Application Of Neural Networks Research Articles

Variation in forest root image annotation by experts, novices, and AI

BackgroundThe manual study of root dynamics using images requires huge investments of time and resources and is prone to previously poorly quantified annotator bias. Artificial intelligence (AI) image-processing tools have been successful in overcoming limitations of manual annotation in homogeneous soils, but their efficiency and accuracy is yet to be widely tested on less homogenous, non-agricultural soil profiles, e.g., that of forests, from which data on root dynamics are key to understanding the carbon cycle. Here, we quantify variance in root length measured by human annotators with varying experience levels. We evaluate the application of a convolutional neural network (CNN) model, trained on a software accessible to researchers without a machine learning background, on a heterogeneous minirhizotron image dataset taken in a multispecies, mature, deciduous temperate forest.ResultsLess experienced annotators consistently identified more root length than experienced annotators. Root length annotation also varied between experienced annotators. The CNN root length results were neither precise nor accurate, taking ~ 10% of the time but significantly overestimating root length compared to expert manual annotation (p = 0.01). The CNN net root length change results were closer to manual (p = 0.08) but there remained substantial variation.ConclusionsManual root length annotation is contingent on the individual annotator. The only accessible CNN model cannot yet produce root data of sufficient accuracy and precision for ecological applications when applied to a complex, heterogeneous forest image dataset. A continuing evaluation and development of accessible CNNs for natural ecosystems is required.

Application of Artificial Neural Networks for Predicting Cooking Dynamics in Industrial Sesame Seed Oil Extraction

Application of Artificial Neural Networks for Predicting Cooking Dynamics in Industrial Sesame Seed Oil Extraction

Redshift Prediction with Images for Cosmology Using a Bayesian Convolutional Neural Network with Conformal Predictions

In the emerging era of big data astrophysics, large-scale extragalactic surveys will soon provide high-quality imaging for billions of celestial objects to answer major questions in astrophysics such as the nature of dark matter and dark energy. Precision cosmology with surveys requires accurate photometric redshift (photo-z) estimation with well-constrained uncertainties as inputs for weak lensing models to measure cosmological parameters. Machine learning methods have shown promise in optimizing the information gained from galaxy images in photo-z estimation; however, many of these methods are limited in their ability to estimate accurate uncertainties. In this work, we present one of the first applications of Bayesian convolutional neural networks (BCNNs) for photo-z estimation and uncertainties. In addition, we use conformal mapping to calibrate the photo-z uncertainties to achieve good statistical coverage. We use the public GalaxiesML data set of ∼300k galaxies from the Hyper Suprime-Cam survey containing five-band photometric images and known spectroscopic redshifts from 0 < z < 4. We find that the performance is much improved when using images compared to photometry, with the BCNN achieving 0.098 rms error, a standard outlier rate of 3.9%, a 3σ outlier rate of 4.5%, and a bias of 0.0007. The performance drops significantly beyond z > 1.5 due to the relative lack of training data beyond those redshifts. This investigation demonstrates the power of using images directly and we advocate that future photo-z analysis of large-scale surveys include galaxy images.

Development of a hydroponic device using potassium Ion-Selective electrode and neural network technology

The rapid development of modern agricultural biotechnology and information technology has become a key driver of modern agricultural growth. The demand for ion detection is prevalent in all aspects of agriculture. This study details the research on an ion sensor agricultural system using potassium (K) ion-selective electrodes (ISEs). The main emphasis is on the application of artificial neural networks (ANNs) for driving ISE development of accuracy. ISEs based on solid contact with metal oxides, specifically manganese dioxide, are studied. Moreover, the design details of an ion signal acquisition device using the NI-9205 acquisition card and LabVIEW are presented. Finally, based on experimental results of nutrient solution samples, ANNs show better performance than the multiple linear regression method. The mean relative error of K-ISE detection was maintained within 4%. This study thoroughly discusses ISE technology to promote its adoption in agriculture.

Потенциальные угрозы, связанные с применением искусственного интеллекта в преступных действиях

The article is devoted to the issues of assessing the threats associated with the use of artificial intelligence in the implementation of criminal actions, taking into account the rapid development of technical capabilities and areas of application of modern neural networks, since the degree of readiness for counteraction directly affects the effectiveness of such counteraction and the efficiency of its application.

Recent advances in electrical engineering: exploring graph neural networks for weather prediction in data-scarce environments

Abstract In regions like Nepal, characterized by diverse geography, missing weather data poses a significant challenge for traditional imputation methods. These methods often struggle to capture the complexities of dynamic environments adequately. To overcome this challenge, our study explores the application of graph neural networks for weather prediction in data-scarce environments. Our approach entails the development of specialized models tailored to accommodate the non-Euclidean topology inherent in weather data. This framework encompasses preprocessing, graph representation, feature selection, and imputation techniques to predict missing atmospheric variables. The adaptability of our models to intricate geography ensures more precise representations of weather conditions. Our research demonstrates the efficacy of these models through rigorous testing on a substantial dataset spanning four decades since 1981. By harnessing state-of-the-art graph neural network technology, our study aims to address existing gaps in weather data prediction, leading to improved historical weather forecasting accuracy. Ultimately, this advancement contributes to enhanced meteorological understanding and forecasting precision in data-scarce regions.

Design, Analysis, and Application of a Discrete Error Redefinition Neural Network for Time-Varying Quadratic Programming.

Time-varying quadratic programming (TV-QP) is widely used in artificial intelligence, robotics, and many other fields. To solve this important problem, a novel discrete error redefinition neural network (D-ERNN) is proposed. By redefining the error monitoring function and discretization, the proposed neural network is superior to some traditional neural networks in terms of convergence speed, robustness, and overshoot. Compared with the continuous ERNN, the proposed discrete neural network is more suitable for computer implementation. Unlike continuous neural networks, this article also analyzes and proves how to select the parameters and step size of the proposed neural networks to ensure the reliability of the network. Moreover, how to achieve the discretization of the ERNN is presented and discussed. The convergence of the proposed neural network without disturbance is proven, and bounded time-varying disturbances can be resisted in theory. Furthermore, the comparison results with other related neural networks show that the proposed D-ERNN has a faster convergence speed, better antidisturbance ability, and lower overshoot.

Dispatch of Decentralized Energy Systems using Artificial Neural Networks: A Comparative Analysis with Emphasis on Training Methods

Due to the availability of flexibility, Decentralized Energy Systems (DES) play a central role in integrating renewable energies. To efficiently utilize renewable energy, dispatchable components must be operated to bridge the time gap between inflexible supply and energy demand. Due to the large number of energy converters, energy storage systems, and flexible consumers, there are many ways to achieve this. Conventional rule-based dispatch strategies often reach their limits here, and optimized dispatch strategies (e.g., model predictive control or the optimal dispatch) are usually based on very good forecasts. Reinforcement learning, particularly the application of Artificial Neural Networks (ANN), offers the possibility to learn complex decision-making processes. Since long training times are required for this, an efficient training framework is needed. The present paper proposes different training methods to learn an ANN-based dispatch strategy. In Method I, the ANN attempts to learn the solution to the corresponding optimal dispatch problem. In method II, the energy system model is simulated during the training to compute the observation state and operating costs resulting from the ANN-based dispatch. Method III uses the fast executable Method I solution as a warm-up solution for the computationally expensive training with Method II. In the present paper, a model-based analysis compares the different ANN-based dispatch strategies with rule-based dispatch strategies, model predictive dispatch (MPC), and optimal dispatch regarding their computational efficiency and the resulting operating costs. The dispatch strategies are compared based on three case studies with different system topologies for which training and test data are applied.Training method I proved to be non-competitive. However, training methods II and III significantly outperformed rule-based dispatch strategies across all case studies for both training and test data sets. Notably, methods II and III also surpassed MPC-based dispatch strategies under high and medium uncertainty forecasts for the training data in the first two case studies. In contrast, MPC-based dispatch was superior in the third case study, likely due to the higher system’s complexity and in the test data set due to the methodological advantage of being optimized for each specific data set. The effectiveness of training method III depends on the performance of the warm-up training with method I: warm-up is beneficial only if this results in an already promising dispatch (as seen in case study two). Otherwise, training method II proves more effective, as observed in case studies one and three.

Data Assimilation and Parameter Identification for Water Waves Using the Nonlinear Schrödinger Equation and Physics-Informed Neural Networks

The measurement of deep water gravity wave elevations using in situ devices, such as wave gauges, typically yields spatially sparse data due to the deployment of a limited number of costly devices. This sparsity complicates the reconstruction of the spatio-temporal extent of surface elevation and presents an ill-posed data assimilation problem, which is challenging to solve with conventional numerical techniques. To address this issue, we propose the application of a physics-informed neural network (PINN) to reconstruct physically consistent wave fields between two elevation time series measured at distinct locations within a numerical wave tank. Our method ensures this physical consistency by integrating residuals of the hydrodynamic nonlinear Schrödinger equation (NLSE) into the PINN’s loss function. We first showcase a data assimilation task by employing constant NLSE coefficients predetermined from spectral wave properties. However, due to the relatively short duration of these measurements and their possible deviation from the narrow-band assumptions inherent in the NLSE, using constant coefficients occasionally leads to poor reconstructions. To enhance this reconstruction quality, we introduce the base variables of frequency and wavenumber, from which the NLSE coefficients are determined, as additional neural network parameters that are fine tuned during PINN training. Overall, the results demonstrate the potential for real-world applications of the PINN method and represent a step toward improving the initialization of deterministic wave prediction methods.

A Distance Transformation Deep Forest Framework With Hybrid-Feature Fusion for CXR Image Classification.

Detecting pneumonia, especially coronavirus disease 2019 (COVID-19), from chest X-ray (CXR) images is one of the most effective ways for disease diagnosis and patient triage. The application of deep neural networks (DNNs) for CXR image classification is limited due to the small sample size of the well-curated data. To tackle this problem, this article proposes a distance transformation-based deep forest framework with hybrid-feature fusion (DTDF-HFF) for accurate CXR image classification. In our proposed method, hybrid features of CXR images are extracted in two ways: hand-crafted feature extraction and multigrained scanning. Different types of features are fed into different classifiers in the same layer of the deep forest (DF), and the prediction vector obtained at each layer is transformed to form distance vector based on a self-adaptive scheme. The distance vectors obtained by different classifiers are fused and concatenated with the original features, then input into the corresponding classifier at the next layer. The cascade grows until DTDF-HFF can no longer gain benefits from the new layer. We compare the proposed method with other methods on the public CXR datasets, and the experimental results show that the proposed method can achieve state-of-the art (SOTA) performance. The code will be made publicly available at https://github.com/hongqq/DTDF-HFF.

Anomaly Detection in Fractal Time Series with LSTM Autoencoders

This study explores the application of neural networks for anomaly detection in time series data exhibiting fractal properties, with a particular focus on changes in the Hurst exponent. The objective is to investigate whether changes in fractal properties can be identified by transitioning from the analysis of the original time series to the analysis of the sequence of Hurst exponent estimates. To this end, we employ an LSTM autoencoder neural network, demonstrating its effectiveness in detecting anomalies within synthetic fractal time series and real EEG signals by identifying deviations in the sequence of estimates. Whittle’s method was utilized for the precise estimation of the Hurst exponent, thereby enhancing the model’s ability to differentiate between normal and anomalous data. The findings underscore the potential of machine learning techniques for robust anomaly detection in complex datasets.

Variable selection of nonparametric spatial autoregressive models via deep learning

With the development of deep learning techniques, the application of neural networks to statistical inference has dramatically increased in popularity. In this paper, we extend the deep neural network-based variable selection method to nonparametric spatial autoregressive models. Our approach incorporates feature selection and parameter learning by introducing Lasso penalties in a residual network structure with spatial effects. We transform the problem into a constrained optimization task, where optimizing an objective function with constraints. Without specifying sparsity, we are also able to obtain a specific set of selected variables. The performance of the method with finite samples is demonstrated through an extensive Monte Carlo simulation study. Finally, we apply the method to California housing price data, further validating its superiority in terms of variable selection and predictive performance.

MO7-4 Artificial neural network application in NSCLC overall staging prediction

MO7-4 Artificial neural network application in NSCLC overall staging prediction

An example of the application of neural networks of a simple architecture to unfocused well electrometry probes

An effective method of finding stable solutions of inverse problems of electric and induction logging along the well is proposed, which allows avoiding the influence of the resistance values of the neighboring formations on the determination of the geoelectrical parameters of the object under study. A highly efficient method was proposed for solving such an unstable inverse problem. This method is based on the application of a neural network with inverse error propagation of a simple architecture. Namely three-layer. The mathematical statement of the problem is given, both the topology of the neural network and all its parameters are described in detail. In the course of the numerical experiment, they were selected as optimal. The process of building a base for training a neural network is described in detail. Namely, how each of the examples of the learning base is built by solving a direct problem. With this cut parameter, the training for each example is chosen arbitrarily, which guarantees a comprehensive range for training the neural network. The number of examples in the training base is one hundred thousand examples. As the activation function, the sigmoid is chosen due to the fact that it is differentiable everywhere. The results of testing the written program are given. The learning rate was estimated to obtain the required small error. It is shown that this approach is stably convergent. For testing, the parameters of the layers of the cut, which are inherent to the geophysical parameters of the cuts of the Dnipro-Donetsk depression, were chosen. A complex of lateral logging sounding was chosen as the electrical logging equipment. Four-probe low-frequency induction logging equipment was chosen as induction logging equipment. Examples for induction and electrical logging are given separately. The obtained results are analyzed in detail. Ways of further improvement of the obtained neural network and its use for other problems of geophysics are given.

Application of artificial neural network for peak load forecasting in 150 kV Semarang power system

Accurate load forecasting is essential for reliable and efficient operation of power systems. Traditional forecasting methods often struggle with capturing complex nonlinear patterns in load data. Artificial neural networks (ANNs) have emerged as a promising alternative due to their ability to learn complex relationships from historical data (Syed et al. in IEEEA 9:54992–55008, 2021. https://doi.org/10.1109/ACCESS.2021.3071654). This study investigates the potential of ANNs for short-term peak load forecasting in a 150 kV power system in Semarang, Indonesia. The study examines the impact of different input variables, including historical peak load, minimum load, population, and energy production, on forecasting accuracy. Several ANN architectures are trained and evaluated using mean absolute percentage error (MAPE) and mean squared error (MSE) metrics as reported by Demuth and De Jesús (neural network design). The results indicate that ANNs can achieve high accuracy in predicting peak load, with MAPE values below 10%. The study also demonstrates the importance of carefully selecting input variables and training parameters for optimal model performance. The findings highlight the potential of ANNs for improving load forecasting accuracy in power systems, contributing to enhanced grid reliability and operational efficiency. The findings of this study contribute to a deeper understanding of the application of ANNs in power system load forecasting. They demonstrate the potential of ANNs to achieve high accuracy and provide valuable insights into the factors influencing model performance. The findings are relevant for power system operators, researchers, and policymakers working to improve grid reliability and efficiency as reported by Prabha Kundur and Malik (Power System Stability and Control, McGraw-Hill Education, New York, 2022. https://www.accessengineeringlibrary.com/content/book/9781260473544).

Application of artificial intelligence technologies at substantiation of effective control algorithms for the electrical engineering complex of urban electric transport traction electrical equipment

Background. Studies on the current state and development trends of urban ground public electric transportation in Russia highlight the urgent need for innovative technologies. These innovations should focus on designing and operating new types of rolling stock, traction electrical equipment, and promising types of electric traction. At the same time, special attention should be paid to building autonomous control systems for electric transportation using artificial intelligence technologies. Aim. This study aims to explore the application of neural networks to develop algorithms for effectively controlling the electrical engineering complex of traction electrical equipment in urban ground rail electric transport. Materials and Methods. The research utilized data from studies on the traction electrical equipment modes of rolling stock. These studies were conducted through both computer simulations and field experiments under real operating conditions of urban electric transport using different control algorithms. By applying probability theory and mathematical statistics, the analysis identified the correlations between operational and energy parameters of rolling stock movement and the operational mode of its traction electrical equipment. Results. The identified correlation dependencies informed the design of an effective network architecture, including its size and complexity, as well as the composition of their training samples. This led to the development of an original, simplified algorithm for determining effective control parameters for the electrical complex of traction electrical equipment during the movement of a vehicle on a given section of track. Conclusion. The research concluded that using “simple” neural networks for calculating the parameters of effective control of traction electrical equipment operation modes in urban electric transport provides higher speed and sufficient accuracy compared to complex neural network models. These results are valuable for developers of intelligent control systems for streetcar transportation.

Time Series Forecasting of Emission Trends Using Recurrent Neural Networks

This paper explores the application of Recurrent Neural Networks (RNNs) for forecasting emission trends, a critical aspect of addressing climate change and formulating effective environmental policies. Traditional forecasting methods, such as Autoregressive Integrated Moving Average (ARIMA) and Exponential Smoothing, often fail to capture the complex nonlinear relationships and temporal dependencies inherent in emission data. In contrast, RNNs, particularly Long Short-Term Memory (LSTM) networks, are designed to recognize patterns in sequential data, making them well-suited for time series forecasting tasks. This study employs a comprehensive methodology that includes data collection from reputable sources, feature selection, RNN model design, and rigorous evaluation using various performance metrics. The results indicate that RNNs significantly outperform traditional forecasting techniques in terms of accuracy, providing valuable insights into future emission trajectories. The findings underscore the potential of RNNs as powerful tools for policymakers and researchers, facilitating more informed decision-making in the fight against climate change.

X-ray Bone Image Processing Based on Improved Densenet

The application of convolutional neural network has been gradually introduced in the field of X-ray bone images. At present, there is less research on methods to automatically detect abnormal parts of the skeleton. The method improves on the Densenet network by adjusting the network structure, adding a convolutional block attention module (CBAM) attention mechanism to the original Densenlayer, fusing spatial attention and channel attention to suppress unnecessary features and strengthen the network‘s capability to extract image features, and optimizing the Transition block by fusing two pooling strategies, average and maximum, to increase the model’s anti-interference capability. The data collected after the experiment show that the improved Densenet has increased accuracy in the detection of skeletal abnormalities at all sites compared with the traditional network. The average accuracy is 1–5% higher than the benchmark method, the highest elbow accuracy reached 77.62%, the lowest hand accuracy also reached 64.28% and the area under the receiver operating characteristic curve is increased by 3–7%, the highest reached 80.83%.

Attributes of residual neural networks for modeling fractional differential equations

This paper offers a pioneering in-depth exploration of applying residual neural networks to approximate Erdélyi-Kober fractional derivatives and establishes a parameter upper bound for these networks. We validate this method using the variational iteration formula to obtain the exact solution of a differential equation. The resulting structure from the variational iteration method serves as a basis for showcasing how residual neural networks can effectively estimate these equations. Furthermore, we provide illustrative examples to elucidate the application of residual neural networks in solving equations involving Erdélyi-Kober fractional derivatives.

Ensemble Learning-Based Fuzzy Aggregation Functions and Their Application in TSK Neural Networks

AbstractTakagi–Sugeno–Kang fuzzy neural networks (TSKFNN) are powerful tools to model vague or imprecise information. Regression is one of the most important tasks commonly tackled by supervised learning techniques. TSKFNNs are considered suitable models to deal with regression problems on account of their simplicity and flexibility. Aggregation methods play an important role in combining various fuzzy rules from a TSKFNN rule base to obtain a model prediction. However, many current aggregation methods rely on expert experience and human knowledge, which may be hard to acquire and could bring human bias. This paper proposes data-driven aggregation functions for rules aggregation based on ensemble learning, namely AdaBoost and bagging, which can achieve superior generalizability in testing compared with the existing rule aggregation methods. Furthermore, they can also provide insights into the importance of each rule in the model’s decision making, thus, helping to improve the interpretability of the model. Extensive experiments on 11 commonly used benchmark datasets with various sizes and dimensionalities validated the superiority of the proposed ensemble learning-based fuzzy aggregation functions compared with existing state-of-the-art TSKFNNs.