Search

Electrochemical sensors are used to measure target analytes in water, meat, fruits, or vegetables, to ensure their safety, security, and integrity for human use. In this paper, a solution‐based fabrication process is presented for a biodegradable electrochemical free chlorine sensor using asparagine that is functionalized onto graphene oxide (GO). An ink solution of the GO functionalized with asparagine is synthesized, and then deposited onto a screen‐printed carbon electrode (SPCE) using a spin coater. The sensor shows high a sensitivity of 0.30 µA ppm−1 over a linear range of 0–8 ppm with a hysteresis‐limited resolution of 0.2 ppm after achieving a steady state at 50 s. From the development and testing of the free chlorine sensor, over 9000 datapoints are collected and used for training an artificial neural network (ANN) model to quantify and characterize the factors affecting the free chlorine sensor's performance, and model its degradation characteristics. The model reports a low mean absolute error (MAE) of 0.1603 and a high model accuracy with a Pearson correlation coefficient (PCC) of 0.9950, demonstrating that these degradation characteristics can be modeled and be used to compensate the degraded performance characteristics of the free chlorine sensors. [ABSTRACT FROM AUTHOR]

Due to the complex interaction of urban and mountainous floods, assessing flood susceptibility in mountainous urban areas presents a challenging task in environmental research and risk analysis. Data-driven machine learning methods can evaluate flood susceptibility in mountainous urban areas lacking essential hydrological data, utilizing remote sensing data and limited historical inundation records. In this study, two ensemble learning algorithms, Random Forest (RF) and XGBoost, were adopted to assess the flood susceptibility of Kunming, a typical mountainous urban area prone to severe flood disasters. A flood inventory was created using flood observations from 2018 to 2022. The spatial database included 10 explanatory factors, encompassing climatic, geomorphic, and anthropogenic factors. Artificial Neural Network (ANN) and Support Vector Machine (SVM) were selected for model comparison. To minimize the influence of expert opinions on model training, this study employed a strategy of uniformly random sampling in historically non-flooded areas for negative sample selection. The results demonstrated that (1) ensemble learning algorithms offer higher accuracy than other machine learning methods, with RF achieving the highest accuracy, evidenced by an area under the curve (AUC) of 0.87, followed by XGBoost at 0.84, surpassing both ANN (0.83) and SVM (0.82); (2) the interpretability of ensemble learning highlighted the differences in the potential distribution of the training data's positive and negative samples. Feature importance in ensemble learning can be utilized to minimize human bias in the collection of flooded-site samples, more targeted flood susceptibility maps of the study area's road network were obtained; and (3) ensemble learning algorithms exhibited greater stability and robustness in datasets with varied negative samples, as evidenced by their performance in F1-Score, Kappa, and AUC metrics. This paper further substantiates the superiority of ensemble learning in flood susceptibility assessment tasks from the perspectives of accuracy, interpretability, and robustness, enhances the understanding of the impact of negative samples on such assessments, and optimizes the specific process for urban flood susceptibility assessment using data-driven methods. [ABSTRACT FROM AUTHOR]

Since the discovery of the quasicrystal, approximately 100 stable quasicrystals are identified. To date, the existence of quasicrystals is verified using transmission electron microscopy; however, this technique requires significantly more elaboration than rapid and automatic powder X‐ray diffraction. Therefore, to facilitate the search for novel quasicrystals, developing a rapid technique for phase‐identification from powder diffraction patterns is desirable. This paper reports the identification of a new Al–Si–Ru quasicrystal using deep learning technologies from multiphase powder patterns, from which it is difficult to discriminate the presence of quasicrystalline phases even for well‐trained human experts. Deep neural networks trained with artificially generated multiphase powder patterns determine the presence of quasicrystals with an accuracy >92% from actual powder patterns. Specifically, 440 powder patterns are screened using the trained classifier, from which the Al–Si–Ru quasicrystal is identified. This study demonstrates an excellent potential of deep learning to identify an unknown phase of a targeted structure from powder patterns even when existing in a multiphase sample. [ABSTRACT FROM AUTHOR]

In the light of the adverse effects of climate change, data analysis and Machine Learning (ML) techniques can provide accurate forecasts, which enable efficient scheduling and operation of energy usage. Especially in the built environment, Energy Load Forecasting (ELF) enables Distribution System Operators or Aggregators to accurately predict the energy demand and generation trade-offs. This paper focuses on developing and comparing predictive algorithms based on historical data from a near Zero Energy Building. This involves energy load, as well as temperature data, which are used to develop and evaluate various base ML algorithms and methodologies, including Artificial Neural Networks and Decision-trees, as well as their combination. Each algorithm is fine-tuned and tested, accounting for the unique data characteristics, such as the presence of photovoltaics, in order to produce a robust approach for One-Step-Ahead ELF. To this end, a novel hybrid model utilizing ensemble methods was developed. It combines multiple base ML algorithms the outputs of which are utilized to train a meta-model voting regressor. This hybrid model acts as a normalizer for any new data input. An experimental comparison of the model against unseen data and other ensemble approaches, showed promising forecasting results (mean absolute percentage error = 5.39%), particularly compared to the base algorithms. [ABSTRACT FROM AUTHOR]

Structures made of heterogeneous materials, such as composites, often require a multiscale approach when their behavior is simulated using the finite element method. By solving the boundary value problem of the macroscale model, for previously homogenized material properties, the resulting stress maps can be obtained. However, such stress results do not describe the actual behavior of the material and are often significantly different from the actual stresses in the heterogeneous microstructure. Finding high-accuracy stress results for such materials leads to time-consuming analyses in both scales. This paper focuses on the application of machine learning to multiscale analysis of structures made of composite materials, to substantially decrease the time of computations of such localization problems. The presented methodology was validated by a numerical example where a structure made of resin epoxy with randomly distributed short glass fibers was analyzed using a computational multiscale approach. Carefully prepared training data allowed artificial neural networks to learn relationships between two scales and significantly increased the efficiency of the multiscale approach. [ABSTRACT FROM AUTHOR]

Pavement engineering has always relied on asphalt concrete as the primary material. As a result, increasing the quality of asphalt concrete for greater performance and longer durability has remained a focus of research. The present paper aims to assess the potential of soft computing-based models, such as Artificial neural networks, Support vector machines, Gaussian process, M5P tree, Random forest, and Random tree-based models, used for the prediction of Marshall Stability of carbon–fiber asphalt mix. Five different statistical indices are used to evaluate the performance of each model with different input variables, such as Bitumen content (BC), Carbon fiber (CF), Bitumen grade (VG), Fiber length (FL), and Fiber diameter (FD), Specific gravity coarse aggregate (SG(CA)), Water absorption coarse aggregate (WA(CA)) and Specific Gravity of bitumen (SG(B)), to get the Marshall Stability (MS) as an output. Five statistical indices were used to assess the effectiveness of the applied models i.e., Coefficient of correlation (CC), Mean absolute error (MAE), Root mean square error (RMSE), Relative absolute error (RAE) and Root relative squared error (RRSE). According to performance evaluation results, it has been found that the ANN-based model has outperformed all the applied models for predicting the Marshall Stability of asphalt concrete using carbon fiber with CC value as 0.9287 and 0.9126, R2 value as 0.8624 and 0.8328, MAE value as 1.7527 and 1.8702, RMSE value as 2.3305 and 2.4438, RAE value as 32.51 and 39.64% and RRSE values as 37.30 and 43.59% for both the training and testing stages respectively. Taylor's diagram suggests that the ANN model outperforms the other applied models. Sensitivity analysis shows that the bitumen content (BC) is the more sensitive parameter in the carbon–fiber asphalt mix. Furthermore, carbon fiber is comparable to the sensitivity of the bitumen content which shows the significance of the carbon fiber in the asphalt mix in predicting the Marshall Stability. [ABSTRACT FROM AUTHOR]

Analysis of phylogenetic trees has become an essential tool in epidemiology. Likelihood-based methods fit models to phylogenies to draw inferences about the phylodynamics and history of viral transmission. However, these methods are often computationally expensive, which limits the complexity and realism of phylodynamic models and makes them ill-suited for informing policy decisions in real-time during rapidly developing outbreaks. Likelihood-free methods using deep learning are pushing the boundaries of inference beyond these constraints. In this paper, we extend, compare, and contrast a recently developed deep learning method for likelihood-free inference from trees. We trained multiple deep neural networks using phylogenies from simulated outbreaks that spread among 5 locations and found they achieve close to the same levels of accuracy as Bayesian inference under the true simulation model. We compared robustness to model misspecification of a trained neural network to that of a Bayesian method. We found that both models had comparable performance, converging on similar biases. We also implemented a method of uncertainty quantification called conformalized quantile regression that we demonstrate has similar patterns of sensitivity to model misspecification as Bayesian highest posterior density (HPD) and greatly overlap with HPDs, but have lower precision (more conservative). Finally, we trained and tested a neural network against phylogeographic data from a recent study of the SARS-Cov-2 pandemic in Europe and obtained similar estimates of region-specific epidemiological parameters and the location of the common ancestor in Europe. Along with being as accurate and robust as likelihood-based methods, our trained neural networks are on average over 3 orders of magnitude faster after training. Our results support the notion that neural networks can be trained with simulated data to accurately mimic the good and bad statistical properties of the likelihood functions of generative phylogenetic models. [ABSTRACT FROM AUTHOR]

Natural streamflow data is required in many hydrological applications. However, many basins are located in data-scarce regions or are impacted by human construction and activities. In this paper, we explore three machine learning algorithms, namely artificial neural networks, random forest and light gradient boosting machine, to simultaneously estimate all the parameters of the coupled modèle du Génie Rural à 4 paramètres Journaliers (GR4J) and snow accounting routine called CemaNeige model. A database of 675 basins in the USA and Quebec is used to train and test ensembles. After using the estimated parameters in GR4J, the resulting naturalized streamflow series are compared with those obtained by the established drainage area ratio and spatial proximity transfer methods in 11 test basins. The results indicate that the machine learning algorithms outperform the drainage area ratio and spatial proximity transfer methods. Among machine learning algorithms, random forests obtain lower (better) continuous ranked probability scores than the other methods for 10 out of 11 test basins. [ABSTRACT FROM AUTHOR]

Supervised learning in deep neural networks is commonly performed using error backpropagation. However, the sequential propagation of errors during the backward pass limits its scalability and applicability to low-powered neuromorphic hardware. Therefore, there is growing interest in finding local alternatives to backpropagation. Recently proposed methods based on forward-mode automatic differentiation suffer from high variance in large deep neural networks, which affects convergence. In this paper, we propose the Forward Direct Feedback Alignment algorithm that combines Activity-Perturbed Forward Gradients with Direct Feedback Alignment and momentum. We provide both theoretical proofs and empirical evidence that our proposed method achieves lower variance than forward gradient techniques. In this way, our approach enables faster convergence and better performance when compared to other local alternatives to backpropagation and opens a new perspective for the development of online learning algorithms compatible with neuromorphic systems. • Forward Gradient methods suffer from high variance that hinders convergence. • Activity-Perturbed Forward Gradients can be used to learn derivatives as direct feedback connections. • Feedback learning acts as a momentum that reduces the gradient variance closer to backpropagation. • Feedback learning reduces the biasness of Direct Feedback Alignment. • Feedback learning enables learning in convolutional layers. [ABSTRACT FROM AUTHOR]

In fiber optic communication systems, the presence of nonlinear noise has an impact on the performance of systems and needs to be reliably monitored. This paper first briefly introduced the fiber optic communication system and then applied a deep neural network (DNN). Eleven features were extracted from the optical signal, and the optical signal-to-noise ratio (OSNR) and nonlinear noise were monitored with the DNN. Moreover, experiments were carried out on the VPI Transmission Maker 9.0 platform to simulate both QPSK and 16QAM modulation formats. It was found that the means absolute error (MAE) value of the DNN was smaller than those of SVM and BPNN. The MAE of the DNN was smaller than 0.3 dB in OSNR monitoring and smaller than 1.2 dB in nonlinear monitoring. The experimental results demonstrate the reliability of the method combined with deep learning for nonlinear noise monitoring. The proposed method can be applied in practice. [ABSTRACT FROM AUTHOR]

Driving behavior monitoring by smartphone sensors is one of the most investigated approaches to ameliorate road safety. Various methods are adopted in the literature; however, to the best of our knowledge, their robustness to the prediction of new unseen data from different drivers and road conditions is not explored. In this paper, a two-phase Machine Learning (ML) method with taking advantage of high-pass, low-pass, and wavelet filters is developed to detect driving brakes and turns. In the first phase, accelerometer and gyroscope filtered time series are fed into Random Forest and Artificial Neural Network classifiers, and the suspicious intervals are extracted by a high recall. Following that, in the next phase, statistical features calculated based on the obtained intervals are used to determine the false and true positive events. To compare the predicted and real labels of the recorded events and calculate the accuracy, a method that covers the limitations of previous sliding windows is also employed. Real-world experimental result shows that the proposed method can predict new unseen datasets with average F1-scores of 71% in brake detection and 82% in turn detection which is comparable with previous works. Moreover, by sensitivity analysis of our proposed model, it is proven that implementing high-pass and low-pass filters can affect the accuracy for turn detection up to 30%. [ABSTRACT FROM AUTHOR]

Background: Detecting breast cancer in its early stages remains a significant challenge in the present context and is a leading cause of death among women, primarily due to delayed identification. This paper presents a practical and accurate approach based on deep learning to identify breast cancer in cytology images. Method: The analytical approach leverages knowledge from a related problem through a technique known as transfer learning. Convolutional neural networks (CNNs) are employed due to their remarkable performance on large datasets. Image classification architectures such as Google network (GoogleNet), Visual geographical group network (VGGNet), residual network (ResNet), and dense convolution network (DenseNet) are utilized in this approach. By applying transfer learning, the images are classified into two categories: those containing cancer cells and those without them. The performance of the proposed ensemble method is evaluated using a breast cytology image dataset. Results: The results of our proposed ensemble framework outperform conventional CNN models in terms of precision, recall, and F1 measures, achieving an impressive 86% prediction accuracy. Visual representations of validation graphs for each classifier demonstrate that the ensemble framework surpasses the performance of pre-trained CNN architectures. Conclusion: Combining the outcomes of conventional CNN architectures into an ensemble framework enhances early breast cancer detection, leading to a reduction in mortality through timely medical interventions. [ABSTRACT FROM AUTHOR]

• A multi-physics 3D FEM is established for exciting electrodes of ECS installed around pipeline subjected to LTCTMF. • The LTCTMF behavior is studied at different levels of LTCTMF. • A theoretical model results of LTCTMF compliance over creep time are analyzed using the Modulus degradation Approach. • A deep learning model is designed to predict compliance for various LTCTMF levels not included in previous FEM evaluation. • The proposed method performance is estimated by computing the accuracy rate, regression rate, and F-score indexes. The composite pipeline is a relatively new and viable alternative pipeline to the more commonly used traditional one due to its good mechanical and fatigue properties and lower production cost. For this purpose, it is critical to assess the mechanical and fatigue performance of composite pipeline material under various working conditions, particularly for monitoring long-term creep thermo-mechanical fatigue behavior. In this paper, a long-term creep thermo-mechanical fatigue behavior in a basalt fiber reinforced polymer laminated composite pipeline is detected through an integrated expert system consisting of the electrical capacitance sensors and a deep learning algorithm. First, a multi-physics finite element model is established for the simulation of a long-term creep thermo-mechanical fatigue behavior in basalt fiber reinforced polymer composite pipelines subjected to long-term fatigue loading of internal pressure and thermal effect. Second, theoretical model results of long-term creep thermo-mechanical fatigue compliance (S f (t)) over the time of creep are analyzed in pipeline material using the modulus degradation approach. Finally, an electrical potential change between electrical capacitance sensors electrodes corresponding to S f (t) over the time of creep for some levels of long-term creep thermo-mechanical fatigue (R f %) is recorded and then used in these datasets for training of the novel deep neural network based on one of the most widely used of the deep neural network families is the convolutional neural network, to predict S f (t) in pipeline for various R f % not included in the previous finite element model evaluation (i.e. electrical capacitance sensors technique). In this paper first is detected the long-term creep thermo-mechanical fatigue behavior for R f % = 25 % , 50 % , and 75 % from a finite element model and modulus degradation approach, and then is predicted the long-term creep thermo-mechanical fatigue behavior for R f % = 15 % , 35 % , 60 % , and 85 % respectively via deep neural network. The proposed method results are in good agreement with the experimental results available in the literature, thus verifying the accuracy and reliability of the proposed technique and its applicability to other different composite structures. [ABSTRACT FROM AUTHOR]

• The proposed AP-GAN-DNN method is able to predict creep fracture life more accurately in the case of small samples, which solves the complex nonlinear problem and the problem of test data dispersion. • Compared with traditional physical methods and machine learning models, the AP-GAN-DNN model has better generalization and robustness for creep fracture life prediction. • AP-GAN data enhancement method can significantly reduce the "pattern collapse" effect of GAN and improve the performance of prediction algorithms. 7050 aluminum alloy has high strength and excellent fracture toughness. However, damage can be caused to the 7050 aluminum alloy by creep at elevated temperatures. The accuracy of conventional creep life prediction methods may fall short of meeting the desired standards. And the application of machine learning (ML) methods is limited due to the scarcity and dispersion of creep sample data. Generative Adversarial Networks (GAN) are often used for data enhancement, but suffer from "pattern collapse" under small sample conditions. To solve the above problems, this paper proposes a creep fracture life prediction method, which combines the affinity propagation (AP) clustering algorithm, GAN, and deep neural networks (DNN) for accurate creep fracture life prediction. The AP clustering algorithm for adaptive clustering was utilized to better reflect the creep sample distribution. Independent GAN models were trained for each cluster to better capture distribution characteristics of the data and generate synthetic data that was highly similar to the real data. The DNN models were trained using the synthetic data and then predicted using real creep fracture life data. The presented method was compared with traditional physical and machine learning methods, and the method combining K-Means, GAN, and DNN. The experimental results show that the method proposed in this paper has better prediction accuracy in a small sample creep fracture life dataset. [ABSTRACT FROM AUTHOR]

A multi-layer neural network is used to extract the value of a superconductor's T c of cuprate from two models. The first model extracts T c from the structure's chemical composition whereas the second model extracts T c from the structure's chemical composition and the lattice parameters. The back-propagation algorithm is used to find the empirical equation of T c. It can calculate error signals and redistribute backward propagation signals. This paper studies four systems of cuprate superconductors: Y Ba Cu O, Bi Sr Ca Cu O, Tl Ba Ca Cu O, and Hg Ba Ca Cu O. In the first model, the T c of four high-temperature oxide superconductors are calculated as a function of eight parameters and one output, which is T c. Although the same output is produced in the second model, it is produced as a function of eleven parameters. The eight parameters are superconductor type number (Bi2212, Bi2223, Hg1201, Hg1212, Hg1223, Y123, Y124, Y247, Tl1223, Tl2212, Tl2223), first component composition, second component composition, third component composition, fourth component composition, atomic number of doping type, doping composition, and oxygen composition of the first model. The previous parameters with the three lattice parameters a , b and c are used in the second model. The trained deep learning models have shown a high degree of performance in matching the trained distributions. After analysing the results, we deduce electronegativity plays an important role in increasing T c of cuprate superconductors. Using the obtained T c prediction model, the scope is expanded to include the eleven unexplored multi-element materials. Candidates for superconductors with a higher T c that can be synthesized are proposed. By comparison with other models of machine learning, the suggested models in this paper give the highest T c for predicting new cuprate superconductors. [ABSTRACT FROM AUTHOR]

Chemical Looping Combustion (CLC) is a carbon capture technology that uses an oxygen carrier to transfer the oxidizing agent to the fuel for combustion. This study used different machine learning algorithms, Artificial neural network and Response surface methodology to estimate the surface region process performance and optimize the process condition for the CLC of different solid fuels waste paper, plastic waste, and sugarcane bagasse blends. Based on the combustion efficiency, CO 2 yield and CO 2 capture efficiency responses, A high performance correlation (R2 > 0.8) was obtained for all the combustion parameters analyzed. The perturbation plot derived from the RSM analysis indicated that the most significant input parameters include the steam to fixed carbon, blend ratio and the fuel reaction temperature. The CLC process was optimized using RSM. For blends of SCB/WP, the best operating conditions were found to be 800 °C, a solid flow rate of 197.7 kg/h, an oxygen carrier to fuel ratio of 1.1, a steam to fixed carbon ratio of 2.16, and a blend ratio of 1. Similarly, for blends of SCB/PW, the optimal operating conditions were 800 °C, a solid flow rate of 199.4 kg/h, an oxygen carrier to fuel ratio of 1.3, steam to fixed carbon ratio of 2, and a blend ratio of 0.3. The optimum combustion performance was found to be 0.98, 0.78, and 0.96 for SCB/WP and 0.99, 0.62, and 0.96 for SCB/PW, respectively. • The process performance of the CLC of MSW/biomass blend was compared using ANN and RSM. • The optimal blend ratios for SCB/WP and SCB/PW blends were 1 (25% WP) and 0.3 (42.5% PW). • The combustion performance of the WP improved by 6.2% and 3.5% in terms of combustion efficiency and CO 2 yield, respectively. • The most significant input factors were discovered to be the blend of fuels ratio and the steam to fixed carbon ratio. [ABSTRACT FROM AUTHOR]

Wind power is a critical source of renewable energy, but the variability of wind speed can impact the efficiency and reliability of wind power generation. To improve the accuracy of wind speed prediction, this paper proposes a novel system that combines deep learning and decomposition algorithms based on ensemble optimization methods. Firstly, the paper proposes an innovative hybrid modal decomposition (HMD) method that extracts accurate features from wind speed data using Singular Value Decomposition (SVD), modal number selection method, and Variational Mode Decomposition (VMD). Secondly, the variable screening method identifies relevant factors affecting wind speed as fixed inputs. Then, the stationary test method is used to identify the sequences of different features in the mode and establish different prediction models: a bidirectional long-term short-time neural network model (Bi-LSTM) model optimized by artificial hummingbird algorithm (AHA) is used for non-stationary sequences; an ARIMA model is used for stationary sequences. Data from Sotavento and Changma wind farms are used to test this forecasting system. Simulation experiments are carried out from multiple dimensions. The results show that all error indicators are significantly improved, and the proposed prediction system is better than other comparative forecasting schemes. • The research can be practically applied in the field of wind power generation. • The research can help improve the energy utilisation of wind power generation. • A new data decomposition algorithm called HMD is proposed. • A new prediction system based on ensemble optimization idea is proposed. • Combining AHA-optimized neural networks and ARIMA to predict wind speed. [ABSTRACT FROM AUTHOR]

• The paper proposes a methodology for a hybrid model that can capture complex non-linear relationships and help understand the interactions between input and output features. • The model overcomes the limitation of traditional neural network models in predicting across different spaces. • The proposed model is an intelligent water quality prediction model that can provide decision support for predicting COD Mn concentration and managing watershed risks in the Changdang Lake basin, with good application prospects and practical value. The organic pollution of lake water can cause a tremendous threat to the water ecosystem and human health. The COD Mn is one of the crucial indicators of lake water quality and is commonly utilized to gauge the extent of organic pollution in lake water. Therefore, this paper selected COD Mn as the research object and used the water quality monitoring data of Changdang Lake in China and its upstream and downstream to predict the COD Mn concentration in the lake. In order to study the spatial relationship between the lake and upstream and downstream water quality, reflect the joint action of multiple water quality factors in prediction and the interaction between different feature factors. This study combined the XGBoost feature filtering algorithm, maximum mutual information coefficient (MIC), and improved recurrent neural network (GRU) and proposes a hybrid model called XGB-MIC-GRU. The model first used XGBoost to screen and extract the relative importance of water quality characteristics and used the Shapley addition extension (SHAP) method to explain XGBoost feature extraction. Then, the correlation between the lake and the upstream and downstream water quality is calculated through MIC analysis. Finally, the selected water quality factor characteristics and spatial characteristics are input into the GRU model for prediction. The experimental results showed that water temperature, total phosphorus, and total nitrogen are the most important to COD Mn , and the upstream US1 and downstream DS1 and DS2 stations are the most closely related to the concentration of COD Mn in the lake. By comparing the prediction effect of the model in different time steps, the best 16-time steps related data were selected to predict the value of the next time. MAE, RMSE, and R2 of the model are 0.10, 0.13, and 0.96, respectively. The model has better prediction accuracy and correlation error than the traditional SVR and GPR. The proposed mixed model can accurately predict the concentration of COD Mn in the lake. It can assist decision-makers in timely implementation of effective measures to safeguard the lake ecosystem. [ABSTRACT FROM AUTHOR]

Cardiovascular diseases are currently the major causes of death globally. Among the strategies to prevent cardiovascular issues, the automated classification of heart sound abnormalities is an efficient way to detect early signs of cardiac conditions leading to heart failure or other, even asymptomatic, complications, quite effective for timely interventions. Despite the significant improvements in this field, there are still limitations due to the lack of solutions, available data-sets and poor (mainly binary — normal vs abnormal) classification models and algorithms. This paper presents a Medical Cyber–Physical System (MCPS) for the automatic classification of heart valve diseases onsite, in a timely manner. The proposed MCPS, indeed, can be deployed into personal and mobile devices, addressing the limitations of existing solutions for patients, healthcare practitioners, and researchers, through an efficient and easy accessible tool. It combines different neural network models trained on a new Italian dataset of 132 adult patients covering 9 heart sound categories (1 normal and 8 abnormal), also validated against two main open-access (Physionet/CinC Challenge 2016 and Korean) datasets. The overall MCPS performance (time, processing and energy resource utilization) and the high accuracy of the models (up to 98%) demonstrated the feasibility of the proposed solution, even with few data. The dataset supporting the findings of this paper is available upon request to the authors. • DB of 132 heart sounds of Italian patients in 9 categories, available upon request. • MCPS for automated HVD classification via hierarchical ML model structures. • Compared six ML classifiers (RF, SVM, NB, LR, DNN, LSTM) for HVD and majority voting. • MCPS validated on two open access datasets (Physionet/CinC 2016 and Korean). • Time, processing and energy efficiency of MCPS validated, with usage guidelines. [ABSTRACT FROM AUTHOR]

Marine ecosystems and their fish habitats are becoming increasingly important due to their integral role in providing a valuable food source and conservation outcomes. Due to their remote and difficult to access nature, marine environments and fish habitats are often monitored using underwater cameras to record videos and images for understanding fish life and ecology, as well as for preserve the environment. There are currently many permanent underwater camera systems deployed at different places around the globe. In addition, there exists numerous studies that use temporary cameras to survey fish habitats. These cameras generate a massive volume of digital data, which cannot be efficiently analysed by current manual processing methods, which involve a human observer. Deep Learning (DL) is a cutting-edge Artificial Intelligence (AI) technology that has demonstrated unprecedented performance in analysing visual data. Despite its application to a myriad of domains, its use in underwater fish habitat monitoring remains under explored. In this paper, we provide a tutorial that covers the key concepts of DL, which help the reader grasp a high-level understanding of how DL works. The tutorial also explains a step-by-step procedure on how DL algorithms should be developed for challenging applications such as underwater fish monitoring. In addition, we provide a comprehensive survey of key deep learning techniques for fish habitat monitoring including classification, counting, localisation, and segmentation. Furthermore, we survey publicly available underwater fish datasets, and compare various DL techniques in the underwater fish monitoring domains. We also discuss some challenges and opportunities in the emerging field of deep learning for fish habitat processing. This paper is written to serve as a tutorial for marine scientists who would like to grasp a high-level understanding of DL, develop it for their applications by following our step-by-step tutorial, and see how it is evolving to facilitate their research efforts. At the same time, it is suitable for computer scientists who would like to survey state-of-the-art DL-based methodologies for fish habitat monitoring. • Marine environments and fish habitats are widely surveyed using underwater cameras. • Deep learning (DL) offers an effective solution for processing underwater videos. • We write a tutorial on the key concepts and steps of DL for underwater monitoring. • We provide a survey of key DL-based visual fish monitoring methods/datasets. • We shed light on challenges/opportunities of DL for underwater fish monitoring. [ABSTRACT FROM AUTHOR]

Geopolymer concrete is a sustainable replacement to the Ordinary Portland Cement (OPC) concrete as it mitigates some of the associated problems of OPC manufacturing such as greenhouse gas emission and natural resource depletion. There has been significant recent research in the design of fly ash-based geopolymer concrete using advanced machine learning techniques which can address some of the problems with classical mix design approaches. However, practical application of geopolymer concrete is limited due to lack of standard mix design procedure. This comprehensive review summarizes the current literature on machine learning methodologies to predict the compressive strength of fly ash-based geopolymer concrete. Firstly, the input parameters used for the machine learning model development are categorized based on feature selection or feature extraction. Secondly, available machine learning approaches are categorized based on analysis methods namely, nonlinear regression, ensemble learning, and evolutionary programming. The effect of hyperparameters on the individual model performance, and model comparison based on the prediction performance are also discussed to identify potentially more suitable model type and hyper parameter ranges. Further, the paper discusses the input variable's sensitivity towards the model performance which provides guidance towards future model developments. Overall, this paper will provide an understanding of the current state of machine learning approaches to predict the compressive strength of geopolymer concrete and the gaps in research for the development of models and achieving the required performance. Hence, the summarized knowledge will be highly beneficial to design prospective research towards sustainable cement-free concrete using fly ash. • Artificial neural networks (ANN) predict geopolymer concrete strength well, offering reliable forecasts for new data. • Support vector machines and random forests offer ANN- like performance, serving as alternatives in machine learning (ML). • The success of ML model relies on proper selection of inputs and tuning hyperparameters for optimal performance. • The chemical, physical, and mineralogical characteristics of fly ash emerge as pivotal input variables in ML models. • Validating models through laboratory experiments is imperative, ensuring generalization for real-world applications. [ABSTRACT FROM AUTHOR]

Despite the existence of evidence-based rehabilitation strategies that address biomechanical deficits, the persistence of recurrent ankle problems in 70% of patients with acute ankle sprains highlights the unresolved nature of this issue. Artificial intelligence (AI) emerges as a promising tool to identify definitive predictors for ankle sprains. This paper aims to summarize the use of AI in investigating the ankle biomechanics of healthy and subjects with ankle sprains. Articles published between 2010 and 2023 were searched from five electronic databases. 59 papers were included for analysis with regards to: i). types of motion tested (functional vs. purposeful ankle movement); ii) types of biomechanical parameters measured (kinetic vs kinematic); iii) types of sensor systems used (lab-based vs field-based); and, iv) AI techniques used. Most studies (83.1%) examined biomechanics during functional motion. Single kinematic parameter, specifically ankle range of motion, could obtain accuracy up to 100% in identifying injury status. Wearable sensor exhibited high reliability for use in both laboratory and on-field/clinical settings. AI algorithms primarily utilized electromyography and joint angle information as input data. Support vector machine was the most used supervised learning algorithm (18.64%), while artificial neural network demonstrated the highest accuracy in eight studies. The potential for remote patient monitoring is evident with the adoption of field-based devices. Nevertheless, AI-based sensors are underutilized in detecting ankle motions at risk of sprain. We identify three key challenges: sensor designs, the controllability of AI models, and the integration of AI-sensor models, providing valuable insights for future research. [Display omitted] • Application of sensors and artificial intelligence to analyse ankle biomechanics. • Lab sensors predict parameters, paving the way for post-modern rehabilitation. • Field devices show potential for ankle injury prediction. • Focus on streamlined smart sensors and effective data management in the future. [ABSTRACT FROM AUTHOR]

Corrosion presents significant challenges in the marine, offshore, and oil and gas industries, resulting in annual economic losses amounting to billions of dollars. To address these losses and ensure the structural integrity of marine infrastructure, it is essential to implement effective corrosion monitoring techniques. In recent years, machine learning algorithms have gained prominence across various fields, offering innovative solutions to corrosion-related concerns. This paper provides a comprehensive critical review, primarily focusing on the two most prevalent machine learning algorithms: artificial neural networks and random forests. The review critically analyzes their applications, methodologies, and effectiveness in the realm of marine and offshore steel structures, oil and gas pipelines, as well as construction materials like Al alloys and Mg alloys and the analysis of corrosion coating behavior. Furthermore, this study explores the key findings and inherent limitations of these machine learning techniques, emphasizing their potential in corrosion prediction, detection, and the mitigation of corrosion issues in the marine, offshore, and oil and gas industries. By identifying existing research gaps and offering recommendations for future investigations, this paper emerges as an invaluable resource for researchers, engineers, and practitioners aiming to advance corrosion prevention and management strategies within these pivotal domains. • In-depth analysis of ANN and RF in maritime, offshore, and oil and gas corrosion research (2018-2023). • Critical evaluation of ML algorithms in maritime steel structures, pipelines, and construction materials. • Valuable review for cost-effective maritime corrosion maintenance strategies. • Provides concise corrosion management expertise to empower researchers and industry experts. [ABSTRACT FROM AUTHOR]

This paper presents a new framework for stochastic updating of a finite element model for a composite plate, considering the influence of temperature on Lamb wave propagation. The framework involves deterministic updating to optimize mechanical properties and stochastic updating to derive probability density functions for key parameters. It utilizes sensitivity analysis and Bayesian inference with Markov-Chain Monte Carlo simulations and the Metropolis–Hastings sampling algorithm. This paper proposes a machine learning surrogate model based on artificial neural networks to improve computational efficiency. This surrogate modeling approach allows parallelized Monte Carlo simulations, reducing updating time significantly without compromising the accuracy of the resulting probability density functions for model parameters. These advancements show a promising way to enhance composite plate modeling and Lamb wave propagation studies, providing a more efficient and accurate approach to verify and validate finite element models with potential applications in engineering simulations. [ABSTRACT FROM AUTHOR]

This paper proposes a data-driven model for predicting the code-based seismic vulnerability index calibrated on a dataset comprising almost 300 buildings. The vulnerability index, estimated following the Italian Seismic Code, involved rigorous investigations, including geometric surveys, experimental tests, and numerical modelling. Leveraging data from these investigations, encompassing approximately 15 categorical and numerical explanatory variables, the authors developed several regression and classification predictive models, such as Logistic Regression and Artificial Neural Networks (ANN). The optimal models perform binary classification to determine the categorization into two macro-classes, defined by an arbitrary vulnerability threshold. The ANN model stands out as the best performer. When adjusting the vulnerability threshold to obtain a balanced dataset, such a model achieves an accuracy higher than 85%. The paper also discusses the importance of each feature by calculating the SHapley Additive exPlanations (SHAP) values. The proposed model can aid decision-makers in allocating resources effectively to mitigate seismic risks of built environments. • Data-driven model for code-based seismic vulnerability assessment. • 15 explanatory variables are considered. • Regression models perform poorly. • Binary classification is the only reliable approach. • The ANN model has an 85% accuracy on binary classification with balanced dataset. [ABSTRACT FROM AUTHOR]

The critical heat flux (CHF) is an important parameter determining the heat transfer capability of nuclear reactors. Therefore, prediction of CHF with accuracy and correct understanding is essential for the design and safety analysis of nuclear power plants (NPPs) and industrial boiling systems. This paper focuses on the CHF prediction using the Gaussian process regression (GPR), a machine learning (ML) technique for modeling nonlinear systems. The covariance kernel is a critical component of GPR modeling because it contains assumptions about the function we want to know and defines the dependence and similarity between the data. In this study, the prediction of CHF is investigated during training and prediction in two different approaches: isotropic and anisotropic covariance kernels. Besides, we evaluate the influence of various isotropic and anisotropic kernels on the accuracy of CHF prediction and quantification of uncertainty encoded in the posterior variances in each of the approaches. The use of anisotropic kernels, considering different shape parameters in line with different data dimensions, results in higher accuracy and better generalization. In addition, compared to other ML tools such as support vector regression (SVR) and artificial neural networks (ANNs), the GPR with anisotropic kernels has much better performance. The evaluation criteria involving root mean square error (RMSE) and mean absolute percentage error (MAPE) in anisotropic kernels are significantly improved compared to isotropic kernels. For example, in squared exponential and rational quadratic kernels, RMSE and MAPE values improved by {65.81%, 67.28%} and {61.97%, 60.12%} values, respectively. The results of the GPR method with the anisotropic kernels show the relative superiority of this method compared to SVR and ANN. The lowest RMSE and MAPE values of all three methods were compared, and these values have improved in GPR compared to SVR by 96.01% and 94.25% and compared to ANN by 84.40% and 85.51%, respectively. Finally, some valuable ideas and practical findings will be offered based on numerical simulations and comparisons between isotropic and anisotropic kernel assumptions. Since the approach of using anisotropic kernels has high computational time despite its high flexibility, we will address this issue in future studies and also use this approach for other nuclear engineering problems. [Display omitted] • A flexible GPR structure is presented. • We compared isotropic & anisotropic kernels for critical heat flux prediction. • Anisotropic model outperforms isotropic in critical heat flux prediction. • Anisotropic GPR outperforms SVR & ANN for critical heat flux prediction. • Broader applicability to other CHF predictions in nuclear engineering applications. [ABSTRACT FROM AUTHOR]

Flood modelling and forecasting can enhance our understanding of flood mechanisms and facilitate effective management of flood risk. Conventional flood hazard and risk assessments usually consider one driver at a time, whether it is ocean, fluvial or pluvial, without considering the compound nature of flood events. In this paper, we developed a novel approach for modelling and forecasting compound coastal-fluvial floods using a two-step framework. In step one, a hydrodynamic model is used to simulate floodwater propagation; while in step two, machine learning (ML) models are used to generate flood forecasts. The architecture of hydrodynamic-ML forecasting system incorporates a hydrodynamic model covering a specific domain, with individual ML models trained for each pixel. In total 7 ML models including: Support Vector Regression (SVR), Support Vector Machine (SVM), Radial Basis Function (RBF), Linear Regression (LR), Gaussian Process Regression (GPR), Decision Tree (DT), and Artificial Neural Network (ANN) were applied in this study. Forecasting compound floods is achieved using two sets of inputs: timeseries of river discharges in the upstream fluvial section and downstream ocean water levels in the coastal areas. The accuracy of the flood forecasting system is demonstrated for Cork City, Ireland; and modelling performance was evaluated using several statistical tools. Results show that the proposed models can provide reliable estimates of flood inundation and associated water depths. Overall, the RBF model exhibits the best performance. Despite the complexity of compound multi-driver floods, this study shows that the coupled hydrodynamic-ML approach can forecast coastal-fluvial flood with limited hydraulic and hydrological input data. This system overcomes the limitations of traditional hydrodynamic model-based systems where trade-offs between the always competing numerical model accuracy and computational time prohibit the model to be used for short-term flood forecasting. Once trained, the ML component of the coupled system can perform flood forecasting in near real-time, potentially integrating into a flood early warning system. Accurate flood forecasting has a wide range of positive societal impacts, including improved flood preparedness, increased confidence, better resource allocation, reduced flood damage, and potentially even flood prevention. • Novel technique to improve compound coastal-fluvial flood modelling. • Flood modelling technique based on seven Machine Learning methods. • Approach is successfully implemented, and results are evaluated over Cork, Ireland. • The results demonstrate minimal quantitative errors for the proposed models. [ABSTRACT FROM AUTHOR]

The conventional standardized theoretical models (such as Webster, Alcelik, Indo-HCM) used for the delay estimation revolve around the mathematical hypothesis and assumptions, making them static with limitations in accommodating the dynamic traffic behaviors. Recent advances in artificial intelligence make machine learning techniques suitable for estimating vehicle control delay compared to conventional methods. This paper demonstrates the application of several machine learning models developed by focusing on the fluctuations of traffic observed at an intersection having heterogeneous traffic conditions in Ahmedabad city for delay estimation. Several parameters are extracted from on-field and video surveys. However, not all parameters are relevant for accurately estimating vehicle control delay. Hence, a feature selection process consisting of several feature-scoring techniques from filter, wrapper, and embedded methods is applied to all the parameters. This process gave insights into the most statistically relevant independent parameters, and out of all the parameters, cycle time was found to be insignificant, with a feature score of 0 from almost all techniques. Hence, it was removed, and then the prominent parameters were then used to build a vehicle control delay model using support vector regression (SVR), K-nearest neighbor (KNN), artificial neural network (ANN), random forest regression (RF), and decision tree regression (DT). Error distribution, standard deviation of errors, coefficient of Determination (R2), and Root Mean Squared Error (RMSE) are the parameters used for evaluating the performance of the machine learning models. RF outperformed them all with a standard deviation of errors, R2, and RMSE of 11.065, 0.926, and 11.081 on testing data. But ANN, KNN, and DT also performed satisfactorily. Compared with conventional standardized theoretical models, all the machine learning models except SVR performed better. [ABSTRACT FROM AUTHOR]

Soil water retention curves (SWRC) are constitutive relationships that are critical for predicting the hydro-mechanical behaviour of unsaturated soil in a wide range of applications in geoenvironmental and geotechnical engineering, hydrology, and agricultural and soil science. Directly measuring SWRC can be costly and time-consuming. Recent research has shown that machine learning, especially artificial neural networks (ANNs), can effectively predict SWRC using easy-to-measure soil properties as inputs. However, significant questions remain about prediction accuracy and what are the most effective input parameters to use, and only shallow neural networks with one hidden layer have been developed in the past for this purpose. In this study, effectiveness of deep neural networks (DNNs) - ANNs with more than one hidden layer - for SWRC prediction is explored for a range of models with different combinations that require easy-to-measure input parameters. Specifically, the study investigates whether switching from a shallow neural network (SNN) to a deep neural network (DNN) can enhance the accuracy of SWRC predictions for these models. Significant differences are found in seven out of thirteen cases when shifting from SNN to DNN. It was also found that models including soil texture, augmented by either dry density or soil porosity as input parameters, perform well. Specific gravity, soil depth, and organic content, on the other hand, do not add to the predictive capability of these models. Findings of this paper can help improve SWRC prediction using machine learning and can lead to more accurate modelling of unsaturated soil behaviour. [ABSTRACT FROM AUTHOR]

The critical heat flux (CHF) is an important parameter determining the heat transfer capability of nuclear reactors. Therefore, prediction of CHF with accuracy and correct understanding is essential for the design and safety analysis of nuclear power plants (NPPs) and industrial boiling systems. This paper focuses on the CHF prediction using the Gaussian process regression (GPR), a machine learning (ML) technique for modeling nonlinear systems. The covariance kernel is a critical component of GPR modeling because it contains assumptions about the function we want to know and defines the dependence and similarity between the data. In this study, the prediction of CHF is investigated during training and prediction in two different approaches: isotropic and anisotropic covariance kernels. Besides, we evaluate the influence of various isotropic and anisotropic kernels on the accuracy of CHF prediction and quantification of uncertainty encoded in the posterior variances in each of the approaches. The use of anisotropic kernels, considering different shape parameters in line with different data dimensions, results in higher accuracy and better generalization. In addition, compared to other ML tools such as support vector regression (SVR) and artificial neural networks (ANNs), the GPR with anisotropic kernels has much better performance. The evaluation criteria involving root mean square error (RMSE) and mean absolute percentage error (MAPE) in anisotropic kernels are significantly improved compared to isotropic kernels. For example, in squared exponential and rational quadratic kernels, RMSE and MAPE values improved by {65.81%, 67.28%} and {61.97%, 60.12%} values, respectively. The results of the GPR method with the anisotropic kernels show the relative superiority of this method compared to SVR and ANN. The lowest RMSE and MAPE values of all three methods were compared, and these values have improved in GPR compared to SVR by 96.01% and 94.25% and compared to ANN by 84.40% and 85.51%, respectively. Finally, some valuable ideas and practical findings will be offered based on numerical simulations and comparisons between isotropic and anisotropic kernel assumptions. Since the approach of using anisotropic kernels has high computational time despite its high flexibility, we will address this issue in future studies and also use this approach for other nuclear engineering problems. [Display omitted] • A flexible GPR structure is presented. • We compared isotropic & anisotropic kernels for critical heat flux prediction. • Anisotropic model outperforms isotropic in critical heat flux prediction. • Anisotropic GPR outperforms SVR & ANN for critical heat flux prediction. • Broader applicability to other CHF predictions in nuclear engineering applications. [ABSTRACT FROM AUTHOR]

Soil water retention curves (SWRC) are constitutive relationships that are critical for predicting the hydro-mechanical behaviour of unsaturated soil in a wide range of applications in geoenvironmental and geotechnical engineering, hydrology, and agricultural and soil science. Directly measuring SWRC can be costly and time-consuming. Recent research has shown that machine learning, especially artificial neural networks (ANNs), can effectively predict SWRC using easy-to-measure soil properties as inputs. However, significant questions remain about prediction accuracy and what are the most effective input parameters to use, and only shallow neural networks with one hidden layer have been developed in the past for this purpose. In this study, effectiveness of deep neural networks (DNNs) - ANNs with more than one hidden layer - for SWRC prediction is explored for a range of models with different combinations that require easy-to-measure input parameters. Specifically, the study investigates whether switching from a shallow neural network (SNN) to a deep neural network (DNN) can enhance the accuracy of SWRC predictions for these models. Significant differences are found in seven out of thirteen cases when shifting from SNN to DNN. It was also found that models including soil texture, augmented by either dry density or soil porosity as input parameters, perform well. Specific gravity, soil depth, and organic content, on the other hand, do not add to the predictive capability of these models. Findings of this paper can help improve SWRC prediction using machine learning and can lead to more accurate modelling of unsaturated soil behaviour. [ABSTRACT FROM AUTHOR]

This paper proposes a novel hardware architecture for a Feed-Forward Neural Network (FFNN) with the objective of minimizing the number of execution clock cycles needed for the network's computation. The proposed architecture depends mainly on using two physical layers that are multiplexed and reused during the computation of the FFNN to achieve an efficient parallel design. Two physical layers are designed to handle the computation of different sizes of Neural Networks (NN). The proposed FFNN architecture hardware resources are independent of the NN's number of layers, instead, they depend only on the number of neurons in the largest layer. This versatile architecture serves as an accelerator in Deep Neural Network (DNN) computations as it exploits parallelism by making the two physical layers work in parallel through the computations. The proposed implementation was implemented with 18-bit fixed point representation reaching 200 MHz clock speed on a Spartan7 FPGA. Furthermore, the proposed architecture achieves a lower neuron computation factor compared to previous works in the literature. [Display omitted] [ABSTRACT FROM AUTHOR]

Machine-learning (ML) techniques have bloomed in recent years, especially in fluid mechanics applications. In this paper, we trained, validated and compared two types of ML-based models to augment Reynolds-averaged Navier–Stokes (RANS) simulations. The methodology was tested in a series of flows around bumps, characterized by different levels of flow separation and curvatures. Initially, the ML-based models were trained in three configurations presenting attached flow, small and moderate separation and tested in two configurations presenting incipient and large separation. The output quantity of the machine-learning model is the turbulent viscosity as done in Volpiani et al. (2022). The new models based on artificial neural networks (NN) and random forest (RF) improved the results if compared to the baseline Spalart–Allmaras model, in terms of velocity field and skin-friction profiles. We noted that NN has better extrapolation properties than RF, but the skin-friction distribution can present small oscillations when using certain input features. These oscillations can be reduced if the RF model is employed. One major advantages of RF is that raw quantities can be given as input features, avoiding normalization issues (such as division by zero) and allowing a larger number of universal inputs. At the end, we propose a mixed NN-RF model that combines the strengths of each method and, as a result, improves considerably the RANS prediction capability, even for a case with strong separation where the Boussinesq hypothesis (and therefore the eddy-viscosity assumption) lacks accuracy. • We combine neural networks and random forest to create a new data-driven RANS model. • The new machine learning-based model does not require to transport unclosed terms. • The new model improves the velocity, wall-pressure and skin-friction distributions. • It was proved to be robust even in predicting extrapolated flows. [ABSTRACT FROM AUTHOR]

• The UCS of rock was correlated using only three non-destructive test indexes; • A parametric analysis was performed to obtain the optimum ANN architecture; • Metaheuristic techniques were applied to optimize the ANN weights and biases; • The accuracy of the developed model is higher than the available in the literature; • An explicit equation was extracted for practical engineering design. The unconfined compressive strength (UCS) of intact rocks is crucial for engineering applications, but traditional laboratory testing is often impractical, especially for historic buildings lacking sufficient core samples. Non-destructive tests like the Schmidt hammer rebound number and compressional wave velocity offer solutions, but correlating these with UCS requires complex mathematical models. This paper introduces a novel approach using an artificial neural network (ANN) to simultaneously correlate UCS with three non-destructive test indexes: Schmidt hammer rebound number, compressional wave velocity, and open-effective porosity. The proposed ANN model outperforms existing methods, providing accurate UCS predictions for various rock types. Contour maps generated from the model offer practical tools for geotechnical and geological engineers, facilitating decision-making in the field and enhancing educational resources. This integrated approach promises to streamline UCS estimation, improving efficiency and accuracy in engineering assessments of intact rock materials. [ABSTRACT FROM AUTHOR]

This paper proposes a mesh-free computational framework and machine learning theory for solving elliptic PDEs on unknown manifolds, identified with point clouds, based on diffusion maps (DM) and deep learning. The PDE solver is formulated as a supervised learning task to solve a least-squares regression problem that imposes an algebraic equation approximating a PDE (and boundary conditions if applicable). This algebraic equation involves a graph-Laplacian type matrix obtained via DM asymptotic expansion, which is a consistent estimator of second-order elliptic differential operators. The resulting numerical method is to solve a highly non-convex empirical risk minimization problem subjected to a solution from a hypothesis space of neural networks (NNs). In a well-posed elliptic PDE setting, when the hypothesis space consists of neural networks with either infinite width or depth, we show that the global minimizer of the empirical loss function is a consistent solution in the limit of large training data. When the hypothesis space is a two-layer neural network, we show that for a sufficiently large width, gradient descent can identify a global minimizer of the empirical loss function. Supporting numerical examples demonstrate the convergence of the solutions, ranging from simple manifolds with low and high co-dimensions, to rough surfaces with and without boundaries. We also show that the proposed NN solver can robustly generalize the PDE solution on new data points with generalization errors that are almost identical to the training errors, superseding a Nyström-based interpolation method. [ABSTRACT FROM AUTHOR]

Extensive research has been conducted on analyzing human movements, driven by its diverse practical applications such as human–robot interaction, human learning, and clinical diagnosis. However, the current state-of-the-art still encounters scientific challenges when it comes to modeling human movements. There are two key aspects that need to be addressed. Firstly, new models should consider the stochastic nature of human movement and the physical structure of the human body to accurately predict the patterns in full-body motion descriptors over time. Secondly, while deep learning algorithms have been utilized, they lack explainability in terms of predicting body posture sequences, making it essential to improve their comprehensible representation of human movement. This paper aims to tackle these challenges by presenting three innovative methods for creating explainable representations of human movement. The study formulates human body movement as a state-space model based on the Gesture Operational Model (GOM). Model parameters are estimated through either one-shot training employing Kalman Filters or data-intensive training utilizing artificial neural networks. The trained models are utilized for analyzing the dexterity of expert professionals in full-body movements, enabling the identification of dynamic associations between body joints and gesture recognition. Additionally, these models are employed to generate artificial professional movements. • Three innovative methods for explainable human movement models. • Body dexterity analysis: Models reveal how artisans and operators perform tasks. • Minimal motion descriptors to enhance task recognition. • Artificial generation of full-body professional movements. • Extensive experimentation with real-world datasets. [ABSTRACT FROM AUTHOR]

Active learning alleviates labeling costs by selecting and labeling the most informative examples from an unlabeled pool. However, most existing active learning approaches estimate informativeness with uncalibrated confidence, resulting in unreliable informativeness estimation. These approaches generally ignored two significant issues caused by uncalibrated confidence methods. Firstly, the average uncalibrated confidence generated by modern neural networks is usually higher than the accuracy. Secondly, examples located near the decision boundaries are unstable during prediction when the target model updates parameters in the last several epochs, even throughout the training process. This phenomenon, caused by the forgetting characteristic of neural networks, has a significant impact on some specific models that estimate the informativeness by predicted probability vectors or pseudo labels. To address these issues, in this paper, we propose a novel active learning approach to reliably estimate informativeness with calibrated confidence. Specifically, we integrate the intermediate predictions for each unlabeled example, generated by the target model during the training process, to generate calibrated confidence. The calibrated confidence can capture a tendentious label from an indecisive subset of the class space. We show that the calibrated confidence with tendentiousness can maintain the ability of correct predictions. The empirical results demonstrate that our approach outperforms the state-of-the-art active learning methods on image classification tasks. • The active learning algorithm selects unstable examples by calibrated confidence.. • The confidence calibration method only requires training a single model. • Extensive experiments show the competitive performance of the proposed approach. [ABSTRACT FROM AUTHOR]

In power transformers, accurate diagnosis prediction plays a crucial role in ensuring the reliability and efficiency of electrical systems. This paper presents an enhanced diagnostic prediction approach for power transformers by combining the Synthetic Minority Over-sampling Technique (SMOTE) and Deep Neural Networks (DNN). Our approach addresses the challenge of imbalanced data in power transformer diagnosis prediction by leveraging SMOTE to generate synthetic samples and balance the dataset. By effectively handling rare events through the augmentation of minority class instances, our predictive model becomes more robust. Additionally, using deep neural networks enables the exploration of complex patterns and relationships within the transformer dataset. The DNN architecture integrates multiple layers of learnable features, enabling the prediction model to extract high-level representations and achieve improved accuracy and performance. To evaluate the effectiveness of our proposed approach, we conducted extensive experiments using real-world power transformer datasets. Comparative analysis of the results demonstrates that the combination of SMOTE and DNN outperforms traditional classification techniques applied to imbalanced datasets. The proposed model achieves a higher training accuracy of 98.22 % and a testing accuracy of 94.6 % and mitigates the risks associated with misdiagnosis, contributing to power systems' overall reliability and maintenance efficiency. [ABSTRACT FROM AUTHOR]

This paper introduces a novel computational fluid dynamics-artificial neural network (CFD-ANN) approach that has been devised to enhance the efficiency of plunger valves. The primary emphasis of this research is to achieve an optimal equilibrium between hydraulic flow and geometric configuration. This study is a novel contribution to the field as it explores the flow dynamics of plunger valves using Computational Fluid Dynamics (CFD) and proposes a unique methodology by incorporating Machine Learning (ML) for performance forecasting. An artificial neural network (ANN) architecture was developed using a thorough comprehension of flow physics and the impact of geometric parameters acquired through computational fluid dynamics (CFD). Using optimization, the primary aspects of the Artificial Neural Network (ANN), including the learning algorithm and the number of hidden layers, have been modified. This refinement has resulted in the development of an architecture exhibiting a remarkably high R2 value of 0.987. This architectural design was employed to optimize the plunger valve. By utilizing Artificial Neural Networks (ANN), a comprehensive analysis comprising 1000 distinct configurations was effectively performed, resulting in a significant reduction in time expenditure compared to relying on Computational Fluid Dynamics (CFD). The result was a refined arrangement that achieved maximum head loss, subsequently verified using computational fluid dynamics (CFD) simulations, resulting in a minimal discrepancy of 2.66%. The efficacy of artificial neural networks (ANN) becomes apparent due to their notable cost-efficiency, along with their capacity to produce outcomes that are arduous and expensive to get through conventional optimization research utilizing computational fluid dynamics (CFD). • Innovative Fusion: Introduces a pioneering Computational Fluid Dynamics-Artificial Neural Network (CFD-ANN) approach for optimizing plunger valves, achieving a unique synergy between hydraulic flow and geometric configuration. • Optimized ANN Architecture: Develops a refined ANN architecture with an impressive R2 value of 0.987, demonstrating accuracy in predicting plunger valve performance. Key parameters are modified, leading to an 88% reduction in time expenditure compared to traditional CFD studies. • Geometric Parameter Impact: Analyzes the effects of valve slot number, diameter, and length on plunger valve performance, providing valuable insights into the interplay between geometric factors and hydraulic flow. • Efficient Optimization Process: Validates the enhanced CFD method through experimental work, ensuring a minimal 8.9% error. The study showcases cost-efficiency and superior performance in optimizing plunger valves through the ANN approach. [ABSTRACT FROM AUTHOR]

One of the most important composite indicators (CIs) to assess the development of countries or regions is the human development index (HDI) which is used by the United Nations (UN) to rank countries. HDI has three dimensions including healthy life, population education, and standard of living. A total of four different sub-indicators are defined for these three dimensions. The UN evaluates and ranks all countries using a simple arithmetic or geometric average of the sub-indicators and then categorizes the countries into four different groups based on their HDI scores. To measure the HDI, the benefit-of-the-doubt (BOD) model is used by researchers instead of the geometric mean. The conventional BOD model has some main drawbacks. The first is not accounting for data uncertainty, and the second is evaluating countries using different weights for the same sub-indicators. Furthermore, BOD model is not capable of predicting countries' future HDI scores. To overcome these deficiencies, this paper proposes a common weight fuzzy BOD (CWFBOD) model to measure the HDI scores. First, to take into account the uncertainty, data are considered fuzzy numbers, and a fuzzy BOD model (FBOD) is introduced. Then, to find a set of common weights for the three dimensions of HDI, the proposed FBOD model is transformed into a multiple-objective CWFBOD model. To convert and solve the multiple objective CWFBOD model to a single objective model, a fuzzy theory approach is used. In addition, of predicting the future HDI scores of countries, an artificial neural network (ANN) is designed and trained, where the original data on sub-indicators health, education, and income are considered as the features, and the HDI scores generated by CWBOD are assumed as the target of ANN. Finally, this study applies the fuzzy C-Means clustering technique to cluster all countries into four different clusters based on the HDI scores generated by FBOD and CWFBOD models. To illustrate the ability of the proposed methodology, the HDI scores of 190 countries during the period of 2015–2021 have been estimated and predicted. The results show that the proposed integrated methodology can be effectively used to estimate and predict the HDI scores as well as to cluster countries. [ABSTRACT FROM AUTHOR]

Cold-Formed Steel Lipped (CFSL) channels are susceptible to a localized failure mechanism known as web crippling, triggered by concentrated loads or reactions applied to the web of the section. These loads induce buckling and distortion in the web, ultimately leading to the member's collapse. It is a challenging task to accurately determine the web crippling capacity of a CFSL channel due to its complexity and various influencing factors. This paper presents hybrid soft computing techniques for accurately predicting the web crippling capacity of CFSL channels subjected to two flange load cases. The developed soft computing techniques combine Artificial Neural Networks (ANN) with either Genetic Algorithms (GA) or Particle Swarm Optimization (PSO) to improve computational efficiency and accuracy. The finite element models of CFSL channels are developed and validated by experimental results and then employed to generate a database, which is used to train machine learning models, including ANN, GA-ANN, and PSO-ANN. Analysis is undertaken on the reliability of existing design formulas for determining the web crippling capacity of CFSL channels. It is shown that the PSO-ANN model outperforms the other models in terms of prediction accuracy. The existing design codes and formulas are not reliable in estimating the web crippling capacity of CFSL channels. However, the proposed model yields good correlation with finite element analysis results. A user- friendly graphical interface tool is developed for the practical design of cold-formed steel lipped channels. • FE model is developed that simulates the web crippling behavior of CFSL channels. • Hybrid ML models are developed for predicting web crippling capacity of CFSL channels. • Reliability of existing formulas for estimating web crippling capacity is investigated. • A user-friendly graphical interface tool is developed for design purpose. [ABSTRACT FROM AUTHOR]

• A scheme to recognize the distraction level was proposed. • MLP-AutoEncoder and DPC algorithms were used to define distraction-level labels. • Factors affecting driver distraction level were explored with mixed-model analyses. • A distraction-level prediction model with stacking ensemble learning was made. Driver distraction-level recognition while performing secondary tasks in full-touch in-vehicle information systems (FTIVISs) is essential for the harmonious co-driving of human and intelligent vehicle systems. However, there has been little research on this topic. To respond to this issue, this paper proposes a distraction-level recognition framework with a combination of semi-supervised learning, unsupervised learning, and supervised learning. First, unsupervised learning and semi-supervised is used to divide the collected unlabeled samples of driving distraction behavior into three categories of distraction levels: high, medium, and low. Second, the factors influencing the distraction level are explored through a mixed model analysis. Finally, a stacking-based ensemble learning model is proposed to recognize the driver distraction level by supervised learning, with the influencing factors of the distraction level used as model input parameters. To improve the recognition performance of the stacking model, four heterogeneous classifiers selected as the base classifiers, and principal component analysis (PCA) is introduced in the base classifier layer, which improves the ability of the meta -classifier to process raw features based on overfitting resistance. We conducted a real road experiment under different road and FTIVIS task conditions, and the proposed model performed better than traditional machine learning models. In addition, the model exhibited the greatest advantage when the deep neural network (DNN) algorithm was used as the meta -classifier of the model, with a recognition accuracy of 92.5%. The study findings are significant for developing a human–machine co-driving control strategy and improving vehicle driving safety. [ABSTRACT FROM AUTHOR]

Surface texture plays an important role in reducing friction, which has been widely applied in mechanical equipment. In this paper, a surface texture design method for sliding friction pairs based on machine learning is proposed, which consists of three parts: model training and construction, texture design and result verification. Firstly, artificial neural network (ANN) and gradient boosting decision tree (GBDT) are selected as the optimal forward and reverse models respectively by comparing five machine learning models. Then the optimal forward and reverse models are combined to design surface texture and verify the design results. The results show that the combination of forward and reverse models is reliable. Lubricant viscosity and friction coefficient obviously affect the design of texture size, depth and coverage. Finally, the feasibility and effectiveness of this method are validated by friction experiments. The results provide a new approach for the design of surface texture. [ABSTRACT FROM AUTHOR]

Stainless steel has many advantages when used in structures, however, the initial cost is high. Hence, it is essential to develop reliable and accurate design methods that can optimize the material. As novel, reliable soft computation methods, machine learning provided more accurate predictions than analytical formulae and solved highly complex problems. The present study aims to develop machine learning models to predict the cross-section resistance of circular hollow section stainless steel stub column. A parametric study is conducted by varying the diameter, thickness, length, and mechanical properties of the column. This database is used to train, validate, and test machine learning models, Artificial Neural Network (ANN), Decision Trees for Regression (DTR), Gene Expression Programming (GEP) and Support Vector Machine Regression (SVMR). Thereafter, results are compared with finite element models and Eurocode 3 (EC3) to assess their accuracy. It was concluded that the EC3 models provided conservative predictions with an average Predicted-to-Actual ratio of 0.698 and Root Mean Square Error (RMSE) of 437.3. The machine learning models presented the highest level of accuracy. However, the SVMR model based on RBF kernel presented a better performance than the ANN, GEP and DTR machine learning models, and RMSE value for SVMR, ANN, GEP and DTR is 22.6, 31.6, 152.84 and 29.07, respectively. The GEP leads to the lowest level of accuracy among the other three machine learning models, yet, it is more accurate than EC3. The machine learning models were implemented in a user-friendly tool, which can be used for design purposes. • The paper studies behaviour of stainless steel CHS stub columns. • ANN, SVR, GEP and DTR machine learning algorithms are developed and validated. • Machine learning-based design approach for predicting the capacity is proposed. • A comparison with EC3 is presented to assess the performance of the models. [ABSTRACT FROM AUTHOR]

Accurate numerical analysis in geotechnical engineering heavily relies on the constitutive model and its parameters. The advanced constitutive model can describe the complex mechanical behaviors of soil that may involve a number of parameters. However, determining the values of constitutive parameters always relies on manual trial-and-error, which can be a time-consuming process and not conducive to widespread application. This paper presents an identification method that combines machine learning with search algorithm based on the laboratory and in-situ testing. Initially, the sensitivity of constitutive parameters was analyzed by investigating the effects of variations in soil overconsolidation and structural parameters on the results of triaxial and pressuremeter tests. Subsequently, the initial state parameter values and material control parameter ranges of the soil can be identified from the triaxial tests, this is achieved by using the neural network model. In order to accurately determine the parameters value, the numerical model was established based on in-situ pressuremeter test, and traversal algorithm was implemented to search for the optimal fit values within the range of material control parameters. Finally, the proposed identification method was applied to layers 3–5 of Shanghai clay, and the inverted parameters exhibited a good fit with the outcomes of triaxial tests and pressuremeter tests. The combination of laboratory and in-situ testing can enhance the reliability of obtaining constitutive parameters, and this method provides an insight into the parameters identification for advanced constitutive models. [ABSTRACT FROM AUTHOR]

Convolutional neural networks (CNNs) have gained immense popularity in recent years, finding their utility in diverse fields such as image recognition, natural language processing, and bio-informatics. Despite the remarkable progress made in deep learning theory, most studies on CNNs, especially in regression tasks, tend to heavily rely on the least squares loss function. However, there are situations where such learning algorithms may not suffice, particularly in the presence of heavy-tailed noises or outliers. This predicament emphasizes the necessity of exploring alternative loss functions that can handle such scenarios more effectively, thereby unleashing the true potential of CNNs. In this paper, we investigate the generalization error of deep CNNs with the rectified linear unit (ReLU) activation function for robust regression problems within an information-theoretic learning framework. Our study demonstrates that when the regression function exhibits an additive ridge structure and the noise possesses a finite p th moment, the empirical risk minimization scheme, generated by the maximum correntropy criterion and deep CNNs, achieves fast convergence rates. Notably, these rates align with the mini-max optimal convergence rates attained by fully connected neural network model with the Huber loss function up to a logarithmic factor. Additionally, we further establish the convergence rates of deep CNNs under the maximum correntropy criterion when the regression function resides in a Sobolev space on the sphere. [ABSTRACT FROM AUTHOR]

With the significant increase in photovoltaic (PV) electricity generation, more attention has been given to PV power forecasting. Indeed, accurate forecasting allows power grid operators to better schedule and dispatch their assets, such as energy storage systems and reserve. In this paper, a hybrid deep learning model and a convolutional neural network with memory is proposed, to provide intraday (2 h) solar irradiance forecasts using sequentially-collected images from public webcams. The performance of the proposed model is compared to those of a standard time-series forecast models, a linear regression as well as state-of-the-art neural networks. All models are trained and tested using images collected from two webcams on EPFL's campus for just over a year. The results show that the proposed method outperforms all other models and matches the state-of-the-art methodology while providing simplicity of implementation and efficient computation. • A novel method for estimating global horizontal irradiance is proposed. • The method uses images public webcams instead of all-sky cameras. • The method combines images from different cameras to improve forecasts' accuracy. • The method can be extended to include other types of data (meteorological data). • This simple method matches state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Many environmental variables, in particular, related to air or water quality, are measured in a limited number of points and often for a limited time span. This forbids the development of accurate models for interesting locations with missing or insufficient data and poses the question of whether a model developed for another measurement site can be reliably applied. Such a question is particularly critical when the model is entirely data-driven, such as a neural network. In this context, the paper proposes a procedure to evaluate the expected performance of an existing neural network model applied to a new unmonitored station. This transferability assessment is exemplified by the problem of forecasting ozone concentrations in different environmental settings around the Alpine Arc. Long Short-Term Memory (LSTM) neural network models are applied for predicting hourly concentrations in 20 stations of different types (urban, rural, and mountain). The analysis of the results allows us to determine the expected performance of such models in new cases and reduce the transferability uncertainty when the existing models can be partitioned into clusters. The LSTM models demonstrate the possibility of high accuracy in ozone forecasting at all sites. Given the significant impacts of this gas on human health and the environment, this can contribute to better decision-making and mitigation strategies for air pollution control. • We investigate the possibility of training a model in a site and reuse it elsewhere. • We introduce the concept of transferability matrix and transferability indicators. • The transfer learning reliability is enhanced by clustering the sites. • Ozone concentration forecasting for 20 locations in the Alpine region is considered. [ABSTRACT FROM AUTHOR]

With the increasing impact of climate change and relative sea level rise, low-lying coastal communities face growing risks from recurrent nuisance flooding and storm tides. Thus, timely and reliable predictions of coastal water levels are critical to resilience in vulnerable coastal areas. Over the past decade, there has been increasing interest in utilizing machine learning (ML) based models for emulation and prediction of coastal water levels. However, flood advisory systems still rely on running computationally demanding hydrodynamic models. To alleviate the computational burden, these physics-based models are either run at small scales with high resolution or at large scales with low resolution. While ML-based models are very fast, they face challenges in terms of ensuring reliability and ability to capture any surge levels. In this paper, we develop a deep neural network for spatiotemporal prediction of water levels in coastal areas of the Chesapeake Bay in the U.S. Our model relies on data from numerical weather prediction models as the atmospheric input and astronomical tide levels, while its outputs are time series of predicted water levels at several tide gauge locations across the Chesapeake Bay. We utilized a CNN-LSTM setting as the architecture of the model. The CNN part extracts the features from a sequence of gridded wind fields and fuses its output to several independent LSTM units. The LSTM units concatenate the atmospheric features with respective astronomical tide levels and produce water level time series. The novel contribution of the present work is in spatiotemporality and in prioritization of the physical relationships in the model to maintain a high analogy to hydrodynamic modeling, either in the network architecture or in the selection of predictors and predictands. The results show that this setting yields a strong performance in predicting coastal water levels that cause flooding from minor to major levels. We also show that the model stands up successfully to the rigorous comparison with a high-fidelity ADCIRC model, yielding mean RMSE and correlation coefficient of 14.3 cm and 0.94, respectively, in two extreme cases, versus 12.30 cm and 0.96 for the ADCIRC model. The results highlight the practical feasibility of employing fast yet inexpensive data-driven models for resilient coastal management. • A deep learning model is developed to predict a wide range of coastal water levels using wind and tides as input. • CNN layers extract features from the wind field and fuse them to independent LSTM units, creating spatiotemporality. • The model compares well with the data for different storm scenarios. • The model is comparable to or surpasses a high-fidelity hydrodynamic model while taking a fraction of a second to run. [ABSTRACT FROM AUTHOR]

[Display omitted] • Two bare electrodes are used for non-faradaic electrochemical impedance spectroscopy (EIS) data and machine learning. • Automated electro-mechanical fluidic system is built to prepare 148 solutions of LiCl, NaCl, and KCl and measure EIS data. • A data-augmentation model is proposed for non-faradaic voltage sweep EIS datafor deep neural network (DNN) training. • Ion types and their concentrations are detected successfully with machine learning. • Trained DNN models was successful with 4.51 mM average deviation from the 200 mM total solution concentration. Detecting ion types and their concentrations in multi-ion aqueous solutions poses a complex challenge with significant implications for sensing applications. This paper introduces an automated fluidic system using two bare electrodes to measure electrochemical impedance spectroscopy (EIS) data and evaluates deep neural network (DNN) for ion type and concentration detection. Additionally, a data-augmentation model is proposed for non-faradaic voltage sweep EIS data, intended for neural network training. To validate the effectiveness of our approach, prepared solutions featuring varying concentrations of LiCl, NaCl, and KCl are experimented. Impedance (Z) vs DC bias voltage (V) data, i.e., ZV-EIS are measured from −400 mV to + 400 mV at 9 different frequencies up to ∼ 200 kHz, for 148 automatically prepared solutions, having total salt concentrations up to 200 mM. DNN models are trained with augmented samples and successfully identified individual ions in test set solutions and their concentrations with 4.51 mM average deviation. The study delves into the nuanced impacts of factors such as sampling voltage window, and measurement frequency on the performance of the machine learning models, 8 mV and 20 Hz giving the most significant results. [ABSTRACT FROM AUTHOR]