Identity and Posture Recognition in Smart Beds with Deep Multitask Learning

TL;DR

This paper introduces a deep multitask learning model for accurate identification of subjects and their sleep postures using pressure mapping data, achieving high accuracy and robustness for clinical and smart home applications.

Contribution

The study presents a novel deep learning approach that simultaneously detects subjects and sleep postures with high accuracy, improving over previous methods.

Findings

Achieved up to 99% accuracy in posture classification.

Successfully identified subjects with minimal errors.

Learning both tasks simultaneously enhances performance.

Abstract

Sleep posture analysis is widely used for clinical patient monitoring and sleep studies. Earlier research has revealed that sleep posture highly influences symptoms of diseases such as apnea and pressure ulcers. In this study, we propose a robust deep learning model capable of accurately detecting subjects and their sleeping postures using the publicly available data acquired from a commercial pressure mapping system. A combination of loss functions is used to discriminate subjects and their sleeping postures simultaneously. The experimental results show that our proposed method can identify the patients and their in-bed posture with almost no errors in a 10-fold cross-validation scheme. Furthermore, we show that our network achieves an average accuracy of up to 99% when faced with new subjects in a leave-one-subject-out validation procedure on the three most common sleeping posture categories. We demonstrate the effects of the combined cost function over its parameter and show that learning both tasks simultaneously improves performance significantly. Finally, we evaluate our proposed pipeline by testing it over augmented images of our dataset. The proposed algorithm can ultimately be used in clinical and smart home environments as a complementary tool with other available automated patient monitoring systems.