# Identity and Posture Recognition in Smart Beds with Deep Multitask Learning

arXiv: https://arxiv.org/abs/2104.02159 · HTML: https://mlsanity.com/paper/2104.02159/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 40 references that are in the map.
- First posted on arXiv 5 Apr 2021.

## Builds on (most cited first, 4 of 4)

- [OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1812.08008/) (2018)
- [Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks](https://mlsanity.com/paper/1604.02878/) (2016)
- [DeepSaliency: Multi-Task Deep Neural Network Model for Salient Object Detection](https://mlsanity.com/paper/1510.05484/) (2015)
- [In-Bed Pose Estimation: Deep Learning with Shallow Dataset](https://mlsanity.com/paper/1711.01005/) (2017)

## Built on by (most cited first, 3 of 3)

- [Estimating Pose from Pressure Data for Smart Beds with Deep Image-based Pose Estimators](https://mlsanity.com/paper/2206.06518/) (2022)
- [Human Pose Estimation from Ambiguous Pressure Recordings with Spatio-temporal Masked Transformers](https://mlsanity.com/paper/2303.05691/) (2023)
- [Sleep Position Classification using Transfer Learning for Bed-based Pressure Sensors](https://mlsanity.com/paper/2505.08111/) (2025)

## Abstract (arXiv)

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.