Search Results (16)

The increasing risk of air pollution in closed areas like passenger vehicles requires smart and real-time air quality reading solutions. Gases such as carbon monoxide (CO)—which is colorless and odorless and is produced by exhaust systems—air conditioners, and combustion sources are very dangerous to health because they can cause respiratory distress and poisoning at high levels. Traditional in-vehicle CO monitoring systems use a single-point sensor and a fixed threshold, which are insufficient in a dynamic cabin environment subject to factors such as vehicle size, ventilation rate, number of occupants, and incoming traffic. To address these drawbacks, this paper proposes a new E-Nose system with Virtual Sensor-Augmented Embedded Intelligence to estimate the CO concentration in vehicle cabins in real time. The system combines data from cheap gas sensors and improves it using virtual sensor machine learning models trained to predict or enhance sensor responses in real time. Embedded intelligence, deployed locally on edge hardware, supports low-latency processing, dynamic calibration, and noise filtering to respond to fluctuating environmental conditions adaptively. This architecture enables more accurate, robust, and context-aware estimation of CO levels compared to traditional threshold-based methods. Experimental validation across varied vehicular scenarios demonstrates superior precision and responsiveness, providing timely warnings even under complex dispersion patterns. Classifier Gradient Boosting, which builds an ensemble of weak learners sequentially, matched the Random Forest with 99.94% training and 98.59% model accuracy, confirming its strong predictive capability. The system is designed to be cost-effective, scalable, and easily integrable into modern automotive platforms. This study also contributes to the field of smart ecological recording and demonstrates the effectiveness of the virtual sensor-enhanced embedded system as an effective way to improve passenger safety by providing pre-emptive on-board air quality monitoring. Full article

The rapid development of intelligent transportation systems and autonomous driving technologies has made visual perception a key component in ensuring safety and improving efficiency in complex traffic environments. As a core task in visual perception, object detection directly affects the reliability of downstream modules such as path planning and decision control. However, adverse weather conditions (e.g., fog, rain, and snow) significantly degrade image quality—causing texture blurring, reduced contrast, and increased noise—which in turn weakens the robustness of traditional detection models and raises potential traffic safety risks. To address this challenge, this paper proposes an enhanced object detection framework, ECL-YOLOv11 (Edge-enhanced, Context-guided, and Lightweight YOLOv11), designed to improve detection accuracy and real-time performance under adverse weather conditions, thereby providing a reliable solution for in-vehicle perception systems. The ECL-YOLOv11 architecture integrates three key modules: (1) a Convolutional Edge-enhancement (CE) module that fuses edge features extracted by Sobel operators with convolutional features to explicitly retain boundary and contour information, thereby alleviating feature degradation and improving localization accuracy under low-visibility conditions; (2) a Context-guided Multi-scale Fusion Network (AENet) that enhances perception of small and distant objects through multi-scale feature integration and context modeling, improving semantic consistency and detection stability in complex scenes; and (3) a Lightweight Shared Convolutional Detection Head (LDHead) that adopts shared convolutions and GroupNorm normalization to optimize computational efficiency, reduce inference latency, and satisfy the real-time requirements of on-board systems. Experimental results show that ECL-YOLOv11 achieves mAP@50 and mAP@50–95 values of 62.7% and 40.5%, respectively, representing improvements of 1.3% and 0.8% over the baseline YOLOv11, while the Precision reaches 73.1%. The model achieves a balanced trade-off between accuracy and inference speed, operating at 237.8 FPS on standard hardware. Ablation studies confirm the independent effectiveness of each proposed module in feature enhancement, multi-scale fusion, and lightweight detection, while their integration further improves overall performance. Qualitative visualizations demonstrate that ECL-YOLOv11 maintains high-confidence detections across varying motion states and adverse weather conditions, avoiding category confusion and missed detections. These results indicate that the proposed framework provides a reliable and adaptable foundation for all-weather perception in autonomous driving systems, ensuring both operational safety and real-time responsiveness. Full article

As intelligent transportation systems continue to advance, on-board surveillance video has become essential for train safety and intelligent scheduling. However, high-resolution video transmission faces bandwidth limitations, and existing deep learning-based super-resolution models find it difficult to meet real-time requirements due to high computational complexity. To address this, this paper proposes an “edge–end” collaborative multi-terminal task inference framework, which improves inference speed by integrating resources of in-vehicle end devices and edge servers. The framework establishes a real-time-priority mathematical model, uses game theory to solve the problem of minimizing multi-terminal task inference latency, and proposes a multi-terminal task model partitioning strategy and an adaptive adjustment mechanism. It can dynamically partition the model according to device performance and network status, prioritizing real-time performance and minimizing the maximum inference delay. Experimental results show that the dynamic model partitioning mechanism can adaptively determine the optimal partition point, effectively reducing the inference delay of each end device in high-speed mobile and bandwidth-constrained scenarios and providing high-quality video data support for safety monitoring and intelligent analysis. Full article

This article presents the design, implementation, and comparative evaluation of two Unmanned Aerial Vehicles (UAV)-based architectures for automated road data acquisition and processing. The first system uses Arduino Portenta H7 boards to perform real-time inference at the edge, reducing connectivity dependency. The second employs ESP32-CAM modules that transmit raw data for remote server-side processing. We experimentally validated and compared both systems in terms of power consumption, latency, and detection accuracy. Results show that the Portenta-based system consumes 36.2% less energy and achieves lower end-to-end latency (10,114 ms vs. 11,032 ms), making it suitable for connectivity-constrained scenarios. Conversely, the ESP32-CAM system is simpler to deploy and allows rapid model updates at the server. These findings provide a reference for Intelligent Transportation System (ITS) deployments requiring scalable, energy-efficient, and flexible road monitoring solutions. Full article

The increasing traffic on roads poses a significant challenge to the structural integrity of bridges and viaducts. Indirect structural monitoring offers a cost-effective and efficient solution for monitoring multiple infrastructures. The presented work aims to explore new sensing strategies based on digital MEMS sensors integrated into an intelligent IoT infrastructure to predict the bridge deflection behaviour for indirect Bridge Structural Health Monitoring purposes. An experimental setup comprising a bridge model and vehicle equipped with a smart sensing node has been used to generate the dataset. Various models for bridge deflection estimation are deployed on the sensorized vehicle, exploiting edge AI capabilities of smart sensors. This study shows the potential of leveraging data-driven technologies to enhance the performance of low-cost sensors. Additionally, it demonstrates the viability of assessing static deflection shapes of bridges through indirect measurements on board vehicles, underlining the potential of this approach to make SHM more cost-effective and scalable. Full article

Strain clamps are critical components in high-voltage overhead transmission lines, and detection of their defects becomes an important part of regular inspection of transmission lines. A dual UAV (unmanned aerial vehicle) system was proposed to detect strain clamps in multiple split-phase conductors. The main UAV was equipped with a digital radiography (DR) imaging device, a mechanical arm, and an edge intelligence module with visual sensors. The slave UAV was equipped with a digital imaging board and visual sensors. A workflow was proposed for this dual UAV system. Target detection and distance detection of the strain clamps, as well as detection of the defects of strain clamps in DR images, are the main procedures of this workflow. To satisfy the demands of UAV-borne and real-time deployment, the improved YOLOv8-TR algorithm was proposed for the detection of strain clamps (the mAP@50 was 60.9%), and the KD-ResRPA algorithm is used for detecting defects in DR images (the average AUCROC of the three datasets was 82.7%). Field experiments validated the suitability of our dual UAV-based system for charged detection of strain clamps in double split-phase conductors, demonstrating its potential for practical application in live detecting systems. Full article

Artificial intelligence and the Internet of Things (IoT) have brought great convenience to people’s everyday lives. With the emergence of edge computing, IoT devices such as unmanned aerial vehicles (UAVs) can process data instantly at the point of generation, which significantly decreases the requirement for on-board processing power and minimises the data transfer time to enable real-time applications. Meanwhile, with federated learning (FL), UAVs can enhance their intelligent decision-making capabilities by learning from other UAVs without directly accessing their data. This facilitates rapid model iteration and improvement while safeguarding data privacy. However, in many UAV applications such as UAV logistics, different UAVs may perform different tasks and cover different areas, which can result in heterogeneous data and add to the problem of non-independent and identically distributed (Non-IID) data for model training. To address such a problem, we introduce a novel cloud–edge–end collaborative FL framework, which organises and combines local clients through clustering and aggregation. By employing the cosine similarity, we identified and integrated the most appropriate local model into the global model, which can effectively address the issue of Non-IID data in UAV logistics. The experimental results showed that our approach outperformed traditional FL algorithms on two real-world datasets, CIFAR-10 and MNIST. Full article

Advances in deep learning and computer vision have overcome many challenges inherent in the field of autonomous intelligent vehicles. To improve the detection accuracy and efficiency of EdgeBoard intelligent vehicles, we proposed an optimized design of EdgeBoard based on our PP-YOLOE+ model. This model innovatively introduces a composite backbone network, incorporating deep residual networks, feature pyramid networks, and RepResBlock structures to enrich environmental perception capabilities through the advanced analysis of sensor data. The incorporation of an efficient task-aligned head (ET-head) in the PP-YOLOE+ framework marks a pivotal innovation for precise interpretation of sensor information, addressing the interplay between classification and localization tasks with high effectiveness. Subsequent refinement of target regions by detection head units significantly sharpens the system’s ability to navigate and adapt to diverse driving scenarios. Our innovative hardware design, featuring a custom-designed mainboard and drive board, is specifically tailored to enhance the computational speed and data processing capabilities of intelligent vehicles. Furthermore, the optimization of our Pos-PID control algorithm allows the system to dynamically adjust to complex driving scenarios, significantly enhancing vehicle safety and reliability. Besides, our methodology leverages the latest technologies in edge computing and dynamic label assignment, enhancing intelligent vehicles’ operations through seamless sensor integration. Our custom dataset, specifically designed for this study, includes 4777 images captured by intelligent vehicles under a variety of environmental and lighting conditions. The dataset features diverse scenarios and objects pertinent to autonomous driving, such as pedestrian crossings and traffic signs, ensuring a comprehensive evaluation of the model’s performance. We conducted extensive testing of our model on this dataset to thoroughly assess sensor performance. Evaluated against metrics including accuracy, error rate, precision, recall, mean average precision (mAP), and F1-score, our findings reveal that the model achieves a remarkable accuracy rate of 99.113%, an mAP of 54.9%, and a real-time detection frame rate of 192 FPS, all within a compact parameter footprint of just 81 MB. These results demonstrate the superior capability of our PP-YOLOE+ model to integrate sensor data, achieving an optimal balance between detection accuracy and computational speed compared with existing algorithms. Full article

The convergence of vehicular communications, 5th generation mobile network (5G) technology, and edge computing marks a paradigm shift in intelligent transportation. Vehicular communication systems, including Vehicle-to-Vehicle and Vehicle-to-Infrastructure, are integral to Intelligent Transportation Systems. The advent of 5G enhances connectivity, while edge computing brings computational processes closer to data sources. This synergy holds the potential to revolutionize transportation efficiency and safety. This research investigates vehicular communication and edge computing dynamics within a 5G network, considering varying distances between On Board Units and Roadside Units. Energy consumption patterns and CPU load at the RSU are analyzed through meticulous real-world experiments and simulations. Our results show stable energy consumption at shorter distances, with fluctuations increasing at greater ranges. CPU load correlates with communication distance, highlighting the need for adaptive algorithms. While experiments exhibit higher variability, our simulations validate these findings, emphasizing the importance of considering transmission range in vehicular communication network design. Full article

Network slicing is introduced for elastically instantiating logical network infrastructure isolation to support different application types with diversified quality of service (QoS) class indicators. In particular, vehicular communications are a trending area that consists of massive mission-critical applications in the range of safety-critical, intelligent transport systems, and on-board infotainment. Slicing management can be achieved if the network infrastructure has computing sufficiency, a dynamic control policy, elastic resource virtualization, and cross-tier orchestration. To support the functionality of slicing management, incorporating core network infrastructure with deep learning and reinforcement learning has become a hot topic for researchers and practitioners in analyzing vehicular traffic/resource patterns before orchestrating the steering policies. In this paper, we propose QoS-driven management by considering (edge) resource block utilization, scheduling, and slice instantiation in a three-tier resource placement, namely, small base stations/access points, macro base stations, and core networks. The proposed scheme integrates recurrent neural networks to trigger hidden states of resource availability and predict the output of QoS. The intelligent agent and slice controller, namely, RDQ3N, gathers the resource states from three-tier observations and optimizes the action on allocation and scheduling algorithms. Experiments are conducted on both physical and virtual representational vehicle-to-everything (V2X) environments; furthermore, service requests are set to massive thresholds for rendering V2X congestion flow entries. Full article

Artificial intelligence (A.I.) has revolutionised a wide range of human activities, including the accelerated development of autonomous vehicles. Self-navigating delivery robots are recent trends in A.I. applications such as multitarget object detection, image classification, and segmentation to tackle sociotechnical challenges, including the development of autonomous driving vehicles, surveillance systems, intelligent transportation, and smart traffic monitoring systems. In recent years, object detection and its deployment on embedded edge devices have seen a rise in interest compared to other perception tasks. Embedded edge devices have limited computing power, which impedes the deployment of efficient detection algorithms in resource-constrained environments. To improve on-board computational latency, edge devices often sacrifice performance, creating the need for highly efficient A.I. models. This research examines existing loss metrics and their weaknesses, and proposes an improved loss metric that can address the bounding box regression problem. Enhanced metrics were implemented in an ultraefficient YOLOv5 network and tested on the targeted datasets. The latest version of the PyTorch framework was incorporated in model development. The model was further deployed using the ROS 2 framework running on NVIDIA Jetson Xavier NX, an embedded development platform, to conduct the experiment in real time. Full article

Edge Computing enables to perform measurement and cognitive decisions outside a central server by performing data storage, manipulation, and processing on the Internet of Things (IoT) node. Also, Artificial Intelligence (AI) and Machine Learning applications have become a rudimentary procedure in virtually every industrial or preliminary system. Consequently, the Raspberry Pi is adopted, which is a low-cost computing platform that is profitably applied in the field of IoT. As for the software part, among the plethora of Machine Learning (ML) paradigms reported in the literature, we identified Rulex, as a good ML platform, suitable to be implemented on the Raspberry Pi. In this paper, we present the porting of the Rulex ML platform on the board to perform ML forecasts in an IoT setup. Specifically, we explain the porting Rulex’s libraries on Windows 32 Bits, Ubuntu 64 Bits, and Raspbian 32 Bits. Therefore, with the aim of carrying out an in-depth verification of the application possibilities, we propose to perform forecasts on five unrelated datasets from five different applications, having varying sizes in terms of the number of records, skewness, and dimensionality. These include a small Urban Classification dataset, three larger datasets concerning Human Activity detection, a Biomedical dataset related to mental state, and a Vehicle Activity Recognition dataset. The overall accuracies for the forecasts performed are: 84.13%, 99.29% (for SVM), 95.47% (for SVM), and 95.27% (For KNN) respectively. Finally, an image-based gender classification dataset is employed to perform image classification on the Edge. Moreover, a novel image pre-processing Algorithm was developed that converts images into Time-series by relying on statistical contour-based detection techniques. Even though the dataset contains inconsistent and random images, in terms of subjects and settings, Rulex achieves an overall accuracy of 96.47% while competing with the literature which is dominated by forward-facing and mugshot images. Additionally, power consumption for the Raspberry Pi in a Client/Server setup was compared with an HP laptop, where the board takes more time, but consumes less energy for the same ML task. Full article

The world’s oceans are one of the most valuable sources of biodiversity and resources on the planet, although there are areas where the marine ecosystem is threatened by human activities. Marine protected areas (MPAs) are distinctive spaces protected by law due to their unique characteristics, such as being the habitat of endangered marine species. Even with this protection, there are still illegal activities such as poaching or anchoring that threaten the survival of different marine species. In this context, we propose an autonomous surface vehicle (ASV) model system for the surveillance of marine areas by detecting and recognizing vessels through artificial intelligence (AI)-based image recognition services, in search of those carrying out illegal activities. Cloud and edge AI computing technologies were used for computer vision. These technologies have proven to be accurate and reliable in detecting shapes and objects for which they have been trained. Azure edge and cloud vision services offer the best option in terms of accuracy for this task. Due to the lack of 4G and 5G coverage in offshore marine environments, it is necessary to use radio links with a coastal base station to ensure communications, which may result in a high response time due to the high latency involved. The analysis of on-board images may not be sufficiently accurate; therefore, we proposed a smart algorithm for autonomy optimization by selecting the proper AI technology according to the current scenario (SAAO) capable of selecting the best AI source for the current scenario in real time, according to the required recognition accuracy or low latency. The SAAO optimizes the execution, efficiency, risk reduction, and results of each stage of the surveillance mission, taking appropriate decisions by selecting either cloud or edge vision models without human intervention. Full article

Vehicle-to-everything (V2X) communications enable real-time information exchange between vehicles and infrastructure, which extends the perception range of vehicles beyond the limits of on-board sensors and, thus, facilitating the realisation of cooperative, connected, and automated mobility (CCAM) services that will improve road safety and traffic efficiency. In the context of CCAM, the successful deployments of cooperative intelligent transport system (C-ITS) use cases, with the integration of advanced wireless communication technologies, are effectively leading to make transport safer and more efficient. However, the evaluation of multi-vendor and multi-protocol based CCAM service architectures can become challenging and complex. Additionally, conducting on-demand field trials of such architectures with real vehicles involved is prohibitively expensive and time-consuming. In order to overcome these obstacles, in this paper, we present the development of a standards-compliant experimental vehicular on-board unit (OBU) that supports the integration of multiple V2X protocols from different vendors to communicate with heterogeneous cloud-based services that are offered by several original equipment manufacturers (OEMs). We experimentally demonstrate the functionalities of the OBU in a real-world deployment of a cooperative collision avoidance service infrastructure that is based on edge and cloud servers. In addition, we measure end-to-end application-level latencies of multi-protocol supported V2X information flows to show the effectiveness of interoperability in V2X communications between different vehicle OEMs. Full article

Vehicular ad-hoc Networks (VANETs) are an integral part of intelligent transportation systems (ITS) that facilitate communications between vehicles and the internet. More recently, VANET communications research has strayed from the antiquated DSRC standard and favored more modern cellular technologies, such as fifth generation (5G). The ability of cellular networks to serve highly mobile devices combined with the drastically increased capacity of 5G, would enable VANETs to accommodate large numbers of vehicles and support range of applications. The addition of thousands of new connected devices not only stresses the cellular networks, but also the computational and storage requirements supporting the applications and software of these devices. Autonomous vehicles, with numerous on-board sensors, are expected to generate large amounts of data that must be transmitted and processed. Realistically, on-board computing and storage resources of the vehicle cannot be expected to handle all data that will be generated over the vehicles lifetime. Cloud computing will be an essential technology in VANETs and will support the majority of computation and long-term data storage. However, the networking overhead and latency associated with remote cloud resources could prove detrimental to overall network performance. Edge computing seeks to reduce the overhead by placing computational resources nearer to the end users of the network. The geographical diversity and varied hardware configurations of resource in a edge-enabled network would require careful management to ensure efficient resource utilization. In this paper, we introduce an architecture which evaluates available resources in real-time and makes allocations to the most logical and feasible resource. We evaluate our approach mathematically with the use of a multi-criteria decision analysis algorithm and validate our results with experiments using a test-bed of cloud resources. Results demonstrate that an algorithmic ranking of physical resources matches very closely with experimental results and provides a means of delegating tasks to the best available resource. Full article