Analytical Challenges of Quantum and Classical Computing in Thailand: A Comparative Exploration of Machine Learning Through Classification
Issued Date
2024-01-01
Resource Type
Scopus ID
2-s2.0-85202624103
Journal Title
5th Technology Innovation Management and Engineering Science International Conference, TIMES-iCON 2024 - Proceedings
Rights Holder(s)
SCOPUS
Bibliographic Citation
5th Technology Innovation Management and Engineering Science International Conference, TIMES-iCON 2024 - Proceedings (2024)
Suggested Citation
Chaipunha N., Panya V., Leelasantitham A. Analytical Challenges of Quantum and Classical Computing in Thailand: A Comparative Exploration of Machine Learning Through Classification. 5th Technology Innovation Management and Engineering Science International Conference, TIMES-iCON 2024 - Proceedings (2024). doi:10.1109/TIMES-ICON61890.2024.10630768 Retrieved from: https://repository.li.mahidol.ac.th/handle/20.500.14594/100987
Title
Analytical Challenges of Quantum and Classical Computing in Thailand: A Comparative Exploration of Machine Learning Through Classification
Author(s)
Author's Affiliation
Corresponding Author(s)
Other Contributor(s)
Abstract
This research explores the integration of classical and quantum machine learning (QML) for classification tasks, focusing on applications in Thailand. We evaluate QML algorithms, including Variational Quantum Classifier (VQC), Quantum Support Vector Classifier (QSVC), and Quantum Neural Network (QNN), against the classical Support Vector Machine (SVM) using the Iris and Wine datasets on IBM's Qiskit platform. Our analysis highlights the trade-offs between accuracy and preprocessing time for quantum encoding, noting that while some QML algorithms achieve high accuracy, their preprocessing times are significantly longer than those of classical SVM. This underscores current limitations in QML for practical classification tasks. However, the study also identifies future opportunities for QML applications in sectors like healthcare, materials science, logistics, and financial modeling in Thailand. This research contributes to the field by providing a comparative analysis of QML and classical algorithms, revealing that QML, despite its high accuracy, is often hindered by lengthy preprocessing. It also emphasizes QML's potential to address specific technological challenges in Thailand.