This work proposes a novel theoretical framework utilizing quantum walk principles for feature extraction from polysomnographic (PSG) signals, focusing on the classification of sleep stages. By mapping EEG signals to a quantum graph and leveraging the probabilistic and path-dependent properties of quantum walks, this approach offers a potentially transformative methodology for analyzing brain activity. Also discussing the potential solution to class imbalance in sleep datasets using the innate qualities of quantum mechanics like superposition, highlighting the possible use of a hybrid loss function for classification.Outlining the conceptual basis of this framework, discussing its implications, and suggesting potential applications and future research directions.
This work proposes a novel theoretical framework utilizing quantum walk principles for feature extraction from polysomnographic (PSG) signals, focusing on the classification of sleep stages. By mapping EEG signals to a quantum graph and leveraging the probabilistic and path-dependent properties of quantum walks, this approach offers a potentially transformative methodology for analyzing brain activity. Also discussing the potential solution to class imbalance in sleep datasets using the innate qualities of quantum mechanics like superposition, highlighting the possible use of a hybrid loss function for classification.Outlining the conceptual basis of this framework, discussing its implications, and suggesting potential applications and future research directions.
This paper presents a novel approach to graph traversal and feature extraction leveraging the principles of quantum walks. Classical graph algorithms often suffer from performance limitations when dealing with large, complex graphs, primarily due to their sequential nature and the exponential growth of possible paths. Quantum walks, utilizing superposition and interference, provide a fundamentally different paradigm for graph exploration, offering the potential for significant speedups. We detail the theoretical framework for applying quantum walks to graph traversal, focusing on the efficient extraction of features from nodes and edges. The core concept involves mapping the graph's nodes and edges onto a quantum Hilbert space, allowing the quantum walk to explore the graph's connectivity in a probabilistic manner. We demonstrate how interference effects can be strategically utilized to guide the walk towards regions of interest, thereby enhancing feature extraction. The methodology outlined here provides a robust foundation for developing quantum algorithms for graph analysis across various domains, including social network analysis, knowledge graph reasoning, and anomaly detection. This work establishes a new direction for graph processing, shifting from classical sequential algorithms to quantum probabilistic exploration, ultimately leading to improved efficiency and scalability.
Sleep staging is an important task in the field of medicine and is significant for diagnosing sleep disorders and assessing overall health. Classical machine learning has made significant progress in this field, and with the development of quantum computing, quantum machine learning (QML) provides a new model for solving complex data classification tasks. In this paper, we propose a hybrid quantum-classical neural network (HQCNN) architecture based on electroencephalogram (EEG) single-channel signals for automating the sleep staging task. The classical part uses a convolutional neural network (CNN) and a long short-term memory network (LSTM) to extract features of the EEG signal, while the quantum part utilizes variational quantum circuit (VQC) for feature mapping and classification. We evaluated the model on different datasets. The results show that the model is satisfactory for classification. This indicates that the combination of quantum computing and machine learning has great potential and provides new research directions and technical approaches for developing more efficient computational models and dealing with complex data problems.
Sleep disorders affect about one billion people worldwide, yet automated sleep staging is limited by class imbalance in polysomnographic datasets and the representational capacity of classical generative models. This work compares a classical Generative Adversarial Network (GAN) with two Quantum Wasserstein GAN-GP (QWGAN-GP) variants—noiseless and noisy simulator—for synthetic EEG augmentation in sleep stage classification using the ANPHY-Sleep dataset [1]. Models are trained under a Wasserstein GAN with Gradient Penalty (WGAN-GP) across subsets of 2–4 statistical EEG features over 50 epochs. Results show consistent quantum-enhanced variance matching: QWGAN-GP variants achieve lower standard deviation mean absolute error (StdMAE) than the classical GAN, with reductions up to 70.9% at 3 features. The 6-qubit generator (26= 64-dimensional Hilbert space) captures EEG variance more faithfully than a classical multilayer perceptron. Moderate Gaussian noise (σ = 0.1) during QGAN training acts as implicit regularisation, yielding the best StdMAE (0.064) and competitive classification (Accuracy = 0.880, F1 = 0.880). The classical GAN suffers mode collapse at higher dimensions, dropping to 0.535–0.585 accuracy, while the noiseless QGAN reaches 0.905 at 3 features. A downstream classification evaluation on real PSG labels confirms that the quantum generator preserves N1 minority-class F1 (up to 0.1053 at 4 features) where the classical GAN consistently collapses to N1 F1 = 0.000 across all feature configurations. These results demonstrate that hybrid quantum-classical generative models provide a structurally distinct and empirically superior approach for minority-class distribution learning in imbalanced clinical time-series, albeit with higher classical simulation overhead.
This paper explores the application of quantum random walks (QRWs) to feature extraction from high-dimensional data. Classical random walks often struggle with the curse of dimensionality, leading to inefficient exploration of the data space. QRWs, leveraging the inherent randomness of quantum mechanics, offer a potential solution by enabling more efficient exploration and potentially uncovering hidden correlations. This work details the theoretical framework for implementing QRWs on graph-based representations of data, presenting algorithms for both discrete and continuous graphs. We investigate the key differences between classical and quantum random walks, focusing on the role of superposition and entanglement in expanding the search space. The core claim is that QRWs can be utilized to extract meaningful features from high-dimensional data. We provide a mathematical formulation for analyzing the convergence and efficiency of QRWs, demonstrating the potential advantages over traditional methods. The paper concludes with a discussion on the challenges and future directions for this emerging field.
Electroencephalography is widely used in braincomputer interfaces, neurological research, and brain-state classification. However, EEG signals contain noise, artifacts, and variations between individuals, making accurate classification difficult. This project proposes an Adaptive Quantum Computing Framework for EEG Brain-State Classification Using Entanglement-Aware Feature Mapping. Initially, EEG signals are collected from publicly available datasets and preprocessed using filtering, artifact removal, segmentation, and normalization techniques. Relevant temporal and frequency-domain features are extracted and encoded into quantum states using parameterized quantum gates. An entanglement-aware featuremapping technique captures relationships between selected features through quantum entangling operations. A Variational Quantum Classifier is then employed to classify brain states using a hybrid quantum-classical optimization process. The adaptive mechanism evaluates different feature maps, entanglement patterns, circuit depths, and training parameters to identify suitable configurations. The proposed framework is evaluated using accuracy, precision, recall, macroF1 score, computational cost, and noise sensitivity. Classical machine learning and deep learning models are used for comparison. Subjectindependent testing assesses the model's ability to classify EEG signals from previously unseen participants. The study aims to investigate the effectiveness and limitations of adaptive quantum computing for EEG brain-state classification. Keywords: Quantum Computing, EEG Classification, Quantum Machine Learning, Entanglement-Aware Feature Mapping, Variational Quantum Classifier, Brain–Computer Interface.
This paper explores the application of quantum walks as a novel approach to optimization within the realm of combinatorial problems. The core argument posits that quantum walks, leveraging the principles of quantum mechanics like superposition and interference, can potentially outperform classical walk-based optimization methods, particularly when dealing with complex problem landscapes. We propose a framework where combinatorial problems are represented as graphs and navigated via quantum walks. The implementation utilizes the inherent probabilistic nature of quantum walks to explore the solution space more efficiently through constructive interference, while suppressing destructive interference that would lead to unproductive exploration. We detail the theoretical underpinnings, focusing on the mathematical formulation of the quantum walk and its interaction with the problem graph. The key objective is to demonstrate a potential speedup in convergence compared to traditional optimization techniques. This work provides a foundational exploration, aiming to lay the groundwork for future research and development in this emerging field.