Earth Observation Data Classification with Quantum-Classical Convolutional Neural Network

Fan, Fan; Shi, Yilei; Zhu, Xiao Xiang

doi:10.1109/igarss46834.2022.9883949

Cited by 5 publications

(4 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[40]. Since, classification is a process of supervised learning .A new Quantum pattern classification algorithm introduced with Quantum machine learning for hamming distance calculation in Quantum computer environment .Algorithm that performs Linear regression with least square optimization is also discussed in [41].…”

Section: Twin Support Vector Machines Based On Fruit Fly Optimization...mentioning

confidence: 99%

“…To address the issues discussed above [27], a soft clusteringbased local multiple shows that the kernel weights solved by the algorithm are better suited to the characteristics of the data sets.LMKL is a sample-based proposed method and all experiments are done on the UCI data set. The author compared the results of SVM with a single Gaussian kernel [41]. [6] 2023 presented ideas from Quantum physics to help and create a machine learning application using Quantum computing specifically for optimizing the computational complexity of massive data sets calculations [42].…”

Section: Twin Support Vector Machines Based On Fruit Fly Optimization...mentioning

confidence: 99%

See 1 more Smart Citation

Quantum Image processing algorithms comparison using datasets of machine learning based applications

SINGH,

Indu,

majumdar

2024

Preprint

View full text Add to dashboard Cite

This article analyzes and compares various Quantum learning algorithms on big data. The main contribution of this article is to provide a new machine-learning approach using Quantum computing for big data analysis with features of robust, novel, and effective Quantum machine images and transit mode. Currently, there is no efficient method for doing Quantum image recognition or classification due to the lack of an effective Quantum feature extraction technique. This work proposes a global Quantum feature extraction technique based on Schmidt decomposition for the first time. Additionally, a new version of the Quantum learning algorithm is shown, which uses the features' Hamming distance to classify images. With the help of algorithm analysis and experimental findings from the benchmark database Caltech 101, a successful method for large-scale image classification is developed and put forth in the context of big data. The proposed model yields an with an average accuracy of 98\% with the proposed enhanced Quantum classifier, QeSVM classifier, swarm particle optimizer with Twin wave SVM, QPSO-TWSVM, and other Q-CNN models on different Big Data sets.

show abstract

Section: Twin Support Vector Machines Based On Fruit Fly Optimization...mentioning

confidence: 99%

Section: Twin Support Vector Machines Based On Fruit Fly Optimization...mentioning

confidence: 99%

Quantum Image processing algorithms comparison using datasets of machine learning based applications

SINGH,

Indu,

majumdar

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…They can be embedded in qubits without the constraint of their neighbors, making processing less resource-intensive [43]. For instance, one QML model known as a quantum convolutional neural network (QCNN) requires approximately 4, 000 quantum gates only to embed the element R 64×64×12 in the Eurosat dataset and roughly 60, 000 quantum gates for embedding the multispectral image R 300×290×3 illustrated in Figure 3 in the input qubits [59]. Hence, multispectral images are not viable for deploying QCNNs on today's quantum machines, even on future quantum machines.…”

Section: ) Selecting Earth Observation Data For Quantum Machinesmentioning

confidence: 99%

Exploiting the Quantum Advantage for Satellite Image Processing: Review and Assessment

Otgonbaatar,

Kranzlmüller

2023

Preprint

View full text Add to dashboard Cite

<p>This article examines the current status of quantum computing in Earth observation (EO) and satellite imagery. We analyze the potential limitations and applications of quantum learning models when dealing with satellite data, considering the persistent challenges of profiting from quantum advantage and finding the optimal sharing between high-performance computing (HPC) and quantum computing (QC). We then assess some parameterized quantum circuit models transpiled into a Clifford+T universal gate set. The T-gates shed light on the quantum resources required to deploy quantum models, either on an HPC system or several QC systems. In particular, if the T-gates cannot be simulated efficiently on an HPC system, we can apply a quantum computer and its computational power over conventional techniques. Our quantum resource estimation showed that quantum machine learning (QML) models, with a sufficient number of T-gates, provide the quantum advantage if and only if they generalize on unseen data points better than their classical counterparts deployed on the HPC system and they break the symmetry in their weights at each learning iteration like in conventional deep neural networks. We also estimated the quantum resources required for some QML models as an initial innovation. Lastly, we defined the optimal sharing between an HPC+QC system for executing QML models for hyperspectral satellite images. These are a unique dataset compared to other satellite images since they have a limited number of input qubits and a small number of labeled benchmark images, making them less challenging to deploy on quantum computers.</p>

show abstract

Section: ) Selecting Earth Observation Data For Quantum Machinesmentioning

confidence: 99%

Exploiting the Quantum Advantage for Satellite Image Processing: Review and Assessment

Otgonbaatar,

Kranzlmüller

2023

Preprint

View full text Add to dashboard Cite

<p>We first review the current state of the art of quantum computing for Earth observation (EO) and satellite images. There are the persisting challenges of profiting from quantum advantage, and finding the optimal sharing between high-performance computing (HPC) and quantum computing (QC), i.e. the HPC+QC paradigm, for computational EO problems. Secondly, we assess some parameterized quantum circuit models transpiled into a Clifford+T universal gate set, where the Clifford+T quantum gate set sheds light on the quantum resources required for deploying quantum models either on an HPC system or several QCs. If the Clifford+T quantum gate set cannot be simulated efficiently on an HPC system then we can apply a quantum computer and its computational power over conventional computers. Our resulting quantum resource estimation demonstrates that Quantum Machine Learning (QML) models having a sufficient number of T-gates provide the quantum advantage if and only if they generalize on unseen data points better than their classical counterparts deployed on the HPC system and they break the symmetry in their weights at each learning iteration like in conventional deep neural networks. As an initial innovation, we estimate the quantum resources required for some QML models. Secondly, we define the optimal sharing between an HPC+QC system for executing QML models for Hyperspectral Satellite Images (HSIs); HSIs are a unique dataset compared to multispectral images to be deployed on quantum computers due to the limited number of their input qubits, and the commonly used small number of labeled benchmark HSIs.</p>

show abstract

Earth Observation Data Classification with Quantum-Classical Convolutional Neural Network

Cited by 5 publications

References 8 publications

Quantum Image processing algorithms comparison using datasets of machine learning based applications

Quantum Image processing algorithms comparison using datasets of machine learning based applications

Exploiting the Quantum Advantage for Satellite Image Processing: Review and Assessment

Exploiting the Quantum Advantage for Satellite Image Processing: Review and Assessment

Contact Info

Product

Resources

About