Quantum Computation in a Human Environment

Craig S. Lent

Markus Bertl

The complexity of global supply chains places immense cognitive demands on human planners, creating a high-pressure environment where optimal decision-making is paramount yet increasingly difficult to achieve. This research addresses the central challenge of how to leverage quantum computing (QC) and artificial intelligence (AI) to augment human capabilities in solving complex, NP-hard logistical problems that are often intractable for human planners alone. It contrasts the theoretical underpinnings of hybrid quantum-classical algorithms with the practical, empirically verified results from an industrial case study of an AI-driven logistics solution at Malaysian Airlines' MAB Cargo. The analysis demonstrates that while a generalized 'quantum advantage' remains a long-term goal, significant value is created today through hybrid systems that function as collaborative partners for human operators. In this model, AI excels at structuring complex data and managing operational workflows, while quantum processors tackle specific, computationally intensive sub-problems, presenting optimized solutions to their human counterparts. The findings suggest that the most viable path forward is a synergistic human-machine integration, where quantum-AI components handle the heavy computations, thereby elevating the human role from tedious manual calculation to strategic oversight and exception management.

Alvaro Huerga, Unai Aguilera, Aitor Almeida +1 more

As quantum computing technologies become more mature, their applicability increases. One of the main challenges in intelligent environments is to correctly model and ascertain the users' behavior in order to react to it and cater to their needs. One of the main challenges in human behavior modeling is predicting the users' next actions. In this paper we propose using two different quantum computing algorithms in order to predict human behavior: Quantum Kernel Alignment and Quantum Support Vector Machines. Our experiments show that those algorithms outperform other traditional machine learning algorithms in this task. We also present a study that analyzes the influence of qubit noise in the performance of the quantum approach. This helps to understand how the accuracy of the quantum computing algorithms will increase as the underlying hardware matures and qubit noise is reduced.

Stefano Patarnello

Yu-Chao Hsu, Jiun-Cheng Jiang, Chun-Hua Lin +5 more

In this work, we introduce the Federated Quantum Kernel-Based Long Short-term Memory (Fed-QK-LSTM) framework, integrating the quantum kernel methods and Long Shortterm Memory into federated learning. Within Fed-QK-LSTM framework, we enhance human activity recognition (HAR) in privacy-sensitive environments and leverage quantum computing for distributed learning systems. The DeepConv-QK-LSTM architecture on each client node employs convolutional layers for efficient local pattern capture, this design enables the use of a shallow QK-LSTM to model long-range relationships within the HAR data. The quantum kernel method enables the model to capture complex non-linear relationships in multivariate time-series data with fewer trainable parameters. Experimental results on RealWorld HAR dataset demonstrate that Fed-QK-LSTM framework achieves competitive accuracy across different client settings and local training rounds. We showcase the potential of Fed-QK-LSTM framework for robust and privacy-preserving human activity recognition in real-world applications, especially in edge computing environments and on scarce quantum devices.

Sukhpal Singh Gill, Oktay Cetinkaya, S. Marrone +14 more