Quantum Machine Learning for Industry 5.0

Anupam Ghosh, Soumi Dutta, Asit Kumar Das +2 more

Zulqarnain Ahmed, J H Hemanth Kakarla, Abhishek Hazra +1 more

Pijush Dutta, Mittapally Sandeep Reddy, Yogendra Chhetri +4 more

The current review's goal is to examine the strategic significance of Quantum Machine Learning (QML) as a technology tool or strategic enabler of Industry 5.0, the approaching industrial revolution. To summarize and categorize the most common forms, antecedents, and outcomes of sustainable innovation, the primary objective of this study is to systematically identify and critically evaluate the literature on sustainable innovation in Industry 5.0 since January 2020. A thorough search and review of 5984 scholarly articles were identified during the systematic review, and 36 publications were chosen by a cyclic filtration for a careful review in the fields of Industry 5.0 and QML to analyze the articles' contents. The findings demonstrate that QML provides a revolutionary improvement in decision-making platforms, system security, and data analytics in Industry 4.0. By taking into consideration a methodical and critical assessment of the research manuscripts, the proposed survey offers readers an impactful insight into the functions of quantum machine learning as an enabler to Industry 5.0 processes. QML is emphasized as a key driver for secure, intelligent, and sustainable industrial ecosystems through QML-assisted designs across various verticals, such as smart healthcare, manufacturing, digital twins, and Cobots, as this review methodically examines the enabling technologies shaping the Industry 5.0 vision. It also highlights how QML can improve decision-making, ensure post-quantum security, optimize resources, and speed up the realization of human-centric, energy-efficient, and resilient Industry 5.0 systems as quantum computing advances.

P Kuppusamy, Nnvs Yaswanth Kumar, Jyotsna Dontireddy +1 more

The rapid development of machine learning technology leads to make the devices in the industries working autonomously. However, the growth of sensors in the industries leads to produce vast data that is utilized by machine learning algorithms to improve the autonomous devices’ performances. However, classical ML algorithms and hardware systems cannot process large data to meet real-time problems. Hence, the researchers have developed Quantum Computing hardware systems and Quantum Machine learning algorithms to speed up the process. This research work presented the review of quantum computing mechanisms and QML algorithms that are applied to classify the images. This work demonstrated the performance comparison of various QML algorithms. It showed that the images are classified using various QML algorithms faster than classical ML algorithms in terms of time.

Huruy Bsrat, Hongmei Chi, Yong Shi +3 more

Machine learning has addressed a wide range of practical challenges. However, the generation of massive datasets across engineering systems has introduced new issues in computational efficiency, training time, and memory usage. Quantum Machine Learning (QML) has emerged as a promising solution, leveraging quantum mechanical properties such as superposition and entanglement to process high-dimensional, unstructured data more efficiently. This paper proposes the integration of hands-on QML laboratories into the engineering curriculum to better equip students for emerging challenges, particularly those associated with Industry 4.0 and nanotechnology within industry 4.0 environments. Building on an established Python-based machine learning curriculum, the proposed framework introduces quantum computing concepts, such as data encoding, variational classifiers, and quantum kernel methods, implemented through platforms including PennyLane and Qiskit. Students explore both supervised and unsupervised paradigms through classical and quantum frameworks, gaining practical experience with QML tools. This initiative supports ABET accreditation goals and equips students with the interdisciplinary competencies necessary for the evolving quantum workforce.

Amarthaluri Tirupathaiah, V. Balaraju