Search Results (106)

Background/Objectives: In automatic medical image analysis, particularly for diabetic retinopathy, the accuracy of labeled data is crucial, as label noise can significantly complicate the analysis and lead to diagnostic errors. To tackle the issue of label noise in retinal image segmentation, an innovative label correction framework is introduced that combines Confident Learning (CL) with a human-in-the-loop re-annotation process to meticulously detect and rectify pixel-level labeling inaccuracies. Methods: Two CL-oriented strategies are assessed: Confident Joint Analysis (CJA) employing DeeplabV3+ with a ResNet-50 architecture, and Prune by Noise Rate (PBNR) utilizing ResNet-18. These methodologies are implemented on four publicly available retinal image datasets: HRF, STARE, DRIVE, and CHASE_DB1. After the models have been trained on the original labeled datasets, label noise is quantified, and amendments are executed on suspected misclassified pixels prior to the assessment of model performance. Results: The reduction in label noise yielded consistent advancements in accuracy, Intersection over Union (IoU), and weighted IoU across all the datasets. The segmentation of tiny structures, such as the fovea, demonstrated a significant enhancement following refinement. The Mean Boundary F1 Score (MeanBFScore) remained invariant, signifying the maintenance of boundary integrity. CJA and PBNR demonstrated strengths under different conditions, producing variations in performance that were dependent on the noise level and dataset characteristics. CL-based label correction techniques, when amalgamated with human refinement, could significantly enhance the segmentation accuracy and evaluation robustness for Accuracy, IoU, and MeanBFScore, achieving values of 0.9156, 0.8037, and 0.9856, respectively, with regard to the original ground truth, reflecting increases of 4.05%, 9.95%, and 1.28% respectively. Conclusions: This methodology represents a feasible and scalable solution to the challenge of label noise in medical image analysis, holding particular significance for real-world clinical applications. Full article

Interferometric synthetic aperture radar (InSAR) plays a significant role in monitoring permafrost deformation. However, owing to environmental constraints in permafrost regions, some regions exhibit temporal incoherence, which results in deformation with fewer measurement points and difficulties with deformation automatic detection. In this study, a full-coverage deformation rate map of the 10 km buffer of the Qinghai–Tibet Engineering Corridor (QTEC) was generated by combining nine driving factors and the deformation rate of the 5 km buffer along the QTEC based on three machine learning methods. The importance of the factors contributing to ground deformation was explored. The experimental results show that support vector regression (SVR) yielded the best performance (R2 = 0.98, RMSE = 0.76 mm/year, MAE = 0.74 mm/year). The 10 km buffer of deformation data obtained not only preserved the original deformation data well, but it also filled the blank areas in the deformation map. Subsequently, we trained the Faster R-CNN model on the deformation rate map simulated by SVR and used it for the automatic detection of permafrost thaw settlement areas. The results showed that the Faster R-CNN could identify the permafrost thawing slump quickly and accurately. More than 300 deformation areas along the QTEC were detected through our proposed method, with some of these areas located near thaw slump and thermokarst lake regions. This study confirms the significant potential of combining InSAR and deep learning techniques for permafrost degradation monitoring applications. Full article

This study proposes an automatic gear shift classification algorithm in M1 category vehicles using data acquired through the onboard diagnostic system (OBD II) and GPS. The proposed approach is based on the analysis of identification parameters (PIDs), such as manifold absolute pressure (MAP), revolutions per minute (RPM), vehicle speed (VSS), torque, power, stall times, and longitudinal dynamics, to determine the efficiency and behavior of the vehicle in each of its gears. In addition, the unsupervised K-means algorithm was implemented to analyze vehicle gear changes, identify driving patterns, and segment the data into meaningful groups. Machine learning techniques, including K-Nearest Neighbors (KNN), decision trees, logistic regression, and Support Vector Machines (SVMs), were employed to classify gear shifts accurately. After a thorough evaluation, the KNN (Fine KNN) model proved to be the most effective, achieving an accuracy of 99.7%, an error rate of 0.3%, a precision of 99.8%, a recall of 99.7%, and an F1-score of 99.8%, outperforming other models in terms of accuracy, robustness, and balance between metrics. A multiple linear regression model was developed to estimate instantaneous fuel consumption (in L/100 km) using the gear predicted by the KNN algorithm and other relevant variables. The model, built on over 66,000 valid observations, achieved an R² of 0.897 and a root mean square error (RMSE) of 2.06, indicating a strong fit. Results showed that higher gears (3, 4, and 5) are associated with lower fuel consumption. In contrast, a neutral gear presented the highest levels of consumption and variability, especially during prolonged idling periods in heavy traffic conditions. In future work, we propose integrating this algorithm into driver assistance systems (ADAS) and exploring its applicability in autonomous vehicles to enhance real-time decision making. Such integration could optimize gear shift timing based on dynamic factors like road conditions, traffic density, and driver behavior, ultimately contributing to improved fuel efficiency and overall vehicle performance. Full article

Visual target detection under adverse weather conditions presents a fundamental challenge for autonomous driving, particularly in achieving all-weather operational capabilities. Unlike existing reviews that concentrate on individual technical domains such as image restoration or detection robustness, this review introduces an innovative “restoration–detection” collaborative framework. This paper systematically examines state-of-the-art methods for degraded image recovery and improvement of detection model robustness, encompassing from traditional, physically driven approaches as well as contemporary deep learning paradigms. A comprehensive overview and comparative analysis are provided to elucidate these advancements. Regarding the recovery of degraded images, traditional methods demonstrate advantages in interpretability within specific scenarios, such as those based on dark channel prior. In contrast, deep learning methods have achieved significant breakthroughs in modeling complex degradations and enhancing cross-domain generalization through a data-driven paradigm. In the field of enhancing detection robustness, traditional improvement techniques that utilize anisotropic filtering, alongside deep learning methods such as SSD, R-CNN, and the YOLO series, contribute to perceptual stability through feature optimization and end-to-end learning approaches, respectively. This paper summarizes 11 types of mainstream public datasets, examining their multimodal annotation system and addressing issues related to discrepancies. Furthermore, it provides an extensive evaluation of algorithm performance using PSNR, SSIM, mAP, among others. It has been identified that significant bottlenecks persist in dynamic weather coupling modeling, multimodal heterogeneous data fusion, and the efficiency of edge deployment. Future research should focus on establishing a physically guided hybrid learning architecture, developing techniques for dynamic and adaptive timing calibration, and designing a flexible multimodal fusion framework to overcome the limitations associated with complex environment perception. This paper serves as a systematic reference for both the theoretical development and practical implementation of automatic driving vision detection technology under severe weather conditions. Full article

Conventional model-free control (MFC) is widely used in motor drives due to its simplicity and model independence, yet its performance suffers from imperfect disturbance estimation and input gain mismatch. To address these issues, this paper proposes an adaptive enhanced model-free speed control (AEMFSC) scheme based on an ultra-local model for permanent magnet synchronous motor (PMSM) drives. First, by integrating a nonlinear disturbance observer (NDOB) and a PD control law into the generalized model-free controller, an enhanced model-free speed controller (EMFSC) was developed to ensure closed-loop stability. Compared with a conventional MFSC, the proposed method eliminated steady-state errors, reduced the speed overshoot, and achieved faster settling with improved disturbance rejection. Second, to address the performance degradation induced by input gain $\alpha$ mismatch during time-varying load conditions, we developed an online parameter identification method for real-time $\alpha$ estimation. This adaptive mechanism enabled automatic controller parameter adjustment, which significantly enhanced the transient tracking performance of the PMSM drive. Furthermore, an algebraic-framework-based high-precision identification technique is proposed to optimize the initial $\alpha$ selection, which effectively reduces the parameter tuning effort. Simulation and experimental results demonstrated that the proposed AEMFSC significantly enhanced the PMSM’s robustness against load torque variations and parameter uncertainties. Full article

Diagnostic systems for drive with AC motors of key importance for machine safety require the use of limitations related to the processing of measurement information. These limitations result in significant difficulties in assessing the technical condition of the object’s components. The article proposes the use of a combination of artificial intelligence techniques in the form of shallow and convolutional structures in the diagnostics of stator winding damage from an induction motor. The proposed approach ensures a high level of defect detection efficiency while using information preserved in samples from three periods of current signals. The research presents the possibility of combining the data classification capabilities of self-organizing maps (SOMs) with the automatic feature extraction of a convolutional neural network (CNN). The system was verified in steady and transient operating states on a test stand with a 1.5 kW motor. Remarkably, this approach achieves a high detection precision of 97.92% using only 600 samples, demonstrating that this reduced data acquisition does not compromise performance. On the contrary, this efficiency facilitates effective fault detection even in transient operating states, a challenge for traditional methods, and surpasses the 97.22% effectiveness of a reference system utilizing a full 6 s signal. Full article

The fusion of infrared and visible images provides complementary information from both modalities and has been widely used in surveillance, military, and other fields. However, most of the available fusion methods have only been evaluated with subjective metrics of visual quality of the fused images, which are often independent of the following relevant high-level visual tasks. Moreover, as a useful technique especially used in low-light scenarios, the effect of low-light conditions on the fusion result has not been well-addressed yet. To address these challenges, a decoupled and semantic segmentation-driven infrared and visible image fusion network is proposed in this paper, which connects both image fusion and the downstream task to drive the network to be optimized. Firstly, a cross-modality transformer fusion module is designed to learn rich hierarchical feature representations. Secondly, a semantic-driven fusion module is developed to enhance the key features of prominent targets. Thirdly, a weighted fusion strategy is adopted to automatically adjust the fusion weights of different modality features. This effectively merges the thermal characteristics from infrared images and detailed information from visible images. Additionally, we design a refined loss function that employs the decoupling network to constrain the pixel distributions in the fused images and produce more-natural fusion images. To evaluate the robustness and generalization of the proposed method in practical challenge applications, a Maritime Infrared and Visible (MIV) dataset is created and verified for maritime environmental perception, which will be made available soon. The experimental results from both widely used public datasets and the practically collected MIV dataset highlight the notable strengths of the proposed method with the best-ranking quality metrics among its counterparts. Of more importance, the fusion image achieved with the proposed method has over 96% target detection accuracy and a dominant high mAP@[50:95] value that far surpasses all the competitors. Full article

Electromobility contributes to decreasing environmental pollution and fossil fuel dependence, as well as increasing the integration of renewable energy resources. The increasing interest in using electric vehicles (EVs), enhanced by machine learning (ML) algorithms for intelligent automation, has reduced the reliance on. This shift has created an interdependence between power, automatically, and transportation networks, adding complexity to their management and scheduling. Moreover, due to complex charging infrastructures, such as variations in power supply, efficiency, driver behaviors, charging demand, and electricity price, advanced techniques should be applied to predict a wide range of variables in EV performance. As the adoption of EVs continues to accelerate, the integration of ML and especially deep learning (DL) algorithms will play a pivotal role in shaping the future of sustainable transportation. This paper provides a mini review of the ML impacts on mobility electrification. The applications of ML are evaluated in various aspects of e-mobility, including battery management, range prediction, charging infrastructure optimization, autonomous driving, energy management, predictive maintenance, traffic management, vehicle-to-grid (V2G), and fleet management. The main advantages and challenges of models in the years 2013–2024 have been represented for all mentioned applications. Also, all new trends for future work and the strengths and weaknesses of ML models in various aspects of mobility transportation are covered. By discussing and reviewing research papers in this field, it is revealed that leveraging ML models can accelerate the transition to electric mobility, leading to cleaner, safer, and more sustainable transportation systems. This paper states that the dependence on big data for training, the high uncertainty of parameters affecting the performance of electric vehicles, and cybersecurity are the main challenges of ML in the e-mobility sector. Full article

Vehicle detection algorithms are essential for intelligent traffic management and autonomous driving systems. Current vehicle detection algorithms largely rely on deep learning techniques, enabling the automatic extraction of vehicle image features through convolutional neural networks (CNNs). However, in real traffic scenarios, relying only on a single feature extraction unit makes it difficult to fully understand the vehicle information in the traffic scenario, thus affecting the vehicle detection effect. To address this issue, we propose a lightweight vehicle detection algorithm based on Mamba_ViT. First, we introduce a new feature extraction architecture (Mamba_ViT) that separates shallow and deep features and processes them independently to obtain a more complete contextual representation, ensuring comprehensive and accurate feature extraction. Additionally, a multi-scale feature fusion mechanism is employed to enhance the integration of shallow and deep features, leading to the development of a vehicle detection algorithm named Mamba_ViT_YOLO. The experimental results on the UA-DETRAC dataset show that our proposed algorithm improves mAP@50 by 3.2% compared to the latest YOLOv8 algorithm, while using only 60% of the model parameters. Full article

Induction motors are widely used machines in a variety of applications as primary components for generating rotary motion. This is mainly due to their high efficiency, robustness, and ease of control. Despite their high robustness, these machines can experience failures throughout their lifespan due to various mechanical, electrical, and environmental factors. To prevent irreversible failures and all the implications and costs associated with breakdowns, various methodologies have been developed over the years. Many of these methodologies have focused on analyzing various physical quantities, either during start-up transients or during steady-state operations. This involves the use of specific techniques depending on the focus of the methodology (start-up transients or steady-state) to obtain optimal results. In this regard, it is of great importance to develop methods capable of separating and detecting the start-up transient of the motor from the steady state. This will enable the development of automatic diagnostic methodologies focused on the specific operating state of the motor. This paper proposes a methodology for the automatic detection of start-up transients in induction motors by using magnetic stray flux signals and processing by means of statistical indicators in time-sliding windows, the calculation of variances with a proposed method, and obtaining optimal values for the design parameters by using a Particle Swarm Optimization (PSO). The results obtained demonstrate the effectiveness of the proposed method for the start-up and steady-state regimes automatic separation, which is validated on a 0.746 kW induction motor supplied by a variable frequency drive (VFD). Full article

An integrated structural optimization strategy was produced in this study for direct-drive electrical generator structures of offshore wind turbines, implementing a design for an additive manufacturing approach, and using generative design techniques. Direct-drive configurations are widely implemented on offshore wind energy systems due to their high efficiency, reliability, and structural simplicity. However, the greatest challenge associated with these types of machines is the structural optimization of the electrical generator due to the demanding operating conditions. An integrated structural optimization strategy was developed to assess a 100-kW permanent magnet direct-drive generator structure. Generated topologies were evaluated by performing finite element analyses and a metal additive manufacturing process simulation. This novel approach assembles a vast amount of structural information to produce a fit-for-purpose, adaptative, optimization strategy, combining data from static structural analyses, modal analyses, and manufacturing analyses to automatically generate an efficient model through a generative iterative process. The results obtained in this study demonstrate the importance of developing an integrated structural optimization strategy at an early phase of a large-scale project. By considering the typical working condition loads and the machine’s dynamic behavior through the structure’s natural frequencies during the optimization process coupled with a design for an additive manufacturing approach, the operational range of the wind turbine was maximized, the overall costs were reduced, and production times were significantly diminished. Integrating the constraints associated with the additive manufacturing process into the design stage produced high-efficiency results with over 23% in weight reduction when compared with conventional structural optimization techniques. Full article

Single-particle tracking is a powerful technique to investigate the motion of molecules or particles. Here, we review the methods for analyzing the reconstructed trajectories, a fundamental step for deciphering the underlying mechanisms driving the motion. First, we review the traditional analysis based on the mean squared displacement (MSD), highlighting the sometimes-neglected factors potentially affecting the accuracy of the results. We then report methods that exploit the distribution of parameters other than displacements, e.g., angles, velocities, and times and probabilities of reaching a target, discussing how they are more sensitive in characterizing heterogeneities and transient behaviors masked in the MSD analysis. Hidden Markov Models are also used for this purpose, and these allow for the identification of different states, their populations and the switching kinetics. Finally, we discuss a rapidly expanding field—trajectory analysis based on machine learning. Various approaches, from random forest to deep learning, are used to classify trajectory motions, which can be identified by motion models or by model-free sets of trajectory features, either previously defined or automatically identified by the algorithms. We also review free software available for some of the analysis methods. We emphasize that approaches based on a combination of the different methods, including classical statistics and machine learning, may be the way to obtain the most informative and accurate results. Full article

Enabling rapid and accurate comprehensive environmental perception for vehicles poses a major challenge. Object detection and monocular distance estimation are the two main technologies, though they are often used separately. Thus, it is necessary to strengthen and optimize the interaction between them. Vehicle motion or object occlusions can cause sudden variations in the positions or sizes of detection boxes within temporal data, leading to fluctuations in distance estimates. So, we propose a method to integrate a detector based on YOLOv5-RedeCa, a Bot-Sort tracker and an anomaly jumping change filter. This combination allows for more accurate detection and tracking of objects. The anomaly jump filter smooths distance variations caused by sudden changes in detection box sizes. Our method increases accuracy while reducing computational demands, showing outstanding performance on several datasets. Notably, on the KITTI dataset, the standard deviation of the continuous ranging results remains consistently low, especially in scenarios with multiple object occlusions or disappearances. These results validate our method’s effectiveness and precision in managing dual tasks. Full article

Sharing traffic information on the vehicular network can help in the implementation of intelligent traffic management, such as car accident warnings, road construction notices, and driver route changes to reduce traffic congestion earlier. If the exposed traffic incident is incorrect, the driving route will be misleading, and the driving response may be in danger. The blockchain ensures the correctness of data and tampers resistance in the consensus mechanism, which can solve such similar problems. The traffic data are collected through the roadside units, and the passing vehicles will verify the correctness when receiving the event notification. We employ data collection, preprocessing, sentiment analysis, geospatial analysis, and machine learning techniques to automatically identify and categorize traffic events, such as accidents, congestion, or road closures, based on information shared by users on various social media platforms. The framework aims to provide accurate and timely insights into traffic conditions, enabling better urban planning and incident response. Full article

Nowadays, online examination (exam in short) platforms are becoming more popular, demanding strong security measures for digital learning environments. This includes addressing key challenges such as head pose detection and estimation, which are integral for applications like automatic face recognition, advanced surveillance systems, intuitive human–computer interfaces, and enhancing driving safety measures. The proposed work holds significant potential in enhancing the security and reliability of online exam platforms. It achieves this by accurately classifying students’ attentiveness based on distinct head poses, a novel approach that leverages advanced techniques like federated learning and deep learning models. The proposed work aims to classify students’ attentiveness with the help of different head poses. In this work, we considered five head poses: front face, down face, right face, up face, and left face. A federated learning (FL) framework with a pre-trained deep learning model (ResNet50) was used to accomplish the classification task. To classify students’ activity (behavior) in an online exam environment using the FL framework’s local client device, we considered the ResNet50 model. However, identifying the best hyperparameters in the local client ResNet50 model is challenging. Hence, in this study, we proposed two hybrid bio-inspired optimized methods, namely, Particle Swarm Optimization with Genetic Algorithm (PSOGA) and Particle Swarm Optimization with Elitist Genetic Algorithm (PSOEGA), to fine-tune the hyperparameters of the ResNet50 model. The bio-inspired optimized methods employed in the ResNet50 model will train and classify the students’ behavior in an online exam environment. The FL framework trains the client model locally and sends the updated weights to the server model. The proposed hybrid bio-inspired algorithms outperform the GA and PSO when independently used. The proposed PSOGA not only outperforms the proposed PSOEGA but also outperforms the benchmark algorithms considered for performance evaluation by giving an accuracy of 95.97%. Full article