Search Results (327)

Real-time traffic light detection is essential for the safe navigation of autonomous vehicles, where timely and accurate recognition of signal states is critical. YOLOv8, a state-of-the-art object detection model, offers enhanced speed and precision, making it well-suited for real-time applications in complex driving environments. This study presents a modified YOLOv8 architecture optimized for traffic light detection by integrating Depth-Wise Separable Convolutions (DWSCs) throughout the backbone and head. The model was first pretrained on a public traffic light dataset to establish a strong baseline and then fine-tuned on a custom real-time dataset consisting of 480 images collected from video recordings under diverse road conditions. Experimental results demonstrate high detection performance, with precision scores of 0.992 for red, 0.995 for yellow, and 0.853 for green lights. The model achieved an average mAP@0.5 of 0.947, with stable F1 scores and low validation losses over 80 epochs, confirming effective learning and generalization. Compared to existing YOLO variants, the modified architecture showed superior performance, especially for red and yellow lights. Full article

The growth of urban and industrial areas is accompanied by an increase in vehicle traffic, resulting in rising concentrations of various air pollutants. This is a global issue that causes environmental damage and risks to human health. The dataset presented in this research contains records with measurements of the air pollutants ozone (O₃) and carbon monoxide (CO), as well as meteorological parameters such as temperature (T), relative humidity (RH), and barometric pressure (BP). This dataset was collected using a set of low-cost sensors over a four-month study period (March to June) in 2024. The monitoring of air pollutants and meteorological parameters was conducted in a city with high industrial activity, heavy traffic, and close proximity to a petrochemical refinery plant. The data were subjected to a series of statistical analyses for visualization using plots that allow for the identification of their behavior. Finally, the dataset can be utilized for air quality studies, public health research, and the development of prediction models based on mathematical approaches or artificial intelligence algorithms. Full article

Rural regions face significant barriers to adopting IoT technologies, due to limited connectivity, energy constraints, and poor technical infrastructure. While urban environments benefit from advanced digital systems and cloud services, rural areas often lack the necessary conditions to deploy and evaluate secure and autonomous IoT solutions. To help overcome this gap, this paper presents the Smart Rural IoT Lab, a modular and reproducible testbed designed to replicate the deployment conditions in rural areas using open-source tools and affordable hardware. The laboratory integrates long-range and short-range communication technologies in six experimental scenarios, implementing protocols such as MQTT, HTTP, UDP, and CoAP. These scenarios simulate realistic rural use cases, including environmental monitoring, livestock tracking, infrastructure access control, and heritage site protection. Local data processing is achieved through containerized services like Node-RED, InfluxDB, MongoDB, and Grafana, ensuring complete autonomy, without dependence on cloud services. A key contribution of the laboratory is the generation of structured datasets from real network traffic captured with Tcpdump and preprocessed using Zeek. Unlike simulated datasets, the collected data reflect communication patterns generated from real devices. Although the current dataset only includes benign traffic, the platform is prepared for future incorporation of adversarial scenarios (spoofing, DoS) to support AI-based cybersecurity research. While experiments were conducted in an indoor controlled environment, the testbed architecture is portable and suitable for future outdoor deployment. The Smart Rural IoT Lab addresses a critical gap in current research infrastructure, providing a realistic and flexible foundation for developing secure, cloud-independent IoT solutions, contributing to the digital transformation of rural regions. Full article

The development of big data analytics in healthcare has created a demand for privacy-conscious and scalable machine learning algorithms that can allow the use of patient information across different healthcare organizations. In this study, the difficulties that come with traditional federated learning frameworks in healthcare sectors, such as scalability, computational effectiveness, and preserving patient privacy for numerous healthcare systems, are discussed. In this work, a new conceptual model known as Hierarchical Federated Learning (HFL) for large, integrated healthcare organizations that include several institutions is proposed. The first level of aggregation forms regional centers where local updates are first collected and then sent to the second level of aggregation to form the global update, thus reducing the message-passing traffic and improving the scalability of the HFL architecture. Furthermore, the HFL framework leveraged more robust privacy characteristics such as Local Differential Privacy (LDP), Gaussian Differential Privacy (GDP), Secure Multi-Party Computation (SMPC) and Homomorphic Encryption (HE). In addition, a Novel Aggregated Gradient Perturbation Mechanism is presented to alleviate noise in model updates and maintain privacy and utility. The performance of the proposed HFL framework is evaluated on real-life healthcare datasets and an artificial dataset created using Generative Adversarial Networks (GANs), showing that the proposed HFL framework is better than other methods. Our approach provided an accuracy of around 97% and 30% less privacy leakage compared to the existing models of FLBM-IoT and PPFLB. The proposed HFL approach can help to find the optimal balance between privacy and model performance, which is crucial for healthcare applications and scalable and secure solutions. Full article

Network Intrusion Detection Systems (NIDS) driven by Machine Learning (ML) algorithms are usually trained using publicly available datasets consisting of labeled traffic samples, where labels refer to traffic classes, usually one benign and multiple harmful. This paper studies the generalizability of models trained on such datasets. This issue is crucial given the application of such a model to actual internet traffic because high-performance measures obtained on datasets do not necessarily imply similar efficiency on the real traffic. We propose a procedure consisting of cross-validation using various sets sharing some standard traffic classes combined with the t-SNE visualization. We apply it to investigate four well-known and widely used datasets: UNSW-NB15, CIC-CSE-IDS2018, BoT-IoT, and ToN-IoT. Our investigation reveals that the high accuracy of a model obtained on one set used for training is reproducible on others only to a limited extent. Moreover, benign traffic classes’ generalizability differs from harmful traffic. Given its application in the actual network environment, it implies that one needs to select the data used to train the ML model carefully to determine to what extent the classes present in the dataset used for training are similar to those in the real target traffic environment. On the other hand, merging datasets may result in more exhaustive data collection, consisting of a more diverse spectrum of training samples. Full article

Low-altitude drones, which are unimpeded by traffic congestion or urban terrain, have become a critical asset in emergency rescue missions. To address the current lack of emergency rescue data, UAV aerial videos were collected to create an experimental dataset for action classification and localization annotation. A total of 5082 keyframes were labeled with 1–5 targets each, and 14,412 instances of data were prepared (including flight altitude and camera angles) for action classification and position annotation. To mitigate the challenges posed by high-resolution drone footage with excessive redundant information, we propose the SlowFast-Traffic (SF-T) framework, a spatio-temporal sequence-based algorithm for recognizing traffic accident rescue actions. For more efficient extraction of target–background correlation features, we introduce the Actor-Centric Relation Network (ACRN) module, which employs temporal max pooling to enhance the time-dimensional features of static backgrounds, significantly reducing redundancy-induced interference. Additionally, smaller ROI feature map outputs are adopted to boost computational speed. To tackle class imbalance in incident samples, we integrate a Class-Balanced Focal Loss (CB-Focal Loss) function, effectively resolving rare-action recognition in specific rescue scenarios. We replace the original Faster R-CNN with YOLOX-s to improve the target detection rate. On our proposed dataset, the SF-T model achieves a mean average precision (mAP) of 83.9%, which is 8.5% higher than that of the standard SlowFast architecture while maintaining a processing speed of 34.9 tasks/s. Both accuracy-related metrics and computational efficiency are substantially improved. The proposed method demonstrates strong robustness and real-time analysis capabilities for modern traffic rescue action recognition. Full article

Efficient detection of road surface defects is vital for timely maintenance and traffic safety. This study introduces a novel AI-powered web framework, TriRoad AI, that integrates multiple versions of the You Only Look Once (YOLO) object detection algorithms—specifically YOLOv8 and YOLOv11—for automated detection of potholes and cracks. A user-friendly browser interface was developed to enable real-time image analysis, confidence-based prediction filtering, and severity-based geolocation mapping using OpenStreetMap. Experimental evaluation was conducted using two datasets: one from online sources and another from field-collected images in Ankara, Turkey. YOLOv8 achieved a mean accuracy of 88.43% on internet-sourced images, while YOLOv11-B demonstrated higher robustness in challenging field environments with a detection accuracy of 46.15%, and YOLOv8 followed closely with 44.92% on mixed field images. The Gemini AI model, although highly effective in controlled environments (97.64% detection accuracy), exhibited a significant performance drop of up to 80% in complex field scenarios, with its accuracy falling to 18.50%. The proposed platform’s uniqueness lies in its fully integrated, browser-based design, requiring no device-specific installation, and its incorporation of severity classification with interactive geospatial visualization. These contributions address current gaps in generalization, accessibility, and practical deployment, offering a scalable solution for smart infrastructure monitoring and preventive maintenance planning in urban environments. Full article

The covert nature of DNS covert channels makes them a widely utilized method for data exfiltration by malicious attackers. In response to this challenge, the present study proposes a detection methodology for DNS covert channels that employs a Deep Boltzmann Machine with Enhanced Security (DBM-ENSec). This approach entails the creation of a dataset through the collection of malicious traffic associated with various DNS covert channel attacks. Time-dependent grouping features are excluded, and feature optimization is conducted on individual traffic data through feature selection and normalization to minimize redundancy, enhancing the differentiation and stability of the features. The result of this process is the extraction of 23-dimensional features for each DNS packet. The extracted features are converted to gray scale images to improve the interpretability of the model and then fed into an improved Deep Boltzmann Machine for further optimization. The optimized features are then processed by an ensemble of classifiers (including Random Forest, XGBoost, LightGBM, and CatBoost) for detection purposes. Experimental results show that the proposed method achieves 99.92% accuracy in detecting DNS covert channels, with a validation accuracy of up to 98.52% on publicly available datasets. Full article

Intrusion detection systems are crucial for cybersecurity applications. Network traffic data originate from diverse terminal sources, exhibiting multi-view feature spaces, while the collection of unknown intrusion data is costly. Current one-class classification (OCC) approaches are mainly designed for single-view data. Multi-view OCC approaches usually require collecting multi-view traffic data from all sources and have difficulty detecting intrusion independently in each view. Furthermore, they commonly ignore the potential subcategories in normal traffic data. To address these limitations, this paper utilizes the Broad Learning System (BLS) technique and proposes an intrusion detection framework based on a multi-view cluster structure guided one-class BLS-autoencoder (IDF-MOCBLSAE). Specifically, a multi-view co-association matrix optimization objective function with doubly-stochastic constraints is first designed to capture the cross-view cluster structure. Then, a multi-view cluster structure guided one-class BLS-autoencoder (MOCBLSAEs) is proposed, which learns the discriminative patterns of normal traffic data by preserving the cross-view clustering structure while minimizing the intra-view sample reconstruction errors, thereby enabling the identification of unknown intrusion data. Finally, an intrusion detection framework is constructed based on multiple MOCBLSAEs to achieve both individual and ensemble intrusion detection. Through experimentation, IDF-MOCBLSAE is validated on real-world network traffic datasets for multi-view one-class classification tasks, demonstrating its superiority over state-of-the-art one-class approaches. Full article

Face-to-face interaction is one of the most natural forms of human communication. Unsurprisingly, Video Conferencing (VC) Applications have experienced a significant rise in demand over the past decade. With the widespread availability of cellular devices equipped with high-resolution cameras, Instant Messaging Video Call Applications (IMVCAs) now constitute a substantial portion of VC communications. Given the multitude of IMVCA options, maintaining a high Quality of Experience (QoE) is critical. While content providers can measure QoE directly through end-to-end connections, Internet Service Providers (ISPs) must infer QoE indirectly from network traffic—a non-trivial task, especially when most traffic is encrypted. In this paper, we analyze a large dataset collected from WhatsApp IMVCA, comprising over 25,000 s of VC sessions. We apply four Machine Learning (ML) algorithms and a Large Multimodal Model (LMM)-based agent, achieving mean errors of 4.61%, 5.36%, and 13.24% for three popular QoE metrics: BRISQUE, PIQE, and FPS, respectively. Full article

Biomass burning processes affect many semi-rural areas in the Mediterranean, but there is a lack of long-term datasets focusing on their classification, obtained by monitoring carbonaceous particle concentrations and optical properties variations. To address this issue, a campaign to measure equivalent black carbon (eBC) and particle number size distributions (0.3–10 μm) was carried out from August 2019 to November 2020 at a coastal semi-rural site in the Basilicata region of Southern Italy. Long-term datasets were useful for aerosol characterization, helping to clearly identify traffic as a constant eBC source. For a shorter period, PM_2.5 mass concentrations were also measured, allowing the estimation of elemental and organic carbon (EC and OC), and chemical and SEM (scanning electron microscope) analysis of aerosols collected on filters. This multi-instrumental approach enabled the discrimination among different biomass burning (BB) processes, and the analysis of three case studies related to domestic heating, regional smoke plume transport, and a local smoldering process. The AAE (Ångström absorption exponent) daily pattern was characterized as having a peak late in the morning and mean hourly values that were always higher than 1.3. Full article

Urban traffic congestion poses persistent challenges to mobility, public safety, and governance efficiency in metropolitan areas. This study proposes an intelligent traffic flow forecasting framework based on an extended Long Short-Term Memory (xLSTM) model, specifically designed for real-time congestion prediction and proactive police dispatch support. Utilizing a real-world dataset collected from over 300 vehicle detector (VD) sensors, the proposed model integrates vehicle volume, speed, and lane occupancy data at five-minute intervals. Methodologically, the xLSTM model incorporates matrix-based memory cells and exponential gating mechanisms to enhance spatio-temporal learning capabilities. Model performance is evaluated using multiple metrics, including congestion classification accuracy, F1-score, MAE, RMSE, and inference latency. The xLSTM model achieves a congestion prediction accuracy of 87.3%, an F1-score of 0.882, and an average inference latency of 41.2 milliseconds—outperforming baseline LSTM, GRU, and Transformer-based models in both accuracy and speed. These results validate the system’s suitability for real-time deployment in police control centers, where timely prediction of traffic congestion enables anticipatory patrol allocation and dynamic signal adjustment. By bridging AI-driven forecasting with public safety operations, this research contributes a validated and scalable approach to intelligent transportation governance, enhancing the responsiveness of urban mobility systems and advancing smart city initiatives. Full article

Automatic license plate recognition (ALPR) plays an important role in applications such as intelligent traffic systems, vehicle access control in specific areas, and law enforcement. The main novelty brought by the present research consists in the development of an automatic vehicle license plate recognition system adapted to the Romanian context, which integrates the YOLOv12 detection architecture with the PaddleOCR library while also providing functionalities for recognizing the type of vehicle on which the license plate is mounted and identifying the county of registration. The integration of these functionalities allows for an extension of the applicability range of the proposed solution, including for addressing issues related to restricting access for certain types of vehicles in specific areas, as well as monitoring vehicle traffic based on the county of registration. The dataset used in the study was manually collected and labeled using the makesense.ai platform and was made publicly available for future research. It includes 744 images of vehicles registered in Romania, captured in real traffic conditions (the training dataset being expanded by augmentation). The YOLOv12 model was trained to automatically detect license plates in images with vehicles, and then it was evaluated and validated using standard metrics such as precision, recall, F1 score, mAP@0.5, mAP@0.5:0.95, etc., proving very good performance. Experimental results demonstrate that YOLOv12 achieved superior performance compared to YOLOv11 for the analyzed issue. YOLOv12 outperforms YOLOv11 with a 2.3% increase in precision (from 97.4% to 99.6%) and a 1.1% improvement in F1 score (from 96.7% to 97.8%). Full article

With the advancement of intelligent transportation systems, vehicle trajectory data have become a key component in areas like traffic flow prediction, route planning, and traffic management. However, high-quality, publicly available trajectory datasets are scarce due to concerns over privacy, copyright, and data collection costs. The lack of data creates challenges for training machine learning models and optimizing algorithms. To address this, we propose a new method for generating synthetic vehicle trajectory data, leveraging traffic flow characteristics and road maps. The approach begins by estimating hourly traffic volumes, then it uses the Poisson distribution modeling to assign departure times to synthetic trajectories. Origin and destination (OD) distributions are determined by analyzing historical data, allowing for the assignment of OD pairs to each synthetic trajectory. Path planning is then applied using a road map to generate a travel route. Finally, trajectory points, including positions and timestamps, are calculated based on road segment lengths and recommended speeds, with noise added to enhance realism. This method offers flexibility to incorporate additional information based on specific application needs, providing valuable opportunities for machine learning in intelligent transportation systems. Full article

Wireless Sensor Networks (WSNs) consist of distributed sensor nodes that collect and transmit environmental data, often in resource-constrained and unsecured environments. These characteristics make WSNs highly vulnerable to various security threats. To address this, the objective of this research is to design and evaluate a deep learning-based Intrusion Detection System (IDS) that is both accurate and efficient for real-time threat detection in WSNs. This study proposes a hybrid IDS model combining one-dimensional Convolutional Neural Networks (Conv1Ds), Gated Recurrent Units (GRUs), and Self-Attention mechanisms. A Conv1D extracts spatial features from network traffic, GRU captures temporal dependencies, and Self-Attention emphasizes critical sequence components, collectively enhancing detection of subtle and complex intrusion patterns. The model was evaluated using the WSN-DS dataset and demonstrated superior performance compared to traditional machine learning and simpler deep learning models. It achieved an accuracy of 98.6%, precision of 98.63%, recall of 98.6%, F1-score of 98.6%, and an ROC-AUC of 0.9994, indicating strong predictive capability even with imbalanced data. In addition to centralized training, the model was tested under cooperative, node-based learning conditions, where each node independently detects anomalies and contributes to a collective decision-making framework. This distributed approach improves detection efficiency and robustness. The proposed IDS offers a scalable and resilient solution tailored to the unique challenges of WSN security. Full article