# Classification of Sleep Quality and Aging as a Function of Brain Complexity: A Multiband Non-Linear EEG Analysis

^{1}

^{2}

^{3}

^{4}

^{5}

^{6}

^{7}

^{*}

## Abstract

**:**

## 1. Introduction

- Can the proposed algorithm effectively categorize individuals’ brain complexity based on age? (e.g., distinguishing between younger individuals with good sleep quality and older individuals with good sleep quality). Previous studies have noted an increase in slower frequencies among older adults [32]. Additionally, some researchers have suggested a reduction in complexity at a global network level and an increase at a local level [17]. Therefore, we hypothesized that the algorithm would successfully classify participants by age, yielding higher accuracy rates, particularly in the theta and delta sub-bands.
- Is the proposed algorithm capable of better distinguishing between older and younger individuals when one group experiences compromised sleep quality? The extent to which participants can be classified based on both sleep quality and age remains uncertain. However, considering the observed alterations in complexity associated with sleep and aging, higher accuracies in distinguishing between young and older individuals were anticipated, particularly when comparing young adults with good sleep quality to older adults experiencing sleep disturbances. Essentially, we expected these two groups to exhibit the greatest dissimilarities, as we incorporate variations in sleep quality alongside the aging process.
- Does sleep quality affect the awake resting state brain complexity and stability in young adults and in older adults? Which sub-bands and regions enable a better classification level? (YG vs. YB and OG vs. OB). As mentioned previously, sleep quality is associated with a decrease in complexity [33], hence discrimination between these pairs of groups is expected although with lower accuracy levels than when contrasting groups of different ages.

## 2. Materials and Methods

#### 2.1. Participants

#### 2.2. Data Description

#### 2.2.1. Sleep Quality Assessment (PSQI)

#### 2.2.2. EEG Data Collection

#### 2.3. EEG Data Preprocessing

#### 2.4. EEG Signal Processing and Feature Extraction

#### 2.4.1. Multiband EEG Decomposition

#### 2.4.2. EEG Non-Linear Analysis

_{i}= [x(i), x (i +τ), …, x(i + (m − 1) τ)],

#### 2.5. Feature Extraction

#### 2.5.1. Features Extracted from Reconstructed Attractor

_{i}, x

_{j}} present a distance between them equal to or less than r [30,46,47]. From this, the correlation dimension can be estimated as:

_{j}that satisfies min

_{j}||x

_{i}− x

_{j}||. The estimates are given by [30,48].

_{s}is the sampling period. The LLE is defined by the slope of the best linear approximation of λ(i) [48].

#### 2.5.2. Features Extracted Directly from the Time Series

#### Long Term Memory Measures

_{m}(k) is estimated for each m-long segment of $y\left(k\right).$ The following formula defines the signal’s average fluctuation as a function of m [47]:

#### Fractal Dimension Measures

_{max}, where k

_{max}is obtained experimentally despite k

_{max}= 8 being initially proposed, a distance measure is computed as [30,46,47].

_{max}. The FD estimate, denoted by FDH, is then given by the slope of the best linear approximation of ln[L(k)] as a function of ln(1/k).

_{K}): additionally, the Katz [51] algorithm (FD

_{K}) was used to determine FD:

#### Energy and Entropy

## 3. Results

#### 3.1. Tomographic Maps for Discrimination over Scalp

#### 3.2. Discriminatory Capability of Used Classifiers

#### 3.3. Differences in Specific Regions across Groups

- (i)
- Young versus older adults

- (ii)
- Old good sleep versus old bad sleep

- (iii)
- Young good sleep versus young bad sleep

## 4. Discussion

## 5. Conclusions

## Supplementary Materials

## Author Contributions

## Funding

## Institutional Review Board Statement

## Informed Consent Statement

## Data Availability Statement

## Acknowledgments

## Conflicts of Interest

## References

- Scullin, M.K.; Bliwise, D.L. Sleep, Cognition, and Normal Aging: Integrating a Half-Century of Multidisciplinary Research. Perspect. Psychol. Sci.
**2015**, 10, 97–137. [Google Scholar] [CrossRef] [PubMed] - Hoch, C.C.; Dew, M.A.; Reynolds, C.F.; Buysse, D.J.; Nowell, P.D.; Monk, T.H.; Mazumdar, S.; Borland, M.D.; Miewald, J.; Kupfer, D.J. Aging and Sleep. 1 Longitudinal Changes in Diary-and Laboratory-Based Sleep Measures in Healthy “Old Old” and “Young Old” Subjects: A Three-Year Follow-Up. Sleep
**1997**, 20, 192–202. [Google Scholar] [CrossRef] [PubMed] - Scullin, M.K. Do Older Adults Need Sleep? A Review of Neuroimaging, Sleep, and Aging Studies. Curr. Sleep. Med. Rep.
**2017**, 3, 204–214. [Google Scholar] [CrossRef] [PubMed] - Abichou, K.; la Corte, V.; Hubert, N.; Orriols, E.; Gaston-Bellegarde, A.; Nicolas, S.; Piolino, P. Young and Older Adults Benefit From Sleep, but Not From Active Wakefulness for Memory Consolidation of What-Where-When Naturalistic Events. Front. Aging Neurosci.
**2019**, 11, 58. [Google Scholar] [CrossRef] - Stickgold, R.; Walker, M.P. Memory consolidation and reconsolidation: What is the role of sleep? Trends Neurosci.
**2005**, 28, 408–415. [Google Scholar] [CrossRef] [PubMed] - Mcewen, B.S.; Sapolsky, R.M. Stress and cognitive function. Curr. Opin. Neurobiol.
**1995**, 5, 205–216. [Google Scholar] [CrossRef] [PubMed] - Vgontzas, A.N.; Zoumakis, E.; Bixler, E.O.; Lin, H.M.; Follett, H.; Kales, A.; Chrousos, G.P. Adverse Effects of Modest Sleep Restriction on Sleepiness, Performance, and Inflammatory Cytokines. J. Clin. Endocrinol. Metab.
**2004**, 89, 2119–2126. [Google Scholar] [CrossRef] - McEwen, B.S. Sleep deprivation as a neurobiologic and physiologic stressor: Allostasis and allostatic load. Metabolism
**2006**, 55, S20–S23. [Google Scholar] [CrossRef] [PubMed] - Gulia, K.K.; Kumar, V.M. Sleep disorders in the elderly: A growing challenge. Psychogeriatrics
**2018**, 18, 155–165. [Google Scholar] [CrossRef] - Dregan, A.; Armstrong, D. Age, cohort and period effects in the prevalence of sleep disturbances among older people: The impact of economic downturn. Soc. Sci. Med.
**2009**, 69, 1432–1438. [Google Scholar] [CrossRef] - Double, K.; Halliday, M.; Kril, J.; Harasty, J.A.; Cullen, K.; Brooks, W.S.; Creasey, H.; Broe, G.A.; Halliday, G.M.; Kril, J.J. Topography of Brain Atrophy During Normal Aging and Alzheimer’s Disease. Neurobiol. Aging
**1996**, 17, 513–521. [Google Scholar] [CrossRef] [PubMed] - Nebes, R.D.; Buysse, D.J.; Halligan, E.M.; Houck, P.R.; Monk, T.H. Self-reported sleep quality predicts poor cognitive performance in healthy older adults. J. Gerontol. Ser. B Psychol. Sci. Soc. Sci.
**2009**, 64, 180–187. [Google Scholar] [CrossRef] - Arenaza-Urquijo, E.M.; Vemuri, P. Resistance vs. resilience to Alzheimer disease. Neurology
**2018**, 90, 695–703. [Google Scholar] [CrossRef] - Schreiber, S.; Vogel, J.; Schwimmer, H.D.; Marks, S.M.; Schreiber, F.; Jagust, W. Impact of lifestyle dimensions on brain pathology and cognition. Neurobiol. Aging
**2016**, 40, 164–172. [Google Scholar] [CrossRef] [PubMed] - Hou, F.; Wu, C.; C-k, P.; Yu, Z.; Peng, C.-K.; Yang, A.; Ma, Y. Complexity of Wake Electroencephalography Correlates With Slow Wave Activity After Sleep Onset. Front. Neurosci.
**2018**, 12, 809. [Google Scholar] [CrossRef] - Yang, A.C.; Jann, K.; Michel, C.M.; Wang, D.J.J. Editorial: Advances in Multi-Scale Analysis of Brain Complexity. Front. Neurosci.
**2020**, 14, 510091. [Google Scholar] [CrossRef] - McIntosh, R.; Antoni, M.; Seay, J.; Fletcher, M.A.; Ironson, G.; Klimas, N.; Kumar, M.; Schneiderman, N. Associations Among Trajectories of Sleep Disturbance, Depressive Symptomology and 24-Hour Urinary Cortisol in HIV+ Women Following a Stress Management Intervention. Behav. Sleep Med.
**2019**, 17, 605–620. [Google Scholar] [CrossRef] [PubMed] - Colombo, M.A.; Wei, Y.; Ramautar, J.R.; Linkenkaer-Hansen, K.; Tagliazucchi, E.; van Someren, E.J.W. More severe insomnia complaints in people with stronger long-range temporal correlations in wake resting-state EEG. Front. Physiol.
**2016**, 7, 229402. [Google Scholar] [CrossRef] - Cassani, R.; Estarellas, M.; San-Martin, R.; Fraga, F.J.; Falk, T.H. Systematic review on resting-state EEG for Alzheimer’s disease diagnosis and progression assessment. Dis. Markers
**2018**, 2018, 5174815. [Google Scholar] [CrossRef] - Sanei, S.; Chambers, J.A. EEG Signal Processing; John Wiley & Sons: Hoboken, NJ, USA, 2007. [Google Scholar]
- Babloyantz, A.; Salazar, J.M.; Nicolis, C. Evidence of chaotic dynamics of brain activity during the sleep cycle. Phys. Lett. A
**1985**, 11, 152–156. [Google Scholar] [CrossRef] - Chialvo, D.R. Life at the edge: Complexity and criticality in biological function. arXiv
**2018**, arXiv:1810.11737. [Google Scholar] [CrossRef] - Cifre, I.; Miller Flores, M.T.; Penalba, L.; Ochab, J.K.; Chialvo, D.R. Revisiting Nonlinear Functional Brain Co-activations: Directed, Dynamic, and Delayed. Front. Neurosci.
**2021**, 15, 700171. [Google Scholar] [CrossRef] - Miller, P. Dynamical systems, attractors, and neural circuits [version 1; referees: 3 approved]. F1000Research
**2016**, 5, 992. [Google Scholar] [CrossRef] [PubMed] - Faust, O.; Bairy, M.G. Nonlinear analysis of physiological signals: A review. J. Mech. Med. Biol.
**2012**, 12, 1240015. [Google Scholar] [CrossRef] - Qian, B.; Rasheed, K. Hurst exponent and financial market predictability. In Proceedings of the IASTED Conference on Financial Engineering and Applications, Berkeley, CA, USA, 24–26 September 2007. [Google Scholar]
- Jeong, J.; Kim, D.-J.; Kim, S.Y.; Chae, J.-H.; Go, H.J.; Kim, K.-S. Effect of Total Sleep Deprivation on the Dimensional Complexity of the Waking EEG sleep deprivation and waking EEG. Sleep
**2001**, 24, 197–202. [Google Scholar] - Wang, Z. Brain Entropy Mapping in Healthy Aging and Alzheimer’s Disease. Front. Aging Neurosci.
**2020**, 12, 596122. [Google Scholar] [CrossRef] - Keshmiri, S. Entropy and the Brain: An Overview. Entropy
**2020**, 22, 917. [Google Scholar] [CrossRef] - Silva, G.; Alves, M.; Cunha, R.; Bispo, B.C.; Oliveira-Silva, P.; Rodrigues, P.M. Early Detection of Alzheimer’s and Parkinson’s Diseases Using Multiband Nonlinear EEG Analysis. Psychol. Neurosci.
**2022**, 15, 360. [Google Scholar] [CrossRef] - Shahbakhti, M.; Beiramvand, M.; Eigirdas, T.; Solé-Casals, J.; Wierzchon, M.; Broniec-Wojcik, A.; Augustyniak, P.; Marozas, V. Discrimination of Wakefulness From Sleep Stage I Using Nonlinear Features of a Single Frontal EEG Channel. IEEE Sens. J.
**2022**, 22, 6975–6984. [Google Scholar] [CrossRef] - Scally, B.; Burke, M.R.; Bunce, D.; Delvenne, J.F. Resting-state EEG power and connectivity are associated with alpha peak frequency slowing in healthy aging. Neurobiol. Aging
**2018**, 71, 149–155. [Google Scholar] [CrossRef] - Amorim, L.; Magalhães, R.; Coelho, A.; Moreira, P.S.; Portugal-Nunes, C.; Castanho, T.C.; Marques, P.; Sousa, N.; Santos, N.C. Poor Sleep Quality Associates with Decreased Functional and Structural Brain Connectivity in Normative Aging: A MRI Multimodal Approach. Front. Aging Neurosci.
**2018**, 10, 375. [Google Scholar] [CrossRef] [PubMed] - Crook-Rumsey, M. Neurophysiology of Prospective Memory in Typical and Atypical Ageing; Nottingham Trent University: Nottingham, UK, 2020. [Google Scholar]
- Buysse, D.J.; Reynolds, C.F., III. The Pittsburgh Sleep Quality Index: A new instrument for psychiatric practice and research. Psychiatry Res.
**1989**, 28, 193–213. [Google Scholar] [CrossRef] - Benedict, R.H.B.; Schretlen, D.; Groninger, L.; Brandt, J. Hopkins verbal learning test—Revised: Normative data and analysis of inter-form and test-retest reliability. Clin. Neuropsychol.
**1998**, 12, 43–55. [Google Scholar] [CrossRef] - De Jager, C.A.; Budge, M.M.; Clarke, R. Utility of TICS-M for the assessment of cognitive function in older adults. Int. J. Geriatr. Psychiatry
**2003**, 18, 318–324. [Google Scholar] [CrossRef] - Delorme, A.; Makeig, S. EEGLAB: An open-source toolbox for analysis of single-trial EEG dynamics. J. Neurosci. Methods
**2004**, 134, 9–21. [Google Scholar] [CrossRef] - Doborjeh, M.G.; Wang, G.Y.; Kasabov, N.K.; Kydd, R.; Russell, B. A Spiking Neural Network Methodology and System for Learning and Comparative Analysis of EEG Data from Healthy Versus Addiction Treated Versus Addiction Not Treated Subjects. IEEE Trans. Biomed. Eng.
**2016**, 63, 1830–1841. [Google Scholar] [CrossRef] - Vetterli, M.; Kovacevic, J. Wavelets and Subband Coding; Prentice Hall: Englewood Cliffs, NJ, USA, 1995. [Google Scholar]
- Rodrigues, P.M.; Bispo, B.C.; Garrett, C.; Alves, D.; Teixeira, J.P.; Freitas, D. Lacsogram: A New EEG Tool to Diagnose Alzheimer’s Disease. IEEE J. Biomed. Health Inform.
**2021**, 25, 3384–3395. [Google Scholar] [CrossRef] - Malvar, H.S. Signal Processing with Lapped Transforms; Artech House, Inc.: London, UK, 1992. [Google Scholar]
- Vetterli, M. Wavelets, approximation, and compression. IEEE Signal Process. Mag.
**2001**, 18, 59–73. [Google Scholar] [CrossRef] - BenSaïda, A. A practical test for noisy chaotic dynamics. SoftwareX
**2015**, 3–4, 1–5. [Google Scholar] [CrossRef] - Stam, C.J. Nonlinear dynamical analysis of EEG and MEG: Review of an emerging field. Clin. Neurophysiol.
**2005**, 116, 2266–2301. [Google Scholar] [CrossRef] - Rodríguez-Bermúdez, G.; García-Laencina, P.J. Analysis of EEG signals using nonlinear dynamics and chaos: A review. Appl. Math. Inf. Sci.
**2015**, 9, 2309–2321. [Google Scholar] - Lau, Z.J.; Pham, T.N.; Chen, S.H.A.; Makowski, D. Brain Entropy, Fractal Dimensions and Predictability: A Review of Complexity Measures for EEG in Healthy and Neuropsychiatric Populations. Eur. J. Neurosci.
**2021**, 56, 5047–5069. [Google Scholar] [CrossRef] [PubMed] - Rosenstein’, M.T.; Collins, J.J.; de Luca, C.J.; Rapp, P.E. A practical method for calculating largest Lyapunov exponents from small data sets. Phys. D Nonlinear Phenom.
**1993**, 65, 117–134. [Google Scholar] [CrossRef] - Gifani, P.; Rabiee, H.R.; Hashemi, M.H.; Taslimi, P.; Ghanbari, M. Optimal fractal-scaling analysis of human EEG dynamic for depth of anesthesia quantification. J. Franklin Inst.
**2007**, 344, 212–229. [Google Scholar] [CrossRef] - Lee, J.-M.; Kim, D.-J.; Kim, I.-Y.; Park, K.-S.; Kim, S.I. Detrended ductuation analysis of EEG in sleep apnea using MIT/BIH polysomnography data. Comput. Biol. Med.
**2002**, 32, 37–47. [Google Scholar] [CrossRef] [PubMed] - Katz, M.J. Fractals and the analysis of waveforms. Comput. Biol. Med.
**1988**, 18, 145–156. [Google Scholar] [CrossRef] [PubMed] - Das, A.B.; Bhuiyan, M.I.H. Discrimination and classification of focal and non-focal EEG signals using entropy-based features in the EMD-DWT domain. Biomed. Signal Process Control
**2016**, 29, 11–21. [Google Scholar] [CrossRef] - Rodríguez-Sotelo, J.L.; Osorio-Forero, A.; Jiménez-Rodríguez, A.; Cuesta-Frau, D.; Cirugeda-Roldán, E.; Peluffo, D. Automatic sleep stages classification using EEG entropy features and unsupervised pattern analysis techniques. Entropy
**2014**, 16, 6573–6589. [Google Scholar] [CrossRef] - Babiloni, C.; Triggiani, A.I.; Lizio, R.; Cordone, S.; Tattoli, G.; Bevilacqua, V.; Soricelli, A.; Ferri, R.; Nobili, F.; Gesualdo, L.; et al. Classification of single normal and Alzheimer’s disease individuals from cortical sources of resting state EEG rhythms. Front. Neurosci.
**2016**, 10, 47. [Google Scholar] [CrossRef] - Ishii, R.; Canuet, L.; Aoki, Y.; Hata, M.; Iwase, M.; Ikeda, S.; Nishida, K.; Ikeda, M. Healthy and Pathological Brain Aging: From the Perspective of Oscillations, Functional Connectivity, and Signal Complexity. Neuropsychobiology
**2018**, 75, 151–161. [Google Scholar] [CrossRef] - Davidson, P.N.; Davidson, K.A. Electroencephalography in the elderly. Neurodiagnostic J.
**2012**, 52, 3–19. [Google Scholar] - Münch, M.; Knoblauch, V.; Blatter, K.; Schröder, C.; Schnitzler, C.; Kräuchi, K.; Wirz-Justice, A.; Cajochen, C. The frontal predominance in human EEG delta activity after sleep loss decreases with age. Eur. J. Neurosci.
**2004**, 20, 1402–1410. [Google Scholar] [CrossRef] [PubMed] - Long, S.; Ding, R.; Wang, J.; Yu, Y.; Lu, J.; Yao, D. Sleep Quality and Electroencephalogram Delta Power. Front. Neurosci.
**2021**, 15, 803507. [Google Scholar] [CrossRef] - Hong, J.K.; Lee, H.J.; Chung, S.; Yoon, I.Y. Differences in sleep measures and waking electroencephalography of patients with insomnia according to age and sex. J. Clin. Sleep Med.
**2021**, 17, 1175–1182. [Google Scholar] [CrossRef] [PubMed] - Barracca, N. The Brain-Sleep Connection: GCBH Recommendations on Sleep and Brain Health. 2017. Available online: https://www.ageuk.org.uk/globalassets/age-ni/documents/reports-and-publications/reports-and-briefings/health--wellbeing/gcbh/gcbh_sleep-brain-connection.pdf (accessed on 10 May 2022).

**Figure 1.**Methodology overview. Left to right, 32 channels included in analysis, time series of 32 channels selected and split into 5 s windows, Discrete Wavelet Transform (DWT) applied to achieve conventional sub-bands per window, electrode and subject. Features extracted for each sub-band, window, and each subject, and then per channel an average of each feature time series vector has been computed. Non-linear features organized per binary groups and sub-band and z-score normalization performed per study group pairs. Non-linear features normalized were input of classifiers trained/tested within a leave-one-out-cross-validation procedure. SVM = Support Vector Machine; KNN = K-Nearest Neighbor; Log.reg = Logistic Regression; trees = decision trees.

**Figure 2.**Topographic map classification results at scalp level for each pair of groups. YG = Young adults’ good sleep; YB = Young adults’ bad sleep; OG = Older adults’ good sleep; OB = Older adults’ bad sleep.

**Figure 3.**Mean accuracy in each pair of groups that displays how accurately algorithm predicted sleep quality and aging considering brain complexity of each participant. Y axis accuracy percentages are depicted and in X axis six pairs of groups: YG = Young adults’ good sleep; YB = Young adults’ bad sleep; OG = older adults’ good sleep; OB = Older adults’ bad sleep.

Classification Models | Classifier | Optimized Hyper-Parameters |
---|---|---|

Decision Trees | Fine Tree | Maximum number of splits = 4 |

Medium Tree | Maximum number of splits = 20 | |

Coarse Tree | Maximum number of splits = 100 | |

Logistic Regression | Covariance structure: complete | |

Support Vector Machines (SVM) | Linear SVM | Box constraint level = 3 |

Quadratic SVM | Box constraint level = 3 | |

Cubic SVM | Box constraint level = 4 | |

Fine Gaussian | Box constraint level = 3 | |

Medium Gaussian | Box constraint level = 3 | |

Coarse Gaussian | Box constraint level = 1 | |

K-Nearest-Neighbors (KNN) | Fine KNN | Number of neighbors = 1 |

Medium KNN | Number of neighbors = 10 | |

Coarse KNN | Number of neighbors = 100 | |

Cosine KNN | Number of neighbors = 10 | |

Cubic KNN | Number of neighbors = 10 | |

Weighted KNN | Number of neighbors = 10 |

Group | Classifier | Mean/Max | Sub-Bands | ||||
---|---|---|---|---|---|---|---|

Gamma | Beta | Alpha | Theta | Delta | |||

YG vs. OB | Cosine KNN | Mean | 70% | 73% | 80% | 82% | 85% |

Max | 75% | 89% | 89% | 89% | 92% | ||

YB vs. OB | Cosine KNN | Mean | 68% | 72% | 77% | 78% | 83% |

Max | 76% | 87% | 87% | 89% | 92% | ||

YB vs. OG | Coarse KNN | Mean | 60% | 62% | 75% | 79% | 80% |

Max | 82% | 82% | 91% | 91% | 91% | ||

YG vs. OG | Linear SVM | Mean | 59% | 56% | 67% | 70% | 77% |

Max | 90% | 70% | 90% | 90% | 95% | ||

OG vs. OB | Linear SVM | Mean | 72% | 72% | 72% | 71% | 71% |

Max | 85% | 82% | 74% | 76% | 79% | ||

YG vs. YB | Logistic regression | Mean | 43% | 50% | 49% | 47% | 50% |

Max | 63% | 75% | 88% | 71% | 75% |

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. |

© 2024 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

**MDPI and ACS Style**

Penalba-Sánchez, L.; Silva, G.; Crook-Rumsey, M.; Sumich, A.; Rodrigues, P.M.; Oliveira-Silva, P.; Cifre, I.
Classification of Sleep Quality and Aging as a Function of Brain Complexity: A Multiband Non-Linear EEG Analysis. *Sensors* **2024**, *24*, 2811.
https://doi.org/10.3390/s24092811

**AMA Style**

Penalba-Sánchez L, Silva G, Crook-Rumsey M, Sumich A, Rodrigues PM, Oliveira-Silva P, Cifre I.
Classification of Sleep Quality and Aging as a Function of Brain Complexity: A Multiband Non-Linear EEG Analysis. *Sensors*. 2024; 24(9):2811.
https://doi.org/10.3390/s24092811

**Chicago/Turabian Style**

Penalba-Sánchez, Lucía, Gabriel Silva, Mark Crook-Rumsey, Alexander Sumich, Pedro Miguel Rodrigues, Patrícia Oliveira-Silva, and Ignacio Cifre.
2024. "Classification of Sleep Quality and Aging as a Function of Brain Complexity: A Multiband Non-Linear EEG Analysis" *Sensors* 24, no. 9: 2811.
https://doi.org/10.3390/s24092811