The rapid growth of Internet of Things (IoT) devices has increased the scale and diversity of cyberattacks, exposing limitations in traditional intrusion detection systems. Classical machine learning (ML) models such as Random Forest and Support Vector Machine perform well on known attacks but require retraining to detect unseen or zero-day threats. This study investigates lightweight decoder-only Large Language Models (LLMs) for IoT attack detection by integrating structured-to-text conversion, Quantized Low-Rank Adaptation (QLoRA) fine-tuning, and Retrieval-Augmented Generation (RAG). Network traffic features are transformed into compact natural-language prompts, enabling efficient adaptation under constrained hardware. Experiments on the CICIoT2023 dataset show that a QLoRA-tuned LLaMA-1B model achieves an F1-score of 0.7124, comparable to the Random Forest (RF) baseline (0.7159) for known attacks. With RAG, the system attains 42.63% accuracy on unseen attack types without additional training, demonstrating practical zero-shot capability. These results highlight the potential of retrieval-enhanced lightweight LLMs as adaptable and resource-efficient solutions for next-generation IoT intrusion detection.
In this study, a Multi-Sensor IoT Device (MSID) is developed that is designed to collect various environmental data and interconnect with the cloud and blockchain to ensure reliable data management. The MSID is designed with a flexible, modular structure that supports a variety of sensor configurations and is easily expandable with 3D-printed components. The system performance was monitored in real-time, with a high cloud upload success rate of 98.35% and an average transmission delay of only 0.64 s, confirming stable data collection every minute. Blockchain-based sensor data storage ensured data integrity and tamper-proofness, with all transactions successfully recorded and verified via smart contract. The proposed Blockchain-based Mobile IoT System (BMIS) has shown strong potential for use in environmental monitoring, industrial asset management, and other areas that require reliable data collection and long-term preservation.
The safe and swift evacuation of passengers from Maritime Vessels, requires an effective Internet of Things(IoT) as well as an information and communication technology(ICT) infrastructure. However, during emergencies, delays in IoT and ICT systems that guide evacuees, can impair the evacuation process. This paper presents explores the impact of the key IoT and ICT elements. The methodology builds upon the deadline-aware adaptive navigation strategy (ANT), which offers the path segment that minimizes the evacuation time for each evacuee at each decision instant. The simulations on a real cruise ship configuration, show that delays in the delivery of correct instructions to evacuees can significantly hinder the effectiveness of the evacuation. Our findings stress the need to design robust and computationally fast IoT and ICT systems to support the evacuation of passengers in ships, and underscores the key role played by the IoT in the success of passenger evacuation and safety.
Paolo Cerutti, Fabio Palmese, Marco Cominelli
et al.
Wi-Fi sensing is an emerging technology that uses channel state information (CSI) from ambient Wi-Fi signals to monitor human activity without the need for dedicated sensors. Wi-Fi sensing does not only represent a pivotal technology in intelligent Internet of Things (IoT) systems, but it can also provide valuable insights in forensic investigations. However, the high dimensionality of CSI data presents major challenges for storage, transmission, and processing in resource-constrained IoT environments. In this paper, we investigate the impact of lossy compression on the accuracy of Wi-Fi sensing, evaluating both traditional techniques and a deep learning-based approach. Our results reveal that simple, interpretable techniques based on principal component analysis can significantly reduce the CSI data volume while preserving classification performance, making them highly suitable for lightweight IoT forensic scenarios. On the other hand, deep learning models exhibit higher potential in complex applications like activity recognition (achieving compression ratios up to 16000:1 with minimal impact on sensing performance) but require careful tuning and greater computational resources. By considering two different sensing applications, this work demonstrates the feasibility of integrating lossy compression schemes into Wi-Fi sensing pipelines to make intelligent IoT systems more efficient and improve the storage requirements in forensic applications.
The rapid expansion of the Internet of Things (IoT) has intensified security challenges, notably from Distributed Denial of Service (DDoS) attacks launched by compromised, resource-constrained devices. Traditional defenses are often ill-suited for the IoT paradigm, creating a need for lightweight, high-performance, edge-based solutions. This paper presents the design, implementation, and evaluation of an IoT security framework that leverages the extended Berkeley Packet Filter (eBPF) and the eXpress Data Path (XDP) for in-kernel mitigation of DDoS attacks. The system uses a rate-based detection algorithm to identify and block malicious traffic at the earliest stage of the network stack. The framework is evaluated using both Docker-based simulations and real-world deployment on a Raspberry Pi 4, showing over 97% mitigation effectiveness under a 100 Mbps flood. Legitimate traffic remains unaffected, and system stability is preserved even under attack. These results confirm that eBPF/XDP provides a viable and highly efficient solution for hardening IoT edge devices against volumetric network attacks.
Francisco-Jose Alvarado-Alcon, Rafael Asorey-Cacheda, Antonio-Javier Garcia-Sanchez
et al.
The Internet of Things (IoT) is gaining significant attention for its ability to digitally transform various sectors by enabling seamless connectivity and data exchange. However, deploying these networks is challenging due to the need to tailor configurations to diverse application requirements. To date, there has been limited focus on examining and enhancing the carbon footprint (CF) associated with these network deployments. In this study, we present an optimization framework leveraging machine learning techniques to minimize the CF associated with IoT multi-hop network deployments by varying the placement of the required gateways. Additionally, we establish a direct comparison between our proposed machine learning method and the integer linear program (ILP) approach. Our findings reveal that placing gateways using neural networks can achieve a 14% reduction in the CF for simple networks compared to those not using optimization for gateway placement. The ILP method could reduce the CF by 16.6% for identical networks, although it incurs a computational cost more than 250 times higher, which has its own environmental impact. Furthermore, we highlight the superior scalability of machine learning techniques, particularly advantageous for larger networks, as discussed in our concluding remarks.
Electronic computers. Computer science, Information technology
Monitoring and diagnosis of cardiovascular diseases rely on cardiac motion estimation. The methods used for registering echocardiographic images have drawbacks such as low resolution, noise, and distortion of the anatomy. In order to enhance the prediction of cardiac motion, this research presents an AI-powered architecture that makes use of Vision Transformers, Diffusion Models, and Neural Radiance Fields (NeRF). Adversarial and self-supervised contrastive learning enhance picture quality and generalisability across adult and foetal echocardiography, while a graph neural network (GNN)-based anatomical constraint maintains heart shape. Better, more accurate, more efficient real-time motion tracking without relying on massive labelled datasets is possible with the proposed approach. Cardiac motion analysis in a wide range of patient populations is now therapeutically viable, thanks to this innovative approach that improves echocardiographic picture registration. • Utilizes Vision Transformers, Diffusion Models, and NeRF for high-quality cardiac motion prediction. • Adversarial and self-supervised contrastive learning improve echocardiographic registration across demographics. • A GNN-based anatomical constraint ensures accurate heart morphology during motion analysis.
Giacomo Giannetti, Marco Badii, Giovanni Lasagni
et al.
This work presents an Internet of Things (IoT) node designed for low-power agrifood chain tracking in remote areas, where long-range terrestrial communication is either unavailable or severely limited. The novelty of this study lies in the development and characterization of an IoT node prototype that leverages direct-to-satellite connectivity through a geostationary Earth orbit (GEO) satellite, using long-range frequency-hopping spread spectrum (LR-FHSS) modulation in the licensed S-band. The prototype integrates a microcontroller unit that manages both the radio modem and a suite of sensors, enclosed in a plastic box suitable for field deployment. Characterization in an anechoic chamber demonstrated a maximum effective isotropic radiated power (EIRP) of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>27.5</mn></mrow></semantics></math></inline-formula> dBm, sufficient to establish a reliable satellite link. The onboard sensors provide global positioning as well as measurements of acceleration, temperature, humidity, and solar radiation intensity. Prototype performance was assessed in two representative scenarios: stationary and mobile. Regarding energy consumption, the average charge drained by the radio modem per transmission cycle was measured to be 356 mC. With a battery pack composed of four 2500 mAh NiMH cells, the estimated upper bound on the number of transmitted packets is approximately 25,000.
El IoT (Internet de las cosas, por su acrónimo en inglés) ha revolucionado la forma en que interactuamos con el mundo digital, conectando dispositivos y sistemas para recopilar y compartir datos. Sin embargo, la calidad del software en IoT es crucial, ya que manejan datos que son importantes y confidenciales de las empresas que las utilizan. Es signicativo hacer un análisis de las plataformas que existen en el mercado para identificar la que se adapte mejor a las necesidades del cliente. Los modelos de calidad, como FURPS (Functionality, Usability, Reliability, Performance, Supportability, por su acrónimo en inglés), ofrecen un marco para evaluar la calidad del software o plataformas, lo que ayuda a elegir el elemento factible para una empresa. En el presente trabajo, se hace una comparación de tres plataformas que son sobresalientes en el mercado, a través del modelo de calidad FURPS y con la escala de Likert se asigna una ponderación para identificar la plataforma factible en cuanto a tratamiento de datos y compatibilidad con otras herramientas
As the world becomes increasingly urbanized, the development of smart cities and the deployment of IoT applications will play an essential role in addressing urban challenges and shaping sustainable and resilient urban environments. However, there are also challenges to overcome, including privacy and security concerns, and interoperability issues. Addressing these challenges requires collaboration between governments, industry stakeholders, and citizens to ensure the responsible and equitable implementation of IoT technologies in smart cities. The IoT offers a vast array of possibilities for smart city applications, enabling the integration of various devices, sensors, and networks to collect and analyze data in real time. These applications span across different sectors, including transportation, energy management, waste management, public safety, healthcare, and more. By leveraging IoT technologies, cities can optimize their infrastructure, enhance resource allocation, and improve the quality of life for their citizens. In this paper, eight smart city global models have been proposed to guide the development and implementation of IoT applications in smart cities. These models provide frameworks and standards for city planners and stakeholders to design and deploy IoT solutions effectively. We provide a detailed evaluation of these models based on nine smart city evaluation metrics. The challenges to implement smart cities have been mentioned, and recommendations have been stated to overcome these challenges.
Machine Learning (ML) is becoming increasingly important for IoT-based applications. However, the dynamic and ad-hoc nature of many IoT ecosystems poses unique challenges to the efficacy of ML algorithms. One such challenge is data incompleteness, which is manifested as missing sensor readings. Many factors, including sensor failures and/or network disruption, can cause data incompleteness. Furthermore, most IoT systems are severely power-constrained. It is important that we build IoT-based ML systems that are robust against data incompleteness while simultaneously being energy efficient. This paper presents an empirical study of SECOE - a recent technique for alleviating data incompleteness in IoT - with respect to its energy bottlenecks. Towards addressing the energy bottlenecks of SECOE, we propose ENAMLE - a proactive, energy-aware technique for mitigating the impact of concurrent missing data. ENAMLE is unique in the sense that it builds an energy-aware ensemble of sub-models, each trained with a subset of sensors chosen carefully based on their correlations. Furthermore, at inference time, ENAMLE adaptively alters the number of the ensemble of models based on the amount of missing data rate and the energy-accuracy trade-off. ENAMLE's design includes several novel mechanisms for minimizing energy consumption while maintaining accuracy. We present extensive experimental studies on two distinct datasets that demonstrate the energy efficiency of ENAMLE and its ability to alleviate sensor failures.
Vadim Safronov, Ionut Bostan, Nicholas Allott
et al.
The rapid development of the Internet of Things (IoT) has enabled novel user-centred applications, including many in safety-critical areas such as healthcare, smart environment security, and emergency response systems. The diversity in IoT manufacturers, standards, and devices creates a combinatorial explosion of such deployment scenarios, leading to increased security and safety threats due to the difficulty of managing such heterogeneity. In almost every IoT deployment, wireless gateways are crucial for interconnecting IoT devices and providing services, yet they are vulnerable to external threats and serve as key entry points for large-scale IoT attacks. Memory-based vulnerabilities are among the most serious threats in software, with no universal solution yet available. Legacy memory protection mechanisms, such as canaries, RELRO, NX, and Fortify, have enhanced memory safety but remain insufficient for comprehensive protection. Emerging technologies like ARM-MTE, CHERI, and Rust are based on more universal and robust Secure-by-Design (SbD) memory safety principles, yet each entails different trade-offs in hardware or code modifications. Given the challenges of balancing security levels with associated overheads in IoT systems, this paper explores the impact of memory safety on the IoT domain through an empirical large-scale analysis of memory-related vulnerabilities in modern wireless gateways. Our results show that memory vulnerabilities constitute the majority of IoT gateway threats, underscoring the necessity for SbD solutions, with the choice of memory-protection technology depending on specific use cases and associated overheads.
With the proliferation of digitization and its usage in critical sectors, it is necessary to include information about the occurrence and assessment of cyber threats in an organization's threat mitigation strategy. This Cyber Threat Intelligence (CTI) is becoming increasingly important, or rather necessary, for critical national and industrial infrastructures. Current CTI solutions are rather federated and unsuitable for sharing threat information from low-power IoT devices. This paper presents a taxonomy and analysis of the CTI frameworks and CTI exchange platforms available today. It proposes a new CTI architecture relying on the MISP Threat Intelligence Sharing Platform customized and focusing on IoT environment. The paper also introduces a tailored version of STIX (which we call tinySTIX), one of the most prominent standards adopted for CTI data modeling, optimized for low-power IoT devices using the new lightweight encoding and cryptography solutions. The proposed CTI architecture will be very beneficial for securing IoT networks, especially the ones working in harsh and adversarial environments.
K. S. Viswanadh, Akshit Gureja, Nagesh Walchatwar
et al.
Remote labs are a groundbreaking development in the education industry, providing students with access to laboratory education anytime, anywhere. However, most remote labs are costly and difficult to scale, especially in developing countries. With this as a motivation, this paper proposes a new remote labs (RLabs) solution that includes two use case experiments: Vanishing Rod and Focal Length. The hardware experiments are built at a low-cost by retrofitting Internet of Things (IoT) components. They are also made portable by designing miniaturised and modular setups. The software architecture designed as part of the solution seamlessly supports the scalability of the experiments, offering compatibility with a wide range of hardware devices and IoT platforms. Additionally, it can live-stream remote experiments without needing dedicated server space for the stream. The software architecture also includes an automation suite that periodically checks the status of the experiments using computer vision (CV). RLabs is qualitatively evaluated against seven non-functional attributes - affordability, portability, scalability, compatibility, maintainability, usability, and universality. Finally, user feedback was collected from a group of students, and the scores indicate a positive response to the students' learning and the platform's usability.
Daniela Popescul, Lily Murariu, Laura-Diana Radu
et al.
Utilizing readily accessible information and communication technologies (ICTs), such as mobile devices, applications, and simple Internet of Things (IoT) sensors, and harnessing their potential through Experimentation as a Service (EaaS), crowdsensing, and gamification, represents one of the most effective approaches to implementing co-creation in smart cities. The benefits of this bottom-up approach are closely related to accurately identifying the real needs of city residents and increasing the chances of designing and implementing solutions with genuine impact, ensuring equity, social inclusion, sustainability, and community resilience. This paper investigates the utilization of ICTs to support social sustainability by analyzing 157 smart city projects funded under the Horizon 2020 program at the European Union level and 5 smart city projects from Canada. The results reveal the utilization of technological solutions such as testbeds, living labs, EaaS, crowdsensing, open data, and more for co-creation in smart city projects. In the discussion part, we point out the importance of focusing on technologies that are familiar to the beneficiaries and on leveraging resources already available as wearable devices or in the citizens’ homes, the versatility of the technological solutions analyzed, the role of heterogeneous and open data, and cross-disciplinary teams in creating new perspectives on urban problems, reducing inequity in the development of solutions to solve them. The concerns raised and problems reported relate to the technology itself (errors in operation), users (difficulties in stimulating their involvement and keeping it constant), and data (quality of data collected, difficult to process, ethics and security of data collection and use). Based on our results, we extract, synthetize and present six distinct categories of lessons learned by the implementation teams of the analyzed projects.
Gudapalli Karuna, Md Amruth Pasha, Yagateela Sree Ohm
et al.
The Car AC Control Using IoT Sensor. The interior temperature of the car rapidly increases mostly during the hot summer months. This paper aims to address the challenge of maintaining a comfortable interior temperature in car, especially during hot summer months. To overcome this problem a mobile application is developed which helps to monitor the temperature in the car by using the Internet of Things (IoT). With this application the AC can be switched ON before getting into the car as the AC controller is linked to the mobile application. To power the system, a lithium-ion battery is used, which is recharged by the conversion of kinetic energy generated by the vehicle's movement, particularly from the wingtips. The intelligent design of air conditioners will ensures the efficient energy consumption with which the battery life can be prolonged. The proposed method will monitor the temperature inside the car.
Nassmah Y. Al-Matari, Ammar T. Zahary, Asma A. Al-Shargabi
Abstract The emergence of 6G cognitive radio IoT networks introduces both opportunities and complexities in spectrum access and security. Blockchain technology has emerged as a viable solution to address these challenges, offering enhanced security, transparency, and efficiency in spectrum management. This survey paper offers a thorough analysis of recent advancements in blockchain-enabled security mechanisms specifically for spectrum access within 6G cognitive radio IoT networks. Covering literature from 2019 to the present, the paper highlights significant contributions and developments in integrating blockchain technology with cognitive radio and IoT systems. It reviews spectrum access security and shows how blockchain’s decentralized approach can solve related issues. Key areas of focus include secure authentication systems, tamper-resistant spectrum sensing, decentralized databases, and smart contracts for spectrum management. The paper also addresses ongoing challenges like interoperability, scalability, and the need for comprehensive security frameworks. Future research directions are proposed, emphasizing the development of advanced blockchain protocols, integration with machine learning, and addressing regulatory and standardization concerns. This paper provides valuable insights for researchers and practitioners aiming to leverage blockchain technology, alongside ML/AI, to enhance security and efficiency in next-generation cognitive radio IoT networks.
Habibullah Safi, Ali Imran Jehangiri, Zulfiqar Ahmad
et al.
The Internet of Things (IoT) is a growing network of interconnected devices used in transportation, finance, public services, healthcare, smart cities, surveillance, and agriculture. IoT devices are increasingly integrated into mobile assets like trains, cars, and airplanes. Among the IoT components, wearable sensors are expected to reach three billion by 2050, becoming more common in smart environments like buildings, campuses, and healthcare facilities. A notable IoT application is the smart campus for educational purposes. Timely notifications are essential in critical scenarios. IoT devices gather and relay important information in real time to individuals with special needs via mobile applications and connected devices, aiding health-monitoring and decision-making. Ensuring IoT connectivity with end users requires long-range communication, low power consumption, and cost-effectiveness. The LPWAN is a promising technology for meeting these needs, offering a low cost, long range, and minimal power use. Despite their potential, mobile IoT and LPWANs in healthcare, especially for emergency response systems, have not received adequate research attention. Our study evaluated an LPWAN-based emergency response system for visually impaired individuals on the Hazara University campus in Mansehra, Pakistan. Experiments showed that the LPWAN technology is reliable, with 98% reliability, and suitable for implementing emergency response systems in smart campus environments.