An official website of the United States government
In automated sleep monitoring systems, bed occupancy detection is the foundation or the first step before other downstream tasks, such as inferring sleep activities and vital signs. The existing methods do not generalize well to real-world environments due to single environment settings and rely on threshold-based approaches. Manually selecting thresholds requires observing a large amount of data and may not yield optimal results. In contrast, acquiring extensive labeled sensory data poses significant challenges regarding cost and time. Hence, developing models capable of generalizing across diverse environments with limited data is imperative. This paper introduces SeismoDot, which consists of a self-supervised learning module and a spectral-temporal feature fusion module for bed occupancy detection. Unlike conventional methods that require separate pre-training and fine-tuning, our self-supervised learning module is co-optimized with the primary target task, which directs learned representations toward a task-relevant embedding space while expanding the feature space. The proposed feature fusion module enables the simultaneous exploitation of temporal and spectral features, enhancing the diversity of information from both domains. By combining these techniques, SeismoDot expands the diversity of embedding space for both the temporal and spectral domains to enhance its generalizability across different environments. SeismoDot not only achieves high accuracy (98.49%) and F1 scores (98.08%) across 13 diverse environments, but it also maintains high performance (97.01% accuracy and 96.54% F1 score) even when trained with just 20% (4 days) of the total data. This demonstrates its exceptional ability to generalize across various environmental settings, even with limited data availability.
more »
« less
This content will become publicly available on June 9, 2026
Multi-granularity Supervised Contrastive Learning with Online Adaptation for Contactless In-bed Posture Classification
In-bed postures offer valuable information about an individual's sleep quality and overall health conditions, particularly for patients with sleep apnea. However, current in-bed posture classification systems lack privacy-friendly and easy-to-install options. Furthermore, existing solutions do not consider variations between patients and are typically trained only once, neglecting the utilization of time consistency and unlabeled data from new patients. To address these limitations, this paper builds on a seismic sensor to introduce a novel sleep posture framework, which comprises two main components, namely, the Multi-Granularity Supervised Contrastive Learning (MGSCL) module and the ensemble Online Adaptation (oa) module. Unlike most existing contrastive learning frameworks that operate at the sample level, MGSCL leverages multi-granular information, operating not only at the sample level but also at the group level. The oa module enables the model to adapt to new patient data while ensuring time consistency in sleep posture predictions. Additionally, it quantifies model uncertainty to generate weighted predictions, further enhancing performance. Evaluated on a dataset of 100 patients collected at a clinical research center, MGSCLoa achieved an average accuracy of 91.67% and an average F1 score of 91.53% with only 40 seconds of labeled data per posture. In a Phase 2 evaluation with 11 participants over 13 nights in home settings, the framework reached an average accuracy of 85.37% and a weighted F1 score of 83.59% using just 3 minutes of labeled data per common posture for each participant. These results underscore the potential of seismic sensor-based in-bed posture classification for assessing sleep quality and related health conditions.
more »
« less
- Award ID(s):
- 2340049
- PAR ID:
- 10629694
- Publisher / Repository:
- ACM
- Date Published:
- Journal Name:
- Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
- Volume:
- 9
- Issue:
- 2
- ISSN:
- 2474-9567
- Page Range / eLocation ID:
- 1 to 32
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
The COVID-19 pandemic has intensified the need for home-based cardiac health monitoring systems. Despite advancements in electrocardiograph (ECG) and phonocardiogram (PCG) wearable sensors, accurate heart sound segmentation algorithms remain understudied. Existing deep learning models, such as convolutional neural networks (CNN) and recurrent neural networks (RNN), struggle to segment noisy signals using only PCG data. We propose a two-step heart sound segmentation algorithm that analyzes synchronized ECG and PCG signals. The first step involves heartbeat detection using a CNN-LSTM-based model on ECG data, and the second step focuses on beat-wise heart sound segmentation with a 1D U-Net that incorporates multi-modal inputs. Our method leverages temporal correlation between ECG and PCG signals to enhance segmentation performance. To tackle the label-hungry issue in AI-supported biomedical studies, we introduce a segment-wise contrastive learning technique for signal segmentation, overcoming the limitations of traditional contrastive learning methods designed for classification tasks. We evaluated our two-step algorithm using the PhysioNet 2016 dataset and a private dataset from Bayland Scientific, obtaining a 96.43 F1 score on the former. Notably, our segment-wise contrastive learning technique demonstrated effective performance with limited labeled data. When trained on just 1% of labeled PhysioNet data, the model pre-trained on the full unlabeled dataset only dropped 2.88 in the F1 score, outperforming the SimCLR method. Overall, our proposed algorithm and learning technique present promise for improving heart sound segmentation and reducing the need for labeled data.more » « less
-
Sleep is a vital physiological state that significantly impacts overall health. Continuous monitoring of sleep posture, heart rate, respiratory rate, and body movement is crucial for diagnosing and managing sleep disorders. Current monitoring solutions often disrupt natural sleep due to discomfort or raise privacy and instrumentation concerns. We introduce PillowSense, a fabric-based sleep monitoring system seamlessly integrated into a pillowcase. PillowSense utilizes a dual-layer fabric design. The top layer comprises conductive fabrics for sensing electrocardiogram (ECG) and surface electromyogram (sEMG), while the bottom layer features pressure-sensitive fabrics to monitor sleep location and movement. The system processes ECG and sEMG signals sequentially to infer multiple sleep variables and incorporates an adversarial neural network to enhance posture classification accuracy. We fabricate prototypes using off-the-shelf hardware and conduct both lab-based and in-the-wild longitudinal user studies to evaluate the system's effectiveness. Across 151 nights and 912.2 hours of real-world sleep data, the system achieves an F1 score of 88% for classifying seven sleep postures, and clinically-acceptable accuracy in vital sign monitoring. PillowSense's comfort, washability, and robustness in multi-user scenarios underscore its potential for unobtrusive, large-scale sleep monitoring.more » « less
-
Automatic lying posture tracking is an important factor in human health monitoring. The increasing popularity of the wrist-based trackers provides the means for unobtrusive, affordable, and long-term monitoring with minimized privacy concerns for the end-users and promising results in detecting the type of physical activity, step counting, and sleep quality assessment. However, there is limited research on development of accurate and efficient lying posture tracking models using wrist-based sensor. Our experiments demonstrate a major drop in the accuracy of the lying posture tracking using wrist-based accelerometer sensor due to the unpredictable noise from arbitrary wrist movements and rotations while sleeping. In this paper, we develop a deep transfer learning method that improves performance of lying posture tracking using noisy data from wrist sensor by transferring the knowledge from an initial setting which contains both clean and noisy data. The proposed solution develops an optimal mapping model from the noisy data to the clean data in the initial setting using LSTM sequence regression, and reconstruct clean synthesized data in another setting where no noisy sensor data is available. This increases the lying posture tracking F1-Score by 24.9% for left-wrist and by 18.1% for right-wrist sensors comparing to the case without mapping.more » « less
-
Effective Posture Classification using Statistically Significant Data from Flexible Pressure SensorsAdvancements in flexible and printable sensor technologies to overcome the limitations of conventional rigid counterparts offer an excellent opportunity to design various healthcare applications for humans, and their potential flexibility can be used in real-time health monitoring and personalized physical conditions with minimal or no inconvenience. However, managing a large volume of obtained sensor datasets and ensuring accurate predictions can take time and effort. While statistical analysis and the Pearson correlation coefficient can reduce data volume, whether this would lead to losing important information and affect downstream application performance is still being determined. In this paper, we use posture classification as an exemplar of timely services in digital healthcare, especially for bedsores or decubitus ulcers. Our sensors, placed under hospital beds, have a thickness of just 0.4mm and collect pressure data from 28 sensors (7 by 4) at an 8 Hz cycle, categorizing postures into 4 types from 5 patients. We then collected sensor data to explore the possibility of using a small number of pressure sensors for patient posture classification. Next, we apply a statistical analysis to the datasets obtained to select the featured sensor data cells and evaluate the performance of posture classification models on various groups of sensors. Our evaluation involves the analysis of reduced datasets through statistical methods and the Pearson correlation coefficient. The classification performance using datasets comprising 5 featured and 28 sensors are 0.93 and 0.99, respectively. These results suggest comparable performance and the viability of useful classifiers for both cases. Consequently, comparable posture classification performance can be achieved using only 17.9% of the entire dataset.more » « less
