With the increasing requirements for location-based services for Internet of things (IoT) applications, ultrawideband (UWB) technology provides accurate indoor positioning capabilities. However, indoor environments contain various obstacles leading to significant signal propagation effects. This results in errors in the time-of-arrival-based UWB positioning system. Specifically, a non-line-of-sight (NLOS) signal induces additional distance and position errors owing to the path delay compared to a line-of-sight (LOS) signal. Therefore, UWB signal classification is essential for improving positioning accuracy. Recently, various approaches have successfully classified UWB signals, including machine-learning-based methods such as convolutional neural networks (CNNs) and long short-term memory (LSTM). This study proposes a hybrid quantum CNN (HQCNN) inspired by a CNN for UWB signal classification. HQCNN employs a classical layer before a quantum embedding circuit and variational quantum circuits for the convolutional filter. These structures enable efficient training and implementation. We used UWB channel impulse response data to demonstrate the performance of the proposed algorithm and compared the benchmarks with HQCNN using the evaluation metrics. The results showed that the HQCNN outperformed the others.
With the increasing requirements for location-based services for Internet of things (IoT) applications, ultrawideband (UWB) technology provides accurate indoor positioning capabilities. However, indoor environments contain various obstacles leading to significant signal propagation effects. This results in errors in the time-of-arrival-based UWB positioning system. Specifically, a non-line-of-sight (NLOS) signal induces additional distance and position errors owing to the path delay compared to a line-of-sight (LOS) signal. Therefore, UWB signal classification is essential for improving positioning accuracy. Recently, various approaches have successfully classified UWB signals, including machine-learning-based methods such as convolutional neural networks (CNNs) and long short-term memory (LSTM). This study proposes a hybrid quantum CNN (HQCNN) inspired by a CNN for UWB signal classification. HQCNN employs a classical layer before a quantum embedding circuit and variational quantum circuits for the convolutional filter. These structures enable efficient training and implementation. We used UWB channel impulse response data to demonstrate the performance of the proposed algorithm and compared the benchmarks with HQCNN using the evaluation metrics. The results showed that the HQCNN outperformed the others.
Abstract Quantum Neural Networks (QNNs) present a promising research direction in image recognition, demonstrating significant potential for various applications. However, QNNs with a fixed circuit topology structure are prone to encountering the barren plateaus during training when processing exponential number of qubits, which limit their performance and scalability. In this paper, a novel Hybrid Quantum-Classical Inception-inspired Convolutional Neural Networks (HQCNN) is proposed. The HQCNN enhances feature learning capability and mitigates the barren plateau issue by integrating quantum convolutional kernels with diverse circuit topologies across multiple channels. The architecture employs an amplitude encoding layer to map multi-channel classical data into quantum states, followed by diverse quantum convolutional kernels that extract feature representations. Furthermore, Hadamard gates are used to intergrate multi-channel features and incorporate quantum pooling to reduce feature dimensionality, with a fully connected layer mapping the quantum-enhancing features into class labels for classification tasks. Finally, by analyzing the influence of the circuit structures and quantum gate combinations on the models' performance, the optimal HQCNN architecture is constructed. Experimental results demonstrate that HQCNN achieves 98.5% accuracy on the MNIST-4 classification task and 92.5% accuracy on the MNIST-10 classification task, which indicates that the proposed model outperforms state-of-the-art HQCNN models and classical CNN in image classification with about 10% parameters. This study provides an effective approach for alleviating the barren plateau issue and designing multi-channel quantum convolutional neural networks for processing big classic data with fewer quantum resources.
Quantum computing, based on fundamental quantum-mechanical principles and phenomena such as superposition, entanglement, and interference, offers access to high-dimensional quantum feature spaces and complex correlations that may be difficult to efficiently represent using classical computing, along with potential computational advantages through quantum hardware. Therefore, quantum computing has emerged as a promising paradigm for addressing limitations of classical deep learning (DL) through fundamentally different computational mechanisms. Quantum computing-based DL approaches have been applied to image classification; however, most rely on existing quantum computing libraries that impose substantial computational costs, limiting their broader applicability. In this study, hybrid quantum convolutional neural networks (HQCNNs) are proposed for structural damage classification without relying on existing quantum computing libraries. The proposed architectures integrate quanvolutional layers, composed of encoding, variational quantum circuits, and measurement, with conventional convolutional layers in a CNN architecture, enabling quantum-enhanced feature extraction while maintaining compatibility with classical computing systems. The scratch-implemented HQCNN (HQCNN(S)), its library-based counterpart (HQCNN(P)), and the classical CNN are compared in terms of test accuracy, computational cost, and training efficiency. Experimental results demonstrate that HQCNN(S) ( at ) achieves up to 176.57 faster computation than HQCNN(P) and 3.1% higher test accuracy than the classical CNN, while reducing the number of trainable parameters by 60.2%. Moreover, HQCNN(S) achieves comparable performance to the best-performing classical CNN using 75% less training data.
Residual networks (ResNet) are known to be effective for image classification. However, challenges such as computational time remain because of the significant number of parameters. Quantum computing using quantum entanglement and quantum parallelism is an emerging computing paradigm that addresses this issue. Although quantum advantage is still studied in many research fields, quantum machine learning is a research area that leverages the strengths of quantum computing and machine learning. In this study, we investigated the quantum speedup with respect to the number of parameters in each model for a time-series classification task. This paper proposes a novel hybrid quantum residual network (HQResNet) inspired by the classical ResNet for time-series classification. HQResNet introduces a classical layer before a quantum convolutional neural network (QCNN), where the QCNN is used as a residual block. These structures enable shortcut connections and are particularly effective in achieving classification tasks without a data re-uploading scheme. We used ultra-wide-band (UWB) channel impulse response data to demonstrate the performance of the proposed algorithm and compared the state-of-the-art benchmarks with HQResNet using evaluation metrics. The results show that HQResNet achieved high performance with a small number of trainable parameters.
Abstract With the significant enhancement of quantum computing capabilities and their expanding applications in various fields, quantum image processing combined with quantum computing has become a key area of research in quantum computing, holding important theoretical value. In the face of the challenges posed by the digital information era, image classification technology demands higher standards from machine learning algorithms in terms of accuracy, computational speed, generalization capability, and complexity. This paper studies a series of quantum data encoding methods and parametric quantum circuit architectures, and proposes the application of Hybrid Hierarchical Encoding (HHE) and Hybrid Quantum Convolutional Neural Network (HQCNN). The new encoding method HHE integrates the benefits of angle encoding and enhances the hybrid amplitude encoding design to achieve optimal classification performance without compromising the depth of quantum circuits.HQCNN demonstrates outstanding classification performance and remarkable control over model complexity by leveraging the data processing capabilities of classical convolution and the complex computational power of quantum convolution. Experimental results show that HHE and HQCNN achieve better classification accuracy on the MNIST and Fashion-MNIST datasets compared to traditional classical CNN models, particularly when the number of parameters is significantly reduced.
Deep learning-based convolutional neural network (CNN) models are prominent in processing and analyzing sensor signal data such as images for classification. Data augmentation is a powerful technique used in training such models to avoid overfitting and improve accuracy. This letter proposes a data augmentation technique using a quantum circuit for image data. The proposed quantum circuit is suitable to implement on real hardware provided by IBM QX platform. In comparison with other classical data augmentation techniques, the proposed technique increased the prediction accuracy of the CNN from 68.65% to 76.03%. However, CNN models for image classification use many parameters during the training process. Quantum computers can efficiently handle large-scale data inputs using qubits for information processing. Hence, we also propose a hybrid quantum-classical CNN model (HQCNN) for scene classification. The proposed model uses a combination of CNN layers and quantum layers to process images. The proposed HQCNN reduces parameters used for training as quantum layers are used in the model. Our experimental results show that the proposed HQCNN can classify the scenes in UC Merced land-use dataset with an accuracy of 85.28%, compared to the other models.
The growing complexity and scale of image processing tasks challenge classical convolutional neural networks (CNNs) with high computational costs. Hybrid quantum-classical convolutional neural networks (HQCNNs) show potential to improve performance by accelerating processing speed, enhancing classification accuracy, and reducing model parameters, though studies have primarily focused on the RGB color space. However, the effectiveness of HQCNNs in non-RGB color spaces, such as Lab, YCrCb, and HSV, remains largely unexplored. We propose an HQCNN to evaluate image classification across diverse color spaces. The HQCNN integrates parameterized quantum circuits (PQCs) with a classical CNN, leveraging quantum entanglement and trainable gates to enhance expressiveness across varied color representations. We assess performance on MNIST, CIFAR-10, EuroSAT, and SAT-4 datasets. Experimental results demonstrate that the HQCNN outperforms the classical CNN across all tested color spaces for the ten-class MNIST task, achieving a best accuracy of 94.3% in Lab compared to 92.8% in RGB for the CNN, with superior performance on other datasets in various color spaces. These findings highlight the potential of non-RGB color spaces and optimized PQC designs to improve classification performance. We provide new insights for advancing hybrid quantum-classical computer vision through optimized PQC architectures and diverse color space applications.