A Quantum Mechanics-Based Framework for EEG Signal Feature Extraction and Classification

Li, YaoChong; Zhou, Ri-Gui; Xu, Ruiqing; Luo, Jia; Jiang, She-Xiang

doi:10.1109/tetc.2020.3000734

Cited by 50 publications

(17 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The QRNN outperforms traditional Kalman filtering methods and is tested on real-time EEG data and BCI competition test data. The feature extraction and classification portion of EEG data analysis is likewise performed with various quantum machine learning methods such as entropy-based quantum support vector machines [58], quantum-inspired evolutionary algorithms [59], and independent component analysis, wavelet transforms, and Fourier transforms [60]. Finally, quantum methods are facilitating a new level of data resolution in the examination of EEG data.…”

Section: Quantum Eegmentioning

confidence: 99%

Quantum Neurobiology

2022

View full text Add to dashboard Cite

Quantum neurobiology is concerned with potential quantum effects operating in the brain and the application of quantum information science to neuroscience problems, the latter of which is the main focus of the current paper. The human brain is fundamentally a multiscalar problem, with complex behavior spanning nine orders of magnitude-scale tiers from the atomic and cellular level to brain networks and the central nervous system. In this review, we discuss a new generation of bio-inspired quantum technologies in the emerging field of quantum neurobiology and present a novel physics-inspired theory of neural signaling (AdS/Brain (anti-de Sitter space)). Three tiers of quantum information science-directed neurobiology applications can be identified. First are those that interpret empirical data from neural imaging modalities (EEG, MRI, CT, PET scans), protein folding, and genomics with wavefunctions and quantum machine learning. Second are those that develop neural dynamics as a broad approach to quantum neurobiology, consisting of superpositioned data modeling evaluated with quantum probability, neural field theories, filamentary signaling, and quantum nanoscience. Third is neuroscience physics interpretations of foundational physics findings in the context of neurobiology. The benefit of this work is the possibility of an improved understanding of the resolution of neuropathologies such as Alzheimer’s disease.

show abstract

Section: Quantum Eegmentioning

confidence: 99%

Quantum Neurobiology

2022

View full text Add to dashboard Cite

show abstract

“…Supported by the methods of classical physics, such functions usually represent deterministic solutions of differential equations designed as the models of different membrane configurations. An emerging research field is devoted to a quantum mechanics-based framework for EEG signal feature extraction and classification [4]. In this context a crucial step of our radical departure from deterministic solutions of classical physics to the probabilistic reasoning of the quantum theories is the relocation of elementary bioelectric sources from the cellular to molecular level.…”

Section: Stionmentioning

confidence: 99%

Untitled

2021

obm.neurobiol.

View full text Add to dashboard Cite

The probabilistic formalism of quantum mechanics is used to quantitatively link the electroencephalogram (EEG) with the underlying microscale activity of cortical neurons. Previous approaches applied methods of classic physics to reconstruct the EEG in terms of explicit physical models of cortical neurons and the volume conductor. However, the multiplicity of cellular processes with extremely intricate mixtures of deterministic and random factors prevented the creation of consistent biophysical parameter sets. To avoid the uncertainty surrounding the physical attributes of the neuronal ensembles, we undertake here a radical departure from deterministic equations of classical physics to the probabilistic reasoning of quantum mechanics. The crucial step is the relocation of the elementary bioelectric sources from cellular to molecular level. Using a novel method of time-frequency analysis with adaptive segmentation for digital processing of empirical EEG and single trial event related potentials (ERPs), we found universal "building blocks" of these cortical processes both in the frequency and time domains. This result is qualified as a phenomenon known in statistical physics and quantum mechanics as universality. Therationale is that despite dramatic differences in the cellular machineries, the statistical factors governed by the central limit theorem produce the EEG waveform as a statistical

show abstract

“…The obtained results reveal that QIBC outperforms current state-of-the-art techniques in most of the tasks. The QM-based framework has been utilized for feature extraction and classification from the electroencephalogram signal and achieved an accuracy of 0.95 with Gaussian kernel [22]. Further, the classification of osteoarthritis has been accomplished by utilizing classical ML and DL models [23].…”

Section: Introductionmentioning

confidence: 99%

Comparative performance analysis of quantum machine learning with deep learning for diabetes prediction

Gupta

Varshney

Sharma

et al. 2021

Complex Intell. Syst.

View full text Add to dashboard Cite

Background Diabetes, the fastest growing health emergency, has created several life-threatening challenges to public health globally. It is a metabolic disorder and triggers many other chronic diseases such as heart attack, diabetic nephropathy, brain strokes, etc. The prime objective of this work is to develop a prognosis tool based on the PIMA Indian Diabetes dataset that will help medical practitioners in reducing the lethality associated with diabetes. Methods Based on the features present in the dataset, two prediction models have been proposed by employing deep learning (DL) and quantum machine learning (QML) techniques. The accuracy has been used to evaluate the prediction capability of these developed models. The outlier rejection, filling missing values, and normalization have been used to uplift the discriminatory performance of these models. Also, the performance of these models has been compared against state-of-the-art models. Results The performance measures such as precision, accuracy, recall, F1 score, specificity, balanced accuracy, false detection rate, missed detection rate, and diagnostic odds ratio have been achieved as 0.90, 0.95, 0.95, 0.93, 0.95, 0.95, 0.03, 0.02, and 399.00 for DL model respectively, However for QML, these measures have been computed as 0.74, 0.86, 0.85, 0.79, 0.86, 0.86, 0.11, 0.05, and 35.89 respectively. Conclusion The proposed DL model has a high diabetes prediction accuracy as compared with the developed QML and existing state-of-the-art models. It also uplifts the performance by 1.06% compared to reported work. However, the performance of the QML model has been found as satisfactory and comparable with existing literature.

show abstract

A Quantum Mechanics-Based Framework for EEG Signal Feature Extraction and Classification

Cited by 50 publications

References 48 publications

Quantum Neurobiology

Quantum Neurobiology

Untitled

Comparative performance analysis of quantum machine learning with deep learning for diabetes prediction

Contact Info

Product

Resources

About