We aim to use quantum machine learning to detect various anomalies in image inspection by using small size data. Assuming the possibility that the expressive power of the quantum kernel space is superior to that of the classical kernel space, we are studying a quantum machine learning model. Through trials of image inspection processes not only for factory products but also for products including agricultural products, the importance of trials on real data is recognized. In this study, training was carried out on SVMs embedded with various quantum kernels on a small number of agricultural product image data sets collected in the markets. The quantum kernels prepared in this study consisted of a smaller number of rotating gates and control gates. The F1 scores for each quantum kernel showed a significant effect of using CNOT gates. After confirming the results with a quantum simulator, the usefulness of the quantum kernels was confirmed on a quantum computer. Learning with SVMs embedded with specific quantum kernels showed significantly higher values of the AUC compared to classical kernels. The reason for the lack of learning in quantum kernels is considered to be due to kernel concentration or exponential concentration similar to the Baren plateau. The reason why the F1 score does not increase as the number of features increases is suggested to be due to exponential concentration, while at the same time it is possible that only certain features have discriminative ability. Furthermore, it is suggested that controlled Toffoli gate may be a promising quantum kernel component.
We aim to use quantum machine learning to detect various anomalies in image inspection by using small size data. Assuming the possibility that the expressive power of the quantum kernel space is superior to that of the classical kernel space, we are studying a quantum machine learning model. Through trials of image inspection processes not only for factory products but also for products including agricultural products, the importance of trials on real data is recognized. In this study, training was carried out on SVMs embedded with various quantum kernels on a small number of agricultural product image data sets collected in the markets. The quantum kernels prepared in this study consisted of a smaller number of rotating gates and control gates. The F1 scores for each quantum kernel showed a significant effect of using CNOT gates. After confirming the results with a quantum simulator, the usefulness of the quantum kernels was confirmed on a quantum computer. Learning with SVMs embedded with specific quantum kernels showed significantly higher values of the AUC compared to classical kernels. The reason for the lack of learning in quantum kernels is considered to be due to kernel concentration or exponential concentration similar to the Baren plateau. The reason why the F1 score does not increase as the number of features increases is suggested to be due to exponential concentration, while at the same time it is possible that only certain features have discriminative ability. Furthermore, it is suggested that controlled Toffoli gate may be a promising quantum kernel component.
In recent years, the diversification of consumer values has led to an increase in the number of small-quantity, high-mix products. For many manufacturing companies, shipping inspections of such products are of great importance. As all products have the same value, good and defective products need to be efficiently identified. Now, a promising future application of quantum technology is considered to be quantum machine learning. We believe that the quantum classifier for SVMs using quantum kernels is one of the areas where quantum advantages can be demonstrated. At present, there are few examples of quantum classifiers applied to real problems in manufacturing processes. In this study, we aim to build a classifier that can demonstrate the quantum advantage and compare SVMs using classical and quantum kernels with conventional ResNet. Initially, a binarised image was generated after image pre-processing. After principal component analysis and dimensionality reduction were performed on the images, SVM with kernels was carried out. The kernel-based SVMs was then compared with the conventionally implemented Residual neural network (ResNet) using an evaluation index: F1-score. The results showed that the F1-score of SVMs using classical kernels was equivalent to that of Resnet. In addition, SVMs using quantum kernels showed higher F1-score than ResNet. In addition, the impact of the feature map and principal components of the quantum kernel was also investigated. It was found that when the feature map became more complex, conversely, circuit generation took more time. It was also found that the principal components are highly relevant to the image and cannot lead to simple results. In the future, we plan to accumulate more experimental data, look for scenes where quantum machine learning can be used and apply it to the manufacturing field.
Abstract For many manufacturing companies, the production line is very important. In recent years, the number of small-quantity, high-mix products have been increasing, and the identification of good and defective products must be carried out efficiently. At that time, machine learning is a very important issue on shipping inspection using small amounts of data. Quantum machine learning is one of most exciting prospective applications of quantum technologies. SVM using kernel estimation is one of most popular methods for classifiers. Our purpose is to search quantum advantage on classifier to enable us to classifier in inspection test for small size datasets. In this study, we made clear the difference between classical and quantum kernel learning in initial state and propose analysis of learning process by plotting ROC space. To meet the purpose, we investigated the effect of each feature map compared to classical one, using evaluation index. The simulation results show that the learning model construction process between quantum and classical kernel learning is different in initial state. Moreover, the result indicates that the learning model of quantum kernel is the method to decrease the false positive rate (FPR) from high FPR, keeping high true positive rates on several datasets. We demonstrate that learning process on quantum kernel is different from classical one in initial state and plotting to ROC space graph is effective when we analyse the learning model process.
Outgoing inspection of the production line is very important for many manufacturing companies. In recent years, two class classification of good and defective products must be carried out efficiently as the number of small-quantity, high-mix products have been increasing. The support vector machine with kernel method (kernel learning) is the most popular method in two class classification used in factories. Quantum kernel learning is one of the most promising applications of quantum technology. In this study, we propose an analysis method that allows us to know the difference between classical and quantum machine learning by plotting false positive rate (FPR) and true positive rate (TPR) on Receiver Operating Characteristic (ROC) space. Quantum machine learning uses quantum data with feature maps. We compared quantum and classical data using a small-sized existing datasets. First, it was not possible to confirm that the quantum data incorporating quantum entanglement could achieve the effect in this study. Next, when we examined the learning process of quantum data with Pauli feature map and classical data, we observed differences in the initial learning process. Based on these results, in contrast to the commonly used ROC curve, we plotted the FPR and TPR separately on the ROC space according to the training size. Plotting on ROC space in this experiment shows that quantum kernel learning is a method to reduce only FPR from high FPR and TPR. We found that the kernel learning process using quantum data is different from one using classical data.
Quantum machine learning has attracted much attention in recent years as one of the applications of quantum computing. In particular, classification using quantum kernels has attracted attention as a means of efficient classification by mapping to a feature space. We aim to use quantum machine learning to identify good and defective products in images including factory products, building, and farm products. Though a fruit apple looks delicious, it has a vine crack inside when it is split in two, it loses its commercial value. It is very difficult to distinguish normal apples from apples with internal vine cracks which are not visible on the exterior, using photographs of the exterior. In this study, an attempt was made to classify internal defects with classical and quantum kernels using binarized images of apples, which are difficult to distinguish with the naked eye. As a result, the accuracy of the classical kernel was less than 0.75. However, with the quantum kernel, an accuracy of over 0.94 could be obtained. The performance of the quantum kernel varied significantly depending on its type. We found that quantum kernel circuits having Hadamard, and control Ry gate have affected the construction of the learning model. We have demonstrated that high accuracy can be achieved by using quantum kernels for the classification of images that are difficult to discriminate visually.
Machine learning is widely used for industrial anomaly detection; however, when anomaly distributions overlap, high false positive rates (FPR) often occur, hindering practical implementation. While quantum kernel methods have been proposed as a solution, the specific conditions under which they outperform conventional methods remain unclear. This study investigated the conditions under which quantum kernels outperform the classical RBF kernel in industrial acoustic anomaly detection. Using autoregressive (AR) features and an unsupervised One-Class SVM, we compared a conventional radial basis function (RBF) kernel with two types of quantum kernels: QK1 (employing linear entanglement) and QK2 (employing all-to-all entanglement). Two datasets with distinct characteristics were used for the experiments: “Open Belt Drive (OBD),” where the anomaly class is separable, and “Mini 4WD (M4W),” where anomaly distributions overlap. While all methods achieved perfect classification for the OBD dataset, the quantum kernels reached optimal performance using fewer features. In contrast, for the M4W dataset, QK2 significantly outperformed the RBF kernel, achieving an F1 score of 0.893 and an FPR of 0.033 (compared to 0.428 and 0.600 for RBF, respectively). t-SNE analysis confirmed that the M4W anomaly data were difficult to separate in the conventional feature space. These results suggest that quantum kernels offer the greatest advantage in problems involving overlapping distributions and that analyzing separability via t-SNE helps identify anomaly detection tasks suitable for the application of quantum technology.
Anomaly detection (AD) underpins fraud prevention, network security, industrial condition monitoring, medical diagnosis, and searches for new physics. However, it remains challenging due to rare anomalies, scarce labeled data, and the high dimensionality and strong correlation of sensor data. Many classical machine learning (ML) algorithms are designed to address AD in various settings, but the growth of quantum computing opens a new path for these problems. Quantum machine learning (QML) offers new tools, from exploring exponentially large Hilbert spaces and promising speed-ups to the native processing of quantum data. Thus, this review connects the two fields. We first present the basics of quantum computing, quantum algorithms, and QML with the most influential literature, and formalize the classical anomaly scores that quantum methods inherit. We then systematically review 30 primary studies of quantum anomaly detection (QAD) published between 2018 and 2026, express each method family through its anomaly score, and organize the field into a taxonomy of six families: quantum kernel methods, quantum autoencoders, quantum generative models, variational quantum classifiers, quantum linear-algebra methods, and detectors for quantum data. A cross-study analysis shows that the field has moved from asymptotic speed-up proposals to small hybrid experiments, that kernels and autoencoders dominate, that only nine studies run on gate-based hardware, and that none yet demonstrates a robust, practically relevant advantage over well-tuned classical detectors. We close with the main obstacles, such as data embedding, barren plateaus, kernel concentration, and weak baselines, and a research roadmap that prioritizes quantum data, fair benchmarks against classical baselines, and robust detectors for sequential and distributed data.