The Internet of Things (IoT) provides a virtual view, via the Internet Protocol, to a huge variety of real life objects, ranging from a car, to a teacup, to a building, to trees in a forest. Its appeal is the ubiquitous generalized access to the status and location of any “thing” we may be interested in. Wireless sensor networks (WSN) are well suited for long-term environmental data acquisition for IoT representation. This paper presents the functional design and implementation of a complete WSN platform that can be used for a range of long-term environmental monitoring IoT applications. The application requirements for low cost, high number of sensors, fast deployment, long lifetime, low maintenance, and high quality of service are considered in the specification and design of the platform and of all its components. Low-effort platform reuse is also considered starting from the specifications and at all design levels for a wide array of related monitoring applications.
The current evolution of the traditional medical model toward the participatory medicine can be boosted by the Internet of Things (IoT) paradigm involving sensors (environmental, wearable, and implanted) spread inside domestic environments with the purpose to monitor the user's health and activate remote assistance. RF identification (RFID) technology is now mature to provide part of the IoT physical layer for the personal healthcare in smart environments through low-cost, energy-autonomous, and disposable sensors. It is here presented a survey on the state-of-the-art of RFID for application to body centric systems and for gathering information (temperature, humidity, and other gases) about the user's living environment. Many available options are described up to the application level with some examples of RFID systems able to collect and process multichannel data about the human behavior in compliance with the power exposure and sanitary regulations. Open challenges and possible new research trends are finally discussed.
Zeinab Lashkaripour, Masoud Khosravi-Farmad, AhmadReza Montazerolghaem
et al.
IoT is a dynamic network of interconnected things that communicate and exchange data, where security is a significant issue. Previous studies have mainly focused on attack classifications and open issues rather than presenting a comprehensive overview on the existing threats and vulnerabilities. This knowledge helps analyzing the network in the early stages even before any attack takes place. In this paper, the researchers have proposed different security aspects and a novel Bayesian Security Aspects Dependency Graph for IoT (BSAGIoT) to illustrate their relations. The proposed BSAGIoT is a generic model applicable to any IoT network and contains aspects from five categories named data, access control, standard, network, and loss. This proposed Bayesian Security Aspect Graph (BSAG) presents an overview of the security aspects in any given IoT network. The purpose of BSAGIoT is to assist security experts in analyzing how a successful compromise and/or a failed breach could impact the overall security and privacy of the respective IoT network. In addition, root cause identification of security challenges, how they affect one another, their impact on IoT networks via topological sorting, and risk assessment could be achieved. Hence, to demonstrate the feasibility of the proposed method, experimental results with various scenarios has been presented, in which the security aspects have been quantified based on the network configurations. The results indicate the impact of the aspects on each other and how they could be utilized to mitigate and/or eliminate the security and privacy deficiencies in IoT networks.
Wilfrid Sougrinoma Compaoré, Yaya Etiabi, El Mehdi Amhoud
et al.
Federated Learning (FL) has emerged as a promising paradigm for enabling collaborative machine learning while preserving data privacy, making it particularly suitable for Internet of Things (IoT) environments. However, resource-constrained IoT devices face significant challenges due to limited energy,unreliable communication channels, and the impracticality of assuming infinite blocklength transmission. This paper proposes a federated learning framework for IoT networks that integrates finite blocklength transmission, model quantization, and an error-aware aggregation mechanism to enhance energy efficiency and communication reliability. The framework also optimizes uplink transmission power to balance energy savings and model performance. Simulation results demonstrate that the proposed approach significantly reduces energy consumption by up to 75\% compared to a standard FL model, while maintaining robust model accuracy, making it a viable solution for FL in real-world IoT scenarios with constrained resources. This work paves the way for efficient and reliable FL implementations in practical IoT deployments. Index Terms: Federated learning, IoT, finite blocklength, quantization, energy efficiency.
Bradley Boswell, Seth Barrett, Swarnamugi Rajaganapathy
et al.
The proliferation of Internet of Things (IoT) devices has expanded the attack surface, necessitating efficient intrusion detection systems (IDSs) for network protection. This paper presents FLARE, a feature-based lightweight aggregation for robust evaluation of IoT intrusion detection to address the challenges of securing IoT environments through feature aggregation techniques. FLARE utilizes a multilayered processing approach, incorporating session, flow, and time-based sliding-window data aggregation to analyze network behavior and capture vital features from IoT network traffic data. We perform extensive evaluations on IoT data generated from our laboratory experimental setup to assess the effectiveness of the proposed aggregation technique. To classify attacks in IoT IDS, we employ four supervised learning models and two deep learning models. We validate the performance of these models in terms of accuracy, precision, recall, and F1-score. Our results reveal that incorporating the FLARE aggregation technique as a foundational step in feature engineering, helps lay a structured representation, and enhances the performance of complex end-to-end models, making it a crucial step in IoT IDS pipeline. Our findings highlight the potential of FLARE as a valuable technique to improve performance and reduce computational costs of end-to-end IDS implementations, thereby fostering more robust IoT intrusion detection systems.
The IoT facilitates a connected, intelligent, and sustainable society; therefore, it is imperative to protect the IoT ecosystem. The IoT-based 5G and 6G will leverage the use of machine learning and artificial intelligence (ML/AI) more to pave the way for autonomous and collaborative secure IoT networks. Zero-touch, zero-trust IoT security with AI and machine learning (ML) enablement frameworks offers a powerful approach to securing the expanding landscape of Internet of Things (IoT) devices. This paper presents a novel framework based on the integration of Zero Trust, Zero Touch, and AI/ML powered for the detection, mitigation, and prevention of DDoS attacks in modern IoT ecosystems. The focus will be on the new integrated framework by establishing zero trust for all IoT traffic, fixed and mobile 5G/6G IoT network traffic, and data security (quarantine-zero touch and dynamic policy enforcement). We perform a comparative analysis of five machine learning models, namely, XGBoost, Random Forest, K-Nearest Neighbors, Stochastic Gradient Descent, and Native Bayes, by comparing these models based on accuracy, precision, recall, F1-score, and ROC-AUC. Results show that the best performance in detecting and mitigating different DDoS vectors comes from the ensemble-based approaches.
Emmanuel Ahoa, Ayalew Kassahun, Cor Verdouw
et al.
Traditional farming has evolved from standalone computing systems to smart farming, driven by advancements in digitalization. This has led to the proliferation of diverse information systems (IS), such as IoT and sensor systems, decision support systems, and farm management information systems (FMISs). These systems often operate in isolation, limiting their overall impact. The integration of IS into connected smart systems is widely addressed as a key driver to tackle these issues. However, it is a complex, multi-faceted issue that is not easily achievable. Previous studies have offered valuable insights, but they often focus on specific cases, such as individual IS and certain integration aspects, lacking a comprehensive overview of various integration dimensions. This systematic review of 74 scientific papers on IS integration addresses this gap by providing an overview of the digital technologies involved, integration levels and types, barriers hindering integration, and available approaches to overcoming these challenges. The findings indicate that integration primarily relies on a point-to-point approach, followed by cloud-based integration. Enterprise service bus, hub-and-spoke, and semantic web approaches are mentioned less frequently but are gaining interest. The study identifies and discusses 27 integration challenges into three main areas: organizational, technological, and data governance-related challenges. Technologies such as blockchain, data spaces, AI, edge computing and microservices, and service-oriented architecture methods are addressed as solutions for data governance and interoperability issues. The insights from the study can help enhance interoperability, leading to data-driven smart farming that increases food production, mitigates climate change, and optimizes resource usage.
Pedro Carvalho da Fonseca Guimaraes, Leonardo Braga de Cristo, Marcos Eduardo Pivaro Monteiro
et al.
Ensuring the proper use of Personal Protective Equipment (PPE) is critical for safeguarding workers in high-risk environments, such as power distribution systems. This work presents an innovative approach to monitoring PPE usage through Deep Neural Networks (DNNs). Using data from inertial measurement units (IMUs) integrated into PPE items, we propose a solution to classify three usage states—namely carrying, still, and wearing—using raw accelerometer and gyroscope data. More specifically, this work assesses the effectiveness of three distinct network architectures — Convolutional Neural Networks (CNN), Bidirectional Long Short-Term Memory (BiLSTM), and CNN-BiLSTM—on a publicly released dataset on PPE usage provided by this study, while also comparing them against a traditional baseline Multi-Layer Perceptron (MLP) architecture. Our results demonstrate the superiority of BiLSTM in balancing high accuracy with computational efficiency, achieving above 98% accuracy regardless of the PPE type. This work represents the first application of DNNs for PPE monitoring using IMU data, offering significant implications for enhancing safety compliance and operational monitoring in power distribution.
Abstract The Internet of Things (IoT) is emerging as a functional occurrence in developing numerous critical applications. These applications rely on centralized storage, raising concerns about confidentiality, security, and single points of failure. Conventional IoT security methods are inadequate to address the growing nature of attacks and threats. Blockchain technology has been employed by many investigators in intrusion detection systems for enhanced detection and monitoring, inhibition of mischievous attacks or activities, and tamper-proof dealings and storage in IoT networks and devices. At present, using artificial intelligence knowledge, mainly deep learning and machine learning approaches, endures the basics to deliver a dynamically improved and up-to-date security method for next-generation IoT systems. This study proposes a Leveraging Blockchain for Cybersecurity Detection Using Golden Jackal Optimization (LBCCD-GJO) method in IoT. The presented LBCCD-GJO method initially applies data pre-processing using min–max normalization to convert input data into a beneficial format. Moreover, the feature selection process is implemented by utilizing the golden jackal optimization (GJO) model. Furthermore, the proposed LBCCD-GJO model employs the gated recurrent unit (GRU) technique for the classification process of cyberattacks. Finally, the hyperparameter selection of the GRU technique is performed by implementing the hybrid of prairie dog optimization with a differential evolution (PDO-DE) technique. An extensive set of simulations was performed to exhibit the promising outcomes of the LBCCD-GJO methodology under the TON_IoT_Train_Test_Network dataset. The experimental validation of the LBCCD-GJO methodology is 99.67% compared to the previous techniques.
Precision irrigation is essential for sustainable agriculture under increasing water scarcity. This study compared regression and ensemble learning algorithms for forecasting irrigation requirements in sweet potato, a crop characterized by high variability in water demand. An Internet of Things (IoT)-based prototype was deployed to collect real-time data on soil moisture, temperature, humidity, light intensity, and atmospheric pressure over 42 hours and 50 minutes (August 4-5, 2025), encompassing two complete diurnal cycles at 10-minute intervals and yielding 243 temporal observations. Following preprocessing and feature engineering with lag-based temporal features, the final dataset comprised 240 samples (192 training, 48 testing) using chronological time-based splitting to prevent data leakage. Five algorithms, Support Vector Regression (SVR), AdaBoost, Extreme Gradient Boosting (XGBoost), Random Forest Regressor (RFR), and CatBoost, were evaluated under default and hyperparameter-tuned configurations using Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and Coefficient of Determination (R²) as evaluation metrics. Tuned Random Forest achieved superior performance (R² = 0.9802, RMSE = 9.58, MAE = 6.08), followed by default Random Forest (R² = 0.9786) and default CatBoost (R² = 0.9687). XGBoost demonstrated strong performance (R² = 0.9670 tuned) but exhibited overfitting tendencies with near-perfect training scores. SVR improved substantially after tuning (R² = 0.328 to 0.797), although it remained inferior to ensemble methods. Overall, ensemble methods, particularly XGBoost and Random Forest, demonstrated superior efficacy for sweet potato irrigation forecasting. These findings underscore the potential of IoT-integrated machine learning to enhance water-use efficiency and support sustainable smart farming practices.
Kunal Chandnani, Suryakant Tripathy, Ashutosh Krishna Parbhakar
et al.
Abstract The IoT Smart Cradle for Baby Monitoring System & Infant Care is introduced as an innovative solution to address critical gaps in contemporary infant care. This system integrates Internet of Things (IoT) technology, machine learning, and smart automation to offer a safer, more responsive, and comfortable environment for babies. A significant challenge in current infant care is the limitations of traditional monitoring systems. These systems often fail to provide comprehensive, real-time monitoring of essential environmental parameters and lack automated responses to an infant’s immediate needs, potentially increasing parental anxiety and compromising infant safety and well-being. This smart cradle is designed to overcome these limitations by employing a comprehensive network of sensors—including temperature, humidity, gas, noise sensors, and a cry-detection microphone—to monitor the baby’s needs and environmental conditions in real time. Microcontrollers like Raspberry Pi and NodeMCU use intelligent machine-learning algorithms to process the collected data and trigger adaptive responses. These responses include regulating temperature and humidity, filtering harmful gases, and activating a motorized rocking mechanism to soothe the infant. A dedicated mobile application offers parents secure, real-time monitoring and control over the cradle’s functions. The system demonstrates high accuracy in sensor readings, with temperature and humidity measurements reaching approximately 99.6% accuracy, and cry detection achieving approximately 93.2% accuracy. User feedback indicates that 95% of parents found the interface easy to use, and 87% reported a positive impact on their parenting experience. In contrast to traditional solutions that often require manual intervention or provide limited automation, this smart cradle uses predictive analytics to proactively address potential discomforts and hazards, thus presenting a more reliable, intelligent, and user-friendly solution for modern parenting.
Haider Q. Mutashar, Hiba A. Abu-Alsaad, Sawsan M. Mahmoud
It is essential to assign the correct triage level to patients as soon as they arrive in the emergency department in order to save lives, especially during peak demand. However, many healthcare systems estimate the triage levels by manual eyes-on evaluation, which can be inconsistent and time consuming. This study creates a full Digital Twin-based architecture for patient monitoring and automated triage level recommendation using IoT sensors, AI, and cloud-based services. The system can monitor all patients’ vital signs through embedded sensors. The readings are used to update the Digital Twin instances that represent the present condition of the patients. This data is then used for triage prediction using a pretrained model that can predict the patients’ triage levels. The training of the model utilized the synthetic minority over-sampling technique, combined with Tomek links to lessen the degree of data imbalance. Additionally, Lagrange element optimization was applied to select those features of the most informative nature. The final triage level is predicted using the Tabular Prior-Data Fitted Network, a transformer-based model tailored for tabular data classification. This combination achieved an overall accuracy of 87.27%. The proposed system demonstrates the potential of integrating digital twins and AI to improve decision support in emergency healthcare environments.