In the last few years, the Internet of Things (IoT) has grown significantly due to technological advancements. However, until recently, there has been no universal set of rules applicable to IoT security. This has opened an area for researchers. The IoT environment enables various smart devices to connect and exchange information; thus, ensuring the authenticity of devices in the IoT network is crucial. We have classified the diverse methods used to authenticate IoT devices to access the data they generate. This study conducted a systematic literature review to identify research gaps, recurring patterns, and potential future directions in IoT authentication, with particular attention to the architectures employed. This review analyzed different authentication techniques and presented their advantages and disadvantages using several criteria for categorization. This survey provides researchers and practitioners with a consolidated understanding of the current state of authentication mechanisms in the IoT. Furthermore, the survey examines emerging authentication paradigms, including blockchain-enabled authentication frameworks, machine-learning-augmented authentication models, and lightweight authentication schemes tailored for resource-constrained IoT devices. The goal of this survey is to aid in creating more robust and secure authentication solutions for the developing IoT by highlighting strengths, limitations, and emerging trends.
In recent years, technological solutions have become increasingly important in agriculture to increase productivity and minimize environmental impacts. This paper presents a quadruped robot system for the detection and classification of pests in agriculture using generative artificial intelligence (AI) and autonomous robotic systems. The system enriches the dataset by generating synthetic data using generative adversarial networks (GANs) based approach and thus achieves high accuracy rates despite the limited amount of real data. Using the deep convolutional GAN (DCGAN) algorithm, 2000 synthetic insect images were generated from 400 real insect images (leaving 100 original images completely isolated as an unseen test set). Using these images, deep learning models such as DenseNet-121 and ResNet-152 were trained. The results show that when trained on the augmented dataset with DCGAN, the ResNet-152 model achieved the highest success with 94% accuracy and an F1 score of 0.93, significantly increasing the 76.4% accuracy obtained using only real images. The Gazebo and RViz simulations confirmed the system’s resilience against physical restrictions, such as gravity (9.81 m/s 2 ), a friction coefficient ( μ = 0.6 ) and fluctuating wind speeds (0–5 m/s). The crawl gait algorithm maintained the robot’s balance by keeping its center of mass within the support polygon, thereby enabling it to move smoothly over rough terrain. Field prototype tests confirmed the functional feasibility of the integrated system for autonomous and precision pest management in sustainable agriculture.
The Internet of Things (IoT)-enabled smart healthcare systems improve quality of life (QoL) but face more threats leading to an increase in abuse of the system. A key security technique is four-step threat modelling during system design, based on the four-layer IoT reference model. The objective of this article is to provide a review of studies published in the period 2014–2025 utilizing Google Scholar, IEEE Xplore and Web of Science. The search was conducted using the following keyword combinations: (threat modelling OR threat analysis) AND (Internet of Things) AND (smart healthcare). The review is based on 19 studies dealing with practical threat modelling or analysis of smart IoT healthcare systems. The reviewed studies reveal that threat modelling is rarely subjected to systematic validation, leaving it largely theoretical rather than practical. This recurring pattern highlights a methodological limitation that reduces the applicability and impact of current research. Moreover, they show that current research seldom addresses higher-level, context-rich layers where privacy, safety and QoL impacts are most significant. This consistent focus on lower layers suggests a systemic limitation, as threats propagate across multiple levels. Lack of automation, reliance on new technologies and no standardized methodology may explain why many studies fail to cover all security layers and threat modelling steps. To tackle IoT-enabled smart healthcare security issues, four solutions are proposed: (i) embedding thorough threat modelling into healthcare policies, (ii) performing comprehensive four-step threat modelling for IoT healthcare systems, (iii) developing a standardized approach and (iv) fostering automated, industry-specific threat modelling frameworks.
By addressing the operational and maintenance constraints of physical ground-based weather stations, this study proposes a deep learning (DL) framework for estimating reference evapotranspiration (ET 0 ) by combining open-access climate services and remote sensing (RS) data. The proposed approach is benchmarked against traditional machine learning (ML) models, while multiple deep neural network (DNN) architectures are also evaluated, including multilayer perceptron (MLP), convolutional neural networks (CNNs), and recurrent neural networks (RNNs). Experiments conducted on three agricultural plots in southeastern Spain, representing contrasting meteorological conditions, demonstrate that RNNs achieve the best performance, with a coefficient of determination of R 2 = 0.92. Furthermore, model interpretability was addressed using SHapley Additive exPlanations analysis, which confirmed the biophysical consistency of the predictions and identified land surface temperature as the primary driver of the model's estimations. A key contribution is the demonstration that infrastructure-free models trained solely on open-access satellite and climate data can match or even surpass conventional meteorology-based methods, providing a scalable solution for ET 0 prediction. Based on a validation performed upon three agricultural plots in southeastern Spain, which represent contrasting semi-arid meteorological conditions, the framework showcases its potential applicability for global scalability by utilizing location-agnostic, open-access data. Moreover, the integration of crop coefficients enables accurate forecasting of daily irrigation demand. Overall, the proposed methodology illustrates the feasibility of artificial intelligence-driven irrigation management across diverse climates and highlights its potential to advance sustainable water use in agriculture.
The concept of Digital Twins (DT) has experienced a remarkable surge in popularity over the past few years. A DT is a computer system designed to monitor, simulate and predict various aspects of a specific physical object. In other words, it is like an enhanced digital counterpart of a real object. Human Digital Twins (HDT) have emerged as an evolution of this concept, where the physical object twinned is a human being. Nevertheless, the inherent complexity of human beings turns the creation of their digital representation into a challenging endeavour. In this study, a systematic literature review was conducted that aimed at clarifying the HDT concept and the different aspects a proper HDT should consider. To shed some light on how the different facets of a HDT are addressed in the literature, we delved into its fields of application, the human dimensions a HDT considers, the information handled, its underlying technological frameworks, what quality assessment processes are being applied to HDT, and lastly, those ethical and legal concerns related to HDT. As a result of this systematic literature review, a HDT research agenda is presented to fill the gaps and shortcomings identified in the literature reviewed and highlight some challenges that should be addressed in the near future.
Maintaining thermal comfort and regulating humidity in footwear is critical, particularly in environments where fluctuations in temperature and moisture impact user experience. Correct estimation of these parameters is crucial in selecting suitable material, thereby improving the efficiency and comfort of the footwear. This study proposes a comparison of the deep learning models (recurrent neural networks, long short-term memory (LSTM), bidirectional LSTM, DeepAR, and hybrid model (Cay, Vassiliadis et al.)) for the forecasting of temperature and humidity inside various types of footwear based on the multi-sensor data. A foot model that mimicked the actual temperature and perspiration process of the human foot was used, and sensor readings were taken from various points of the footwear. Performance of deep learning models was evaluated using four key metrics: mean absolute error, root mean squared error, explained variance score, and mean absolute percentage error. The findings indicate that the hybrid model outperforms the other models and achieves the highest predictive accuracy across all tested footwear conditions. This research contributes to the development of artificial intelligence-based predictive modeling for footwear climate control, offering a robust approach for determining thermophysiological comfort in wearable technologies and smart-manufacturing applications.
This study evaluates the walkability around the bus rapid transit (BRT) system, Metrobus, which will commence operations in Coimbra, Portugal, in 2025. As part of the first phase of an electric mobility system, Metrobus will traverse the city along two primary axes, reshaping urban mobility patterns. Given this shift, assessing the pedestrian environment around BRT stations is crucial to anticipate potential increases in walking trips. This research employs the OS-WALK-EU tool, which operationalises walkability through four sub-indices - amenity proximity, pedestrian-network permeability, accessible green/blue space and residential density - while incorporating a slope-dependent reduction of the effective pedestrian catchment. Using open data sources, the study demonstrates that OS-WALK-EU is an effective method for assessing walkability, with potential applications in other urban contexts. The findings reveal significant asymmetries in walkability along the BRT corridors, highlighting areas where infrastructure improvements are needed to enhance pedestrian accessibility. These insights are particularly relevant for city planners and policymakers, as they underscore the importance of targeted urban interventions to maximise the benefits of the new mobility paradigm. Ensuring high-quality pedestrian access to Metrobus stations will be essential for leveraging sustainable mobility and fostering a more walkable and connected urban environment in Coimbra.
Air pollution poses a major global health challenge, with particulate matter (PM) linked to millions of premature deaths each year. This study forecasts PM concentrations in Istanbul's Kartal district using bi-daily observations collected throughout 2022. Four supervised machine learning (ML) models, including support vector machines, random forests (RFs), artificial neural networks, and K-nearest neighbors, were applied using surface meteorological variables and radiosonde-derived inversion parameters. The RF model achieved the highest predictive accuracy, with R2 values of 0.64 for PM10 and 0.70 for PM2.5, along with the lowest mean squared error. The study incorporates key enhancements, including the integration of vertical inversion metrics with surface pollutant data, the use of autocorrelation analysis to justify lagged features, and statistical evaluation of model differences using paired t-tests. Feature importance analysis showed that inversion thickness and lagged PM levels improved forecasts, highlighting the value of upper-air dynamics and temporal persistence. The aim of this study is to systematically evaluate multiple ML algorithms for PM forecasting at a single urban site. The findings provide transparent, site-specific methodological insights that highlight the role of upper-air dynamics and temporal persistence, offering practical implications for similar urban environments and guiding future multi-site applications.
To ensure productivity in the higher education sector, tracking lecture attendance of instructors and students is vital. Low attendance often leads to negative consequences in terms of optimal output for both individuals and the institution. Traditional methods of locating lecture rooms and tracking attendance are inefficient and error-prone. In this article, we propose Geo-Lecture, a location-based recommender algorithm which leverages a geographical information system (GIS). Using student and location data from a Technical University in Ghana, Geo-Lecture provides accurate, and real-time lecture attendance tracking. Evaluation results demonstrate that Geo-Lecture significantly outperforms contemporary methods with the highest precision of 0.31, recall of 0.34, and an F1-score of 0.32. Additionally, the mean absolute error (MAE) and Normalized MAE both illustrate results of 0.69 and 0.17, respectively, which are the lowest comparatively. These results validate Geo-Lecture's superiority in terms of accuracy, reliability, and usability in comparison to existing approaches.
This paper focuses on the prospects and challenges of emerging agricultural technologies and provides a comprehensive overview of the current state of agricultural technology. This review paper examines the potential benefits and risks of robotics, artificial intelligence (AI), and 5G technology applications in agriculture. It provides a comprehensive overview of the current state of Agricultural Technology trends, including the most promising applications. This paper highlights the use of robots, drones and AI algorithms in precision agriculture, crop monitoring, autonomous agriculture, live-stock monitoring, and farm-to-table logistics. The challenge, however, is a lack of reliable infrastructure, effective data management, and a clear regulatory framework. The study comes to the conclusion that although AgriTech has the potential to increase agricultural sustainability and production, its use will present some difficulties. AgriTech innovations can only be fully realized by inculcating more research and development.
Collaborative robots (cobots) have revolutionized industrial automation by enabling seamless human–robot interaction in shared workspaces. These advanced robots are designed to work alongside humans, enhancing productivity, efficiency, and safety through sophisticated sensing and control capabilities. This review provides a comprehensive analysis of collaborative robotics, while introducing the Internet of Cobots (IoC) as a pivotal enabler of next-generation manufacturing systems. Through IoC capabilities, cobots are transforming industrial environments by implementing advanced safety protocols, enabling dynamic task allocation, and achieving seamless integration with human workers over 5G networks. This paper synthesizes the key technological advancements, starting from fundamental sensing, control, and actuation architectures to sophisticated artificial intelligence and machine learning algorithms that enable human-like adaptability. Special attention is given to the industrial safety norms that enhance workplace safety of the IoC through real-time data sharing of job processing, human proximity, and potential hazards, while building trust in the decision-making of human–robot collaboration. This review highlights emerging trends within the Industry 5.0 paradigm, where IoC-enabled cobots drive the human-centric and personalized manufacturing processes. By providing a comprehensive overview of networked cobots, their transformative impact, and regulatory frameworks, this review offers a valuable insight into the future of intelligent, adaptable, and human-centred industrial automation.
Accurate assessment of electromechanical system status is essential for the safe and efficient management of airport energy stations, where pointer-meter readings serve as key operational indicators. To address pointer-meter detection under complex lighting and cluttered backgrounds, this study proposes YOLO-METER, a vision-based detection model tailored for airport energy stations. The model integrates a Triple Attention Mechanism (TAM) in the backbone to suppress background interference and employs a weighted bidirectional feature pyramid network (BiFPN) in the neck for efficient multi-scale feature fusion. Furthermore, an Improved Sparrow Search Algorithm (ISSA) is used to optimize 12 hyperparameters, substantially improving convergence and detection performance. An inspection-robot platform was built, and on-site images were collected to construct a dedicated pointer-meter detection dataset. Experimental results show that YOLO-METER achieves mAP@0.5 of 97.6%, Precision of 96.46%, and 224.8 FPS, outperforming multiple YOLO variants. These results indicate that YOLO-METER provides an effective and efficient solution for real-time pointer-meter detection, supporting autonomous inspection in airport energy stations.
The present work reports the impacts on urban mobility and air quality in Lisbon, Portugal, of the imposed restrictions to curb the transmission of SARS-CoV-2 virus, which causes COVID-19 disease. We performed a data-driven approach over Lisbon Smart cities data, collected from several sources, such as traffic and pollution. During the first Portuguese emergency period (18-03-2020 to 03-05-2020) the sharp reductions in anthropogenic activities, most importantly road traffic, resulted in generally reduced criteria air pollutant concentration compared to an homologous baseline from 2013-2019 measured in the six air quality monitoring stations throughout the city. The most negatively impacted air pollutants were NO2, with a reduction of 54.35% in traffic stations and 28.62% in background stations. Google mobility indicator for local commerce was found to be the main anthropogenic activity indicator for Lisbon, with a moderate and positive correlation with NO2 concentration (r=+0.54). A regressor ML pipeline was trained to predict NO2 concentration with the available anthropogenic activity, weather, and air pollutant inputs from March/2020 to March/2021, achieving R2 = 0.925 on the test set.
Forests are crucial for preserving biodiversity and regulating the global climate. However, they are increasingly at risk from destructive wildfires that threaten the environment and human communities. Accurate prediction models are essential to minimize the impact of forest fires. This study presents a new hybrid model that combines the Apriori association rule mining algorithm with the binary golden ratio optimization method (BGROM) to improve the accuracy of forest fire prediction. The BGROM, based on the golden ratio observed in plant and animal growth and formulated by the renowned mathematician Fibonacci. It is used to select the candidate features, which are then used by the Apriori algorithm to generate classification rules to predict the risk of wildfires. Integrating the Apriori algorithm with BGROM improves the accuracy of forest fire prediction and enhances our understanding of the complex interactions and patterns that influence wildfire behavior. This innovative approach holds great promise for advancing the development of effective forest fire prevention and management strategies. Experimental results show that the proposed model outperforms existing prediction methods, offering a more reliable tool for early forest fire detection and risk management.
