Search Results (1,445)

The paper considers the neural network application to detect microstructure defects in dissimilar welded joints using the acoustic emission (AE) method. The peculiarity of the proposed approach is that defect detection is carried out taking into account a priori information about the properties of the AE source and the acoustic waveguide parameters of the testing structure. Industrial process pipelines with dissimilar welded joints were studied as the testing object, and diffusion interlayers formed in fusion zones of welded joints were considered microstructure defects. The simulation of AE signals was carried out using a hybrid method: the signal waveform was determined based on a finite element model, while the amplitudes of AE hits were determined based on a physical experiment on mechanical testing of dissimilar welded joints. Measurement data from industrial process pipelines were used as noise realizations. As a result, a data sample was formed that considered the parameters of the AE source and the parameters of the acoustic waveguide with realistic noise parameters and a signal-to-noise ratio. The proposed method allows for a more accurate determination of the waveform, spectrum, and amplitude parameters of the AE signal. Greater certainty in the useful signal parameters allows for achieving a more accurate and reliable classification result. When using a backpropagation neural network, a percentage of correct classification of more than 90% was obtained for a data set in which the signal-to-noise ratio was less than (−5 dB) in 90% of cases. Full article

With escalating global environmental challenges and worsening air quality, there is an urgent need for enhanced environmental monitoring capabilities. Low-cost sensor networks are emerging as a vital solution, enabling widespread and affordable deployment at fine spatial resolutions. In this context, machine learning for the calibration of low-cost sensors is particularly valuable. However, traditional machine learning models often lack interpretability and generalizability when applied to complex, dynamic environmental data. To address this, we propose a causal feature selection approach based on convergent cross mapping within the machine learning pipeline to build more robustly calibrated sensor networks. This approach is applied in the calibration of a low-cost optical particle counter OPC-N3, effectively reproducing the measurements of ${\mathrm{PM}}_1$ and ${\mathrm{PM}}_{2.5}$ as recorded by research-grade spectrometers. We evaluated the predictive performance and generalizability of these causally optimized models, observing improvements in both while reducing the number of input features, thus adhering to the Occam’s razor principle. For the ${\mathrm{PM}}_1$ calibration model, the proposed feature selection reduced the mean squared error on the test set by 43.2% compared to the model with all input features, while the SHAP value-based selection only achieved a reduction of 29.6%. Similarly, for the ${\mathrm{PM}}_{2.5}$ model, the proposed feature selection led to a 33.2% reduction in the mean squared error, outperforming the 30.2% reduction achieved by the SHAP value-based selection. By integrating sensors with advanced machine learning techniques, this approach advances urban air quality monitoring, fostering a deeper scientific understanding of microenvironments. Beyond the current test cases, this feature selection method holds potential for broader applications in other environmental monitoring applications, contributing to the development of interpretable and robust environmental models. Full article

In coal mining operations, methane explosions constitute a severe safety risk, endangering miners’ lives and causing substantial economic losses, which, in turn, weaken the production efficiency and economic benefits of the mining industry and hinder the sustainable development of the industry. To address this challenge, this article explores the application of decoupling network-based methods in methane explosion simulation, aiming to optimize underground mine ventilation system design through scientific means and enhance safety protection for miners. We used the one-dimensional finite difference method (FDM) software Flowmaster to simulate the propagation process of shock waves from a gas explosion source in complex underground tunnel networks, covering a wide range of scenarios from laboratory-scale parallel network samples to full-scale experimental mine settings. During the simulation, we traced the pressure loss in the propagation of the shock wave in detail, taking into account the effects of pipeline friction, shock losses caused by bends and obstacles, T-joint branching connections, and cross-sectional changes. The results of these two case studies were presented, leading to the following insights: (1) geometric variations within airway networks exert a relatively minor influence on overpressure; (2) the positioning of the vent positively contributes to attenuation effects; (3) rarefaction waves propagate over greater distances than compression waves; and (4) oscillatory phenomena were detected in the conduits connecting to the surface. This research introduces a computationally efficient method for predicting methane explosions in complex underground ventilation networks, offering reasonable engineering accuracy. These research results provide valuable references for the safe design of underground mine ventilation systems, which can help to create a safer and more efficient mining environment and effectively protect the lives of miners. Full article

The degradation and failure of the urban water supply network may lead to serious safety hazards, including pipe breaks, water supply interruptions, water resource losses, and contaminant intrusions. The risk evaluation of water supply pipeline failure in a distribution network is a challenging task, because most of the available data cannot fully reflect pipeline failure events and many of the mechanisms still cannot be fully understood. Therefore, a predictive model is urgently needed to assess pipeline failure risk based on available data. In this paper, based on the traditional risk assessment theory, seven main factors affecting pipeline failure are selected and scored, and then a pipeline failure model is established by using the particle swarm optimization (PSO) neural network. The model uses the neural network training of historical data to evaluate the failure of the water supply pipeline, and the PSO is used to optimize the neural network to effectively improve the training time and accuracy. The model error and correlation coefficient are 0.003 and 0.987, respectively. The proposed model can be used as a powerful support tool to assist infrastructure managers and pipeline maintainers in their plans and decision-making. Full article

Long non-coding RNAs (lncRNAs) are crucial in regulating secondary metabolite production in plants, but their role in artemisinin (ART) biosynthesis, a key anti-malarial compound from Artemisia annua, remains unclear. Here, by investigating high-artemisinin-producing (HAP) and lowartemisinin-producing (LAP) genotypes, we found that the final artemisinin content in A. annua is influenced by the quantity of the precursor compounds. We report on RNA deep sequencing in HAP and LAP genotypes. Based on the application of a stringent pipeline, 1419 novel lncRNAs were identified. Moreover, we identified 256 differentially expressed lncRNAs between HAP and LAP. We then established correlations between lncRNAs and artemisinin biosynthesis genes in order to identify a molecular framework for the differential expression of the pathway between the two genotypes. Three potential lncRNAs (MSTRG.33718.2, MSTRG.30396.1 and MSTRG.2697.4) linked to the key artemisinin biosynthetic genes (ADS: Amorpha-4,11-diene synthase, DXS: 1-deoxy-D-xylulose-5-phosphate synthase, and HMGS: 3-hydroxyl-3-methyglutaryl CoA synthase) were detected. Importantly, we observed that up-regulation of these lncRNAs positively modulates the target artemisinin biosynthetic genes, potentially leading to high artemisinin biosynthesis in HAP. In contrast, BAS (beta-amyrin synthase), which is involved in the artemisinin competing pathway, was strongly down-regulated in HAP compared to LAP, in line with the expression pattern of the linked lncRNA MSTRG.30396.1. By identifying and characterizing lncRNAs that are potentially linked to the regulation of key biosynthetic genes, this work provides new insights into the complex regulatory networks governing artemisinin production in A. annua. Such findings could pave the way for innovative approaches in metabolic engineering, potentially enhancing artemisinin yields and addressing challenges in sustainable production. Full article

The aerial transportation system belongs to a symmetrical system and has recently garnered increasing attention from researchers due to its broad application range and convenient operation. The control difficulty of the aerial transportation system lies in the fact that the load is not directly actuated, posing a significant challenge for state-constrained control. Taking the motion of an unmanned aerial vehicle (UAV) suspension transportation system within complex pipelines as an example, this paper employs the the swept volume signed distance field (SVSDF) method to search for state boundaries, which is an aspect not considered or elaborated in many state-constrained control approaches. Furthermore, adaptive state-constrained control based on the radial basis function (RBF) neural network is utilized for the case of experiencing unknown air resistance. The convergence of the proposed method for underactuated and actuated state variables is theoretically demonstrated based on the Lyapunov technique. Compared with existing methods, the error integral index demonstrates that the proposed method displays better convergence capability in the simulation section when considering state constraints under disturbance and air resistance. Full article

Pipeline leakage represents a critical challenge in smart cities and various industries, leading to severe economic, environmental, and safety consequences. Early detection of leaks is essential for overcoming these risks and ensuring the safe operation of pipeline systems. In this study, a hybrid convolutional neural network–long short-term memory (CNN-LSTM) model for pipeline leak detection that uses acoustic emission signals was designed. In this model, acoustic emission signals are initially preprocessed using a Savitzky–Golay filter to reduce noise. The filtered signals are input into the hybrid model, where spatial features are extracted using a CNN. The features are then passed to an LSTM network, which extracts temporal features from the signals. Based on these features, the presence or absence of a leakage is determined. The performance of the proposed model was compared with two alternative approaches: a method that employs combined features from the time domain and LSTM and a bidirectional gated recurrent unit model. The proposed approach demonstrated superior performance, as evidenced by lower validation loss, higher validation accuracy, enhanced confusion matrices, and improved t-distributed stochastic neighbor embedding plots compared to the other models when tested on industrial data. The findings indicate that the proposed model is more effective in accurately detecting pipeline leaks, offering a promising solution for enhancing smart cities and industrial safety. Full article

Congenital heart defects (CHDs) rank among the most common birth defects, presenting diverse phenotypes. Genetic and environmental factors are critical in molding the process of cardiogenesis. However, these factors’ interactions are not fully comprehended. Hence, this study aimed to identify and characterize differentially expressed genes involved in CHD development through bioinformatics pipelines. We analyzed experimental datasets available in genomic databases, using transcriptome, gene enrichment, and systems biology strategies. Network analysis based on genetic and phenotypic ontologies revealed that EP300, CALM3, and EGFR genes facilitate rapid information flow, while NOTCH1, TNNI3, and SMAD4 genes are significant mediators within the network. Differential gene expression (DGE) analysis identified 2513 genes across three study types, (1) Tetralogy of Fallot (ToF); (2) Hypoplastic Left Heart Syndrome (HLHS); and (3) Trisomy 21/CHD, with LYVE1, PLA2G2A, and SDR42E1 genes found in three of the six studies. Interaction networks between genes from ontology searches and the DGE analysis were evaluated, revealing interactions in ToF and HLHS groups, but none in Trisomy 21/CHD. Through enrichment analysis, we identified immune response and energy generation as some of the relevant ontologies. This integrative approach revealed genes not previously associated with CHD, along with their interactions and underlying biological processes. Full article

Background: Although estrogenic compounds promise therapeutic potential in treating various conditions, concerns regarding their endocrine-disrupting effects have been raised. Current methodologies for screening estrogenicity in rodent models are limited to the female-specific uterotrophic bioassay. Studies have reported enlargement of the seminal vesicles in orchiectomized males treated with estrogens. However, identifying estrogenicity strictly through changes in wet weights is uninformative regarding the molecular mechanisms of these agents. Therefore, protein-based biomarkers can complement and improve the sensitivity of weight-based assessments. To this end, we present a discovery-driven proteomic analysis of 17β-estradiol’s effects on the seminal vesicles. Methods: We treated orchidectomized mice with the hormone for five days and used the vehicle-treated group as a control. Seminal vesicles were analyzed by shotgun approach using data-dependent nanoflow liquid chromatography–tandem mass spectrometry and label-free quantification. Proteins found to be differentially expressed between the two groups were processed through a bioinformatics pipeline focusing on pathway analyses and assembly of protein interaction networks. Results: Out of 668 identified proteins that passed rigorous validation criteria, 133 were regulated significantly by 17β-estradiol. Ingenuity Pathway Analysis^® linked them to several hormone-affected pathways, including those associated with immune function such as neutrophil degranulation. The altered protein interaction networks were also related to functions including endocrine disruption, abnormal metabolism, and therapeutic effects. Conclusions: We identified several potential biomarkers for estrogenicity in mouse seminal vesicles, many of them not previously linked with exogenous 17β-estradiol exposure. Full article

Background: As the demand for early and accurate diagnosis of autism spectrum disorder (ASD) increases, the integration of machine learning (ML) and explainable artificial intelligence (XAI) is emerging as a critical advancement that promises to revolutionize intervention strategies by improving both accuracy and transparency. Methods: This paper presents a method that combines XAI techniques with a rigorous data-preprocessing pipeline to improve the accuracy and interpretability of ML-based diagnostic tools. Our preprocessing pipeline included outlier removal, missing data handling, and selecting pertinent features based on clinical expert advice. Using R and the caret package (version 6.0.94), we developed and compared several ML algorithms, validated using 10-fold cross-validation and optimized by grid search hyperparameter tuning. XAI techniques were employed to improve model transparency, offering insights into how features contribute to predictions, thereby enhancing clinician trust. Results: Rigorous data-preprocessing improved the models’ generalizability and real-world applicability across diverse clinical datasets, ensuring a robust performance. Neural networks and extreme gradient boosting models achieved the best performance in terms of accuracy, precision, and recall. XAI techniques demonstrated that behavioral features significantly influenced model predictions, leading to greater interpretability. Conclusions: This study successfully developed highly precise and interpretable ML models for ASD diagnosis, connecting advanced ML methods with practical clinical application and supporting the adoption of AI-driven diagnostic tools by healthcare professionals. This study’s findings contribute to personalized intervention strategies and early diagnostic practices, ultimately improving outcomes and quality of life for individuals with ASD. Full article

Underwater natural gas pipelines constitute critical infrastructure for energy transportation. Any damage or leakage in these pipelines poses serious security risks, directly threatening marine and lake ecosystems, and potentially causing operational issues and economic losses in the energy supply chain. However, current methods for detecting deterioration and regularly inspecting these submerged pipelines remain limited, as they rely heavily on divers, which is both costly and inefficient. Due to these challenges, the use of unmanned underwater vehicles (UUVs) becomes crucial in this field, offering a more effective and reliable solution for pipeline monitoring and maintenance. In this study, we conducted an underwater pipeline tracking and damage detection experiment using a remote-controlled unmanned underwater vehicle (UUV) with autonomous features. The primary objective of this research is to demonstrate that UUV systems provide a more cost-effective, efficient, and practical alternative to traditional, more expensive methods for inspecting submerged natural gas pipelines. The experimental method included vehicle (UUV) setup, pre-test calibration, pipeline tracking mechanism, 3D navigation control, damage detection, data processing, and analysis. During the tracking of the underwater pipeline, damages were identified, and their locations were determined. The navigation information of the underwater vehicle, including orientation in the x, y, and z axes (roll, pitch, yaw) from a gyroscope integrated with a magnetic compass, speed and position information in three axes from an accelerometer, and the distance to the water surface from a pressure sensor, was integrated into the vehicle. Pre-tests determined the necessary pulse width modulation values for the vehicle’s thrusters, enabling autonomous operation by providing these values as input to the thruster motors. In this study, 3D movement was achieved by activating the vehicle’s vertical thruster to maintain a specific depth and applying equal force to the right and left thrusters for forward movement, while differential force was used to induce deviation angles. In pool experiments, the unmanned underwater vehicle autonomously tracked the pipeline as intended, identifying damages on the pipeline using images captured by the vehicle’s camera. The images for damage assessment were processed using a convolutional neural network (CNN) algorithm, a deep learning method. The position of the damage relative to the vehicle was estimated from the pixel dimensions of the identified damage. The location of the damage relative to its starting point was obtained by combining these two positional pieces of information from the vehicle’s navigation system. The damages in the underwater pipeline were successfully detected using the CNN algorithm. The training accuracy and validation accuracy of the CNN algorithm in detecting underwater pipeline damages were 94.4% and 92.87%, respectively. The autonomous underwater vehicle also followed the designated underwater pipeline route with high precision. The experiments showed that the underwater vehicle followed the pipeline path with an error of 0.072 m on the x-axis and 0.037 m on the y-axis. Object recognition and the automation of the unmanned underwater vehicle were implemented in the Python environment. Full article

There has been a strong interest in using neural networks to solve several tasks in PET medical imaging. One of the main problems faced when using neural networks is the quality, quantity, and availability of data to train the algorithms. In order to address this issue, we have developed a pipeline that enables the generation of voxelized synthetic PET phantoms, simulates the acquisition of a PET scan, and reconstructs the image from the simulated data. In order to achieve these results, several pieces of software are used in the different steps of the pipeline. This pipeline solves the problem of generating diverse PET datasets and images of high quality for different types of phantoms and configurations. The data obtained from this pipeline can be used to train convolutional neural networks for PET reconstruction. Full article

This study proposes a low-cost, automatic, wide-area real-time water pipeline monitoring model based on Narrowband Internet of Things (NB-IoT) technology, aiming to solve the challenges faced in the context of global water pipeline management. This model focuses on real-time monitoring of pipeline operations to reduce water waste and improve management efficiency, directly contributing to the achievement of the sustainable development goals (SDGs). Water resource management faces several significant global challenges, including water scarcity, inefficient resource utilization, and infrastructure degradation. Traditional water pipeline monitoring systems are often manual, time-consuming, and unable to detect leaks or failures in real time, leading to significant water loss and financial costs. In response to these issues, NB-IoT technology offers a promising solution with its advantages of low power consumption, long-range communication, and cost-effectiveness. The development of an NB-IoT-based smart water pipeline monitoring system is therefore essential for enhancing the efficiency and sustainability of water resource management. Through enabling real-time monitoring and data collection, this system can address critical issues in global water management, reducing waste and supporting the sustainable development goals (SDGs). This model utilizes Low-Power Wide-Area Network (LPWAN) technology, combined with an LTE mobile network and ARM Cortex-M4 microcontroller, to achieve long-distance multi-sensor data collection and monitoring. The research results show that NB-IoT technology can effectively improve water resource management efficiency, reduce water waste, and is of great significance for the digital transformation of infrastructure and the development of smart cities. This technical solution not only supports “Goal 6: Clean Drinking Water and Sanitation” in the United Nations’ sustainable development goals (SDGs) but also promotes the realization of low-cost teaching aids related to engineering education-related information and communication technologies (ICTs). This study demonstrates the key role of ICTs in promoting sustainable development and provides a concrete practical example for smart water resource management. Full article

Accidental leakage from oil–gas storage tanks can lead to the formation of liquid pools. These pools can result in vapor cloud explosions (VCEs) if combustible vapors encounter ignition energy. Conducting accurate and comprehensive consequence analyses of such explosions is crucial for quantitative risk assessments (QRAs) in industrial safety. In this study, a methodology based on the SLAB-TNO model to calculate the overpressure resulting from a VCE is presented. Based on this method, the consequences of the VCE accident considering the gas cloud concentration diffusion are studied. The probit model is employed to evaluate casualty probabilities under varying environmental and operational conditions. The effects of key parameters, including gas diffusion time, wind speed, lower flammability limit (LFL), and environment temperature, on casualty diffusion are systematically investigated. The results indicate that when the diffusion time is less than 100 s, the VCE consequences are significantly more severe due to the rapid spread of the gas cloud. Furthermore, increasing wind speed accelerates gas dispersion, reducing the spatial extent of casualty isopleths. The LFL is shown to have a direct impact on both the mass and diffusion of the flammable gas cloud, with higher LFL values shifting the explosion’s epicenter upward. The environmental temperature promotes gas diffusion in the core area and increases the mass of the combustible gas cloud. These findings provide critical insights for improving the safety protocols in oil and gas storage facilities and can serve as a valuable reference for consequence assessment and emergency response planning in similar industrial scenarios. Full article

The automatic identification of plant species using unmanned aerial vehicles (UAVs) is a valuable tool for ecological research. However, challenges such as reduced spatial resolution due to high-altitude operations, image degradation from camera optics and sensor limitations, and information loss caused by terrain shadows hinder the accurate classification of plant species from UAV imagery. This study addresses these issues by proposing a novel image preprocessing pipeline and evaluating its impact on model performance. Our approach improves image quality through a multi-step pipeline that includes Enhanced Super-Resolution Generative Adversarial Networks (ESRGAN) for resolution enhancement, Contrast-Limited Adaptive Histogram Equalization (CLAHE) for contrast improvement, and white balance adjustments for accurate color representation. These preprocessing steps ensure high-quality input data, leading to better model performance. For feature extraction and classification, we employ a pre-trained VGG-16 deep convolutional neural network, followed by machine learning classifiers, including Support Vector Machine (SVM), random forest (RF), and Extreme Gradient Boosting (XGBoost). This hybrid approach, combining deep learning for feature extraction with machine learning for classification, not only enhances classification accuracy but also reduces computational resource requirements compared to relying solely on deep learning models. Notably, the VGG-16 + SVM model achieved an outstanding accuracy of 97.88% on a dataset preprocessed with ESRGAN and white balance adjustments, with a precision of 97.9%, a recall of 97.8%, and an F1 score of 0.978. Through a comprehensive comparative study, we demonstrate that the proposed framework, utilizing VGG-16 for feature extraction, SVM for classification, and preprocessed images with ESRGAN and white balance adjustments, achieves superior performance in plant species identification from UAV imagery. Full article