Sentiment analysis (SA) is an essential component of natural language processing (NLP) and is used to analyze sentiments, attitudes, and emotional tones in various contexts. It provides valuable insights into public opinion, customer feedback, and user experiences. Researchers have developed various classical machine learning (ML) and neuro-fuzzy approaches to address the exponential growth of data and the complexity of language structures in SA. However, these approaches often fail to determine the optimal number of clusters, interpret results accurately, handle noise or outliers efficiently, and scale effectively to high-dimensional data. In addition, they are frequently insensitive to input variations. In this article, we propose a novel hybrid approach for SA called the quantum fuzzy neural network (QFNN), which leverages quantum properties and incorporates a fuzzy layer to overcome the limitations of classical SA algorithms. In this study, we test the proposed approach on two Twitter datasets: the Coronavirus Tweets Dataset (CVTD) and the General Sentimental Tweets Dataset (GSTD), and compare it with classical and hybrid algorithms. The results show that QFNN outperforms all classical, quantum, and hybrid algorithms, achieving 100% and 90% accuracy in the case of CVTD and GSTD, respectively. Furthermore, QFNN demonstrates its robustness against six different noise models, providing the potential to tackle the computational complexity associated with SA on a large scale in a noisy environment. The proposed approach expedites sentiment data processing and precisely analyzes different forms of textual data, thus improving sentiment classification and insights associated with SA.

Low-energy carbon Internet of Things (IoT) systems are essential for sustainable development, as they reduce carbon emissions while ensuring efficient device performance. Although classical algorithms manage energy efficiency and data processing within these systems, they often face scalability and real-time processing limitations. Quantum algorithms offer a solution to these challenges by delivering faster computations and improved optimization, thereby enhancing both the performance and sustainability of low-energy carbon IoT systems. Therefore, we introduced three quantum algorithms: quantum neural networks utilizing Pennylane (QNN-P), Qiskit (QNN-Q), and hybrid quantum neural networks (QNN-H). These algorithms are applied to two low-energy carbon IoT datasets—room occupancy detection (RODD) and GPS tracker (GPSD). For the RODD dataset, QNN-P achieved the highest accuracy at 0.95, followed by QNN-H at 0.91 and QNN-Q at 0.80. Similarly, for the GPSD dataset, QNN-P attained an accuracy of 0.94, QNN-H 0.87, and QNN-Q 0.74. Furthermore, the robustness of these models is verified against six noise models. The proposed quantum algorithms demonstrate superior computational efficiency and scalability in noisy environments, making them highly suitable for future low-energy carbon IoT systems. These advancements pave the way for more sustainable and efficient IoT infrastructures, significantly minimizing energy consumption while maintaining optimal device performance.

Energy-efficient healthcare systems are becoming increasingly critical for Industry 5.0 as the Internet of Medical Things (IoMT) expands, particularly with the integration of 5G technology. 5G-enabled IoMT systems allow real-time data collection, high-speed communication, and enhanced connectivity between medical devices and healthcare providers. However, these systems face energy consumption and data security challenges, especially with the growing number of connected devices operating in Industry 5.0 environments with limited power resources. Quantum computing integrated with machine learning (ML) algorithms, forming quantum machine learning (QML), offers exponential improvements in computational speed and efficiency through principles such as superposition and entanglement. In this paper, we propose and evaluate three QML algorithms, which are UU, variational UU, and UU-quantum neural networks (QNN) for classifying data from four different datasets: 5G-South Asia, Lumos5G 1.0, WUSTL EHMS 2020, and PS-IoT. Our comparative analysis, using various evaluation metrics, reveals that the UU-QNN method not only outperforms the other algorithms in the 5G-South Asia and WUSTL EHMS 2020 datasets, achieving 100% accuracy, but also aligns with the human-centric goals of Industry 5.0 by allowing more efficient and secure healthcare data processing. Furthermore, the robustness of the proposed quantum algorithms is verified against several noisy channels by analyzing accuracy variations in response to each noise model parameter, which contributes to the resilience aspect of Industry 5.0. These results offer promising quantum solutions for 5G-enabled IoMT healthcare systems by optimizing data classification and reducing power consumption while maintaining high levels of security even in noisy environments.

Social financial technology focuses on trust, sustainability, and social responsibility, which require advanced technologies to address complex financial tasks in the digital era. With the rapid growth in online transactions, automating credit card fraud detection and loan eligibility prediction has become increasingly challenging. Classical machine learning (ML) models have been used to solve these challenges; however, these approaches often encounter scalability, overfitting, and high computational costs due to complexity and high-dimensional financial data. Quantum computing (QC) and quantum machine learning (QML) provide a promising solution to efficiently processing high-dimensional datasets and enabling real-time identification of subtle fraud patterns. However, existing quantum algorithms lack robustness in noisy environments and fail to optimize performance with reduced feature sets. To address these limitations, we propose a quantum feature deep neural network (QFDNN), a novel, resource efficient, and noise-resilient quantum model that optimizes feature representation while requiring fewer qubits and simpler variational circuits. The model is evaluated using credit card fraud detection and loan eligibility prediction datasets, achieving competitive accuracies of 82.2% and 74.4%, respectively, with reduced computational overhead. Furthermore, we test QFDNN against six noise models, demonstrating its robustness across various error conditions. Our findings highlight QFDNN’s potential to enhance trust and security in social financial technology by accurately detecting fraudulent transactions while supporting sustainability through its resource-efficient design and minimal computational overhead.

The escalating complexity of urban transportation systems, increased by traffic congestion, diverse transportation modalities, and shifting commuter preferences, necessitates developing more sophisticated analytical frameworks. Traditional computational approaches often struggle with the voluminous datasets generated by real-time sensor networks, and they generally lack the precision needed for accurate traffic prediction and efficient system optimization. Therefore, we integrate quantum computing techniques to enhance Vehicle Road Cooperation Systems (VRCS). By leveraging quantum algorithms, specifically$UU^{\dagger }$and variational$UU^{\dagger }$, in conjunction with quantum image encoding methods such as Flexible Representation of Quantum Images (FRQI) and Novel Enhanced Quantum Representation (NEQR), we propose an optimized Quantum Neural Network (QNN). The QNN features adjustments in its entangled layer structure and training duration to handle traffic data processing complexities better. Empirical evaluations on two traffic datasets show that our model achieves superior classification accuracies of 97.42% and 84.08% and demonstrates remarkable robustness in various noise conditions. Our study underscores the potential of quantum-enhanced 6G solutions in streamlining complex transportation systems, highlighting the pivotal role of quantum technologies in advancing intelligent transportation solutions.

In transportation cyber-physical systems (CPS), ensuring safety and reliability in real-time decision-making is essential for successfully deploying autonomous vehicles and intelligent transportation networks. However, these systems face significant challenges, such as computational complexity and the ability to handle ambiguous inputs like shadows in complex environments. This paper introduces a Quantum Deep Convolutional Neural Network (QDCNN) designed to enhance the safety and reliability of CPS in transportation by leveraging quantum algorithms. At the core of QDCNN is the UU$\dagger $method, which is utilized to improve shadow detection through a propagation algorithm that trains the centroid value with preprocessing and postprocessing operations to classify shadow regions in images accurately. The proposed QDCNN is evaluated on three datasets on normal conditions and one road affected by rain to test its robustness. It outperforms existing methods in terms of computational efficiency, achieving a shadow detection time of just 0.0049352 seconds, faster than classical algorithms like intensity-based thresholding (0.03 seconds), chromaticity-based shadow detection (1.47 seconds), and local binary pattern techniques (2.05 seconds). This remarkable speed, superior accuracy, and noise resilience demonstrate QDCNN’s —key factors for safe navigation in autonomous transportation in real-time. This research demonstrates the potential of quantum-enhanced models in addressing critical limitations of classical methods, contributing to more dependable and robust autonomous transportation systems within the CPS framework.

By 2050, there will be a 50% rise in energy demand, and existing natural and renewable resources will be under extreme scrutiny. Optimizing current power generation and transmission to reduce energy consumption, cost, and other factors is equally vital to upgrading methods for effectively harvesting renewable energy. However, it gets more challenging for conventional computers to perform optimization as the number of factors affecting power generation and transmission rises. Extreme environmental cases will consequently lead to the imperfect functioning of Internet of Things (IoT) systems. By utilizing quantum-mechanical properties, such as superposition and entanglement, quantum computers can computationally outperform classical computers while consuming much less energy. In this article, we investigate various quantum machine learning algorithms on two data sets (TWTDUS and SDWTT18) related to IoT extreme environment and study the effect of a noisy quantum environment. We observe that for the TWTDUS data set, the variational$UU^{\dagger }$with analytical clustering methods achieves the highest accuracy of 98.10%. Similarly, for the SDWTT18 data set, the$UU^{\dagger }$method with$k$-means clustering achieves an accuracy of 94.43%. The results show that the accuracy of the proposed quantum algorithms outperforms the existing classical methods and can be utilized to forecast output power generation daily by measuring the metrics required in energy sector decision-making situations. This will be useful to save energy and costs in an IoT-extreme environment, where energy organizations must decide instantly whether to start or stop generating units.

Intelligent transportation systems (ITS) are a critical component of Industry 4.0 and 5.0, particularly having applications in logistic management. One of their crucial utilization is in supply-chain management and scheduling for optimally routing transportation of goods by vehicles at a given set of locations. This paper discusses the broader problem of vehicle traffic management, more popularly known as the Vehicle Routing Problem (VRP), and investigates the possible use of near-term quantum devices for solving it. For this purpose, we give the Ising formulation for VRP and some of its constrained variants. Then, we present a detailed procedure to solve VRP by minimizing its corresponding Ising Hamiltonian using a hybrid quantum-classical heuristic called Quantum Approximate Optimization Algorithm (QAOA), implemented on the IBM Qiskit platform. We compare the performance of QAOA with classical solvers such as CPLEX on problem instances of up to 15 qubits. We find that performance of QAOA has a multifaceted dependence on the classical optimization routine used, the depth of the ansatz parameterized by$p$, initialization of variational parameters, and problem instance itself.