Search Results (21,505)

Maintaining effluent quality in wastewater treatment plants (WWTPs) comes with significant challenges under variable weather conditions, where sudden changes in flow rate and increased pollutant loads can affect treatment performance. Traditional physical sensors became both expensive and susceptible to failure under extreme conditions. In this study, we evaluate the performance of soft sensors based on artificial intelligence (AI) to predict the components underlying the calculation of the effluent quality index (EQI). We thus focus our study on three ML models: Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU) and Transformer. Using the Benchmark Simulation Model no. 2 (BSM2) as the WWTP, we were able to obtain datasets for training the ML models and to evaluate their performance in dry weather scenarios, rainy episodes, and storm events. To improve the classification of networks according to the type of weather, we developed a Random Forest (RF)-based meta-classifier. The results indicate that for dry weather conditions the Transformer network achieved the best performance, while for rain episodes and storm scenarios the GRU was able to capture sudden variations with the highest accuracy. LSTM performed normally in stable conditions but struggled with rapid fluctuations. These results support the decision to integrate AI-based predictive models in WWTPs, highlighting the top performances of both a recurrent network (GRU) and a feed-forward network (Transformer) in obtaining effluent quality predictions under different weather conditions. Full article

Video Synthetic Aperture Radar (ViSAR) operates by continuously monitoring regions of interest to produce sequences of SAR imagery. The detection and tracking of ground-moving targets, through the analysis of their radiation properties and temporal variations relative to the background environment, represents a significant area of focus and innovation within the SAR research community. In this study, some key challenges in ViSAR systems are addressed, including the abundance of low-confidence shadow detections, high error rates in multi-target data association, and the frequent fragmentation of tracking trajectories. A multi-target tracking algorithm for ViSAR that utilizes re-identification (ReID) features and a multi-stage data association process is proposed. The algorithm extracts high-dimensional ReID features using the Dense-Net121 network for enhanced shadow detection and calculates a cost matrix by integrating ReID feature cosine similarity with Intersection over Union similarity. A confidence-based multi-stage data association strategy is implemented to minimize missed detections and trajectory fragmentation. Kalman filtering is then employed to update trajectory states based on shadow detection. Both simulation experiments and actual data processing experiments have demonstrated that, in comparison to two traditional video multi-target tracking algorithms, DeepSORT and ByteTrack, the newly proposed algorithm exhibits superior performance in the realm of ViSAR multi-target tracking, yielding the highest MOTA and HOTA scores of 94.85% and 92.88%, respectively, on the simulated spaceborne ViSAR data, and the highest MOTA and HOTA scores of 82.94% and 69.74%, respectively, on airborne field data. Full article

Public transportation systems face numerous challenges like traffic congestion, inconsistent schedules, and variable passenger demand. These issues lead to delays, overcrowding, and reduced patron satisfaction. Digital twin (DT) technology is a promising innovation for improving public transportation systems by offering real-time virtual representations of physical systems. By integrating real-time data from various sources, digital twins can enable predictive analytics, optimize operations, and improve the overall performance of public transportation networks. This work explores the potential of digital twins to optimize operational efficiency, enhance passenger experiences, and support sustainable urban mobility. A comprehensive review of the existing literature was conducted by analyzing case studies, theoretical models, and practical implementations to assess the effectiveness of DTs in transit systems. While the benefits of DTs are significant, their successful implementation in bus transportation systems is impeded by several challenges like scalability limitations, interoperability issues, and technical complexities involving data integration and IT infrastructure. This paper discusses ways to overcome these challenges, which include using modular designs, microservices, blockchain for security, and standardized communication for better integration. It emphasizes the importance of collaboration in research and practice to effectively apply digital twin technology to public transit systems. Full article

Ship instance segmentation technologies enable the identification of ship targets and their contours, serving as an auxiliary tool for monitoring, tracking, and providing critical support for maritime and port safety management. However, due to the different shapes and sizes of ships, as well as the complexity and fluctuation of lighting and weather, existing ship instance segmentation approaches frequently struggle to accomplish correct contour segmentation. To address this issue, this paper introduces Ship Contour, a real-time segmentation method for ship instances based on contours that detects ship targets using an improved CenterNet algorithm. This method utilizes DLA-60 (deep layer aggregation) as the core network to ensure detection accuracy and speed, and it integrates an efficient channel attention (ECA) mechanism to boost feature extraction capability. Furthermore, a Mish activation function replaces ReLU to better adapt deep network learning. These improvements to CenterNet enhance model robustness and effectively reduce missed and false detection. In response to the issue of low accuracy in extracting ship target edge contours using the original deep snake end-to-end method, a scale- and translation-invariant normalization scheme is employed to enhance contour quality. To validate the effectiveness of the proposed method, this research builds a dedicated dataset with up to 2300 images. Experiments demonstrate that this method achieves competitive performance, with an accuracy rate of AP_0.5:0.95 reaching 63.6% and a recall rate of AR_0.5:0.95 reaching 67.4%. Full article

Small-scale, dispersed agroforestry spaces in the urban fringe constitute ecological land that serves dual public benefit functions: natural ecological conservation and rural-urban services. The purpose of this study is to construct a green infrastructure network by integrating the existing and potential green spaces in an urban fringe. The urban fringe in Zhengzhou was chosen as the study site. First, the urban fringe of Zhengzhou was identified based on multi-source data and artificial intelligence, followed by the extraction of green infrastructure elements through morphological spatial pattern analysis. Then, a public benefit output evaluation system was constructed to assess the land value of green infrastructure in the study area. Finally, based on the evaluation results, a classified network planning was conducted, and a triple-network integrated planning strategy was proposed. The results showed that (1) the administrative area of Zhengzhou is divided into three spatial types: urban core areas, the urban fringe areas, and urban periphery area; this study focuses on the urban fringe surrounding the main urban area of Zhengzhou, area of 678.93 km²; (2) the patch sizes of green infrastructure land in the study area range from approximately 0.01 km² to 2.83 km²; (3) green infrastructure land was classified into levels 1~5 based on ecological conservation and rural-urban services, and comprehensive high-grade land was identified for the construction of the green infrastructure network; and (4) the green infrastructure network in the study area was divided into the forest natural habitat network, the blue-green infrastructure network, and the agroforestry landscape recreation network, and a triple-network integrated green infrastructure network strategy was developed. This study aims to strengthen the effective protection and utilization of micro-habitats in the urban fringe, contributing to the formulation of strategies to reduce the ecological vulnerability of the urban fringe and promote sustainable urban development. Full article

This study examines the factors influencing the behavioral intention and compliance behavior of Transportation Network Vehicle Service (TNVS) drivers during the COVID-19 pandemic. Grounded in the Theory of Planned Behavior (TPB) and the Health Belief Model (HBM), the study integrates psychological, environmental, and organizational factors to explain TNVS drivers’ adherence to safety protocols. Data were collected from 342 TNVS drivers in the National Capital Region (NCR) and CALABARZON through a structured survey. Structural Equation Modeling (SEM) was employed to analyze the relationships among variables and assess the determinants of compliance behavior. The results indicate that attitude toward compliance (β = 0.453, p < 0.001), risk perception (β = 0.289, p = 0.001), availability of personal protective equipment (PPE) (β = 0.341, p < 0.001), passenger compliance (β = 0.293, p = 0.002), company policies (β = 0.336, p = 0.001), and organizational support systems (β = 0.433, p < 0.001) significantly influence behavioral intention. In turn, behavioral intention strongly predicts compliance behavior (β = 0.643, p < 0.001), confirming its mediating role in linking influencing factors to actual adherence. However, stress and fatigue (β = 0.131, p = 0.211), ride conditions (β = 0.198, p = 0.241), and communication and training (β = 0.211, p = 0.058) showed non-significant relationships, suggesting that their direct effects on behavioral intention are limited. The model explains 69.1% of the variance in compliance behavior, demonstrating its robustness. These findings highlight the importance of fostering positive attitudes, ensuring adequate resource availability, and reinforcing organizational support to improve TNVS drivers’ compliance with safety measures. Practical recommendations include implementing educational campaigns, ensuring PPE access, strengthening company policies, and promoting passenger adherence to safety protocols. The study contributes to the broader understanding of health behavior in the ride-hailing sector, offering actionable insights for policymakers, ride-hailing platforms, and public health authorities. Future research should explore additional contextual factors, gender-based differences, and regional variations, as well as assess long-term compliance behaviors beyond the pandemic context. Full article

To enhance the maintenance efficiency and operational stability of rolling bearings, this work establishes a methodology for bearing life prediction, employing digital twin systems to evaluate the remaining useful life of rolling bearings. A comprehensive digital twin-integrated model for the entire lifecycle of rolling bearings is constructed using the Modelica language. This model generates sufficient and reliable lifecycle twin data for the bearings. Due to the symmetrical physical structure of the bearings, the generated twin data also have symmetry. Based on this characteristic of bearings, a remaining useful life (RUL) prediction algorithm is developed using a recurrent neural network (RNN), specifically an improved gated recurrent unit (GRU) model. An optimization algorithm is employed to adjust the hyperparameters and determine the initial fault point of the bearing. A multi-feature dataset is constructed, effectively enhancing the precision and reliability of lifespan estimation. Based on existing measured data of the bearing’s entire lifecycle, the rolling bearing’s digital twin-integrated model parameters are updated. Through the parameter degradation component of the twin, the lifecycle twin data of the rolling bearing are generated. By combining twin data with actual measurement data, this method addresses the limitations of traditional approaches in situations where complete lifecycle data of bearings are scarce, providing reliable technical support for the intelligent maintenance and optimization of rolling bearings. Full article

Hand gesture recognition (HGR) is a convenient and natural form of human–computer interaction. It is suitable for various applications. Much research has already focused on wearable device-based HGR. By contrast, this paper gives an overview focused on device-free HGR. That means we evaluate HGR systems that do not require the user to wear something like a data glove or hold a device. HGR systems are explored regarding technology, hardware, and algorithms. The interconnectedness of timing and power requirements with hardware, pre-processing algorithm, classification, and technology and how they permit more or less granularity, accuracy, and number of gestures is clearly demonstrated. Sensor modalities evaluated are WIFI, vision, radar, mobile networks, and ultrasound. The pre-processing technologies stereo vision, multiple-input multiple-output (MIMO), spectrogram, phased array, range-doppler-map, range-angle-map, doppler-angle-map, and multilateration are explored. Classification approaches with and without ML are studied. Among those with ML, assessed algorithms range from simple tree structures to transformers. All applications are evaluated taking into account their level of integration. This encompasses determining whether the application presented is suitable for edge integration, their real-time capability, whether continuous learning is implemented, which robustness was achieved, whether ML is applied, and the accuracy level. Our survey aims to provide a thorough understanding of the current state of the art in device-free HGR on edge devices and in general. Finally, on the basis of present-day challenges and opportunities in this field, we outline which further research we suggest for HGR improvement. Our goal is to promote the development of efficient and accurate gesture recognition systems. Full article

The aim of this study was to develop a mobile application for Android devices dedicated to the classification of pathological changes in human eye optical coherence tomography (OCT) B-scans. The classification process is conducted using convolutional neural networks (CNNs). Six models were trained during the study: a simple convolutional neural network with three convolutional layers, VGG16, InceptionV3, Xception, Joint Attention Network + MobileNetV2 and OpticNet-71. All of these models were converted to TensorFlow Lite format to implement them into a mobile application. For this purpose, three models with the best parameters were chosen, taking accuracy, precision, recall, F1-score and confusion matrix into consideration. The Android application designed for the classification of OCT images was developed using the Kotlin programming language within the Android Studio integrated development environment. With the application, classification can be performed on an image chosen from the user’s files or an image acquired using the photo-taking function. The results of the classification are displayed for three neural networks, along with the respective classification times for each neural network and the associated image undergoing the classification task. The mobile application has been tested using various smartphones. The testing phase included an evaluation of image classification times and score accuracy, considering factors such as image acquisition method, i.e., camera or gallery. Full article

Flash floods are highly destructive natural disasters, particularly in arid and semi-arid regions like Egypt, where data scarcity poses significant challenges for analysis. This study focuses on the Wadi Al-Barud basin in Egypt’s Central Eastern Desert (CED), where a severe flash flood occurred on 26–27 October 2016. This flash flood event, characterized by moderate rainfall (16.4 mm/day) and a total volume of 8.85 × 10⁶ m³, caused minor infrastructure damage, with 78.4% of the rainfall occurring within 6 h. A significant portion of floodwaters was stored in dam reservoirs, reducing downstream impacts. Multi-source data, including Landsat 8 OLI imagery, ALOS-PALSAR radar data, Global Precipitation Measurements—Integrated Multi-satellite Retrievals for Final Run (GPM-FR) precipitation data, geologic maps, field measurements, and Triangulated Irregular Networks (TINs), were integrated to analyze the flash flood event. The Soil Conservation Service Curve Number (SCS-CN) method integrated with several hydrologic models, including the Hydrologic Modelling System (HEC-HMS), Soil and Water Assessment Tool (SWAT), and European Hydrological System Model (MIKE-SHE), was applied to evaluate flood forecasting, watershed management, and runoff estimation, with results cross-validated using TIN-derived DEMs, field measurements, and Landsat 8 imagery. The SCS-CN method proved effective, with percentage differences of 5.4% and 11.7% for reservoirs 1 and 3, respectively. High-resolution GPM-FR rainfall data and ALOS-derived soil texture mapping were particularly valuable for flash flood analysis in data-scarce regions. The study concluded that the existing protection plan is sufficient for 25- and 50-year return periods but inadequate for 100-year events, especially under climate change. Recommendations include constructing additional reservoirs (0.25 × 10⁶ m³ and 1 × 10⁶ m³) along Wadi Kahlah and Al-Barud Delta, reinforcing the Safaga–Qena highway, and building protective barriers to divert floodwaters. The methodology is applicable to similar flash flood events globally, and advancements in geomatics and datasets will enhance future flood prediction and management. Full article

Mitochondria are the powerhouses of cells, also involved in ROS (reactive oxygen species) generation and cellular death regulation. Thus, several diseases are associated with mitochondrial impairment, including cardiovascular disorders (CVDs). Since CVDs are currently the leading cause of death worldwide, it is very important to evaluate targeting mitochondrial effectors in clinical treatment protocols. Hence, in the present study, antimycin A and rotenone, established inhibitors of the mitochondrial electron transfer chain, were shown to halt apoptotic death induced by curcumin (50 μM) and sorbitol (0.5 M), in H9c2 cardiac cells. In particular, immunoblotting analysis revealed that they totally abolished PARP [poly(ADP-ribose) polymerase] proteolysis, under these conditions. This finding was accompanied by an enhancement of cell viability, recovery of mitochondria networks’ integrity, suppression of cytochrome c release into the cytoplasm, and reversal of chromatin condensation. Chelating extracellular calcium (with EGTA) further enhanced the beneficial impact of antimycin A and rotenone on curcumin- or sorbitol-treated H9c2 cells viability. Of interest, the phosphorylation of eIF2α, indicative of the onset of the pro-survival Integrated Stress Response (IRS), was sustained under these conditions. Overall, our data highlight the anti-apoptotic effect of these compounds, unmasking their potential as mediators in novel therapeutic interventions against mitochondria-associated cardiac dysfunction. Full article

Distinguishing galaxies as either fast or slow rotators plays a vital role in understanding the processes behind galaxy formation and evolution. Standard techniques, which are based on the ${\lambda }_R$ spin parameter obtained from stellar kinematics, frequently face difficulties in classifying fast and slow rotators accurately. These challenges arise particularly in cases where galaxies have complex interaction histories or exhibit significant morphological diversity. In this paper, we evaluate the performance of a Convolutional Neural Network (CNN) in classifying galaxy rotation kinematics based on stellar kinematic maps from the SAMI survey. Our results show that the optimal CNN architecture achieves an accuracy and precision of approximately 91% and 95%, respectively, on the test dataset. Subsequently, we apply our trained model to classify previously unknown rotator galaxies for which traditional statistical tools have been unable to determine whether they exhibit fast or slow rotation, such as certain irregular galaxies or those in dense clusters. We also used Integrated Gradients (IGs) to reveal the crucial kinematic features that influenced the CNN’s classifications. This research highlights the power of CNNs to improve our comprehension of galaxy dynamics and emphasizes their potential to contribute to upcoming large-scale Integral Field Spectrograph (IFS) surveys. Full article

Resistance is a key index of a ship’s hydrodynamic performance, and studying the design of the bulbous bow is an important method to reduce ship resistance. Based on the ship resistance sample data obtained from computational fluid dynamics (CFD) simulation, this study uses a machine learning method to realize the fast prediction of ship resistance corresponding to different bulbous bows. To solve the problem of insufficient accuracy in the single surrogate model, this study proposes a CBR surrogate model that integrates convolutional neural networks with backpropagation and radial basis function models. The coordinates of the control points of the NURBS surface at the bulbous bow are taken as the design variables. Then, a convergence factor is introduced to balance the global and local search abilities of the whale algorithm to improve the convergence speed. The sample space is then iteratively searched using the improved whale algorithm. The results show that the mean absolute error and root mean square error of the CBR model are better than those of the BP and RBF models. The accuracy of the model prediction is significantly improved. The optimized bulbous bow design minimizes the ship resistance, which is reduced by 4.95% compared with the initial ship model. This study provides a reliable and efficient machine learning method for ship resistance prediction. Full article

With the intensification of global climate change, the frequency and intensity of urban flood disasters have been increasing significantly, highlighting the necessity for a scientific assessment of urban flood risks. However, most existing studies focus primarily on the spatial distribution of urban flood data and their socio-economic impacts, with limited attention on the urban flood control engineering system (UFCES) itself and the analysis of urban flood risks from the perspective of the degree of system failure. To address this gap, we proposed a rapid prediction method for key information of the UFCES based on a machine learning model. With the aim of improving the accuracy and timeliness of information prediction, we employed a coupled modeling approach that integrates physical mechanisms with data-driven methods to simulate and predict the information. Taking the Wusha River Basin in Nanchang City as a case study, we generated the training, validation, and testing datasets for machine learning using the urban flood mechanism model. Subsequently, we compared the prediction performance of four machine learning models: random forest (RF), XGBoost (XGB), support vector regression (SVR), and the backpropagation neural network (BP). The results indicate that the XGB model provides more stable and accurate simulation outcomes for key information, with Nash coefficient (R²) values above 0.87 and relative error (RE) values below 0.06. Additionally, the XGB model exhibited significant advantages in terms of simulation speed and model generalization performance. Furthermore, we explored methods for selecting key information indicators and generating samples required for the coupled model. These findings are crucial for the rapid prediction of key information in the UFCES. These achievements improve the technical level of urban flood simulation and provide richer information for urban flood risk management. Full article

Thin-walled structures are widely used in aeronautical and aerospace engineering due to their light weight and high structural performance. Ensuring their integrity is crucial for safety and reliability, which is why structural health monitoring (SHM) methods, such as guided wave-based techniques, have been developed to detect and characterize damage in such components. This study presents a novel damage identification procedure for guided wave-based SHM using deep neural networks (DNNs) trained with experimental data. This technique employs the so-called wave damage interaction coefficients (WDICs) as highly sensitive damage features that describe the unique scattering pattern around possible damage. The DNNs learn intricate relationships between damage characteristics, e.g., size or orientation, and corresponding WDIC patterns from only a limited number of damage cases. An experimental training data set is used, where the WDICs of a selected damage type are extracted from measurements using a scanning laser Doppler vibrometer. Surface-bonded artificial damages are selected herein for demonstration purposes. It is demonstrated that smart DNN interpolations can replicate WDIC patterns even when trained on noisy measurement data, and their generalization capabilities allow for precise predictions for damages with arbitrary properties within the range of trained damage characteristics. These WDIC predictions are readily available, i.e., ad hoc, and can be compared to measurement data from an unknown damage for damage characterization. Furthermore, the fully trained DNN allows for predicting WDICs specifically for the sensing angles requested during inspection. Additionally, an anglewise principal component analysis is proposed to efficiently reduce the feature dimensionality on average by more than $90\%$ while accounting for the angular dependencies of the WDICs. The proposed damage identification methodology is investigated under challenging conditions using experimental data from only three sensors of a damage case not contained in the training data sets. Detailed statistical analyses indicate excellent performance and high recognition accuracy for this experimental data-based approach. This study also analyzes differences between simulated and experimental WDIC patterns. Therefore, an existing DNN trained on simulated data is also employed. The differences between the simulations and experiments affect the identification performance, and the resulting limitations of the simulation-based approach are clearly explained. This highlights the potential of the proposed experimental data-based DNN methodology for practical applications of guided wave-based SHM. Full article