real-world setting. A context-aware framework is proposed for myoelectric prosthesis control, wherein EMG hand gesture recognition is augmented by the visual detection of objects of interest in a scene, effectively mitigating risks of false movements. By supporting EMG gesture predictions produced by a Siamese deep convolution neural network (SDCNN) with context derived from object detection using a tailored YOLO computer vision model, the system prevents false detection during gesture onset and during static gesture maintenance.

ChatGPT for phenotypes extraction: one model to rule them all?

Information Extraction (IE) is a core task in Natural Language Processing (NLP) where the objective is to identify factual knowledge in textual documents (often unstructured), and feed downstream use cases with the resulting output. In genomic medicine for instance, being able to extract the most precise list of phenotypes associated to a patient allows to improve genetic disease diagnostic, which represents a vital step in the modern deep phenotyping approach. As most of the phenotypic information lies in clinical reports, the challenge is to build an IE pipeline to automatically recognize phenotype concepts from free-text notes.