Various Artificial Intelligence (AI) techniques in water resource management highlight the current methodologies’ strengths and limitations in forecasting, optimization, and control. We identify a gap in integrating these diverse approaches for enhanced water prediction and management. We critically analyze the existing literature on artificial neural networks (ANNs), deep learning (DL), long short-term memory (LSTM) networks, machine learning (ML) models such as supervised learning (SL) and unsupervised learning (UL), and random forest (RF). In response, we propose a novel framework that synergizes these techniques into a unified, multi-layered model and incorporates a digital twin and a multi-modal transformer approach. This integration aims to leverage the collective advantages of each method while overcoming individual constraints, significantly enhancing prediction accuracy and operational efficiency. This paper sets the foundation for an innovative digital twin-integrated solution, focusing on reviewing past works as a precursor to a detailed exposition of our proposed model in a subsequent publication. This advanced approach promises to redefine accuracy in water demand forecasting and contribute significantly to global sustainability and efficiency in water use.

Industry 5.0 builds on the foundations of Industry 4.0 and ensures the transition to a sustainable, flexible, and human-centric workplace. The transition from Industry 4.0 to Industry 5.0 addresses important limitations of traditional automation, such as limited flexibility, human-machine collaboration. Industry 5.0 seeks to overcome these issues through evolution, with an emphasis on sustainability, resilience, and human-centric interactions. However, these changes come with challenges related to real-time adaptation and optimal resource allocation in dynamic industrial environments. To facilitate this transition, we propose a Digital Twin (DT) system that employs a Soft Actor-Critic (SAC) , which is a reinforcement learning algorithm. This integration enhances adaptability in real-time, efficient resource allocation, and flexibility in dynamic industrial environments. The SAC-DT algorithm is evaluated using three main scenarios: demand change management, real-time control under uncertain conditions, and optimization of performance. These scenarios demonstrate how the SAC-DT increases productivity, adaptability, reliability, energy efficiency, and reduced downtime. The proposed scheme is compared with baseline models which include DRL-DRP and GCNN-DRL. The analyses show that the SAC-DT scheme yields better productivity, flexibility and, resource utilization efficiency, thus highlighting the applicability of this proposed scheme as valuable to move closer to Industry 5.0 that will guarantee solid, reliable, pragmatic, sustainable technological implementations that meet industrial goals and requirements in future.

The rapid growth of Internet of Things (IoT) devices presents significant cybersecurity challenges due to their diverse and resource-constrained nature. Existing security solutions often fall short in addressing the dynamic and distributed environments of IoT systems. This study aims to propose a novel deep learning framework, SecEdge, designed to enhance real-time cybersecurity in mobile IoT environments. The SecEdge framework integrates transformer-based models for efficient handling of long-range dependencies and Graph Neural Networks (GNNs) for modeling relational data, coupled with federated learning to ensure data privacy and reduce latency. The adaptive learning mechanism continuously updates model parameters to counter evolving cyber threats. The framework's performance was evaluated in a simulation environment using the NSL-KDD, UNSW-NB15, and CICIDS2017 datasets. Results demonstrated that SecEdge outperformed state-of-the-art methods with a detection rate of 98.8% for DoS attacks on NSL-KDD, 98.5% for MitM attacks on UNSW-NB15, and 98.7% for data injection attacks on CICIDS2017.

This paper proposes an Enhanced Edge-Linked Caching (EELC) scheme for Internet of Things (IoT) environments under Information-Centric Networking (ICN), employing an advanced use of Proximal Policy Optimization (PPO), a form of deep reinforcement learning, to inform the caching decisions of edge nodes. The rapid proliferation of IoT devices has led to significant challenges in managing content efficiently within networks, particularly in terms of scalability, latency, and energy consumption. Traditional IP-based architectures are inadequate in addressing these challenges, necessitating a shift towards a content-centric approach provided by ICN. By leveraging PPO, EELC dynamically adapts to changing IoT network conditions, optimizing caching strategies to enhance energy efficiency and improve network responsiveness. In our simulation, we verify the performance of EELC in comparison to the Edge-Linked Caching (ELC) and Leave Copy Everywhere (LCE) approaches under different cache sizes and Zipf-distributed content requests. EELC performs far better than ELC under energy efficiency, cache hit ratios, and server hit reduction in all tested scenarios. This indicates that EELC could be a potential approach for significantly improving network efficiency and responsiveness in IoT networks.

Artificial intelligence (AI) is transforming the electrical grid by incorporating advanced communication protocols and novel monitoring infrastructure. This transformation alters traditional methods of electricity consumption and billing, shifting from manual meter reading to dynamic peak-hour tariff rates. While people are open to upgrading their energy consumption systems with cutting-edge technology, they express concerns over transmitting their data over wireless networks, fearing unauthorized access to their private information for unpredictable purposes. Thus, establishing trust in the new technology is crucial before individuals feel secure about sharing their personal information. In this study, we introduce PowerTrust, an ensemble learning stacking model designed to evaluate trust and safeguard user privacy in the Internet of Grid Things. PowerTrust is divided into two parts. In the first part, it assesses the trustworthiness of smart grid devices. In the second part, it proposes a secure scrambling method to protect electricity readings before they are transmitted to the control center. During trust evaluation, data is balanced, important features are extracted, and then a classification model is applied. The yynthetic minority oversampling technique is used to balance the dataset, and recursive feature elimination is used to select important features. The results show that the proposed scheme is secure and efficient in maintaining trust and privacy in the grid environment.

In modern healthcare monitoring, wearable sensors play a crucial role in collecting patient data, especially for individuals with disabilities. However, analyzing this data presents significant challenges, such as high energy consumption, latency, and task allocation inefficiencies. Healthcare monitoring systems face computational demands due to the processing of data from wearable sensors, which are constrained by limited resources and often affected by connectivity issues for data offloading. To address these challenges, this paper proposes a Cooperative Dew-Computing for Healthcare (CCH) framework, which integrates wearable sensors and dew devices within a cloud-fog-dew infrastructure. The CCH framework ensures efficient task distribution and computational offloading by selecting appropriate anchor devices using probabilistic and fuzzy logic techniques, taking into account energy efficiency and computational capabilities. Cooperative communication among anchor devices enables efficient task management, allowing tasks to be offloaded or distributed among multiple anchor devices. The proposed framework enhances healthcare monitoring systems by improving computational efficiency, optimizing resource utilization, and mitigating connectivity issues. This is particularly beneficial for disabled patients who rely on continuous monitoring and efficient data processing. Our evaluations demonstrate that the CCH framework outperforms existing techniques in terms of energy efficiency, latency, and task delay reduction, underscoring its effectiveness in providing timely and efficient data processing for healthcare monitoring systems.