The Mobile Reliable Opportunistic Routing (MROR) protocol improves data-forwarding reliability in Cognitive Radio Sensor Networks (CRSNs) through mobility-aware virtual contention groups and handover zoning. However, its heuristic decision logic is difficult to optimize under highly dynamic spectrum access and random node mobility. To address this limitation, we present DRL-MROR, a refined routing framework that incorporates deep reinforcement learning (DRL) to enable intelligent and adaptive forwarding decisions. In DRL-MROR, the secondary users (SUs) act as autonomous agents that observe local state information, including primary-user activity, link quality, residual energy, and neighbor-mobility patterns. Each agent learns a forwarding policy through a Deep Q-Network (DQN) optimized for long-term network utility in terms of throughput, delay, and energy efficiency. We formulate routing as a Markov Decision Process (MDP) and use experience replay with prioritized sampling to improve learning stability and convergence. The DQN used at each node is intentionally lightweight, requiring 5514 trainable parameters, about 21.5 kB of weight storage in 32-bit precision, and approximately 5.4k multiply-accumulate operations per inference, which supports practical deployment on edge-capable CRSN nodes. Extensive simulations show that DRL-MROR outperforms the original MROR protocol and representative AI-based routing baselines such as AIRoute under diverse operating conditions. The results indicate gains of up to 38% in throughput, 42% in goodput, a 29% reduction in energy consumed per packet, and an approximately 18% improvement in network lifetime, while maintaining high route stability and fairness. DRL-MROR also reduces control overhead by about 30% and average end-to-end delay by up to 32%, maintaining strong performance even under elevated PU activity and higher node mobility. These results show that augmenting opportunistic routing with lightweight DRL can substantially improve adaptability and efficiency in next-generation IoT-oriented CRSNs.

The pervasive adoption of AI and AIoT applications at the network edge presents both opportunities and challenges for smart cities. With a focus on the energy efficiency of AI in urban environments, this paper provides a systematic comparative analysis of representative edge hardware platforms, i.e., embedded GPUs, FPGAs, and ultra-low-power microcontroller-/sensor-class devices, assessing their suitability for AI workloads in IoT-driven smart city infrastructures. The evaluation, based on direct characterization of diverse neural networks and relevant datasets, quantifies computational performance and energy behavior through inference latency, throughput, and energy/per inference measurements. Across the evaluated network–board pairs, the measured inference power spans several orders of magnitude, ranging from 0.1–10 mW for ultra-low-power Intelligent Sensor Processing Units (ISPUs) up to 1–10 W for embedded GPUs, highlighting the wide design space between the least and most power-demanding configurations. Results indicate that embedded GPUs provide a favorable performance-to-power ratio for computationally intensive workloads, while MCU/ISPU-class solutions, despite throughput limitations, offer compelling advantages in ultra-low-power scenarios when combined with quantization and pruning, making them well-suited for distributed sensing and actuation typical of smart city deployments. Overall, this comparative analysis guides hardware selection for heterogeneous, sustainable AI-enabled urban services.

Traffic congestion and travel time uncertainty remain major challenges to the operational efficiency of Bus Rapid Transit (BRT) systems in urban areas of developing countries. This study proposes an integrated solution for the Trans Metro Bandung (TMB) system by leveraging Internet of Things (IoT)–based GPS data and tree-based ensemble machine learning algorithms. Spatio-temporal data collected from on-board GPS modules are processed to predict traffic congestion levels and estimate travel time across route segments. The performance of Decision Tree, Random Forest, and XGBoost models is evaluated in terms of prediction accuracy, interpretability, and computational efficiency, with particular consideration for deployment on resource-constrained hardware. Experiments conducted on 20,156 data samples show that the Decision Tree model achieves the highest congestion classification accuracy of 96.8%, while Random Forest outperforms other models in travel time regression, achieving an R2 value of 0.95 and a root mean square error (RMSE) of 5.80 min. The trained models are successfully deployed on a Raspberry Pi 3B microcontroller for real-time inference, enabling fleet management and travel planning without reliance on cloud connectivity. The results demonstrate that cost-effective and interpretable machine learning solutions can deliver reliable performance in heterogeneous urban infrastructures while providing a replicable framework for medium-sized cities seeking to implement affordable smart transportation systems.

The growing demand for IoT applications in highly dynamic environments with multiple connected devices introduces significant scalability and low-latency challenges. In the context of software-defined networking (SDN) integrated with Edge environments, adopting machine learning (ML) techniques has emerged as a promising approach to meet these requirements. This study presents a Systematic Literature Review (SLR) that identifies and analyzes ML-based solutions applied to Software-Defined Internet of Things (SD-IoT) infrastructures in Edge environments, emphasizing improving low latency and scalability. Following established methodological best practices, we conducted the review, including a clear definition of research questions, well-defined inclusion and exclusion criteria, a structured search protocol, and multiple scientific databases. Based on the analysis of selected studies, the main strategies employed to enhance network performance are categorized, along with the level of fidelity and complexity of the experimental environments used, and the realism and applicability of the proposed solutions are discussed. Furthermore, drawing from the context of the selected studies, the most recurrent ML approaches are presented—including supervised, unsupervised, and reinforcement learning methods—along with a discussion of their advantages and limitations in dynamic network scenarios. By compiling and organizing the contributions from the literature, this paper provides a comprehensive overview of the state of the art in applying ML to SD-IoT networks, shedding light on current trends, existing gaps, and research opportunities aimed at building more intelligent and adaptable solutions for IoT environments.

Since the deployment of the Internet of Things (IoT), it has transformed everyday life by enabling intelligent environments that improve efficiency and automate services in domains such as agriculture, healthcare, smart cities, and industry. However, the rapid proliferation of IoT devices has introduced significant security challenges, largely driven by the heterogeneity of devices, resource constraints, and the increasing exposure of network communications. This work proposes a lightweight security protection mechanism for IoT networks based on trust modelling. The proposed approach integrates machine learning techniques to evaluate IoT node behavior using network-layer (Layer 3) traffic features under different labeling granularities, including binary, categorical, and subcategorical classifications. By focusing on network-layer observations, the model remains applicable across heterogeneous IoT devices while preserving a low computational footprint. In addition, the Common Vulnerability Scoring System (CVSS) is incorporated as a standardized vulnerability severity metric, enabling the integration of probabilistic security evidence with contextual information about potential impact. This combination allows the estimation of trust to reflect not only the likelihood of anomalous behavior but also its associated severity. Experimental evaluation was conducted using a representative IoT traffic dataset, multiple preprocessing strategies, and several classical machine learning models. The results demonstrate that aggregating traffic-based intrusion detection outputs with vulnerability severity metrics enables a more robust, flexible, and interpretable trust estimation process. This approach supports the early identification of potentially compromised nodes while maintaining scalability and efficiency, making it suitable for deployment in heterogeneous IoT environments.

The predominant approach in the realm of industrial process monitoring and control involves the utilization of HMI (Human–Machine Interface) interfaces and conventional SCADA (Supervisory Control and Data Acquisition) systems. This limitation restricts user mobility, interaction with industrial equipment, and process status assessment. In the context of Industry 4.0, the ability to monitor and control industrial processes in real time is paramount. The present paper designs and implements a system for monitoring and controlling an industrial assembly line based on mixed reality. The technology employed to facilitate communication between the system and the industrial line is S7.Net. These elements facilitate direct communication with the industrial process equipment. The system facilitates the visualization of operating parameters and the status of the equipment utilized in the industrial process and its control. All data is superimposed on the physical environment through virtual operational panels. The system functions independently, negating the necessity for intermediate servers or other complex structures. The system’s operation is predicted on a series of algorithms. These instruments facilitate the automated analysis of industrial process parameters. These devices are utilized to ascertain the operational dynamics of the industrial line. The experimental results were obtained using a real industrial line. These models are employed to demonstrate the performance of data transmission, the identification of the system’s operating states, and the system’s ability to shut down in the event of operating errors. The proposed system is designed to function in a variety of industrial environments within the paradigm of Industry 4.0, facilitating the utilization of multiple virtual interfaces that enable user interaction with various elements through which the assembly process is monitored and controlled.

Narrowband Internet of Things (NB-IoT) is widely used for connecting low-power devices that must operate for years without maintenance. To design reliable systems, it is essential to understand how much energy these devices consume under different conditions and which power sources can support long lifetimes. This study presents a detailed experimental evaluation of NB-IoT power consumption using a commercial System-on-Module (LMT-SoM). We measured various transmissions across different payload sizes, signal strengths, and temperatures. The results show that sending larger packets is far more efficient: a 1280-byte message requires about 7 times less energy per bit than an 80-byte message. However, standby currents varied widely between devices, from 6.7 µA to 23 µA, which has a major impact on battery life. Alongside these experiments, we compared different power sources for a 5-year deployment. Alkaline and lithium-thionyl chloride batteries were the most cost-effective solutions for indoor use, while solar panels combined with supercapacitors provided a sustainable option for outdoor applications. These findings offer practical guidance for engineers and researchers to design NB-IoT devices that balance energy efficiency, cost, and sustainability.

In the 21st century, Urbanization, population growth, and climate change have created significant problems in water resource management. Recent advancements in technologies such as Internet of Things (IoT), Edge Computing (EC), Artificial Intelligence (AI), and Big Data Analytics (BDA) are changing the operations of the water resource management systems. In this study, we present a systematic review, highlighting the contributions of these technologies in water management systems. More specifically, we highlight the IoT and EC water monitoring systems that enable real-time sensing of water quality and consumption. In addition, AI methods for anomaly detection and predictive maintenance are reviewed, focusing on water demand forecasting. BDA methods are also discussed, highlighting their ability to integrate data from different data sources, such as sensors and historical data. Additionally, a discussion is provided of how Water management systems could enhance sustainability, resilience, and efficiency by combining big data, IoT, EC, and AI. Lastly, future directions are outlined regarding how state-of-the-art technologies may further support efficient water resources management.

There is increasing interest in improving the reliability of short-range wireless links in dense IoT deployments, where BLE is widely used due to its low power consumption and robust GFSK modulation. For this purpose, this work presents a novel Orthogonal Space-Time (OST) scheme for transmission and detection of BLE signals while preserving the BLE GFSK waveform and modulation constraints. The proposed signal processing system integrates advanced OST coding techniques with nonlinear GFSK modulation to achieve high-quality communication while maintaining phase continuity. This implies that the standard BLE GFSK modulator and demodulator blocks can be reused, with additional processing introduced only in the multi-antenna encoder and combiner. A detailed theoretical analysis demonstrates the feasibility of employing the Rayleigh fading channel model in BLE communications and establishes the BER performance bounds for various MIMO configurations. Simulations confirm the advantages of the proposed OST-GFSK signal processing scheme, maintaining a consistent performance when compared with OST linear modulation approaches under Rayleigh fading channels. As a result, the proposed IoT-enabling technology integrates the advantages of widely used OST linear modulation with nonlinear GFSK modulation required for BLE.