Sleep Posture Recognition Method Based on Sparse Body Pressure Features
Abstract
:1. Introduction
- A model of an airbag mattress that can recognize sleeping posture and modify its softness and stiffness at numerous spots is offered. The methods for recognizing sleeping positions and adjusting firmness utilize identical hardware configurations, hence diminishing system complexity.
- On the basis of using entropy-weighted scores to filter base learners, the complementarity scores between models are combined to filter two sets of base classifier combinations. These two approaches can greatly enhance the complementary nature of the model in ensemble learning, where selected combinations of base classifiers and convolutional neural networks (CNNs) are used together to build the base learning layer of the model. Among other things, CNNs can explore deep relationships between features.
- An ensemble learning model combining voting and stacking was developed. It can not only further extract data features based on the foundational model, thus diminishing the bias of an individual model, but also streamline the model’s structure with hyperparameters optimized for each base model utilizing the Ivy optimization algorithm to enhance model performance.
2. Related Work
3. System Design
4. Methodology
4.1. Sleeping Position Definition
4.2. Data Collection
4.3. Feature Engineering
4.4. Ensemble Learning
4.5. Judging Criteria
4.6. Selection of Base Learners
4.7. Characteristic Importance Analysis
4.8. Sleep Posture Recognition Method
4.9. Hyperparameter
5. Results
5.1. Analysis of Sleeping Position Classification Results
5.2. Comparison of Results
6. Discussion
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Ramar, K.; Malhotra, R.K.; Carden, K.A.; Martin, J.L.; Abbasi-Feinberg, F.; Aurora, R.N.; Kapur, V.K.; Olson, E.J.; Rosen, C.L.; Rowley, J.A. Sleep is essential to health: An American Academy of Sleep Medicine position statement. J. Clin. Sleep Med. 2021, 17, 2115–2119. [Google Scholar] [CrossRef]
- Lim, D.C.; Najafi, A.; Afifi, L.; Bassetti, C.L.; Buysse, D.J.; Han, F.; Högl, B.; Melaku, Y.A.; Morin, C.M.; Pack, A.I. The need to promote sleep health in public health agendas across the globe. Lancet Public Health 2023, 8, e820–e826. [Google Scholar] [CrossRef] [PubMed]
- Ji, K.-H.; Yun, C.-H. Emerging Technologies to Track and Improve Sleep Health. Sleep Med. Clin. 2025, 20, 47–55. [Google Scholar] [CrossRef] [PubMed]
- Dashti, H.S.; Cade, B.E.; Stutaite, G.; Saxena, R.; Redline, S.; Karlson, E.W. Sleep health, diseases, and pain syndromes: Findings from an electronic health record biobank. Sleep 2021, 44, zsaa189. [Google Scholar] [CrossRef] [PubMed]
- Zhang, Y.; Xiao, A.; Zheng, T.; Xiao, H.; Huang, R. The relationship between sleeping position and sleep quality: A flexible sensor-based study. Sensors 2022, 22, 6220. [Google Scholar] [CrossRef]
- Yo, S.W.; Joosten, S.A.; Wimaleswaran, H.; Mansfield, D.; Thomson, L.; Landry, S.A.; Edwards, B.A.; Hamilton, G.S. Body position during laboratory and home polysomnography compared to habitual sleeping position at home. J. Clin. Sleep Med. 2022, 18, 2103–2111. [Google Scholar] [CrossRef]
- Piele, D.; Ilie, E.; Rusu, L.; Marin, M.I. Relevance of Surface Electromyography Assessment and Sleep Impairment in Scoliosis: A Pilot Study. Appl. Sci. 2023, 13, 11108. [Google Scholar] [CrossRef]
- Gattinoni, L.; Tognoni, G.; Pesenti, A.; Taccone, P.; Mascheroni, D.; Labarta, V.; Malacrida, R.; Di Giulio, P.; Fumagalli, R.; Pelosi, P. Effect of prone positioning on the survival of patients with acute respiratory failure. N. Engl. J. Med. 2001, 345, 568–573. [Google Scholar] [CrossRef]
- Mäki-Turja-Rostedt, S.; Leino-Kilpi, H.; Korhonen, T.; Vahlberg, T.; Haavisto, E. Consistent practice for pressure ulcer prevention in long-term older people care: A quasi-experimental intervention study. Scand. J. Caring sciences 2021, 35, 962–978. [Google Scholar] [CrossRef]
- Harvey, A.G.; Dong, L.; Hein, K.; Yu, S.H.; Martinez, A.J.; Gumport, N.B.; Smith, F.L.; Chapman, A.; Lisman, M.; Mirzadegan, I.A. A randomized controlled trial of the Transdiagnostic Intervention for Sleep and Circadian Dysfunction (TranS-C) to improve serious mental illness outcomes in a community setting. J. Consult. Clin. Psychol. 2021, 89, 537. [Google Scholar] [CrossRef]
- Gottesman, R.F.; Lutsey, P.L.; Benveniste, H.; Brown, D.L.; Full, K.M.; Lee, J.-M.; Osorio, R.S.; Pase, M.P.; Redeker, N.S.; Redline, S. Impact of sleep disorders and disturbed sleep on brain health: A scientific statement from the American Heart Association. Stroke 2024, 55, e61–e76. [Google Scholar] [CrossRef] [PubMed]
- Zhang, L.; Li, G.; Bao, Y.; Liu, M. Role of sleep disorders in patients with cardiovascular disease: A systematic review. Int. J. Cardiol. Cardiovasc. Risk Prev. 2024, 21, 200257. [Google Scholar] [CrossRef]
- Li, X.; Gong, Y.; Jin, X.; Shang, P. Sleep posture recognition based on machine learning: A systematic review. Pervasive Mob. Comput. 2023, 90, 101752. [Google Scholar] [CrossRef]
- Jakkaew, P.; Onoye, T. Non-contact respiration monitoring and body movements detection for sleep using thermal imaging. Sensors 2020, 20, 6307. [Google Scholar] [CrossRef] [PubMed]
- Özdil, A.; Yılmaz, B. Automatic body part and pose detection in medical infrared thermal images. Quant. InfraRed Thermogr. J. 2022, 19, 223–238. [Google Scholar] [CrossRef]
- Khan, A.; Kim, C.; Kim, J.-Y.; Nam, Y. Sleep Posture Classification Using RGB and Thermal Cameras Based on Deep Learning Model. CMES-Comput. Model. Eng. Sci. 2024, 140, 1729–1755. [Google Scholar] [CrossRef]
- Lai, D.K.-H.; Zha, L.-W.; Leung, T.Y.-N.; Tam, A.Y.-C.; So, B.P.-H.; Lim, H.-J.; Cheung, D.S.K.; Wong, D.W.-C.; Cheung, J.C.-W. Dual ultra-wideband (UWB) radar-based sleep posture recognition system: Towards ubiquitous sleep monitoring. Eng. Regen. 2023, 4, 36–43. [Google Scholar] [CrossRef]
- Lai, D.K.-H.; Tam, A.Y.-C.; So, B.P.-H.; Chan, A.C.-H.; Zha, L.-W.; Wong, D.W.-C.; Cheung, J.C.-W. Deciphering Optimal Radar Ensemble for Advancing Sleep Posture Prediction through Multiview Convolutional Neural Network (MVCNN) Approach Using Spatial Radio Echo Map (SREM). Sensors 2024, 24, 5016. [Google Scholar] [CrossRef]
- Liu, X.; Jiang, W.; Chen, S.; Xie, X.; Liu, H.; Cai, Q.; Tong, X.; Shi, T.; Qu, W. PosMonitor: Fine-grained sleep posture recognition with mmWave radar. IEEE Internet Things J. 2023, 11, 11175–11189. [Google Scholar] [CrossRef]
- Lai, D.K.-H.; Yu, Z.-H.; Leung, T.Y.-N.; Lim, H.-J.; Tam, A.Y.-C.; So, B.P.-H.; Mao, Y.-J.; Cheung, D.S.K.; Wong, D.W.-C.; Cheung, J.C.-W. Vision Transformers (ViT) for blanket-penetrating sleep posture recognition using a triple ultra-wideband (UWB) radar system. Sensors 2023, 23, 2475. [Google Scholar] [CrossRef]
- Jeon, Y.; Kim, S.; Kang, S. A Method for Detecting Movement and Posture During Sleep Using an Acceleration Sensor of a Wearable Device. IEMEK J. Embed. Syst. Appl. 2022, 17, 1–7. [Google Scholar]
- Yoshihi, M.; Okada, S.; Wang, T.; Kitajima, T.; Makikawa, M. Estimating sleep stages using a head acceleration sensor. Sensors 2021, 21, 952. [Google Scholar] [CrossRef]
- Intongkum, C.; Sasiwat, Y.; Sengchuai, K.; Booranawong, A.; Phukpattaranont, P. Monitoring and Classification of Human Sleep Postures, Seizures, and Falls From Bed Using Three-Axis Acceleration Signals and Machine Learning. SN Comput. Sci. 2023, 5, 104. [Google Scholar] [CrossRef]
- Vu, H.-D.; Tran, D.-N.; Pham, H.-H.; Pham, D.-D.; Can, K.-L.; Dao, T.-H.; Tran, D.-T. Human sleep position classification using a lightweight model and acceleration data. Sleep Breath. 2025, 29, 95. [Google Scholar] [CrossRef]
- He, C.; Fang, Z.; Liu, S.; Wu, H.; Li, X.; Wen, Y.; Lin, J. A smart detection method for sleep posture based on a flexible sleep monitoring belt and vital sign signals. Heliyon 2024, 10, e31839. [Google Scholar] [CrossRef] [PubMed]
- Breuss, A.; Gnarra, O.; Fujs, M.; Schmidt, M.; Riener, R. Sleep position classification with a compact pressure textile sensor mattress using convolutional neural networks. Biomed. Signal Process. Control 2024, 90, 105775. [Google Scholar] [CrossRef]
- Diao, H.; Chen, C.; Yuan, W.; Amara, A.; Tamura, T.; Fan, J.; Meng, L.; Liu, X.; Chen, W. Deep residual networks for sleep posture recognition with unobtrusive miniature scale smart mat system. IEEE Trans. Biomed. Circuits Syst. 2021, 15, 111–121. [Google Scholar] [CrossRef]
- Yoon, J.; Moon, A.; Son, S.W. Effective Posture Classification Using Statistically Significant Data from Flexible Pressure Sensors. IEEE J. Flex. Electron. 2024, 3, 173–180. [Google Scholar] [CrossRef]
- Chao, Y.; Liu, T.; Shen, L.-M. Method of recognizing sleep postures based on air pressure sensor and convolutional neural network: For an air spring mattress. Eng. Appl. Artif. Intell. 2023, 121, 106009. [Google Scholar] [CrossRef]
- Li, Z.; Zhou, Y.; Zhou, G. A dual fusion recognition model for sleep posture based on air mattress pressure detection. Sci. Rep. 2024, 14, 11084. [Google Scholar] [CrossRef]
- Peruzzi, G.; Galli, A.; Giorgi, G.; Pozzebon, A. Sleep Posture Detection via Embedded Machine Learning on a Reduced Set of Pressure Sensors. Sensors 2025, 25, 458. [Google Scholar] [CrossRef] [PubMed]
- Xu, X.; Mo, Q.; Wang, Z.; Zhao, Y.; Li, C. Classification of Sleeping Position Using Enhanced Stacking Ensemble Learning. Entropy 2024, 26, 817. [Google Scholar] [CrossRef]
- Verdonck, T.; Baesens, B.; Óskarsdóttir, M.; vanden Broucke, S. Special issue on feature engineering editorial. Mach. Learn. 2024, 113, 3917–3928. [Google Scholar] [CrossRef]
- De Leva, P. Adjustments to Zatsiorsky-Seluyanov’s segment inertia parameters. J. Biomech. 1996, 29, 1223–1230. [Google Scholar] [CrossRef]
- Winter, D.A. Biomechanics and Motor Control of Human Movement; John Wiley & Sons: Hoboken, NJ, USA, 2009. [Google Scholar]
- Dong, X.; Yu, Z.; Cao, W.; Shi, Y.; Ma, Q. A survey on ensemble learning. Front. Comput. Sci. 2020, 14, 241–258. [Google Scholar] [CrossRef]
- Biau, G.; Scornet, E. A random forest guided tour. Test 2016, 25, 197–227. [Google Scholar] [CrossRef]
- Niazkar, M.; Menapace, A.; Brentan, B.; Piraei, R.; Jimenez, D.; Dhawan, P.; Righetti, M. Applications of XGBoost in water resources engineering: A systematic literature review (Dec 2018–May 2023). Environ. Model. Softw. 2024, 174, 105971. [Google Scholar] [CrossRef]
- Awe, O.O.; Opateye, G.O.; Johnson, C.A.G.; Tayo, O.T.; Dias, R. Weighted hard and soft voting ensemble machine learning classifiers: Application to anaemia diagnosis. In Sustainable Statistical and Data Science Methods and Practices: Reports from LISA 2020 Global Network, Ghana, 2022; Springer: Cham, Switzerland, 2024; pp. 351–374. [Google Scholar]
- Luo, S.; Wang, B.; Gao, Q.; Wang, Y.; Pang, X. Stacking integration algorithm based on CNN-BiLSTM-Attention with XGBoost for short-term electricity load forecasting. Energy Rep. 2024, 12, 2676–2689. [Google Scholar] [CrossRef]
- Bisong, E. Logistic regression. In Building Machine Learning and Deep Learning Models on Google Cloud Platform: A Comprehensive Guide for Beginners; Apress: Berkeley, CA, USA, 2019; pp. 243–250. [Google Scholar]
- Reddy, E.M.K.; Gurrala, A.; Hasitha, V.B.; Kumar, K.V.R. Introduction to Naive Bayes and a review on its subtypes with applications. In Bayesian Reasoning and Gaussian Processes for Machine Learning Applications; Chapman and Hall/CRC: Boca Raton, FL, USA, 2022; pp. 1–14. [Google Scholar]
- Charbuty, B.; Abdulazeez, A. Classification based on decision tree algorithm for machine learning. J. Appl. Sci. Technol. Trends 2021, 2, 20–28. [Google Scholar] [CrossRef]
- Zhang, S. Challenges in KNN classification. IEEE Trans. Knowl. Data Eng. 2021, 34, 4663–4675. [Google Scholar] [CrossRef]
- Abdullah, D.M.; Abdulazeez, A.M. Machine learning applications based on SVM classification a review. Qubahan Acad. J. 2021, 1, 81–90. [Google Scholar] [CrossRef]
- Villacampa-Calvo, C.; Zaldívar, B.; Garrido-Merchán, E.C.; Hernández-Lobato, D. Multi-class Gaussian process classification with noisy inputs. J. Mach. Learn. Res. 2021, 22, 1–52. [Google Scholar]
- Kislay, K.; Singh, S.; Joshi, S.; Dutta, R.; Flint, J.S.G.; Zhu, K. Evaluating K-Fold Cross Validation for Transformer Based Symbolic Regression Models. arXiv 2024, arXiv:2410.21896. [Google Scholar]
- Rimal, Y.; Sharma, N.; Alsadoon, A. The accuracy of machine learning models relies on hyperparameter tuning: Student result classification using random forest, randomized search, grid search, bayesian, genetic, and optuna algorithms. Multimed. Tools Appl. 2024, 83, 74349–74364. [Google Scholar] [CrossRef]
- Ghasemi, M.; Zare, M.; Trojovský, P.; Rao, R.V.; Trojovská, E.; Kandasamy, V. Optimization based on the smart behavior of plants with its engineering applications: Ivy algorithm. Knowl.-Based Syst. 2024, 295, 111850. [Google Scholar] [CrossRef]
Body Types | Weight (/kg) | Height (/m) | BMI (kg/m2) |
---|---|---|---|
Lighter | 48.3 | 1.66 | 17.52 |
Standard | 64.4 | 1.72 | 21.77 |
Heavier | 76.3 | 1.76 | 24.63 |
Sleep Posture | (/kPa) | (/kPa) | (/kPa) | (/kPa) |
---|---|---|---|---|
Initial air pressure | 1.296 | 1.366 | 1.324 | 1.231 |
Supine | 4.797 | 5.388 | 4.341 | 2.246 |
Pressed-legged supine | 5.862 | 5.047 | 5.494 | 2.645 |
Crossed-legged supine | 6.107 | 5.55 | 6.752 | 1.835 |
Side lying | 4.812 | 3.983 | 5.275 | 3.37 |
Baby-side lying | 4.658 | 3.776 | 4.759 | 2.523 |
Prone | 5.212 | 3.854 | 4.914 | 1.539 |
Edge sleeper | 4.851 | 4.532 | 4.998 | 2.217 |
Model | Hyperparameter |
---|---|
RF | n_estimators = 177, max_depth = 8, min_samples_split = 7. |
XGBoost | C = 7.3912, gamma = 0.049. |
SVM | n_estimators = 76, max_depth = 4, learning_rate = 0.254, subsam-ple = 0.7783, colsample_bytree = 0.7194. |
Gradient Boosting | n_estimators = 171, max_depth = 9, learning_rate = 0.2740. |
Model | Accuracy | Precision | F1 | Kappa |
---|---|---|---|---|
GP | 91.54% | 91.61% | 91.53% | 90.62% |
XGBoost | 93.18% | 93.20% | 93.18% | 92.33% |
RF | 94.21% | 94.25% | 94.15% | 93.57% |
SVM | 94.31% | 94.35% | 94.31% | 93.65% |
CNNs | 94.66% | 94.77% | 94.64% | 94.06% |
Our model | 95.63% | 95.70% | 95.63% | 94.90% |
Sensor | Type | Model | Accuracy |
---|---|---|---|
RGB and thermal cameras [16] | non-contact | Normally distributed sequences | 99% |
Triple ultra-wideband radar [20] | non-contact | Swin Transformer | 80.8% |
Triaxial accelerometer sensors [23] | contact | KNN | 93% |
Single accelerometer [24] | contact | AnpoNet | 94.67% |
Airbag pressure sensor [29] | contact | CNNs | 99.3% |
Airbag pressure sensor [30] | contact | AdaBoost-SVM | 99.9% |
Pressure sensors [31] | contact | SVM | 90.00% |
Sparse airbag pressure sensor | contact | Our model | 95.63% |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Li, C.; Ren, G.; Wang, Z. Sleep Posture Recognition Method Based on Sparse Body Pressure Features. Appl. Sci. 2025, 15, 4920. https://doi.org/10.3390/app15094920
Li C, Ren G, Wang Z. Sleep Posture Recognition Method Based on Sparse Body Pressure Features. Applied Sciences. 2025; 15(9):4920. https://doi.org/10.3390/app15094920
Chicago/Turabian StyleLi, Changyun, Guoxin Ren, and Zhibing Wang. 2025. "Sleep Posture Recognition Method Based on Sparse Body Pressure Features" Applied Sciences 15, no. 9: 4920. https://doi.org/10.3390/app15094920
APA StyleLi, C., Ren, G., & Wang, Z. (2025). Sleep Posture Recognition Method Based on Sparse Body Pressure Features. Applied Sciences, 15(9), 4920. https://doi.org/10.3390/app15094920