Search Results (30)

High-definition maps (HDMaps) are critical for safe autonomy on structured roads. Yet traditional production—relying on dedicated mapping fleets and manual quality control—is costly and slow, impeding large-scale, frequent updates. Recently, standard-definition maps (SDMaps) derived from remote sensing have been adopted as priors to support HDMap perception, lowering cost but struggling with subtle urban changes and localization drift. We propose Loop-MapNet, a self-evolving, multimodal, closed-loop mapping framework. Loop-MapNet effectively leverages surround-view images, LiDAR point clouds, and SDMaps; it fuses multi-scale vision via a weighted BiFPN, and couples PointPillars BEV and SDMap topology encoders for cross-modal sensing. A Transformer-based bidirectional adaptive cross-attention aligns SDMap with online perception, enabling robust fusion under heterogeneity. We further introduce a confidence-guided masked autoencoder (CG-MAE) that leverages confidence and probabilistic distillation to both capture implicit SDMap priors and enhance the detailed representation of low-confidence HDMap regions. With spatiotemporal consistency checks, Loop-MapNet incrementally updates SDMaps to form a perception–mapping–update loop, compensating remote-sensing latency and enabling online map optimization. On nuScenes, within 120 m, Loop-MapNet attains 61.05% mIoU, surpassing the best baseline by 0.77%. Under extreme localization errors, it maintains 60.46% mIoU, improving robustness by 2.77%; CG-MAE pre-training raises accuracy in low-confidence regions by 1.72%. These results demonstrate advantages in fusion and robustness, moving beyond one-way prior injection and enabling HDMap–SDMap co-evolution for closed-loop autonomy and rapid SDMap refresh from remote sensing. Full article

In the aluminum electrolysis production process, the traditional cell control method based on cell voltage and series current can no longer meet the goals of energy conservation, consumption reduction, and digital-intelligent transformation. Therefore, a new digital cell control technology that is centrally dependent on various process parameters has become an urgent demand in the aluminum electrolysis industry. Among them, the real-time online measurement of alumina concentration is one of the key data points for implementing such technology. However, due to the harsh production environment and limitations of current sensor technologies, hardware-based detection of alumina concentration is difficult to achieve. To address this issue, this study proposes a soft-sensing model for alumina concentration based on a long short-term memory (LSTM) neural network optimized by a weighted average algorithm (WAA). The proposed method outperforms BiLSTM, CNN-LSTM, CNN-BiLSTM, CNN-LSTM-Attention, and CNN-BiLSTM-Attention models in terms of predictive accuracy. In comparison to LSTM models optimized using the Grey Wolf Optimizer (GWO), Harris Hawks Optimization (HHO), Optuna, Tornado Optimization Algorithm (TOC), and Whale Migration Algorithm (WMA), the WAA-enhanced LSTM model consistently achieves significantly better performance. This superiority is evidenced by lower MAE and RMSE values, along with higher R² and accuracy scores. The WAA-LSTM model remains stable throughout the training process and achieves the lowest final loss, further confirming the accuracy and superiority of the proposed approach. Full article

The increasing deployment of wind energy systems, particularly offshore wind farms, necessitates advanced monitoring and maintenance strategies to ensure optimal performance and minimize downtime. Supervisory Control And Data Acquisition (SCADA) systems have become indispensable tools for monitoring the operational health of wind turbines, generating vast quantities of time series data from various sensors. Anomaly detection techniques applied to this data offer the potential to proactively identify deviations from normal behavior, providing early warning signals of potential component failures. Traditional model-based approaches for fault detection often struggle to capture the complexity and non-linear dynamics of wind turbine systems. This has led to a growing interest in data-driven methods, particularly those leveraging machine learning and deep learning, to address anomaly detection in wind energy applications. This study focuses on the development and application of a semi-supervised, multivariate anomaly detection model for horizontal axis wind turbines. The core of this study lies in Bidirectional Long Short-Term Memory (BI-LSTM) networks, specifically a BI-LSTM autoencoder architecture, to analyze time series data from a SCADA system and automatically detect anomalous behavior that could indicate potential component failures. Moreover, the approach is reinforced by the integration of the Isolation Forest algorithm, which operates in an unsupervised manner to further refine normal behavior by identifying and excluding additional anomalous points in the training set, beyond those already labeled by the data provider. The research utilizes a real-world dataset provided by EDP Renewables, encompassing two years of comprehensive SCADA records collected from a single offshore wind turbine operating in the Gulf of Guinea. Furthermore, the dataset contains the logs of failure events and recorded alarms triggered by the SCADA system across a wide range of subsystems. The paper proposes a multi-modal anomaly detection framework orchestrating an unsupervised module (i.e., decision tree method) with a supervised one (i.e., BI-LSTM AE). The results highlight the efficacy of the BI-LSTM autoencoder in accurately identifying anomalies within the SCADA data that exhibit strong temporal correlation with logged warnings and the actual failure events. The model’s performance is rigorously evaluated using standard machine learning metrics, including precision, recall, F1 Score, and accuracy, all of which demonstrate favorable results. Further analysis is conducted using Cumulative Sum (CUSUM) control charts to gain a deeper understanding of the identified anomalies’ behavior, particularly their persistence and timing leading up to the failures. Full article

(1) Background: Self-control is an essential capacity in educating young generations for the good management of personal resources and a healthy life adapted to the constantly changing demands of technological society. Artificial intelligence is an economical and efficient solution for designing medical education programs aimed at optimizing this capacity, which can be personalized according to each personal needs and characteristics. (2) Methodology: This research is a sequential intervention study that aims to investigate if the level of impulsivity decreases and consequently the self-control in adolescents studying drama can be improved by using an online program designed for this purpose. The program’s effectiveness is evaluated by analyzing its impact on vocational performance and the reduction in unhealthy lifestyle habits. A sample of 90 subjects aged between 14 and 17 years, enrolled in the compulsory vocational education system was included in this study. The study was conducted over a five-month period and was organized in three stages: 1. The preparatory stage in which the Barratt Impulsiveness Scale was initially applied (pre-test scores); 2. Selecting the tasks for the online self-control education program and uploading the artificial intelligence network; the application of the program lasted for three months; 3. Applying Barratt Impulsiveness Scale (post-test scores). (3) Results: The results indicated both a statistically significant decrease in self-reported impulsivity and an improvement in the self-control of the sample of adolescents after three months of training on the online platform, compared to the pretest scores of impulsivity. (4) Conclusion: A comparative analysis between the initial and the final BIS scores showed a statistically significant decrease in teens‘ impulsivity, suggesting that the program was effective for this sample of adolescents. Consequently, the study findings indicate significant improvements in adolescents’ self-control after completing the three-month training program, which included cognitive-behavioral games. Full article

This study analyzes factors influencing injury severity in motorcycle accidents involving non-helmeted riders using Bayesian spatiotemporal logistic models. Five models were developed, four of which incorporated different spatiotemporal configurations, including spatial, temporal, and spatiotemporal interaction error terms. The results indicate that the optimal model integrated Leroux CAR spatial priors, temporal random walks, and interaction terms, achieving 86.74% classification accuracy, with a 3% reduction in the DIC value; obtaining the lowest numerical fit demonstrating spatiotemporal interactions is critical for capturing complex risk patterns (e.g., rain amplifying nighttime collision severity). The results highlight rain (OR = 1.53), age ≥ 50 (OR = 1.90), and bi-directional roads (OR = 1.82) as critical risk factors. Based on these findings, several sustainable traffic safety strategies are proposed. Short-term measures include IoT-based dynamic speed control on high-risk roads and app-enforced helmet checks via ride-hailing platforms. Long-term strategies integrate age-specific behavioral training focusing on hazard perception and reaction time improvement, which reduced elderly fatalities by 18% in Japan’s “Silver Rider” program by directly modifying high-risk riding habits (non-helmets). These solutions, validated by global case studies, demonstrate that helmet use could mitigate over 60% of severe head injuries in these high-risk scenarios, promoting sustainable traffic governance through spatiotemporal risk targeting and helmet enforcement. Full article

This study developed and evaluated a novel upper-limb rehabilitation device that integrates piano playing into task-oriented occupational therapy, addressing the limitations of traditional continuous passive motion (CPM) training in patient engagement and functional recovery. The system features a bi-axial sliding platform for precise 61-key positioning and a ten-link, four-loop robotic hand for key striking. A hierarchical control framework incorporates MIDI-based task mapping, finger optimization using an improved Hungarian algorithm, and impedance–admittance hybrid control for adaptive force–position modulation. An 8-week randomized controlled trial demonstrated that the experimental group significantly outperformed the control group, with a 74.7% increase in Fugl–Meyer scores (50.5 ± 2.5), a 14.6-point improvement in the box and block test (BBT), a 20.2-s reduction in nine-hole peg test (NHPT) time, and a 72.6% increase in rehabilitation motivation scale (RMS) scores (55.4 ± 3.8). The results indicate that combining piano playing with robotic rehabilitation enhances neuroplasticity and engagement, significantly improving motor function, daily activity performance, and rehabilitation adherence. This mechanical-control synergy introduces a new paradigm for music-interactive rehabilitation, with potential applications in home-based remote therapy and multimodal treatment integration. Full article

To address the challenges of detecting cotton pests and diseases in natural environments, as well as the similarities in the features exhibited by cotton pests and diseases, a Lightweight Cotton Disease Detection in Natural Environment (LCDDN-YOLO) algorithm is proposed. The LCDDN-YOLO algorithm is based on YOLOv8n, and replaces part of the convolutional layers in the backbone network with Distributed Shift Convolution (DSConv). The BiFPN network is incorporated into the original architecture, adding learnable weights to evaluate the significance of various input features, thereby enhancing detection accuracy. Furthermore, it integrates Partial Convolution (PConv) and Distributed Shift Convolution (DSConv) into the C2f module, called PDS-C2f. Additionally, the CBAM attention mechanism is incorporated into the neck network to improve model performance. A Focal-EIoU loss function is also integrated to optimize the model’s training process. Experimental results show that compared to YOLOv8, the LCDDN-YOLO model reduces the number of parameters by 12.9% and the floating-point operations (FLOPs) by 9.9%, while precision, mAP@50, and recall improve by 4.6%, 6.5%, and 7.8%, respectively, reaching 89.5%, 85.4%, and 80.2%. In summary, the LCDDN-YOLO model offers excellent detection accuracy and speed, making it effective for pest and disease control in cotton fields, particularly in lightweight computing scenarios. Full article

This study aimed to evaluate the vegetative, productive, and fruit quality parameters of the European pear cultivars ‘Rocha’ and ‘Santa Maria’ under the training systems of Tall Spindle, with branches bent at an angle of 45° (Tall Spindle—45°) and 90° (Tall Spindle—90°) to the leader, and Bi-axis. The evaluation was conducted over the 2016/2017 to 2022/2023 growing seasons in the highland region of southern Brazil. Both Tall Spindle systems significantly improved the yield and productive efficiency compared to the Bi-axis system, with ‘Santa Maria’ showing superior performance under Tall Spindle—90°. While ‘Rocha’ exhibited no significant differences between Tall Spindle systems, it benefited from better vigor control and reduced biennial bearing when trained under the Bi-axis system. Fruit quality parameters were consistent across training systems, indicating Tall Spindle—90° as an optimal choice for productivity and stability in ‘Santa Maria’. These results emphasize the adaptability and efficiency of training systems for pear orchard management. Full article

This study addresses the issues of the limited data storage capacity of Argo buoys and satellite communication charges on the basis of data volume by proposing a block lossless data compression method that combines bidirectional long short-term memory networks and multi-head self-attention with a multilayer perceptron (BiLSTM-MHSA-MLP). We constructed an Argo buoy data compression system using the main buoy control board, Jetson nano development board, and the BeiDou-3 satellite transparent transmission module. By processing input sequences bidirectionally, BiLSTM enhances the understanding of the temporal relationships within profile data, whereas the MHSA processes the outputs of the BiLSTM layer in parallel to obtain richer representations. Building on this preliminary probability prediction model, a multilayer perceptron (MLP) and a block length parameter (block_len) are introduced to achieve block compression during training, dynamically updating the model and optimizing symbol probability distributions for more accurate predictions. Experiments conducted on multiple 4000 m single-batch profile datasets from both the PC and Jetson nano platforms demonstrate that this method achieves a lower compression ratio, shorter compression time, and greater specificity. This approach significantly reduces the communication time between Argo buoys and satellites, laying a foundation for the future integration of Jetson Nano into Argo buoys for real-time data compression. Full article

Although the benefits of exercise training have been shown repeatedly in many studies, its relationship with the occurrence of atrial fibrillation (AF) in competitive athletes still remains controversial. In the present review, we sought to demonstrate a comprehensive report of the incidence, pathophysiology, and therapeutic approaches to AF in elite athletes. A 2 to 10 times higher frequency of AF has been shown in many studies in high-intensity endurance athletes compared to individuals who do not exercise. Moreover, a U-shaped relationship between male elite athletes and AF is demonstrated through this finding, while the type and the years of physical activity seem to relate to AF development. A strong correlation seems to exist among the type of exercise (endurance sports), age (>55 years), gender (males), and the time of exercise training, all contributing to an increased risk of AF. The pathophysiology of AF still remains unclear; however, several theories suggest that complex mechanisms are involved, such as bi-atrial dilatation, pulmonary vein stretching, cardiac inflammation, fibrosis, and increased vagal tone. Elite athletes with AF require a comprehensive clinical evaluation and risk factor optimization, similar to the approach taken for nonathletes. Although anticoagulation and rate or rhythm control are cornerstones of AF management, there are still no specific guidelines for elite athletes. Full article

This study addresses the challenges of predicting ship heave motion in real time, which is essential for mitigating sensor–actuator delays in high-performance active compensation control. Traditional methods often fall short due to training on specific sea conditions, and they lack real-time prediction capabilities. To overcome these limitations, this study introduces a multi-step prediction model based on a Seq2Seq framework, training with heave data taken from various sea conditions. The model features a long-term encoder with attention-enhanced Bi-LSTM, a short-term encoder with Gated CNN, and a decoder composed of multiple fully connected layers. The long-term encoder and short-term encoder are designed to maximize the extraction of global characteristics and multi-scale short-term features of heave data, respectively. An optimized Huber loss function is used to improve the fitting performance in peak and valley regions. The experimental results demonstrate that this model outperforms baseline methods across all metrics, providing precise predictions for high-sampling-rate real-time applications. Trained on simulated sea conditions and fine-tuned through transfer learning on actual ship data, the proposed model shows strong generalization with prediction errors smaller than 0.02 m. Based on both results from the regular test and the generalization test, the model’s predictive performance is shown to meet the necessary criteria for active heave compensation control. Full article

Effective air quality prediction models are crucial for the timely prevention and control of air pollution. However, previous models often fail to fully consider air quality’s temporal and spatial distribution characteristics. In this study, Xi’an City is used as the study area. Data from 1 January 2019 to 31 October 2020 are used as the training set, while data from 1 November 2020 to 31 December 2020 are used as the test set. This paper proposes a multi-time and multi-site air quality prediction model for Xi’an, leveraging a deep learning network model based on APSO-CNN-Bi-LSTM. The CNN model extracts the spatial features of the input data, the Bi-LSTM model extracts the time series features, and the PSO algorithm with adaptive inertia weight (APSO) optimizes the model’s hyperparameters. The results show that the model achieves the best results in terms of MAE and RMSE. Compared to the PSO-SVR, BPTT, CNN-LSTM, and GA-ACO-BP models, the MAE improved by 9.375%, 6.667%, 2.276%, and 4.975%, while the RMSE improved by 8.371%, 8.217%, 6.327%, and 5.293%. These significant improvements highlight the model’s accuracy and its promising application prospects. Full article

The ever-increasing diversity of Internet applications and the rapid evolution of network infrastructure due to emerging technologies have made network management more challenging. Effective traffic classification is critical for efficiently managing network resources and aligning with service quality and security demands. The centralized controller of software-defined networking provides a comprehensive network view, simplifying traffic analysis and offering direct programmability features. When combined with deep learning techniques, these characteristics enable the incorporation of intelligence into networks, leading to optimization and improved network management and maintenance. Therefore, this research aims to develop a model for traffic classification by application types and network attacks using deep learning techniques to enhance the quality of service and security in software-defined networking. The SEMMA method is employed to deploy the model, and the classifiers are trained with four algorithms, namely LSTM, BiLSTM, GRU, and BiGRU, using selected features from two public datasets. These results underscore the remarkable effectiveness of the GRU model in traffic classification. Hence, the outcomes achieved in this research surpass state-of-the-art methods and showcase the effectiveness of a deep learning model within a traffic classification in an SDN environment. Full article

A fault diagnosis method based on deep learning integration is proposed focusing on fault text data to effectively improve the efficiency of fault repair and the accuracy of fault localization in the braking control system of an electric multiple unit (EMU). First, the Borderline-SMOTE algorithm is employed to synthesize minority class samples at the boundary, addressing the data imbalance and optimizing the distribution of data within the fault text. Then, a multi-dimensional word representation is generated using the multi-layer bidirectional transformer architecture from the pre-training model, BERT. Next, BiLSTM captures bidirectional context semantics and, in combination with the attention mechanism, highlights key fault information. Finally, the LightGBM classifier is employed to reduce model complexity, enhance analysis efficiency, and increase the practicality of the method in engineering applications. An experimental analysis of fault data from the braking control system of the EMU indicates that the deep learning integration method can further improve diagnostic performance. Full article

Growth in renewable energy systems, direct current (DC) microgrids, and the adoption of electric vehicles (EVs) will substantially increase the demand for bi-directional converters. Precise control mechanisms are essential to ensure optimal performance and better efficiency of these converters. This paper proposes a deep neural network (DNN)-based controller designed to precisely control bi-directional converters for vehicle-to-vehicle (V2V) and vehicle-to-grid (V2G) applications. This control technique allows the converter to quickly attain new reference values, enhancing performance and efficiency by significantly reducing the overshoot duration. To train the DNN controller, large synthetic data are used by performing simulations for various sets of conditions, and the results are validated with a hardware setup. The real-time performance of the DNN controller is compared with a conventional proportional–integral (PI)-based controller through simulated results using MATLAB Simulink (version 2023a) and with a real-time setup. The converter attains a new reference of about 975 $\mathrm{\mu }$s with the proposed control technique. In contrast, the PI controller takes about 220 ms, which shows that the proposed control technique is far better than the PI controller. Full article