The growing demand for reliable service delivery and real-time data processing has intensified challenges in efficiently distributing workloads across geographically distributed server nodes in Internet of Things (IoT)-enabled Digital Twin (DT) environments. To address this issue, this study proposes a quantum computing–inspired (QCi) optimization–based framework to enhance load balancing in IoT–DT systems. The approach integrates a novel QCi optimization strategy with a QCi-based predictive neural network to estimate optimal server node allocation by considering real-time server availability and workload dynamics. Extensive evaluations show that the proposed method outperforms Bayesian Belief Networks, conventional Artificial Neural Networks, and Support Vector Machines, achieving a sensitivity of 87.36%, specificity of 94.38%, precision of 91.25%, and coverage of 97.51%. The results demonstrate that combining QCi optimization with DT technology significantly improves processing efficiency, prediction accuracy, and adaptability for real-time IoT workloads.

Assessing groundwater resources is crucial for managing water contamination and preventing illnesses. Effective water quality evaluation requires continuous real-time parametric data collection. Previous systems have failed to incorporate unpredictability and flexibility, relying on static models that lead to errors. This study introduces a novel Virtual Twin-inspired Water Quality System (VTWQS) for real-time water quality assessment, addressing these limitations and providing quantitative insights into health risks. The validity of the method is confirmed using experimental data from the Maheru surveillance post in Punjab, India. Results indicate strong performance in water quality evaluation, with an overall prediction accuracy of 94.14%, recall of 91.47%, precision of 93.74%, and f-measure of 92.37%. The system also demonstrates lower computing latency, higher reliability, and increased dependability, making it an effective choice for accurate water quality forecasts.

Artificial Intelligence (AI) is widely used in the healthcare sector, including healthcare administration, predictive analytics for medical outcomes, decision-making processes, and diagnoses. While AI has advanced to rival human proficiency in certain healthcare tasks, its implementation is limited due to perceived opacity and lack of trust. To address this limitation, this study introduces an innovative approach to interpretable deep learning for detecting Respiratory Syncytial Virus (RSV). The proposed technique aggregates audio and image data features to generate a cumulative probabilistic outcome and employs the SHapley Additive exPlanations (SHAP) technique for transparent explanations. Two public datasets, Coswara and Virufy, were used to train and evaluate the approach. The technique outperformed existing techniques by achieving an overall Accuracy, Precision, Recall, and F1-Score of 97.56%, 98.78%, 95.87%, and 97.86%, respectively. After generating probabilistic predictions, each prognosis is explained using the SHAP technique that considers both localized and global perspectives. In this manner, the proposed approach offers explanations for predictions, increasing trust in AI applications in the healthcare sector.

Digital Twins (DT), specialized simulated modeling that has been popularized in the industrial domain, are starting to be implemented in the domain of healthcare with significant success. Individualized Internet of Things (IoT) models also have various applications in healthcare, from developing medicine to optimizing treatment. These advancements have the potential to integrate and analyze data from different sources. A Digital Twin-inspired IoT-assisted framework is introduced to analyze irregular physical, visual, and behavioral events of individuals with anxiety disorders in academic environments. The framework utilizes quantum probability techniques to determine irregularities and performs Temporal Data Mining (TDM) to frame requested data granules. These granules are then forwarded to the proposed Multi-level Bi-Gated Recurrent Unit (ML-Bi-GRU) for Health Severity Index (HSI) determination. A smart warning deliverance approach is also proposed to notify caregivers of assistive care. The proposed solution’s health irregularity and severity determination is evaluated on a real-time dataset with a total of 35730 instances. The methodology’s efficacy in the domain of smart healthcare is defined through a case study.

Recently, deep learning and blockchain technologies have gained successful attention due to the high potential of generating accurate decisions and data security, respectively. The data provenances characteristics such as transparency, traceability, and trustworthiness are provided by the vast majority of centralized server-based deep learning approaches. This article examines the advantages of combining deep learning algorithms with blockchain technology. In addition, the most effective strategy for combining these two technologies to achieve the best result is identified through the most recent state-of-the-art literature. In this manner, the article is divided into seven thematic taxonomies based on the literature review: applications of deep learning and blockchain, deep learning techniques, protocols, domains, types of blockchain, and datasets. We have outlined the advantages and disadvantages of blockchain-based deep learning frameworks to facilitate insightful discussions.

Panic disorder (PD) is considered one of the destructive ailments, with various individuals experiencing a critical functional disorder. As the range of remission for PD is achieved only between 20% and 50% with the help of regular pharmacotherapy, modern solutions are expected to deal with this issue. By taking the advantage of Internet of Things (IoT), a novel IoT-inspired behaviour monitoring framework is proposed for the analysis of panic disorder in a particular context. A quantum probability-inspired quantification measure is calculated to determine the scale of health irregularity. In addition, Temporal Data Mining (TDM) is performed for the formulation of temporal data granules to measure Individual Health Index (IHI) by utilising the Multi-scaled Gated Recurrent Unit (M-GRU) technique of deep learning. Moreover, a two-phased alert generation approach is proposed for notifying the current health condition of an individual to the concerned caretaker or medical specialist for assistive or medical services. In the comparative analysis, the proposed framework has outperformed the state-of-the-art approaches by achieving a considerable classification accuracy of 96.89% for event determination and 94.14% accuracy for health severity determination. Similarly, a considerable improvement with respect to Specificity, Sensitivity, and F-measure has been observed for the proposed framework.

Abstract In this pandemic, providing a quality environment is considered one of the essential objectives of smart wellbeing observation. Therefore, the prediction of irregular events has become a fundamental requirement of assistive or clinical consideration. By concentrating on this need, a dew computation-inspired irregular physical event determination solution is presented to determine the symptoms of COVID-19 by analyzing the physical activities of the individuals at their initial stage. The benefit of the proposed solution is enhanced by forwarding the predicted outcomes and their occurrence within a speculated time on a private cloud database to decide the health seriousness. Furthermore, a dynamic decisive-module is introduced to notify medical specialists about the current wellbeing status of the individuals under monitoring. The real-time prediction efficiency of the proposed solution is determined by implementing and calculating the outcomes on both the dew and cloud platforms. The calculated outcomes exhibit the improved viability of the dew platform over the cloud platform by increasing the prediction speed of 46.27% for 40 and 45.54% for 30 frames per second. Moreover, the event prediction performance is justified over the state-of-the-art monitoring arrangements by achieving accuracy (92.88%), specificity (90.87%), sensitivity (88.26%) and F1-measure (89.53%) with the least decision-making delay.

Information and communication technology (ICT) empowered by the Internet of Things (IoT) and fog–cloud paradigm has been widely adopted in several domains of logistics, healthcare, and agriculture. Inspired by the enormous benefits of IoT technology, this research proposes a novel notion of smart restaurants for assessing the food quality using the game theory. Specifically, this research presents a smart framework for food quality assessment inside restaurants. Real-time data are acquired using numerous IoT devices for food quality assessment. The data are communicated to the fog nodes backed by the cloud platform. This enables the time-sensitive analysis of food quality for formalizing a quantifiable measure, i.e., food quality estimate (FQE) using the Bayesian modeling technique. FQE presents a quantification factor for assessing the food quality over temporal patterns in terms of the quality support index (QSI). This is followed by the 2-player game model for effective food quality assessment. The presented model is validated by deploying it over four data sets. Based on the comparative analysis with other decision-making techniques, the presented technique has registered superior performance in terms of temporal effectiveness, classification efficacy, statistical efficiency, and reliability.