SIM-CNN: Self-Supervised Individualized Multimodal Learning for Stress Prediction on Nurses Using Biosignals
Jul 28, 2023
Sprecher:innen
Sunmin Eom
Sprecher:in · 0 Follower:innen
Sunwoo Eom
Sprecher:in · 0 Follower:innen
Peter Washington
Sprecher:in · 0 Follower:innen
Über
Precise stress recognition from biosignals is inherently challenging due to the heterogeneous nature of stress, individual physiological differences, and scarcity of labeled data. To address these issues, we developed SIM-CNN, a self-supervised learning (SSL) method for personalized stress-recognition models using multimodal biosignals. SIM-CNN involves training a multimodal 1D convolutional neural network (CNN) that leverages SSL to utilize massive unlabeled data, optimizing individual parameters and hyperparameters for precision health. SIM-CNN is evaluated on a real-world multimodal dataset collected from nurses that consists of 1,250 hours of biosignals, 83 hours of which are explicitly labeled with stress levels. SIM-CNN is pre-trained on the unlabeled biosignal data with next-step time series forecasting and fine-tuned on the labeled data for stress classification. Compared to SVMs and baseline CNNs with an identical architecture but without self-supervised pre-training, SIM-CNN shows clear improvements in the average AUC and accuracy, but a further examination of the data also suggests some intrinsic limitations of patient-specific stress recognition using biosignals recorded in the wild.Precise stress recognition from biosignals is inherently challenging due to the heterogeneous nature of stress, individual physiological differences, and scarcity of labeled data. To address these issues, we developed SIM-CNN, a self-supervised learning (SSL) method for personalized stress-recognition models using multimodal biosignals. SIM-CNN involves training a multimodal 1D convolutional neural network (CNN) that leverages SSL to utilize massive unlabeled data, optimizing individual paramete…
Gefällt euch das Format? Vertraut auf SlidesLive, um euer nächstes Event festzuhalten!
Professionelle Aufzeichnung und Livestreaming – weltweit.
Freigeben
Empfohlene Videos
Präsentationen, deren Thema, Kategorie oder Sprecher:in ähnlich sind
Learning Controllable Degradation for Real-World Super-Resolution via Constrained Flows
Später ansehen
Seobin Park, …
Towards Unbiased Training in Federated Open-world Semi-supervised Learning
Später ansehen
Jie Zhang, …
Constraint Reasoning Embedded Structured Prediction
Später ansehen
Nan Jiang, …
Causal Modeling of Policy Interventions From Treatments-Outcomes Sequences
Später ansehen
Çağlar Hızlı, …
Hierarchical Programmatic Reinforcement Learning via Learning to Compose Programs
Später ansehen
Guanting Liu, …