Search

Generative adversarial networks (or GANs) are a specific deep learning architecture often used for different usages, such as data generation or image-to-image translation. In recent years, this structure has gained increased popularity and has been used in different fields. One area of expertise currently in vogue is the use of GANs to produce synthetic aperture radar (SAR) data, and especially expand training datasets for SAR automatic target recognition (ATR). In effect, the complex SAR image formation makes these kind of data rich in information, leading to the use of deep networks in deep learning-based methods. Yet, deep networks also require sufficient data for training. However, contrary to optical images, we generally do not have a substantial number of available SAR images because of their acquisition and labelling cost; GANs are then an interesting tool. Concurrently, how to improve explainability for SAR ATR deep neural networks and how to make their reasoning more transparent have been increasingly explored as model opacity deteriorates trust of users. This paper aims at reviewing how GANs are used with SAR images, but also giving perspectives on how GANs could be used to improve interpretability and explainability of SAR classifiers. [ABSTRACT FROM AUTHOR]

Neural network models are often used to analyse non-linear systems; here, in cases of small datasets, we review our complementary approach to deep learning with the purpose of highlighting the importance and roles (linear, non-linear or threshold) of certain variables (assumed as causal) in determining the behaviour of a target variable; this also allows us to make predictions for future scenarios of these causal variables. We present a neural tool endowed with an ensemble strategy and its applications to influence analyses in terms of pruning, attribution and future predictions (free code issued). We describe some case studies on climatic applications which show reliable results and the potentialities of our method for medical studies. The discovery of the importance and role (linear, non-linear or threshold) of causal variables and the possibility of applying the relationships found to future scenarios could lead to very interesting applications in medical research and the study and treatment of cancer, which are proposed in this paper. [ABSTRACT FROM AUTHOR]

Noise in large urban areas, which is mainly generated by road traffic and by the human activities carried out nearby and inside the area under study, is a relevant problem. The continuous exposure to high noise levels, in fact, can lead to several problems, largely documented in the scientific literature. The analysis and forecasting of the noise level in a given area are, then, fundamental for control and prevention, especially when field measurements present peculiar trends and slopes, which can be modeled with a Time Series Analysis approach. In this paper, a hybrid model is presented for the analysis and the forecasting of noise time series in urban areas: this technique is based on the application of a deterministic decomposition model followed in cascade by a predictor of the forecasting errors based on an artificial neural network. Two variants of the hybrid model have been implemented and presented. The time series used to calibrate and validate the model is composed of sound pressure level measurements detected on a busy road near the commercial port of an Italian city. The proposed hybrid model has been calibrated on a part of the entire time series and validated on the remaining part. Residuals and error analysis, together with a detailed statistical description of the simulated noise levels and error metrics describe in detail the method's performances and its limitations. [ABSTRACT FROM AUTHOR]

The management of large enterprises influences their efficiency and profitability. One of the important aspects is the appropriate management of electricity consumption used for production and daily operation. The problem becomes more complicated when you need to manage not one but a large complex of buildings with heterogeneous purposes. In the paper, we examine real-time series data of electrical energy consumption in a complex of heterogeneous buildings, including offices and warehouses, using time series analysis methods such as the Holt–Winters model and ARIMA/SARIMA model, and neural networks (Deep Neural Network, Recurrent Neural Network, and Long Short-Term Memory). Experimental research was performed on a dataset obtained from an energy consumption meter placed in the building complex, built in different periods, and equipped with a variety of automation devices. The data were collected over a period of four years 2018–2021 in the form of time series. Results show that classic models are good at predicting energy consumption in the mentioned type of buildings. The ARIMA model gave the best results—for buildings characterized by seasonality and trends the forecasts were almost perfect with actual values. [ABSTRACT FROM AUTHOR]

Intelligent control methodologies and artificial intelligence (AI) are essential components for the efficient management of energy storage modern systems, specifically those utilizing superconducting magnetic energy storage (SMES). Through the implementation of AI algorithms, SMES units are able to optimize their operations in real time, thereby maximizing energy efficiency. To have a more advanced understanding of this issue, DynamoMan is presented in this paper. For use with SMES systems, DynamoMan, an Artificial Neural Network (ANN)-tuned Fractional Order PID Brain Emotional Learning-Based Intelligent Controller (ANN-FOPID-BELBIC), has been developed. ANN tuning is employed to optimize the key settings of the reward/penalty generator of a BELBIC, which are important for its overall efficacy. Following this, DynamoMan is integrated into the SMES control system and compared to scenarios in which a BELBIC, PID, PI, and P are utilized. The findings indicate that DynamoMan performs considerably better than other models, demonstrating robust and control attributes alongside a considerably reduced period of settling time, especially when incorporated with the power grid. [ABSTRACT FROM AUTHOR]

This paper explores the application of multi-objective optimization techniques, including MOPSO, NSGA II, and SPEA2, to optimize the hyperparameters of artificial neural networks (ANNs) and support vector machines (SVMs) for predicting the physical properties of textile polymer composite materials (TPCMs). The optimization process utilizes data on the physical characteristics of the constituent fibers and fabrics used to manufacture these composites. By employing optimization algorithms, we aim to enhance the predictive accuracy of the ANN and SVM models, thereby facilitating the design and development of high-performance textile polymer composites. The effectiveness of the proposed approach is demonstrated through comparative analyses and validation experiments, highlighting its potential for optimizing complex material systems. [ABSTRACT FROM AUTHOR]

This paper presents a novel approach to sentiment analysis specifically customized for predicting stock market movements, bypassing the need for external dictionaries that are often unavailable for many languages. Our methodology directly analyzes textual data, with a particular focus on context-specific sentiment words within neural network models. This specificity ensures that our sentiment analysis is both relevant and accurate in identifying trends in the stock market. We employ sophisticated mathematical modeling techniques to enhance both the precision and interpretability of our models. Through meticulous data handling and advanced machine learning methods, we leverage large datasets from Twitter and financial markets to examine the impact of social media sentiment on financial trends. We achieved an accuracy exceeding 75%, highlighting the effectiveness of our modeling approach, which we further refined into a convolutional neural network model. This achievement contributes valuable insights into sentiment analysis within the financial domain, thereby improving the overall clarity of forecasting in this field. [ABSTRACT FROM AUTHOR]

This paper presents the results of a study on data preprocessing and modeling for predicting corrosion in water pipelines of a steel industrial plant. The use case is a cooling circuit consisting of both direct and indirect cooling. In the direct cooling circuit, water comes into direct contact with the product, whereas in the indirect one, it does not. In this study, advanced machine learning techniques, such as extreme gradient boosting and deep neural networks, have been employed for two distinct applications. Firstly, a virtual sensor was created to estimate the corrosion rate based on influencing process variables, such as pH and temperature. Secondly, a predictive tool was designed to foresee the future evolution of the corrosion rate, considering past values of both influencing variables and the corrosion rate. The results show that the most suitable algorithm for the virtual sensor approach is the dense neural network, with MAPE values of (25 ± 4)% and (11 ± 4)% for the direct and indirect circuits, respectively. In contrast, different results are obtained for the two circuits when following the predictive tool approach. For the primary circuit, the convolutional neural network yields the best results, with MAPE = 4% on the testing set, whereas for the secondary circuit, the LSTM recurrent network shows the highest prediction accuracy, with MAPE = 9%. In general, models employing temporal windows have emerged as more suitable for corrosion prediction, with model performance significantly improving with a larger dataset. [ABSTRACT FROM AUTHOR]

Demand response management (DRM) plays a crucial role in the prospective development of smart grids. The precise estimation of electricity demand for individual houses is vital for optimizing the operation and planning of the power system. Accurate forecasting of the required components holds significance as it can substantially impact the final cost, mitigate risks, and support informed decision-making. In this paper, a forecasting approach employing neural networks for smart grid demand-side management is proposed. The study explores various enhanced artificial neural network (ANN) architectures for forecasting smart grid consumption. The performance of the ANN approach in predicting energy demands is evaluated through a comparison with three statistical models: a time series model, an auto-regressive model, and a hybrid model. Experimental results demonstrate the ability of the proposed neural network framework to deliver accurate and reliable energy demand forecasts. [ABSTRACT FROM AUTHOR]

The planning, regulation and effectiveness of the product design process depend on various characteristics. Recently, bio-inspired collective intelligence approaches have been applied in this process in order to create more appealing product forms and optimize the design process. In fact, the use of neural network models in product form design analysis is a complex process, in which the type of network has to be determined, as well as the structure of the network layers and the neurons in them; the connection coefficients, inputs and outputs have to be explored; and the data have to be collected. In this paper, an impulsive discrete fractional neural network modeling approach is introduced for product design analysis. The proposed model extends and complements several existing integer-order neural network models to the generalized impulsive discrete fractional-order setting, which is a more flexible mechanism to study product form design. Since control and stability methods are fundamental in the construction and practical significance of a neural network model, appropriate impulsive controllers are designed, and practical Mittag-Leffler stability criteria are proposed. The Lyapunov function strategy is applied in providing the stability criteria and their efficiency is demonstrated via examples and a discussion. The established examples also illustrate the role of impulsive controllers in stabilizing the behavior of the neuronal states. The proposed modeling approach and the stability results are applicable to numerous industrial design tasks in which multi-agent systems are implemented. [ABSTRACT FROM AUTHOR]

Nowadays, trajectory control is a significant issue for unmanned micro aerial vehicles (MAVs) due to large disturbances such as wind and storms. Trajectory control is typically implemented using a proportional–integral–derivative (PID) controller. In order to achieve high accuracy in trajectory tracking, it is essential to set the PID gain parameters to optimum values. For this reason, separate gain values are set for roll, pitch and yaw movements before autonomous flight in quadrotor systems. Traditionally, this adjustment is performed manually or automatically in autotune mode. Given the constraints of narrow orchard corridors, the use of manual or autotune mode is neither practical nor effective, as the quadrotor system has to fly in narrow apple orchard corridors covered with hail nets. These reasons require the development of an innovative solution specific to quadrotor vehicles designed for constrained areas such as apple orchards. This paper recognizes the need for effective trajectory control in quadrotors and proposes a novel neural network-based approach to tuning the optimal PID control parameters. This new approach not only improves trajectory control efficiency but also addresses the unique challenges posed by environments with constrained locational characteristics. Flight simulations using the proposed neural network models have demonstrated successful trajectory tracking performance and highlighted the superiority of the feed-forward back propagation network (FFBPN), especially in latitude tracking within 7.52745 × 10−5 RMSE trajectory error. Simulation results support the high performance of the proposed approach for the development of automatic flight capabilities in challenging environments. [ABSTRACT FROM AUTHOR]

During the development of the nervous system, neuronal cells extend axons and dendrites that form complex neuronal networks, which are essential for transmitting and processing information. Understanding the physical processes that underlie the formation of neuronal networks is essential for gaining a deeper insight into higher-order brain functions such as sensory processing, learning, and memory. In the process of creating networks, axons travel towards other recipient neurons, directed by a combination of internal and external cues that include genetic instructions, biochemical signals, as well as external mechanical and geometrical stimuli. Although there have been significant recent advances, the basic principles governing axonal growth, collective dynamics, and the development of neuronal networks remain poorly understood. In this paper, we present a detailed analysis of nonlinear dynamics for axonal growth on surfaces with periodic geometrical patterns. We show that axonal growth on these surfaces is described by nonlinear Langevin equations with speed-dependent deterministic terms and gaussian stochastic noise. This theoretical model yields a comprehensive description of axonal growth at both intermediate and long time scales (tens of hours after cell plating), and predicts key dynamical parameters, such as speed and angular correlation functions, axonal mean squared lengths, and diffusion (cell motility) coefficients. We use this model to perform simulations of axonal trajectories on the growth surfaces, in turn demonstrating very good agreement between simulated growth and the experimental results. These results provide important insights into the current understanding of the dynamical behavior of neurons, the self-wiring of the nervous system, as well as for designing innovative biomimetic neural network models. [ABSTRACT FROM AUTHOR]

Nowadays, wireless communication technology is evolving towards high data rates, a low latency, and a high throughput to meet increasingly complex business demands. Key technologies in this direction include multiple-input multiple-output (MIMO) and orthogonal frequency division multiplexing (OFDM). This research is based on our previous work DMCNet. In this article, we focus on studying the deep learning (DL) application of neural networks to solve the reception of single-antenna OFDM signals. Specifically, in multi-antenna scenarios, the channel model is more complex compared to single-antenna cases. By leveraging the characteristics of DL, such as automatic learning of parameters using deep neural networks, we treat the reception process of MIMO-OFDM signals as a black box and utilize neural networks to accomplish the signal reception task. Moreover, we propose a data-driven multi-pilot convolution neural network for MIMO-OFDM receivers (DMCNet). By incorporating complex convolution and complex fully connected structures, we design a receiver network to recover the transmitted signals from the received signals. We validate the accuracy and robustness of DMCNet under different channel conditions, comparing the bit error rates with different schemes. Additionally, we discuss the factors influencing various channel effects. At the same time, we also propose a model-driven scheme, DMCNet-pro, which has a higher accuracy and fewer parameters in some scenarios. The experimental results demonstrate that the DL-based reception scheme exhibits promising feasibility in terms of accuracy and interference resistance when compared to traditional approaches. [ABSTRACT FROM AUTHOR]

Credit risk refers to the possibility of borrower default, and its assessment is crucial for maintaining financial stability. However, the journey of credit risk data generation is often gradual, and machine learning techniques may not be readily applicable for crafting evaluations at the initial stage of the data accumulation process. This article proposes a credit risk modeling methodology, TED-NN, that first constructs an indicator system based on expert experience, assigns initial weights to the indicator system using the Analytic Hierarchy Process, and then constructs a neural network model based on the indicator system to achieve a smooth transition from an empirical model to a data-driven model. TED-NN can automatically adapt to the gradual accumulation of data, which effectively solves the problem of risk modeling and the smooth transition from no to sufficient data. The effectiveness of this methodology is validated through a specific case of credit risk assessment. Experimental results on a real-world dataset demonstrate that, in the absence of data, the performance of TED-NN is equivalent to the AHP and better than untrained neural networks. As the amount of data increases, TED-NN gradually improves and then surpasses the AHP. When there are sufficient data, its performance approaches that of a fully data-driven neural network model. [ABSTRACT FROM AUTHOR]

Neural networks have been extensively applied to a variety of tasks, achieving astounding results. Applying neural networks in the scientific field is an important research direction that is gaining increasing attention. In scientific applications, the scale of neural networks is generally moderate size, mainly to ensure the speed of inference during application. Additionally, comparing neural networks to traditional algorithms in scientific applications is inevitable. These applications often require rapid computations, making the reduction in neural network sizes increasingly important. Existing work has found that the powerful capabilities of neural networks are primarily due to their nonlinearity. Theoretical work has discovered that under strong nonlinearity, neurons in the same layer tend to behave similarly, a phenomenon known as condensation. Condensation offers an opportunity to reduce the scale of neural networks to a smaller subnetwork with a similar performance. In this article, we propose a condensation reduction method to verify the feasibility of this idea in practical problems, thereby validating existing theories. Our reduction method can currently be applied to both fully connected networks and convolutional networks, achieving positive results. In complex combustion acceleration tasks, we reduced the size of the neural network to 41.7% of its original scale while maintaining prediction accuracy. In the CIFAR10 image classification task, we reduced the network size to 11.5% of the original scale, still maintaining a satisfactory validation accuracy. Our method can be applied to most trained neural networks, reducing computational pressure and improving inference speed. [ABSTRACT FROM AUTHOR]

Driving style and road traffic play pivotal roles in the development of smart cities, influencing traffic flow, safety, and environmental sustainability. This study presents an innovative approach for detecting road traffic conditions and driving styles using On-Board Diagnostics (OBD) data and smartphone sensors. This approach offers an inexpensive implementation of prediction, as it utilizes existing vehicle data without requiring additional setups. Two Artificial Neural Network (ANN) models were employed: the first utilizes a forward neural network architecture, while the second leverages bootstrapping or bagging neural networks to enhance detection accuracy for low-labeled classes. Support Vector Machine (SVM) is implemented to serve as a baseline for comparison. Experimental results demonstrate that ANNs exhibit significant improvements in detection accuracy compared to SVM. Moreover, the neural network with bagging model showcases enhanced recall values and a substantial improvement in accurately detecting instances belonging to low-labeled classes in both driving style road traffic. [ABSTRACT FROM AUTHOR]

First-order algorithms have long dominated the training of deep neural networks, excelling in tasks like image classification and natural language processing. Now there is a compelling opportunity to explore alternatives that could outperform current state-of-the-art results. From the estimation theory, the Extended Kalman Filter (EKF) arose as a viable alternative and has shown advantages over backpropagation methods. Current computational advances offer the opportunity to review algorithms derived from the EKF, almost excluded from the training of convolutional neural networks. This article revisits an approach of the EKF with decoupling and it brings the Fully Decoupled Extended Kalman Filter (FDEKF) for training convolutional neural networks in image classification tasks. The FDEKF is a second-order algorithm with some advantages over the first-order algorithms, so it can lead to faster convergence and higher accuracy, due to a higher probability of finding the global optimum. In this research, experiments are conducted on well-known datasets that include Fashion, Sports, and Handwritten Digits images. The FDEKF shows faster convergence compared to other algorithms such as the popular Adam optimizer, the sKAdam algorithm, and the reduced extended Kalman filter. Finally, motivated by the finding of the highest accuracy of FDEKF with images of natural scenes, we show its effectiveness in another experiment focused on outdoor terrain recognition. [ABSTRACT FROM AUTHOR]

The accurate classification of brain tumors is an important step for early intervention. Artificial intelligence (AI)-based diagnostic systems have been utilized in recent years to help automate the process and provide more objective and faster diagnosis. This work introduces an enhanced AI-based architecture for improved brain tumor classification. We introduce a hybrid architecture that integrates vision transformer (ViT) and deep neural networks to create an ensemble classifier, resulting in a more robust brain tumor classification framework. The analysis pipeline begins with preprocessing and data normalization, followed by extracting three types of MRI-derived information-rich features. The latter included higher-order texture and structural feature sets to harness the spatial interactions between image intensities, which were derived using Haralick features and local binary patterns. Additionally, local deeper features of the brain images are extracted using an optimized convolutional neural networks (CNN) architecture. Finally, ViT-derived features are also integrated due to their ability to handle dependencies across larger distances while being less sensitive to data augmentation. The extracted features are then weighted, fused, and fed to a machine learning classifier for the final classification of brain MRIs. The proposed weighted ensemble architecture has been evaluated on publicly available and locally collected brain MRIs of four classes using various metrics. The results showed that leveraging the benefits of individual components of the proposed architecture leads to improved performance using ablation studies. [ABSTRACT FROM AUTHOR]

The fourth industrial revolution has transformed the industry, with information technology playing a crucial role in this shift. The increasing digitization of industrial systems demands efficient sensing and control methods, giving rise to soft sensors that have the potential to replace traditional physical sensors in order to reduce costs and enhance efficiency. This study explores the implementation of an artificial neural network (ANN) based soft sensor model in a water supply system to predict flow rates within the system. The soft sensor is centered on a Long Short-Term Memory (LSTM) artificial neural network model using Monte Carlo dropout to reduce uncertainty and improve estimation performance. Based on the results of this work, it is concluded that the proposed soft sensor (with Monte Carlo dropout) can predict flow rates more precisely, contributing to the reduction in water losses, as well as cost savings. This approach offers a valuable solution for minimizing water losses and ensuring the efficient use of this vital resource. Regarding the use of soft sensors based on LSTM neural networks with a careful choice of Monte Carlo dropout parameters, when compared to the multilayer perceptron model, the LSTM model with Monte Carlo dropout showed better mean absolute error, root mean square error, and coefficient of determination: 0.2450, 0.3121, and 0.996437 versus 0.2556, 0.3522, and 0.9954. Furthermore, this choice of Monte Carlo dropout parameters allowed us to achieve an LSTM network model capable of reducing uncertainty to 1.8290, keeping the error metrics also at low levels. [ABSTRACT FROM AUTHOR]

Understanding how price-volume information determines future price movement is important for market makers who frequently place orders on both buy and sell sides, and for traders to split meta-orders to reduce price impact. Given the complex non-linear nature of the problem, we consider the prediction of the movement direction of the mid-price on an option order book, using machine learning tools. The applicability of such tools on the options market is currently missing. On an intraday tick-level dataset of options on an exchange traded fund from the Chinese market, we apply a variety of machine learning methods, including decision tree, random forest, logistic regression, and long short-term memory neural network. As machine learning models become more complex, they can extract deeper hidden relationship from input features, which classic market microstructure models struggle to deal with. We discover that the price movement is predictable, deep neural networks with time-lagged features perform better than all other simpler models, and this ability is universal and shared across assets. Using an interpretable model-agnostic tool, we find that the first two levels of features are the most important for prediction. The findings of this article encourage researchers as well as practitioners to explore more sophisticated models and use more relevant features. [ABSTRACT FROM AUTHOR]

This article presents an innovative method for efficiently synthesizing radiation patterns by combining the Taguchi method and neural networks, validating the results on a ten-element antenna array. The Taguchi method aims to minimize product and process variability, while neural networks are used to model the relationship between antenna design parameters and radiation pattern characteristics. This approach utilizes Taguchi parameters as inputs for the neural network, which is then trained on a dataset generated by the Taguchi method. After training, the network is validated using a real ten-element antenna array. Analytical results demonstrate that this method enables efficient synthesis of radiation patterns, with a significant reduction in computation time compared to traditional approaches. Furthermore, validation on the antenna array confirms the accuracy and robustness of the approach, showing a high correlation between the performance predicted by the neural network model and actual measurements on the antenna array. In summary, our article highlights that the combined use of the Taguchi method and neural networks, with validation on a real antenna array, offers a promising approach for efficient synthesis of antenna radiation patterns. This approach combines speed, accuracy, and reliability in antenna system design. [ABSTRACT FROM AUTHOR]

A data-driven aerodynamic modeling method is proposed to address the problem that traditional modeling methods based on physical mechanisms cannot fully represent the special aerodynamic characteristics of tiltrotor evtol aircraft. By analyzing the uniquely complex aerodynamic characteristics of electric vertical take-off and landing (evtol) aircraft, an MLP neural network model has been constructed that reflects the coupling characteristics between influencing factors. Using the XV15 wind tunnel test data, a dataset was constructed, and the neural network model was trained and validated. Simulation results show that the selected data-driven method can accurately predict the aerodynamic characteristics of the longitudinal transition phase of the tiltrotor evtol. [ABSTRACT FROM AUTHOR]

The finite element numerical simulation results of deep pit deformation are greatly influenced by soil layer parameters, which are crucial in determining the accuracy of deformation prediction results. This study employs the orthogonal experimental design to determine the combinations of various soil layer parameters in deep pits. Displacement values at specific measurement points were calculated using PLAXIS 3D under these varying parameter combinations to generate training samples. The nonlinear mapping ability of the Back Propagation (BP) neural network and Particle Swarm Optimization (PSO) were used for sample global optimization. Combining these with actual onsite measurements, we inversely calculate soil layer parameter values to update the input parameters for PLAXIS 3D. This allows us to conduct dynamic deformation prediction studies throughout the entire excavation process of deep pits. The results indicate that the use of the PSO-BP neural network for inverting soil layer parameters effectively enhances the convergence speed of the BP neural network model and avoids the issue of easily falling into local optimal solutions. The use of PLAXIS 3D to simulate the excavation process of the pit accurately reflects the dynamic changes in the displacement of the retaining structure, and the numerical simulation results show good agreement with the measured values. By updating the model parameters in real-time and calculating the pile displacement under different working conditions, the absolute errors between the measured and simulated values of pile top vertical displacement and pile body maximum horizontal displacement can be effectively reduced. This suggests that inverting soil layer parameters using measured values from working conditions is a feasible method for dynamically predicting the excavation process of the pit. The research results have some reference value for the selection of soil layer parameters in similar areas. [ABSTRACT FROM AUTHOR]

This study introduces a novel approach for fault classification in bearing components utilizing raw accelerometer data. By employing various neural network models, including deep learning architectures, we bypass the traditional preprocessing and feature-extraction stages, streamlining the classification process. Utilizing the Case Western Reserve University (CWRU) bearing dataset, our methodology demonstrates remarkable accuracy, particularly in deep learning networks such as the three variant convolutional neural networks (CNNs), achieving above 98% accuracy across various loading levels, establishing a new benchmark in fault-detection efficiency. Notably, data exploration through principal component analysis (PCA) and t-distributed stochastic neighbor embedding (t-SNE) provided valuable insights into feature relationships and patterns, aiding in effective fault detection. This research not only proves the efficacy of neural network classifiers in handling raw data but also opens avenues for more straightforward yet effective diagnostic methods in machinery health monitoring. These findings suggest significant potential for real-world applications, offering a faster yet reliable alternative to conventional fault-classification techniques. [ABSTRACT FROM AUTHOR]

Carbonation is one of the critical issues affecting the durability of reinforced concrete. Evaluating the depth of concrete carbonation is of great significance for ensuring the quality and safety of construction projects. In recent years, various prediction algorithms have been developed for evaluating concrete carbonation depth. This article provides a detailed overview of the existing prediction models for concrete carbonation depth. According to the data processing methods used in the model, the existing prediction models can be divided into mathematical curve models and machine learning models. The machine learning models can be further divided into the following categories: artificial neural network model, decision tree model, support vector machine model, and combined models. The basic idea of the mathematical curve model is to directly establish the relationship between the carbonation depth and age of concrete by using certain function curves. The advantage of the mathematical curve model is that only a small amount of experimental data is needed for curve fitting, which is very convenient for engineering applications. The limitation of the curve model is that it can only consider the influence of some factors on the carbonation depth of concrete, and the prediction accuracy cannot be guaranteed. The advantage of using the machine learning model to predict the carbonation depth of concrete is that many factors can be considered at the same time. When there are sufficient experimental data, the trained machine learning model can give more accurate prediction results than the mathematical curve model. The main defect of the machine learning model is that it needs a lot of experimental data as training samples, so it is not as convenient as the mathematical curve model in engineering applications. A future research direction may be to combine a machine learning model with a mathematical curve model to evaluate the carbonation depth of concrete more accurately. [ABSTRACT FROM AUTHOR]

Machine learning is a widespread technology that plays a crucial role in digitalisation and aims to explore rules and patterns in large datasets to autonomously solve non-linear problems, taking advantage of multiple source data. Due to its versatility, machine learning can be applied to agriculture. Better crop management, plant health assessment, and early disease detection are some of the main challenges facing the agricultural sector. Plant phenotyping can play a key role in addressing these challenges, especially when combined with machine learning techniques. Therefore, this study reviews available scientific literature on the applications of machine learning algorithms in plant phenotyping with a specific focus on sunflowers. The most common algorithms in the agricultural field are described to emphasise possible uses. Subsequently, the overview highlights machine learning application on phenotyping in three primaries areas: crop management (i.e., yield prediction, biomass estimation, and growth stage monitoring), plant health (i.e., nutritional status and water stress), and disease detection. Finally, we focus on the adoption of machine learning techniques in sunflower phenotyping. The role of machine learning in plant phenotyping has been thoroughly investigated. Artificial neural networks and stacked models seems to be the best way to analyse data. [ABSTRACT FROM AUTHOR]

A dendritic neuron model (DNM) is a deep neural network model with a unique dendritic tree structure and activation function. Effective initialization of its model parameters is crucial for its learning performance. This work proposes a novel initialization method specifically designed to improve the performance of DNM in classifying high-dimensional data, notable for its simplicity, speed, and straightforward implementation. Extensive experiments on benchmark datasets show that the proposed method outperforms traditional and recent initialization methods, particularly in datasets consisting of high-dimensional data. In addition, valuable insights into the behavior of DNM during training and the impact of initialization on its learning performance are provided. This research contributes to the understanding of the initialization problem in deep learning and provides insights into the development of more effective initialization methods for other types of neural network models. The proposed initialization method can serve as a reference for future research on initialization techniques in deep learning. [ABSTRACT FROM AUTHOR]

The Delta robot is an over-actuated parallel robot with highly nonlinear kinematics and dynamics. Designing the control for a Delta robot to carry out various operations is a challenging task. Various advanced control algorithms, such as adaptive control, sliding mode control, and model predictive control, have been investigated for trajectory tracking of the Delta robot. However, these control algorithms require a reliable input–output model of the Delta robot. To address this issue, we have created a control-affine neural network model of the Delta robot with stepper motors. This is a completely data-driven model intended for control design consideration and is not derivable from Newton's law or Lagrange's equation. The neural networks are trained with randomly sampled data in a sufficiently large workspace. The sliding mode control for trajectory tracking is then designed with the help of the neural network model. Extensive numerical results are obtained to show that the neural network model together with the sliding mode control exhibits outstanding performance, achieving a trajectory tracking error below 5 cm on average for the Delta robot. Future work will include experimental validation of the proposed neural network input–output model for control design for the Delta robot. Furthermore, transfer learnings can be conducted to further refine the neural network input–output model and the sliding mode control when new experimental data become available. [ABSTRACT FROM AUTHOR]

Currently, direct surveys are used less and less to assess satisfaction with the quality of user services. One of the most effective methods to solve this problem is to extract user attitudes from social media texts using natural language text mining. This approach helps to obtain more objective results by increasing the representativeness and independence of the sample of service consumers being studied. The purpose of this article is to improve existing methods and test a method for classifying Russian-language text reviews of patients about the work of medical institutions and doctors, extracted from social media resources. The authors developed a hybrid method for classifying text reviews about the work of medical institutions and tested machine learning methods using various neural network architectures (GRU, LSTM, CNN) to achieve this goal. More than 60,000 reviews posted by patients on the two most popular doctor review sites in Russia were analysed. Main results: (1) the developed classification algorithm is highly efficient—the best result was shown by the GRU-based architecture (val_accuracy = 0.9271); (2) the application of the method of searching for named entities to text messages after their division made it possible to increase the classification efficiency for each of the classifiers based on the use of artificial neural networks. This study has scientific novelty and practical significance in the field of social and demographic research. To improve the quality of classification, in the future, it is planned to expand the semantic division of the review by object of appeal and sentiment and take into account the resulting fragments separately from each other. [ABSTRACT FROM AUTHOR]

Measuring oculomotor abnormalities in human subjects is challenging due to the delicate spatio-temporal nature of the oculometric measures (OMs) used to assess eye movement abilities. Some OMs require a gaze estimation accuracy of less than 2 degrees and a sample rate that enables the detection of movements lasting less than 100 ms. While past studies and applications have used dedicated and limiting eye tracking devices to extract OMs, recent advances in imaging sensors and computer vision have enabled video-based gaze detection. Here, we present a self-calibrating neural network model for gaze detection that is suitable for oculomotor abnormality measurement applications. The model considers stimuli target locations while the examined subjects perform visual tasks and calibrate its gaze estimation output in real time. The model was validated in a clinical trial and achieved an axial accuracy of 0.93 degrees and 1.31 degrees for horizontal and vertical gaze estimation locations, respectively, as well as an absolute accuracy of 1.80 degrees. The performance of the proposed model enables the extraction of OMs using affordable and accessible setups—such as desktop computers and laptops—without the need to restrain the patient's head or to use dedicated equipment. This newly introduced approach may significantly ease patient burden and improve clinical results in any medical field that requires eye movement measurements. [ABSTRACT FROM AUTHOR]

Simple Summary: Stimulated Raman Histology (SRH) is a technique that uses laser light to create detailed images of tissues without the need for traditional staining. This study aimed to use deep learning to classify oral squamous cell carcinoma (OSCC) and different non-malignant tissue types using SRH images. The performances of the classifications between SRH images and the original images obtained from stimulated Raman scattering (SRS) were compared. A deep learning model was trained on 64 images and tested on 16, showing that it could effectively identify tissue types during surgery, potentially speeding up decision making in oral cancer surgery. Stimulated Raman Histology (SRH) employs the stimulated Raman scattering (SRS) of photons at biomolecules in tissue samples to generate histological images. Subsequent pathological analysis allows for an intraoperative evaluation without the need for sectioning and staining. The objective of this study was to investigate a deep learning-based classification of oral squamous cell carcinoma (OSCC) and the sub-classification of non-malignant tissue types, as well as to compare the performances of the classifier between SRS and SRH images. Raman shifts were measured at wavenumbers k1 = 2845 cm−1 and k2 = 2930 cm−1. SRS images were transformed into SRH images resembling traditional H&E-stained frozen sections. The annotation of 6 tissue types was performed on images obtained from 80 tissue samples from eight OSCC patients. A VGG19-based convolutional neural network was then trained on 64 SRS images (and corresponding SRH images) and tested on 16. A balanced accuracy of 0.90 (0.87 for SRH images) and F1-scores of 0.91 (0.91 for SRH) for stroma, 0.98 (0.96 for SRH) for adipose tissue, 0.90 (0.87 for SRH) for squamous epithelium, 0.92 (0.76 for SRH) for muscle, 0.87 (0.90 for SRH) for glandular tissue, and 0.88 (0.87 for SRH) for tumor were achieved. The results of this study demonstrate the suitability of deep learning for the intraoperative identification of tissue types directly on SRS and SRH images. [ABSTRACT FROM AUTHOR]

The transit method allows the detection and characterization of planetary systems by analyzing stellar light curves. Convolutional neural networks appear to offer a viable solution for automating these analyses. In this research, two 1D convolutional neural network models, which work with simulated light curves in which transit-like signals were injected, are presented. One model operates on complete light curves and estimates the orbital period, and the other one operates on phase-folded light curves and estimates the semimajor axis of the orbit and the square of the planet-to-star radius ratio. Both models were tested on real data from TESS light curves with confirmed planets to ensure that they are able to work with real data. The results obtained show that 1D CNNs are able to characterize transiting exoplanets from their host star's detrended light curve and, furthermore, reducing both the required time and computational costs compared with the current detection and characterization algorithms. [ABSTRACT FROM AUTHOR]

The intent of this work was to investigate the feasibility of developing machine learning models for calculating values of airplane configuration design variables when provided time-series, mission-informed performance data. Shallow artificial neural networks were developed, trained, and tested using data pertaining to the blended wing body (BWB) class of aerospace vehicles. Configuration design parameters were varied using a Latin-hypercube sampling scheme. These data were used by a parametric-based BWB configuration generator to create unique BWBs. Performance for each configuration was obtained via a performance estimation tool. Training and testing of neural networks was conducted using a K-fold cross-validation scheme. A random forest approach was used to determine the values of predicted configuration design variables when evaluating neural network accuracy across a blended wing body vehicle survey. The results demonstrated the viability of leveraging neural networks in mission-dependent, inverse design of blended wing bodies. In particular, feed-forward, shallow neural network architectures yielded significantly better predictive accuracy than cascade-forward architectures. Furthermore, for both architectures, increasing the number of neurons in the hidden layer increased the prediction accuracy of configuration design variables by at least 80%. [ABSTRACT FROM AUTHOR]

The incorporation of renewable energy systems in the world energy system has been steadily increasing during the last few years. In terms of the building sector, the usual consumers are becoming increasingly prosumers, and the trend is that communities of energy, whose households share produced electricity, will increase in number in the future. Another observed tendency is that the aggregator (the entity that manages the community) trades the net community energy in public energy markets. To accomplish economically good transactions, accurate and reliable forecasts of the day-ahead net energy community must be available. These can be obtained using an ensemble of multi-step shallow artificial neural networks, with prediction intervals obtained by the covariance algorithm. Using real data obtained from a small energy community of four houses located in the southern region of Portugal, one can verify that the deterministic and probabilistic performance of the proposed approach is at least similar, typically better than using complex, deep models. [ABSTRACT FROM AUTHOR]

In order to enhance the retrieval accuracy of cloud top height (CTH) from MODIS data, neural network models were employed based on Cloud-Aerosol Lidar with Orthogonal Polarization (CALIOP) data. Three types of methods were established using MODIS inputs: cloud parameters, calibrated radiance, and a combination of both. From a statistical standpoint, models with combination inputs demonstrated the best performance, followed by models with calibrated radiance inputs, while models relying solely on calibrated radiance had poorer applicability. This work found that cloud top pressure (CTP) and cloud top temperature played a crucial role in CTH retrieval from MODIS data. However, within the same type of models, there were slight differences in the retrieved results, and these differences were not dependent on the quantity of input parameters. Therefore, the model with fewer inputs using cloud parameters and calibrated radiance was recommended and employed for individual case studies. This model produced results closest to the actual cloud top structure of the typhoon and exhibited similar cloud distribution patterns when compared with the Cloud-Aerosol Lidar and Infrared Pathfinder Satellite Observation (CALIPSO) CTHs from a climatic statistical perspective. This suggests that the recommended model has good applicability and credibility in CTH retrieval from MODIS images. This work provides a method to improve accurate CTHs from MODIS data for better utilization. [ABSTRACT FROM AUTHOR]

In this study, we analyzed in situ data from the years 2018–2022 encompassing entire forest plantations in Poland. Based on data regarding stand density and the occurrence of fungal, water-related, climate-related, fire, and insect factors that may intensify with climate changes, we determined the correlation between their occurrence and the decline in wood increments for six tree species: pine, birch, oak, spruce, beech, and alder. Subsequently, we identified age intervals in which the species–factor interaction exhibited statistically significant effects. Next, we developed neural network models for short-term wood increment predictions. Utilizing these models, we estimated a reduction in wood supply harvested in accordance with the plans for the years 2023–2025 assuming a tenfold greater intensity of factors than in 2022. Findings indicate: birch: water-related factors may reduce wood production by 0.1%–0.2%. This aligns with previous research linking drought to birch wood decline, highlighting its sensitivity to water-related issues. Oak: fungal and insect factors could decrease wood production by up to 0.1%. Prior studies emphasize the significant influence of fungal diseases on oak health and regeneration, as well as the impact of insect infestation on wood production. Alder: water-related factors may lead to a slight reduction in wood production, approximately 0.02%. The impact is significant within specific age ranges, indicating potential effects on harvesting. Pine: water- and climate-related factors may result in up to a 0.05% reduction in wood production. Pine, a key forest-forming species in Poland, is notably sensitive to these factors, especially as it nears harvesting age. Spruce: insects, fungi, and climate-related factors could lead to a reduction in wood production of up to 0.2%–0.3%. Analyses demonstrate sensitivity, resulting in a noticeable growth differential compared to the typical rate. Short-term predictions based on neural networks were developed, acknowledging their suitability for short-term forecasts due to uncertainties regarding long-term factor impacts. Additionally, our study discussed modeling wood increments in divisions well below the harvesting time, emphasizing that the influence of current and 2023–2025 factors on wood increments and supply may only manifest several decades from now. These results imply important indications for the economic and financial performance of the wood industry. [ABSTRACT FROM AUTHOR]