ABSTRACT
This paper introduces LIBS, a light-weight and inexpensive wearable sensing system, that can capture electrical activities of human brain, eyes, and facial muscles with two pairs of custom-built flexible electrodes each of which is embedded on an off-the-shelf foam earplug. A supervised non-negative matrix factorization algorithm to adaptively analyze and extract these bioelectrical signals from a single mixed in-ear channel collected by the sensor is also proposed. While LIBS can enable a wide class of low-cost self-care, human computer interaction, and health monitoring applications, we demonstrate its medical potential by developing an autonomous whole-night sleep staging system utilizing LIBS's outputs. We constructed a hardware prototype from off-the-shelf electronic components and used it to conduct 38 hours of sleep studies on 8 participants over a period of 30 days. Our evaluation results show that LIBS can monitor biosignals representing brain activities, eye movements, and muscle contractions with excellent fidelity such that it can be used for sleep stage classification with an average of more than 95% accuracy.
Supplemental Material
- American Academy of Sleep Medicine. http://www.aasmnet.org/. Accessed: August 03, 2016.Google Scholar
- K. A. I. Aboalayon, W. S. Almuhammadi, and M. Faezipour. A comparison of different machine learning algorithms using single channel EEG signal for classifying human sleep stages. In Proceedings of 2015 IEEE Long Island Systems, Applications and Technology Conference (LISAT), pages 1--6, 2015.Google ScholarCross Ref
- C. Alloway, R. Ogilvie, and C. Shapiro. The alpha attenuation test: assessing excessive daytime sleepiness in narcolepsy-cataplexy. Sleep, 20(4):258âĂŤ266, 1997.Google ScholarCross Ref
- Aware. https://goo.gl/eh48HA. Accessed: August 03, 2016.Google Scholar
- Basis. http://www.mybasis.com/. Accessed: August 03, 2016.Google Scholar
- M. Bleichner, M. Lundbeck, M. Selisky, F. Minow, M. Jäger, R. Emkes, S. Debener, and M. D. Vos. Exploring miniaturized EEG electrodes for brain-computer interfaces. An EEG you do not see? Physiological Reports, 3(4), 2015.Google Scholar
- C. Damon, A. Liutkus, A. Gramfort, and S. Essid. Non-negative matrix factorization for single-channel EEG artifact rejection. In Proceedings of 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 1177--1181, 2013.Google ScholarCross Ref
- S. Essid. A single-class SVM based algorithm for computing an identifiable NMF. In Proceedings of 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 2053--2056, 2012.Google ScholarCross Ref
- J. Fell, J. Roschke, K. Mann, and C. Schaffner. Discrimination of sleep stages: a comparison between spectral and nonlinear EEG measures. Electroencephalography and Clinical Neurophysiology, 98(5):401--410, 1996.Google ScholarCross Ref
- Fitbit. http://www.fitbit.com/. Accessed: August 03, 2016.Google Scholar
- V. Goverdovsky, D. Looney, P. Kidmose, and D. Mandic. In-ear EEG from viscoelastic generic earpieces: Robust and unobtrusive 24/7 monitoring. IEEE Sensors Journal, 2015.Google Scholar
- M. Grenness. Mapping Morphologic Change in the External Ear. In Masters dissertation. Hobart, Australia: University of Tasmania, 1999.Google Scholar
- W. Gu, Z. Yang, L. Shangguan, W. Sun, K. Jin, and Y. Liu. InEar BioFeedController: A Headset For Hands-Free And Eyes-Free Interaction With Mobile Devices. In CHI, pages 1293--1298, 2013. Google ScholarDigital Library
- S. Gudmundsson, T. Runarsson, and S. Sigurdsson. Automatic Sleep Staging Using Support Vector Machines with Posterior Probability Estimates. In Proceedings of the International Conference on Computational Intelligence for Modelling, Control and Automation and International Conference on Intelligent Agents, Web Technologies and Internet Commerce (CIMCA-IAWTIC), pages 366--372, 2005. Google ScholarDigital Library
- H. Hallez, B. Vanrumste, R. Grech, J. Muscat, W. Clercq, A. Vergult, Y. D'Asseler, K. Camilleri, S. Fabri, S. Huffel, and I. Lemahieu. Review on solving the forward problem in EEG source analysis. Journal of NeuroEngineering and Rehabilitation, 4(1):1--29, 2007.Google ScholarCross Ref
- D. He, E. Winokur, and C. Sodini. An ear-worn continuous ballistocardiogram (BCG) sensor for cardiovascular monitoring. In Proceedings of 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pages 5030--5033, 2012.Google ScholarCross Ref
- Jawbone. https://jawbone.com/. Accessed: August 03, 2016.Google Scholar
- KOKOON. https://kokoon.io/. Accessed: August 03, 2016.Google Scholar
- B. Koley and D. Dey. An Ensemble System for Automatic Sleep Stage Classification Using Single Channel EEG Signal. Comput. Biol. Med., 42(12):1186--1195, 2012. Google ScholarDigital Library
- A. Krakovska and K. Mezeiova. Automatic sleep scoring: A search for an optimal combination of measures. Artificial Intelligence in Medicine, 53(1):25--33, 2011. Google ScholarDigital Library
- A. Kulkarni, P. Rao, S. Natarajan, A. Goldman, V. S. Sabbisetti, Y. Khater, N. Korimerla, V. Chandrasekar, R. A. Mashelkar, and S. Sengupta. Soft, curved electrode systems capable of integration on the auricle as a persistent brain-computer interface. In Proceedings of the National Academy of Sciences of the United States of America, 2015.Google Scholar
- C. Kushida et al. Practice parameters for the indications for polysomnography and related procedures: an update for 2005. Sleep, 28(4):499--521, 2005.Google ScholarCross Ref
- J. H. Lee, S. M. Lee, H. J. Byeon, J. S. Hong, K. S. Park, and S. Lee. CNT/PDMS-based canal-typed ear electrodes for inconspicuous EEG recording. Journal of Neural Engineering, 11(4), 2014.Google Scholar
- S. Liang, C. Kuo, Y. Hu, and Y. Cheng. A rule-based automatic sleep staging method. Journal of Neuroscience Methods, 205(1):169--176, 2012.Google ScholarCross Ref
- S. F. Liang, C. E. Kuo, Y. C. Lee, W. C. Lin, Y. C. Liu, P. Y. Chen, F. Y. Cherng, and F. Z. Shaw. Development of an EOG-Based Automatic Sleep-Monitoring Eye Mask. In IEEE Transactions on Instrumentation and Measurement, 2015.Google ScholarCross Ref
- D. Looney, P. Kidmose, and D. Mandic. Ear-EEG: User-Centered and Wearable BCI, volume 6 of Biosystems & Biorobotics, pages 41--50. Springer Berlin Heidelberg, 2014.Google Scholar
- D. Looney, P. Kidmose, C. Park, M. Ungstrup, M. Rank, K. Rosenkranz, and D. Mandic. The In-the-Ear Recording Concept: User-Centered and Wearable Brain Monitoring. IEEE Pulse, 3(6):32--42, 2012.Google ScholarCross Ref
- H. Manabe, M. Fukumoto, and T. Yagi. Conductive rubber electrodes for earphone-based eye gesture input interface. Journal of Personal and Ubiquitous Computing, 19(1):143--154, 2015. Google ScholarDigital Library
- N. Merrill, M. T. Curran, J. Yang, and J. Chuang. Classifying Mental Gestures with In-Ear EEG. In Proceedings of 13th International Conference on Wearable and Implantable Body Sensor Network (BSN), 2016.Google ScholarCross Ref
- Misfit. http://misfit.com/. Accessed: August 03, 2016.Google Scholar
- S. Motamedi-Fakhr, M. Moshrefi-Torbati, M. Hill, C. Hill, and P. White. Signal processing techniques applied to human sleep EEG signals - A review. Biomedical Signal Processing and Control, 10:21--33, 2014.Google ScholarCross Ref
- A. Nawrocka and K. Holewa. Brain - Computer interface based on Steady - State Visual Evoked Potentials (SSVEP). In Proceedings of 14th International Carpathian Control Conference (ICCC), pages 251--254, 2013.Google ScholarCross Ref
- A. Nguyen, R. Alqurashi, A. C. Halbower, and T. Vu. mSleepWatcher: Why didnâĂŹt I sleep well? In Proceedings of ISSAT International Conference on Modeling of Complex Systems and Environments (MCSE), pages 96--103, 2015.Google Scholar
- A. Nguyen, R. Alqurashi, Z. Raghebi, F. Banaei-kashani, A. C. Halbower, T. Dinh, and T. Vu. In-ear Biosignal Recording System: A Wearable for Automatic Whole-night Sleep Staging. In Proceedings of the 2016 Workshop on Wearable Systems and Applications (ACM MobiSys-WearSys), pages 19--24, 2016. Google ScholarDigital Library
- R. Oliveira. The dynamic ear canal. Ballachandra B, ed. The Human Ear Canal. San Diego: Singular Publishing Group, pages 83--111, 1995.Google Scholar
- R. Oliveira, B. Hammer, A. Stillman, J. Holm, C. Jons, and R. Margolis. A look at ear canal changes with jaw motion. Ear Hear, 13(6):464--466, 1992.Google ScholarCross Ref
- R. Oliveira and G. Hoeker. Ear canal anatomy and activity. In Pirzanski C, ed. Ear Impressions and New Laser Shell Technology. Seminars in Hear, pages 265--275, 2003.Google Scholar
- R. Oliveira, V. Kolpe, and G. Hoeker. The dynamic human ear canal: Quantitative changes in canal volume with jaw articulation and its relevance to hearing aid use. In Poster presented at IHCON, 2002.Google Scholar
- OpenBCI. http://openbci.com/. Accessed: August 03, 2016.Google Scholar
- J. Owens. Insufficient Sleep in Adolescents and Young Adults: An Update on Causes and Consequences. Pediatrics, 134(3):921--932, 2014.Google ScholarCross Ref
- M. Poh, K. Kim, A. Goessling, N. Swenson, and R. Picard. Heartphones: Sensor Earphones and Mobile Application for Non-obtrusive Health Monitoring. In Proceedings of International Symposium on Wearable Computers (ISWC), pages 153--154, 2009. Google ScholarDigital Library
- M. Poh, K. Kim, A. Goessling, N. Swenson, and R. Picard. Cardiovascular Monitoring Using Earphones and a Mobile Device. In Proceedings of IEEE Pervasive Computing, pages 18--26, 2012. Google ScholarDigital Library
- C. P. Pollak, W. W. Tryon, H. Nagaraja, and R. Dzwonczyk. How Accurately Does Wrist Actigraphy Identify the States of Sleep and Wakefulness? SLEEP, 24(8), 2001.Google Scholar
- Polysmith - NIHON KOHDEN. http://www.nihonkohden.de/. Accessed: August 03, 2016.Google Scholar
- Types of Sleep Studies. http://www.nhlbi.nih.gov/health/health-topics/topics/slpst/types. Accessed: August 03, 2016.Google Scholar
- A. Rechtscheffen and A. Kales. A manual of standardized terminology, techniques, and scoring system for sleep stages of human subjects. Washington: Public Health Service, US Government Printing Office, 1968.Google Scholar
- M. Ronzhina, O. Janousek, J. Kolarova, M. Novakova, P. Honzik, and I. Provaznik. Sleep scoring using artificial neural networks. Sleep Medicine Reviews, 16(3):251--263, 2012.Google ScholarCross Ref
- A. Sano, T. Tomita, and H. Oba. Applications using Earphone with Biosignal Sensors. In Human Interface Society Meeting, volume 12, pages 1--6, 2010.Google Scholar
- B. Sen, M. Peker, A. Cavusoglu, and F. V. Celebi. A Comparative Study on Classification of Sleep Stage Based on EEG Signals Using Feature Selection and Classification Algorithms. Journal of Medical Systems, 38(3):1--21, 2014.Google ScholarCross Ref
- Sleep Shepherd. http://sleepshepherd.com/. Accessed: August 03, 2016.Google Scholar
- D. Shrivastava, S. Jung, M. Saadat, R. Sirohi, and K. Crewson. How to interpret the results of a sleep study. Journal of Community Hospital Internal Medicine Perspectives, 4(5), 2014.Google ScholarCross Ref
- What Are Sleep Studies? http://www.nhlbi.nih.gov/health/health-topics/topics/slpst/. Accessed: August 03, 2016.Google Scholar
- Trackit Mark III - LifeLines Neurodiagnostic Systems. https://www.lifelinesneuro.com/. Accessed: August 03, 2016.Google Scholar
- R. A. U., O. Faust, N. Kannathal, T. Chua, and S. Laxminarayan. Non-linear analysis of EEG signals at various sleep stages. Computer Methods and Programs in Biomedicine, 80(1):37--45, 2005. Google ScholarDigital Library
- Brain Basics: Understanding Sleep. http://www.ninds.nih.gov/disorders/brain_basics/understanding_sleep.htm. Accessed: August 03, 2016.Google Scholar
- C. van der Reijden, L. Mens, and A. Snik. Signal-to-noise ratios of the auditory steady-state response from fifty-five EEG derivations in adults. Journal of the American Academy of Audiology, 15(10):692--701, 2004.Google ScholarCross Ref
- T. Virtanen, J. F. Gemmeke, B. Raj, and P. Smaragdis. Compositional Models for Audio Processing: Uncovering the structure of sound mixtures. IEEE Signal Processing Magazine, 32(2):125--144, 2015.Google ScholarCross Ref
- S. Vogel, M. Hulsbusch, T. Hennig, V. Blazek, and S. Leonhardt. In-Ear Vital Signs Monitoring Using a Novel Microoptic Reflective Sensor. IEEE Transactions on Information Technology in Biomedicine, 13(6):882--889, 2009. Google ScholarDigital Library
- T. Vollmer, P. Schauerte, M. Zink, S. Glggler, J. Schiefer, M. Schiek, U. Johnen, and S. Leonhardt. Individualized biomonitoring in heart failure - Biomon-HF "Keep an eye on heart failure - especially at night". Biomedical Engineering (Berl), 59(2):103--111, 2014.Google ScholarCross Ref
- P. D. Welch. The use of fast Fourier transform for the estimation of power spectra: a method based on time averaging over short, modified periodograms. IEEE Trans. on Audio Electroacoustics, AU-15(2):70--73, 1967.Google ScholarCross Ref
- E. Winokur, D. He, and C. Sodini. A wearable vital signs monitor at the ear for continuous heart rate and Pulse Transit Time measurements. In Proceedings of 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pages 2724--2727, 2012.Google ScholarCross Ref
- L. Zoubek, S. Charbonnier, S. Lesecq, A. Buguet, and F. Chapotot. Feature selection for sleep/wake stages classification using data driven methods. Biomedical Signal Processing and Control, 2(3):171--179, 2007.Google ScholarCross Ref
Recommendations
In-ear Biosignal Recording System: A Wearable For Automatic Whole-night Sleep Staging
WearSys '16: Proceedings of the 2016 Workshop on Wearable Systems and ApplicationsIn this work, we present a low-cost and light-weight wearable sensing system that can monitor bioelectrical signals generated by electrically active tissues across the brain, the eyes, and the facial muscles from inside human ears. Our work presents two ...
Automatic sleep scoring: A search for an optimal combination of measures
Objective: The objective of this study is to find the best set of characteristics of polysomnographic signals for the automatic classification of sleep stages. Methods: A selection was made from 74 measures, including linear spectral measures, ...
Research on Automatic Sleep Staging of Sleep Based on Different Reference Montages of Single Channel EEG
ICBBE '22: Proceedings of the 2022 9th International Conference on Biomedical and Bioinformatics EngineeringSleep staging is very important for the effective diagnosis and pre-intervention of patients with sleep disorders. The traditional sleep staging method based on manual scoring is highly subjective, time-consuming and the collection methods are ...
Comments